Wireless communication method and device

Abstract

The embodiment of the invention provides a wireless communication method and device, and a first communication device can monitor the prediction performance of a first positioning model according to at least one network model, and does not need the precise position of a terminal in the model monitoring process. After the output information of the first positioning model is obtained, the performance monitoring of the first positioning model can be completed, so that the positioning precision of the first positioning model is ensured. The wireless communication method comprises the following steps: a first communication device monitors the prediction performance of a first positioning model according to at least one network model; wherein the input information of the at least one network model is output information of the first positioning model, or the input information of the at least one network model is determined based on the output information of the first positioning model, or the input information of the at least one network model is associated with the output information of the first positioning model; wherein the output information of the at least one network model is pre-estimated for the input information of the first positioning model.

Description

Wireless communication method and device Technical Field

[0001] The present invention relates to the field of communications, and more specifically, to a method and device for wireless communications. Background Art

[0002] In New Radio (NR) systems, artificial intelligence (AI) and machine learning (ML) can be introduced to improve system performance. For example, AI / ML can be used for terminal positioning, where trained AI / ML models are used to predict terminal location information, improving terminal positioning accuracy. However, when the wireless propagation environment changes, the effectiveness of the AI / ML model may be difficult to guarantee. Therefore, monitoring the effectiveness of the AI / ML model is a problem that needs to be solved.

[0003] Summary of the Invention

[0004] An embodiment of the present application provides a method and device for wireless communication, in which a first communication device can monitor the predictive performance of a first positioning model based on at least one network model. The precise location of the terminal is not required during the model monitoring process. After obtaining the output information of the first positioning model, the performance monitoring of the first positioning model can be completed, thereby ensuring the positioning accuracy of the first positioning model.

[0005] In a first aspect, a wireless communication method is provided, the method comprising:

[0006] The first communication device monitors the prediction performance of the first positioning model based on at least one network model;

[0007] The input information of the at least one network model is the output information of the first positioning model, or the input information of the at least one network model is determined based on the output information of the first positioning model, or the input information of the at least one network model is associated with the output information of the first positioning model;

[0008] The output information of the at least one network model is an estimate of the input information of the first positioning model.

[0009] In a second aspect, a communication device is provided. The communication device is a first communication device, configured to execute the method in the first aspect.

[0010] Specifically, the communication device includes a functional model for executing the method in the first aspect above.

[0011] In a third aspect, a communication device is provided, which is a first communication device, and includes a processor and a memory; the memory is used to store computer programs, and the processor is used to call and run the computer programs stored in the memory, so that the communication device executes the method in the above-mentioned first aspect.

[0012] In a fourth aspect, a device is provided for implementing the method in the first aspect. Specifically, the device includes: a processor configured to call and execute a computer program from a memory, so that a device equipped with the device executes the method in the first aspect.

[0013] In a fifth aspect, a computer-readable storage medium is provided for storing a computer program, which enables a computer to execute the method in the first aspect.

[0014] In a sixth aspect, a computer program product is provided, comprising computer program instructions, wherein the computer program instructions enable a computer to execute the method in the first aspect.

[0015] In a seventh aspect, a computer program is provided, which, when executed on a computer, enables the computer to execute the method in the first aspect.

[0016] Through the above technical solution, the first communication device can monitor the predictive performance of the first positioning model based on at least one network model. The precise location of the terminal is not required during the model monitoring process. After obtaining the output information of the first positioning model, the performance monitoring of the first positioning model can be completed, thereby ensuring the positioning accuracy of the first positioning model. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] FIG1 is a schematic diagram of a communication system architecture applied in an embodiment of the present application.

[0018] FIG2 is a schematic diagram of a neuron provided in the present application.

[0019] FIG3 is a schematic diagram of a neural network provided by the present application.

[0020] FIG4 is a schematic diagram of a convolutional neural network provided in this application.

[0021] FIG5 is a schematic diagram of an LSTM unit provided in this application.

[0022] FIG6 is a schematic diagram of a downlink-based positioning method provided in the present application.

[0023] FIG7 is a schematic diagram of an uplink-based positioning method provided in the present application.

[0024] FIG8 is a schematic diagram of the combination of an AI / ML model and a positioning method provided in this application.

[0025] FIG9 is a schematic flowchart of a wireless communication method provided according to an embodiment of the present application.

[0026] FIG10 is a schematic diagram of monitoring the prediction performance of a first positioning model based on a first network model according to an embodiment of the present application.

[0027] FIG11 is a schematic flowchart of periodic monitoring feedback by an LMF entity provided according to an embodiment of the present application.

[0028] FIG12 is a schematic flowchart of a LMF entity performing non-periodic monitoring feedback according to an embodiment of the present application.

[0029] FIG13 is a schematic flowchart of another LMF entity performing non-periodic monitoring feedback according to an embodiment of the present application.

[0030] FIG14 is a schematic flowchart of periodic monitoring feedback by a UE according to an embodiment of the present application.

[0031] FIG15 is a schematic flowchart of a UE performing non-periodic monitoring feedback according to an embodiment of the present application.

[0032] FIG16 is a schematic diagram of monitoring the prediction performance of the first positioning model based on the second network model and the third network model according to an embodiment of the present application.

[0033] FIG17 is another schematic diagram of monitoring the prediction performance of the first positioning model based on the second network model and the third network model according to an embodiment of the present application.

[0034] Figure 18 is a schematic flowchart of an LMF entity performing cross-checking and periodically performing monitoring feedback according to an embodiment of the present application.

[0035] FIG19 is a schematic flowchart of another LMF entity performing periodic monitoring feedback according to an embodiment of the present application.

[0036] Figure 20 is a schematic block diagram of a communication device provided according to an embodiment of the present application.

[0037] Figure 21 is a schematic block diagram of another communication device provided according to an embodiment of the present application.

[0038] Figure 22 is a schematic block diagram of a device provided according to an embodiment of the present application.

[0039] Figure 23 is a schematic block diagram of a communication system provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0040] The following will describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. With respect to the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0041] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Global System of Mobile communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced Long Term Evolution (LTE-A) system, New Radio (NR) system, NR system evolution system, LTE-based access to unlicensed spectrum (LTE-U) system on unlicensed spectrum, NR-based access to unlicensed spectrum (NR-U) system on unlicensed spectrum, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Internet of Things (IoT), Wireless Fidelity (WFI) system. Fidelity, WiFi), fifth-generation communication (5th-Generation, 5G) system, sixth-generation communication (6G) system or other communication systems.

[0042] Generally speaking, traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communications, but will also support, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine type communication (MTC), vehicle-to-vehicle (V2V) communication, sidelink (SL) communication, vehicle-to-everything (V2X) communication, etc. The embodiments of the present application can also be applied to these communication systems.

[0043] In some embodiments, the communication system in the embodiments of the present application can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, an independent (SA) networking scenario, or a non-standalone (NSA) networking scenario.

[0044] In some embodiments, the communication system in the embodiments of the present application can be applied to an unlicensed spectrum, where the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiments of the present application can also be applied to an authorized spectrum, where the authorized spectrum can also be considered as an unshared spectrum.

[0045] In some embodiments, the communication system in the embodiments of the present application can be applied to the FR1 frequency band (corresponding to the frequency band range of 410MHz to 7.125GHz), can also be applied to the FR2 frequency band (corresponding to the frequency band range of 24.25GHz to 52.6GHz), and can also be applied to new frequency bands such as high-frequency bands corresponding to the frequency band range of 52.6GHz to 71GHz or the frequency band range of 71GHz to 114.25GHz.

[0046] The embodiments of the present application describe various embodiments in conjunction with network devices and terminal devices, wherein the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.

[0047] The terminal device can be a station (STA) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a next-generation communication system such as an NR network, or a terminal device in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0048] In an embodiment of the present application, the terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on the water surface (such as a ship, etc.); it can also be deployed in the air (for example, on an airplane, balloon, and satellite, etc.).

[0049] In an embodiment of the present application, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city or a wireless terminal device in a smart home, an in-vehicle communication device, a wireless communication chip / application specific integrated circuit (ASIC) / system on chip (SoC), etc.

[0050] As an example and not a limitation, in the embodiment of the present application, the terminal device may also be a wearable device. Wearable devices may also be called wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0051] In an embodiment of the present application, the network device may be a device for communicating with a mobile device. The network device may be an access point (AP) in WLAN, a base station (BTS) in GSM or CDMA, a base station (NodeB, NB) in WCDMA, an evolved base station (eNB or eNodeB) in LTE, or a relay station or access point, or a network device or base station (gNB) or a transmission reception point (TRP) in a vehicle-mounted device, a wearable device, and an NR network, or a network device in a future evolved PLMN network or a network device in an NTN network, etc.

[0052] As an example and not a limitation, in an embodiment of the present application, the network device may have a mobile feature, for example, the network device may be a mobile device. In some embodiments, the network device may be a satellite or a balloon station. For example, the satellite may be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. In some embodiments, the network device may also be a base station set up in a location such as land or water.

[0053] In an embodiment of the present application, the network device can provide services for a cell, and the terminal device communicates with the network device through the transmission resources used by the cell (for example, frequency domain resources, or spectrum resources). The cell can be a cell corresponding to the network device (for example, a base station). The cell can belong to a macro base station or a base station corresponding to a small cell. The small cells here may include: metro cells, micro cells, pico cells, femto cells, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.

[0054] For example, a communication system 100 used in an embodiment of the present application is shown in FIG1 . The communication system 100 may include a network device 110, which may be a device that communicates with a terminal device 120 (or a communication terminal or terminal). The network device 110 may provide communication coverage for a specific geographic area and may communicate with terminal devices within the coverage area.

[0055] FIG1 exemplarily shows a network device and two terminal devices. In some embodiments, the communication system 100 may include multiple network devices and each network device may include another number of terminal devices within its coverage area, which is not limited in the embodiments of the present application.

[0056] In some embodiments, the communication system 100 may further include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiments of the present application.

[0057] It should be understood that in the embodiments of the present application, a device having a communication function in a network / system may be referred to as a communication device. Taking the communication system 100 shown in FIG1 as an example, the communication device may include a network device 110 and a terminal device 120 having a communication function. The network device 110 and the terminal device 120 may be the specific devices described above and will not be described in detail here. The communication device may also include other devices in the communication system 100, such as a network controller, a mobility management entity, and other network entities, which are not limited in the embodiments of the present application.

[0058] It should be understood that the terms "system" and "network" are often used interchangeably herein. The term "and / or" is simply a description of an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " generally indicates that the related objects are in an "or" relationship.

[0059] The terms used in the embodiments of this application are intended only to explain the specific embodiments of this application and are not intended to limit this application. The terms "first," "second," "third," and "fourth," etc. in the specification and claims of this application and the accompanying drawings are used to distinguish different objects, not to describe a specific order. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions.

[0060] It should be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association between A and B.

[0061] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and being indicated, configuration and being configured, etc.

[0062] In the embodiments of the present application, "pre-definition" or "pre-configuration" may be implemented by pre-storing corresponding codes, tables, or other methods that can be used to indicate relevant information in a device (e.g., a terminal device and a network device). The present application does not limit the specific implementation method. For example, pre-definition may refer to information defined in a protocol.

[0063] In the embodiments of the present application, the “protocol” may refer to a standard protocol in the communications field, for example, it may be an evolution of an existing LTE protocol, NR protocol, Wi-Fi protocol, or a protocol related to other communication systems. The present application does not limit the protocol type.

[0064] To facilitate a better understanding of the embodiments of the present application, the neural network and machine learning (ML) related to the present application are explained.

[0065] A neural network is a computational model composed of multiple interconnected neuron nodes. The connections between nodes represent weighted values ​​from input signals to output signals, called weights. Each node performs a weighted summation (SUM) of different input signals and outputs them using a specific activation function (f). An example of a neuron structure is shown in Figure 2. A simple neural network, shown in Figure 3, consists of an input layer, a hidden layer, and an output layer. By using different connections between multiple neurons, weights, and activation functions, different outputs can be generated, thereby fitting the mapping relationship from input to output.

[0066] Deep learning utilizes deep neural networks with multiple hidden layers, significantly improving the network's ability to learn features and fitting complex, nonlinear mappings from input to output. Consequently, it has found widespread application in speech and image processing. In addition to deep neural networks, deep learning also includes other commonly used basic structures such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) for different tasks.

[0067] The basic structure of a convolutional neural network includes an input layer, multiple convolutional layers, multiple pooling layers, a fully connected layer, and an output layer, as shown in Figure 4. Each neuron in the convolution kernel of the convolutional layer is locally connected to its input, and the introduction of the pooling layer extracts the local maximum or average features of a certain layer, effectively reducing the network parameters and mining local features, enabling the convolutional neural network to converge quickly and achieve excellent performance.

[0068] RNNs are neural networks that model sequential data and have achieved remarkable success in natural language processing applications such as machine translation and speech recognition. Specifically, the network memorizes information from past moments and uses it in the calculation of current outputs. This means that nodes in the hidden layers are no longer disconnected but connected, and the input to a hidden layer includes not only the input layer but also the output of the previous hidden layer. Common RNN structures include long short-term memory (LSTM) and gated recurrent unit (GRU). Figure 5 shows a basic LSTM cell structure, which can include a tanh activation function. Unlike RNNs, which only consider the most recent state, the LSTM cell state determines which states should be retained and which should be forgotten, addressing the shortcomings of traditional RNNs in long-term memory.

[0069] To facilitate a better understanding of the embodiments of the present application, the positioning technology in NR related to the present application is explained.

[0070] The positioning methods in NR can be classified as follows:

[0071] UE-based positioning method: the terminal device directly calculates the location of the target device;

[0072] UE-assisted positioning method / LMF-based positioning method: The terminal device reports the measurement results to the Location Management Function (LMF), and the LMF calculates the target device's location based on the collected measurement results;

[0073] Next-generation Radio Access Network (NG-RAN) node-assisted positioning method: The base station reports the measurement results of the Transmission Reception Point (TRP) to the LMF, and the LMF calculates the location of the target device based on the collected measurement results.

[0074] In traditional positioning methods, for different methods, the UE or LMF applies traditional algorithms, such as the Chan algorithm, Taylor expansion, etc., to estimate the location of the target device.

[0075] To support various positioning methods, NR introduces a Positioning Reference Signal (PRS) in the downlink and a Sounding Reference Signal (SRS) for positioning in the uplink.

[0076] The NR-based positioning function mainly involves three parts: terminal (UE), multiple TRPs and positioning server (Location Server); among them, multiple TRPs around the terminal participate in cellular positioning, a base station may be a TRP, and a base station may have multiple TRPs under it. The positioning server is responsible for the entire positioning process and often includes a positioning management function (LMF) entity.

