WO2025228294A1 - Radio map acquisition method, and apparatus - Google Patents

Abstract

Disclosed in the present application are a radio map acquisition method and an apparatus. The method comprises: a fourth device acquires task information, the task information corresponding to a plurality of first tasks; and then the fourth device determines one or more first radio maps on the basis of the task information, the first tasks having a mapping relationship with the first radio maps. According to the embodiments of the present application, by establishing the mapping relationship between the first tasks and the first radio maps, the radio maps can be acquired on the premise of low storage and processing overhead so as to execute a plurality of tasks, thereby outputting multifunctional radio information.

Description

Radio map acquisition method and device

This application claims priority to Chinese Patent Application No. 202410537250.2, filed on April 29, 2024, entitled "Method and Apparatus for Obtaining Radio Maps", the entire contents of which are incorporated herein by reference.

Technical Field

This application relates to the field of wireless communication technology, and in particular to a method and apparatus for acquiring radio maps.

Background Technology

Radio frequency (RF) maps reflect parameter values at various locations within a wireless network, such as channel parameters, communication performance parameters, or aggregated characteristics of the wireless environment. Common radio maps include channel gain maps, received signal strength maps, and power spectral density maps. Radio maps are widely used in wireless communication and networking, including network planning, interference control, power control, resource allocation, handover management, multi-hop routing, dynamic spectrum access, and cognitive radio network tasks.

Existing radio maps are generally single-function radio maps, meaning their output is a specific radio message. Alternatively, multi-layer radio maps can be built upon existing single-function radio maps. Multi-layer radio maps consist of multiple "layers," each capable of outputting different radio messages. While this approach allows for the final output of various radio messages, it requires establishing a mapping between the radio messages (input) and the radio map to obtain the multi-layered radio map. Given the wide variety of radio messages, the overhead of building and storing the corresponding mapping is significant.

Summary of the Invention

This application provides a radio map acquisition method and apparatus that can acquire radio maps to perform multiple tasks with low storage and processing overhead, and achieve multifunctional radio information output.

In a first aspect, this application provides a method for acquiring radio maps. The method includes: acquiring task information, where the task information corresponds to multiple first tasks; and determining one or more first radio maps based on the task information, wherein there is a mapping relationship between the first tasks and the first radio maps. The solution described in the first aspect can be executed by a first device, which can be a communication device, a module within the communication device (such as a chip system), or a logical node, logical module, or software capable of implementing all or part of the functions of the communication device; there is no limitation in this regard.

From a technical perspective, this embodiment establishes a mapping relationship between first tasks and first radio maps. Since the number of first tasks is necessarily less than the number of complex radio information types, the construction cost and storage overhead of the mapping relationship between first tasks and first radio maps are also lower. Furthermore, based on the established mapping relationship, one or more first radio maps corresponding to multiple first tasks described by task information can be quickly determined, thereby invoking multiple first radio maps to execute multiple first tasks. In summary, this method reduces the cost of implementing multiple functions using radio maps while improving implementation efficiency.

In one feasible implementation, determining one or more first radio maps based on task information includes: sending a first request message to a first device, the first request message being used to request the acquisition of one or more first radio maps corresponding to the task information; and receiving a first response message from the first device, the first response message indicating one or more first radio maps.

In this embodiment, a task planner is deployed on a radio map server (first device). The radio map server determines multiple first tasks corresponding to the task information, and then determines one or more first radio maps corresponding to the multiple first tasks based on the mapping relationship between the first tasks and first radio maps stored in its own database. Because the radio map server has powerful processing capabilities and stores the mapping relationship between all second tasks (including first tasks) and first radio maps, this process ensures that one or more first radio maps corresponding to the task information are determined in the most efficient and accurate manner.

In one feasible implementation, determining one or more first radio maps based on mission information includes: determining a plurality of first missions based on the mission information; and determining one or more first radio maps based on the plurality of first missions.

In one feasible implementation, determining multiple first tasks based on task information includes: sending a second request message to a second device, the second request message being used to request the acquisition of multiple first tasks corresponding to the task information; and receiving a second response message from the second device, the second response message indicating multiple first tasks.

In this embodiment, the task planner is deployed on a third-party server (second device). The third-party server determines multiple first tasks corresponding to the task information and feeds these first tasks back to the radio map user. The radio map user then determines one or more first radio maps corresponding to the multiple first tasks based on their stored mapping relationships or through the radio map server. This task planning process, executed by the third-party server, reduces the processing power consumed by the radio map user or the radio map server, thereby minimizing the impact of the task planning process on other services of the radio map user or the radio map server.

In one feasible implementation, multiple first tasks are determined based on task information, including: inputting the task information vector corresponding to the task information into a first model for processing to obtain multiple first tasks, wherein the first model is used to perform classification planning for the first tasks.

In one feasible implementation, multiple first tasks are determined based on task information, including: inputting task information, prompt information, and a task information database into a second model for processing to obtain multiple first tasks. The second model is used to retrieve the first tasks, and the prompt information is used to indicate that the first task corresponding to the task information is determined by searching the task information database.

In this embodiment, a task planner is deployed on a radio map user (fourth device). The radio map user determines multiple first tasks corresponding to the task information, and the radio map server determines one or more first radio maps corresponding to the multiple first tasks based on the mapping relationship between the first tasks and first radio maps stored in its own database. During this process, the radio map user does not need to perform any external transmission interaction in determining the first radio maps, improving the efficiency of determining the first radio maps while ensuring the reliability of the process. Furthermore, when the mapping relationship between the third tasks and first radio maps stored in the radio map user's own database does not include the first tasks, the radio map user can obtain the first radio map corresponding to the first task from the radio map server, further ensuring the feasibility of determining the first radio maps.

In one feasible implementation, one or more first radio maps determined based on a plurality of first tasks include: determining one or more first radio maps corresponding to a plurality of first tasks based on a stored mapping relationship between first tasks and first radio maps.

In one feasible implementation, one or more first radio maps determined based on multiple first tasks include: sending a third request message to a first device, the third request message being used to request the acquisition of one or more first radio maps corresponding to multiple first tasks, the first device including a mapping relationship between second tasks and first radio maps, the second task including multiple first tasks; and receiving a third response message from the first device, the third response message indicating one or more first radio maps corresponding to multiple first tasks.

In one feasible implementation, before determining the first radio map based on mission information, the method further includes aligning a second mission with the first device.

In one feasible implementation, aligning a second task with a first device includes: receiving a second task from the first device; or sending a second task to the first device and receiving an acknowledgment message from the first device, the acknowledgment message indicating that the second task sent to the first device is the same as the second task stored in the second device; or receiving a second task from a third device, the third device also being used to send the second task to the first device.

In one feasible implementation, after aligning the second task with the first device, the method further includes: obtaining and storing a mapping relationship between a third task and a first radio map from the first device, wherein the third task is all or part of the second task.

In this embodiment, the second task is first aligned with the first device, and then the mapping relationship between the third task and the first radio map is acquired and stored according to different situations. This allows the first task or the first radio map to be quickly determined based on the stored mapping relationship without occupying too much of its own storage space, thus improving the efficiency of acquiring the first radio map.

In one feasible implementation, obtaining and storing the mapping relationship between the third task and the first radio map from the first device includes: obtaining and storing the mapping relationship between the third task and the first radio map from the first device according to a preset period; or obtaining and storing the mapping relationship between the third task and the first radio map from the first device according to the usage of the mapping relationship; or obtaining and storing the mapping relationship between the third task and the first radio map from the first device according to an operation instruction.

In one feasible implementation, after acquiring and storing the mapping relationship between the third task and the first radio map from the first device, the method further includes: deleting low-frequency mapping relationships, which are the stored mapping relationships that use frequencies lower than a preset frequency threshold and/or use intervals exceeding a preset interval threshold.

