Location method for user equipment side model or base station side model, location-related monitoring data reporting method, location-related model transfer method, user equipment location capability assistance method, user equipment, base station, location management function entity, and wireless communication device

Abstract

Embodiments of the present application provide a location method for a user equipment (UE) side model or a base station side model, a location-related monitoring data reporting method, a location-related model transfer method, a UE location capability assistance method, a UE, a base station, a location management function (LMF) entity, and a wireless communication device. The location method for a UE side model is executed by a UE, and comprises: when receiving, by means of signaling, an indication sent by an LMF entity, the UE provides the LMF entity with non-artificial intelligence (AI) location information and / or AI location information, wherein the AI location information comprises UE position information and / or a transmission reception point (TRP) inference measurement value which are output by an AI model.

Description

Positioning method of user equipment side model or base station side model, positioning related monitoring data reporting method, positioning related model transfer method, user equipment positioning capability auxiliary method, user equipment, base station, positioning management function entity, and wireless communication device Technical Field

[0001] The embodiments of the present application relate to the field of wireless communication technology, and specifically to a positioning method for a user equipment (UE) side model or a base station side model, a positioning-related monitoring data reporting method, a positioning-related model transfer method, a UE positioning capability assistance method, a UE, a base station, a location management function (LMF) entity, and a wireless communication device. Background Art

[0002] In existing technologies, artificial intelligence / machine learning (AI / ML) is a system that can replace human labor through computational learning. AI / ML can be used to solve various problems, such as natural language processing, computing, and graphics processing. In recent years, AI / ML has been applied in the communications field. However, there are unresolved issues in positioning-related methods used in AI / ML applications in communications. Therefore, there is a need to propose a positioning-related method and wireless communication device to address these and other issues in existing technologies.

[0003] Summary of the Invention

[0004] Embodiments of the present application provide a positioning method for a user equipment (UE) side model or a base station side model, a positioning-related monitoring data reporting method, a positioning-related model transfer method, a UE positioning capability assistance method, a UE, a base station, a location management function (LMF entity), and a wireless communication device.

[0005] An embodiment of the present application provides a positioning method for a user equipment UE side model, which is executed on the UE, wherein the positioning method includes: after the UE receives an indication sent by a positioning management function LMF entity through signaling, providing non-artificial intelligence AI positioning information and / or AI positioning information to the LMF entity, wherein the AI ​​positioning information includes UE location information output by the AI ​​model and / or sending and receiving point TRP inference measurement values.

[0006] Through the above technical solution, the UE provides non-artificial intelligence AI positioning information and / or AI positioning information to the LMF entity. In this way, the positioning method under the user equipment side model can be improved, the energy consumption of the UE can be reduced, and / or the stability of the model operation can be improved. A positioning method of a base station side model provided in an embodiment of the present application is executed on a base station, wherein the positioning method includes: after the positioning service is turned on, the base station receives a measurement request sent by a positioning management function LMF entity through signaling, wherein the measurement request instructs the base station to obtain measurement information and provide measurement results to the LMF entity, and the measurement request also indicates the sending and receiving point TRP measurement amount and the measurement method corresponding to the TRP measurement amount; the base station initiates a measurement response or measurement report to the LMF entity through the signaling, wherein the content of the measurement response or the measurement report includes the TRP measurement value corresponding to the measurement amount and / or the measurement method used to obtain the measurement value.

[0007] Through the above technical solution, a base station receives a measurement request from a location management function (LMF) entity and initiates a measurement response or measurement report to the LMF entity. This improves the positioning method under the base station-side model, reduces base station energy consumption, and / or improves the stability of the model operation.

[0008] An embodiment of the present application provides a method for reporting positioning-related monitoring data of a user equipment UE side model, which is executed on the UE, wherein the positioning-related monitoring data reporting method includes: when monitoring indicator solution is performed on the UE and model monitoring is performed on the positioning management function LMF entity, the UE reports the monitoring indicator solution result to the LMF entity through signaling.

[0009] Through the above technical solution, the UE reports the monitoring indicator solution result to the LMF entity. In this way, the positioning-related monitoring data reporting positioning method under the user equipment side model can be improved and / or the stability of the model operation can be improved.