[0077] Downlink-based positioning methods can be further divided into the following two categories: terminal-assisted positioning methods (UE-assisted) and UE-based positioning methods (UE-based).

[0078] Specifically, in a terminal-assisted positioning method (UE-assisted), the UE is responsible for positioning-related measurements, and the network calculates location information based on measurement results reported by the UE.

[0079] Specifically, in a UE-based positioning method, the UE performs positioning-related measurements and calculates location information based on the measurement results.

[0080] In some embodiments, a downlink-based positioning method (UE-assisted positioning method) is used as an example to illustrate the basic process, as shown in FIG6 , which may specifically include the following steps 1 to 5:

[0081] Step 1: The positioning server notifies the TRP-related configuration, which may include PRS configuration information and / or the type of measurement results that the terminal needs to report;

[0082] Step 2: TRP sends a positioning signal PRS;

[0083] Step 3: The terminal receives the positioning signal PRS and performs measurement. Depending on the positioning method, the measurement results required by the terminal are different.

[0084] Step 4: The terminal feeds back the measurement result to the positioning server; wherein the terminal feeds back the measurement result to the positioning server through the base station;

[0085] Step 5: The positioning server calculates the location-related information.

[0086] Specifically, Figure 6 illustrates a process flow for UE-assisted positioning. For terminal-based positioning (UE-based), in step 4 above, the terminal directly calculates location-related information based on measurement results, eliminating the need to report these results to a positioning server. This network element then performs the calculations. With UE-based positioning, the terminal needs to know the location information corresponding to the TRP, so the network must notify the UE of this information in advance.

[0087] In some embodiments, a basic process is described by taking an uplink-based positioning method as an example, as shown in FIG7 , which may specifically include the following steps 1 to 5:

[0088] Step 1: The positioning server notifies the TRP of the relevant configuration;

[0089] Step 2: The base station sends relevant signaling to the terminal;

[0090] Step 3: The terminal sends an uplink signal (SRS for positioning);

[0091] Step 4: The TRP measures the SRS for positioning and sends the measurement results to the positioning server.

[0092] Step 5: The positioning server calculates the location-related information.

[0093] To facilitate a better understanding of the embodiments of the present application, the AI-based positioning method related to the present application is described.

[0094] In 3GPP, AI-based positioning enhancement is widely discussed as a research project. The positioning method based on artificial intelligence (AI) extracts the potential mapping relationship between model input information and terminal location, and uses a large amount of labeled data for training, so that the model can significantly improve positioning accuracy in a fixed environment. By combining with the positioning method in NR, it replaces the traditional algorithm to estimate the location of the terminal device, thereby improving positioning accuracy. The AI / ML model can be deployed on the UE side or on the LMF side, or on both the UE and LMF sides. The combination of the AI / ML model and the positioning method can be divided into AI / ML direct positioning and AI / ML assisted positioning. Specifically, as shown in Figure 8, the model input of AI-based direct positioning is generally measurement signals such as channel impulse response (CIR) and channel power delay profile (PDP), and the AI ​​model output is the location of the terminal device; for AI-based assisted positioning, the model input is the same, but the model output is some intermediate results, such as the downlink time of arrival (DL TOA) between the terminal device and multiple base stations, or the downlink time difference of arrival (DL TDOA), or line of sight (LOS) / non-line of sight (NLOS) identification results. The terminal device or LMF entity then uses these intermediate results and adopts the positioning algorithm in NR to further obtain the location of the terminal device.

[0095] In order to facilitate a better understanding of the embodiments of the present application, the problems solved by the present application are explained.

[0096] Disadvantages of NR positioning methods: Existing positioning methods in NR systems rely on LoS paths between terminal devices and multiple base stations, calculating terminal positions based on geometric relationships. However, in environments with severe NLoS, such as typical indoor factory environments, the probability of a LoS path between terminal devices and base stations is very low. This results in very poor performance of NR positioning methods that use geometric relationships, and the horizontal positioning error cannot meet actual requirements.

[0097] Disadvantages of AI-based positioning methods: While AI-based positioning methods can achieve centimeter-level horizontal positioning accuracy, they also have significant issues. Due to the limited generalization performance of AI models, they are only applicable to relatively fixed scenarios. For example, when the wireless environment changes within a space, the original AI model may no longer adapt, resulting in reduced positioning performance. Furthermore, in the case of AI-based positioning, due to the difficulty in obtaining accurate positioning information during actual deployment, such as the location of terminal devices and DL TDOA information, it is impossible to monitor and verify the effectiveness of the AI ​​model. How to solve the problem of AI-based positioning accuracy monitoring is a technical challenge that needs to be solved.

[0098] Based on the above problems, this application proposes a solution for monitoring the predictive performance of the positioning model. The precise location of the terminal is not required during the model monitoring process. The performance monitoring of the positioning model can be completed after obtaining the output information of the positioning model, thereby ensuring the positioning accuracy of the positioning model.

[0099] To facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions of the present application are described in detail below through specific embodiments. The following related technologies can be combined with the technical solutions of the embodiments of the present application as optional solutions, and they all fall within the scope of protection of the embodiments of the present application. The embodiments of the present application include at least part of the following contents.

[0100] FIG9 is a schematic flowchart of a wireless communication method 200 according to an embodiment of the present application. As shown in FIG9 , the wireless communication method 200 may include at least part of the following contents:

[0101] S210, the first communication device monitors the prediction performance of the first positioning model based on at least one network model; wherein the input information of the at least one network model is the output information of the first positioning model, or the input information of the at least one network model is determined based on the output information of the first positioning model, or the input information of the at least one network model is associated with the output information of the first positioning model; wherein the output information of the at least one network model is an estimate of the input information of the first positioning model.

[0102] In the embodiment of the present application, the first positioning model is used to implement terminal positioning.

[0103] In an embodiment of the present application, the first communication device can monitor the predictive performance of the first positioning model based on at least one network model. The precise location of the terminal is not required during the model monitoring process. The performance monitoring of the first positioning model can be completed after obtaining the output information of the first positioning model, thereby ensuring the positioning accuracy of the first positioning model.

[0104] In an embodiment of the present application, the input information of the at least one network model is the output information of the first positioning model, or the input information of the at least one network model is determined based on the output information of the first positioning model, or the input information of the at least one network model is associated with the output information of the first positioning model, that is, the at least one network model is a dual model of the first positioning model.

[0105] It should be noted that the network model described in the embodiments of the present application may be an AI / ML model.

[0106] In an embodiment of the present application, when the prediction result of the first positioning model is inaccurate, it is necessary to perform operations such as model switching or model online updating.

[0107] In some embodiments, the "first positioning model" described in the embodiments of the present application can also be replaced by a network model used to implement other functions (such as CSI feedback, beam prediction, etc.), and the embodiments of the present application are not limited to this.

[0108] In some embodiments, the first communication device is a terminal device.

[0109] In some embodiments, the first communication device is a network device, for example, a LMF entity, an access network device (such as a base station).

[0110] In some embodiments, the input information of the first positioning model includes but is not limited to at least one of the following: CIR, channel PDP, DL TOA, and DL TDOA.

[0111] In some embodiments, the output information of the first positioning model includes but is not limited to at least one of the following: location information of the terminal device, DL TOA, and DL TDOA.

[0112] It should be noted that in two-dimensional space positioning, the location information of the terminal device is generally a binary vector composed of the terminal's horizontal coordinates (x, y); in three-dimensional space positioning, the location information of the terminal device is generally a ternary vector composed of the terminal's three-dimensional coordinates (x, y, z).

[0113] In some embodiments, when the number of the at least one network model is greater than or equal to 2, different network models are implemented using different model architectures. For example, one network model uses a fully connected network model architecture, while another network model uses a convolutional neural network model architecture. In this embodiment, by using different dual model architectures, the probability of simultaneous false detection of at least one network model is reduced, thereby improving the model monitoring accuracy of the dual model.

[0114] In some embodiments, the at least one network model includes a first network model, that is, the first network model is a dual model of the first positioning model, the input information of the first network model is the output information of the first positioning model, or, the input information of the first network model is determined based on the output information of the first positioning model (such as the output information of the first positioning model is quantized with a certain accuracy to obtain the input information of the first network model), or, the input information of the first network model is associated with the output information of the first positioning model, and the output information of the first network model is an estimate of the input information of the first positioning model.

[0115] In some embodiments, the above S210 may specifically include:

[0116] The first communication device monitors the prediction performance of the first positioning model according to a check value obtained by checking the first check function;

[0117] The check value corresponding to the first check function is used to reflect the similarity between the output information of the first network model and the input information of the first positioning model.

[0118] Specifically, as shown in FIG10 , the check value corresponding to the first check function is used to reflect the similarity between the output information of the first network model and the input information of the first positioning model.

[0119] In this embodiment, the prediction performance of the first positioning model can be monitored based on the dual model (i.e., the first network model) without the actual location of the terminal as a reference. The forward mapping and reverse mapping relationships between the terminal location and the input information of the first positioning model are utilized to evaluate the accuracy of the first positioning model through the dual model (i.e., the first network model).

[0120] For example, taking the input information of the first positioning model as CIR (denoted as h1), the output information of the first network model is the estimate of CIR, denoted as h2. Here, the first network model is called the dual model of the first positioning model, which is used to extract the mapping relationship from the terminal location information (input information of the first network model) to the channel information (output information of the first network model). In fact, it uses the AI ​​method to simulate the channel generation process in the positioning model, and can be considered as a type of channel generator based on AI implementation. Specifically, the first verification function is defined as r(h1,h2), and the verification value corresponding to the first verification function is used to reflect the similarity between the output information of the first network model and the input information of the first positioning model.

[0121] In some embodiments, the first verification function can calculate the verification value through indicators such as mean square error (MSE), normalized mean square error (NMSE), and cosine similarity (CS); or, the first verification function is a pre-trained AI function that can output the verification value by inputting the output information of the first network model and the input information of the first positioning model.

[0122] In some embodiments, when the check value obtained by the first check function is greater than or equal to the first threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, when the check value obtained by the first check function is less than the first threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

[0123] That is, in this embodiment, when the check value obtained by the first check function is greater than or equal to the first threshold, it is considered that the output information of the first network model is highly consistent with the input information of the first positioning model. At this time, it means that the output information of the first positioning model (that is, the positioning coordinates) and the actual position error of the terminal are small, and the first positioning model can work normally in the current environment; when the check value obtained by the first check function is less than the first threshold, it means that the output information of the first network model and the input information of the first positioning model are less consistent, which means that the output information of the first positioning model (that is, the positioning coordinates) and the actual position error of the terminal are high, that is, the positioning accuracy is low, and it is considered that the positioning accuracy of the first positioning model does not meet the requirements, and it is necessary to perform model switching or model online update and other operations.

[0124] In some embodiments, when a value obtained by filtering a plurality of check values ​​obtained by checking the first check function within the first time length is greater than or equal to a first threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or when a value obtained by filtering a plurality of check values ​​obtained by checking the first check function within the first time length is less than the first threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

[0125] Optionally, the filtering processing corresponding to the multiple verification values ​​obtained by verifying the first verification function within the first time period includes:

[0126] The first verification function takes the average of multiple verification values ​​obtained by verification within the first time length, or the first verification function takes the weighted average of multiple verification values ​​obtained by verification within the first time length, or the first verification function takes the average of multiple verification values ​​obtained by verification within the first time length after removing the maximum value and / or minimum value, or the first verification function takes the weighted average of multiple verification values ​​obtained by verification within the first time length after removing the maximum value and / or minimum value.

[0127] Of course, the filtering process described in this embodiment can also be implemented through other filtering algorithms, and this application is not limited to this.

[0128] In some embodiments, when multiple verification values ​​obtained by the first verification function within the first time length are all greater than or equal to the first threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, when there is a verification value less than the first threshold among the multiple verification values ​​obtained by the first verification function within the first time length, the first communication device determines that the prediction result of the first positioning model is inaccurate.

[0129] In some embodiments, when the probability that the multiple verification values ​​obtained by the first verification function within the first time period are greater than or equal to the first threshold is greater than or equal to the second threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, when the probability that the multiple verification values ​​obtained by the first verification function within the first time period are greater than or equal to the first threshold is less than the second threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

[0130] It should be noted that the first duration may also be referred to as the first time window, or a similar name, and this application does not limit this.

[0131] In some embodiments, the first threshold is agreed upon by a protocol, or the first threshold is configured by a network device.

[0132] In some embodiments, the second threshold is agreed upon by a protocol, or the second threshold is configured by a network device.

[0133] In some embodiments, as example 1, the first communication device is an LMF entity, the first network model is deployed on the LMF entity side, and the first positioning model is deployed on the terminal device side.

[0134] Optionally, in Example 1, the first network model is a cell-granularity network model, and the first positioning model is a terminal-granularity network model. In other words, since the first positioning model is deployed on the terminal side, the first positioning model is considered terminal-specific, that is, different terminals can use different positioning models to implement the positioning function; and since the first network model is deployed on the LMF entity side, the first network model is cell-specific and can monitor different positioning models of different terminals.

[0135] Specifically, when the first positioning model is deployed on the terminal device side and the first network model is deployed on the LMF entity side, the LMF entity monitors and manages the first positioning model. At this time, the output information of the first positioning model is quantized and fed back to the LMF entity side by the terminal device, and the input information of the first network model is obtained through dequantization on the LMF entity side.

[0136] In order for the LMF entity side to monitor the first positioning model, the terminal device should also feed back the input information of the first positioning model to the LMF entity side, so that the LMF entity can calculate the verification function (i.e., the first verification function) between the input information of the first positioning model and the output information of the first network model, and determine whether the verification value obtained by the first verification function reaches the first threshold, thereby monitoring the prediction performance of the first positioning model (i.e., determining the availability of the first positioning model). Specifically, the input information of the first positioning model and the output information of the first positioning model can be fed back through the first feedback information.

[0137] Optionally, in Example 1, the first communication device receives first feedback information sent by the terminal device;

[0138] The first feedback information includes input information of the first positioning model and / or output information of the first positioning model.

[0139] In Example 1, the terminal device may periodically send the first feedback information (ie, periodic monitoring feedback), or the terminal device may trigger a non-periodic sending of the first feedback information (ie, triggered a non-periodic monitoring feedback).

[0140] Specifically, the first communication device may obtain input information of the first network model based on output information of the first positioning model, and the first communication device may determine a check value based on the input information of the first positioning model.

[0141] Optionally, the first feedback information may be carried by at least one of the following: Radio Resource Control (RRC) signaling, Media Access Control Control Element (MAC CE), and uplink control information (UCI).