Secondly, this application provides a method for acquiring radio maps. The method includes: receiving a first request message from a fourth device, the first request message being used to request the acquisition of one or more first radio maps corresponding to task information, or to request the acquisition of one or more first radio maps corresponding to multiple first tasks; wherein the task information corresponds to multiple first tasks, and there is a mapping relationship between the first tasks and one or more first radio maps; and sending a first response message, the first response message indicating one or more first radio maps. The solution described in the second aspect can be executed by a second device, which can be a communication device, a module within the communication device (such as a chip system), or a logical node, logical module, or software capable of implementing all or part of the functions of the communication device; there is no limitation thereto.

In one feasible implementation, when the first request message is used to request the acquisition of one or more first radio maps corresponding to the task information, the method further includes: determining a plurality of first tasks based on the task information; and acquiring one or more first radio maps corresponding to the plurality of first tasks.

In one feasible implementation, obtaining one or more first radio maps corresponding to multiple first tasks includes: determining one or more first radio maps corresponding to multiple first tasks based on a stored mapping relationship between second tasks and first radio maps, wherein the second tasks include multiple first tasks.

In one feasible implementation, multiple first tasks are determined based on task information, including: inputting the task information vector corresponding to the task information into a first model for processing to obtain multiple first tasks, wherein the first model is used to perform classification planning for the first tasks.

In one feasible implementation, multiple first tasks are determined based on task information, including: inputting task information, prompt information, and a task information database into a second model for processing to obtain multiple first tasks. The second model is used to retrieve the first tasks, and the prompt information is used to indicate that the first task corresponding to the task information is determined by searching the task information database.

In one feasible implementation, the method further includes: sending a mapping relationship between a third task and a first radio map to a fourth device, wherein the third task is all or part of the second task.

Thirdly, this application provides a radio map acquisition method, which includes: receiving a second request message from a fourth device, the second request message being used to request acquisition of multiple first tasks corresponding to task information; and sending a second response message, the second response message indicating the multiple first tasks. The solution described in this third aspect can be executed by a third device, which can be a communication device, a module within the communication device (such as a chip system), or a logical node, logical module, or software capable of implementing all or part of the functions of the communication device; there is no limitation thereto.

In one feasible implementation, after receiving the second request message from the fourth device, the method further includes: inputting the task information vector corresponding to the task information into a first model for processing to obtain multiple first tasks, wherein the first model is used to perform classification planning for the first tasks.

In one feasible implementation, after receiving the second request message from the fourth device, the method further includes: inputting task information, prompt information, and a task information database into a second model for processing to obtain multiple first tasks. The second model is used to retrieve the first tasks, and the prompt information is used to indicate that the first task corresponding to the task information is determined by searching the task information database.

Fourthly, a communication device is provided, the communication device including units or modules for performing any of the possible methods in the first, second or third aspects described above.

Fifthly, embodiments of this application provide a communication device, the communication device including at least one processor coupled to a memory; wherein the at least one processor is configured to execute a computer program or instructions stored in the memory, such that the methods that may be implemented in any of the first to third aspects described above are executed.

Sixthly, embodiments of this application provide a communication system including a first device, a second device, and a fourth device, wherein the fourth device is used to perform the method described in any one of the first aspects, the first device is used to perform the method described in any one of the second aspects, and the second device is used to perform the method described in any one of the third aspects. Where possible, the communication system may also include the third device or similar device described in the first aspect, used to perform the related methods of the first aspect.

In a seventh aspect, embodiments of this application provide a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions, which, when executed, cause the computer to perform the method described in any of the above methods.

Eighthly, embodiments of this application provide a computer program product, the computer program product including: computer program code, which, when executed by a computer, causes the computer to perform the method described in any of the above methods.

Ninthly, embodiments of this application provide a chip coupled to a memory for reading and executing program instructions in the memory, so that the device in which the chip is located implements the method described in any of the above methods.

Attached Figure Description

The accompanying drawings used in the embodiments of this application are described below.

Figure 1 shows a wireless communication system architecture provided in an embodiment of this application.

Figure 2A is a schematic diagram of an MLP provided in an embodiment of this application.

Figure 2B is a schematic diagram of a loss function optimization provided in an embodiment of this application.

Figure 2C is a schematic diagram of gradient backpropagation provided in an embodiment of this application.

Figure 3A is a schematic diagram of a single-function radio map provided in an embodiment of this application.

Figure 3B is a schematic diagram of a multi-layer radio map provided in an embodiment of this application.

Figure 4A is a flowchart of a radio map acquisition method provided in an embodiment of this application.

Figure 4B is a schematic diagram of a process for determining multiple first tasks based on a first model according to an embodiment of this application.

Figure 4C is a schematic diagram of a process for determining multiple first tasks based on a second model according to an embodiment of this application.

Figures 5 to 7 are flowcharts of the method for determining a first radio map provided in the embodiments of this application.

Figure 8 is a schematic diagram of the structure of a communication device provided in an embodiment of this application.

Figure 9 is a simplified structural diagram of a network device provided in an embodiment of this application.

Figure 10 is a simplified structural diagram of a UE provided in an embodiment of this application.

Detailed Implementation

The technical solutions in the embodiments of this application will be described below with reference to the accompanying drawings. The terms "system" and "network" in the embodiments of this application can be used interchangeably. Unless otherwise stated, "/" indicates that the objects before and after are in an "or" relationship; for example, A/B can represent A or B. "And/or" in this application is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and/or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Furthermore, in the description of this application, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be one or multiple. Furthermore, to facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish between network elements and similar items with essentially the same function. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that the terms "first" and "second" are not necessarily different.

References to "one embodiment" or "some embodiments" in the embodiments described in this application mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

The following detailed embodiments further illustrate the objectives, technical solutions, and beneficial effects of this application. It should be understood that the following are merely specific embodiments of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made based on the technical solutions of this application should be included within the scope of protection of this application.

In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and/or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

The system architecture involved in the embodiments of this application is described below.

The embodiments of this application can be applied to wireless communication systems such as cellular mobile communication, satellite communication, and short-range communication. Referring to Figure 1, Figure 1 illustrates a wireless communication system architecture provided by an embodiment of this application. As shown in Figure 1, the wireless communication system can consist of cells, each cell containing a base station (BS). The base station provides communication services to multiple distributed nodes (in the illustration, the distributed nodes are terminals). The wireless communication system can also perform point-to-point communication, such as communication between multiple terminals.

It should be noted that the wireless communication systems mentioned in the embodiments of this application include, but are not limited to: narrowband Internet of Things (NB-IoT), Global System for Mobile Communications (GSM), enhanced data rate for GSM evolution (EDGE), wideband code division multiple access (WCDMA), and code division multiple access 2000 (CDMA). The three major application scenarios of 2000), Time Division-Synchronization Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), and next-generation 5G mobile communication systems are enhanced mobile broadband (eMBB), ultra-reliable and low-latency communications (URLLC), and enhanced machine-type communication (eMTC).

The distributed nodes involved in the embodiments of this application may include various handheld devices, vehicle-mounted devices, wearable devices, computing devices, or other processing devices connected to a wireless modem with wireless communication capabilities. The distributed nodes may also be called mobile stations (MS), or subscriber units, cellular phones, smartphones, wireless data cards, personal digital assistant (PDA) computers, tablet computers, wireless modems, handsets, laptop computers, machine-type communication (MTC) terminals, etc.

The base station in Figure 1 above refers to the device in a mobile communication system that connects terminal devices to a wireless network. It can also be called an access network element, a radio access network (RAN) node (or device, or network element), an access point (AP), a network device, a small tower, etc. The RAN equipment in this application embodiment includes, but is not limited to: next-generation base stations (g nodeB, gNB) in 5G, evolved node B (eNB), radio network controller (RNC), node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (e.g., home evolved nodeB, or home node B, HNB), baseband unit (BBU), wireless fidelity (WiFi) access point, world interoperability for microwave access (WiMAX) base station, transmitting and receiving point (TRP), transmitting point (TP), or mobile switching center, etc. In systems employing different wireless access technologies, the names of devices with base station functions may vary. For example, in 5G communication systems, they are called RAN or gNB (5G NodeB); in LTE systems, they are called evolved NodeB (eNB or eNodeB); and in third-generation (3G) communication systems, they are called Node B, etc.

