[go: up one dir, main page]

WO2024027576A1 - Procédé et appareil de supervision de performance pour modèle de réseau d'ia, et dispositif de communication - Google Patents

Procédé et appareil de supervision de performance pour modèle de réseau d'ia, et dispositif de communication Download PDF

Info

Publication number
WO2024027576A1
WO2024027576A1 PCT/CN2023/109767 CN2023109767W WO2024027576A1 WO 2024027576 A1 WO2024027576 A1 WO 2024027576A1 CN 2023109767 W CN2023109767 W CN 2023109767W WO 2024027576 A1 WO2024027576 A1 WO 2024027576A1
Authority
WO
WIPO (PCT)
Prior art keywords
network model
target
information
terminal
performance
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/CN2023/109767
Other languages
English (en)
Chinese (zh)
Inventor
贾承璐
邬华明
杨昂
孙鹏
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.)
Vivo Mobile Communication Co Ltd
Original Assignee
Vivo Mobile Communication 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 Vivo Mobile Communication Co Ltd filed Critical Vivo Mobile Communication Co Ltd
Publication of WO2024027576A1 publication Critical patent/WO2024027576A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/08—Testing, supervising or monitoring using real traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Definitions

  • This application belongs to the field of communication technology, and specifically relates to a performance supervision method, device and communication equipment for an AI network model.
  • artificial intelligence Artificial Intelligence, AI
  • network models can be used to locate terminals in wireless communication networks.
  • Embodiments of the present application provide a performance supervision method, device and communication equipment for an AI network model, which can supervise the performance of the AI network model, thereby promptly discovering situations where the performance of the AI network model is low.
  • the first aspect provides a performance supervision method for AI network models, which includes:
  • the terminal obtains first information, the first information is used to determine the performance of a target AI network model, and the target AI network model is used to locate the terminal;
  • the terminal sends the first information to a network side device, or the terminal determines the performance of the target AI network model based on the first information.
  • a performance supervision device of an AI network model which is applied to a terminal.
  • the device includes:
  • An acquisition module configured to acquire first information, the first information being used to determine the performance of a target AI network model, and the target AI network model being used to position the terminal;
  • a first sending module or a first determination module is used to send the first information to a network side device.
  • the first determination module is used to determine the target AI network model according to the first information. performance.
  • a performance supervision method for AI network models including:
  • the network side device receives the first information from the terminal, and determines the performance of the target AI network model based on the first information, wherein the first information is used to determine the performance of the target AI network model, and the target AI network model is To locate the terminal;
  • the network side device receives fifth indication information from the terminal, wherein the fifth indication information is used to indicate that the Describe the performance of the target AI network model.
  • a performance supervision device of an AI network model which is applied to network-side equipment.
  • the device includes:
  • a third receiving module and a second determining module the third receiving module is used to receive the first information from the terminal, and the second determining module is used to determine the performance of the target AI network model according to the first information, wherein , the first information is used to determine the performance of the target AI network model, and the target AI network model is used to locate the terminal;
  • the fourth receiving module is configured to receive fifth indication information from the terminal, where the fifth indication information is used to indicate the performance of the target AI network model.
  • a communication device in a fifth aspect, includes a processor and a memory.
  • the memory stores a program or instructions that can be run on the processor.
  • the program or instructions are implemented when executed by the processor. The steps of the method described in the first aspect or the third aspect.
  • a communication device including a processor and a communication interface, wherein when the communication device is a terminal, the communication interface is used to obtain first information, and the first information is used to determine the target AI The performance of the network model, the target AI network model is used to locate the terminal; the communication interface is also used to send the first information to the network side device or the processor is used to determine based on the first information The performance of the target AI network model; or,
  • the communication interface is used to receive first information from a terminal, and the processor is used to determine the performance of the target AI network model according to the first information, wherein the first The information is used to determine the performance of the target AI network model, and the target AI network model is used to locate the terminal; or the communication interface is used to receive fifth indication information from the terminal, wherein the fifth indication The information is used to indicate the performance of the target AI network model.
  • a communication system including: a terminal and a network side device.
  • the terminal can be used to perform the steps of the performance supervision method of the AI network model as described in the first aspect.
  • the network side device can be used to perform The steps of the performance supervision method of the AI network model as described in the third aspect.
  • a readable storage medium is provided. Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method are implemented as described in the first aspect. The steps of the method described in the third aspect.
  • a chip in a ninth aspect, includes a processor and a communication interface.
  • the communication interface is coupled to the processor.
  • the processor is used to run programs or instructions to implement the method described in the first aspect. , or implement the method as described in the third aspect.
  • a computer program/program product is provided, the computer program/program product is stored in a storage medium, and the computer program/program product is executed by at least one processor to implement the method as described in the first aspect
  • the steps of the performance supervision method of the AI network model, or the computer program/program product is executed by at least one processor to implement the steps of the performance supervision method of the AI network model as described in the third aspect.
  • the terminal obtains first information, the first information is used to determine the performance of the target AI network model, and the target AI network model is used to locate the terminal; the terminal transmits information to the network side device Send the first information, or the terminal determines the performance of the target AI network model based on the first information.
  • the terminal can obtain the first information used to assist in determining the performance of the target AI network model, and report the first information to the network side device, so that the network side device determines the performance of the target AI network model based on the first information, or directly The terminal determines the performance of the target AI network model based on the first information.
  • Figure 1 is a schematic structural diagram of a wireless communication system to which embodiments of the present application can be applied;
  • Figure 2 is a flow chart of a performance supervision method for an AI network model provided by an embodiment of the present application
  • Figure 3 is a flow chart of another performance supervision method for an AI network model provided by an embodiment of the present application.
  • Figure 4 is a schematic structural diagram of a performance monitoring device for an AI network model provided by an embodiment of the present application
  • Figure 5 is a schematic structural diagram of another performance monitoring device for an AI network model provided by an embodiment of the present application.
  • Figure 6 is a schematic structural diagram of another performance monitoring device for an AI network model provided by an embodiment of the present application.
  • Figure 7 is a schematic structural diagram of a communication device provided by an embodiment of the present application.
  • Figure 8 is a schematic diagram of the hardware structure of a terminal provided by an embodiment of the present application.
  • Figure 9 is a schematic diagram of the hardware structure of a network side device provided by an embodiment of the present application.
  • first, second, etc. in the description and claims of this application are used to distinguish similar objects and are not used to describe a specific order or sequence. It is to be understood that the terms so used are interchangeable under appropriate circumstances so that the embodiments of the present application can be practiced in sequences other than those illustrated or described herein, and that "first" and “second” are distinguished objects It is usually one type, and the number of objects is not limited.
  • the first object can be one or multiple.
  • “and/or” in the description and claims indicates at least one of the connected objects, and the character “/" generally indicates that the related objects are in an "or” relationship.
  • LTE Long Term Evolution
  • LTE-Advanced, LTE-A Long Term Evolution
  • LTE-A Long Term Evolution
  • CDMA Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • FDMA Frequency Division Multiple Access
  • OFDMA Orthogonal Frequency Division Multiple Access
  • SC-FDMA Single-carrier Frequency Division Multiple Access
  • NR New Radio
  • FIG. 1 shows a block diagram of a wireless communication system to which embodiments of the present application are applicable.
  • the wireless communication system includes a terminal 11 and a network side device 12.
  • the terminal 11 can be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), or a notebook computer, a personal digital assistant (Personal Digital Assistant, PDA), a handheld computer, a netbook, or a super mobile personal computer.
  • Tablet Personal Computer Tablet Personal Computer
  • laptop computer laptop computer
  • PDA Personal Digital Assistant
  • PDA Personal Digital Assistant
  • UMPC Ultra-Mobile Personal Computer
  • MID Mobile Internet Device
  • AR Augmented Reality
  • VR Virtual Reality
  • PUE wearable devices
  • smart home home equipment with wireless communication functions, such as refrigerators, TVs, washing machines or furniture, etc.
  • game consoles personal computers
  • Personal Computer Personal Computer, PC
  • Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, Smart anklets, etc.), smart wristbands, smart clothing, etc.
  • the network side equipment 12 may include access network equipment or core network equipment, where the access network equipment may also be called wireless access network equipment, radio access network (Radio Access Network, RAN), radio access network function or wireless access network unit.
  • Access network equipment can include base stations, Wireless Local Area Networks (WLAN) access points or Wireless Fidelity (WiFi) nodes, etc.
  • the base station can be called Node B, Evolved Node B (Evolved Node B).
  • the base station is not limited to specific technical terms. It needs to be explained that , in the embodiment of this application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.
  • AI network models such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. This application takes a neural network as an example for explanation, but does not limit the specific type of AI network model.
  • the AI algorithm selected and the network model used are also different.
  • the main way to improve 5G network performance with the help of AI network models is to enhance or replace existing algorithms or processing modules with neural network-based algorithms and models.
  • neural network-based algorithms and models can achieve better performance than deterministic-based algorithms.
  • the more commonly used neural networks include deep neural networks, convolutional neural networks, and recurrent neural networks.
  • the embodiments of the present application can analyze the performance of the target AI network model used for terminal positioning.
  • the target AI network model can locate the terminal according to the wireless communication information of the terminal.