[0142] Optionally, in Example 1, before the first communication device receives the first feedback information, the first communication device sends first configuration information to the terminal device;

[0143] Among them, the first configuration information is used to configure at least one of the following: the feedback format of the input information of the first positioning model, the terminal device feedbacks the input information of the first positioning model within the first time length, the feedback format of the output information of the first positioning model, and the terminal device feedbacks the output information of the first positioning model within the first time length.

[0144] Optionally, in Example 1, when the first feedback information is periodically sent information, the first configuration information is also used to configure the periodic information of the terminal device to feedback the input information of the first positioning model and / or the output information of the first positioning model.

[0145] Specifically, for periodic monitoring feedback, after the terminal accesses the network, the LMF entity configures the feedback period T of the first feedback information and the time window length (i.e., the first duration) W of each feedback period, the feedback format of the input information of the first positioning model, and the feedback format of the output information of the first positioning model through the first configuration information. For example, the quantization method, the effective length of the input information of the first positioning model, etc. Among them, the effective length of the input information of the first positioning model, taking the input information of the first positioning model as CIR as an example, can include the following aspects:

[0146] a: In the time dimension, you can configure the reporting to only report the first N1 paths of the CIR.

[0147] b: In the spatial dimension, only the N2 TRPs with the highest power can be configured to be reported;

[0148] c: Configure reporting of the first N1 paths of the N2 TRPs with the largest feedback power in both the time and space dimensions.

[0149] d: Other possible methods of truncating or extracting the first input information.

[0150] The above first configuration information is performed by the LMF entity and indicated to the terminal through downlink signaling. The signaling can be RRC, MAC CE or DCI signaling, or dedicated downlink signaling for model monitoring and management. Under periodic monitoring feedback, after the LMF entity completes the configuration of the terminal once, the parameters such as {T, W, N1, N2} are determined, and the terminal periodically sends the first feedback information according to the parameters until the subsequent LMF entity updates the first configuration information through downlink signaling.

[0151] Optionally, the first configuration information may be carried by at least one of the following: RRC signaling, MAC CE, downlink control information (Downlink Control Information, DCI).

[0152] Optionally, in Example 1, for triggered non-periodic monitoring feedback, the first configuration information is also used to trigger the terminal device to feedback the input information of the first positioning model and / or the output information of the first positioning model. Specifically, when triggered by the LMF entity side, the LMF entity can directly trigger model monitoring by sending the first configuration information to the terminal. Similarly, the first configuration information does not include the feedback period T, but only includes parameters such as {W, N1, N2}. After the LMF entity receives the first feedback information, the LMF entity verifies and filters the feedback information obtained within the time window W through the first network model, and indicates the monitoring results of the first positioning model to the terminal.

[0153] Optionally, in Example 1, for triggered non-periodic monitoring feedback, before the first communication device sends the first configuration information, the first communication device receives a first model monitoring request sent by the terminal device; wherein, the first model monitoring request is used to request monitoring of the prediction performance of the first positioning model, and the first model monitoring request triggers the first communication device to send the first configuration information. Specifically, when triggered by the terminal side, the terminal can trigger the LMF entity to send the first configuration information through the first model monitoring request, and the first configuration information does not include the feedback period T, but only includes parameters such as {W, N1, N2}. The first model monitoring request can be carried by uplink signaling, for example, UCI, or other uplink dedicated signaling for model monitoring and management. After the LMF entity receives the first feedback information, the LMF entity verifies and filters the feedback information obtained within the time window W through the first network model, and indicates the monitoring result of the first positioning model to the terminal.

[0154] Optionally, in Example 1, for triggered non-periodic monitoring feedback, the first communication device sends first monitoring information to the terminal device; wherein, the first monitoring information is used to indicate that the prediction result of the first positioning model is inaccurate, or, the first monitoring information is used to indicate whether the prediction result of the first positioning model is accurate. Specifically, after the LMF entity completes the monitoring of the first positioning model deployed on the terminal side, it indicates to the terminal through downlink signaling whether the first positioning model used for AI positioning is applicable to the current environment and whether its positioning result is reliable. When it is indicated that the first positioning model is unreliable, strategies such as model switching or model updating can be further considered.

[0155] Optionally, in Example 1, for periodic monitoring feedback, the first communication device periodically sends second monitoring information to the terminal device; wherein, the second monitoring information is used to indicate whether the prediction result of the first positioning model is accurate within the corresponding period. Specifically, after the LMF entity completes the monitoring of the first positioning model deployed on the terminal side, it indicates to the terminal through downlink signaling whether the first positioning model used for AI positioning is applicable to the current environment and whether its positioning results are reliable. When it is indicated that the first positioning model is unreliable, strategies such as model switching or model updating can be further considered.

[0156] In Example 1, for periodic monitoring feedback, the signaling flow chart of periodic monitoring feedback on the LMF entity side is shown in Figure 11. For aperiodic monitoring feedback triggered by the LMF entity, the signaling flow chart of aperiodic monitoring feedback triggered by the LMF entity is shown in Figure 12. For aperiodic monitoring feedback triggered by the terminal, the signaling flow chart of aperiodic monitoring feedback triggered by the terminal is shown in Figure 13.

[0157] In some embodiments, as Example 2, the first communication device is a LMF entity, and the first network model and the first positioning model are both deployed on the LMF entity side.

[0158] In Example 2, when the first network model and the first positioning model are both deployed on the LMF entity side, the input information of the first positioning model required for the positioning function of the first positioning model is measured and fed back by the terminal. Here, since the first network model is also located on the LMF entity side, the input information of the first positioning model used for model monitoring and the output information of the first positioning model no longer need to be reported by the terminal separately and can be obtained directly on the LMF entity side.

[0159] Optionally, in Example 2, the first network model and the first positioning model are both cell-granularity network models. Specifically, the first positioning model on the LMF entity side is cell-specific, that is, multiple terminals in the current environment share the first positioning model for positioning; the first network model is also cell-specific, so the monitoring results of the first positioning model through the first network model are also applicable to all terminals in the cell. The monitoring results of the first network model at this time can be obtained by filtering the long-term verification values ​​of different terminals.

[0160] Optionally, in Example 2, the first communication device sends third monitoring information;

[0161] The third monitoring information is used to indicate that the prediction result of the first positioning model is inaccurate.

[0162] Optionally, in Example 2, the monitoring of the prediction performance of the first positioning model is performed periodically, or the monitoring of the prediction performance of the first positioning model is performed aperiodically.

[0163] Optionally, in Example 2, when the monitoring of the predictive performance of the first positioning model is performed periodically, the monitoring period of the predictive performance of the first positioning model is agreed upon by a protocol, or the monitoring period of the predictive performance of the first positioning model is determined by the first communication device.

[0164] In Example 2, when the monitoring result of the first positioning model on the LMF entity side meets the requirements, the LMF entity may not make any instructions to the terminal. At this time, the terminal assumes that the first positioning model is working normally and the positioning accuracy meets the requirements; when the monitoring result of the first positioning model on the LMF entity side does not meet the requirements, the LMF entity indicates to the terminal device through downlink signaling that the positioning accuracy of the first positioning model on the LMF entity side does not meet the requirements. The monitoring process is determined by the LMF entity side and can be triggered by the LMF entity periodically or non-periodically. The monitoring process is not visible on the terminal side.

[0165] In some embodiments, as Example 3, the first communication device is a terminal device, and the first network model and the first positioning model are both deployed on the terminal device side.

[0166] In Example 3, when the first network model and the first positioning model are both deployed on the terminal side, the input information of the first positioning model required for the positioning function of the first positioning model is measured and obtained by the terminal. Here, since the first network model is also located on the terminal side, the input information of the first positioning model used for model monitoring and the output information of the first positioning model can be obtained directly on the terminal side.

[0167] Optionally, in Example 3, both the first network model and the first positioning model are terminal-granular network models. Specifically, the first positioning model on the terminal side is terminal-specific; and since the first network model is also deployed on the terminal side, the first network model is also terminal-specific, and different terminals can use different implementation methods. Therefore, the monitoring results of the first positioning model using the first network model are also applicable only to the corresponding terminal.

[0168] In Example 3, the model monitoring process on the terminal side is configured by the LMF entity and is performed in a periodic or aperiodic manner.

[0169] Optionally, in Example 3, the first communication device sends fourth monitoring information; wherein the fourth monitoring information is used to indicate that the prediction result of the first positioning model is inaccurate, or the fourth monitoring information is used to indicate whether the prediction result of the first positioning model is accurate. In other words, in this example, the terminal device can autonomously send the fourth monitoring information without the need for network (such as LMF entity) configuration.

[0170] Optionally, the fourth monitoring information may be carried by at least one of the following: RRC signaling, UCI, MAC CE.

[0171] Optionally, in Example 3, the first communication device receives second configuration information;

[0172] The second configuration information is used to instruct the first communication device to periodically monitor the prediction performance of the first positioning model, or the second configuration information is used to instruct the first communication device to aperiodically monitor the prediction performance of the first positioning model.

[0173] Optionally, the second configuration information may be carried by at least one of the following: RRC signaling, DCI, MAC CE.

[0174] Optionally, in Example 3, when the second configuration information is used to instruct the first communication device to periodically monitor the predictive performance of the first positioning model, the second configuration information includes periodic information of the first communication device monitoring the predictive performance of the first positioning model, or, the periodic information of the first communication device monitoring the predictive performance of the first positioning model is agreed upon by the protocol, or, the periodic information of the first communication device monitoring the predictive performance of the first positioning model is determined by the first communication device.

[0175] Optionally, in Example 3, the first communication device sends fifth monitoring information;

[0176] The fifth monitoring information is used to indicate whether the prediction result of the first positioning model is accurate within the corresponding period.

[0177] Optionally, the fifth monitoring information may be carried by at least one of the following: RRC signaling, UCI, MAC CE.

[0178] Optionally, in Example 3, when the second configuration information is used to instruct the first communication device to non-periodically monitor the predictive performance of the first positioning model, the second configuration information includes first time offset information, and the first time offset information is used to indicate the time when the first communication device reports the monitoring results of the predictive performance of the first positioning model after receiving the second configuration information.

[0179] Optionally, in Example 3, the first communication device sends sixth monitoring information according to the first time offset information;

[0180] The sixth monitoring information is used to indicate whether the prediction result of the first positioning model is accurate.

[0181] Optionally, the sixth monitoring information may be carried by at least one of the following: RRC signaling, UCI, MAC CE.

[0182] For example, in Example 3, for periodic monitoring feedback, after the terminal accesses the network, the LMF entity configures the feedback period T of the model monitoring result through the second configuration information. During this period, the input information of the first positioning model and the output information of the first network model obtained by local measurement of the terminal are verified based on the first verification function, and multiple verification results are obtained. In this configuration, the time window (i.e., the first duration) W monitored by the terminal can be uniformly configured by the LMF entity through downlink signaling, or when the LMF entity is not configured, it can be determined by the terminal according to the default value or self-implementation. This time window (i.e., the first duration) W only affects how many times the output of the first network model and how many verification results are filtered to obtain the final monitoring result of the terminal, and does not affect the feedback overhead on the air interface. At the end of a period T, the terminal reports the model monitoring result of the period to the LMF entity. When the monitoring result indicates that the terminal model positioning accuracy does not meet the standard, the LMF entity can instruct and assist the terminal to perform operations such as model switching or model updating. The specific signaling process is shown in Figure 14.

[0183] For example, in Example 3, for triggered aperiodic monitoring feedback, aperiodic monitoring feedback triggered by the LMF entity or the terminal side can be supported. When triggered by the terminal side, the terminal can directly monitor the first positioning model locally through the first network model and report the results to the LMF entity side. When triggered by the LMF entity side, the LMF entity instructs the terminal to perform model monitoring through downlink signaling and report the model monitoring results. The downlink signaling needs to simultaneously indicate the reporting time offset D of the model monitoring result, that is, the model monitoring result is reported on the Dth time unit after the terminal receives the model monitoring instruction. Here, the model monitoring result is obtained by filtering multiple verification results within the time window W by the first network model on the terminal side. The time window W can be configured by the LMF entity at the same time as the reporting time offset D during downlink signaling. At this time, W<=D. It can also not be configured by the LMF entity, and the terminal adopts the default time window value W=D, or it can be determined by the terminal implementation. The specific signaling process triggered by the LMF entity side is shown in Figure 15.

[0184] In some embodiments, the at least one network model includes a second network model and a third network model, wherein the second network model and the third network model have different model architectures. For example, the second network model adopts a model architecture of a fully connected network, and the third network model adopts a model architecture of a convolutional neural network. In this embodiment, the second network model and the third network model are both dual models of the first positioning model, and the input information of the second network model is the output information of the first positioning model, or the input information of the second network model is determined based on the output information of the first positioning model (such as the output information of the first positioning model is quantized with a certain accuracy to obtain the input information of the second network model), or the input information of the second network model is associated with the output information of the first positioning model, the output information of the second network model is an estimate of the input information of the first positioning model, and the input information of the third network model is the output information of the first positioning model, or the input information of the third network model is determined based on the output information of the first positioning model (such as the output information of the first positioning model is quantized with a certain accuracy to obtain the input information of the third network model), or the input information of the third network model is associated with the output information of the first positioning model, and the output information of the third network model is an estimate of the input information of the first positioning model.

[0185] In this embodiment, the second network model and the third network model are both dual models of the first positioning model. Based on the setting of the dual dual models, it is not necessary to obtain the precise terminal location as a reference. By adopting dual model architectures with different implementation methods as much as possible, the probability of simultaneous false detection of the second network model and the third network model is reduced, thereby improving the model monitoring accuracy of the dual model. Compared with the above-mentioned solution of a single dual model (i.e., the first network model), it can avoid the poor verification performance caused by the unstable performance of the first network model, thereby avoiding the possibility of inaccurate monitoring of the first positioning model.

[0186] In some embodiments, the above S210 may specifically include:

[0187] The first communication device monitors the prediction performance of the first positioning model according to the check value obtained by checking the second check function and the check value obtained by checking the third check function;

[0188] Among them, the verification value corresponding to the second verification function is used to reflect the similarity between the output information of the second network model and the input information of the first positioning model, and the verification value corresponding to the third verification function is used to reflect the similarity between the output information of the third network model and the input information of the first positioning model.

[0189] Specifically, as shown in Figure 16, the verification value corresponding to the second verification function is used to reflect the similarity between the output information of the second network model and the input information of the first positioning model, and the verification value corresponding to the third verification function is used to reflect the similarity between the output information of the third network model and the input information of the first positioning model.