The artificial intelligence technology involved in the embodiments of this application will be described below.

Artificial intelligence (AI) enables machines to possess human-like intelligence, such as allowing them to use computer hardware and software to simulate certain intelligent human behaviors. To achieve AI, machine learning methods can be employed. In machine learning, machines learn (or train) models using training data. These models represent the mapping between inputs and outputs. The learned model can be used for reasoning (or prediction), that is, it can be used to predict the output corresponding to a given input. This output can also be called the reasoning result (or prediction result). Considering AI's excellent performance in various fields, it is also considered one of the important technologies for constructing various radio maps.

The most commonly used machine learning model in the field of artificial intelligence is the deep neural network, which can include fully connected (FC) neural networks, convolutional neural networks (CNNs), or recurrent neural networks (RNNs). This section will use a fully connected neural network as an example. A fully connected neural network is also called a multilayer perceptron (MLP). Referring to Figure 2A, which is a schematic diagram of an MLP provided in an embodiment of this application, an MLP includes an input layer (left), an output layer (right), and multiple hidden layers (middle). Each layer contains several nodes, called neurons. Neurons in adjacent layers are connected pairwise.

Considering neurons in two adjacent layers, the output h of a neuron in the next layer is the weighted sum of all neurons x connected to it in the previous layer, after passing through an activation function. This can be represented by the following formula using matrices:
h＝f(wx+b) (1)

Where w is the weight matrix, b is the bias vector, and f is the activation function. The output of the neural network can then be recursively expressed as:
y＝f _n (w _n f _n-1 (…)+b _n ) (2)

Where n is the index of the neural network layer, n is greater than or equal to 1 and less than or equal to N, where N is the total number of layers in the neural network.

Simply put, a neural network can be understood as a mapping from an input data set to an output data set. Neural networks are typically initialized randomly; the process of obtaining this mapping from random values w and b using existing data is called training the neural network.

The specific training method involves evaluating the output of the neural network using a loss function and backpropagating the error. Referring to Figure 2B, which is a schematic diagram of loss function optimization provided in an embodiment of this application, as shown in Figure 2B, gradient descent can be used to iteratively optimize w and b until the loss function reaches its minimum value.

The gradient descent process can be represented as:

Where θ represents the parameters to be optimized (e.g., w and b), L is the loss function, and η is the learning rate, controlling the step size of gradient descent. This represents the differentiation operation. This indicates taking the derivative of θ with respect to L.

The backpropagation process utilizes the chain rule for partial derivatives, meaning the gradient of the parameters in the previous layer can be recursively calculated from the gradient of the parameters in the next layer. See Figure 2C for a schematic diagram of gradient backpropagation provided in an embodiment of this application. The formula can be expressed as:

Where w _{_ij} is the weight connecting node j to node i, and s _{_i} is the weighted sum of the inputs at node i.

The following describes the radio mapping technology involved in the embodiments of this application.

Referring to Figure 3A, which is a schematic diagram of a single-function radio map provided in an embodiment of this application, as shown in Figure 3A, the radio map takes location information as input, performs relevant processing on the radio map, and outputs a single piece of radio information. For example, the input of the radio map is location information, and the output is the path loss of the radio channel at the corresponding location. In this case, such a radio map can also be called a path loss map. As another example, the input of the radio map is location information, and the output is the radio signal strength at the corresponding location. In this case, such a radio map can also be called a signal strength map.

See also Figure 3B, which is a schematic diagram of a multi-layer radio map provided in an embodiment of this application. As shown in Figure 3B, a multi-layer radio map is constructed based on an existing single-function radio map. The multi-layer radio map includes multiple "layers," namely L1 to L3 in the figure. For the input information of each layer, each layer performs relevant processing and outputs different radio information.

The two existing technologies described above differ in their approaches. The first can only perform a single function using radio maps. While the second can perform multiple functions and ultimately output various types of radio information using radio maps, it requires constructing a mapping relationship between radio information and radio maps to obtain multi-layered radio maps. However, the variety of radio information is vast, and the overhead of constructing and storing the corresponding mapping relationships is significant.

Based on this, please refer to Figure 4A, which is a flowchart of a radio map acquisition method provided by an embodiment of this application. As shown in Figure 4A, the method includes the following steps:

201. The fifth device obtains task information, which corresponds to multiple first tasks.

The fifth device in this embodiment can be a radio map server, specifically the RAN device, base station, or terminal (for end-to-end service) described in Figure 1, or a core network device or over-the-top (OTT) device. It can also be a radio map user (device), specifically the terminal, mobile station, handheld device, or vehicle-mounted device described in Figure 1.

Task information refers to relevant information describing the objectives to be achieved using radio maps. Specifically, it can refer to information describing the objectives in natural language, such as: completing channel estimation; performing beam management and positioning. Alternatively, assuming a task has a corresponding identifier, the task information can be the task identifier. For example, the task information could be 001, and 001 would identify a precoding task.

In this embodiment, the task information corresponds to multiple first tasks. A first task is a task that has a mapping relationship with a first radio map. Assuming that the mapping relationship with the first radio map is constructed according to the most basic and indivisible tasks, the first task can also be called a fundamental task. The first radio map refers to the set of radio maps required to complete the first task. This set of radio maps may include one (directly obtainable) radio map or multiple radio maps.

If the fifth device is a radio map server, it can obtain task information by either sending it to the radio map user equipment or by sending it to the third device, which is a management device used to manage the interaction process between the radio map server and the radio map user.

If the fifth device is a radio map user, it can obtain task information either by following the user's operation instructions or by having other devices send it to it. These other devices can be devices that receive the user's operation instructions, such as handheld devices, wearable devices, or network management functions (OAM).

202. The fifth device determines one or more first radio maps based on mission information, wherein there is a mapping relationship between the first mission and one or more first radio maps.

The task information corresponds to multiple first tasks, and in this embodiment, there is a mapping relationship between the first tasks and the first radio map. This mapping relationship can be illustrated by the following table 1:

Table 1

As shown in Table 1, each first task corresponds to a first radio map, but different first tasks may correspond to the same first radio map.

Additionally, the first task may include its corresponding task identifier (task ID), and the first radio map may include its corresponding map identifier (map ID). When describing the mapping relationship between the first task and the first radio map, the inputs and outputs for each map can also be described, so that after obtaining the radio map according to the mapping relationship, it is known how to input the radio map to execute the first task.

Therefore, the mapping relationship between the first task and the first radio map can also be represented as shown in Table 2 below:

Table 2

As shown in Table 2, the mapping relationship between the first task and the first radio map can be called the task-radio map index table, which can be used to index the radio map.

For example, when the first task ID is 1, the corresponding map ID is 1, indicating that the first radio map 1 needs to be called to perform the channel estimation task. The inputs to this process are coordinates and environmental information, and the output is multipath component (MPC). Among them, the "environmental information" in the input is optional.

As can be seen, in this embodiment, a mapping relationship between the first task and the first radio map is constructed. Since the number of first tasks is less than the number of complex radio information types, the construction cost and storage overhead of the mapping relationship between the first task and the first radio map are also lower. Furthermore, based on the aforementioned mapping relationship, one or more first radio maps corresponding to multiple first tasks described in the task information can be quickly determined, and then multiple first radio maps can be invoked to execute multiple first tasks. In summary, this method reduces the cost of implementing multiple functions using radio maps while improving implementation efficiency.

The process of the fifth device determining one or more first radio maps based on task information includes two intermediate processes: 1) determining multiple first tasks based on task information, which can be referred to as the task determination process; 2) determining one or more first radio maps corresponding to multiple first tasks, which can be referred to as the map determination process.