  • the specific functions and work of the target AI network model The principle is similar to the positioning AI network model in related technologies, and will not be described again here.
  • An embodiment of the present application provides a performance supervision method for an AI network model.
  • the execution subject is a terminal.
  • the terminal can be the terminal 11 in the embodiment shown in Figure 1, or the method shown in Figure 1. Terminals other than the terminal 11 listed in the embodiment are not specifically limited here.
  • the performance supervision method of the AI network model executed by the terminal may include the following steps:
  • Step 201 The terminal obtains first information, the first information is used to determine the performance of the target AI network model, and the target AI network model is used to locate the terminal.
  • the input information of the target AI network model may include: historical location information of the terminal, beam arrival angle, beam departure angle, beam arrival time difference and other information
  • the output information of the target AI network model may include the location information of the terminal.
  • the location information of the terminal can be used as a basis for wireless communication, for example, as a basis for beam selection, as a basis for TRP switching, as a basis for transmission power control, etc., which are not specifically limited here.
  • the location information of the terminal can also be used as the data basis for certain application functions, such as navigation.
  • the use of the terminal location information output by the target AI network model is not specifically limited here.
  • wireless communication based on the terminal location information output by the target AI network model is used as an example for illustration, and no specific limitation is constituted here.
  • the terminal can obtain the above-mentioned first information by at least one of measurement or information exchange with other communication devices.
  • the first information can be used to determine the accuracy of the positioning result obtained by the target AI network model. Or determine information such as the matching degree between the target AI network model and the wireless environment of the terminal. The lower the matching degree between the target AI network model and the wireless environment of the terminal, the more reliable the positioning result of the terminal obtained by the target AI network model will be. The sex is also lower.
  • Step 202 The terminal sends the first information to the network side device, or the terminal determines the performance of the target AI network model based on the first information.
  • the terminal may send the first information to the network side device, and the network side device may A piece of information to determine the performance of the target AI network model, for example: determine based on the first information that the target AI network model is valid in the current wireless environment of the terminal (that is, the positioning result obtained by the target AI network model can meet the positioning accuracy requirements of the terminal, or The positioning results obtained by the target AI network model are more reliable) or invalid (that is, the positioning results obtained by the target AI network model cannot meet the positioning accuracy requirements of the terminal, or the positioning results obtained by the target AI network model are not reliable. lower).
  • the network side device can take corresponding measures to reduce the probability of communication performance degradation or even communication failure when the terminal continues to perform wireless communications according to the positioning results obtained by the target AI network model. . For example: notify the terminal that the target AI network model is invalid; or notify the terminal to stop performing wireless communication-related operations based on the positioning results obtained by the target AI network model; or update the target AI network model and send the updated target AI to the terminal. network model.
  • the terminal can determine the performance of the target AI network model based on the first information.
  • This implementation is similar to the implementation in which the network side device determines the performance of the target AI network model based on the first information. The difference is that in this implementation, the process of determining the performance of the target AI network model based on the first information is performed.
  • the main body is the terminal, which will not be described again here.
  • the first information includes at least one of the following:
  • M is a positive integer
  • the location information of the terminal is determined using a first method that does not include the positioning method corresponding to the target AI network model;
  • the error or confidence of the location information of the terminal determined based on the target AI network model
  • the change amplitude or rate of change of the terminal s channel measurement information
  • the distance information between the terminal and the positioning reference unit (Positioning Reference Unit, PRU) or the transmission receiving node TRP is determined in a second way, and the second way does not include the way corresponding to the target AI network model;
  • the distance information between the terminal and other terminals determined using the second method is the distance information between the terminal and other terminals determined using the second method
  • the location information of the other terminals determined based on the target AI network model
  • LOS Line of Sight
  • NLOS Non-Line of Sight
  • the identification information of the PRU or TRP is the identification information of the PRU or TRP.
  • the terminal can determine the location information and motion status information of the terminal based on the target AI network model within M consecutive time units, wherein the target AI network model can be periodically used to determine the location information of the terminal, Or the first information is detected periodically.
  • the time unit may include time within a cycle.
  • the time unit may include: Orthogonal Frequency Division Multiplex (OFDM) symbols, time slots, subframes, reference signal periods, milliseconds, seconds, minutes, hours, days, etc., which are not specifically limited here.
  • OFDM Orthogonal Frequency Division Multiplex
  • the location information of the terminal in each of the M consecutive time units can be determined based on the target AI network model, and the terminal location information can also be obtained based on other methods (such as using motion sensor detection). (movement status information of the terminal) to determine the movement status information of the terminal within the M consecutive time units, such as: movement speed, movement distance, etc.
  • the position information of the terminal in M continuous time units determined based on the target AI network model and the motion status information of the terminal in M continuous time units can be verified with each other. If the two If there is no match, it can be determined that the target AI network model is invalid.
  • the terminal determines the performance of the target AI network model based on the first information, including: when the difference between the first distance and the second distance is greater than or equal to a first threshold, determining the The target AI network model is invalid, wherein the first distance is the distance between the position of the terminal in the first time unit and the position of the terminal in the Mth time unit determined based on the motion state information, and the The second distance is the distance between the position of the terminal in the first time unit and the position of the terminal in the Mth time unit determined based on the target AI network model, and M is greater than 1.
  • the motion status information is the motion speed of the terminal within the M continuous time units
  • v represents the movement speed of the terminal within the M continuous time units
  • t 1 represents the first time unit among the M continuous time units
  • t M represents the M consecutive time units.
  • the Mth time unit among the continuous time units, T 1 represents the first threshold
  • P 1 represents the terminal at the first time unit among the M consecutive time units determined based on the target AI network model.
  • the position of P M represents the position of the terminal at the Mth time unit among the M consecutive time units determined based on the target AI network model.
  • means finding the distance between P 1 and P M , such as the Euclidean distance.
  • the target AI network model may also be determined to be valid when the difference between the first distance and the second distance is less than the above-mentioned first threshold.
  • the location information of the terminal determined by a first method other than the target AI network model can be verified.
  • the difference between the two When it is larger, it can be determined that the target AI network model is invalid.
  • the above-mentioned first method may include: analyzing the current location information of the terminal based on the historical location information of the terminal, estimating the location information of the terminal based on the sensor's perception information of the terminal, etc., which will not be discussed one by one here. Exhaustive.
  • the distance between the location of the terminal determined using the first method and the location of the terminal determined based on the target AI network model is greater than or equal to a second threshold, determine the The target AI network model is invalid.
  • the distance between the position of the terminal determined using the first method and the position of the terminal determined based on the target AI network model may represent: the distance of the terminal determined using the first method.
  • the location of the terminal determined using the first method and the location based on If the distance between the terminal positions determined by the target AI network model is less than the above-mentioned second threshold, the target AI network model is determined to be valid.
  • the above-mentioned first method may include one or at least two methods, and each method may determine one or at least two positions of the terminal. In this case, the at least two positions determined based on all the first methods may be used.
  • the average or weighted average is used to verify the accuracy of the location of the terminal determined based on the target AI network model, so that the target AI network model can be determined based on the accuracy of the location of the terminal determined by the target AI network model. Performance is good or bad.
  • the target AI network model is invalid, wherein, the first position is the average or weighted average of the N positions of the terminal determined using the first method, and N is an integer greater than 1;
  • the target AI may also be determined when the distance between the first location and the location of the terminal determined based on the target AI network model is less than the above-mentioned third threshold.
  • the network model works.
  • the error or confidence of the terminal's location information determined based on the target AI network model can intuitively reflect the reliability of the terminal's location information determined based on the target AI network model, thereby in If the error in the location information of the terminal determined based on the target AI network model is large or the confidence level is low, it may be determined that the target AI network model is invalid. Correspondingly, when the error of the location information of the terminal determined based on the target AI network model is small or the confidence level is high, it can be determined that the target AI network model is valid.
  • the position of the terminal usually changes continuously, and the position of the terminal can be divided into at least two intervals to determine the degree of error or confidence that the position of the terminal is within the at least two intervals.
  • the minimum error of the location information of the terminal determined based on the target AI network model is greater than or equal to a ninth threshold, it is determined that the target AI network model is invalid.
  • the target AI network model can determine the error that the terminal's position information is located in at least two possible positions or position intervals. If the minimum error of the terminal located in at least two possible positions or position intervals determined based on the target AI network model is greater than or If equal to the ninth threshold, it can be determined that the error of the target AI network model is too large, thereby determining that the target AI network model is invalid.
  • the terminal determined based on the target AI network model is located in at least two possible locations or location intervals.
  • the ninth threshold it can be determined that the error of the target AI network model is small, thereby determining that the target AI network model is effective.