[0190] For example, taking the input information of the first positioning model as CIR (denoted as w1), the output information of the second network model and the output information of the third network model are both estimates of the CIR, denoted as w2 and w3 respectively. Here, the second network model and the third network model are both called dual models of the first positioning model, which are used to extract the mapping relationship from terminal location information (the input information of the second network model and the input information of the third network model) to channel information (the output information of the second network model and the output information of the third network model). In fact, it uses AI methods to simulate the channel generation process in the positioning model and can be considered as a type of channel generator based on AI implementation. Specifically, the second verification function is defined as r(w1, w2) and the third verification function is defined as r(w1, w3). The verification value corresponding to the second verification function is used to reflect the similarity between the output information of the second network model and the input information of the first positioning model, and the verification value corresponding to the third verification function is used to reflect the similarity between the output information of the third network model and the input information of the first positioning model.

[0191] In some embodiments, the second verification function can calculate the verification value through indicators such as mean square error (MSE), normalized mean square error (NMSE), cosine similarity (CS), etc.; or, the second verification function is a pre-trained AI function, which can output the verification value by inputting the output information of the second network model and the input information of the first positioning model.

[0192] In some embodiments, the third verification function can calculate the verification value through indicators such as mean square error (MSE), normalized mean square error (NMSE), cosine similarity (CS), etc.; or, the third verification function is a pre-trained AI function, which can output the verification value by inputting the output information of the third network model and the input information of the first positioning model.

[0193] In some embodiments, when the average of the check value corresponding to the second check function and the check value corresponding to the third check function is greater than or equal to a first threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, when the average of the check value corresponding to the second check function and the check value corresponding to the third check function is less than the first threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

[0194] That is, in this embodiment, when the average of the check value obtained by the second check function and the check value obtained by the third check function is greater than or equal to the first threshold, it is considered that the output information of the second network model is highly consistent with the input information of the first positioning model, and the output information of the third network model is also highly consistent with the input information of the first positioning model. At this time, it indicates that the output information of the first positioning model (i.e., the positioning coordinates) and the actual position error of the terminal are small, and the first positioning model can work normally in the current environment; when the average of the check value obtained by the second check function and the check value obtained by the third check function is less than the first threshold, that is, the output information of the second network model is less consistent with the input information of the first positioning model, and the output information of the third network model is also less consistent with the input information of the first positioning model, indicating that the output information of the first positioning model (i.e., the positioning coordinates) and the actual position error of the terminal are high, that is, the positioning accuracy is low, and it is considered that the positioning accuracy of the first positioning model does not meet the requirements, and it is necessary to perform model switching or model online update and other operations.

[0195] In some embodiments, when the average of the multiple verification values ​​obtained by the second verification function within the first time period after filtering and the average of the multiple verification values ​​obtained by the third verification function within the first time period after filtering is greater than or equal to a first threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, when the average of the multiple verification values ​​obtained by the second verification function within the first time period after filtering and the average of the multiple verification values ​​obtained by the third verification function within the first time period after filtering is less than the first threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

[0196] Optionally, the filtering processing corresponding to the multiple verification values ​​obtained by the second verification function within the first time period includes:

[0197] The second verification function takes the average of the multiple verification values ​​obtained by verification within the first time length, or takes the weighted average of the multiple verification values ​​obtained by verification within the first time length, or takes the average of the multiple verification values ​​obtained by verification within the first time length after removing the maximum value and / or minimum value, or takes the weighted average of the multiple verification values ​​obtained by verification within the first time length after removing the maximum value and / or minimum value.

[0198] Optionally, the filtering processing corresponding to the multiple verification values ​​obtained by the third verification function within the first time period includes:

[0199] The third verification function takes the average of multiple verification values ​​obtained by verification within the first time length, or the third verification function takes the weighted average of multiple verification values ​​obtained by verification within the first time length, or the third verification function takes the average of multiple verification values ​​after removing the maximum value and / or minimum value within the first time length, or the third verification function takes the weighted average of multiple verification values ​​after removing the maximum value and / or minimum value within the first time length.

[0200] Of course, the filtering process described in this embodiment can also be implemented through other filtering algorithms, and this application is not limited to this.

[0201] In some embodiments, when the average of the multiple verification values ​​obtained by the second verification function within the first time period and the multiple verification values ​​obtained by the third verification function within the first time period is greater than or equal to a first threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, when the average of the multiple verification values ​​obtained by the second verification function within the first time period and the multiple verification values ​​obtained by the third verification function within the first time period is less than the first threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

[0202] In some other embodiments, the above S210 may specifically include:

[0203] The first communication device monitors the prediction performance of the first positioning model using a check value obtained by checking the first communication device according to a fourth check function;

[0204] The check value corresponding to the fourth check function is used to reflect the similarity between the output information of the second network model and the output information of the third network model.

[0205] Specifically, as shown in Figure 17, the check value corresponding to the fourth check function is used to reflect the similarity between the output information of the second network model and the output information of the third network model. In other words, the first communications device can monitor the prediction performance of the first positioning model by verifying the similarity between the output information of the second network model and the output information of the third network model, without obtaining the input information of the first positioning model.

[0206] For example, the output information of the second network model and the output information of the third network model are both estimates of the input information of the first positioning model, and are denoted as s1 and s2 respectively. Specifically, the fourth verification function is defined as r(s1, s2), and the verification value corresponding to the fourth verification function is used to reflect the similarity between the output information of the second network model and the output information of the third network model. The fourth verification function can be understood as a cross-verification function, which uses the cross-verification function r(s1, s2) to calculate the similarity between the output information of the second network model and the output information of the third network model, and uses the verification result of the cross-verification function to indicate the monitoring result of the first positioning model.

[0207] In some embodiments, the fourth verification function can calculate the verification value through indicators such as mean square error (MSE), normalized mean square error (NMSE), cosine similarity (CS), etc.; or, the fourth verification function is a pre-trained AI function, which can output the verification value by inputting the output information of the second network model and the output information of the third network model.

[0208] In some embodiments, when the check value obtained by the fourth check function is greater than or equal to the third threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, when the check value obtained by the fourth check function is less than the third threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

[0209] In some embodiments, when a value obtained by filtering a plurality of check values ​​obtained by checking the fourth check function within the first time period is greater than or equal to a third threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or when a value obtained by filtering a plurality of check values ​​obtained by checking the fourth check function within the first time period is less than the third threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

[0210] Optionally, the filtering processing corresponding to the multiple verification values ​​obtained by the fourth verification function within the first time period includes:

[0211] The fourth verification function takes the average of the multiple verification values ​​obtained by verification within the first time length, or takes the weighted average of the multiple verification values ​​obtained by verification within the first time length, or takes the average of the multiple verification values ​​obtained by verification within the first time length after removing the maximum value and / or minimum value, or takes the weighted average of the multiple verification values ​​obtained by verification within the first time length after removing the maximum value and / or minimum value.

[0212] Of course, the filtering process described in this embodiment can also be implemented through other filtering algorithms, and this application is not limited to this.

[0213] In some embodiments, when multiple verification values ​​obtained by the fourth verification function within the first time period are all greater than or equal to the third threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, when there is a verification value less than the third threshold among the multiple verification values ​​obtained by the fourth verification function within the first time period, the first communication device determines that the prediction result of the first positioning model is inaccurate.

[0214] In some embodiments, when the probability that the multiple check values ​​obtained by the fourth check function within the first time period are greater than or equal to the third threshold is greater than or equal to the fourth threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, when the probability that the multiple check values ​​obtained by the fourth check function within the first time period are greater than or equal to the third threshold is less than the fourth threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

[0215] In some embodiments, the third threshold is agreed upon by a protocol, or the third threshold is configured by a network device.

[0216] In some embodiments, the fourth threshold is agreed upon by a protocol, or the fourth threshold is configured by a network device.

[0217] In some embodiments, as Example 4, the first communication device is an LMF entity, the second network model and the third network model are both deployed on the LMF entity side, and the first positioning model is deployed on the terminal device side.

[0218] In Example 4, the first communication device can monitor the prediction performance of the first positioning model based on the verification value obtained by the second verification function and the verification value obtained by the third verification function; and / or, the first communication device can monitor the prediction performance of the first positioning model based on the verification value obtained by the fourth verification function.

[0219] Optionally, in Example 4, the second network model and the third network model are both cell-granularity network models, and the first positioning model is a terminal-granularity network model. In other words, since the first positioning model is deployed on the terminal side, the first positioning model is considered to be terminal-specific, that is, different terminals can use different positioning models to implement the positioning function; and the second network model and the third network model are both deployed on the LMF entity side, so the second network model and the third network model are both cell-specific, and the second network model and the third network model can implement monitoring of different positioning models of different terminals.

[0220] Specifically, when the first positioning model is deployed on the terminal device side, and the second network model and the third network model are both deployed on the LMF entity side, the LMF entity monitors and manages the first positioning model. At this time, the output information of the first positioning model is quantified and fed back to the LMF entity side by the terminal device, and is dequantized on the LMF entity side to obtain the input information of the second network model and the input information of the third network model.

[0221] In the case where the first communication device monitors the prediction performance of the first positioning model based on the check value obtained by the second check function and the check value obtained by the third check function, in order for the LMF entity side to realize the monitoring of the first positioning model, the terminal device should also feed back the input information of the first positioning model to the LMF entity side, for the LMF entity to calculate the check function between the input information of the first positioning model and the output information of the second network model (i.e., the second check function) and the check function between the input information of the first positioning model and the output information of the third network model (i.e., the third check function), and judge whether the average of the check value obtained by the second check function and the check value obtained by the third check function reaches the first threshold, and then monitor the prediction performance of the first positioning model (i.e., judge the availability of the first positioning model). Specifically, the input information of the first positioning model and the output information of the first positioning model can be fed back through the first feedback information.

[0222] Optionally, in Example 4, the first communication device receives first feedback information sent by the terminal device;

[0223] The first feedback information includes input information of the first positioning model and / or output information of the first positioning model.

[0224] For example, when the first communication device can monitor the prediction performance of the first positioning model based on the check value obtained by checking the second check function and the check value obtained by checking the third check function, the first feedback information includes the input information of the first positioning model and the output information of the first positioning model.

[0225] For example, when the first communication device can monitor the prediction performance of the first positioning model according to the check value obtained by checking the fourth check function, the first feedback information may only include the output information of the first positioning model.

[0226] In Example 4, the terminal device may periodically send the first feedback information (ie, periodic monitoring feedback), or the terminal device may trigger a non-periodic sending of the first feedback information (ie, triggered a non-periodic monitoring feedback).

[0227] Optionally, in Example 4, before the first communication device receives the first feedback information, the first communication device sends first configuration information to the terminal device;

[0228] Among them, the first configuration information is used to configure at least one of the following: the feedback format of the input information of the first positioning model, the terminal device feedbacks the input information of the first positioning model within the first time length, the feedback format of the output information of the first positioning model, and the terminal device feedbacks the output information of the first positioning model within the first time length.

[0229] For example, when the first communication device can monitor the prediction performance of the first positioning model based on the check value obtained by checking the second check function and the check value obtained by checking the third check function, the first configuration information is used to configure at least one of the following: the feedback format of the input information of the first positioning model, the terminal device feeds back the input information of the first positioning model within the first time length, the feedback format of the output information of the first positioning model, and the terminal device feeds back the output information of the first positioning model within the first time length.

[0230] For example, when the first communication device can monitor the prediction performance of the first positioning model based on the check value obtained by checking the fourth check function, the first configuration information is used to configure at least one of the following: the feedback format of the output information of the first positioning model, and the terminal device feeds back the output information of the first positioning model within the first time length.

[0231] Optionally, in Example 4, when the first feedback information is information sent periodically, the first configuration information is also used to configure the periodic information of the terminal device to feedback the input information of the first positioning model and / or the output information of the first positioning model.

[0232] Specifically, for periodic monitoring feedback, after the terminal accesses the network, the LMF entity configures the feedback period T of the first feedback information and the time window length (i.e., the first duration) W of each feedback period, the feedback format of the input information of the first positioning model, and the feedback format of the output information of the first positioning model through the first configuration information. For example, the quantization method, the effective length of the input information of the first positioning model, etc. Among them, the effective length of the input information of the first positioning model, taking the input information of the first positioning model as CIR as an example, can include the following aspects:

[0233] a: In the time dimension, you can configure the reporting to only report the first N1 paths of the CIR.

[0234] b: In the spatial dimension, only the N2 TRPs with the highest power can be configured to be reported;

[0235] c: Configure reporting of the first N1 paths of the N2 TRPs with the largest feedback power in both the time and space dimensions.

[0236] d: Other possible methods of truncating or extracting the first input information.

[0237] The above first configuration information is performed by the LMF entity and indicated to the terminal through downlink signaling. The signaling can be RRC, MAC CE or DCI signaling, or dedicated downlink signaling for model monitoring and management. Under periodic monitoring feedback, after the LMF entity completes the configuration of the terminal once, the parameters such as {T, W, N1, N2} are determined, and the terminal periodically sends the first feedback information according to the parameters until the subsequent LMF entity updates the first configuration information through downlink signaling.

[0238] Optionally, the first configuration information may be carried by at least one of the following: RRC signaling, MAC CE, DCI.

[0239] Optionally, in Example 4, for triggered non-periodic monitoring feedback, the first configuration information is also used to trigger the terminal device to feedback the input information of the first positioning model and / or the output information of the first positioning model. Specifically, when triggered by the LMF entity side, the LMF entity can directly trigger model monitoring by sending the first configuration information to the terminal. Similarly, the first configuration information does not include the feedback period T, but only includes parameters such as {W, N1, N2}. After the LMF entity receives the first feedback information, the LMF entity verifies and filters the feedback information obtained within the time window W through the first network model, and indicates the monitoring results of the first positioning model to the terminal.

[0240] Optionally, in Example 4, for triggered non-periodic monitoring feedback, before the first communication device sends the first configuration information, the first communication device receives a first model monitoring request sent by the terminal device; wherein, the first model monitoring request is used to request monitoring of the prediction performance of the first positioning model, and the first model monitoring request triggers the first communication device to send the first configuration information. Specifically, when triggered by the terminal side, the terminal can trigger the LMF entity to send the first configuration information through the first model monitoring request, and the first configuration information does not include the feedback period T, but only includes parameters such as {W, N1, N2}. The first model monitoring request can be carried by uplink signaling, for example, UCI, or other uplink dedicated signaling for model monitoring and management. After the LMF entity receives the first feedback information, the LMF entity verifies and filters the feedback information obtained within the time window W through the first network model, and indicates the monitoring result of the first positioning model to the terminal.

[0241] Optionally, in Example 4, for triggered non-periodic monitoring feedback, the first communication device sends first monitoring information to the terminal device; wherein, the first monitoring information is used to indicate that the prediction result of the first positioning model is inaccurate, or, the first monitoring information is used to indicate whether the prediction result of the first positioning model is accurate. Specifically, after the LMF entity completes the monitoring of the first positioning model deployed on the terminal side, it indicates to the terminal through downlink signaling whether the first positioning model used for AI positioning is applicable to the current environment and whether its positioning result is reliable. When it is indicated that the first positioning model is unreliable, strategies such as model switching or model updating can be further considered.