For intermediate process 1), multiple primary tasks can be determined using the AI techniques described above. Specifically, the primary tasks can be obtained using deep neural network models such as classification models or large language models.

Optionally, multiple first tasks are determined based on the task information, including: inputting the task information vector corresponding to the task information into a first model for processing to obtain multiple first tasks, and the first model is used to perform classification planning for the first tasks.

Referring to Figure 4B, which is a schematic diagram of a process for determining multiple first tasks based on a first model according to an embodiment of this application, as shown in Figure 4B, the task information used in this embodiment may include task objects and task objectives described in natural language, such as the task object being to aggregate users and the task objective being to improve throughput. Therefore, after obtaining the task information, it is first input into a natural language encoder for processing to obtain a task information vector. Then, the task information vector is input into the first model. Since the first model is a classification planner, its output is an N-dimensional vector, where N can be the number of second tasks, and this vector is a binary vector. If the i-th element is 1, it means that the i-th second task is selected; if the i-th element is 0, it means that the i-th second task is not selected. The combination of basic tasks corresponding to all items with a value of 1 in the output vector is the final result. As shown in Figure 4B, second task 1 and second task 2 are determined as the first tasks corresponding to the task information. In this embodiment of the application, the second task refers to a task defined by the management device, manufacturer, or standard, and the second task includes the first task.

In the above schemes, the natural language encoder can be implemented using neural networks, such as the Transformer architecture. The classification planner can be implemented using neural networks, such as MLP, or other AI methods, such as support vector machines.

Optionally, multiple first tasks are determined based on task information, including: inputting task information, prompt information, and a task information database into a second model for processing to obtain multiple first tasks. The second model is used to retrieve the first tasks, and the prompt information is used to indicate the first task corresponding to the task information by retrieving the task information database.

Referring to Figure 4C, which is a schematic diagram of a process for determining multiple first tasks based on a second model according to an embodiment of this application, as shown in Figure 4C, task information and prompt information are input into the second model. The task information can include task objects and task objectives. The prompt information indicates two things: first, that multiple first tasks corresponding to the task information need to be determined; and second, that results need to be retrieved from the task information database. Specifically, the prompt information indicates that a suitable second task should be selected from the task information database as the first task. Simultaneously, the task information database is input into the second model to provide knowledge for it. The task information database contains information on all second tasks. The information corresponding to each second task may include the following fields: 1. Identifier (ID) of the second task; 2. Name of the second task; 3. Input and output of the second task; 4. Creation time of the second task; 5. Solution complexity of the second task. Other fields may also be included, which are not limited in this embodiment. The second model matches keywords in the task information with keywords in the task information database to obtain retrieval results.

The second model can be a large language model (LLM), an intelligent agent, or a multimodal large model, etc., and the embodiments of this application are not limited thereto.

As can be seen, the process of obtaining the first task using the first model in this embodiment of the application can quickly and easily determine multiple first tasks because the task information is first vectorized. The process of obtaining the first task using the second model allows the task information to be directly input into the second model without additional processing, thus simplifying the operation of determining the first task.

The first and second models described above are used to obtain multiple first tasks and can be collectively referred to as task planners. Task planners can also be other types of models or forms, such as logic analysis algorithms, etc., which are not limited in the embodiments of this application.

The task planner can be trained in a centralized or distributed manner. After training, it can be deployed on a fifth device. That is, the aforementioned intermediate process 1) can be executed by the fifth device itself. Alternatively, the task planner can be deployed on a third-party server other than the fifth device (i.e., other than the radio map server and radio map users), and the third-party server can execute intermediate process 1). The determined multiple first tasks are then fed back to the fifth device for subsequent intermediate processes 2). Specific details will be described in the embodiments described later.

After acquiring multiple first tasks, the fifth device can determine one or more first radio maps corresponding to the multiple first tasks based on the mapping relationship between the first tasks and the first radio maps, such as the mapping relationship described in Tables 1 and 2 above. Then, assuming the fifth device is a radio map user, it can execute the multiple first tasks based on the first radio maps. Alternatively, assuming the fifth device is a radio map server, it can indicate one or more first radio maps to the radio map user so that the radio map user can execute the multiple first tasks based on the first radio maps. Specific details will be described in the following embodiments.

This embodiment describes the deployment of a task planner on a radio map server. Referring to Figure 5, which is a flowchart of a method for determining a first radio map according to an embodiment of this application, the method includes the following steps:

301. The fourth device obtains task information, which corresponds to multiple first tasks.

The fourth device in this embodiment is a radio map user. The method for a radio map user to obtain task information can be found in the relevant description in step 201 of the aforementioned embodiment.

302. The fourth device sends a first request message to the first device. The first request message is used to request one or more first radio maps corresponding to the task information.

In this embodiment, the first device is a radio map server. The first request message sent by the fourth device includes task information, used to request the acquisition of the first radio map corresponding to the task information. Since the task information corresponds to multiple first tasks, the multiple first tasks may correspond to the same (or a group) first radio map, or they may correspond to multiple (or groups) first radio maps.

The fifth device in the foregoing embodiments can refer to either the fourth device in the embodiments or the first device.

303. The first device receives the first request message and determines one or more first radio maps corresponding to the task information based on the first request message.

After receiving the first request message, the first device obtains one or more corresponding first radio maps based on the task information. The specific process may include the intermediate processes 1) and 2) described in the foregoing embodiments for determining one or more first radio maps based on the task information.

304. The first device sends a first response message to the fourth device, the first response message indicating one or more first radio maps corresponding to the task information.

After the first device determines one or more first radio maps corresponding to the task information, it can instruct the fourth device through a first response message. That is, the first response message may include the map identifier or map name of one or more first radio maps, or it may include both the map identifier and map name. Furthermore, the first device may directly send one or more first radio maps to the fourth device through the first response message.

Upon receiving the first response message, the fourth device can determine one or more first radio maps corresponding to the task information. If the first response message includes map identifiers and/or map names for one or more first radio maps, the fourth device retrieves the first radio map corresponding to the map identifier and/or map name from its stored first radio map information database (including the name, identifier, and map content of the first radio map). If the first response message includes one or more first radio maps, the fourth device can retrieve one or more first radio maps from the first response message.

Where possible, the fourth device does not store radio maps corresponding to map identifiers and/or map names of one or more first radio maps. Therefore, the method may further include the following steps:

305. The fourth device sends a map request message to the first device to request one or more first radio maps corresponding to the map identifier and/or map name of one or more first radio maps.

306. The first device sends a map request response message to the fourth device, which includes one or more first radio maps.

The fourth device receives a map request response message and obtains one or more first radio maps based on the map request response message.

The steps 305 to 306 described above are used for the fourth device to obtain the first radio map from the first device, and therefore can be referred to as the outward map acquisition process.

After acquiring one or more first radio maps, the fourth device can apply the first radio maps to perform multiple first tasks. Specifically, the fourth device performs multiple first tasks by acquiring inputs for multiple first tasks (or each first radio map), combining the inputs of each first radio map with the first radio map to perform multiple first tasks, thereby realizing various functions of the first radio map, such as channel estimation or precoding.

As can be seen, in this embodiment, the task planner is deployed on a radio map server (first device). The radio map server determines multiple first tasks corresponding to the task information, and determines one or more first radio maps corresponding to the multiple first tasks based on the mapping relationship between the first tasks and the first radio maps stored in its own database. Because the radio map server has powerful processing capabilities and stores the mapping relationship between all second tasks (including first tasks) and the first radio maps, this process can ensure that one or more first radio maps corresponding to the task information are determined in the most efficient and accurate manner.

Before step 302 in this embodiment, the method may further include the following steps:

3000, the fourth device aligns with the first device for the second task.

3001. The fourth device obtains and stores the mapping relationship between the third task and the first radio map from the first device.

