[go: up one dir, main page]

WO2023169101A1 - Procédé de communication et appareil de communication - Google Patents

Procédé de communication et appareil de communication Download PDF

Info

Publication number
WO2023169101A1
WO2023169101A1 PCT/CN2023/074121 CN2023074121W WO2023169101A1 WO 2023169101 A1 WO2023169101 A1 WO 2023169101A1 CN 2023074121 W CN2023074121 W CN 2023074121W WO 2023169101 A1 WO2023169101 A1 WO 2023169101A1
Authority
WO
WIPO (PCT)
Prior art keywords
network element
network
analysis
analysis result
model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2023/074121
Other languages
English (en)
Chinese (zh)
Inventor
李卓明
时书锋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Publication of WO2023169101A1 publication Critical patent/WO2023169101A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/22—Traffic simulation tools or models
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition

Definitions

  • the embodiments of the present application relate to the field of communication, and more specifically, to a communication method and a communication device.
  • Data analysis network elements can provide intelligent analysis services to adjust the network and optimize business experience.
  • the data analysis network element can collect network data from multiple sources and dimensions, train a model based on the collected network data, and output analysis results or prediction results to the business processing network element based on the trained model, so that the business processing network element can analyze the network Make adjustments.
  • the analysis results or prediction results provided by the data analysis network element to the service processing network element may be inaccurate, thus affecting the stability of network operation.
  • the present application provides a communication method and communication device, which helps to improve the accuracy of analysis results or prediction results provided by data analysis network elements, thereby improving the stability of network operation.
  • a communication method is provided.
  • the method can be executed by a data analysis network element or by a module or unit in the data analysis network element.
  • a data analysis network element For convenience of description, it will be collectively referred to as the data analysis network element below.
  • the method includes: the data analysis network element obtains the first data of the network; the data analysis network element obtains the first analysis result according to the first data and the first model; the data analysis network element sends the data to the business processing network element.
  • the first analysis result is used by the business processing network element to adjust the network; the data analysis network element obtains the adjusted second data of the network; the data analysis The network element obtains a second analysis result based on the second data, where the second analysis result includes adjusted information on key performance indicators of the network.
  • the first analysis result and/or the second analysis result may be a numerical value or a set of numerical values, without limitation.
  • the key performance indicator information may be one or more of the performance indicator information included in the second analysis result.
  • the data analysis network element provides the first analysis result and/or the second analysis result to the business processing network element when specific conditions are met or regularly.
  • the analysis result refers to the current acquisition by the business processing network element. A value or a set of values.
  • the data analysis network element can analyze the first data of the network, obtain the first analysis result for adjusting the network, obtain the second data of the network after adjusting the network according to the first analysis result, and The second data is analyzed to obtain a second analysis result that can be used to evaluate the correctness of the first analysis result.
  • the correctness of the first analysis result can reflect the effectiveness of the first model used to obtain the first analysis result, which helps the data analysis network element to promptly correct the first model when the first model fails, thereby helping To improve the analysis provided by data analysis network elements to improve the accuracy of analysis results or prediction results, thereby improving the stability of network operations.
  • the method further includes: the data analysis network element determines the confidence of the first analysis result based on the information of the key performance indicators; the data analysis network element Determine whether the first model is valid based on the confidence level of the first analysis result.
  • the data analysis network element can determine the confidence level of the first analysis result and determine whether the first model is valid based on the obtained confidence level. This helps the data analysis network element timely analyze the first model when the first model fails.
  • the model is modified to improve the stability of network operation.
  • the data analysis network element can determine whether the first model is valid without knowing the business logic of the network, which can improve the applicability of the data analysis network element.
  • the data analysis network element determines whether the first model is valid based on the confidence of the first analysis result, including: if If the confidence level of the first analysis result is untrustworthy or the number of times within the preset time period that the confidence level of the first analysis result is untrustworthy exceeds the first threshold, the data analysis network element determines that the first model is invalid. ; Or, if the confidence level of the first analysis result is credible, the data analysis network element determines that the first model is valid.
  • the validity or invalidity of the first model is determined based on the credibility or disbelief of the confidence level of the first analysis result. Failure is a more appropriate way to determine it.
  • the method further includes: the data analysis network element sending the confidence of the first analysis result to the business processing network element. .
  • the data analysis network element can provide the confidence level of the first analysis result to the business processing network element, so that the business processing network element uses the currently acquired data based on the confidence level.
  • First analysis results For example, if the confidence level of the first analysis result is the first value, the business processing network element adjusts the network according to the first adjustment range; or, if the confidence level of the first analysis result is the second value, the business processing network element The network is adjusted according to the second adjustment range; or, if the confidence level of the first analysis result is the third value, the service processing network element discards the currently obtained first analysis result.
  • the first value and the second value are in the credible range, and the third value is in the untrustworthy range. When the first value is lower than the second value, the first adjustment range is smaller than the second adjustment range. This helps improve the accuracy of network adjustments.
  • the method further includes: the data analysis network element receives a first message from the service processing network element, and the first The message is used to request subscription to the first analysis result, and the first message is used to instruct the data analysis network element to obtain the second analysis result.
  • the data analysis network element can obtain the first analysis result and monitor the second analysis result at the same time, so that the data analysis network element can evaluate the correctness of the first analysis result according to the instruction of the service processing network element.
  • the second analysis result determines whether the first model is valid, which helps the data analysis network element promptly correct the first model when the first model fails, thereby improving the stability of network operation.
  • the first message carries first information, and the first information is used to determine the confidence level.
  • the first information includes the confidence level and the range of the key performance indicator corresponding to the confidence level.
  • the range of key performance indicators can be a single value.
  • the confidence level and the range of the key performance indicator corresponding to the confidence level satisfy: if the key performance indicator is less than or equal to the third threshold, the confidence level of the first analysis result is untrustworthy; or, if the key performance indicator is greater than the third threshold and is less than the fourth threshold, then the first analysis result is credible and the confidence level is the first value; or, if the key performance indicator is greater than or equal to the fourth threshold, the first analysis result is credible and the confidence level is the second value; where, The first value is lower than the second value.
  • the confidence level and the range of the key performance indicator corresponding to the confidence level satisfy: if the key performance indicator is less than the third threshold, the confidence level of the first analysis result is untrustworthy; or, if the key performance indicator is greater than or equal to the third threshold , then the confidence level of the first analysis result is credible.
  • the values of the third threshold and the fourth threshold can be set according to specific circumstances.
  • the method further includes: the data analysis network element sending the second analysis result to the service processing network element;
  • the data analysis network element receives second information from the service processing unit, the second information is used to indicate whether the first analysis result is correct, and the second information is determined based on the second analysis result;
  • the data analysis network element determines whether the first model is valid based on the second information.
  • the second information may also be used to indicate whether to accept the first analysis result.
  • the business processing network element can evaluate the correctness of the first analysis result based on the second analysis result and feed it back to the data analysis network element, so that the data analysis network element can evaluate the correctness of the first analysis result based on the second analysis result. Determining whether the first model is valid will help the data analysis network element promptly correct the first model when the first model fails, thereby improving the stability of network operation.
  • the data analysis network element can determine whether the first model is valid without knowing the business logic of the network, which can improve the applicability of the data analysis network element.
  • the evaluation of the correctness of the first analysis result can be understood as whether the first analysis result is correct.
  • the method further includes: the data analysis network element sending a second message to the service processing network element, the second message Used to instruct the service processing network element to provide the second information to the data analysis network element.
  • the data analysis network element can instruct the business processing network element to provide a correctness evaluation of the first analysis result, so that the business processing network element receives the instruction and then subscribes to the data analysis network element for the second analysis result to facilitate business processing.
  • the network element evaluates the correctness of the first analysis result based on the second analysis result.
  • the data analysis network element determines whether the first model is valid based on the second information, including: the data analysis network element Determine whether the first analysis result is correct according to the second information; if the first analysis result is wrong or the number of times the first analysis result is wrong within a preset time period exceeds a second threshold, the data analysis network The data analysis network element determines that the first model is invalid; or, if the first analysis result is correct, the data analysis network element determines that the first model is valid.
  • the correctness or error of the first analysis result can well correspond to the validity or failure of the first model, it is a more appropriate determination method to determine whether the first model is valid or invalid based on whether the first analysis result is correct or incorrect.
  • the method further includes: the data analysis network element retrains the first model Or update the first model.
  • the data analysis network element is an analytics logical function (AnLF), and the method further includes: the data analysis The network element obtains the first model from a model training logical function (MTLF).
  • AnLF and MTLF may be independent network elements, or may be functional modules within the data analysis network element, and are not specifically limited in this application.
  • the data analysis network element obtains a second analysis result according to the second data, including: the data analysis network element obtains a second analysis result according to the second data.
  • the second data and the second model obtain the second analysis result.
  • the data analysis network element may obtain the second model from MTLF.
  • the method further includes: the data analysis network element determines that the first model or the second model is invalid.
  • the data analysis network element determines that the first model or the second model is invalid, including: if the third model of another network is If the confidence level of the third analysis result is credible, then the data analysis network element determines that the first model is invalid, wherein the third analysis result is obtained through the third model, and the confidence level of the third analysis result is determined based on the fourth analysis result, which is obtained through the second model; or, if the confidence level of the third analysis result for another network is credible, the data analysis network element determines The second model fails, wherein the third analysis result is obtained through the first model, the confidence level of the third analysis result is determined based on the fifth analysis result, and the fifth analysis result is Obtained through the fourth model.
  • the first analysis result is the network performance analysis result of the network
  • the second analysis result is the service experience analysis result of the network
  • the first analysis result is the network performance analysis result of the network.
  • the user data congestion level analysis result, the second analysis result is the service experience analysis result of the network; or the first analysis result is the redundant transmission experience analysis result of the network, and the second analysis result is The data network performance analysis result of the network; or the first analysis result is the load analysis result of the user data network function of the network, and the second analysis result is the user data congestion analysis result of the network; here No more listing them one by one.
  • the first analysis result and the second analysis result are not specifically limited.
  • the information on key performance indicators is information on one or more key performance indicators included in the second analysis result.
  • the first analysis result is the predicted value of the number of terminals residing in the network, and the key performance indicator information includes the mean opinion score (MOS) of the network; or, The first analysis result is the predicted value of the average service rate and the predicted value of the maximum service rate of the network, and the information about the key performance indicators includes the network function load of the network; or, the first analysis result is The predicted value of user data congestion level of the network, and the information of the key performance indicators includes the MOS of the network; or, the first analysis result is the redundant transmission experience analysis of the network, and the key performance indicators
  • the information includes the maximum packet delay or average packet loss rate in the data network performance statistics of the network; or the first analysis result is the load prediction value of the user data network function of the network, the key performance indicator
  • the information includes the user data congestion level of the network; this will not be listed one by one here. In this application, there are no specific limitations on the information of the first analysis result, the second analysis result, and the key performance indicators.
  • the network is the entire public land mobile network (public land mobile network, PLMN); Alternatively, the network is a wireless network within one to multiple tracking areas (TA); or the network is one to multiple network slices; or the network is one to multiple data networks (Data Network, DN); or, one or more network elements, including policy control network elements, session management network elements, access and mobility management network elements, network slice selection network elements, user plane network elements, or application function network elements.
  • PLMN public land mobile network
  • TA tracking areas
  • Data Network Data Network
  • DN data networks
  • network elements including policy control network elements, session management network elements, access and mobility management network elements, network slice selection network elements, user plane network elements, or application function network elements.
  • adjusting the network includes at least one of the following behaviors: determining or changing the configuration parameters of one or more network elements, determining or changing the parameter settings of one or more network slices or DNs, determining or changing Passing parameters contained in messages between one or more network elements, determining or changing the context parameters of one or more session communications, determining or changing the parameters of one or more terminal contexts, determining or changing the processing of one or more session communications As a result, the processing results of one or more terminals are determined or changed.
  • no specific limitation is made.
  • the data analysis network element includes at least one of the following: network data analytics function (NWDAF), AnLF, management data analytics system (MDAS), or digital twin network; and /Or, the service processing network element includes at least one of the following: a policy control network element, a session management network element, an access and mobility management network element, a network slice selection network element, a user plane network element, or an application function network element.
  • NWDAAF network data analytics function
  • MDAS management data analytics system
  • digital twin network digital twin network
  • the service processing network element includes at least one of the following: a policy control network element, a session management network element, an access and mobility management network element, a network slice selection network element, a user plane network element, or an application function network element.
  • a communication method is provided.
  • the method can be executed by a service processing network element or by a module or unit in the service processing network element.
  • a service processing network element For the convenience of description, it will be collectively referred to as the service processing network element below.
  • the method includes: the service processing network element obtains the first analysis result obtained by the data analysis network element according to the first model; the service processing network element adjusts the network according to the first analysis result; the service processing network element provides The data analysis network element sends a request message, and the request message is used to request a subscription to the second analysis result of the network; the business processing network element obtains the second analysis result from the data analysis network element, so The second analysis result includes adjusted information on key performance indicators of the network; the service processing network element determines second information based on the second analysis result, and the second information is used to indicate the first analysis Whether the result is correct; the business processing network element sends the second information to the data analysis network element, and the second information is used by the data analysis network element to determine whether the first model is valid.
  • the second information may also be used to indicate whether to accept the first analysis result.
  • the business processing network element can evaluate the correctness of the first analysis result based on the second analysis result, and feed it back to the data analysis network element, so that the data analysis network element can evaluate the correctness of the first analysis result based on the second analysis result. Determining whether the first model is valid will help the data analysis network element promptly correct the first model when the first model fails, thereby helping to improve the accuracy of the analysis results or prediction results provided by the data analysis network element, thereby Improve the stability of network operation.
  • the evaluation of the correctness of the first analysis result can be understood as whether the first analysis result is correct.