  • the target AI network model is invalid.
  • the confidence of the terminal's location information is negatively correlated with the error of the terminal's location information in the above optional embodiment. That is, the higher the confidence of the terminal's location information, the smaller the error of the terminal's location information.
  • the target AI network model For example: based on the intermediate results of the target AI network model (such as estimating the location of the terminal based on channel state information), and quantizing the location label, if the quantization interval is 2m, then the location interval of 0-2m is quantized to 1m, and the location interval of 2-4m is quantized. The location interval is quantified as 3m and so on.
  • the problem of position estimation of the terminal can be transformed into the problem of classifying the terminal location, that is, determining the confidence that the terminal location is within the location interval corresponding to each location label.
  • the output result of the last layer function (softmax) of the target AI network model can be used as the confidence level.
  • the maximum value of the confidence levels corresponding to all location labels output by the softmax layer of the last layer of the target AI network model is less than a certain threshold, it can be determined that the target AI network model is invalid.
  • Option four the change amplitude or rate of change of the terminal's channel measurement information.
  • the channel measurement information of the terminal can reflect changes in the wireless communication environment where the terminal is located, and the target AI network model can determine the location information of the terminal based on the wireless communication information of the terminal. Then the changes in the wireless communication environment where the terminal is located The situation is directly related to the accuracy of the location information of the terminal output by the target AI network model.
  • the channel measurement information of the above-mentioned terminal may include at least one of the following:
  • Channel state information includes: at least one of time domain channel state information, frequency domain channel state information, air domain channel state information, delay Doppler domain channel state information, and power delay spectrum;
  • Channel characteristic information which includes: Doppler frequency domain, first path delay, first path power, first path phase, first path angle, maximum H path delay, maximum H path power, maximum H path At least one of the phase and the angle of the maximum H diameter, H is an integer greater than or equal to 1;
  • Channel quality information which includes: Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), Signal-to-noise ratio (SNR) And at least one of the signal-to-noise and interference ratio (SINR).
  • RSRP Reference Signal Received Power
  • RSRQ Reference Signal Received Quality
  • SNR Signal-to-noise ratio
  • SINR Signal-to-noise and interference ratio
  • the more drastic the change amplitude or change rate of the channel measurement information of the terminal it can mean that the position of the terminal changes greatly in adjacent time units or in M consecutive units of time.
  • the change amplitude or change rate of the terminal's channel measurement information can reflect changes in the wireless network environment in which the terminal is located, and due to the continuity of the terminal's movement, the channel of the terminal in two adjacent times or a continuous period of time M
  • the measurement information should be similar. If the channel measurement information measured by the terminal at two adjacent times or within a continuous period of time M changes too drastically, it can indicate that there may be other factors interfering with the wireless network where the terminal is located during this period.
  • the communication environment for example, if a vehicle blocks the terminal's wireless link, causing the terminal's channel measurement information to change in amplitude or rate, the more drastic the change will be. Similarly, the confidence of the information input to the target AI network model during this period is low, and the location information of the terminal output by the target AI network model is The confidence level is low, thereby determining that the target AI network model is invalid.
  • the confidence of the location information of the terminal determined based on the target AI network model can also be set as a function related to the change rate of the channel measurement information. In this way, the change rate of the channel measurement information can be calculated based on The confidence of the terminal's location information determined by the target AI network model can determine that the target AI network model is valid based on the higher confidence, or determine that the target AI network model is invalid based on the lower confidence.
  • RSRP 1 represents the first time unit detection of the terminal in the M consecutive time units.
  • RSRP represents the RSRP detected by the terminal in the M-th time unit among the M consecutive time units
  • T 4 represents the above-mentioned fourth threshold.
  • the second method uses the distance information between the terminal and the positioning reference unit (Positioning Reference Unit, PRU) or transmission reception node (Transmission Reception Point, TRP) determined in the second method, where the second method may include based on the side link ( Distance detection based on sidelink communication, distance detection based on Bluetooth communication, and other methods of distance detection (ranging) are not specifically limited here.
  • PRU Positioning Reference Unit
  • TRP Transmission Reception Point
  • the ground-truth positions of the PRU and TRP are known.
  • the accuracy of the terminal's current position estimation can be assisted to estimate.
  • the number of the above-mentioned PRU/TRP may be one or at least two, and each PRU/TRP may be distinguished by associating the identification information of the PRU/TRP with the location information of each PRU/TRP in the first information.
  • the true location of the TRP (such as the ground-truth location).
  • the third distance is determined using the second method
  • the fourth distance is the distance between the position of the terminal determined based on the target AI network model and the position of the PRU or TRP
  • the third distance between the terminal and the PRU/TRP can be detected through distance detection based on sidelink communication or bluetooth communication, and then the location information of the terminal is determined based on the target AI network model, and the location is determined
  • the errors of the four distances are large, thus determining that the target AI network model is invalid, where P 1 represents the position of the terminal determined based on the target AI network model, P 0 represents the true position of the PRU/TRP, and D represents the above third distance, T 5 represents the fifth threshold value mentioned above.
  • the target AI network model is valid.
  • Option six Use the distance information between the terminal and other terminals determined in the second method.
  • the accuracy of the target AI network model can be verified based on the relative position relationship between the two terminals.
  • the positions of the other terminals can be determined based on the target AI network model, or determined in other ways. For example, for other terminals with fixed positions, the fixed positions of the other terminals can be obtained. For convenience of explanation, in the embodiments of this application , taking the position of other terminals also determined using the above target AI network model as an example to illustrate.
  • the number of the above-mentioned other terminals may be one or at least two, and the location information of each other terminal may be distinguished by associating the identification information of the other terminals with the location information of each other terminal in the first information.
  • the difference between the fifth distance and the sixth distance is greater than or equal to the sixth threshold, it is determined that the target AI network model is invalid, wherein the fifth distance is determined using the second method
  • the distance between the terminal and other terminals, the sixth distance is the distance between the location of the terminal determined based on the target AI network model and the location of the other terminal determined based on the target AI network model
  • the second method has the same meaning as the second method in option five above, and will not be described again here.
  • the positions of the above terminal and other terminals are determined using the target AI network model.
  • the sixth distance can be calculated based on the two positions. For example: if
  • the location information of the other terminals determined based on the target AI network model can be used to verify the positioning accuracy of the target AI network model. For example, for other terminals whose locations are known, their known locations can be The position is compared with the position of the other terminal determined based on the target AI network model. If the distance between the two is large, it can be determined that the positioning accuracy of the target AI network model is low, thereby determining that the target AI network model is invalid.
  • Line of Sight (LOS) or Non-Line of Sight (NLOS) indication information are optionally used.
  • AI network models that can only achieve higher positioning accuracy in LOS scenarios, and some AI network models that can only achieve higher positioning accuracy in NLOS scenarios.
  • the AI network model that can achieve higher positioning accuracy in the LOS scenario can be selected based on the LOS scenario where the wireless communication environment of the terminal is located, and the AI network model that can achieve higher positioning accuracy in the NLOS scenario can be selected based on the wireless communication environment of the terminal being located in the NLOS scenario.
  • AI network model with higher positioning accuracy can be used to be selected based on the LOS scenario where the wireless communication environment of the terminal is located.
  • the target AI network model is a network model used in a LOS scenario, and the LOS or NLOS indication information indicates that the LOS proportion of the terminal is less than or equal to a seventh threshold
  • the target is determined
  • the AI network model fails; and/or, when the target AI network model is a network model used in an NLOS scenario, and the LOS or NLOS indication information indicates that the NLOS proportion of the terminal is less than or equal to the eighth threshold. , determining that the target AI network model is invalid.
  • the LOS indication information may indicate the proportion of LOS paths in the wireless communication environment where the terminal is located
  • the NLOS indication information may indicate the proportion of NLOS paths in the wireless communication environment where the terminal is located.
  • the proportion of LOS paths is less than or equal to the seventh threshold, it means that the wireless communication environment in which the terminal is located is more inclined to the NLOS scenario.
  • the positioning AI network model suitable for the NLOS scenario can achieve better positioning results.
  • the positioning effect is poor when using the positioning AI network model suitable for LOS scenarios; if the proportion of NLOS paths is less than or equal to the eighth threshold, it means that the wireless communication environment in which the terminal is located is more inclined to the LOS scenario.
  • the applicable The positioning AI network model suitable for LOS scenarios can achieve better positioning results, while the positioning effect when using the positioning AI network model suitable for NLOS scenarios is poor.
  • the performance of the target AI network model can be determined based on whether the LOS/NLOS scenario applicable to the target AI network model adopted by the terminal matches the LOS/NLOS scenario of the wireless communication environment in which the terminal is located. .
  • the first threshold, the second threshold, the third threshold, the fourth threshold, the fifth threshold, the sixth threshold, the seventh threshold, the eighth threshold and the ninth threshold may be a terminal
  • the error threshold is determined based on positioning accuracy requirements or business scenarios, or it is the error threshold agreed in the protocol, or the error threshold indicated by the network side device, which is not specifically limited here.
  • the method before the terminal obtains the first information, the method further includes:
  • the terminal receives second indication information or third indication information from the network side device, wherein the second indication information is used to instruct the terminal to measure and/or report the first information, and the third The instruction information is used to instruct the terminal to perform performance supervision on the target AI network model.