Aligning the second task with the first device means that the fourth device and the first device determine the same information related to the second task, which may include the name, quantity, input, and output information of the second task. After aligning the second task with the first device, the fourth device can request the mapping relationship between the third task and the first radio map from the first device. The third task can be some or all of the second tasks. That is, the fourth device can store all the mapping relationships or only a portion of them.

The specific method for aligning the fourth device with the first device for the second task can be as follows:

(1) The fourth device receives the second task from the first device.

The first device is a radio map server, which includes a second task that is configured by the manufacturer, specified by standards, or manages the device configuration. The fourth device can proactively request the second task from the first device, or receive the second task proactively sent by the first device.

(2) The fourth device sends a second task to the first device and receives an acknowledgment message from the first device. The acknowledgment message indicates that the second task sent to the first device is the same as the second task stored in the second device.

The fourth device, acting as a radio map user, may also have its second task configured by the manufacturer or specified by standards. The fourth device then sends its stored second task to the first device, which matches the received second task with its own stored second task. If they match perfectly, the first device sends a confirmation message to the second device to confirm that its stored second task is the same as the one sent by the fourth device.

(3) The fourth device receives the second task from the third device, and the third device is also used to send the second task to the first device.

The fourth device, acting as a radio map user, can receive the second task from the third device, which is a management device. Simultaneously, the third device also manages the first device, the radio map server, and sends the second task to it as well. Since the second task sent by the third device to both the first and fourth devices is identical, the second task alignment between the fourth and first devices is also achieved.

After completing the second task alignment, the fourth device can obtain the mapping relationship between the third task and the first radio map from the first device. Considering the storage limitations of map users, they can determine commonly used first radio maps based on their historical usage of the first radio map. Then, they can obtain the mapping relationship between commonly used first radio maps and the third task from the first device, so that when determining the first task corresponding to the first radio map later, they can determine it based on their stored mapping relationship.

The fourth device may obtain the mapping relationship between the third mission and the first radio map from the first device in the following ways:

①The fourth device acquires and stores the mapping relationship between the third task and the first radio map from the first device according to a preset period.

Specifically, obtaining the mapping relationship according to a preset period can also be called periodic updating of the mapping relationship. Periodic updates require setting an update period. After the update period is reached, the fourth device determines the second task that was frequently used in the previous period as the third task and obtains the corresponding third task-first radio map mapping relationship from the first device. The update period involved here can be configured through higher-layer signaling, such as radio resource control (RRC) signaling. Periodically obtaining the mapping relationship can reduce control complexity.

②The fourth device obtains and stores the mapping relationship between the third task and the first radio map from the first device according to the usage of the mapping relationship.

The fourth device's use of the mapping relationship includes using the stored mapping relationship between the third task and the first radio map (the stored mapping relationship), and using the unstored mapping relationship between the second task and the first radio map (the unstored mapping relationship). When the fourth device uses an unstored mapping relationship between a second task and the first radio map more frequently than a certain frequency threshold, the fourth device is triggered to request the first device to update its stored mapping relationship between the third task and the first radio map, including obtaining the mapping relationship between the second task and the first radio map whose usage frequency exceeds the certain frequency threshold. Alternatively, when the proportion of the fourth device using unstored mapping relationships exceeds a certain preset proportion, the fourth device is triggered to request the first device to obtain and store a (new) mapping relationship between the third task and the first radio map. Non-periodic triggering of mapping relationship acquisition allows for acquisition only when necessary, reducing storage overhead.

③ The fourth device obtains and stores the mapping relationship between the third task and the first radio map from the first device according to the operation instructions.

The fourth device may receive user operation commands, either directly or through other devices. These commands instruct the fourth device to update its stored mapping relationships. The fourth device then requests the first device to retrieve and store the (new) mapping relationship between the third task and the first radio map. Triggering the retrieval of mapping relationships based on operation commands ensures flexibility in this process.

As can be seen, in this embodiment, the fourth device first aligns the second task with the first device, and then acquires and stores the mapping relationship between the third task and the first radio map according to different situations. This allows the first task or the first radio map to be quickly determined based on the stored mapping relationship without occupying too much of its own storage space, thereby improving the efficiency of acquiring the first radio map.

Furthermore, the method may also include the following steps:

3002. The fourth device deletes the low-frequency mapping relationship stored in its own memory.

Low-frequency mapping relationships are those stored in the fourth device that use frequencies lower than a preset frequency threshold, or use intervals exceeding a preset interval threshold, or both. Deleting these low-frequency mapping relationships from the fourth device can maintain reasonable storage space usage as much as possible without affecting the use of the mapping relationships.

The steps 3000 to 3002 above are used for the fourth device to deploy the mapping relationship on itself, and therefore can be called the mapping relationship deployment process.

This embodiment describes the deployment of a task planner on a radio map user. Referring to Figure 6, which is a flowchart of another method for determining a first radio map provided in this embodiment, the method includes the following steps:

401. The fourth device acquires task information.

In this embodiment, the fourth device is a radio map user. The method for a radio map user to obtain task information can be found in the relevant description of step 201 of the aforementioned embodiment.

402. The fourth device determines multiple primary tasks based on the task information.

In this embodiment, the process by which the fourth device determines multiple first tasks based on task information is essentially the process by which the fourth device performs task planning based on the task information. Assuming that the task information directly includes a task identifier or name, the fourth device can directly determine multiple first tasks.

Assuming the task information includes a task object and task objective described in natural language, the fourth device can process the task information using AI technology to determine multiple first tasks. For details, refer to step 202 of the aforementioned embodiments, where a first model and a second model are used to determine multiple first tasks. Alternatively, other models can be used to determine multiple first tasks, which will not be elaborated upon here.

Then the fourth device acquires one or more first radio maps corresponding to multiple first tasks.

The process of the fourth device acquiring the first radio map (map determination) may include two scenarios, corresponding to the following steps:

403a. The fourth device obtains one or more first radio maps corresponding to multiple first tasks based on its stored mapping relationship between third tasks and first radio maps. In this case, the third task includes multiple first tasks.

In another scenario, assuming the fourth device cannot obtain all or part of the first tasks based on its stored mapping relationship between the third tasks and the first radio map (including cases where the fourth device itself does not store any mapping relationship), the method may further include the following steps:

403b. The fourth device sends a third request message to the first device, the third request message being used to request the acquisition of one or more first radio maps corresponding to multiple first tasks, the first device including the mapping relationship between second tasks and first radio maps, the second task including multiple first tasks.

404. The first device determines one or more first radio maps corresponding to multiple first tasks based on the third request message.

405. The first device sends a third response message to the fourth device, the third response message indicating one or more first radio maps corresponding to multiple first tasks.

After receiving the third request message, the first device, since its stored mapping relationship between the second task and the first radio map includes multiple mapping relationships between the first task and the first radio map, can obtain one or more first radio maps corresponding to multiple first tasks. Then, the first device indicates one or more first radio maps to the fourth device through the third response message, including indicating the map identifier and/or map name of the one or more radio maps, or directly sends one or more radio maps to the fourth device.

Steps 403a and 403b-405 described above can be either option A or option B, meaning only one of them can be executed; or they can be executed concurrently, meaning steps 403a and 403b-405 can be executed simultaneously. In this case, the fourth device determines the first radio map corresponding to a portion of the first tasks based on its stored mapping relationship between the third tasks and the first radio map. Since the other portion of the first tasks is not included in the third tasks stored locally by the fourth device, the fourth device also needs to obtain the first radio map corresponding to that portion of the first tasks from the first device via a third request message. Similarly, if the third response message indicates the map identifier and/or map name of one or more radio maps, optional steps 305-306 described in the aforementioned embodiments can be included after step 404 to obtain the map externally. Before the fourth device determines multiple first tasks based on the task information, optional steps 3000-3002 described in the aforementioned embodiments can also be included to complete the mapping relationship deployment. This application embodiment will not elaborate further on this.