  • the service processing network element determines the second information according to the second analysis result, including: the service processing network element determines the second information according to the second analysis result. The confidence level of the first analysis result; the service processing network element determines the second information based on the confidence level of the first analysis result.
  • the service processing network element determines the second information according to the second analysis result, including: the service processing network element determines all the information included in the second analysis result.
  • the information on the key performance indicators is compared with the information on the key performance indicators obtained previously; if the information on the key performance indicators included in the second analysis result is deteriorated relative to the information on the key performance indicators obtained previously, then the business The processing network element determines that the first analysis result is wrong; or, if the information on the key performance indicators included in the second analysis result is optimized relative to the information on the key performance indicators obtained previously, the business processing network element determines The first analysis result is correct.
  • the method further includes: the service processing network element receiving a second message from the data analysis network element, and the second The message is used to instruct the service processing network element to provide the second information to the data analysis network element.
  • the data analysis network element can instruct the business processing network element to provide a correctness evaluation of the first analysis result, so that the business processing network element receives the instruction and then subscribes to the data analysis network element for the second analysis result to facilitate business processing.
  • the network element evaluates the correctness of the first analysis result based on the second analysis result.
  • the method further includes: the business processing network element determines to subscribe to the data analysis network element based on the information of the key performance indicators. The second analysis result.
  • a communication method is provided.
  • the method can be executed by a service processing network element or by a module or unit in the service processing network element.
  • a service processing network element For convenience of description, it will be collectively referred to as the service processing network element below.
  • the method includes: the service processing network element sends a first message to the data analysis network element, the first message is used to request a first analysis result of the subscription network, the first analysis result is used to adjust the network, and the The first message is also used to instruct the data analysis network element to obtain a second analysis result of the network, where the second analysis result includes the adjusted information of key performance indicators of the network; the business processing network The network element receives the first analysis result from the data analysis network element; the business processing network element adjusts the network according to the first analysis result.
  • the data analysis network element can obtain the first analysis result and monitor the second analysis result at the same time, so that the data analysis network element can evaluate the correctness of the first analysis result according to the instruction of the service processing network element.
  • the second analysis result determines whether the first model is valid, which helps the data analysis network element to promptly correct the first model when the first model fails, thereby helping to improve the analysis results or predictions provided by the data analysis network element.
  • the accuracy of the results thereby improves the stability of network operations.
  • the method further includes: the service processing network element determines to instruct the data analysis network element to obtain the second analysis result based on the information of the key performance indicator.
  • the first message carries first information, and the first information is used to determine the confidence of the first analysis result.
  • the first information includes the confidence level and the range of the key performance indicator corresponding to the confidence level.
  • the range of key performance indicators can be a single value.
  • the method further includes: the service processing network element receiving the confidence from the data analysis network element; The processing network element adjusts the network again or discards the first analysis result currently obtained by the service processing network element according to the confidence level.
  • the business processing network element adjusts the network according to the first adjustment range; or, if the confidence level of the first analysis result is the second value, the business processing network element The network is adjusted according to the second adjustment range; or, if the confidence level of the first analysis result is the third value, the service processing network element discards the currently obtained first analysis result.
  • the first value and the second value are in the credible range, and the third value is in the untrustworthy range.
  • the first adjustment range is smaller than the second adjustment range.
  • a fourth aspect provides a communication device, which is used to perform the method provided by any of the above aspects or its implementation.
  • the device may include a single unit for executing the method provided by any one of the above aspects or its implementation.
  • elements and/or modules such as processing units and/or communication units.
  • the device is a data analysis network element or a service processing network element.
  • the communication unit may be a transceiver, or an input/output interface, or a communication interface; the processing unit may be at least one processor.
  • the transceiver is a transceiver circuit.
  • the input/output interface is an input/output circuit.
  • the device is a chip, chip system or circuit used in a data analysis network element or a business processing network element.
  • the communication unit may be an input/output interface, interface circuit, output circuit, input circuit on the chip, chip system or circuit. Circuits, pins or related circuits, etc.; the processing unit may be at least one processor, processing circuit or logic circuit, etc.
  • a communication device which device includes: a memory for storing a program; and at least one processor for executing the computer program or instructions stored in the memory to execute any of the above aspects or the implementation provided by it. method.
  • the device is a data analysis network element or a service processing network element.
  • the device is a chip, chip system or circuit used in a data analysis network element or a business processing network element.
  • a communication device in a sixth aspect, includes: at least one processor and a communication interface.
  • the at least one processor is used to obtain computer programs or instructions stored in a memory through the communication interface to execute any one of the above aspects or The methods provided for its implementation.
  • the communication interface can be implemented by hardware or software.
  • the device further includes the memory.
  • a seventh aspect provides a processor for executing the methods provided in the above aspects.
  • processor output, reception, input and other operations can be understood as processor output, reception, input and other operations.
  • transmitting and receiving operations performed by the radio frequency circuit and the antenna, which is not limited in this application.
  • a computer-readable storage medium stores program code for device execution.
  • the program code includes a method for executing any of the above aspects or the method provided by its implementation.
  • a computer program product containing instructions is provided.
  • the computer program product When the computer program product is run on a computer, it causes the computer to execute the method provided by any of the above aspects or its implementation.
  • a chip in a tenth aspect, includes a processor and a communication interface.
  • the processor reads instructions stored in the memory through the communication interface and executes the method provided by any of the above aspects or its implementation.
  • the communication interface can be implemented by hardware or software.
  • the chip also includes a memory, in which computer programs or instructions are stored.
  • the processor is used to execute the computer programs or instructions stored in the memory.
  • the processor is used to execute Methods provided by any of the above aspects or their implementations.
  • An eleventh aspect provides a communication system, including the above data analysis network element or service processing network element, wherein the data analysis network element is used to perform the method described in the first aspect or any implementation thereof,
  • the service processing network element is used to receive the analysis results sent by the data analysis network element, and adjust the network according to the analysis results.
  • Figure 1 is a schematic diagram of a network architecture to which the technical solution of this application can be applied.
  • Figure 2 is an example of NWDAF.
  • Figure 3 is a schematic diagram of network adjustment based on NWDAF data analysis.
  • Figure 4 is a schematic diagram of a communication method 400 provided by this application.
  • Figure 5 is an example of the communication method provided by this application.
  • Figure 6 is another example of the communication method provided by this application.
  • Figure 7 is another example of the communication method provided by this application.
  • Figure 8 is a schematic structural diagram of a device provided by an embodiment of the present application.
  • Figure 9 is another structural schematic diagram of a device provided by an embodiment of the present application.
  • for indicating” or “instructing” may include direct indicating and indirect indicating, or “for indicating” or “instructing” may indicate explicitly and/or implicitly.
  • indicating information I when describing certain information as indicating information I, it may include that the information directly indicates I or indirectly indicates I, but it does not mean that the information must contain I.
  • an implicit indication may be based on the location and/or resources used for transmission; an explicit indication may be based on one or more parameters, and/or one or more indexes, and/or one or more bits it represents. model.
  • the first, second, third, fourth and various numerical numbers are only for convenience of description and are not used to limit the scope of the embodiments of the present application. For example, distinguish different fields, different information, etc.
  • Pre-definition can be achieved by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in equipment (for example, including data analysis network elements or business processing network elements).
  • This application describes its specific implementation. No restrictions. Among them, “saving” may refer to saving in one or more memories.
  • the type of memory can be any form of storage medium, and this application is not limited thereto.
  • the "protocol” involved in the embodiments of this application may refer to standard protocols in the communication field, and may include, for example, LTE protocols, NR protocols, and related protocols applied in future communication systems. This application does not limit this.
  • At least one means one or more, and “plurality” means two or more.
  • “And/or” describes the association of associated objects, indicating that there can be three relationships, for example, A and/or B, which can mean: A exists alone, A and B exist simultaneously, and B exists alone, where A, B can be singular or plural.
  • the character “/” generally indicates that the related objects are in an “or” relationship.
  • “At least one of the following” or similar expressions refers to this Any combination of these items, including any combination of single items (items) or plural items (items).
  • At least one of a, b and c can mean: a, or, b, or, c, or, a and b, or, a and c, or, b and c, or, a , b and c.
  • a, b and c can be single or multiple respectively.
  • the technical solutions provided by this application can be applied to various communication systems, such as fifth generation (5th generation, 5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division Duplex (frequency division duplex, FDD) system, LTE time division duplex (TDD) system, etc.
  • the technical solution provided by this application can also be applied to future communication systems, such as the sixth generation mobile communication system.
  • the technical solution provided by this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine type Communication (machine type communication, MTC) and Internet of things (Internet of things, IoT) communication systems or other communication systems.
  • D2D device-to-device
  • V2X vehicle-to-everything
  • M2M machine-to-machine
  • MTC machine type Communication
  • Internet of things Internet of things
  • Figure 1 shows a schematic diagram of a network architecture.
  • the network architecture takes the 5G system (the 5th generation system, 5GS) as an example.
  • the network architecture includes access and mobility management network elements, session management function network elements, policy control network elements, slice access control network elements, network repository function (NRF) network elements, unified data management (unified data management (UDM) network element, network exposure function (NEF) network element, application function network element, data analysis network element, and operation management and maintenance (operation administration and maintenance, OAM) network element.
  • unified data management unified data management
  • NEF network exposure function
  • OAM operation administration and maintenance
  • Access and mobility management network elements are mainly used for terminal attachment, mobility management, and tracking area update processes in mobile networks.
  • Access and management network elements terminate non-access stratum (NAS) messages and complete registration. Management, connection management and reachability management, allocation of tracking area list (track area list, TA list) and mobility management, etc., and transparent routing of session management (session management, SM) messages to session management network elements.
  • the access and mobility management network element can be the access and mobility management function (AMF).
  • Session management network elements are mainly used for session management in mobile networks, such as session establishment, modification, and release. Specific functions include assigning Internet Protocol (IP) addresses to terminals and selecting user plane network elements that provide packet forwarding functions.
  • IP Internet Protocol
  • the session management network element can be a session management function (SMF).
  • Policy control network elements are mainly used for user subscription data management, policy control, billing policy control, quality of service (QoS) control, etc.
  • the policy control network element can be the policy control function (PCF).
  • policy control network elements may also be divided into multiple entities according to levels or functions, such as global PCF and PCF within slices, or session management PCF (session management PCF, SM-PCF) and access Management PCF (access management PCF, AM-PCF), etc.
  • levels or functions such as global PCF and PCF within slices, or session management PCF (session management PCF, SM-PCF) and access Management PCF (access management PCF, AM-PCF), etc.
  • Network slice selection network elements are mainly used to select appropriate network slices for terminal services.
  • network slice selection network elements can be network slice selection functions (NSSF).
  • Network repository network elements are mainly used to store network functional entities and description information of the services they provide.
  • the network repository network element can be a network repository function (NRF).
  • the unified data management network element is mainly responsible for managing the contract information of the terminal.
  • the unified data management network element can be unified data management (UDM).
  • Network opening network elements are mainly used to securely open services and capabilities provided by 3GPP network functions to the outside world.
  • network exposure network elements can be network exposure functions (NEF).
  • Application function network elements are mainly used to provide services to the 3GPP network, such as interacting with PCF for policy control, etc.
  • the application function network element can be an application function (AF).
  • Operation administration and maintenance (OAM) network elements are mainly used to complete the analysis, prediction, planning and configuration of the network and its services, as well as to complete daily testing and fault management of the network and its services. Operational activities, etc.
  • Data analysis network elements are mainly used to provide intelligent analysis services to adjust the network and optimize business experience.
  • the data analysis network element can collect network data from multiple sources and multiple dimensions; perform correlation analysis on the collected network data to output analysis results, or train a model based on the collected network data, and output analysis results based on the trained model or Make predictions.
  • the data analysis network element can collect network data from each network function (NF) (such as AMF, SMF, or PCF, etc.), or from AF through NEF, or directly from AF, or from OAM.
  • NF network function
  • the data analysis network element can be the network data analytics function (NWDAF).
  • NWDAF network data analytics function
  • NWDAF is divided into two parts: model training logical function (MTLF) and analytical reasoning logical function (analytics logical function, AnLF).
  • the data analysis network element can be an independent network element, or it can be co-located with other network elements, for example, it can be a data analysis module in other network elements.
  • Figure 2 is an example of NWDAF.
  • NWDAF includes MTLF and AnLF.
  • NWDAF-MTLF the MTLF included in NWDAF is recorded as NWDAF-MTLF
  • NWDAF-AnLF the AnLF included in NWDAF is recorded as NWDAF-AnLF.
  • NWDAF-MTLF is used to train the model based on the collected network data and to one or more NWDAF-AnLF (such as NWDAF-AnLF#1, NWDAF-AnLF#2 and NWDAF-AnLF# in Figure 2) after the model training is completed. 3) Distribute the trained model. NWDAF-AnLF is used to use the obtained model to provide analysis and inference services to business processing network elements that request analysis services.
  • Figure 3 is a schematic diagram of network adjustment based on NWDAF data analysis.
  • NWDAF-MTLF collects current network data and/or historical network data from the network; NWDAF-MTLF trains the model based on the collected network data and distributes the trained model to NWDAF-AnLF, or NWDAF- MTLF updates the model based on the collected network data and distributes the updated model to NWDAF-AnLF; NWDAF-AnLF collects current network data from the network based on the request of the business processing network element and uses the model from NWDAF-MTLF to collect Perform inference analysis on the received network data; then NWDAF-AnLF provides analysis results to the service processing network element.
  • the analysis results can be statistical analysis results and/or predictive analysis results; the service processing network element performs service processing and performs network adjustment actions based on the analysis results. .
  • NWDAF may have both MTLF and AnLF as shown in Figures 2 and 3, or it may have MTLF but not AnLF, or it may have AnLF but not MTLF.
  • MTLF can be an independent network element, or it can be a functional unit in a network element (such as NWDAF); similarly, AnLF can be an independent network element, or it can be a function in a network element (such as NWDAF). unit, this application is not limited.
  • the data analysis network element can also be a network management-related system such as a management data analytics system (MDAS), or it can also be a related functional network element applied in a digital twin network (digital twin network).
  • MDAS management data analytics system
  • digital twin network digital twin network
  • the network architecture may also include some or all of the following devices or network elements.
  • the user plane network element is mainly responsible for processing user messages, such as forwarding, accounting, legal interception, etc.
  • the user plane network element can also be called a protocol data unit (PDU) session anchor (PDU session anchor, PSA).
  • PDU session anchor PDU session anchor
  • PSA protocol data unit
  • the user plane network element can be the user plane function (UPF).
  • UPF can communicate directly with NWDAF through a service-like interface, or it can communicate with NWDAF through other means, such as through SMF or a private interface or internal interface with NWDAF.
  • the terminal is a device with wireless transceiver functions that can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on water (such as ships, etc.); it can also be deployed in the air (such as airplanes, balloons, etc.) and satellites etc.).
  • the terminal in the embodiment of this application may also be called user equipment (UE), user, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, Terminal equipment, wireless communication equipment, user agent or user device, etc.