[0010] An embodiment of the present application provides a method for reporting positioning-related monitoring data of a base station side model, which is executed on a base station, wherein the positioning-related monitoring data reporting method includes: when monitoring indicator solution is performed on the base station and model monitoring is performed on a positioning management function LMF entity, the base station reports the monitoring indicator solution result to the LMF entity through signaling.

[0011] Through the above technical solution, the base station reports the monitoring indicator solution result to the LMF entity. In this way, the positioning-related monitoring data reporting positioning method under the base station side model can be improved and / or the stability of the model operation can be improved.

[0012] An embodiment of the present application provides a positioning-related model transfer method for a user equipment UE side model, which is executed on the UE, wherein the positioning-related model transfer method includes: the UE receives a model transfer trigger condition configured by a positioning management function LMF entity through signaling, wherein the model transfer trigger condition indicates that the UE initiates a model transfer request when a specified condition is met; after the UE determines through model monitoring that the model transfer trigger condition is met, the UE requests model transfer to the LMF entity through the signaling.

[0013] Through the above technical solution, the UE receives the model transfer trigger condition configured by the location management function LMF entity, and the UE requests the model transfer from the LMF entity. In this way, the positioning-related model transfer method under the user equipment side model can be improved and / or the stability of the model operation can be enhanced.

[0014] An embodiment of the present application provides a positioning-related model transfer method for a base station side model, which is executed on the base station, wherein the positioning-related model transfer method includes: the base station receives a model transfer trigger condition configured by a positioning management function LMF entity through signaling, wherein the model transfer trigger condition indicates that the base station initiates a model transfer request when a specified condition is met; after the base station determines through model monitoring that the model transfer trigger condition is met, the base station requests model transfer to the LMF entity through the signaling.

[0015] Through the above technical solution, the base station receives the model transfer trigger condition configured by the location management function LMF entity, and the base station requests the model transfer from the LMF entity. In this way, the positioning-related model transfer method under the base station side model can be improved and / or the stability of the model operation can be enhanced.

[0016] An embodiment of the present application provides a UE positioning capability assistance method for a user equipment (UE) side model, which is executed on the UE, wherein the UE positioning capability assistance method includes: the UE reports AI positioning capability to the network side device through signaling, wherein the AI ​​positioning capability is used to assist the network side device in selecting a model.

[0017] Through the above technical solution, the UE reports its AI positioning capabilities to the network side equipment. This can improve the UE positioning capability assistance method under the user equipment side model and / or enhance the stability of the model operation.

[0018] An embodiment of the present application provides a positioning method for a user equipment UE side model, which is executed on a positioning management function LMF entity, wherein the positioning method includes: after the LMF entity sends an indication to the UE through signaling, it receives non-artificial intelligence AI positioning information and / or AI positioning information provided by the UE, wherein the AI ​​positioning information includes the UE location information output by the AI ​​model and / or the sending and receiving point TRP inference measurement values.

[0019] Through the above technical solution, the LMF entity receives the non-artificial intelligence AI positioning information and / or AI positioning information provided by the UE. In this way, the positioning method under the user equipment side model can be improved, the energy consumption of the user equipment can be reduced, and / or the stability of the model operation can be improved. A positioning method of a base station side model provided in an embodiment of the present application is executed on the positioning management function LMF entity, wherein the positioning method includes: after the positioning service is turned on, the LMF entity sends a measurement request to the base station through signaling, wherein the measurement request instructs the base station to obtain measurement information and provide the measurement result to the LMF entity, and the measurement request also indicates the sending and receiving point TRP measurement amount and the measurement method corresponding to the TRP measurement amount; the LMF entity receives the measurement response or measurement report provided by the base station through the signaling, wherein the content of the measurement response or the measurement report includes the TRP measurement value corresponding to the measurement amount and / or the measurement method used to obtain the measurement value.

[0020] Through the above technical solution, the LMF entity sends a measurement request to the base station, and the LMF entity receives a measurement response or measurement report provided by the base station. In this way, the positioning method under the base station side model can be improved, the energy consumption of the base station can be reduced, and / or the stability of the model operation can be improved.