As can be seen, in this embodiment, the task planner is deployed on the radio map user (fourth device). The radio map user determines multiple first tasks corresponding to the task information, and the radio map server determines one or more first radio maps corresponding to the multiple first tasks based on the mapping relationship between the first tasks and the first radio maps stored in its own database. During this process, the radio map user does not need to perform any external transmission interaction in determining the first radio maps, improving the efficiency of determining the first radio maps while ensuring the reliability of the process. Furthermore, when the mapping relationship between the third tasks and the first radio maps stored in the radio map user's own database does not include the first tasks, the radio map user can obtain the first radio map corresponding to the first task from the radio map server, further ensuring the feasibility of determining the first radio maps.

This embodiment describes the scenario where the task planner is deployed on a third server. Referring to Figure 7, which is a flowchart of another method for determining a first radio map provided in this embodiment, the method includes the following steps:

501. The fourth device acquires task information.

In this embodiment, the fourth device is also a radio map user. The method for a radio map user to obtain task information can be found in the relevant description in step 201 of the aforementioned embodiment.

502. The fourth device sends a second request message to the second device. The second request message is used to request the acquisition of multiple first tasks corresponding to the task information.

In this embodiment, the second device is a third-party server other than the radio map user and the radio map server. A task planner is deployed on the second device. The fourth device sends task information to the second device via a second request message, so that the second device can perform task planning based on the task information and determine multiple first tasks corresponding to the task information.

503. The second device receives the second request message and determines multiple first tasks corresponding to the task information based on the second request message.

After receiving the task information, the second device determines multiple first tasks based on the task information. This process can be referred to in the description of step 202 of the aforementioned embodiment, which describes the intermediate process 1) of determining one or more first radio maps based on the task information. This includes the process of determining multiple first tasks using a first model and a second model. Alternatively, other models can be used to determine multiple first tasks, which will not be elaborated here.

504. The second device sends a second response message to the fourth device, the second response message indicating the plurality of first tasks.

After the second device determines the multiple first tasks corresponding to the task information, it can indicate the multiple first tasks to the fourth device through a second response message. Specifically, it can indicate the task names and/or task identifiers of the multiple first tasks to the fourth device.

505. The fourth device receives the second response message and determines one or more first radio maps corresponding to the multiple first tasks indicated by the second response message.

After the fourth device obtains the task name and/or task identifier of the first task through the second response message, it can determine one or more first radio maps corresponding to multiple first tasks. For specific methods, please refer to the map determination steps 403a to 405 in the foregoing embodiments; they will not be described in detail in this application embodiment.

Similarly, after the first radio map is determined, the method may further include the steps of acquiring the map externally as described in steps 305-306 of the foregoing embodiments. Before the fourth device determines multiple first tasks based on the task information, the method may also include the steps of deploying the mapping relationship as described in steps 3000-3002 of the foregoing embodiments. It should be noted that while the fourth device is aligned with the first device, the second device is also aligned with the first device so that the second device can determine which second tasks are included, and thus determine multiple first tasks among the second tasks based on the task information. The remaining details will not be elaborated upon in this embodiment.

As can be seen, in this embodiment, the task planner is deployed on a third-party server (second device). The third-party server determines multiple first tasks corresponding to the task information and feeds these first tasks back to the radio map user. The radio map user then determines one or more first radio maps corresponding to the multiple first tasks based on their stored mapping relationships or through the radio map server. This task planning process, executed by the third-party server, reduces the processing power consumed by the radio map user or the radio map server, thereby minimizing the impact of the task planning process on other services of the radio map user or the radio map server.

The terms "first device," "second device," "third device," "fourth device," and "fifth device" mentioned above are merely designations for the relevant implementing entities and should not be construed as limiting the specific implementation process. For details on the specific implementation process, please refer to the description of the implementing entities; they will not be repeated here.

Please refer to Figure 8, which is a schematic diagram of a communication device provided in an embodiment of this application. This communication device can be used to execute any of the methods in the foregoing embodiments.

As shown in Figure 8, the communication device includes a processing module 1501 and a transceiver module 1502. The processing module 1501 may be one or more processors, and the transceiver module 1502 may be a transceiver or a communication interface. This communication device can be used to implement the functions of the first device, second device, third device, fourth device, fifth device, or even more devices involved in any of the above method embodiments. These devices may be hardware devices, software functions running on dedicated hardware, or virtualized functions instantiated on a platform (e.g., a cloud platform). Optionally, the communication device may also include a storage module 1503 for storing the program code and data of the communication device.

In a first example, the communication device can function as the fourth device or a chip within the fourth device shown in Figures 5-7, and execute the steps performed by the fourth device in the above method embodiments. The transceiver module 1502 supports communication with the first, second, or third device, etc. The processing module 1501 can be used to support the execution of actions performed by the fourth device in the above method embodiments, excluding sending and receiving.

Specifically, the transceiver module 1502 is used to obtain task information, which corresponds to multiple first tasks;

The processing module 1501 determines one or more first radio maps based on the task information, and there is a mapping relationship between the first task and the first radio map.

In one feasible implementation, determining one or more first radio maps based on task information includes: sending a first request message to a first device, the first request message being used to request the acquisition of one or more first radio maps corresponding to the task information; and receiving a first response message from the first device, the first response message indicating one or more first radio maps.

In one feasible implementation, determining one or more first radio maps based on mission information includes: determining a plurality of first missions based on the mission information; and determining one or more first radio maps based on the plurality of first missions.

In one feasible implementation, multiple first task aspects are determined based on task information. The transceiver module 1502 is used to: send a second request message to the second device, the second request message being used to request the acquisition of multiple first tasks corresponding to the task information; and receive a second response message from the second device, the second response message indicating multiple first tasks.

In one feasible implementation, multiple first tasks are determined based on task information, including: inputting the task information vector corresponding to the task information into a first model for processing to obtain multiple first tasks, wherein the first model is used to perform classification planning for the first tasks.

In one feasible implementation, multiple first tasks are determined based on task information, including: inputting task information, prompt information, and a task information database into a second model for processing to obtain multiple first tasks. The second model is used to retrieve the first tasks, and the prompt information is used to indicate that the first task corresponding to the task information is determined by searching the task information database.

In one feasible implementation, one or more first radio maps determined based on a plurality of first tasks include: determining one or more first radio maps corresponding to a plurality of first tasks based on a stored mapping relationship between first tasks and first radio maps.

In one feasible implementation, regarding one or more first radio maps determined based on multiple first tasks, the transceiver module 1502 is configured to: send a third request message to a first device, the third request message being used to request the acquisition of one or more first radio maps corresponding to multiple first tasks, the first device including a mapping relationship between second tasks and first radio maps, the second task including multiple first tasks; and receive a third response message from the first device, the third response message indicating one or more first radio maps corresponding to multiple first tasks.

In one feasible implementation, before determining the first radio map based on the mission information, the transceiver module 1502 is also used to: align the second mission with the first device.

In one feasible implementation, regarding aligning the second task with the first device, the transceiver module 1502 is specifically configured to: receive the second task from the first device; or send the second task to the first device and receive an acknowledgment message from the first device, the acknowledgment message indicating that the second task sent to the first device is the same as the second task stored in the second device; or receive the second task from a third device, the third device also being configured to send the second task to the first device.

In one feasible implementation, after aligning the second task with the first device, the transceiver module 1502 is further configured to: obtain from the first device and store the mapping relationship between the third task and the first radio map through the processing module 1501, wherein the third task is all or part of the second task.

In one feasible implementation, regarding the acquisition and storage of the mapping relationship between the third task and the first radio map from the first device, the transceiver module 1502 is specifically used to: acquire the mapping relationship between the third task and the first radio map from the first device according to a preset period and store it through the processing module 1501; or acquire the mapping relationship between the third task and the first radio map from the first device and store it through the processing module 1501 according to the usage of the mapping relationship; or acquire the mapping relationship between the third task and the first radio map from the first device and store it through the processing module 1501 according to an operation instruction.