[0242] Optionally, in Example 4, for periodic monitoring feedback, the first communication device periodically sends second monitoring information to the terminal device; wherein the second monitoring information is used to indicate whether the prediction result of the first positioning model is accurate within the corresponding period.

[0243] For example, the second network model and the third network model are both deployed on the LMF entity side, and the first positioning model is deployed on the terminal device side. When the first communication device can monitor the prediction performance of the first positioning model based on the verification value obtained by the fourth verification function (cross-verification function), the first feedback information can only include the output information of the first positioning model. The specific signaling interaction process of the LMF entity periodically monitoring the prediction performance of the first positioning model can be shown in Figure 18.

[0244] In some embodiments, as Example 5, the first communication device is an LMF entity, and the second network model, the third network model and the first positioning model are all deployed on the LMF entity side.

[0245] In Example 5, the first communication device can monitor the prediction performance of the first positioning model based on the verification value obtained by the second verification function and the verification value obtained by the third verification function; and / or, the first communication device can monitor the prediction performance of the first positioning model based on the verification value obtained by the fourth verification function.

[0246] In Example 5, when the second network model, the third network model, and the first positioning model are all deployed on the LMF entity side, the input information of the first positioning model required for the positioning function of the first positioning model is measured and fed back by the terminal. Here, since the second network model and the third network model are also located on the LMF entity side, the input information of the first positioning model used for model monitoring and / or the output information of the first positioning model no longer need to be reported additionally by the terminal, and can be obtained directly on the LMF entity side.

[0247] Optionally, in Example 5, the second network model, the third network model, and the first positioning model are all cell-granularity network models. Specifically, the first positioning model on the LMF entity side is cell-specific, that is, multiple terminals in the current environment share the first positioning model for positioning; the second network model and the third network model are also cell-specific, so the monitoring results of the first positioning model by the second network model and the third network model are also applicable to all terminals in the cell. The monitoring results of the second network model and the third network model at this time can be obtained by filtering the long-term verification values ​​of different terminals.

[0248] Optionally, in Example 5, the first communication device sends third monitoring information;

[0249] The third monitoring information is used to indicate that the prediction result of the first positioning model is inaccurate.

[0250] Optionally, in Example 5, the monitoring of the prediction performance of the first positioning model is performed periodically, or the monitoring of the prediction performance of the first positioning model is performed aperiodically.

[0251] Optionally, in Example 5, when the monitoring of the predictive performance of the first positioning model is performed periodically, the monitoring period of the predictive performance of the first positioning model is agreed upon by the protocol, or the monitoring period of the predictive performance of the first positioning model is determined by the first communication device.

[0252] In Example 5, when the monitoring result of the first positioning model on the LMF entity side meets the requirements, the LMF entity may not make any instructions to the terminal. At this time, the terminal assumes that the first positioning model is working normally and the positioning accuracy meets the requirements; when the monitoring result of the first positioning model on the LMF entity side does not meet the requirements, the LMF entity indicates to the terminal device through downlink signaling that the positioning accuracy of the first positioning model on the LMF entity side does not meet the requirements. The monitoring process is determined by the LMF entity side and can be triggered by the LMF entity periodically or non-periodically. The monitoring process is not visible on the terminal side.

[0253] In some embodiments, as Example 6, the first communication device is a terminal device, and the second network model, the third network model and the first positioning model are all deployed on the terminal device side.

[0254] In Example 6, the first communication device can monitor the prediction performance of the first positioning model based on the verification value obtained by the second verification function and the verification value obtained by the third verification function; and / or, the first communication device can monitor the prediction performance of the first positioning model based on the verification value obtained by the fourth verification function.

[0255] In Example 6, when the second network model, the third network model, and the first positioning model are all deployed on the terminal side, the input information of the first positioning model required for the positioning function of the first positioning model is measured and obtained by the terminal. Here, since the second network model and the third network model are also located on the terminal side, the input information of the first positioning model used for model monitoring and / or the output information of the first positioning model can be obtained directly on the terminal side.

[0256] Optionally, in Example 6, the second network model, the third network model, and the first positioning model are all terminal-granular network models. Specifically, the first positioning model on the terminal side is terminal-specific; and since the second and third network models are also deployed on the terminal side, the second and third network models are also terminal-specific, and different terminals can use different implementation methods. Therefore, the monitoring results of the first positioning model using the second and third network models are also applicable only to the corresponding terminals.

[0257] In Example 6, the model monitoring process on the terminal side is configured by the LMF entity and is performed in a periodic or aperiodic manner.

[0258] Optionally, in Example 6, the first communication device sends fourth monitoring information; wherein the fourth monitoring information is used to indicate that the prediction result of the first positioning model is inaccurate, or the fourth monitoring information is used to indicate whether the prediction result of the first positioning model is accurate. In other words, in this example, the terminal device can autonomously send the fourth monitoring information without the need for network (such as LMF entity) configuration.

[0259] Optionally, in Example 6, the first communication device receives second configuration information;

[0260] The second configuration information is used to instruct the first communication device to periodically monitor the prediction performance of the first positioning model, or the second configuration information is used to instruct the first communication device to aperiodically monitor the prediction performance of the first positioning model.

[0261] Optionally, in Example 6, when the second configuration information is used to instruct the first communication device to periodically monitor the predictive performance of the first positioning model, the second configuration information includes periodic information of the first communication device monitoring the predictive performance of the first positioning model, or the periodic information of the first communication device monitoring the predictive performance of the first positioning model is agreed upon by the protocol, or the periodic information of the first communication device monitoring the predictive performance of the first positioning model is determined by the first communication device.

[0262] Optionally, in Example 6, the first communication device sends fifth monitoring information;

[0263] The fifth monitoring information is used to indicate whether the prediction result of the first positioning model is accurate within the corresponding period.

[0264] Optionally, in Example 6, when the second configuration information is used to instruct the first communication device to non-periodically monitor the predictive performance of the first positioning model, the second configuration information includes first time offset information, and the first time offset information is used to indicate the time when the first communication device reports the monitoring results of the predictive performance of the first positioning model after receiving the second configuration information.

[0265] Optionally, in Example 6, the first communication device sends sixth monitoring information according to the first time offset information;

[0266] The sixth monitoring information is used to indicate whether the prediction result of the first positioning model is accurate.

[0267] For example, in Example 6, for periodic monitoring feedback, after the terminal accesses the network, the LMF entity configures the feedback period T of the model monitoring result through the second configuration information. During this period, the terminal locally measures the input information of the first positioning model, the output information of the second network model, and the output information of the third network model, and performs verification based on the second verification function and the third verification function, and obtains multiple verification results. Alternatively, during this period, the terminal locally measures the output information of the second network model and the output information of the third network model, and performs verification based on the fourth verification function, and obtains multiple verification results. In this configuration, the time window (i.e., the first duration) W monitored by the terminal can be uniformly configured by the LMF entity through downlink signaling, or when the LMF entity is not configured, it can be determined by the terminal according to the default value or by its own implementation. This time window (i.e., the first duration) W only affects how many times the output of the second network model and the third network model and how many verification results are filtered to obtain the final monitoring result of the terminal, and does not affect the feedback overhead on the air interface. At the end of a period T, the terminal reports the model monitoring result of the period to the LMF entity. When the monitoring result indicates that the terminal model positioning accuracy does not meet the standard, the LMF entity can instruct and assist the terminal to perform operations such as model switching or model updating.

[0268] For example, in Example 6, for triggered non-periodic monitoring feedback, non-periodic monitoring feedback triggered by the LMF entity or the terminal side can be supported. When triggered by the terminal side, the terminal can directly monitor the first positioning model locally through the second network model and the third network model, and report the results to the LMF entity side. When triggered by the LMF entity side, the LMF entity instructs the terminal to perform model monitoring through downlink signaling and report the model monitoring results. The downlink signaling needs to simultaneously indicate the reporting time offset D of the model monitoring result, that is, the model monitoring result is reported on the Dth time unit after the terminal receives the model monitoring instruction. Here, the model monitoring result is obtained by filtering multiple verification results within the time window W by the second network model and the third network model on the terminal side. The time window W can be configured by the LMF entity at the same time as the reporting time offset D during downlink signaling. At this time, W<=D, or it can not be configured by the LMF entity, and the terminal adopts the default time window value W=D, or it is determined by the terminal implementation.

[0269] In some embodiments, the at least one network model includes a second network model and a third network model, wherein the second network model and the third network model have different model architectures, the second network model and the first positioning model are both deployed on the terminal device side, the third network model is deployed on the LMF entity side, and the first communication device is an LMF entity.

[0270] In this embodiment, the second network model and the third network model are both dual models of the first positioning model. Based on the setting of the dual dual models, it is not necessary to obtain the precise terminal location as a reference. By adopting dual model architectures with different implementation methods as much as possible, the probability of simultaneous false detection of the second network model and the third network model is reduced, thereby improving the model monitoring accuracy of the dual model. Compared with the above-mentioned solution of a single dual model (i.e., the first network model), it can avoid the poor verification performance caused by the unstable performance of the first network model, thereby avoiding the possibility of inaccurate monitoring of the first positioning model.

[0271] In some embodiments, the above S210 may specifically include:

[0272] The first communication device monitors prediction performance of the first positioning model according to the verification information corresponding to the second verification function and the verification value corresponding to the third verification function;

[0273] The verification information corresponding to the second verification function is obtained from the terminal device, and the verification information corresponding to the second verification function includes a verification value corresponding to the second verification function, or the verification information corresponding to the second verification function includes a monitoring result for the first positioning model determined based on the verification value corresponding to the second verification function, and the verification value corresponding to the second verification function is used to reflect the similarity between the output information of the second network model and the input information of the first positioning model;

[0274] The check value corresponding to the third check function is used to reflect the similarity between the output information of the third network model and the input information of the first positioning model.

[0275] For example, the verification information corresponding to the second verification function includes the verification value corresponding to the second verification function, that is, the terminal device can directly report the verification result of the second network model (which can also be quantified and reported) to the LMF entity.

[0276] For example, the verification information corresponding to the second verification function includes the monitoring result of the first positioning model determined based on the verification value corresponding to the second verification function. For example, the terminal device adds a 1-bit indication field in the UCI to indicate whether the prediction result of the first positioning model determined on the terminal side is accurate.

[0277] In some embodiments, the second verification function can calculate the verification value through indicators such as mean square error (MSE), normalized mean square error (NMSE), cosine similarity (CS), etc.; or, the second verification function is a pre-trained AI function, which can output the verification value by inputting the output information of the second network model and the input information of the first positioning model.

[0278] In some embodiments, the third verification function can calculate the verification value through indicators such as mean square error (MSE), normalized mean square error (NMSE), cosine similarity (CS), etc.; or, the third verification function is a pre-trained AI function, which can output the verification value by inputting the output information of the third network model and the input information of the first positioning model.

[0279] That is, in this embodiment, a terminal with model monitoring capability reports the monitoring results of the second network model to the LMF entity side while reporting the second feedback information (including the input information and output information of the first positioning model). The LMF entity combines the monitoring results reported by the terminal with the monitoring results calculated by the third network model on the LMF entity side to determine whether the prediction results of the first positioning model are accurate.

[0280] In some embodiments, when the verification information corresponding to the second verification function includes a verification value corresponding to the second verification function, the first communications device monitors the prediction performance of the first positioning model according to the verification information corresponding to the second verification function and the verification value corresponding to the third verification function, including:

[0281] When the average of the check value corresponding to the second check function and the check value corresponding to the third check function is greater than or equal to the first threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or when the average of the check value corresponding to the second check function and the check value corresponding to the third check function is less than the first threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

[0282] In some embodiments, when the verification information corresponding to the second verification function includes a monitoring result for the first positioning model determined based on a verification value corresponding to the second verification function, the first communications device monitors the prediction performance of the first positioning model according to the verification information corresponding to the second verification function and the verification value corresponding to the third verification function, including:

[0283] The first communication device determines the monitoring result for the first positioning model determined based on the check value corresponding to the second check function as the final monitoring result, or the first communication device determines the monitoring result for the first positioning model determined based on the check value corresponding to the third check function as the final monitoring result;

[0284] Wherein, when the check value corresponding to the second check function is greater than or equal to the first threshold value, the monitoring result for the first positioning model is that the prediction result of the first positioning model is accurate; and / or, when the check value corresponding to the second check function is less than the first threshold value, the monitoring result for the first positioning model is that the prediction result of the first positioning model is inaccurate;

[0285] Among them, when the verification value corresponding to the third verification function is greater than or equal to the first threshold, the monitoring result for the first positioning model is that the prediction result of the first positioning model is accurate; and / or, when the verification value corresponding to the third verification function is less than the first threshold, the monitoring result for the first positioning model is that the prediction result of the first positioning model is inaccurate.

[0286] Specifically, in the case where the verification information corresponding to the second verification function includes the monitoring result for the first positioning model determined based on the verification value corresponding to the second verification function, whether the LMF entity determines the monitoring result for the first positioning model determined based on the verification value corresponding to the second verification function as the final monitoring result, or determines the monitoring result for the first positioning model determined based on the verification value corresponding to the third verification function as the final monitoring result, can be determined by the LMF based on its own implementation, or determined by instructions from other core network network elements. Preferably, the LMF entity determines the monitoring result for the first positioning model determined based on the verification value corresponding to the third verification function as the final monitoring result.

[0287] In some embodiments, the first communication device receives verification information and second feedback information corresponding to the second verification function sent by the terminal device; wherein the second feedback information includes input information of the first positioning model and output information of the first positioning model.

[0288] Optionally, the verification information and the second feedback information corresponding to the second verification function may be reported through the same signaling or through different signaling, which is not limited in this application.

[0289] In some embodiments, the second feedback information is carried by one of the following: RRC signaling, UCI, MAC CE.

[0290] In some embodiments, before the first communication device receives the second feedback information, the first communication device sends third configuration information to the terminal device; wherein the third configuration information is used to configure at least one of the following: the content included in the verification information corresponding to the second verification function, the feedback format of the input information of the first positioning model, and the feedback format of the output information of the first positioning model.

[0291] In some embodiments, the third configuration information is carried by one of the following: RRC signaling, DCI, MAC CE.

[0292] In some embodiments, the third configuration information is further used to trigger the terminal device to feed back input information of the first positioning model, output information of the first positioning model, and verification information corresponding to the second verification function.

[0293] In some embodiments, before the first communication device sends the third configuration information, the first communication device receives a second model monitoring request sent by the terminal device; wherein the second model monitoring request is used to request monitoring of the prediction performance of the first positioning model, and the second model monitoring request triggers the first communication device to send the third configuration information.