  • the terminal may measure the first information and/or report the first information to the network side device according to the instructions of the second indication information. For example: the terminal measures and obtains the above-mentioned first information according to the second instruction information; or the terminal sends the pre-stored or received first information to the network side device according to the second instruction information; or the terminal obtains the above-mentioned third information according to the second instruction information. information, and sends the first information to the network side device; or, the terminal measures the above-mentioned first information according to the second instruction information, and determines based on the triggering of other instruction information or conditions, and the terminal determines the target based on the first information. Performance of AI network models. Wherein, when the terminal reports the first information to the network side device, the network side device can determine the performance of the target AI network model based on the received first information.
  • the terminal when the terminal receives the third indication information from the network side device, the terminal can determine the performance of the target AI network model based on the first information according to the instructions of the third indication information.
  • the performance supervision process of the target AI network model can be triggered based on the instruction information of the network side device.
  • the third instruction information includes identification information of the first performance supervision method, and the third instruction information is used to instruct the terminal to perform performance supervision on the target AI network model according to the first performance supervision method.
  • the network side device can recommend a performance supervision method to the terminal through the third indication information, for example: supervising the performance of the target AI network model based on the above-mentioned first threshold, second threshold, or third threshold.
  • the third indication information also includes second information, the second information is used to assist the target AI network Performance supervision of network models.
  • the above-mentioned second information may include thresholds used to assist performance supervision of the target AI network model, such as: first threshold, second threshold, third threshold, fourth threshold, fifth threshold, sixth threshold, third threshold. At least one of the seventh threshold, the eighth threshold, and the ninth threshold, and/or the second information may also include location information used to assist performance supervision of the target AI network model, for example: location information of PRU/TRP , or the location information of other terminals.
  • the network side device can dynamically configure the allowable error degree of the target AI network model through the above third indication information, and/or the network side device can provide data for the terminal to judge the performance of the target AI network model through the above third indication information. support.
  • the method before the terminal receives the second indication information or the third indication information from the network side device, the method further includes:
  • the terminal sends first request information to the network side device, where the first request information is used to request performance supervision of the target AI network model.
  • the first request information may request the network side device to perform performance supervision on the target AI network model.
  • the network side device may send second instruction information to the terminal based on the received first request information.
  • the second instruction information may Instruct the terminal to measure and report the first information to the network-side device; or, the first request information may request the network-side device to allow the terminal to perform performance supervision of the target AI network model, so that the network-side device may perform performance supervision on the target AI network model based on the received first request information.
  • the third instruction information may instruct the terminal to determine the performance of the target AI network model based on the measured first information; or the first request information may request that the target AI network model be processed.
  • Performance supervision, and the network side device decides to perform performance supervision on the target AI network model by the network side device or the terminal. In this way, the network side device can send the second instruction information or the third instruction information to the terminal based on the received first request information.
  • the terminal can trigger the performance supervision process of the target AI network model.
  • the first request information includes identification information of the second performance supervision method, and the first request information is used to request performance supervision of the target AI network model according to the second performance supervision method.
  • the terminal can recommend a performance supervision method to the network side device through the first request information, for example, supervising the performance of the target AI network model based on the above-mentioned first threshold, second threshold, or third threshold.
  • the method further includes:
  • the terminal receives fourth indication information from the network side device, where the fourth indication information is used to indicate the performance of the target AI network model.
  • the terminal can report the performance results to the network side device, so that the network side device can learn the performance of the target AI network model and take corresponding measures accordingly, such as:
  • the target AI network model fails, the target AI network model can be retrained and the retrained target AI network model can be delivered to the terminal.
  • the fifth indication information indicates that the target AI network model is invalid
  • the fifth indication information also indicates the cause of the failure of the target AI network model.
  • the reason for the failure of the target AI network model may correspond to the method of determining the performance of the target AI network model based on the first information.
  • the reason for the failure of the target AI network model may include: the first distance and the second distance. The difference between them is greater than or equal to the first threshold, the distance between the location of the terminal determined using the first method and the location of the terminal determined based on the target AI network model is greater than or equal to the second threshold, The distance between the first position and the position of the terminal determined based on the target AI network model is greater than or equal to the third threshold, etc., which will not be described again here.
  • the terminal can inform the network side device of the reason for the failure of the target AI network model through the fifth instruction information.
  • the network side device can take corresponding measures based on the reason, or when adjusting the target AI network model, it can Use this reason to determine how to adjust the target AI network model.
  • the terminal obtains first information, the first information is used to determine the performance of the target AI network model, and the target AI network model is used to locate the terminal; the terminal transmits information to the network side device Send the first information, or the terminal determines the performance of the target AI network model based on the first information.
  • the terminal can obtain the first information used to assist in determining the performance of the target AI network model, and report the first information to the network side device, so that the network side device determines the performance of the target AI network model based on the first information, or directly The terminal determines the performance of the target AI network model based on the first information.
  • the network-side device may be the network-side device 12 in the embodiment shown in Figure 1. Or other network side devices other than the network side device 12 listed in the embodiment as shown in Figure 1, which are not specifically limited here.
  • the performance supervision method of the AI network model executed by the network side device can be Includes the following steps:
  • Step 301 The network side device receives the first information from the terminal, and determines the performance of the target AI network model based on the first information, where the first information is used to determine the performance of the target AI network model, and the target AI The network model is used to locate the terminal.
  • Step 302 The network side device receives fifth indication information from the terminal, where the fifth indication information is used to indicate the performance of the target AI network model.
  • the performance supervision method of the AI network model executed by the network side device includes the above steps 301 and 302 as an example.
  • the AI executed by the network side device The performance supervision method of the network model may include only one of the above-mentioned steps 301 and 302.
  • the specific process please refer to the description in the terminal-side method embodiment as shown in Figure 2, which is not specifically limited here.
  • the first information includes at least one of the following:
  • M is a positive integer
  • the location information of the terminal is determined using a first method that does not include the positioning method corresponding to the target AI network model;
  • the error or confidence of the location information of the terminal determined based on the target AI network model
  • the change amplitude or rate of change of the terminal s channel measurement information
  • the distance information between the terminal and the positioning reference unit PRU or the transmission and reception node TRP is determined in a second way, and the second way does not include a way corresponding to the target AI network model;
  • the distance information between the terminal and other terminals determined using the second method is the distance information between the terminal and other terminals determined using the second method
  • the location information of the other terminals determined based on the target AI network model
  • the identification information of the PRU or TRP is the identification information of the PRU or TRP.
  • the network side device determines the performance of the target AI network model based on the first information, including at least one of the following:
  • the first distance is the terminal determined based on the motion state information.
  • the second distance is the position of the terminal in the first time unit and the position determined based on the target AI network model.
  • the distance between the positions of the terminals in the Mth time unit, M is greater than 1;
  • the target AI network model is invalid, wherein the first The position is the average or weighted average of the N positions of the terminal determined using the first method, and N is an integer greater than 1;
  • the third distance is the terminal determined by the second method.
  • the distance from the positioning reference unit PRU or the transmission reception node TRP, the fourth distance is the distance between the position of the terminal determined based on the target AI network model and the position of the PRU or TRP;
  • the difference between the fifth distance and the sixth distance is greater than or equal to the sixth threshold, it is determined that the target AI network model is invalid, wherein the fifth distance is the terminal determined by the second method.
  • the distance from other terminals, the sixth distance is the distance between the location of the terminal determined based on the target AI network model and the location of the other terminal determined based on the target AI network model;
  • the target AI network model is a network model used in a LOS scenario, and the LOS or NLOS indication information indicates that the LOS proportion of the terminal is less than or equal to the seventh threshold, it is determined that the target AI network model is invalid. ;
  • the target AI network model is a network model used in an NLOS scenario, and the LOS or NLOS indication information indicates that the NLOS proportion of the terminal is less than or equal to the eighth threshold, it is determined that the target AI network model is invalid. ;
  • the minimum error of the location information of the terminal determined based on the target AI network model is greater than or equal to the ninth threshold, it is determined that the target AI network model is invalid;