[0021] An embodiment of the present application provides a method for reporting positioning-related monitoring data of a user equipment UE side model, which is executed on a positioning management function LMF entity, wherein the positioning-related monitoring data reporting method includes: when the monitoring indicator solution is performed on the UE and the model monitoring is performed on the LMF entity, the LMF entity receives the monitoring indicator solution result reported by the UE through the signaling.

[0022] Through the above technical solution, the LMF entity receives the monitoring indicator solution results reported by the UE. In this way, the positioning-related monitoring data reporting method under the user equipment side model can be improved and / or the stability of the model operation can be improved.

[0023] An embodiment of the present application provides a method for reporting positioning-related monitoring data of a base station side model, which is executed in a positioning management function LMF entity, wherein the positioning-related monitoring data reporting method includes: when the monitoring indicator solution is performed in the base station and the model monitoring is performed in the LMF entity, the LMF entity receives the monitoring indicator solution result reported by the base station through the signaling.

[0024] Through the above technical solution, the LMF entity receives the monitoring indicator solution reported by the base station. In this way, the positioning-related monitoring data reporting method under the base station side model can be improved and / or the stability of the model operation can be improved.

[0025] An embodiment of the present application provides a positioning-related model transfer method for a user-set UE-side model, which is executed in a positioning management function LMF entity, wherein the positioning-related model transfer method includes: the LMF entity sends a model transfer trigger condition to the UE through signaling, wherein the model transfer trigger condition indicates that a model transfer request is initiated when a specified condition is met; after the UE determines that the model transfer trigger condition is met through model monitoring, the LMF entity receives the UE's request for model transfer through the signaling.

[0026] Through the above technical solution, the LMF entity sends a model transfer trigger condition to the UE, and the LMF entity receives the UE's request for model transfer. In this way, the positioning-related model transfer method under the user equipment side model can be improved and / or the stability of the model operation can be improved.

[0027] An embodiment of the present application provides a positioning-related model transfer method for a base station side model, which is executed in a positioning management function LMF entity, wherein the positioning-related model transfer method includes: the LMF entity configures a model transfer trigger condition to the base station through signaling, wherein the model transfer trigger condition indicates that a model transfer request is initiated when a specified condition is met; after the base station determines that the model transfer trigger condition is met through model monitoring, the LMF entity receives the base station's request for model transfer through the signaling. Through the above technical solution, the LMF entity configures the model transfer trigger condition to the base station, and the LMF entity receives the base station's request for model transfer. In this way, the positioning-related model transfer method under the base station side model can be improved and / or the stability of the model operation can be improved.

[0028] An embodiment of the present application provides a UE positioning capability assistance method for a user equipment (UE) side model, which is executed on a network side device, wherein the UE positioning capability assistance method includes: the network side device receives the AI ​​positioning capability reported by the UE through signaling, wherein the AI ​​positioning capability is used to assist the network side device in selecting a model.

[0029] Through the above technical solution, the network-side device receives the AI ​​positioning capability reported by the UE. In this way, the UE positioning capability assistance method under the user equipment side model can be improved and / or the stability of the model operation can be enhanced.

[0030] A wireless communication device provided in an embodiment of the present application includes: a processor and a memory, the memory being used to store a computer program, and the processor being used to call and run the computer program stored in the memory to execute the above-mentioned wireless communication method.

[0031] The user equipment provided in the embodiment of the present application 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 to perform the above-mentioned wireless communication method.

[0032] The base station provided in the embodiment of the present application 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 to perform the above-mentioned wireless communication method.

[0033] The positioning management function entity provided in the embodiment of the present application 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 to perform the above-mentioned wireless communication method.

[0034] The network element provided in the embodiment of the present application 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 to perform the above-mentioned wireless communication method.

[0035] The chip provided in the embodiment of the present application is used to implement the above-mentioned wireless communication method.

[0036] Specifically, the chip includes: a processor, which is used to call and run a computer program from a memory, so that a device equipped with the chip executes the above-mentioned wireless communication method.

[0037] The computer-readable storage medium provided in an embodiment of the present application is used to store a computer program, which enables a computer to execute the above-mentioned wireless communication method.

[0038] The computer program product provided in the embodiments of the present application includes computer program instructions, which enable a computer to execute the above-mentioned wireless communication method.