[0294] In some embodiments, the first communication device sends seventh monitoring information to the terminal device; wherein the seventh monitoring information is used to indicate that the prediction result of the first positioning model is inaccurate, or the seventh monitoring information is used to indicate whether the prediction result of the first positioning model is accurate.

[0295] In some embodiments, the seventh monitoring information is carried by one of the following: RRC signaling, DCI, MAC CE.

[0296] In some embodiments, the verification information corresponding to the second verification function and the second feedback information are information sent periodically; wherein, the third configuration information is also used to configure at least one of the following: periodic information of the terminal device feedback of the input information of the first positioning model and the output information of the first positioning model, and periodic information of the terminal device feedback of the verification information corresponding to the second verification function.

[0297] In some embodiments, the first communication device periodically sends eighth monitoring information to the terminal device;

[0298] The eighth monitoring information is used to indicate whether the prediction result of the first positioning model is accurate within the corresponding period.

[0299] In some embodiments, the eighth monitoring information is carried via one of the following: RRC signaling, DCI, MAC CE.

[0300] For example, for periodic monitoring feedback, when the terminal model monitoring result is reported as high-precision feedback (that is, the verification information corresponding to the second verification function includes the verification value corresponding to the second verification function), the LMF entity side combines and averages the model monitoring result reported by the terminal and the model monitoring result calculated locally by the LMF entity to obtain the final model monitoring result, and indicates it to the terminal through downlink signaling. At the end of a period T, the terminal reports the model monitoring result of the period to the LMF entity. When the monitoring result indicates that the terminal model positioning accuracy does not meet the standard, the LMF entity can instruct and assist the terminal to perform operations such as model switching or model updating. The specific signaling process is shown in Figure 19. After the terminal accesses the network, the LMF entity configures at least one of the following through the third configuration information: the content contained in the verification information corresponding to the second verification function, the feedback format of the input information of the first positioning model, and the feedback format of the output information of the first positioning model.

[0301] In some embodiments, the at least one network model includes a second network model and a third network model, wherein the second network model and the third network model have different model architectures, the second network model and the first positioning model are both deployed on the terminal device side, the third network model is deployed on the LMF entity side, and the first communication device is an LMF entity. In this case, it is also possible to determine whether the prediction result of the first positioning model is accurate by a cross-check method similar to the fourth verification function. For details, please refer to the above description of the fourth verification function, which will not be repeated here.

[0302] Therefore, in an embodiment of the present application, the first communication device can monitor the predictive performance of the first positioning model based on at least one network model. The precise location of the terminal is not required during the model monitoring process. The performance monitoring of the first positioning model can be completed after obtaining the output information of the first positioning model, thereby ensuring the positioning accuracy of the first positioning model.

[0303] Specifically, the embodiment of the present application designs a positioning model monitoring solution based on a dual model. By deploying the dual model on the terminal side or the LMF side, and utilizing the mapping relationship between the terminal position (i.e., the output information of the first positioning model) and the input information of the dual model, the similarity between the output of the dual model and the input of the positioning model is evaluated through a test function, thereby measuring the error between the output of the positioning model and the actual terminal position.

[0304] Specifically, the embodiment of the present application designs a positioning model monitoring method based on a dual dual model. By deploying two dual models with different implementation structures and merging the monitoring results of the two positioning models, while achieving positioning model monitoring, the dual model false detection rate can be reduced, further improving the monitoring accuracy of the positioning model. This solution also supports simultaneous model monitoring on the terminal and LMF sides, and reports and merges model monitoring results, further improving the accuracy of model monitoring.

[0305] The main advantage of the embodiments of the present application is that the positioning accuracy of the AI ​​model can be monitored without obtaining the precise terminal location coordinates on the terminal or LMF side. This can save the cost of obtaining the terminal location coordinates during the actual deployment process and improve the model monitoring and management efficiency of the entire positioning system. The embodiments of the present application support periodic and triggered non-periodic model monitoring methods on the terminal and LMF sides by designing corresponding information indication, feedback and monitoring signaling processes, so that the terminal and LMF can more effectively realize the monitoring of the positioning model and the subsequent life cycle management process according to actual conditions.

[0306] The above, in combination with Figures 9 to 19, describes in detail the method embodiment of the present application. The following, in combination with Figures 20 to 23, describes in detail the device embodiment of the present application. It should be understood that the device embodiment and the method embodiment correspond to each other, and similar descriptions can refer to the method embodiment.

[0307] FIG20 shows a schematic block diagram of a communication device 300 according to an embodiment of the present application. The communication device 300 is a first communication device. As shown in FIG20 , the communication device 300 includes:

[0308] The processing unit 310 is configured to monitor the prediction performance of the first positioning model based on at least one network model;

[0309] The input information of the at least one network model is the output information of the first positioning model, or the input information of the at least one network model is determined based on the output information of the first positioning model, or the input information of the at least one network model is associated with the output information of the first positioning model;

[0310] The output information of the at least one network model is an estimate of the input information of the first positioning model.

[0311] In some embodiments, the at least one network model includes a first network model;

[0312] The processing unit 310 is specifically configured to:

[0313] Monitoring the prediction performance of the first positioning model according to a check value obtained by checking the first check function;

[0314] The check value corresponding to the first check function is used to reflect the similarity between the output information of the first network model and the input information of the first positioning model.

[0315] In some embodiments, the processing unit 310 is specifically configured to:

[0316] If the check value obtained by checking the first check function is greater than or equal to the first threshold, determining that the prediction result of the first positioning model is accurate; and / or,

[0317] When the check value obtained by checking the first check function is less than the first threshold, it is determined that the prediction result of the first positioning model is inaccurate.

[0318] In some embodiments, the processing unit 310 is specifically configured to:

[0319] If a value obtained by filtering multiple verification values ​​obtained by verifying the first verification function within the first time period is greater than or equal to a first threshold, determining that the prediction result of the first positioning model is accurate; and / or,

[0320] When a value obtained after filtering of multiple verification values ​​obtained by verifying the first verification function within the first time period is less than a first threshold, it is determined that the prediction result of the first positioning model is inaccurate.

[0321] In some embodiments, the processing unit 310 is specifically configured to:

[0322] If multiple verification values ​​obtained by verifying the first verification function within the first time period are all greater than or equal to the first threshold, determining that the prediction result of the first positioning model is accurate; and / or,

[0323] When a verification value smaller than a first threshold exists among the multiple verification values ​​obtained by verifying the first verification function within the first time period, it is determined that the prediction result of the first positioning model is inaccurate.

[0324] In some embodiments, the processing unit 310 is specifically configured to:

[0325] If the probability that the first verification value obtained by verifying the first verification function within the first time period is greater than or equal to the first threshold is greater than or equal to the second threshold, determining that the prediction result of the first positioning model is accurate; and / or,

[0326] When the probability that the multiple verification values ​​obtained by verifying the first verification function within the first time period are greater than or equal to the first threshold is less than the second threshold, it is determined that the prediction result of the first positioning model is inaccurate.

[0327] In some embodiments, the at least one network model includes a second network model and a third network model, wherein the second network model and the third network model have different model architectures;

[0328] The processing unit 310 is specifically configured to:

[0329] Monitoring the prediction performance of the first positioning model according to a check value obtained by checking the second check function and a check value obtained by checking the third check function;

[0330] Among them, the verification value corresponding to the second verification function is used to reflect the similarity between the output information of the second network model and the input information of the first positioning model, and the verification value corresponding to the third verification function is used to reflect the similarity between the output information of the third network model and the input information of the first positioning model.

[0331] In some embodiments, the processing unit 310 is specifically configured to:

[0332] When the average of the check value corresponding to the second check function and the check value corresponding to the third check function is greater than or equal to the first threshold, determining that the prediction result of the first positioning model is accurate; and / or,

[0333] When the average of the check value corresponding to the second check function and the check value corresponding to the third check function is less than the first threshold, it is determined that the prediction result of the first positioning model is inaccurate.

[0334] In some embodiments, the processing unit 310 is specifically configured to:

[0335] If a value obtained after filtering of multiple verification values ​​obtained by the second verification function within the first time period and a mean value obtained after filtering of multiple verification values ​​obtained by the third verification function within the first time period are greater than or equal to a first threshold, determining that the prediction result of the first positioning model is accurate; and / or,

[0336] When the average of the multiple verification values ​​obtained by the second verification function within the first time period after filtering and the average of the multiple verification values ​​obtained by the third verification function within the first time period after filtering is less than the first threshold, it is determined that the prediction result of the first positioning model is inaccurate.

[0337] In some embodiments, the processing unit 310 is specifically configured to:

[0338] When an average of multiple verification values ​​obtained by verifying the second verification function within the first time period and an average of multiple verification values ​​obtained by verifying the third verification function within the first time period is greater than or equal to a first threshold, determining that the prediction result of the first positioning model is accurate; and / or,

[0339] When the average of the multiple verification values ​​obtained by the second verification function within the first time length and the multiple verification values ​​obtained by the third verification function within the first time length is less than the first threshold, it is determined that the prediction result of the first positioning model is inaccurate.

[0340] In some embodiments, the at least one network model includes a second network model and a third network model, wherein the second network model and the third network model have different model architectures;

[0341] The processing unit 310 is specifically configured to:

[0342] monitoring the prediction performance of the first positioning model according to a check value obtained by checking with a fourth check function;

[0343] The check value corresponding to the fourth check function is used to reflect the similarity between the output information of the second network model and the output information of the third network model.

[0344] In some embodiments, the processing unit 310 is specifically configured to:

[0345] If the check value obtained by checking the fourth check function is greater than or equal to the third threshold, determining that the prediction result of the first positioning model is accurate; and / or,

[0346] When the check value obtained by checking the fourth check function is less than the third threshold, it is determined that the prediction result of the first positioning model is inaccurate.

[0347] In some embodiments, the processing unit 310 is specifically configured to:

[0348] If a value obtained after filtering of multiple verification values ​​obtained by the fourth verification function within the first time period is greater than or equal to a third threshold, determining that the prediction result of the first positioning model is accurate; and / or,

[0349] When a value obtained after filtering of multiple verification values ​​obtained by the fourth verification function within the first time period is less than a third threshold, it is determined that the prediction result of the first positioning model is inaccurate.

[0350] In some embodiments, the processing unit 310 is specifically configured to:

[0351] If the plurality of verification values ​​obtained by verifying the fourth verification function within the first time period are all greater than or equal to the third threshold, determining that the prediction result of the first positioning model is accurate; and / or,

[0352] When a verification value smaller than a third threshold exists among the multiple verification values ​​obtained by verifying the fourth verification function within the first time period, it is determined that the prediction result of the first positioning model is inaccurate.

[0353] In some embodiments, the processing unit 310 is specifically configured to:

[0354] If the probability that the plurality of verification values ​​obtained by the fourth verification function within the first time period are greater than or equal to the third threshold is greater than or equal to the fourth threshold, determining that the prediction result of the first positioning model is accurate; and / or,

[0355] When the probability of the plurality of verification values ​​obtained by the fourth verification function within the first time period being greater than or equal to the third threshold is less than the fourth threshold, it is determined that the prediction result of the first positioning model is inaccurate.

[0356] In some embodiments, the first communication device is a location management function LMF entity, the first network model is deployed on the LMF entity side, and the first positioning model is deployed on the terminal device side.

[0357] In some embodiments, the first network model is a network model at a cell granularity, and the first positioning model is a network model at a terminal granularity.

[0358] In some embodiments, the first communication device is an LMF entity, the second network model and the third network model are both deployed on the LMF entity side, and the first positioning model is deployed on the terminal device side.

[0359] In some embodiments, the second network model and the third network model are both network models at a cell granularity, and the first positioning model is a network model at a terminal granularity.

[0360] In some embodiments, the communication device 300 further includes:

[0361] The communication unit 320 is configured to receive first feedback information sent by the terminal device;

[0362] The first feedback information includes input information of the first positioning model and / or output information of the first positioning model.

[0363] In some embodiments, before the first communication device receives the first feedback information, the communication unit 320 is further configured to send first configuration information to the terminal device;

[0364] Among them, the first configuration information is used to configure at least one of the following: the feedback format of the input information of the first positioning model, the terminal device feedbacks the input information of the first positioning model within the first time length, the feedback format of the output information of the first positioning model, and the terminal device feedbacks the output information of the first positioning model within the first time length.

[0365] In some embodiments, the first configuration information is further used to trigger the terminal device to feed back input information of the first positioning model and / or output information of the first positioning model.

[0366] In some embodiments, before the first communication device sends the first configuration information, the communication unit 320 is further configured to receive a first model monitoring request sent by the terminal device;

[0367] The first model monitoring request is used to request monitoring of the prediction performance of the first positioning model, and the first model monitoring request triggers the first communication device to send the first configuration information.

[0368] In some embodiments, the communication unit 320 is further configured to send first monitoring information to the terminal device;

[0369] The first monitoring information is used to indicate that the prediction result of the first positioning model is inaccurate, or the first monitoring information is used to indicate whether the prediction result of the first positioning model is accurate.

[0370] In some embodiments, the first feedback information is information sent periodically;

[0371] The first configuration information is further used to configure periodic information for the terminal device to feed back input information of the first positioning model and / or output information of the first positioning model.

[0372] In some embodiments, the communication unit 320 is further configured to periodically send second monitoring information to the terminal device;

[0373] The second monitoring information is used to indicate whether the prediction result of the first positioning model is accurate within the corresponding period.

[0374] In some embodiments, the first communication device is a LMF entity, and the first network model and the first positioning model are both deployed on the LMF entity side.

[0375] In some embodiments, the first network model and the first positioning model are both cell-granularity network models.

[0376] In some embodiments, the first communication device is a LMF entity, and the second network model, the third network model and the first positioning model are all deployed on the LMF entity side.

[0377] In some embodiments, the second network model, the third network model, and the first positioning model are all cell-granularity network models.

[0378] In some embodiments, the communication unit 320 is further configured to send third monitoring information;

[0379] The third monitoring information is used to indicate that the prediction result of the first positioning model is inaccurate.

[0380] In some embodiments, the monitoring of the prediction performance of the first positioning model is performed periodically, or the monitoring of the prediction performance of the first positioning model is performed aperiodically.

[0381] In some embodiments, when the monitoring of the predictive performance of the first positioning model is performed periodically, the monitoring period of the predictive performance of the first positioning model is agreed upon by a protocol, or the monitoring period of the predictive performance of the first positioning model is determined by the first communication device.

[0382] In some embodiments, the first communication device is a terminal device, and the first network model and the first positioning model are both deployed on the terminal device side.

[0383] In some embodiments, the first network model and the first positioning model are both terminal-granularity network models.