  • the channel measurement information of the terminal includes at least one of the following:
  • Channel state information includes: at least one of time domain channel state information, frequency domain channel state information, air domain channel state information, delay Doppler domain channel state information, and power delay spectrum;
  • Channel characteristic information which includes: Doppler frequency domain, first path delay, first path power, first path phase, first path angle, maximum H path delay, maximum H path power, maximum H path At least one of the phase and the angle of the maximum H diameter, H is an integer greater than or equal to 1;
  • Channel quality information includes: at least one of reference signal received power RSRP, reference signal received quality RSRQ, signal-to-noise ratio SNR, and signal-to-interference plus noise ratio SINR.
  • the method before the network side device receives the first information from the terminal or receives the fifth indication information from the terminal, the method further includes:
  • the network side device sends second indication information or third indication information to the terminal, where the second indication information is used to instruct the terminal to measure and/or report the first information, and the third indication The information is used to instruct the terminal to perform performance supervision on the target AI network model.
  • the third instruction information includes identification information of the first performance supervision method, and the third instruction information is used to instruct the terminal to perform performance supervision on the target AI network model according to the first performance supervision method.
  • the third indication information also includes second information, and the second information is used to assist performance supervision of the target AI network model.
  • the method before the network side device sends the second indication information or the third indication information to the terminal, the method further includes:
  • the network side device receives first request information from the terminal, where the first request information is used to request performance supervision of the target AI network model.
  • the first request information includes identification information of the second performance supervision method, and the first request information is used to request performance supervision of the target AI network model according to the second performance supervision method.
  • the method further includes:
  • the network side device sends fourth indication information to the terminal, where the fourth indication information is used to indicate the target Performance of AI network models.
  • the fourth indication information indicates that the target AI network model is invalid
  • the fourth indication information also indicates the reason why the target AI network model is invalid.
  • the fifth indication information indicates that the target AI network model is invalid
  • the fifth indication information also indicates the reason why the target AI network model is invalid.
  • the performance supervision method of the AI network model executed by the network side device corresponds to the performance supervision method of the AI network model executed by the terminal, and the terminal and the network side device respectively execute the performance supervision method of their respective AI network models.
  • the steps in the above can promptly detect the low positioning performance of the target AI network model, and then take appropriate measures to reduce the probability of low wireless communication performance and application experience caused by the low positioning performance of the target AI network model.
  • the execution subject may be the performance supervision device of the AI network model.
  • the performance supervision device of the AI network model performs the performance supervision method of the AI network model as an example to illustrate the performance supervision device of the AI network model provided by the embodiment of the present application.
  • An embodiment of the present application provides a performance monitoring device for an AI network model, which can be a device in a terminal.
  • the performance monitoring device 400 for the AI network model can include the following modules:
  • the acquisition module 401 is used to acquire first information, the first information is used to determine the performance of the target AI network model, and the target AI network model is used to locate the terminal;
  • the first sending module 402 is used to send the first information to the network side device.
  • the first determining module 403 is used to determine the target AI network model according to the first information. performance.
  • the performance monitoring device 400 of the AI network model includes both the first sending module 402 and the first determining module 403.
  • the performance of the AI network model The supervision device 400 may include only one of the first sending module 402 and the first determining module 403, which is not specifically limited here.
  • the first information includes at least one of the following:
  • M is a positive integer
  • the location information of the terminal is determined using a first method that does not include the positioning method corresponding to the target AI network model;
  • the error or confidence of the location information of the terminal determined based on the target AI network model
  • the change amplitude or rate of change of the terminal s channel measurement information
  • the distance information between the terminal and the positioning reference unit PRU or the transmission and reception node TRP is determined in a second way, and the second way does not include a way corresponding to the target AI network model;
  • the distance information between the terminal and other terminals determined using the second method is the distance information between the terminal and other terminals determined using the second method
  • the location information of the other terminals determined based on the target AI network model
  • the identification information of the PRU or TRP is the identification information of the PRU or TRP.
  • the first determination module 403 is used to perform at least one of the following:
  • the first distance is the terminal determined based on the motion state information.
  • the second distance is the position of the terminal in the first time unit and the position determined based on the target AI network model.
  • the distance between the positions of the terminals in the Mth time unit, M is greater than 1;
  • the target AI network model is invalid, wherein the first The position is the average or weighted average of the N positions of the terminal determined using the first method, and N is an integer greater than 1;
  • the third distance is the terminal determined by the second method.
  • the distance from the positioning reference unit PRU or the transmission reception node TRP, the fourth distance is the distance between the position of the terminal determined based on the target AI network model and the position of the PRU or TRP;
  • the difference between the fifth distance and the sixth distance is greater than or equal to the sixth threshold, it is determined that the target AI network model is invalid, wherein the fifth distance is the terminal determined by the second method.
  • the distance from other terminals, the sixth distance is the distance between the location of the terminal determined based on the target AI network model and the location of the other terminal determined based on the target AI network model;
  • the target AI network model is a network model used in a LOS scenario, and the LOS or NLOS indication information indicates that the LOS proportion of the terminal is less than or equal to the seventh threshold, it is determined that the target AI network model is invalid. ;
  • the target AI network model is a network model used in an NLOS scenario, and the LOS or NLOS indication information indicates that the NLOS proportion of the terminal is less than or equal to the eighth threshold, it is determined that the target AI network model is invalid. ;
  • the minimum error of the location information of the terminal determined based on the target AI network model is greater than or equal to the ninth threshold, it is determined that the target AI network model is invalid;
  • the channel measurement information of the terminal includes at least one of the following:
  • Channel state information includes: at least one of time domain channel state information, frequency domain channel state information, air domain channel state information, delay Doppler domain channel state information, and power delay spectrum;
  • Channel characteristic information which includes: Doppler frequency domain, first path delay, first path power, first path phase, first path angle, maximum H path delay, maximum H path power, maximum H path At least one of the phase and the angle of the maximum H diameter, H is an integer greater than or equal to 1;
  • Channel quality information includes: at least one of reference signal received power RSRP, reference signal received quality RSRQ, signal-to-noise ratio SNR, and signal-to-interference plus noise ratio SINR.
  • the AI network model performance monitoring device 400 also includes:
  • a first receiving module configured to receive second indication information or third indication information from the network side device, where the second indication information is used to instruct the terminal to measure and/or report the first information,
  • the third instruction information is used to instruct the terminal to perform performance supervision on the target AI network model.
  • the third instruction information includes identification information of the first performance supervision method, and the third instruction information is used to instruct the terminal to perform performance supervision on the target AI network model according to the first performance supervision method.
  • the third indication information also includes second information, and the second information is used to assist performance supervision of the target AI network model.
  • the AI network model performance monitoring device 400 also includes:
  • the second sending module is configured to send first request information to the network side device, where the first request information is used to request performance supervision of the target AI network model.
  • the first request information includes identification information of the second performance supervision method, and the first request information is used to request performance supervision of the target AI network model according to the second performance supervision method.
  • the AI network model performance monitoring device 400 also includes:
  • the second receiving module is configured to receive fourth indication information from the network side device, where the fourth indication information is used to indicate the performance of the target AI network model.
  • the fourth indication information indicates that the target AI network model is invalid
  • the fourth indication information also indicates the reason why the target AI network model is invalid.
  • the AI network model performance monitoring device 400 also includes:
  • the third sending module is configured to send fifth indication information to the network side device, where the fifth indication information is used to indicate the performance of the target AI network model.
  • the fifth indication information indicates that the target AI network model is invalid
  • the fifth indication information also indicates the reason why the target AI network model is invalid.
  • the performance monitoring device 400 of the AI network model provided by the embodiment of the present application can implement various processes implemented by the terminal in the method embodiment shown in Figure 2, and can achieve the same beneficial effects. To avoid duplication, they will not be described again here.
  • Another performance monitoring device for an AI network model provided by an embodiment of the present application may be a device in a network-side device.
  • a performance monitoring device 500 for an AI network model may include the following modules:
  • the third receiving module 501 is used to receive first information from the terminal, where the first information is used to determine the performance of the target AI network model, and the target AI network model is used to locate the terminal;
  • the second determination module 502 is used to determine the performance of the target AI network model according to the first information.
  • another performance monitoring device 600 of an AI network model may include the following modules:
  • the fourth receiving module 601 is configured to receive fifth indication information from the terminal, where the fifth indication information is used to indicate the performance of the target AI network model.