  • the terminal can be a mobile phone (mobile phone), tablet computer (Pad), computer with wireless transceiver function, virtual reality (VR) terminal equipment, augmented reality (AR) terminal equipment, industrial control (industrial control) Wireless terminals in self-driving, wireless terminals in remote medical, wireless terminals in smart grid, wireless terminals in transportation safety, Wireless terminals in smart cities, wireless terminals in smart homes, etc.
  • the embodiments of this application do not limit application scenarios.
  • the (R)AN device is responsible for wireless side access of the terminal.
  • (R)AN equipment can be a base station (base station), an evolved base station (evolved NodeB, eNodeB), a transmission reception point (TRP), or a next generation base station (next generation NodeB, gNB) in the 5G mobile communication system , the next generation base station in the 6th generation (6G) mobile communication system, or the base station in the future mobile communication system, etc.; it can also be a module or unit that completes some functions of the base station, for example, it can be a centralized unit (central unit) unit (CU), distributed unit (DU), RRU or baseband unit (BBU), etc.
  • (R)AN equipment can be a macro base station, a micro base station or an indoor station, or a relay node or a donor node, etc.
  • the data network is mainly used for operator networks that provide data services to terminals.
  • the Internet For example, the Internet, third-party business networks, IP multimedia service (IMS) networks, etc.
  • IMS IP multimedia service
  • each network element can communicate with each other through interfaces.
  • the interface between each network element can be a point-to-point interface or a service-based interface, which is not limited by this application.
  • network architecture shown above is only an illustrative description, and the network architecture applicable to the embodiments of the present application is not limited thereto. Any network architecture that can realize the functions of each of the above network elements is applicable to the embodiments of the present application.
  • network elements shown in Figure 1 can be understood as network elements used to implement different functions, and for example, can be combined into network slices as needed. These network elements can be independent devices, or they can be integrated into the same device to implement different functions, or they can be network elements in hardware devices, software functions running on dedicated hardware, or platforms (for example, cloud The virtualization function instantiated on the platform), this application does not limit the specific form of the above network elements.
  • Figure 4 is a schematic diagram of a communication method 400 provided by this application.
  • Method 400 may be executed by the data analysis network element and the service processing network element, or may be executed by modules or units in the data analysis network element and the service processing network element.
  • the data analysis network element may be one of NWDAF, AnLF, MDAS, digital twin network or an independent AnLF network element.
  • the service processing network element can be one of PCF, SMF, AMF, NSSF, UPF or AF. For convenience of description, they are referred to as data analysis network elements and business processing network elements below.
  • Method 400 may include at least part of the following.
  • Step 401 The data analysis network element obtains the first data of the network.
  • the granularity of the network is not specifically limited.
  • the network here may be a wireless network within a certain cell.
  • the network here may be a wireless network within the range of a certain TA.
  • the network here can be a wireless network within a certain network slice of a certain TA.
  • the data analysis network element can obtain the first data from at least one of the following network elements: NF (such as AMF, SMF, or PCF, etc.), AF, or OAM in the network.
  • NF such as AMF, SMF, or PCF, etc.
  • AF or OAM in the network.
  • the data analysis network element can collect the first data from the AF through NEF, or can directly collect the first data from the AF.
  • the first data here is related to the data analysis network element performing analysis services. For example, if the data analysis network element predicts the number of terminals residing on the network in a future period of time, the first data may include current data and/or historical data on the number of terminals residing on the network. For another example, if the data analysis network element predicts the average service rate of the network in a future period, the first data may include the number of users of the network, and current data and/or historical data of the average service rate per user.
  • Step 402 The data analysis network element obtains the first analysis result based on the first data and the first model.
  • the first analysis result is used by the service processing network element to adjust the network.
  • the first analysis result can be a numerical value or a set of numerical values, without limitation.
  • the first analysis result may be a predicted value of the number of terminals residing on the network within a certain range.
  • the first analysis result may be the predicted value of the average service rate and the predicted value of the maximum service rate of the network within a certain range.
  • the data analysis network element obtains the first analysis result based on the first data and the first model. It can also be understood that the data analysis network element uses the first model to analyze the first data and obtains the first analysis result. Or it can also be understood that the data analysis network element inputs the first data into the first model, and the data analysis network element can input the first data into the first model and obtain the output of the first model, where the output of the first model includes First analysis results.
  • Step 403 The data analysis network element sends the first analysis result to the service processing network element.
  • the service processing network element receives the first analysis result from the data analysis network element.
  • Step 404 The service processing network element adjusts the network according to the first analysis result.
  • the adjustment made by the service processing network element to the network corresponds to the first analysis result.
  • the adjustment made by the service processing network element to the network corresponds to the type of the first analysis result. For example, if the first analysis result includes a predicted value of the number of terminals residing in the network in a future period of time, then the corresponding service processing network element can adjust the number of terminals residing in the network. For another example, if the first analysis result includes a predicted value of the average service rate of the network in a future period of time, then the corresponding service processing network element can adjust the average service rate of the network.
  • the magnitude of the network adjustment made by the service processing network element is related to the value of the first analysis result. For example, if the first analysis result includes a large predicted value, the service processing network element can adjust the network using a larger adjustment range.
  • the service processing network element can adjust the RFSP index of the terminals residing in the network to realize the prediction of the number of terminals residing in the network.
  • the number of terminals is adjusted. Since each RFSP index is associated with one or a group of frequency points on the terminal side, by specifying an RFSP for the terminal, the terminal can no longer rely on the signal strength of each frequency band broadcast by the cell system for cell selection or cell reselection, thereby ensuring The terminals camp at the designated frequency points according to the designated RFSP, thereby adjusting the number of terminals resident in the network.
  • the business processing network element PCF can reduce the authorized maximum data rate of some users who occupy a large amount of bandwidth, thereby reducing the user data congestion of the network. level, improving the quality of business experience for most users.
  • the service processing network element SMF can open or close the redundant transmission path from the terminal to the network in the network slice to realize network slicing.
  • the average packet loss rate is reduced and the resources occupied by network slicing are optimally balanced.
  • the service processing network element SMF can select a UPF with a lighter load for the newly established session to reduce the user data congestion level of the network.
  • Step 405 The data analysis network element obtains the adjusted second data of the network.
  • the second data is data obtained again by the data analysis network element after the service processing network element adjusts the network according to the first analysis result.
  • Step 405 is implemented in the same manner as step 401, and reference may be made to the description of step 401, which will not be described again here.
  • Step 406 The data analysis network element obtains the second analysis result based on the second data.
  • the data analysis network element can analyze the second data and obtain the second analysis result.
  • the second analysis result includes information on key performance indicators of the adjusted network, where the information on key performance indicators can reflect the performance of the adjusted network.
  • the second analysis result may include information on one or more performance indicators. For example, it may include information on performance indicators in terms of network resources, service experience, or network element performance.
  • the key performance indicator information may be one or more of the performance indicator information included in the second analysis result, which is not limited by this application.
  • the service processing network element adjusts the network based on the first analysis result, and the second analysis result is obtained based on the second data of the adjusted network, the information on the key performance indicators of the adjusted network can be used Evaluate the correctness of the first analysis results.
  • the data analysis network element can perform conventional operations on the second data to obtain the second analysis result.
  • the operations here can be some simple operations, such as averaging, variance, etc.
  • the data analysis network element can obtain the second analysis result based on the second data and the second model.
  • the data analysis network element can analyze the first data of the network, obtain the first analysis result for adjusting the network, and obtain the second data of the network after adjusting the network according to the first analysis result,
  • the second data is analyzed to obtain a second analysis result that can be used to evaluate the correctness of the first analysis result.
  • the correctness of the first analysis result can reflect the correctness of the first model used to obtain the first analysis result, which helps the data analysis network element to promptly correct the first model when the first model fails, thereby helping It is used to improve the accuracy of analysis results or prediction results provided by data analysis network elements, thereby improving the stability of network operation.
  • the correctness of the first analysis result can also be described as the accuracy, validity or credibility of the first analysis result, etc.
  • the correctness of the first model can also be described as the accuracy, validity or credibility of the first model, etc.
  • the technical solution of this application is a universal method applicable to all business scenarios and data analysis types.
  • the first analysis result may be a predicted value of the number of terminals residing in the network, and the key performance indicator information may include the MOS of the network.
  • the first analysis result may be the predicted value of the average service rate and the predicted value of the maximum service rate of the network, and the information on the key performance indicators may include the network function load of the network.
  • the first analysis result is the predicted value of the user data congestion level of the network, and the key performance indicator information includes the MOS of the network.
  • the first analysis result is the MOS prediction value of the network's redundant transmission experience analysis
  • the key performance indicator information includes the maximum packet delay or average packet loss rate in the data network performance statistics of the network.
  • the first analysis result is the load prediction value of the user data network function of the network
  • the key performance indicator information includes the user data congestion level of the network.
  • the data analysis network element can determine whether the first model is valid based on the second analysis result.
  • the data analysis network element can determine whether the first model is valid based on the second analysis result.
  • it can be implemented through Method 1 and Method 2 shown in Figure 4.
  • Step 407 The data analysis network element determines the confidence level of the first analysis result based on the second analysis result.
  • the data analysis network element may determine the confidence level of the first analysis result based on the first information used to determine the confidence level and the second analysis result.
  • the first information may indicate a confidence level and a range of key performance indicators corresponding to the confidence level.
  • the range of the key performance indicator may be a single value.
  • the second analysis result includes indicator A, indicator B, and indicator C, and the first information may only indicate the range corresponding to indicator A.
  • the confidence level and the range of the key performance indicator corresponding to the confidence level satisfy: if the key performance indicator is less than or equal to the third threshold, the confidence level of the first analysis result is untrustworthy; or, if the key performance indicator is greater than the third threshold and is less than the fourth threshold, then the first analysis result is credible and the confidence level is the first value; or, if the key performance indicator is greater than or equal to the fourth threshold, the first analysis result is credible and the confidence level is the second value; where, The first value is lower than the second value.
  • the confidence level and the range of the key performance indicator corresponding to the confidence level satisfy: if the key performance indicator is less than the third threshold, the confidence level of the first analysis result is untrustworthy; or, if the key performance indicator is greater than or equal to the third threshold and less than the fourth threshold, then the first analysis result is credible and the confidence level is the first value; or, if the key performance indicator is greater than or equal to the fourth threshold, then the first analysis result is credible and the confidence level is the second value; where , the first value is lower than the second value.
  • the confidence level and the range of the key performance indicator corresponding to the confidence level satisfy: if the key performance indicator is less than the third threshold, the confidence level of the first analysis result is untrustworthy; or, if the key performance indicator is greater than or equal to the third threshold , then the confidence level of the first analysis result is credible.
  • the values of the third threshold and the fourth threshold can be set according to specific circumstances.
  • the first information may be in the form of a table or list, in which the confidence level corresponds to the range of the key performance indicator one-to-one.
  • the first information may include judgment conditions, and the judgment conditions may be specific conditional statements or thresholds that define the range of key performance indicators.
  • the first information may be pre-configured in the data analysis network element.
  • the first information may be obtained by the data analysis network element from the service processing network element.
  • the service processing network element may carry the first information in a message used to request the first analysis result of the subscription network.
  • the service processing network element can subscribe to the data analysis network element for the first analysis result of the network, and instruct the data analysis network element to obtain the second analysis result.
  • the business processing network element sends a first message to the data analysis network element.
  • the data analysis network element receives the first message from the business processing network element, where the first message is used to request the first analysis result of the subscription network and Instruct the data analysis network element to obtain the second analysis result.
  • the service processing network element can determine the key performance indicators that can reflect the correctness of the first analysis results based on the first analysis results, and then determine and instruct the data analysis network element to obtain the second analysis based on the key performance indicators. result.
  • the business processing network element can indicate the analysis services that the data analysis network element needs to provide through an analytics ID.
  • the first message may carry analysis identification #1, analysis identification #2 and TA
  • the identification of #1 where the analysis identification #1 corresponds to the number of predicted analysis terminals, and the analysis identification #2 corresponds to the MOS of the analysis terminal.
  • the service processing network element may also specify a period for outputting the analysis results through the first message. For example, the service processing network element may specify through the first message to output the analysis results every 10 minutes in the future.
  • Step 408 The data analysis network element determines whether the first model is valid based on the confidence level of the first analysis result.
  • Scenario 1 The data analysis network element performs conventional operations on the second data.
  • the credibility or disbelief of the confidence level of the first analysis result may correspond to the validity or failure of the first model.
  • the data analysis network element determines that the first model is invalid; or, if the confidence level of the first analysis result is credible, the data analysis network element determines The first model works.
  • Another possible implementation is that if the number of times the first analysis result is untrustworthy within a preset time period exceeds the first threshold, the data analysis network element determines that the first model is invalid; or, if the first analysis result's confidence level exceeds the first threshold, If the confidence level is credible, the data analysis network element determines that the first model is valid.
  • Scenario 2 The data analysis network element uses the second model to analyze the second data.
  • the confidence of the first analysis result should be credible; when the first model and/or the second model fails, the confidence of the first analysis result may be Appears untrustworthy. Therefore, when the confidence level of the first analysis result is untrustworthy, it may be that the first model fails, it may be that the second model fails, or it may be that both the first model and the second model fail; when the first analysis result When the confidence level of is credible, both the first model and the second model are valid.
  • the data analysis network element determines that the first model is valid.
  • the data analysis network element determines the first model and/or the second The model is invalid.
  • the data analysis network element when the data analysis network element determines that the first model and/or the second model is invalid, the data analysis network element can further determine whether the first model or the second model is invalid.
  • the data analysis network element determines that the first model is invalid, wherein the third analysis result is obtained through the third model, and the confidence level of the third analysis result is The degree is determined based on the fourth analysis result, which is obtained through the second model.
  • the data analysis network element uses the first model to obtain the first analysis result of network #1, uses the third model to obtain the third analysis result of network #2, and uses the second model to obtain the confidence and third analysis results of the first analysis result.
  • the confidence level of the third analysis result If the confidence level of the third analysis result is credible, it means that the shared second model has not failed, then the failed one is the first model.
  • the data analysis network element determines that the second model is invalid, where the third analysis result is obtained through the first model, and the third analysis result is The confidence level is determined based on the fifth analysis result, which is obtained through the fourth model.
  • the data analysis network element uses the first model to obtain the first analysis result of network #1 and the third analysis result of network #2, uses the second model to obtain the confidence of the first analysis result, and uses the fourth model to obtain the third analysis result.
  • the confidence level of the third analysis result If the confidence level of the third analysis result is credible, it means that the shared first model has not failed, then the failed one is the second model.
  • the data analysis network element can also directly Determine the first model and the second model are equally effective.