[0039] The computer program provided in the embodiment of the present application, when executed on a computer, enables the computer to execute the above-mentioned method for wireless communication.

[0040] Through the above technical solutions, the positioning-related methods under the user equipment side model or the base station side model can be improved, the energy consumption of the user equipment or the base station can be reduced, and / or the stability of the model operation can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0042] FIG1A is a schematic diagram of a wireless communication system architecture provided in an embodiment of the present application;

[0043] FIG1B is a schematic diagram of an overall solution of a UE-side model provided in an embodiment of the present application;

[0044] FIG1C is a schematic diagram of an overall solution of a base station side model provided in an embodiment of the present application;

[0045] FIG2A is a flow chart of a positioning method for a user equipment UE side model provided in an embodiment of the present application;

[0046] FIG2B is a flow chart of a positioning method for a user equipment UE side model provided in an embodiment of the present application;

[0047] FIG2C is a flow chart of a positioning method for a user equipment UE side model provided in an embodiment of the present application;

[0048] FIG2D is a schematic diagram of a flow chart of a positioning method for a user equipment UE side model provided in an embodiment of the present application;

[0049] FIG2E is a flow chart of a positioning method for a user equipment UE side model provided in an embodiment of the present application;

[0050] FIG2F is a flow chart of a positioning method for a user equipment UE side model provided in an embodiment of the present application;

[0051] FIG2G is a flow chart of a positioning method for a user equipment UE side model provided in an embodiment of the present application;

[0052] FIG2H is a flow chart of a positioning method for a user equipment UE side model provided in an embodiment of the present application;

[0053] FIG3A is a flow chart of a positioning method using a base station side model according to an embodiment of the present application;

[0054] FIG3B is a flow chart of a positioning method using a base station side model according to an embodiment of the present application;

[0055] FIG3C is a flow chart of a positioning method using a base station side model according to an embodiment of the present application;

[0056] FIG3D is a flow chart of a positioning method using a base station side model according to an embodiment of the present application;

[0057] FIG3E is a flow chart of a positioning method using a base station side model according to an embodiment of the present application;

[0058] FIG3F is a flow chart of a positioning method using a base station side model according to an embodiment of the present application;

[0059] FIG3G is a flow chart of a positioning method using a base station side model according to an embodiment of the present application;

[0060] FIG3H is a flow chart of a positioning method using a base station side model according to an embodiment of the present application;

[0061] FIG4A is a flow chart of a method for reporting positioning-related monitoring data of a UE-side model according to an embodiment of the present application;

[0062] FIG4B is a flow chart of a method for reporting positioning-related monitoring data of a UE-side model according to an embodiment of the present application;

[0063] FIG4C is a flow chart of a method for reporting positioning-related monitoring data of a UE-side model according to an embodiment of the present application;

[0064] FIG5A is a flow chart of a method for reporting positioning-related monitoring data of a base station-side model according to an embodiment of the present application;

[0065] FIG5B is a flow chart of a method for reporting monitoring data related to positioning of a base station side model according to an embodiment of the present application;

[0066] FIG5C is a flow chart of a method for reporting monitoring data related to positioning of a base station side model according to an embodiment of the present application;

[0067] FIG6A is a flow chart of a positioning-related model transfer method of a UE-side model provided in an embodiment of the present application;

[0068] FIG6B is a flow chart of a positioning-related model transfer method of a UE-side model provided in an embodiment of the present application;

[0069] FIG6C is a flow chart of a positioning-related model transfer method of a UE-side model provided in an embodiment of the present application;

[0070] FIG6D is a schematic diagram of AI / ML direct positioning according to an embodiment of the present application;

[0071] FIG6E is a schematic diagram of AI / ML-assisted positioning (multiple TRP inputs) provided in an embodiment of the present application;

[0072] FIG6F is a schematic diagram of AI / ML-assisted positioning (single TRP input, single model) provided in an embodiment of the present application;

[0073] FIG6G is a schematic diagram of AI / ML-assisted positioning (single TRP input, multiple models) provided in an embodiment of the present application;

[0074] FIG7A is a flow chart of a positioning-related model transfer method of a base station side model provided in an embodiment of the present application;