  • the network side device may also include the above-mentioned third receiving module 501, the second determining module 502 and the fourth receiving module 601 at the same time. As shown in Figure 5 or Figure 6, they are only two possible AI networks. Examples of model performance monitoring devices.
  • the first information includes at least one of the following:
  • M is a positive integer
  • the location information of the terminal is determined using a first method that does not include the positioning method corresponding to the target AI network model;
  • the error or confidence of the location information of the terminal determined based on the target AI network model
  • the change amplitude or rate of change of the terminal s channel measurement information
  • the distance information between the terminal and the positioning reference unit PRU or the transmission and reception node TRP is determined in a second way, and the second way does not include a way corresponding to the target AI network model;
  • the distance information between the terminal and other terminals determined using the second method is the distance information between the terminal and other terminals determined using the second method
  • the location information of the other terminals determined based on the target AI network model
  • the identification information of the PRU or TRP is the identification information of the PRU or TRP.
  • the second determination module 502 is used to perform at least one of the following:
  • the first distance is the terminal determined based on the motion state information.
  • the second distance is the position of the terminal in the first time unit and the position determined based on the target AI network model.
  • the distance between the positions of the terminals in the Mth time unit, M is greater than 1;
  • the target AI network model is invalid, wherein the first The position is the average or weighted average of the N positions of the terminal determined using the first method, and N is an integer greater than 1;
  • the third distance is the terminal determined by the second method.
  • the distance from the positioning reference unit PRU or the transmission reception node TRP, the fourth distance is the distance between the position of the terminal determined based on the target AI network model and the position of the PRU or TRP;
  • the difference between the fifth distance and the sixth distance is greater than or equal to the sixth threshold, it is determined that the target AI network model is invalid, wherein the fifth distance is the terminal determined by the second method.
  • the distance from other terminals, the sixth distance is the distance between the location of the terminal determined based on the target AI network model and the location of the other terminal determined based on the target AI network model;
  • the target AI network model is a network model used in a LOS scenario, and the LOS or NLOS indication information indicates that the LOS proportion of the terminal is less than or equal to the seventh threshold, it is determined that the target AI network model is invalid. ;
  • the target AI network model is a network model used in an NLOS scenario, and the LOS or NLOS indication information indicates that the NLOS proportion of the terminal is less than or equal to the eighth threshold, it is determined that the target AI network model is invalid. ;
  • the minimum error of the location information of the terminal determined based on the target AI network model is greater than or equal to the ninth threshold, it is determined that the target AI network model is invalid;
  • the channel measurement information of the terminal includes at least one of the following:
  • Channel state information includes: at least one of time domain channel state information, frequency domain channel state information, air domain channel state information, delay Doppler domain channel state information, and power delay spectrum;
  • Channel characteristic information which includes: Doppler frequency domain, first path delay, first path power, first path phase, first path angle, maximum H path delay, maximum H path power, maximum H path At least one of the phase and the angle of the maximum H diameter, H is an integer greater than or equal to 1;
  • Channel quality information includes: at least one of reference signal received power RSRP, reference signal received quality RSRQ, signal-to-noise ratio SNR, and signal-to-interference plus noise ratio SINR.
  • the performance monitoring device 500 of the AI network model or the performance monitoring device 600 of the AI network model also includes:
  • the fourth sending module is configured to send second indication information or third indication information to the terminal, wherein the second indication information is used to instruct the terminal to measure and/or report the first information, and the third indication information is used to instruct the terminal to measure and/or report the first information.
  • the third instruction information is used to instruct the terminal to perform performance supervision on the target AI network model.
  • the third instruction information includes identification information of the first performance supervision method, and the third instruction information is used to instruct the terminal to perform performance supervision on the target AI network model according to the first performance supervision method.
  • the third indication information also includes second information, and the second information is used to assist performance supervision of the target AI network model.
  • the performance monitoring device 500 of the AI network model or the performance monitoring device 600 of the AI network model also includes:
  • the fifth receiving module is configured to receive first request information from the terminal, where the first request information is used to request performance supervision of the target AI network model.
  • the first request information includes identification information of the second performance supervision method, and the first request information is used to request performance supervision of the target AI network model according to the second performance supervision method.
  • the performance monitoring device 500 of the AI network model or the performance monitoring device 600 of the AI network model also includes:
  • the fifth sending module is configured to send fourth indication information to the terminal, where the fourth indication information is used to indicate the performance of the target AI network model.
  • the fourth indication information indicates that the target AI network model is invalid
  • the fourth indication information also indicates the reason why the target AI network model is invalid.
  • the fifth indication information indicates that the target AI network model is invalid
  • the fifth indication information also indicates the reason why the target AI network model is invalid.
  • the performance supervision device 500 or the performance supervision device 600 of the AI network model provided by the embodiment of the present application can implement each process implemented by the network side device in the method embodiment as shown in Figure 3, and can achieve the same beneficial effects. , to avoid repetition, will not be repeated here.
  • the performance monitoring device of the AI network model in the embodiment of the present application may be an electronic device, such as an electronic device with an operating system, or may be a component in the electronic device, such as an integrated circuit or chip.
  • the electronic device may be a terminal or other devices other than the terminal.
  • terminals may include but are not limited to the types of terminals 11 listed above, and other devices may be servers, network attached storage (Network Attached Storage, NAS), etc., which are not specifically limited in the embodiment of this application.
  • the performance supervision device of the AI network model provided by the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 2 or Figure 3, and achieve the same technical effect. To avoid duplication, it will not be described again here.
  • this embodiment of the present application also provides a communication device 700, which includes a processor 701 and a memory 702.
  • the memory 702 stores programs or instructions that can be run on the processor 701, for example.
  • the communication device 700 is a terminal, when the program or instruction is executed by the processor 701, each step of the method embodiment shown in Figure 2 is implemented, and the same technical effect can be achieved.
  • the communication device 700 is a network-side device, when the program or instruction is executed by the processor 701, each step of the method embodiment shown in Figure 3 is implemented, and the same technical effect can be achieved. To avoid duplication, the details will not be described here.
  • An embodiment of the present application also provides a terminal, including a processor and a communication interface.
  • the communication interface is used to obtain first information.
  • the first information is used to determine the performance of a target AI network model.
  • the target AI network model is For locating the terminal; the communication interface is also used to send the first information to the network side device or the processor is used to determine the performance of the target AI network model based on the first information.
  • FIG. 8 is a schematic diagram of the hardware structure of a terminal that implements an embodiment of the present application.
  • the terminal 800 includes but is not limited to: a radio frequency unit 801, a network module 802, an audio output unit 803, an input unit 804, a sensor 805, a display unit 806, a user input unit 807, an interface unit 808, a memory 809, a processor 810, etc. At least some parts.
  • the terminal 800 may also include a power supply (such as a battery) that supplies power to various components.
  • the power supply may be logically connected to the processor 810 through a power management system, thereby managing charging, discharging, and power consumption through the power management system. Management and other functions.
  • the terminal structure shown in FIG. 8 does not constitute a limitation on the terminal.
  • the terminal may include more or fewer components than shown in the figure, or some components may be combined or arranged differently, which will not be described again here.
  • the input unit 804 may include a graphics processing unit (Graphics Processing Unit, GPU) 8041 and a microphone 8042.
  • the graphics processor 8041 is responsible for the image capture device (GPU) in the video capture mode or the image capture mode. Process the image data of still pictures or videos obtained by cameras (such as cameras).
  • the display unit 806 may include a display panel 8061, which may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like.
  • the user input unit 807 includes a touch panel 8071 and at least one of other input devices 8072 .
  • Touch panel 8071 also known as touch screen.
  • the touch panel 8071 may include two parts: a touch detection device and a touch controller.
  • Other input devices 8072 may include but are not limited to physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be described again here.
  • the radio frequency unit 801 after receiving downlink data from the network side device, the radio frequency unit 801 can transmit it to the processor 810 for processing; in addition, the radio frequency unit 801 can send uplink data to the network side device.
  • the radio frequency unit 801 includes, but is not limited to, an antenna, amplifier, transceiver, coupler, low noise amplifier, duplexer, etc.
  • Memory 809 may be used to store software programs or instructions as well as various data.
  • the memory 809 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, Image playback function, etc.) etc.
  • memory 809 may include volatile memory or non-volatile memory, or memory 809 may include both volatile and non-volatile memory.
  • non-volatile memory can be read-only memory (Read-Only Memory, ROM), programmable read-only memory (Programmable ROM, PROM), erasable programmable read-only memory (Erasable PROM, EPROM), electrically removable memory. Erase programmable read-only memory (Electrically EPROM, EEPROM) or flash memory.
  • Volatile memory can be random access memory (Random Access Memory, RAM), static random access memory (Static RAM, SRAM), dynamic random access memory (Dynamic RAM, DRAM), synchronous dynamic random access memory (Synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (Double Data Rate SDRAM, DDRSDRAM), enhanced synchronous dynamic random access memory (Enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (Synch link DRAM) , SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DRRAM).
  • RAM Random Access Memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • DRAM synchronous dynamic random access memory
  • SDRAM double data rate synchronous dynamic random access memory
  • Double Data Rate SDRAM Double Data Rate SDRAM
  • DDRSDRAM double data rate synchronous dynamic random access memory
  • Enhanced SDRAM, ESDRAM enhanced synchronous dynamic random access memory
  • Synch link DRAM synchronous link dynamic random access memory