  • the data analysis network element when the confidence level of the first analysis result is untrustworthy or the number of times within the preset time period the confidence level of the first analysis result is untrustworthy exceeds the first threshold, the data analysis network element assumes that the first The model fails and the first model is corrected. If the confidence level of the first analysis result obtained by the data analysis network element is still untrustworthy after using the corrected first model, the data analysis network element determines to correct the second model.
  • the data analysis network element when the confidence level of the first analysis result is untrustworthy or the number of times within the preset time period the confidence level of the first analysis result is untrustworthy exceeds the first threshold, the data analysis network element assumes that the second If the model fails, the second model is corrected. If the confidence level of the first analysis result obtained by the data analysis network element is still untrustworthy after using the corrected second model, the data analysis network element determines to correct the first model.
  • the data analysis network element can provide the confidence level of the first analysis result to the business processing network element, so that the business processing network element uses the currently obtained third data based on the confidence level. 1. Analysis results. Specifically, the data analysis network element sends the confidence level of the first analysis result to the business processing network element. Correspondingly, the business processing network element receives the confidence level of the first analysis result from the data analysis network element; the business processing network element performs the analysis according to the confidence level. Adjust the network again or discard the first analysis result currently obtained.
  • the period or frequency in which the data analysis network element provides the first analysis result to the business processing network element may be the same as or may be different from the period or frequency in which the confidence level is provided, therefore, the confidence level currently obtained by the business processing network element It may not be obtained based on the first analysis result currently obtained. However, for the business processing network element, the business processing network element will use the currently acquired first analysis result and the currently acquired confidence level, that is, the business processing network element will use the latest first analysis result and the latest confidence level.
  • the business processing network element adjusts the network according to the first adjustment range; or, if the confidence level of the first analysis result is the second value, the business processing network element The network is adjusted according to the second adjustment range; or, if the confidence level of the first analysis result is the third value, the service processing network element discards the currently obtained first analysis result.
  • the first value and the second value are in the credible range, and the third value is in the untrustworthy range.
  • the first adjustment range is smaller than the second adjustment range.
  • Step 409 The data analysis network element sends the second analysis result to the service processing network element.
  • the service processing network element receives the second analysis result from the data analysis network element.
  • Step 410 The service processing network element determines the second information based on the second analysis result.
  • the second information is used to indicate whether the first analysis result is correct.
  • the second information is used to indicate whether to accept the first analysis result.
  • the following description takes an example in which the second information is used to indicate whether the first analysis result is correct.
  • the service processing network element may determine the confidence level of the first analysis result based on the second analysis result, and then determine the second information based on the confidence level of the first analysis result. Specifically, if the confidence level of the first analysis result is credible, the service processing network element determines that the first analysis result is correct. Alternatively, if the confidence level of the first analysis result is untrustworthy or the number of times within the preset time period the confidence level of the first analysis result is untrustworthy exceeds the first threshold, the service processing network element determines that the first analysis result is incorrect.
  • the service processing network element may determine the confidence level of the first analysis result based on the first information used to determine the confidence level and the second analysis result.
  • the first information may indicate a confidence level and a range of key performance indicators corresponding to the confidence level.
  • the form of the confidence level, the range of the key performance indicators corresponding to the confidence level, and the implementation method of the first information can be referred to Consider the description in step 407, which will not be repeated here.
  • the first information may be pre-configured in the service processing network element, or may be obtained by the service processing network element from other network elements, without limitation.
  • the service processing network element can compare the current second analysis result with the previously obtained second analysis result. If the currently obtained second analysis result includes information on key performance indicators relative to the previously obtained second analysis result, The information on the key performance indicators included in the second analysis result has deteriorated, and the business processing network element determines that the first analysis result is wrong; or if the information on the key performance indicators included in the currently obtained second analysis result is different from the previously obtained second analysis result. When the information on key performance indicators included in the analysis results is optimized, the service processing network element determines that the first analysis result is correct.
  • the business processing network element determines that the first analysis result is wrong, or if the current MOS is greater than the previous MOS, the business processing network element The network element determines that the first analysis result is correct.
  • Step 411 The service processing network element sends the second information to the data analysis network element.
  • the data analysis network element receives the second information from the service processing network element.
  • the second information is used to indicate whether the first analysis result is correct.
  • Step 412 The data analysis network element determines whether the first model is valid based on the second information.
  • Scenario 1 The data analysis network element performs conventional operations on the second data.
  • the correctness or error of the first analysis result may correspond to the validity or invalidation of the first model.
  • the data analysis network element determines that the first model is invalid; or, if the first analysis result is correct, the data analysis network element determines that the first model is valid.
  • the data analysis network element determines that the first model is invalid; or, if the first analysis result is correct, the data analysis network element element determines that the first model is valid.
  • Scenario 2 The data analysis network element uses the second model to analyze the second data.
  • the first analysis result should be correct; when the first model and/or the second model fails, the first analysis result may be wrong. Therefore, when the first analysis result is wrong, it may be that the first model fails, it may be that the second model fails, or it may be that both the first model and the second model fail; when the first analysis result is correct, the first model may fail. Both model and second model are valid.
  • the data analysis network element determines that the first model is valid.
  • the data analysis network element determines that the first model and/or the second model is invalid.
  • the data analysis network element when the data analysis network element determines that the first model and/or the second model is invalid, the data analysis network element can further determine whether the first model or the second model is invalid.
  • the data analysis network element determines that the first model is invalid, where the third analysis result is obtained through the third model, and whether the third analysis result is correct is based on the fourth analysis. The result is determined, and the fourth analysis result is obtained through the second model.
  • the data analysis network element uses the first model to obtain the first analysis result of network #1, uses the third model to obtain the third analysis result of network #2, and uses the second model Obtain the analysis result used to determine whether the first analysis result is correct and the analysis result used to determine whether the third analysis result is correct. If the third analysis result is correct, it means that the shared second model has not failed, then the failed one is the third one.
  • One model is used to determine whether the shared second model has not failed, then the failed one is the third one.
  • the data analysis network element determines that the second model is invalid, where the third analysis result is obtained through the first model, and whether the third analysis result is correct is based on the fifth The analysis results are determined, and the fifth analysis result is obtained through the fourth model.
  • the data analysis network element uses the first model to obtain the first analysis result of network #1 and the third analysis result of network #2, uses the second model to obtain the analysis result used to determine whether the first analysis result is correct, and uses The fourth model obtains the analysis result used to determine whether the third analysis result is correct. If the third analysis result is correct, it means that the shared first model has not failed, and the failed one is the second model.
  • the data analysis network element can also directly determine that the first model and the second model are equally effective.
  • Another possible implementation is that when the first analysis result is wrong or the number of times the first analysis result is wrong within a preset time period exceeds the second threshold, the data analysis network element assumes that the first model is invalid and corrects the first model. If the first analysis result obtained by the data analysis network element is still wrong after adopting the corrected first model, the data analysis network element determines to correct the second model.
  • Another possible implementation is that when the first analysis result is wrong or the number of times the first analysis result is wrong within a preset time period exceeds the second threshold, the data analysis network element assumes that the second model is invalid and corrects the second model. If the first analysis result obtained by the data analysis network element is still wrong after adopting the corrected second model, the data analysis network element determines to correct the first model.
  • the service processing network element may subscribe to the data analysis network element for the first analysis result and the second analysis result of the network.
  • the business processing network element sends a third message to the data analysis network element.
  • the data analysis network element receives the third message from the business processing network element, where the third message is used to request a third message to subscribe to the network.
  • An analysis result the business processing network element sends a request message to the data analysis network element, and accordingly, the data analysis network element receives the request message from the business processing network element, where the request message is used to request the second analysis result of the subscription network.
  • the business processing network element can determine the key performance indicators that can reflect the correctness of the first analysis results based on the first analysis results, and then determine to subscribe to the second analysis results from the data analysis network element based on the key performance indicators.
  • the service processing network element can indicate the analysis service that the data analysis network element needs to provide through the analysis identifier.
  • the request message can carry the analysis identifier #1, the analysis identifier #2, and the identifier of TA#1, where Analysis identification #1 corresponds to the number of predicted analysis terminals, and analysis identification #2 corresponds to the MOS of the analysis terminals.
  • the service processing network element may also specify a period for outputting analysis results through a request message. For example, the service processing network element may specify through a request message to output analysis results every 10 minutes in the future.
  • the third message and the request message can be two independent messages, or they can belong to one message, or they can be the same message. That is, the business processing network element can separately subscribe to the first analysis result and the second analysis result. You can also subscribe to the first analysis results and the second analysis results at the same time.
  • the service processing network element sends a third message to the data analysis network element.
  • the data analysis network element receives the third message from the service processing network element, where the third message is used to request a subscription to the network.
  • first analysis Result The data analysis network element sends a second message to the service processing network element.
  • the service processing network element receives the second message from the data analysis network element, where the second message is used to instruct the service processing network element to send a message to the data analysis network element.
  • the business processing network element can determine the key performance indicators that can reflect the correctness of the first analysis results based on the first analysis results, and then determine to subscribe to the second information from the data analysis network element based on the key performance indicators.
  • the business processing network element sends a request message to the data analysis network element, and accordingly, the data analysis network element receives the request message from the business processing network element, where the request message is used to request the second analysis result of the subscription network.
  • the data analysis network element can instruct the business processing network element to provide a correctness evaluation of the first analysis result. After receiving the instruction, the business processing network element can determine that it needs to subscribe to the second analysis result, thereby providing the data analysis network element with an evaluation of the correctness of the first analysis result. Subscribe to the second analysis results.
  • the data analysis network element may modify the first model.
  • the data analysis network element can obtain network data, and retrain a first model for obtaining the first analysis result based on the obtained network data.
  • Another possible implementation method is that the data analysis network element obtains network data and updates the current first model based on the obtained network data.
  • the data analysis network element includes a second model, and after it is determined that the second model is invalid, the data analysis network element can also modify the second model in the same way.
  • first model and the second model involved in this application may be two independent models, or they may be two functional parts of one model, which is not specifically limited.
  • the first model and/or the second model in the data analysis network element can be obtained by training the data analysis network element. of.
  • the data analysis network element is NWDAF and includes both MTLF and AnLF
  • the data analysis network element can obtain the first model and/or the second model through MTLF training.
  • the data analysis network element needs to obtain the first model and/or the second model from other network elements.
  • the data analysis network element is an independent AnLF network element
  • the data analysis network element needs to obtain the first model and/or the second model from other network elements, such as MTLF network elements.
  • MTLF and/or AnLF can be functions in NWDAF or independent network elements without limitation.
  • MTLF and AnLF as functions in NWDAF as an example.
  • MTLF is recorded as NWDAF-MTLF
  • AnLF is recorded as NWDAF-AnLF.
  • NWDAF-AnLF includes a first model and a second model
  • the first information includes judgment conditions.
  • the judgment conditions can indicate the range of key performance indicators corresponding to the confidence level.
  • the network performance prediction analysis takes the prediction and analysis of the number of terminals resident in the park as an example
  • the business experience analysis takes the analysis of the mean opinion score (MOS) that can reflect the business experience evaluation results of the park as an example.
  • the mobile network will be divided into multiple tracking areas (TAs), and multiple cells with similar geographical locations and frequent terminal movements will be divided into the same TA.
  • Different TAs are distinguished by tracking area identities (TAI). Assume that TA#1 is a tracking area where the macro base station covers the entire campus and its nearby areas, and TA#2 is a tracking area where the micro base station covers the entire campus in the high-frequency band. That is, TA#1 and TA#2 overlap in the campus. .
  • the network will redirect some low-priority terminals to TA#1.
  • the technical solution of this application is a universal method applicable to all business scenarios and data analysis types.
  • the business scenarios and data analysis types in the examples below are only exemplary and do not mean that the technology of this application will be used. Solutions are limited to specific business scenarios and data analysis types.
  • the technical solution of this application can also be applied to other business scenarios and other data analysis types.
  • the business processing network element can also be an SMF
  • the network performance prediction analysis can be data network performance analysis (DN performance prediction analytics) for edge computing (EC), such as predicting and analyzing the average traffic rate of the data network (average traffic rate) and maximum traffic rate (maximum traffic rate).
  • DN performance prediction analytics data network performance analysis
  • EC edge computing
  • SMF can request from NWDAF to subscribe to the predicted values of the average service rate and maximum service rate; SMF adjusts service routing and UPF selection based on the obtained predicted values to prevent edge computing in hotspot areas from being overloaded; SMF also monitors edge computing in hotspot areas.
  • the analysis results of UPF's network function load (NF load) are used to ensure that UPF's network function load is controlled due to SMF adjusting service routing and UPF selection to prevent UPF's network function overload.
  • Figure 5 is an example of the communication method provided by this application.
  • Method 500 in Figure 5 includes at least part of the following.
  • Step 501 NWDAF-MTLF distributes the trained first model and second model to NWDAF-AnLF.
  • Network performance prediction analysis can be an analysis service provided by NWDAF that predicts network performance such as the number of network users and wireless resource occupancy in a specified area based on current data and/or historical data of network operation.
  • NWDAF-AnLF can calculate the current and/or historical data of network operation (such as the number of current and/or historical resident terminals) based on the first model and the current and/or historical number of terminals resident in the specified area (such as The number of terminals residing in TA#2).
  • the second model is used for business experience analysis.
  • Business experience analysis is an analysis service provided by NWDAF that simulates and calculates subjective service experience scores based on the statistical indicators of a group of terminals.
  • the statistical indicators of the terminals can include at least one of the following: bit rate, packet delay, transmission, or reuse. The number of transmitted messages, etc.
  • NWDAF-AnLF can output a MOS that reflects the service experience evaluation results based on the second model and the current statistical indicators of the terminal.
  • first model and the second model may be two parts of one model, or may be two independent models, which is not limited by this application.
  • Step 502 PCF sends the first message to NWDAF-AnLF.
  • NWDAF-AnLF receives the first message from PCF.
  • the first message is used to request subscription to network performance prediction analysis.
  • the first message may also carry judgment conditions for checking whether the results of the network performance prediction analysis are accurate. Due to its own business needs, after receiving the results of the network performance prediction analysis of NWDAF-AnLF (that is, the predicted value of the number of terminals resident in the network in TA#2), PCF will adjust TA based on the results of the network performance prediction analysis. The number of terminals residing in TA#2 will affect the MOS of the network-resident terminals in TA#2. Therefore, the MOS of the network-resident terminals in TA#2 can reflect the results of PCF's network performance prediction analysis. network adjustment Effect.