[0075] FIG7B is a flow chart of a positioning-related model transfer method of a base station side model provided in an embodiment of the present application;

[0076] FIG7C is a flow chart of a positioning-related model transfer method of a base station side model provided in an embodiment of the present application;

[0077] FIG8A is a flow chart of a UE positioning capability assistance method of a UE side model provided in an embodiment of the present application;

[0078] FIG8B is a flow chart of a UE positioning capability assistance method of a UE side model provided in an embodiment of the present application;

[0079] FIG8C is a flow chart of a UE positioning capability assistance method of a UE-side model provided in an embodiment of the present application;

[0080] FIG8D is a flow chart of a UE positioning capability assistance method of a UE-side model provided in an embodiment of the present application;

[0081] FIG9 is a schematic structural diagram of a wireless communication device provided in an embodiment of the present application;

[0082] FIG10 is a schematic structural diagram of a chip according to an embodiment of the present application;

[0083] FIG11 is a schematic block diagram of a wireless communication system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0084] 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 described embodiments are part of the embodiments of this application, not all of the embodiments. Based on 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.

[0085] The technical solutions of the embodiments of the present application can be applied to various wireless communication systems, such as: Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD) system, 5G communication system or future wireless communication systems, etc.

[0086] Exemplarily, a wireless communication system 100 used in an embodiment of the present application is shown in FIG1A . The wireless communication system 100 may include a base station 110, which may be a device that communicates with a user equipment 120 (User Equipment, UE). The base station 110 may provide communication coverage for a specific geographical area and may communicate with user equipment located within the coverage area. Optionally, the base station 110 may be an evolved base station (eNB or eNodeB) in an LTE system, or the base station may be a mobile switching center, a relay station, an access point, a vehicle-mounted device, a wearable device, a hub, a switch, a bridge, a router, a network-side device in a 5G network, or a base station in a future communication system, etc.

[0087] The wireless communication system 100 also includes at least one user equipment 120 located within the coverage area of ​​the base station 110. As used herein, "user equipment" includes, but is not limited to, a device configured to receive / send communication signals via a wired connection, such as a Public Switched Telephone Network (PSTN), a Digital Subscriber Line (DSL), a digital cable, a direct cable connection; and / or another data connection / network; and / or via a wireless interface, such as a cellular network, a Wireless Local Area Network (WLAN), a digital television network such as a DVB-H network, a satellite network, an AM-FM broadcast transmitter; and / or another user equipment; and / or an Internet of Things (IoT) device. A user equipment configured to communicate via a wireless interface may be referred to as a "wireless communication terminal," "wireless terminal," or "mobile terminal." Examples of mobile terminals include, but are not limited to, satellite or cellular telephones; Personal Communications System (PCS) terminals that can combine cellular radiotelephones with data processing, fax, and data communication capabilities; PDAs that can include radiotelephones, pagers, Internet / Intranet access, web browsers, notepads, calendars, and / or Global Positioning System (GPS) receivers; and conventional laptop and / or palmtop receivers or other electronic devices that include radiotelephone transceivers. User equipment can refer to access terminals, subscriber units, subscriber stations, mobile stations, mobile stations, remote stations, remote user equipment, mobile devices, wireless communication devices, or user agents. An access terminal can be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, a wearable device, a user device in a 5G network, or a user device in a future evolved PLMN, etc.

[0088] The wireless communication system 100 also includes a network 130. Network 130 may be a Location Management Function (LMF) entity. Network 130 may be an IP mobile communication network operated by a mobile communication operator. For example, network 130 may be a core network used by a mobile communication operator that operates and manages the wireless communication system 100, or a core network used by a virtual mobile communication operator such as an MVNO (Mobile Virtual Network Operator).

[0089] The network 130 can be connected to the base station 110 and serve as a relay device for transmitting user data. The user equipment 120 transmits and receives user data via the network 130. It should be noted that the communication of user data is not limited to IP communication and can also be non-IP communication.

[0090] In some embodiments of the present invention, after receiving an instruction from a location management function (LMF) entity via signaling, the UE 120 provides non-AI positioning information and / or AI positioning information to the LMF entity 130. Through the above technical solution, the UE 120 provides non-AI positioning information and / or AI positioning information to the LMF entity 130. This improves the positioning method under the user equipment side model, reduces UE energy consumption, and / or improves the stability of the model operation.