  • SLDRAM direct memory bus
  • the processor 810 may include one or more processing units; optionally, the processor 810 integrates an application processor and a modem processor, where the application processor mainly handles operations related to the operating system, user interface, application programs, etc., Modem processors mainly process wireless communication signals, such as baseband processors. It can be understood that the above modem The processor may not be integrated into the processor 810.
  • the radio frequency unit 801 is used to obtain first information, the first information is used to determine the performance of the target AI network model, and the target AI network model is used to locate the terminal;
  • the radio frequency unit 801 is also configured to send the first information to the network side device, or the processor 810 is configured to determine the performance of the target AI network model based on the first information.
  • the first information includes at least one of the following:
  • M is a positive integer
  • the location information of the terminal is determined using a first method that does not include the positioning method corresponding to the target AI network model;
  • the error or confidence of the location information of the terminal determined based on the target AI network model
  • the change amplitude or rate of change of the terminal s channel measurement information
  • the distance information between the terminal and the positioning reference unit PRU or the transmission and reception node TRP is determined in a second way, and the second way does not include a way corresponding to the target AI network model;
  • the distance information between the terminal and other terminals determined using the second method is the distance information between the terminal and other terminals determined using the second method
  • the location information of the other terminals determined based on the target AI network model
  • the identification information of the PRU or TRP is the identification information of the PRU or TRP.
  • the determination of the performance of the target AI network model based on the first information performed by the processor 810 includes at least one of the following:
  • the first distance is the terminal determined based on the motion state information.
  • the second distance is the position of the terminal in the first time unit and the position determined based on the target AI network model.
  • the distance between the positions of the terminals in the Mth time unit, M is greater than 1;
  • the target AI network model is invalid, wherein the first The position is the average or weighted average of the N positions of the terminal determined using the first method, and N is an integer greater than 1;
  • the third distance is the terminal determined by the second method.
  • the fourth distance is the distance between the location of the terminal determined based on the target AI network model and the location of the PRU or TRP;
  • the difference between the fifth distance and the sixth distance is greater than or equal to the sixth threshold, it is determined that the target AI network model is invalid, wherein the fifth distance is the terminal determined by the second method.
  • the distance from other terminals, the sixth distance is the distance between the location of the terminal determined based on the target AI network model and the location of the other terminal determined based on the target AI network model;
  • the target AI network model is a network model used in a LOS scenario, and the LOS or NLOS indication information indicates that the LOS proportion of the terminal is less than or equal to the seventh threshold, it is determined that the target AI network model is invalid. ;
  • the target AI network model is a network model used in an NLOS scenario, and the LOS or NLOS indication information indicates that the NLOS proportion of the terminal is less than or equal to the eighth threshold, it is determined that the target AI network model is invalid. ;
  • the minimum error of the location information of the terminal determined based on the target AI network model is greater than or equal to the ninth threshold, it is determined that the target AI network model is invalid;
  • the channel measurement information of the terminal includes at least one of the following:
  • Channel state information includes: at least one of time domain channel state information, frequency domain channel state information, air domain channel state information, delay Doppler domain channel state information, and power delay spectrum;
  • Channel characteristic information which includes: Doppler frequency domain, first path delay, first path power, first path phase, first path angle, maximum H path delay, maximum H path power, maximum H path At least one of the phase and the angle of the maximum H diameter, H is an integer greater than or equal to 1;
  • Channel quality information includes: at least one of reference signal received power RSRP, reference signal received quality RSRQ, signal-to-noise ratio SNR, and signal-to-interference plus noise ratio SINR.
  • the radio frequency unit 801 is also configured to receive second indication information or third indication information from the network side device, wherein the second indication information is used to indicate the The terminal measures and/or reports the first information, and the third instruction information is used to instruct the terminal to perform performance supervision on the target AI network model.
  • the third instruction information includes identification information of the first performance supervision method, and the third instruction information is used to instruct the terminal to perform performance supervision on the target AI network model according to the first performance supervision method.
  • the third indication information also includes second information, and the second information is used to assist performance supervision of the target AI network model.
  • the radio frequency unit 801 before performing the reception of the second indication information or the third indication information from the network side device, the radio frequency unit 801 is also configured to send first request information to the network side device.
  • the first request The information is used to request performance supervision of the target AI network model.
  • the first request information includes identification information of the second performance supervision method, and the first request information is used to request performance supervision of the target AI network model according to the second performance supervision method.
  • the radio frequency unit 801 is further configured to receive fourth indication information from the network side device, where the fourth indication information is used to indicate the The performance of the target AI network model.
  • the fourth indication information indicates that the target AI network model is invalid
  • the fourth indication information also indicates the reason why the target AI network model is invalid.
  • the radio frequency unit 801 is further configured to send fifth indication information to the network side device, and the fifth The indication information is used to indicate the performance of the target AI network model.
  • the fifth indication information indicates that the target AI network model is invalid
  • the fifth indication information also indicates the reason why the target AI network model is invalid.
  • the terminal 800 provided by the embodiment of the present application can execute each process performed by each module in the performance monitoring device 400 of the AI network model as shown in Figure 4, and can achieve the same beneficial effects. To avoid duplication, they will not be described again here. .
  • Embodiments of the present application also provide a network side device, including a processor and a communication interface.
  • the communication interface is used to receive first information from a terminal.
  • the processor is used to determine the target AI network model based on the first information. Performance, wherein the first information is used to determine the performance of the target AI network model, and the target AI network model is used to locate the terminal; or the communication interface is used to receive fifth indication information from the terminal , wherein the fifth indication information is used to indicate the performance of the target AI network model.
  • This network-side device embodiment corresponds to the above-mentioned network-side device method embodiment.
  • Each implementation process and implementation manner of the above-mentioned method embodiment can be applied to this network-side device embodiment, and can achieve the same technical effect.
  • the embodiment of the present application also provides a network side device.
  • the network side device 900 includes: an antenna 901, a radio frequency device 902, a baseband device 903, a processor 904 and a memory 905.
  • Antenna 901 is connected to radio frequency device 902.
  • the radio frequency device 902 receives information through the antenna 901 and sends the received information to the baseband device 903 for processing.
  • the baseband device 903 processes the information to be sent and sends it to the radio frequency device 902.
  • the radio frequency device 902 processes the received information and then sends it out through the antenna 901.
  • the method performed by the network side device in the above embodiment can be implemented in the baseband device 903, which includes a baseband processor.
  • the baseband device 903 may include, for example, at least one baseband board on which multiple chips are disposed, as shown in FIG. 9 .
  • One of the chips is, for example, a baseband processor, which is connected to the memory 905 through a bus interface to call the Program to perform the network device operations shown in the above method embodiments.
  • the network side device may also include a network interface 906, which is, for example, a Common Public Radio Interface (CPRI).
  • CPRI Common Public Radio Interface
  • the network side device 900 in this embodiment of the present invention also includes: instructions or programs stored in the memory 905 and executable on the processor 904.
  • the processor 904 calls the instructions or programs in the memory 905 to execute Figure 5 or Figure 6 Place It shows the execution method of each module and achieves the same technical effect. To avoid duplication, it will not be repeated here.
  • Embodiments of the present application also provide a readable storage medium.
  • Programs or instructions are stored on the readable storage medium.
  • the program or instructions are executed by a processor, each process of the method embodiment shown in Figure 2 or Figure 3 is implemented. , and can achieve the same technical effect, so to avoid repetition, they will not be described again here.
  • the processor is the processor in the terminal described in the above embodiment.
  • the readable storage medium includes computer readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disk or optical disk, etc.
  • An embodiment of the present application further provides a chip.
  • the chip includes a processor and a communication interface.
  • the communication interface is coupled to the processor.
  • the processor is used to run programs or instructions.
  • the implementation is as shown in Figure 2 or Figure 3. Each process of the method embodiment is shown, and the same technical effect can be achieved. To avoid repetition, the details will not be described here.
  • chips mentioned in the embodiments of this application may also be called system-on-chip, system-on-a-chip, system-on-chip or system-on-chip, etc.
  • the embodiment of the present application further provides a computer program/program product, the computer program/program product is stored in a storage medium, and the computer program/program product is executed by at least one processor to implement Figure 2 or Figure 3
  • a computer program/program product is stored in a storage medium
  • the computer program/program product is executed by at least one processor to implement Figure 2 or Figure 3
  • Embodiments of the present application also provide a communication system, including: a terminal and a network side device.
  • the terminal can be used to perform the steps of the performance supervision method of the AI network model as shown in Figure 2.
  • the network side device can be used to perform The steps of the performance supervision method of the AI network model are shown in Figure 3.
  • the methods of the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is better. implementation.
  • the technical solution of the present application can be embodied in the form of a computer software product that is essentially or contributes to the existing technology.
  • the computer software product is stored in a storage medium (such as ROM/RAM, disk , CD), including several instructions to cause a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of this application.