  • NWDAF-AnLF that is, the predicted value of the number of terminals resident in the network in TA#2
  • the PCF can determine the MOS of the network-resident terminal in TA#2 based on the service correlation, can verify whether the results of the network performance prediction analysis based on the network adjustment are accurate, and can even make accuracy predictions on the results of the network performance prediction analysis. Evaluation, so that the first message carries judgment conditions for checking whether the results of the network performance prediction analysis are accurate.
  • the judgment condition may be one or more MOS thresholds used for judgment.
  • NWDAF-AnLF may use the one or more MOS thresholds in a default or agreed manner.
  • the judgment condition can be a specific conditional statement.
  • the judgment conditions may include the first MOS threshold and the second MOS threshold, and NWDAF-AnLF may be judged in the following manner:
  • MOS is the result of business experience analysis.
  • the specific values of the first MOS threshold and the second MOS threshold can be set according to specific circumstances.
  • the first MOS threshold may be 3.0
  • the second MOS threshold may be 3.5.
  • the first MOS threshold may be 3.5
  • the second MOS threshold may be 4.0.
  • the judgment condition may include the above conditional statements 1), 2) and 3).
  • the judgment condition may also include only the first MOS threshold, and NWDAF-AnLF may be judged in the following manner:
  • MOS is the result of business experience analysis.
  • the specific value of the first MOS threshold can be set according to specific circumstances.
  • the first MOS threshold may be 3.0, 4.0, etc.
  • the judgment condition may include the above conditional statements 4) and 5).
  • NWDAF-AnLF can be judged according to conditional statements 1), 2) and 3).
  • the PCF instructs the NWDAF-AnLF: after outputting the analysis results of the network performance prediction analysis to the PCF, start monitoring whether the MOS obtained by the business experience analysis satisfies the above judgment. condition.
  • Step 503 NWDAF-AnLF accepts the PCF's request and sends a response message to the PCF.
  • PCF receives the response message from NWDAF-AnLF.
  • the response message is used to indicate that the network performance prediction analysis subscription is successful.
  • Step 504 NWDAF-AnLF collects network data from at least one of 5GC NF, AF or OAM.
  • the network data here may include the number of terminals currently resident in the network in TA#2, statistical indicators of terminals resident in the network in TA#2, etc.
  • the statistical indicators of the terminal may include at least one of the following: bit rate, packet delay, number of transmission or retransmission packets, etc.
  • the above two types of network data can be obtained simultaneously or separately, depending on the frequency or period of NWDAF-AnLF's network performance prediction analysis and NWDAF-AnLF's service experience analysis.
  • Step 505 NWDAF-AnLF is based on the first model obtained in step 501 and the current data collected in step 504.
  • the number of terminals residing in the network in TA#2 is analyzed by network performance prediction, and the result of the network performance prediction analysis is obtained, that is, the predicted value of the number of terminals residing in the network in TA#2.
  • Step 506 NWDAF-AnLF performs service experience analysis based on the second model obtained in step 501 and the statistical indicators of network-resident terminals in TA#2 collected in step 504, and obtains the result of the service experience analysis, that is, the The MOS of the network-resident terminal.
  • Step 507 NWDAF-AnLF determines whether the results of the network performance prediction analysis are valid based on the judgment conditions obtained in step 502 and the results of the service experience analysis.
  • NWDAF-AnLF determines that the result of the network performance prediction analysis is valid, and steps 508-511 may be performed subsequently.
  • NWDAF-AnLF determines that the result of the network performance prediction analysis is invalid, and steps 512-515 may be performed subsequently.
  • Step 508 NWDAF-AnLF further determines the confidence level of the results of the network performance prediction analysis based on the judgment conditions obtained in step 502 and the results of the service experience analysis.
  • the confidence can be accuracy, credibility, etc., and is not limited.
  • NWDAF-AnLF determines that the confidence level of the result of the network performance prediction analysis is low.
  • NWDAF-AnLF determines that the confidence level of the result of the network performance prediction analysis is high.
  • Step 509 NWDAF-AnLF provides the PCF with the results of the network performance prediction analysis and the confidence level of the results of the network performance prediction analysis.
  • Step 510 PCF adjusts the radio access technology/frequency selection priority (RFSP) index of the terminal in the campus location based on the results of the network performance prediction analysis and the confidence level of the results of the network performance prediction analysis.
  • RFSP radio access technology/frequency selection priority
  • PCF can adopt a relatively conservative adjustment range and only adjust the RFSP index of a small number of terminals per unit time.
  • the PCF can adopt a normal adjustment range.
  • each RFSP index is associated with one or a group of frequency points on the terminal side
  • the terminal can no longer rely on the signal strength of each frequency band broadcast by the cell system for cell selection or cell reselection, thereby ensuring The terminal camps on the specified frequency point according to the specified RFSP. In this way, it is possible to instruct some of the terminals at the same location to camp on the cell of TA#2 and the other part to camp on the cell of TA#1.
  • the frequency or period in which NWDAF-AnLF performs network performance prediction analysis and the frequency or period in which NWDAF-AnLF performs service experience analysis may be the same or different.
  • network performance prediction analysis and business experience analysis can be two independent processes.
  • the result of the network performance prediction analysis based on which the network is adjusted and the confidence of the result of the network performance prediction analysis may be the latest value of the result of the network performance prediction analysis and the latest value of the confidence of the result of the network performance prediction analysis. , but the two latest values may not be obtained at the same time, and even the latest value of the confidence of the result of the network performance prediction analysis does not reflect the confidence of the latest value of the result of the network performance prediction analysis.
  • Step 511 PCF sends the adjusted RFSP index to AMF so that AMF can make subsequent network adjustments.
  • the AMF receives the adjusted RFSP index from the PCF.
  • the PCF can send the adjusted RFSP index through a message used to modify the mobility management policy of the terminal.
  • the above-mentioned subsequent network adjustments are not shown in Figure 5 .
  • the subsequent network adjustment may be: the AMF sends the adjusted RFSP index to the access network device connected to the terminal through the N2 interface; the access network device assigns the reselection priority of the frequency point to the terminal based on the received RFSP index.
  • the terminal can reselect the cell of the designated frequency point, thereby achieving the purpose of controlling the number of terminals in TA#2.
  • Step 512 NWDAF-AnLF determines whether the first model fails or the second model fails.
  • the first model is a model used for network performance prediction analysis.
  • the second model is a model used for business experience analysis. Model failure here can be understood as the model being inaccurate, incorrect, or inapplicable.
  • NWDAF-AnLF determines whether the first model fails or the second model fails based on the results of other business scenarios where the technical solution of the present application is applied.
  • NWDAF-AnLF uses the third model for user data congestion prediction analytics (user data congestion prediction analytics), uses the second model for business experience analysis, and SMF uses the user data congestion prediction output by NWDAF-AnLF.
  • NWDAF-AnLF uses the third transmission rate commonly used in the two scenarios.
  • the second model is normal, while the first model is invalid.
  • NWDAF-AnLF uses the first model for network performance prediction analysis and the fourth model for business experience analysis.
  • PCF uses the results of the network performance prediction analysis and business experience analysis output by NWDAF-AnLF.
  • NWDAF-AnLF could determine that the first model used in the two scenarios was normal, and the second model is invalid.
  • step 512 is an optional step, and NWDAF-AnLF may also directly request NWDAF-MTLF to retrain or update the first model and/or the second model.
  • Step 513 NWDAF-AnLF requests NWDAF-MTLF to retrain or update the failed model based on the result of step 512.
  • Step 514 NWDAF-MTLF collects the latest network data and retrains or updates the failed model.
  • Step 515 NWDAF-MTLF distributes the retrained or updated model to NWDAF-AnLF, so that NWDAF-AnLF can use the retrained or updated model to conduct network performance prediction analysis or business experience analysis.
  • steps 504 to 515 may be executed in a loop until the PCF cancels the subscription to network performance prediction analysis.
  • NWDAF-AnLF can also start executing the above-mentioned step 506 according to the requirements of step 502 after one or more cycles after providing the results of the network performance prediction analysis to the PCF, so that subsequent judgments on whether the model is invalid can be more accurate.
  • NWDAF performs network performance prediction analysis and at the same time monitors the results of business experience analysis related to network performance prediction analysis, so that NWDAF can determine network performance based on the results of business experience analysis without knowing the business logic. Whether the results of the prediction analysis are valid, so when the results of the network performance prediction analysis are invalid, the training data can be obtained in time, and the corresponding model can be retrained or updated to provide correct analysis results to PCF.
  • Figure 6 is another example of the communication method provided by this application.
  • Method 600 in Figure 6 includes at least part of the following.
  • Step 601 NWDAF-MTLF distributes the trained first model and second model to NWDAF-AnLF.
  • Step 601 is the same as step 501 in Figure 5.
  • step 601 reference can be made to step 501, which will not be described again here.
  • Step 602 PCF sends a third message to NWDAF-AnLF.
  • NWDAF-AnLF receives the third message from the PCF.
  • the third message is used to request subscription to network performance prediction analysis.
  • Step 603 NWDAF-AnLF accepts the PCF's request and sends a response message to the PCF.
  • PCF receives the response message from NWDAF-AnLF.
  • the response message is used to indicate that the network performance prediction analysis subscription is successful.
  • Step 604 PCF requests a message from NWDAF-AnLF.
  • NWDAF-AnLF receives the request message from PCF.
  • the request message is used to request subscription to business experience analysis.
  • the request message also carries the identification of TA#2 (for example, the TAI of TA#2) to limit the scope of network performance prediction analysis.
  • the request message may also specify a period for outputting the analysis results, for example, specifying that the analysis results be output every 10 minutes in the future.
  • PCF will adjust TA based on the results of the network performance prediction analysis.
  • the number of terminals residing in TA#2 will affect the MOS of the network-resident terminals in TA#2. Therefore, the MOS of the network-resident terminals in TA#2 can reflect the results of PCF's network performance prediction analysis. The effect of making network adjustments.
  • the PCF can determine the MOS of the network-resident terminal in TA#2 based on the service association, which can be used to verify whether the results of the network performance prediction analysis based on the network adjustment are accurate, and can even make accurate decisions on the results of the network performance prediction analysis. Degree of evaluation, thereby sending a request message to request NWDAF-AnLF to subscribe to service experience analysis.
  • Step 605 NWDAF-AnLF accepts the PCF's request and sends a response message to the PCF.
  • PCF receives the response message from NWDAF-AnLF.
  • the response message is used to indicate that the business experience analysis subscription is successful.
  • the above third message and request message may be one message, that is, PCF may subscribe to network performance prediction analysis and business experience analysis at the same time in one message, or they may be different messages.
  • the response messages in steps 603 and 605 can also be one message or different messages.
  • Step 606 NWDAF-AnLF collects network data from at least one of 5GC NF, AF or OAM.
  • Step 606 is the same as step 504 in Figure 5.
  • step 606 reference can be made to step 504, which will not be described again here.
  • Step 607 NWDAF-AnLF is based on the first model obtained in step 601 and the current data collected in step 606.
  • the number of terminals residing in the network in TA#2 is analyzed by network performance prediction, and the result of the network performance prediction analysis is obtained, that is, the predicted value of the number of terminals residing in the network in TA#2.
  • Step 608 NWDAF-AnLF provides the results of network performance prediction analysis to PCF.
  • Step 609 PCF adjusts the RFSP index of the terminal in the campus location based on the results of network performance prediction analysis.
  • each RFSP index is associated with one or a group of frequency points on the terminal side
  • the terminal can no longer rely on the signal strength of each frequency band broadcast by the cell system for cell selection or cell reselection, thereby ensuring The terminal camps on the specified frequency point according to the specified RFSP. In this way, it is possible to instruct some of the terminals at the same location to camp on the cell of TA#2 and the other part to camp on the cell of TA#1.
  • Step 610 PCF sends the adjusted RFSP index to AMF so that AMF can make subsequent network adjustments.
  • the AMF receives the adjusted RFSP index from the PCF.
  • the PCF can send the adjusted RFSP index through a message used to modify the mobility management policy of the terminal.
  • the above-mentioned subsequent network adjustments are not shown in Figure 6 .
  • the subsequent network adjustment may be: the AMF sends the adjusted RFSP index to the access network device connected to the terminal through the N2 interface; the access network device assigns the reselection priority of the frequency point to the terminal based on the received RFSP index.
  • the terminal can reselect the cell of the designated frequency point, thereby achieving the purpose of controlling the number of terminals in TA#2.
  • Step 611 NWDAF-AnLF performs service experience analysis based on the second model obtained in step 601 and the statistical indicators of terminals resident in the network in TA#2 collected in step 606, and obtains the result of the service experience analysis, that is, the service experience in TA#2 The MOS of the network-resident terminal.
  • Step 612 NWDAF-AnLF provides the results of the service experience analysis to the PCF.
  • the frequency or period in which NWDAF-AnLF performs network performance prediction analysis and the frequency or period in which NWDAF-AnLF performs service experience analysis may be the same or different.
  • network performance prediction analysis and business experience analysis can be two independent processes.
  • NWDAF-AnLF can provide network performance prediction analysis results and service experience analysis results to PCF at the same time, or can provide PCF with network performance prediction analysis results and service experience analysis results separately.
  • Step 613 PCF determines whether the results of the network performance prediction analysis are correct based on the results of the service experience analysis.
  • PCF can determine whether the results of network performance prediction analysis are correct based on the judgment conditions and the results of business experience analysis.
  • judgment condition reference may be made to the relevant description of step 502 in Figure 5 , which will not be described again here.
  • PCF can make judgments according to conditional statements 1), 2) and 3). In this way, if MOS is less than or equal to the first MOS threshold, NWDAF-AnLF judges that the result of the network performance prediction analysis is wrong. Or, if the MOS is greater than the first MOS threshold, NWDAF-AnLF determines that the result of the network performance prediction analysis is correct.
  • Step 614 PCF sends second information to NWDAF-AnLF.
  • NWDAF-AnLF receives the second information from the PCF.
  • the second information is used to indicate whether the result of the network performance prediction analysis is correct.
  • Step 615 NWDAF-AnLF determines whether the first model fails or the second model fails based on the second information.
  • the first model is a model used for network performance prediction analysis.
  • the second model is a model used for business experience analysis. Model failure here can be understood as the model being inaccurate, incorrect, or inapplicable.
  • NWDAF-AnLF determines that the first model and the second model are valid.
  • NWDAF-AnLF determines that the first model is invalid or the second model is invalid.
  • the way NWDAF-AnLF determines whether the first model fails or the second model fails may refer to the description in step 512, which will not be described again here.
  • NWDAF-AnLF determines that the first model and the second model are valid.
  • NWDAF-AnLF determines that the first model fails or the second model fails.
  • the way NWDAF-AnLF determines whether the first model fails or the second model fails may refer to the description in step 512, which will not be described again here.
  • step 615 is an optional step, and NWDAF-AnLF can also directly request NWDAF-MTLF to retrain or update the first model and/or the second model.
  • Step 616 NWDAF-AnLF requests NWDAF-MTLF to retrain or update the failed model based on the result of step 615.
  • Step 617 NWDAF-MTLF collects the latest network data and retrains or updates the failed model.
  • Step 618 NWDAF-MTLF distributes the retrained or updated model to NWDAF-AnLF, so that NWDAF-AnLF can use the retrained or updated model to conduct network performance prediction analysis or business experience analysis.
  • Steps 616-618 are the same as steps 513-515 in Figure 5.
  • steps 616-618 please refer to steps 513-515, which will not be described again here.
  • steps 606 to 618 may be executed in a loop until the PCF cancels the subscription to network performance prediction analysis.
  • the PCF can also adjust the RFSP index of the terminal in the campus location based on the results of the network performance prediction analysis and the confidence level of the results of the network performance prediction analysis.
  • PCF can further determine the confidence of the result of network performance prediction analysis based on the judgment conditions and the results of business experience analysis, so that PCF
  • the RFSP index of the terminal in the campus location is adjusted according to the results of the network performance prediction analysis and the confidence level of the results of the network performance prediction analysis.
  • the manner in which the PCF adjusts the RFSP index of the terminal in the campus location based on the results of the network performance prediction analysis and the confidence of the results of the network performance prediction analysis can refer to the relevant description of step 510 in Figure 5 .
  • PCF subscribes to NWDAF for network performance prediction analysis and service experience analysis associated with network performance prediction analysis.
  • PCF can determine whether the results of network performance prediction analysis are correct based on the service experience analysis and feed it back to NWDAF.
  • NWDAF can obtain training data in time, retrain or update the corresponding model, thereby providing correct analysis results to PCF.
  • Figure 7 is another example of the communication method provided by this application.
  • Method 700 in Figure 7 includes at least part of the following.
  • Step 701 NWDAF-MTLF distributes the trained first model and second model to NWDAF-AnLF.
  • Step 702 PCF sends a third message to NWDAF-AnLF.
  • NWDAF-AnLF receives the third message from the PCF.
  • the third message is used to request subscription to network performance prediction analysis.
  • Steps 701-702 are the same as steps 601-602 in Figure 6.
  • steps 701-702 please refer to steps 601-602, which will not be described again here.
  • Step 703 NWDAF-AnLF sends a response message to PCF.
  • PCF receives the response message from NWDAF-AnLF.
  • the response message is used to indicate that the network performance prediction analysis subscription is successful and to instruct PCF to provide a correctness evaluation of the results of the network performance prediction analysis, where the correctness evaluation can be a score of the accuracy of the analysis results, or the correctness evaluation can also be analysis Feedback on whether the results are accepted, where acceptance indicates that the analysis results are accurate, and rejection indicates that the analysis results are inaccurate.