[0091] In some embodiments of the present invention, base station 110 receives a measurement request sent by location management function (LMF) entity 130 via signaling, and base station 110 initiates a measurement response or measurement report to the LMF entity via the signaling. Through the above technical solution, base station 110 receives a measurement request sent by location management function (LMF) entity 130, and base station 110 initiates a measurement response or measurement report to the LMF entity 130. This improves the positioning method under the base station-side model, reduces base station energy consumption, and / or enhances the stability of model operation.

[0092] Optionally, the user equipments 120 may perform device-to-device (D2D) communication with each other.

[0093] Optionally, the 5G communication system or 5G network may also be referred to as a New Radio (NR) system or NR network.

[0094] Figure 1A exemplarily shows a base station 110, two user equipments 120 and a network 130. Optionally, the wireless communication system 100 may include multiple base stations and the coverage of each base station may include other numbers of user equipments, which is not limited in this embodiment of the present application. The multiple base stations are, for example, a first base station and a second base station. The first base station is, for example, a source base station. The second base station is, for example, a target base station (target base station). The network 130 may be a Location Management Function (LMF entity) entity. Optionally, the wireless communication system 100 may also include other network entities such as a network controller, a mobility management entity, a network element, etc., which is not limited in this embodiment of the present application. For example, the network 130 may include other network entities such as a network controller, a mobility management entity, a network element, etc., which is not limited in this embodiment of the present application.

[0095] It should be understood that the device with wireless communication function in the network / system in the embodiment of the present application may be referred to as a wireless communication device. Taking the wireless communication system 100 shown in Figure 1A as an example, the wireless communication device may include a base station 110 with communication function, a user device 120 and a network 130. The base station 110 and the user device 120 may be the specific devices described above and will not be repeated here; the network 130 may be a location management function (LMF entity) entity. The wireless communication device may also include other devices (network 130) in the wireless communication system 100. For example, the network 130 may include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiment of the present application.

[0096] The embodiment of the present application introduces an AI positioning method based on the traditional user equipment side model positioning process and the base station side model positioning process, and designs a UE side model overall solution as provided in Figure 1B and a base station side model overall solution as provided in Figure 1C to support the normal operation of AI positioning in wireless communication systems.

[0097] As shown in Figure 1B , a UE-side model overall solution introduces AI capability interaction between UE 120 and LMF entity 130 to ensure the normal operation of AI positioning. A signaling process for the AI ​​positioning operation mechanism is designed, including simultaneous operation of AI positioning and non-AI positioning, non-simultaneous operation of AI positioning and non-AI positioning, and dynamic operation of AI positioning and non-AI positioning, enabling the communication system to support AI positioning while reducing UE power consumption. Considering the situation where the model monitoring function is located on the UE side or LMF entity side, the implementation method of the AI ​​positioning monitoring method and the corresponding monitoring indicator solution results that need to be reported are introduced, as well as the signaling process for model transfer to ensure the stability of the model during operation. As shown in Figure 1C , a base station-side model overall solution is designed, including signaling processes for the AI ​​positioning operation mechanism, including simultaneous operation of AI positioning and non-AI positioning, non-simultaneous operation of AI positioning and non-AI positioning, and dynamic operation of AI positioning and non-AI positioning, enabling the communication system to support AI positioning while reducing base station power consumption. Considering the situation where the model monitoring function is located on the base station side or LMF entity side, the implementation method of the AI ​​positioning monitoring method and the corresponding monitoring indicator solution results that need to be reported are introduced, as well as the signaling process for model transfer to ensure the stability of the model during operation.