In one feasible implementation, after acquiring and storing the mapping relationship between the third task and the first radio map from the first device, the processing module 1501 is further configured to: delete low-frequency mapping relationships, which are the stored mapping relationships that use frequencies lower than a preset frequency threshold and/or use intervals exceeding a preset interval threshold.

In a second example, the communication device can function as the first device or a chip within the first device shown in Figures 5-7, and execute the steps performed by the first device in the above method embodiments. The transceiver module 1502 supports communication with a fourth device or a second device, etc. The processing module 1501 can be used to support the execution of actions performed by the first device in the above method embodiments, other than sending and receiving.

Specifically, the transceiver module 1502 is used to receive a first request message from the fourth device. The first request message is used to request to obtain one or more first radio maps corresponding to task information, or to request to obtain one or more first radio maps corresponding to multiple first tasks. The task information corresponds to multiple first tasks, and there is a mapping relationship between the first tasks and one or more first radio maps. The transceiver module 1502 sends a first response message, which indicates one or more first radio maps.

In one feasible implementation, when the first request message is used to request the acquisition of one or more first radio maps corresponding to the task information, the processing module 1501 is used to: determine multiple first tasks based on the task information; and acquire one or more first radio maps corresponding to the multiple first tasks.

In one feasible implementation, in obtaining one or more first radio maps corresponding to multiple first tasks, the processing module 1501 is specifically configured to: determine one or more first radio maps corresponding to multiple first tasks based on the stored mapping relationship between second tasks and first radio maps, wherein the second tasks include multiple first tasks.

In one feasible implementation, multiple first task aspects are determined based on task information. The processing module 1501 is specifically used to: input the task information vector corresponding to the task information into a first model for processing to obtain multiple first tasks. The first model is used to perform classification planning for the first tasks.

In one feasible implementation, multiple first task aspects are determined based on task information. The processing module 1501 is specifically used to: input task information, prompt information, and task information database into a second model for processing to obtain multiple first tasks. The second model is used to retrieve the first tasks, and the prompt information is used to indicate that the first task corresponding to the task information is determined by retrieving the task information database.

In one feasible implementation, the transceiver module 1502 is further configured to: send the mapping relationship between the third task and the first radio map to the fourth device, wherein the third task is all or part of the second task.

In a third example, the communication device can function as the second device or a chip within the second device shown in Figures 5-7, and execute the steps performed by the second device in the above method embodiments. The transceiver module 1502 supports communication with the second device. The processing module 1501 can be used to support the execution of actions performed by the second device in the above method embodiments, other than sending and receiving.

Specifically, the transceiver module 1502 is used to receive a second request message from the fourth device, the second request message being used to request the acquisition of multiple first tasks corresponding to the task information; and to send a second response message, the second response message indicating multiple first tasks.

In one feasible implementation, after receiving the second request message from the fourth device, the processing module 1501 is used to: input the task information vector corresponding to the task information into the first model for processing to obtain multiple first tasks, and the first model is used to perform classification planning of the first tasks.

In one feasible implementation, after receiving the second request message from the fourth device, the processing module 1501 is used to: input the task information, prompt information, and task information database into the second model for processing to obtain multiple first tasks. The second model is used to retrieve the first tasks, and the prompt information is used to indicate that the first task corresponding to the task information is determined by searching the task information database.

The processing module 1501 may be a processor that can execute computer execution instructions stored in the storage module to cause the chip to perform the methods involved in any of the above embodiments.

Furthermore, a processor may include a controller, an arithmetic logic unit (ALU), and registers. For example, the controller is primarily responsible for instruction decoding and issuing control signals for the operations corresponding to the instructions. The ALU is primarily responsible for performing fixed-point or floating-point arithmetic operations, shift operations, and logical operations, and can also perform address operations and translations. Registers are primarily responsible for storing register operands and intermediate operation results temporarily stored during instruction execution. In specific implementations, the processor's hardware architecture can be an ASIC architecture, a microprocessor without interlocked piped stages architecture (MIPS), an advanced reduced instruction set machine (RISC) machine (ARM) architecture, or a network processor (NP) architecture, etc. The processor can be single-core or multi-core.

The storage module can be an internal storage module of the chip, such as a register or cache. Alternatively, the storage module can be an external storage module, such as ROM or other types of static storage devices that can store static information and instructions, such as RAM.

It should be noted that the functions of the processor and interface can be implemented through hardware design, software design, or a combination of both; no restrictions are imposed here.

Please refer to Figure 9, which is a simplified structural diagram of a network device provided in an embodiment of this application. It can be used as an implementation of the first device, the second device, or even more devices in this application.

The network device includes a radio frequency (RF) signal transceiver and conversion section and a baseband section 42. The RF signal transceiver and conversion section further includes a receiving module 41 and a transmitting module 43 (which can also be collectively referred to as the transceiver module). The RF signal transceiver and conversion section is mainly used for transmitting and receiving RF signals and converting RF signals to baseband signals; the baseband section 42 is mainly used for baseband processing and controlling the network device. The receiving module 41 can also be called a receiver, receiver circuit, etc., and the transmitting module 43 can also be called a transmitter, transmitter, transmitter circuit, etc. The baseband section 42 is usually the control center of the network device, and can also be called a processing module, used to execute the steps performed by the network device in any of the above methods. See the descriptions in the relevant sections above for details.

The baseband section 42 may include one or more boards, each board may include one or more processors and one or more memories. The processors are used to read and execute programs in the memories to implement baseband processing functions and control network devices. If multiple boards exist, they can be interconnected to increase processing power. As an optional implementation, multiple boards may share one or more processors, multiple boards may share one or more memories, or multiple boards may simultaneously share one or more processors.

For example, the sending module 43 is used to perform the functions of the reader in any of the methods described above.

Please refer to Figure 10, which is a simplified structural diagram of a UE provided in an embodiment of this application, as an implementation of the fourth device, the first device, or the second device in this application.

For ease of understanding and illustration, Figure 10 uses a mobile phone as an example of the UE. As shown in Figure 10, the UE includes at least one processor, and may also include radio frequency (RF) circuitry, an antenna, and input/output devices. The processor can be used to process communication protocols and communication data, and can also be used to control the UE, execute software programs, and process data from the software programs. The UE may also include a memory, which is mainly used to store software programs and data. These programs can be loaded into the memory at the time the communication device leaves the factory, or they can be loaded into the memory later when needed. The RF circuitry is mainly used for converting baseband signals to RF signals and processing RF signals. The antenna is mainly used for transmitting and receiving RF signals in the form of electromagnetic waves, and the antenna is the antenna provided in the embodiments of this application. Input/output devices, such as touchscreens, displays, and keyboards, are mainly used to receive user input data and output data to the user. It should be noted that some types of UEs may not have input/output devices.

When data needs to be transmitted, the processor performs baseband processing on the data to be transmitted and outputs a baseband signal to the radio frequency (RF) circuit. The RF circuit then processes the baseband signal and transmits it outward as an electromagnetic wave through the antenna. When data is sent to the UE, the RF circuit receives the RF signal through the antenna, converts it into a baseband signal, and outputs the baseband signal to the processor. The processor converts the baseband signal back into data and processes it. For ease of explanation, only one memory and processor are shown in Figure 10. In actual UE products, there may be one or more processors and one or more memories. Memory can also be called storage medium or storage device, etc. Memory can be set up independently of the processor or integrated with the processor; this application embodiment does not limit this.

In this embodiment, the antenna and radio frequency circuit with transceiver functions can be regarded as the receiving unit and transmitting unit of the UE (or collectively referred to as the transceiver unit), and the processor with processing functions can be regarded as the processing unit of the UE. As shown in Figure 10, the UE includes a receiving module 31, a processing module 32, and a transmitting module 33. The receiving module 31 can also be referred to as a receiver, receiver circuit, etc., and the transmitting module 33 can also be referred to as a transmitter, transmitter, transmitter circuit, etc. The processing module 32 can also be referred to as a processor, processing board, processing device, etc.