  • Instructing PCF to provide the correctness evaluation of the results of network performance prediction analysis which can also be understood as subscribing to PCF for the correctness evaluation of the results of network performance prediction analysis, that is, requiring PCF to feedback the correctness of the results of network performance prediction analysis to NWDAF-AnLF. evaluate.
  • the effectiveness can also be accuracy, adaptability, etc., without limitation.
  • Step 704 PCF determines service experience analysis related to network performance prediction analysis based on the service association relationship.
  • the business experience analysis related to the network performance prediction analysis can be understood as the results of the business experience analysis can reflect the effect of network adjustment by PCF based on the results of the network performance prediction analysis.
  • PCF can determine the MOS of the network-resident terminals in TA#2 based on service correlation, which can be used to verify the basis for network adjustment. Are the results of network performance prediction analysis correct? Therefore, PCF can subscribe to and monitor the MOS of network-resident terminals within TA#2.
  • Step 705 PCF requests a message from NWDAF-AnLF.
  • NWDAF-AnLF receives the request message from PCF.
  • the request message is used to request subscription to business experience analysis.
  • Step 706 NWDAF-AnLF accepts the PCF's request and sends a response message to the PCF.
  • PCF receives the response message from NWDAF-AnLF.
  • the response message is used to indicate that the business experience analysis subscription is successful.
  • Steps 705-706 are the same as steps 604-605 in Figure 6.
  • steps 705-706 please refer to steps 604-605, which will not be described again here.
  • steps 707-719 are the same as steps 606-618 in Figure 6.
  • steps 707-719 please refer to steps 606-618, which will not be described again here.
  • PCF subscribes to network performance prediction analysis from NWDAF, determines the need to subscribe to NWDAF for business experience analysis associated with network performance prediction analysis according to the instructions of NWDAF, and judges the results of network performance prediction analysis based on the results of the business experience analysis. Is it correct and provide feedback to NWDAF. In this way, when the PCF feedback network performance prediction analysis results are wrong, NWDAF can obtain training data in time, retrain or update the corresponding model, thereby providing correct analysis results to PCF.
  • the device in Figure 8 or Figure 9 includes corresponding hardware structures and/or software modules for performing each function.
  • the units and method steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software driving the hardware depends on the specific application scenarios and design constraints of the technical solution.
  • FIGS 8 and 9 are schematic structural diagrams of possible devices provided by embodiments of the present application. These devices can be used to implement the functions of the data analysis network element or the service processing network element in the above method embodiments, and therefore can also achieve the beneficial effects of the above method embodiments.
  • the device 800 includes a transceiver unit 810 and a processing unit 820 .
  • the transceiver unit 810 is used to: obtain the first data of the network.
  • the processing unit 820 is configured to obtain a first analysis result according to the first data and the first model.
  • the transceiver unit 810 is also configured to send the first analysis result to the service processing network element, where the first analysis result is used by the service processing network element to adjust the network.
  • the transceiver unit 810 is also configured to obtain the adjusted second data of the network.
  • the processing unit 820 is further configured to: obtain a second analysis result according to the second data, where the second analysis result includes adjusted information on key performance indicators of the network.
  • the processing unit 820 is further configured to: determine the confidence of the first analysis result according to the information of the key performance indicator; determine whether the first model is based on the confidence of the first analysis result. efficient.
  • the processing unit 820 is specifically configured to: if the confidence level of the first analysis result is untrustworthy or the number of times within the preset time period that the confidence level of the first analysis result is untrustworthy exceeds the first threshold, the data analysis network element determines that the first model is invalid; or, if the confidence level of the first analysis result is credible, the data analysis network element determines that the first model is valid.
  • the transceiver unit 810 is further configured to send the confidence level of the first analysis result to the service processing network element.
  • the transceiver unit 810 is further configured to: receive a first message from the service processing network element, where the first message is used to request subscription to the first analysis result, and the first message is Instructing the data analysis network element to obtain the second analysis result.
  • the first message carries first information, and the first information is used to determine the confidence level.
  • the first information includes the confidence level and the range of key performance indicators corresponding to the confidence level.
  • the range of key performance indicators can be a single value.
  • the transceiver unit 810 is further configured to: send the second analysis result to the service processing network element; receive second information from the service processing unit, where the second information is used to indicate the Whether the first analysis result is correct, the second information is determined based on the second analysis result.
  • the processing unit 820 is also configured to determine whether the first model is valid according to the second information.
  • the transceiver unit 810 is further configured to: send a second message to the service processing network element, where the second message is used to instruct the service processing network element to provide the data analysis network element with the Second information.
  • the processing unit 820 is specifically configured to: determine whether the first analysis result is correct according to the second information; if the first analysis result is wrong or the first analysis result is within a preset time period, If the number of errors exceeds the second threshold, the data analysis network element determines that the first model is invalid; or, if the first analysis result is correct, the data analysis network element determines that the first model is valid.
  • the data analysis network element is AnLF
  • the transceiver unit 810 is further configured to: obtain the first model and the second model from MTLF.
  • the processing unit 820 is specifically configured to: obtain the second analysis result according to the second data and the second model.
  • handle it Unit 820 is also used to determine whether the first model or the second model is invalid.
  • the processing unit 820 is specifically configured to: if the confidence level of the third analysis result for another network is credible, determine that the first model is invalid, wherein the third analysis result is obtained by Obtained by the third model, the confidence of the third analysis result is determined based on the fourth analysis result, the fourth analysis result is obtained by the second model; or, if the third analysis result of another network is If the confidence level of the analysis result is credible, it is determined that the second model is invalid, wherein the third analysis result is obtained through the first model, and the confidence level of the third analysis result is based on the fifth analysis. The result is determined, and the fifth analysis result is obtained through the fourth model.
  • the first analysis result is the network performance of the network
  • the information on the key performance indicators is used to indicate the service experience evaluation result of the network.
  • the first analysis result is a predicted value of the number of terminals residing in the network, and the key performance indicator information includes the MOS of the network; or, the first analysis result is The predicted value of the average service rate and the predicted value of the maximum service rate of the network, and the information about the key performance indicators includes the network function load of the network.
  • the network is a wireless network within the scope of the TA; or, the network is a wireless network within the scope of the network slice of the TA.
  • the data analysis network element includes at least one of the following: NWDAF, AnLF, MDAS, or digital twin network; and/or the service processing network element includes at least one of the following: policy control network element, session management network element, access and Mobile management network elements, network slicing selection network elements, user plane network elements, or application function network elements.
  • the transceiver unit 810 when the device 800 is used to implement the functions of the service processing network element in the above method embodiment, the transceiver unit 810 is used to: obtain the first analysis result obtained by the data analysis network element according to the first model.
  • the processing unit 820 is configured to adjust the network according to the first analysis result.
  • the transceiver unit 810 is also configured to: send a request message to the data analysis network element, where the request message is used to request a subscription to the second analysis result of the network; and obtain the second analysis result from the data analysis network element.
  • the second analysis result includes adjusted information on key performance indicators of the network.
  • the processing unit 820 is further configured to determine second information according to the second analysis result, where the second information is used to indicate whether the first analysis result is correct.
  • the transceiver unit 810 is also configured to send the second information to the data analysis network element, where the second information is used by the data analysis network element to determine whether the first model is valid.
  • the processing unit 820 is specifically configured to: determine the confidence level of the first analysis result based on the second analysis result; and determine the second information based on the confidence level of the first analysis result.
  • the processing unit 820 is specifically configured to: compare the information on the key performance indicators included in the second analysis result with the previously obtained key performance indicators; if the information on the key performance indicators included in the second analysis result is If the information on the key performance indicators deteriorates compared to the previously obtained key performance indicators, it is determined that the first analysis result is wrong; or if the information on the key performance indicators included in the second analysis result is worse than the previously obtained key performance indicators. If the information is optimized, it is determined that the first analysis result is correct.
  • the transceiver unit 810 is further configured to: receive a second message from the data analysis network element, where the second message is used to instruct the service processing network element to provide the data analysis network element with the information. Describe the second information.
  • the method further includes: the service processing network element determines to subscribe to the second analysis result from the data analysis network element based on the information of the key performance indicators.
  • the first analysis result is the network performance of the network
  • the information on the key performance indicators is used to indicate the service experience evaluation result of the network.
  • the first analysis result is a predicted value of the number of terminals residing in the network, and the key performance indicator information includes the MOS of the network; or, the first analysis result is The predicted value of the average service rate and the predicted value of the maximum service rate of the network, and the information about the key performance indicators includes the network function load of the network.
  • the network is a wireless network within the scope of the TA, or a wireless network within the scope of a network slice of the TA.
  • the data analysis network element includes at least one of the following: NWDAF, AnLF, MDAS, or digital twin network; and/or the service processing network element includes at least one of the following: policy control network element, session Management network elements, access and mobility management network elements, network slicing selection network elements, user plane network elements, or application function network elements.
  • the transceiver unit 810 is used to: send a first message to the data analysis network element, the first message is used to request Subscribing to the first analysis result of the network, the first analysis result is used to adjust the network, the first message is also used to instruct the data analysis network element to obtain the second analysis result of the network, the second The analysis results include the adjusted key performance indicators of the network; the service processing network element receives the first analysis results from the data analysis network element.
  • the processing unit 820 is configured to adjust the network according to the first analysis result.
  • the processing unit 820 is further configured to determine and instruct the data analysis network element to obtain the second analysis result according to the information on the key performance indicator.
  • the first message carries first information, and the first information is used to determine the confidence of the first analysis result.
  • the first information includes the confidence level and the range of key performance indicators corresponding to the confidence level.
  • the range of key performance indicators can be a single value.
  • the transceiver unit 810 is further configured to: receive the confidence level from the data analysis network element.
  • the processing unit 820 is also configured to: adjust the network again or discard the first analysis result currently obtained by the service processing network element according to the confidence level.
  • the first analysis result is the network performance of the network
  • the information on the key performance indicators is used to indicate the service experience evaluation result of the network.
  • the first analysis result is a predicted value of the number of terminals residing in the network, and the key performance indicator information includes the average opinion value MOS of the network; or, the first The analysis results are the predicted value of the average service rate and the predicted value of the maximum service rate of the network, and the information on the key performance indicators includes the network function load of the network.
  • the network is a wireless network within the scope of the TA, or a wireless network within the scope of a network slice of the TA.
  • the data analysis network element includes at least one of the following: NWDAF, AnLF, MDAS, or digital twin network; and/or the service processing network element includes at least one of the following: policy control network element, session Management network elements, access and mobility management network elements, network slicing selection network elements, user plane network elements, or application function network elements.
  • transceiver unit 810 and processing unit 820 For a more detailed description of the above-mentioned transceiver unit 810 and processing unit 820, reference may be made to the relevant descriptions in the above-mentioned method embodiments, which will not be described again here.
  • the apparatus 900 includes a processor 910 .
  • the apparatus 900 may also include an interface circuit 920.
  • the processor 910 and the interface circuit 920 are coupled to each other. It can be understood that the interface circuit 920 may be a transceiver or an input-output interface.
  • the apparatus 900 may further include a memory 930 for storing instructions executed by the processor 910 or input data required for the processor 910 to run the instructions or data generated after the processor 910 executes the instructions.
  • the processor 910 is used to implement the functions of the above-mentioned processing unit 820, and the interface circuit 920 is used to implement the functions of the above-mentioned transceiver unit 810.
  • the chip When the device 900 is a chip applied to a data analysis network element, the chip implements the functions of the data analysis network element in the above method embodiment.
  • the chip receives information from other modules (such as radio frequency modules or antennas) in the data analysis network element, and the information is sent to the data analysis network element by other devices; or, the chip sends information to other modules (such as radio frequency) in the data analysis network element. module or antenna) to send information, which is sent by the data analysis network element to other devices.
  • modules such as radio frequency modules or antennas
  • the chip When the device 900 is a chip applied to a service processing network element, the chip implements the functions of the service processing network element in the above method embodiment.
  • the chip receives information from other modules (such as radio frequency modules or antennas) of the service processing network element, and the information is sent to the service processing network element by other devices; or, the chip sends information to other modules (such as radio frequency modules) in the service processing network element. or antenna) to send information, which is sent to other devices by the service processing network element.
  • modules such as radio frequency modules or antennas
  • the application also provides a communication device, including a processor, the processor is coupled to a memory, the memory is used to store computer programs or instructions and/or data, the processor is used to execute the computer programs or instructions stored in the memory, or read the memory storage data to perform the methods in each of the above method embodiments.
  • a communication device including a processor, the processor is coupled to a memory, the memory is used to store computer programs or instructions and/or data, the processor is used to execute the computer programs or instructions stored in the memory, or read the memory storage data to perform the methods in each of the above method embodiments.
  • the communication device includes memory.
  • the memory is integrated with the processor, or is provided separately.
  • the present application also provides a computer-readable storage medium on which are stored computer instructions for implementing the methods executed by the data analysis network element or the business processing network element in each of the above method embodiments.
  • This application also provides a computer program product, which includes instructions.
  • the instructions are executed by a computer, the methods executed by the data analysis network element or the business processing network element in each of the above method embodiments are implemented.
  • This application also provides a communication system, which includes the data analysis network element or business processing network element in the above embodiments.
  • processor in the embodiment of the present application can be a central processing unit (CPU), or other general-purpose processor, digital signal processor (DSP), or application-specific integrated circuit (application specific integrated circuit, ASIC), field programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof.
  • CPU central processing unit
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA field programmable gate array
  • a general-purpose processor can be a microprocessor or any conventional processor.
  • the method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions.
  • Software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory In memory, register, hard disk, mobile hard disk, CD-ROM or any other form of storage medium well known in the art.
  • An exemplary storage medium is coupled to the processor such that the processor can read information from the storage medium and write information to the storage medium.
  • the storage medium can also be an integral part of the processor.
  • the processor and storage media may be located in an ASIC.
  • the ASIC can be located in a data analysis network element or a business processing network element.
  • the processor and storage medium can also exist as discrete components in the data analysis network element or business processing network element. middle.
  • the computer program product includes one or more computer programs or instructions.
  • the computer may be a general purpose computer, a special purpose computer, a computer network, a network device, a user equipment, or other programmable device.
  • the computer program or instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another.
  • the computer program or instructions may be transmitted from a website, computer, A server or data center transmits via wired or wireless means to another website site, computer, server, or data center.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media.
  • the available media may be magnetic media, such as floppy disks, hard disks, and tapes; optical media, such as digital video optical disks; or semiconductor media, such as solid-state hard drives.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