Landscapes

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

Abstract

La présente demande se rapporte au domaine technique des communications, et concerne un procédé et un appareil de supervision de performance pour un modèle de réseau d'IA, et un dispositif de communication. Le procédé de supervision de performance pour un modèle de réseau d'IA dans des modes de réalisation de la présente demande comprend les étapes suivantes : un terminal acquiert des premières informations, les premières informations étant utilisées pour déterminer les performances d'un modèle de réseau d'IA cible, et le modèle de réseau d'IA cible étant utilisé pour déterminer la position du terminal ; et le terminal envoie les premières informations à un dispositif côté réseau, ou le terminal détermine les performances du modèle de réseau d'IA cible selon les premières informations.
PCT/CN2023/109767 2022-08-03 2023-07-28 Procédé et appareil de supervision de performance pour modèle de réseau d'ia, et dispositif de communication Ceased WO2024027576A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210926618.5 2022-08-03
CN202210926618.5A CN117560708A (zh) 2022-08-03 2022-08-03 一种智能ai网络模型的性能监督方法、装置和通信设备

Publications (1)

Publication Number Publication Date
WO2024027576A1 true WO2024027576A1 (fr) 2024-02-08

Family

ID=89815230

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/109767 Ceased WO2024027576A1 (fr) 2022-08-03 2023-07-28 Procédé et appareil de supervision de performance pour modèle de réseau d'ia, et dispositif de communication

Country Status (2)

Country Link
CN (1) CN117560708A (fr)
WO (1) WO2024027576A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025231594A1 (fr) * 2024-05-06 2025-11-13 Nec Corporation Dispositif terminal, procédé et support lisible par ordinateur pour une communication

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106604392A (zh) * 2016-11-22 2017-04-26 上海斐讯数据通信技术有限公司 一种基于双向信号强度数据的wifi定位方法及服务器
CN107770860A (zh) * 2017-10-12 2018-03-06 贵州大学 一种基于神经网络改进算法的WiFi室内定位系统及定位方法
CN113543305A (zh) * 2020-04-22 2021-10-22 维沃移动通信有限公司 定位方法、通信设备和网络设备
CN114363921A (zh) * 2020-10-13 2022-04-15 维沃移动通信有限公司 Ai网络参数的配置方法和设备
CN114521012A (zh) * 2020-11-18 2022-05-20 维沃移动通信有限公司 定位方法、装置、终端设备、基站及位置管理服务器

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106604392A (zh) * 2016-11-22 2017-04-26 上海斐讯数据通信技术有限公司 一种基于双向信号强度数据的wifi定位方法及服务器
CN107770860A (zh) * 2017-10-12 2018-03-06 贵州大学 一种基于神经网络改进算法的WiFi室内定位系统及定位方法
CN113543305A (zh) * 2020-04-22 2021-10-22 维沃移动通信有限公司 定位方法、通信设备和网络设备
CN114363921A (zh) * 2020-10-13 2022-04-15 维沃移动通信有限公司 Ai网络参数的配置方法和设备
CN114521012A (zh) * 2020-11-18 2022-05-20 维沃移动通信有限公司 定位方法、装置、终端设备、基站及位置管理服务器

Also Published As

Publication number Publication date
CN117560708A (zh) 2024-02-13

Similar Documents

Publication Publication Date Title
EP4422248A1 (fr) Procédé de demande de modèle, procédé de traitement de demande de modèle et dispositif associé
US20240314728A1 (en) Positioning method and communication device
WO2023143572A1 (fr) Procédé de positionnement basé sur un modèle d'intelligence artificielle (ia), et dispositif de communication
US20240259988A1 (en) Positioning Method, Terminal, and Network Side Device
CN116234000A (zh) 定位方法及通信设备
WO2023040885A1 (fr) Procédé de sélection de paramètre, procédé de configuration de paramètre, terminal et dispositif côté réseau
US20250227507A1 (en) Ai model processing method and apparatus, and communication device
WO2023103911A1 (fr) Procédé et appareil de mesure, dispositif et support de stockage
WO2023072239A1 (fr) Procédé et appareil de prédiction de canal, dispositif côté réseau et terminal
WO2023179617A1 (fr) Procédé et appareil de localisation, terminal et dispositif côté réseau
WO2023179540A1 (fr) Procédé et appareil de prédiction de canal, et dispositif de communication sans fil
WO2024027576A1 (fr) Procédé et appareil de supervision de performance pour modèle de réseau d'ia, et dispositif de communication
WO2023185865A1 (fr) Procédé et appareil de rétroaction de validation de modèle, terminal et dispositif côté réseau
WO2023174253A1 (fr) Procédé et dispositif de traitement de modèle d'ia
WO2024093997A1 (fr) Procédé et appareil de détermination d'applicabilité de modèle, et dispositif de communication
WO2024083004A1 (fr) Procédé de configuration de modèle d'ia, terminal et dispositif côté réseau
CN118282899A (zh) 功能性生命周期管理的模型监测方法、装置、通信设备、系统及存储介质
WO2023174325A1 (fr) Procédé et dispositif de traitement de modèle d'ia
WO2023155839A1 (fr) Procédé et appareil d'apprentissage en ligne pour un modèle d'ia, ainsi que dispositif de communication et support de stockage lisible
CN117676687A (zh) 测量反馈处理方法、装置、终端及网络侧设备
CN120021208A (zh) 模型确定方法、装置及通信设备
WO2025140432A1 (fr) Procédé et appareil de création de compte-rendu d'informations
WO2024208167A1 (fr) Procédé de traitement d'informations, appareil de traitement d'informations, terminal et dispositif côté réseau
WO2024230626A1 (fr) Procédé et appareil de gestion de modèle, et dispositif de communication
CN119938459A (zh) 模型性能监督方法、装置及设备

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: 23849284

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: 23849284

Country of ref document: EP

Kind code of ref document: A1