[0384] In some embodiments, the first communication device is a terminal device, and the second network model, the third network model and the first positioning model are all deployed on the terminal device side.

[0385] In some embodiments, the second network model, the third network model, and the first positioning model are all terminal-granularity network models.

[0386] In some embodiments, the communication unit 320 is further configured to send fourth monitoring information;

[0387] The fourth monitoring information is used to indicate that the prediction result of the first positioning model is inaccurate, or the fourth monitoring information is used to indicate whether the prediction result of the first positioning model is accurate.

[0388] In some embodiments, the communication unit 320 is further configured to receive second configuration information;

[0389] The second configuration information is used to instruct the first communication device to periodically monitor the prediction performance of the first positioning model, or the second configuration information is used to instruct the first communication device to aperiodically monitor the prediction performance of the first positioning model.

[0390] In some embodiments, when the second configuration information is used to instruct the first communication device to periodically monitor the predictive performance of the first positioning model, the second configuration information includes periodic information of the first communication device monitoring the predictive performance of the first positioning model, or the periodic information of the first communication device monitoring the predictive performance of the first positioning model is agreed upon by the protocol, or the periodic information of the first communication device monitoring the predictive performance of the first positioning model is determined by the first communication device.

[0391] In some embodiments, the communication unit 320 is further configured to send fifth monitoring information;

[0392] The fifth monitoring information is used to indicate whether the prediction result of the first positioning model is accurate within the corresponding period.

[0393] In some embodiments, when the second configuration information is used to instruct the first communication device to non-periodically monitor the prediction performance of the first positioning model, the second configuration information includes first time offset information, and the first time offset information is used to indicate the time when the first communication device reports the monitoring results of the prediction performance of the first positioning model after receiving the second configuration information.

[0394] In some embodiments, the communication unit 320 is further configured to send sixth monitoring information according to the first time offset information;

[0395] The sixth monitoring information is used to indicate whether the prediction result of the first positioning model is accurate.

[0396] In some embodiments, the at least one network model includes a second network model and a third network model, wherein the second network model and the third network model have different model architectures, the second network model and the first positioning model are both deployed on the terminal device side, the third network model is deployed on the LMF entity side, and the first communication device is an LMF entity;

[0397] The processing unit 310 is specifically configured to:

[0398] Monitoring prediction performance of the first positioning model according to verification information corresponding to the second verification function and a verification value corresponding to the third verification function;

[0399] The verification information corresponding to the second verification function is obtained from the terminal device, and the verification information corresponding to the second verification function includes a verification value corresponding to the second verification function, or the verification information corresponding to the second verification function includes a monitoring result for the first positioning model determined based on the verification value corresponding to the second verification function, and the verification value corresponding to the second verification function is used to reflect the similarity between the output information of the second network model and the input information of the first positioning model;

[0400] The check value corresponding to the third check function is used to reflect the similarity between the output information of the third network model and the input information of the first positioning model.

[0401] In some embodiments, when the verification information corresponding to the second verification function includes a verification value corresponding to the second verification function, the processing unit 310 is specifically configured to:

[0402] When the average of the check value corresponding to the second check function and the check value corresponding to the third check function is greater than or equal to the first threshold, determining that the prediction result of the first positioning model is accurate; and / or,

[0403] When the average of the check value corresponding to the second check function and the check value corresponding to the third check function is less than the first threshold, it is determined that the prediction result of the first positioning model is inaccurate.

[0404] In some embodiments, when the verification information corresponding to the second verification function includes a monitoring result for the first positioning model determined based on the verification value corresponding to the second verification function, the processing unit 310 is specifically configured to:

[0405] Determining the monitoring result for the first positioning model determined based on the verification value corresponding to the second verification function as the final monitoring result, or determining the monitoring result for the first positioning model determined based on the verification value corresponding to the third verification function as the final monitoring result;

[0406] Wherein, when the check value corresponding to the second check function is greater than or equal to the first threshold value, the monitoring result for the first positioning model is that the prediction result of the first positioning model is accurate; and / or, when the check value corresponding to the second check function is less than the first threshold value, the monitoring result for the first positioning model is that the prediction result of the first positioning model is inaccurate;

[0407] Among them, when the verification value corresponding to the third verification function is greater than or equal to the first threshold, the monitoring result for the first positioning model is that the prediction result of the first positioning model is accurate; and / or, when the verification value corresponding to the third verification function is less than the first threshold, the monitoring result for the first positioning model is that the prediction result of the first positioning model is inaccurate.

[0408] In some embodiments, the communication unit 320 is further configured to receive verification information and second feedback information corresponding to the second verification function sent by the terminal device;

[0409] The second feedback information includes input information of the first positioning model and output information of the first positioning model.

[0410] In some embodiments, before the first communication device receives the second feedback information, the communication unit 320 is further configured to send third configuration information to the terminal device;

[0411] The third configuration information is used to configure at least one of the following: content included in the verification information corresponding to the second verification function, a feedback format of input information of the first positioning model, and a feedback format of output information of the first positioning model.

[0412] In some embodiments, the third configuration information is further used to trigger the terminal device to feed back input information of the first positioning model, output information of the first positioning model, and verification information corresponding to the second verification function.

[0413] In some embodiments, before the first communication device sends the third configuration information, the communication unit 320 is further configured to receive a second model monitoring request sent by the terminal device;

[0414] The second model monitoring request is used to request monitoring of the prediction performance of the first positioning model, and the second model monitoring request triggers the first communication device to send the third configuration information.

[0415] In some embodiments, the communication unit 320 is further configured to send seventh monitoring information to the terminal device;

[0416] The seventh monitoring information is used to indicate that the prediction result of the first positioning model is inaccurate, or the seventh monitoring information is used to indicate whether the prediction result of the first positioning model is accurate.

[0417] In some embodiments, the verification information corresponding to the second verification function and the second feedback information are periodically sent information;

[0418] The third configuration information is further used to configure at least one of the following: periodic information of the terminal device feeding back the input information of the first positioning model and the output information of the first positioning model, and periodic information of the terminal device feeding back the verification information corresponding to the second verification function.

[0419] In some embodiments, the communication unit 320 is further configured to periodically send eighth monitoring information to the terminal device;

[0420] The eighth monitoring information is used to indicate whether the prediction result of the first positioning model is accurate within the corresponding period.

[0421] In some embodiments, the input information of the first positioning model includes at least one of the following: channel impulse response CIR, channel power delay profile PDP, downlink time of arrival DL TOA, downlink time difference of arrival DL TDOA; and / or,

[0422] The output information of the first positioning model includes at least one of the following: location information of the terminal device, DL TOA, and DL TDOA.

[0423] In some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip. The processing unit may be one or more processors.

[0424] It should be understood that the communication device 300 according to the embodiment of the present application may correspond to the first communication device in the method embodiment of the present application, and the above-mentioned and other operations and / or functions of each unit in the communication device 300 are respectively for implementing the corresponding processes of the first communication device in the method 200 shown in Figure 9. For the sake of brevity, they will not be repeated here.

[0425] Figure 21 is a schematic structural diagram of a communication device 400 provided in an embodiment of the present application. The communication device 400 shown in Figure 21 includes a processor 410, which can call and run a computer program from a memory to implement the method in the embodiment of the present application.

[0426] In some embodiments, as shown in FIG21 , the communication device 400 may further include a memory 420. The processor 410 may call and execute a computer program from the memory 420 to implement the method in the embodiment of the present application.

[0427] The memory 420 may be a separate device independent of the processor 410 , or may be integrated into the processor 410 .

[0428] In some embodiments, as shown in FIG. 21 , the communication device 400 may further include a transceiver 430 , and the processor 410 may control the transceiver 430 to communicate with other devices. Specifically, the transceiver 430 may send information or data to other devices, or receive information or data sent by other devices.

[0429] The transceiver 430 may include a transmitter and a receiver. The transceiver 430 may further include an antenna, and the number of antennas may be one or more.

[0430] In some embodiments, the processor 410 may implement the functions of a processing unit in the communication device 300 , which will not be described in detail here for the sake of brevity.

[0431] In some embodiments, the transceiver 430 may implement the functionality of a communication unit in the communication device 300 , which will not be described in detail here for the sake of brevity.

[0432] In some embodiments, the communication device 400 may specifically be the communication device 300 of the embodiment of the present application, and the communication device 400 may implement the corresponding processes implemented by the first communication device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0433] Figure 22 is a schematic structural diagram of an apparatus according to an embodiment of the present application. The apparatus 500 shown in Figure 22 includes a processor 510, which can call and execute a computer program from a memory to implement the method according to the embodiment of the present application.

[0434] In some embodiments, as shown in FIG22 , the apparatus 500 may further include a memory 520. The processor 510 may call and execute a computer program from the memory 520 to implement the method in the embodiment of the present application.

[0435] The memory 520 may be a separate device independent of the processor 510 , or may be integrated into the processor 510 .

[0436] In some embodiments, the processor 510 may implement the functions of a processing unit in the communication device 300 , which will not be described in detail here for the sake of brevity.

[0437] In some embodiments, the apparatus 500 may further include an input interface 530. The processor 510 may control the input interface 530 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips. Optionally, the processor 510 may be located inside or outside the chip.

[0438] In some embodiments, the input interface 530 may implement the functionality of a communication unit in the communication device 300 .

[0439] In some embodiments, the apparatus 500 may further include an output interface 540. The processor 510 may control the output interface 540 to communicate with other devices or chips, specifically, to output information or data to other devices or chips. Optionally, the processor 510 may be located inside or outside the chip.

[0440] In some embodiments, the output interface 540 may implement the functionality of a communication unit in the communication device 300 .

[0441] In some embodiments, the apparatus can be applied to the communication device 300 in the embodiments of the present application, and the apparatus can implement the corresponding processes implemented by the first communication device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0442] In some embodiments, the device mentioned in the embodiments of the present application may also be a chip, such as a system-on-chip, a system-on-chip, a chip system, or a system-on-chip chip.

[0443] FIG23 is a schematic block diagram of a communication system 600 provided in an embodiment of the present application. As shown in FIG23 , the communication system 600 includes a terminal device 610 and a LMF entity 620 .

[0444] Among them, the terminal device 610 can be used to implement the corresponding functions implemented by the terminal device in the above method, and the LMF entity 620 can be used to implement the corresponding functions implemented by the LMF entity in the above method. For the sake of brevity, they will not be repeated here.

[0445] It should be understood that the processor of the embodiments of the present application may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by hardware integrated logic circuits in the processor or software instructions. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly implemented as a hardware decoding processor, or can be implemented by a combination of hardware and software models in the decoding processor. The software model can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0446] It is understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0447] It should be understood that the above-mentioned memories are exemplary but not restrictive. For example, the memories in the embodiments of the present application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM RAM (DR RAM), etc. In other words, the memories in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0448] An embodiment of the present application also provides a computer-readable storage medium for storing a computer program.

[0449] In some embodiments, the computer-readable storage medium can be applied to the first communication device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the first communication device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0450] An embodiment of the present application also provides a computer program product, including computer program instructions.

[0451] In some embodiments, the computer program product can be applied to the first communication device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the first communication device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0452] The embodiment of the present application also provides a computer program.

[0453] In some embodiments, the computer program can be applied to the first communication device in the embodiments of the present application. When the computer program runs on a computer, the computer executes the corresponding processes implemented by the first communication device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0454] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0455] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0456] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0457] The units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0458] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0459] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. In view of this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0460] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A wireless communication method, characterized in that: include: The first communication device monitors the prediction performance of the first positioning model based on at least one network model; The input information of the at least one network model is the output information of the first positioning model, or the input information of the at least one network model is determined based on the output information of the first positioning model, or the input information of the at least one network model is associated with the output information of the first positioning model; The output information of the at least one network model is an estimate of the input information of the first positioning model.

2. The method according to claim 1, characterized in that The at least one network model comprises a first network model; The first communication device monitors the prediction performance of the first positioning model according to at least one network model, including: The first communication device monitors the prediction performance of the first positioning model according to a check value obtained by checking the first check function; The check value corresponding to the first check function is used to reflect the similarity between the output information of the first network model and the input information of the first positioning model.

3. The method according to claim 2, characterized in that The first communication device monitors the prediction performance of the first positioning model according to the check value obtained by checking the first check function, including: When the check value obtained by checking the first check function is greater than or equal to the first threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, When the check value obtained by checking the first check function is less than a first threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

4. The method according to claim 2, characterized in that The first communication device monitors the prediction performance of the first positioning model according to the check value obtained by checking the first check function, including: When a value obtained after filtering of multiple check values ​​obtained by checking the first check function within the first time period is greater than or equal to a first threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, When a value obtained by filtering a plurality of check values ​​obtained by checking the first check function within the first time period is less than a first threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

5. The method according to claim 2, characterized in that The first communication device monitors the prediction performance of the first positioning model according to the check value obtained by checking the first check function, including: When multiple check values ​​obtained by checking the first check function within the first time period are all greater than or equal to the first threshold, the first communications device determines that the prediction result of the first positioning model is accurate; and / or, When there is a check value less than a first threshold among multiple check values ​​obtained by checking the first check function within the first time length, the first communications device determines that the prediction result of the first positioning model is inaccurate.

6. The method according to claim 2, characterized in that The first communication device monitors the prediction performance of the first positioning model according to the check value obtained by checking the first check function, including: When the probability that the first verification function is greater than or equal to the first threshold among the multiple verification values ​​obtained by the first verification function within the first time period is greater than or equal to the second threshold, the first communications device determines that the prediction result of the first positioning model is accurate; and / or, When the probability that the multiple verification values ​​obtained by the first verification function within the first time period are greater than or equal to the first threshold is less than the second threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

7. The method according to claim 1, characterized in that The at least one network model comprises a second network model and a third network model, wherein the second network model and the third network model have different model architectures; The first communication device monitors the prediction performance of the first positioning model according to at least one network model, including: The first communication device monitors the prediction performance of the first positioning model according to the check value obtained by checking the second check function and the check value obtained by checking the third check function; Among them, the verification value corresponding to the second verification function is used to reflect the similarity between the output information of the second network model and the input information of the first positioning model, and the verification value corresponding to the third verification function is used to reflect the similarity between the output information of the third network model and the input information of the first positioning model.

8. The method according to claim 7, characterized in that The first communication device monitors the prediction performance of the first positioning model according to the check value obtained by checking the second check function and the check value obtained by checking the third check function, including: When the average of the check value corresponding to the second check function and the check value corresponding to the third check function is greater than or equal to the first threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, When the average of the check value corresponding to the second check function and the check value corresponding to the third check function is less than the first threshold value, In this case, the first communication device determines that the prediction result of the first positioning model is inaccurate.