La présente demande concerne un procédé de communication et un appareil de communication. Selon le procédé, un élément de réseau d'analyse de données peut analyser des premières données d'un réseau pour obtenir un premier résultat d'analyse utilisé pour ajuster le réseau, acquérir des secondes données du réseau après l'ajustement du réseau selon le premier résultat d'analyse, et analyser les secondes données pour obtenir un second résultat d'analyse qui peut être utilisé pour évaluer l'exactitude du premier résultat d'analyse. L'exactitude du premier résultat d'analyse peut refléter l'efficacité d'un premier modèle utilisé pour obtenir le premier résultat d'analyse de sorte que l'élément de réseau d'analyse de données peut corriger le premier modèle de manière opportune lorsque le premier modèle échoue, ce qui contribue à améliorer la précision d'un résultat d'analyse ou d'un résultat de prédiction fourni par l'élément de réseau d'analyse de données, et à améliorer la stabilité de fonctionnement du réseau.
PCT/CN2023/074121 2022-03-08 2023-02-01 Procédé de communication et appareil de communication Ceased WO2023169101A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210219923.0 2022-03-08
CN202210219923.0A CN116782253A (zh) 2022-03-08 2022-03-08 一种通信方法和通信装置

Publications (1)

Publication Number Publication Date
WO2023169101A1 true WO2023169101A1 (fr) 2023-09-14