For example, processing module 32 is used to perform the functions of the reader in any of the above methods.

This application provides a communication device, which includes at least one processor and a memory; wherein the memory is used to store computer programs or instructions; and at least one processor is used to execute the computer programs or instructions in the memory, such that the methods corresponding to each device or network element in any of the above methods are executed.

This application provides a communication system, which includes a fourth device and a first device.

This application provides a communication system, which includes a fourth device, a first device, and a second device.

This application provides a communication system, which includes a fourth device, a first device, a second device, and a third device.

This application provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions, which, when executed, cause the computer to perform the method described in any of the above methods.

This application provides a computer program product, which includes computer program code. When the computer program code is run, it causes the computer to perform the method described in any of the above methods.

This application provides a chip coupled to a memory for reading and executing program instructions in the memory, so that the device containing the chip implements the method described in any of the above methods.

In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not described in detail in a particular embodiment can be found in the relevant descriptions of other embodiments. It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims (28)

A method for acquiring radio maps, characterized in that the method includes: Obtain task information, wherein the task information corresponds to multiple first tasks; Based on the task information, one or more first radio maps are determined, and the first task has a mapping relationship with the first radio map. The method according to claim 1, wherein determining one or more first radio maps based on the task information comprises: Send a first request message to the first device, the first request message being used to request the acquisition of one or more first radio maps corresponding to the task information; Receive a first response message from the first device, the first response message indicating the one or more first radio maps. The method according to claim 1, wherein determining one or more first radio maps based on the task information comprises: The plurality of first tasks are determined based on the task information; One or more first radio maps are determined based on the plurality of first tasks. The method according to claim 3, wherein determining the plurality of first tasks based on the task information includes: Send a second request message to the second device, the second request message being used to request the acquisition of multiple first tasks corresponding to the task information; Receive a second response message from the second device, the second response message indicating the plurality of first tasks. The method according to claim 3, wherein determining the plurality of first tasks based on the task information includes: The task information vector corresponding to the task information is input into the first model for processing to obtain the plurality of first tasks. The first model is used to perform classification planning for the first tasks. The method according to claim 3, wherein determining the plurality of first tasks based on the task information includes: The task information, prompt information, and task information database are input into a second model for processing to obtain the plurality of first tasks. The second model is used to retrieve the first tasks, and the prompt information is used to indicate that the first task corresponding to the task information is determined by searching the task information database. The method according to any one of claims 3-6, characterized in that determining one or more first radio maps based on the plurality of first tasks comprises: The one or more first radio maps corresponding to the plurality of first tasks are determined based on the stored mapping relationship between the first tasks and the first radio maps. The method according to any one of claims 3-6, characterized in that determining one or more first radio maps based on the plurality of first tasks comprises: A third request message is sent to the first device, the third request message being used to request the acquisition of one or more first radio maps corresponding to the plurality of first tasks, the first device including the mapping relationship between the second tasks and the first radio maps, the second tasks including the plurality of first tasks; Receive a third response message from the first device, the third response message indicating one or more first radio maps corresponding to the plurality of first tasks. The method according to claim 8, characterized in that, before determining the first radio map based on the task information, the method further includes: aligning the second task with the first device. The method according to claim 9, wherein aligning the second task with the first device comprises: Receive the second task from the first device; or Send the second task to the first device and receive an acknowledgment message from the first device, the acknowledgment message indicating that the second task sent to the first device is the same as the second task stored in the second device; or The device receives the second task from a third device, which is also configured to send the second task to the first device. The method according to claim 9 or 10, characterized in that, after aligning the second task with the first device, the method further comprises: The mapping relationship between the third task and the first radio map is obtained and stored from the first device, wherein the third task is all or part of the second task. The method according to claim 11, wherein acquiring and storing the mapping relationship between the third task and the first radio map from the first device comprises: According to a preset period, the mapping relationship between the third task and the first radio map is obtained from the first device and stored. Alternatively, the mapping relationship between the third task and the first radio map can be obtained from the first device and stored according to the usage of the mapping relationship; Alternatively, the mapping relationship between the third task and the first radio map can be obtained from the first device according to the operation instructions. The method according to claim 11 or 12, characterized in that, after obtaining and storing the mapping relationship between the third task and the first radio map from the first device, the method further includes: Delete low-frequency mapping relationships, which are the stored mapping relationships that use frequencies lower than a preset frequency threshold and/or use intervals exceeding a preset interval threshold. A method for acquiring radio maps, characterized in that the method includes: A first request message is received from a fourth device. The first request message is used to request one or more first radio maps corresponding to task information, or to request one or more first radio maps corresponding to multiple first tasks. The task information corresponds to multiple first tasks, and there is a mapping relationship between the first tasks and the one or more first radio maps. Send a first response message, which indicates the one or more first radio maps. The method according to claim 14, characterized in that, when the first request message is used to request the acquisition of one or more first radio maps corresponding to task information, the method further includes: The plurality of first tasks are determined based on the task information; Obtain one or more first radio maps corresponding to the plurality of first tasks. The method according to claim 14 or 15, characterized in that, obtaining one or more first radio maps corresponding to the plurality of first tasks includes: One or more first radio maps corresponding to the plurality of first tasks are determined based on the stored mapping relationship between the second tasks and the first radio maps, wherein the second tasks include the plurality of first tasks. The method according to claim 15, wherein determining the plurality of first tasks based on the task information includes: The task information vector corresponding to the task information is input into the first model for processing to obtain the plurality of first tasks. The first model is used to perform classification planning for the first tasks. The method according to claim 15, wherein determining the plurality of first tasks based on the task information includes: The task information, prompt information, and task information database are input into a second model for processing to obtain the plurality of first tasks. The second model is used to retrieve the first tasks, and the prompt information is used to indicate that the first task corresponding to the task information is determined by searching the task information database. The method according to any one of claims 16-18, characterized in that the method further comprises: Send the mapping relationship between the third task and the first radio map to the fourth device, wherein the third task is all or part of the second task. A method for acquiring radio maps, characterized in that the method includes: Receive a second request message from a fourth device, the second request message being used to request the acquisition of multiple first tasks corresponding to the task information; Send a second response message, which indicates the plurality of first tasks. The method according to claim 20, characterized in that, after receiving the second request message from the fourth device, the method further includes: The task information vector corresponding to the task information is input into the first model for processing to obtain the plurality of first tasks. The first model is used to perform classification planning for the first tasks. The method according to claim 20, characterized in that, after receiving the second request message from the fourth device, the method further includes: The task information, prompt information, and task information database are input into a second model for processing to obtain the plurality of first tasks. The second model is used to retrieve the first tasks, and the prompt information is used to indicate that the first task corresponding to the task information is determined by searching the task information database. A communication device, characterized in that it includes a unit or module for implementing the method as described in any one of claims 1 to 22. A communication device, characterized in that, The communication device includes at least one processor coupled to a memory; The at least one processor is configured to execute a computer program or instructions stored in the memory, such that the method of any one of claims 1 to 22 is performed. A communication system, characterized in that, The communication system includes a fourth device, a first device, and a second device; The fourth device is used to perform the method as described in any one of claims 1 to 13, the first device is used to perform the method as described in any one of claims 14 to 19, and the second device is used to perform the method as described in any one of claims 20 to 22. A chip system, characterized in that the chip system includes at least one processor, a memory, and an interface circuit, wherein the memory, the interface circuit, and the at least one processor are interconnected via circuits, and the at least one memory stores instructions; when the instructions are executed by the processor, the method described in any one of claims 1-22 is implemented. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, which, when executed, enables the implementation of the method according to any one of claims 1-22. A computer program product, characterized in that the computer program product includes instructions, which, when executed, enable the method described in any one of claims 1-22.