9. The method according to claim 7, characterized in that The first communication device monitors the prediction performance of the first positioning model according to the check value obtained by checking the second check function and the check value obtained by checking the third check function, including: When the average of the multiple verification values ​​obtained by filtering the second verification function within the first time period and the average of the multiple verification values ​​obtained by filtering the third verification function within the first time period is greater than or equal to the first threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, When the average of the multiple check values ​​obtained by filtering the second check function within the first time period and the average of the multiple check values ​​obtained by filtering the third check function within the first time period are less than the first threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

10. The method according to claim 7, characterized in that The first communication device monitors the prediction performance of the first positioning model according to the check value obtained by checking the second check function and the check value obtained by checking the third check function, including: When the average of multiple check values ​​obtained by checking the second check function within the first time length and the average of multiple check values ​​obtained by checking the third check function within the first time length is greater than or equal to a first threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, When the average of multiple verification values ​​obtained by the second verification function within the first time length and the average of multiple verification values ​​obtained by the third verification function within the first time length are less than a first threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

11. The method according to claim 1, characterized in that The at least one network model comprises a second network model and a third network model, wherein the second network model and the third network model have different model architectures; The first communication device monitors the prediction performance of the first positioning model according to at least one network model, including: The first communication device monitors the prediction performance of the first positioning model according to a check value obtained by checking with a fourth check function; The check value corresponding to the fourth check function is used to reflect the similarity between the output information of the second network model and the output information of the third network model.

12. The method according to claim 11, characterized in that The first communication device monitors the prediction performance of the first positioning model according to the check value obtained by checking the fourth check function, including: When the check value obtained by checking the fourth check function is greater than or equal to the third threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, When the check value obtained by checking the fourth check function is less than the third threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

13. The method according to claim 11, characterized in that The first communication device monitors the prediction performance of the first positioning model according to the check value obtained by checking the fourth check function, including: When a value obtained after filtering of multiple check values ​​obtained by the fourth check function within the first time period is greater than or equal to a third threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, When a value obtained after filtering of multiple check values ​​obtained by the fourth check function within the first time period is less than a third threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

14. The method according to claim 11, characterized in that The first communication device monitors the prediction performance of the first positioning model according to the check value obtained by checking the fourth check function, including: When multiple check values ​​obtained by checking the fourth check function within the first time period are greater than or equal to the third threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, When there is a check value less than a third threshold among the multiple check values ​​obtained by checking the fourth check function within the first time period, the first communication device determines that the prediction result of the first positioning model is inaccurate.

15. The method according to claim 11, characterized in that The first communication device monitors the prediction performance of the first positioning model according to the check value obtained by checking the fourth check function, including: When the probability that the plurality of check values ​​obtained by checking the fourth check function within the first time period are greater than or equal to the third threshold is greater than or equal to the fourth threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, When the probability that the plurality of check values ​​obtained by the fourth check function within the first time period are greater than or equal to the third threshold is less than the fourth threshold, the first communication device determines that the prediction result of the first positioning model is inaccurate.

16. The method according to any one of claims 2 to 6, characterized in that The first communication device is a location management function LMF entity, the first network model is deployed on the LMF entity side, and the first The positioning model is deployed on the terminal device side.

17. The method according to claim 16, characterized in that The first network model is a network model at a cell granularity, and the first positioning model is a network model at a terminal granularity.

18. The method according to any one of claims 7 to 15, characterized in that The first communication device is a LMF entity, the second network model and the third network model are both deployed on the LMF entity side, and the first positioning model is deployed on the terminal device side.

19. The method according to claim 18, characterized in that The second network model and the third network model are both network models at a cell granularity, and the first positioning model is a network model at a terminal granularity.

20. The method according to any one of claims 16 to 19, characterized in that The method further comprises: The first communication device receives first feedback information sent by the terminal device; The first feedback information includes input information of the first positioning model and / or output information of the first positioning model.

21. The method of claim 20, wherein: Before the first communication device receives the first feedback information, the method further includes: The first communication device sends first configuration information to the terminal device; Among them, the first configuration information is used to configure at least one of the following: the feedback format of the input information of the first positioning model, the terminal device feedbacks the input information of the first positioning model within a first time length, the feedback format of the output information of the first positioning model, and the terminal device feedbacks the output information of the first positioning model within a first time length.

22. The method according to claim 21, characterized in that The first configuration information is further used to trigger the terminal device to feed back input information of the first positioning model and / or output information of the first positioning model.

23. The method of claim 21, wherein: Before the first communication device sends the first configuration information, the method further includes: The first communication device receives a first model monitoring request sent by the terminal device; The first model monitoring request is used to request monitoring of the prediction performance of the first positioning model, and the first model monitoring request triggers the first communication device to send the first configuration information.

24. The method according to any one of claims 16 to 23, characterized in that The method further comprises: The first communication device sends first monitoring information to the terminal device; The first monitoring information is used to indicate that a prediction result of the first positioning model is inaccurate, or the first monitoring information is used to indicate whether a prediction result of the first positioning model is accurate.

25. The method of claim 21, wherein: The first feedback information is information sent periodically; The first configuration information is further used to configure period information for the terminal device to feed back input information of the first positioning model and / or output information of the first positioning model.

26. The method of claim 25, wherein: The method further comprises: The first communication device periodically sends second monitoring information to the terminal device; The second monitoring information is used to indicate whether the prediction result of the first positioning model is accurate within a corresponding period.

27. The method according to any one of claims 2 to 6, characterized in that The first communication device is a LMF entity, and the first network model and the first positioning model are both deployed on the LMF entity side.

28. The method according to any one of claims 27, characterized in that The first network model and the first positioning model are both network models at a cell granularity.

29. The method according to any one of claims 7 to 15, characterized in that The first communication device is a LMF entity, and the second network model, the third network model and the first positioning model are all deployed on the LMF entity side.

30. The method of claim 29, wherein: The second network model, the third network model and the first positioning model are all network models at a cell granularity.

31. The method according to any one of claims 27 to 30, characterized in that The method further comprises: The first communication device sends third monitoring information; The third monitoring information is used to indicate that the prediction result of the first positioning model is inaccurate.

32. The method according to any one of claims 27 to 31, characterized in that The monitoring of the prediction performance of the first positioning model is performed periodically, or the monitoring of the prediction performance of the first positioning model is performed aperiodically.

33. The method of claim 32, wherein: In the case where the monitoring of the prediction performance of the first positioning model is performed periodically, the monitoring period of the prediction performance of the first positioning model is agreed upon by a protocol, or the monitoring period of the prediction performance of the first positioning model is determined by the first communication device.

34. The method according to any one of claims 2 to 6, characterized in that The first communication device is a terminal device, and the first network model and the first positioning model are both deployed on the terminal device side.

35. The method according to any one of claims 34, characterized in that The first network model and the first positioning model are both network models at the terminal granularity.

36. The method according to any one of claims 7 to 15, characterized in that The first communication device is a terminal device, and the second network model, the third network model and the first positioning model are all deployed on the terminal device side.

37. The method of claim 36, wherein: The second network model, the third network model and the first positioning model are all network models at the terminal granularity.

38. The method according to any one of claims 34 to 37, characterized in that The method further comprises: The first communication device sends fourth monitoring information; The fourth monitoring information is used to indicate that a prediction result of the first positioning model is inaccurate, or the fourth monitoring information is used to indicate whether a prediction result of the first positioning model is accurate.

39. The method according to any one of claims 34 to 37, characterized in that The method further comprises: The first communication device receives second configuration information; The second configuration information is used to instruct the first communication device to periodically monitor the prediction performance of the first positioning model, or the second configuration information is used to instruct the first communication device to non-periodically monitor the prediction performance of the first positioning model.

40. The method of claim 39, wherein: In the case where the second configuration information is used to instruct the first communication device to periodically monitor the predictive performance of the first positioning model, the second configuration information includes periodic information of the first communication device monitoring the predictive performance of the first positioning model, or the periodic information of the first communication device monitoring the predictive performance of the first positioning model is agreed upon by the protocol, or the periodic information of the first communication device monitoring the predictive performance of the first positioning model is determined by the first communication device.

41. The method of claim 40, wherein: The method further comprises: The first communication device sends fifth monitoring information; The fifth monitoring information is used to indicate whether the prediction result of the first positioning model is accurate within the corresponding period.

42. The method of claim 39, wherein: In the case where the second configuration information is used to instruct the first communication device to non-periodically monitor the predictive performance of the first positioning model, the second configuration information includes first time offset information, and the first time offset information is used to indicate the time when the first communication device reports the monitoring results of the predictive performance of the first positioning model after receiving the second configuration information.

43. The method of claim 42, wherein: The method further comprises: The first communication device sends sixth monitoring information according to the first time offset information; The sixth monitoring information is used to indicate whether the prediction result of the first positioning model is accurate.

44. The method of claim 1, wherein: The at least one network model includes a second network model and a third network model, wherein the second network model and the third network model have different model architectures, the second network model and the first positioning model are both deployed on the terminal device side, the third network model is deployed on the LMF entity side, and the first communication device is an LMF entity; The first communication device monitors the prediction performance of the first positioning model according to at least one network model, including: The first communication device monitors the prediction performance of the first positioning model according to the verification information corresponding to the second verification function and the verification value corresponding to the third verification function; The verification information corresponding to the second verification function is obtained from the terminal device, and the verification information corresponding to the second verification function includes a verification value corresponding to the second verification function, or the verification information corresponding to the second verification function includes a monitoring result for the first positioning model determined based on the verification value corresponding to the second verification function, and the verification value corresponding to the second verification function is used to reflect the similarity between the output information of the second network model and the input information of the first positioning model; The check value corresponding to the third check function is used to reflect the similarity between the output information of the third network model and the input information of the first positioning model.

45. The method of claim 44, wherein: In a case where the verification information corresponding to the second verification function includes a verification value corresponding to the second verification function, the first communications device monitoring prediction performance of the first positioning model according to the verification information corresponding to the second verification function and the verification value corresponding to the third verification function, including: When the average of the check value corresponding to the second check function and the check value corresponding to the third check function is greater than or equal to the first threshold, the first communication device determines that the prediction result of the first positioning model is accurate; and / or, When the average of the check value corresponding to the second check function and the check value corresponding to the third check function is less than the first threshold value, In this case, the first communication device determines that the prediction result of the first positioning model is inaccurate.

46. ​​The method of claim 44, wherein: In a case where the verification information corresponding to the second verification function includes a monitoring result for the first positioning model determined based on a verification value corresponding to the second verification function, the first communications device monitoring prediction performance of the first positioning model according to the verification information corresponding to the second verification function and the verification value corresponding to the third verification function, including: The first communication device determines the monitoring result for the first positioning model determined based on the check value corresponding to the second check function as the final monitoring result, or the first communication device determines the monitoring result for the first positioning model determined based on the check value corresponding to the third check function as the final monitoring result; Wherein, when the check value corresponding to the second check function is greater than or equal to the first threshold, the monitoring result for the first positioning model is that the prediction result of the first positioning model is accurate; and / or, when the check value corresponding to the second check function is less than the first threshold, the monitoring result for the first positioning model is that the prediction result of the first positioning model is inaccurate; Among them, when the verification value corresponding to the third verification function is greater than or equal to the first threshold, the monitoring result for the first positioning model is that the prediction result of the first positioning model is accurate; and / or, when the verification value corresponding to the third verification function is less than the first threshold, the monitoring result for the first positioning model is that the prediction result of the first positioning model is inaccurate.

47. The method according to any one of claims 44 to 46, characterized in that The method further comprises: The first communication device receives verification information and second feedback information corresponding to the second verification function sent by the terminal device; The second feedback information includes input information of the first positioning model and output information of the first positioning model.

48. The method of claim 47, wherein: Before the first communication device receives the second feedback information, the method further includes: The first communication device sends third configuration information to the terminal device; The third configuration information is used to configure at least one of the following: content contained in the verification information corresponding to the second verification function, feedback format of input information of the first positioning model, and feedback format of output information of the first positioning model.

49. The method of claim 48, wherein: The third configuration information is also used to trigger the terminal device to feed back input information of the first positioning model, output information of the first positioning model, and verification information corresponding to the second verification function.

50. The method of claim 48, wherein: Before the first communication device sends the third configuration information, the method further includes: The first communication device receives a second model monitoring request sent by the terminal device; The second model monitoring request is used to request monitoring of the prediction performance of the first positioning model, and the second model monitoring request triggers the first communication device to send the third configuration information.

51. The method according to any one of claims 44 to 50, characterized in that The method further comprises: The first communication device sends seventh monitoring information to the terminal device; The seventh monitoring information is used to indicate that the prediction result of the first positioning model is inaccurate, or the seventh monitoring information is used to indicate whether the prediction result of the first positioning model is accurate.

52. The method of claim 48, wherein: The verification information corresponding to the second verification function and the second feedback information are periodically sent information; The third configuration information is further used to configure at least one of the following: periodic information of the terminal device feeding back input information of the first positioning model and output information of the first positioning model, and periodic information of the terminal device feeding back verification information corresponding to the second verification function.

53. The method of claim 52, wherein: The method further comprises: The first communication device periodically sends eighth monitoring information to the terminal device; The eighth monitoring information is used to indicate whether the prediction result of the first positioning model is accurate within the corresponding period.

54. The method according to any one of claims 1 to 53, characterized in that The input information of the first positioning model includes at least one of the following: channel impulse response CIR, channel power delay profile PDP, downlink arrival time DL TOA, downlink arrival time difference DL TDOA; and / or, The output information of the first positioning model includes at least one of the following: location information of the terminal device, DL TOA, and DL TDOA.

55. A communication device, characterized in that: The communication device is a first communication device, and the communication device includes: a processing unit, configured to monitor a prediction performance of the first positioning model based on at least one network model; The input information of the at least one network model is the output information of the first positioning model, or the input information of the at least one network model is determined based on the output information of the first positioning model, or the input information of the at least one network model is associated with the output information of the first positioning model; The output information of the at least one network model is an estimate of the input information of the first positioning model.

56. A communication device, characterized in that: The communication device is a first communication device, and the communication device includes: a processor and a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory, so that the communication device executes the method as described in any one of claims 1 to 54.

57. A chip, characterized in that: include: A processor, configured to call and run a computer program from a memory, so that a device equipped with the chip executes a method as claimed in any one of claims 1 to 54.

58. A computer-readable storage medium, characterized in that: Used to store a computer program, when the computer program is executed, the method according to any one of claims 1 to 54 is implemented.

59. A computer program product, characterized in that Comprising computer program instructions, when the computer program instructions are executed, the method according to any one of claims 1 to 54 is implemented.

60. A computer program, characterized in that When the computer program is executed, the method according to any one of claims 1 to 54 is implemented.

Images