Family

ID=87937106

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/074121 Ceased WO2023169101A1 (fr) 2022-03-08 2023-02-01 Procédé de communication et appareil de communication

Country Status (2)

Country Link
CN (1) CN116782253A (fr)
WO (1) WO2023169101A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120128947A (zh) * 2025-03-11 2025-06-10 中国联合网络通信集团有限公司 通感一体感知算法的自更新方法、装置及设备

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111836291A (zh) * 2019-04-18 2020-10-27 中国移动通信有限公司研究院 一种切片资源调度方法及网元
CN113709776A (zh) * 2020-05-22 2021-11-26 华为技术有限公司 一种通信方法、装置及系统

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111836291A (zh) * 2019-04-18 2020-10-27 中国移动通信有限公司研究院 一种切片资源调度方法及网元
CN113709776A (zh) * 2020-05-22 2021-11-26 华为技术有限公司 一种通信方法、装置及系统

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
"3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Study of Enablers for Network Automation for 5G System (5GS); Phase 3 (Release 18)", 3GPP STANDARD; TECHNICAL REPORT; 3GPP TR 23.700-81, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, no. V0.1.0, 7 March 2022 (2022-03-07), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, pages 1 - 14, XP052144437 *
HUAWEI, HISILICON: "KI#1, New Sol: Detect and Improve correctness of NWDAF analytics", 3GPP DRAFT; S2-2205071, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. SA WG2, no. e-meeting; 20220516 - 20220520, 20 May 2022 (2022-05-20), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, XP052160546 *
HUAWEI, HISILICON: "New KI on Detection of Improved Correctness of an Analytics (WT1.2)", 3GPP DRAFT; S2-2200276, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. SA WG2, no. e-meeting; 20220214 - 20220225, 28 January 2022 (2022-01-28), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, XP052124518 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120128947A (zh) * 2025-03-11 2025-06-10 中国联合网络通信集团有限公司 通感一体感知算法的自更新方法、装置及设备

Also Published As

Publication number Publication date
CN116782253A (zh) 2023-09-19

Similar Documents

Publication Publication Date Title
US11758416B2 (en) System and method of network policy optimization
CA3112926C (fr) Procede et appareil de traitement d'informations de tranche
US10638356B2 (en) Transmission of network slicing constraints in 5G wireless networks
US12483476B2 (en) Slice control method and apparatus
US11929938B2 (en) Evaluating overall network resource congestion before scaling a network slice
US20190097753A1 (en) Quality parameter transmission method, terminal, and network side device
US20230344717A1 (en) Policy conflict management method, apparatus, and system
US20250023795A1 (en) Communication method and apparatus
US20240283714A1 (en) Data collection method and communication apparatus
WO2023213177A1 (fr) Procédé et appareil de communication
US20230362716A1 (en) Method and apparatus for determining machine learning model based on network congestion information in wireless communication system
CN116208964B (zh) 一种业务传输及其控制方法、设备
US20240155478A1 (en) Method and apparatus for establishing pdu sessions using a network slice
CN114125857A (zh) 一种确定传输规则的方法、网络设备及装置
WO2022067643A1 (fr) Procédé et appareil de sélection de cellule et procédé et appareil de radiomessagerie
CN115379535B (zh) 选网策略的确定方法及装置
EP4138508A1 (fr) Procédé, dispositif et système de communication
WO2023169101A1 (fr) Procédé de communication et appareil de communication
US20240389046A1 (en) Method and apparatus for controlling energy use in wireless communication system
US12477445B2 (en) Method and apparatus for supporting monitoring for external services in a wireless communication system
EP4564988A1 (fr) Communication relative à une session pdu redondante
US20250365217A1 (en) Communication method and communication apparatus
WO2025140013A1 (fr) Procédé de communication et appareil associé
WO2025148675A1 (fr) Procédé d'analyse de données de réseau et appareil de communication
KR20240029492A (ko) 무선 통신 시스템에서, 네트워크 슬라이스를 설정하기 위한 방법 및 장치

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23765681

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 23765681

Country of ref document: EP

Kind code of ref document: A1