[0098] The following describes the specific processes of UE-side model AI positioning and base station-side model AI positioning respectively. As shown in Figure 1B, a UE-side model overall solution, the specific process of UE-side model AI positioning includes at least one of the following steps: Step 1: AI positioning capability interaction is initiated by the LMF entity or actively initiated by the UE to provide the AI ​​positioning capability supported by the UE; Step 2: The LMF entity requests AI positioning information from the UE, and indicates the operation mechanism of AI positioning on the UE side by introducing signaling related to positioning method switching and fallback. At the same time, the trigger condition for model transfer is introduced to indicate the model request on the UE side; Step 3: After model inference, the UE reports AI positioning information to the LMF entity, and feedbacks the current UE positioning mode by introducing indication information such as fallback type; Step 4a: If the monitoring indicator solution is performed on the UE side and the model monitoring is performed on the LMF entity side, the UE reports the monitoring indicator solution result to the LMF entity, and introduces the implementation methods of the label-based method and the label-free method and the corresponding monitoring indicators; Step 4b: If the monitoring indicator solution and model monitoring are both performed on the UE side, the AI ​​model is trained and stored on the LMF entity side. After the trigger condition configured by the LMF entity is met, the UE requests the LMF entity to transfer the model and provides indication information to assist the LMF entity in model selection.

[0099] As shown in Figure 1C, a base station-side model overall solution is provided. The specific process of base station-side model AI positioning includes at least one of the following operations; Step 1: The LMF entity requests measurement from the base station and instructs the base station to provide AI positioning information. By introducing signaling related to positioning method switching and fallback, the operating mechanism of AI positioning on the base station side is indicated. At the same time, the trigger condition for model transfer is introduced to indicate the model request on the base station side; Step 2: After model inference, the base station responds to or reports measurement to the LMF entity, which includes AI positioning information. By introducing indication information such as fallback type, the current base station positioning mode is fed back; Step 3a: If the monitoring indicator solution is performed on the base station side and the model monitoring is performed on the LMF entity side, the base station reports the monitoring indicator solution result to the LMF entity, introduces the implementation methods of label-based and label-free methods and the corresponding monitoring indicators; Step 3b: If the monitoring indicator solution and model monitoring are both performed on the base station side, the AI ​​model is trained and stored on the LMF entity side. After the trigger condition configured by the LMF entity is met, the base station requests model transfer from the LMF entity and provides indication information to assist the LMF entity in model selection.

[0100] 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.

[0101] To facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions related to the embodiments of the present application are described below.

[0102] First embodiment: Operation mechanism of UE-side model AI positioning:

[0103] The first embodiment can be implemented independently. In some embodiments of the present application, the first embodiment can also be combined with other embodiments. For example, the first embodiment can be implemented in combination with the second embodiment, the third embodiment, the fourth embodiment, the fifth embodiment, the sixth embodiment, and / or the seventh embodiment. These embodiments can be implemented in sequence or in parallel, and the present application is not limited thereto.

[0104] FIG2A is a flow chart of a positioning method for a user equipment (UE) side model provided in an embodiment of the present application. As shown in FIG2A , the positioning method for the user equipment (UE) side model is executed on the UE and includes at least one of the following operations: Operation 201A: After the UE receives an instruction sent by a positioning management function (LMF) entity through signaling, it provides non-artificial intelligence (AI) positioning information and / or AI positioning information to the LMF entity. The AI ​​positioning information includes UE location information output by the AI ​​model and / or TRP inference measurement values ​​of the sending and receiving points.

[0105] Through the above technical solution, the UE provides non-artificial intelligence AI positioning information and / or AI positioning information to the LMF entity. In this way, the positioning method under the user equipment side model can be improved, the energy consumption of the UE can be reduced, and / or the stability of the model operation can be improved. Figure 2B is a flow chart of the positioning method of the user equipment UE side model provided in an embodiment of the present application. As shown in Figure 2B, the positioning method of the user equipment UE side model is executed in the positioning management function LMF entity, including at least one of the following operations: Operation 201B: After the LMF entity sends an indication to the UE through signaling, it receives the non-artificial intelligence AI positioning information and / or AI positioning information provided by the UE. Among them, the AI ​​positioning information includes the UE location information output by the AI ​​model and / or the TRP inference measurement values ​​of the sending and receiving points.

[0106] Through the above technical solution, the LMF entity receives non-AI positioning information and / or AI positioning information provided by the UE. This improves the positioning method under the user equipment side model, reduces the energy consumption of the user equipment, and / or improves the stability of the model operation. Specifically, the UE is, for example, user equipment 120 shown in Figure 1A. The base station is, for example, base station 110 shown in Figure 1A. Base station 110 is, for example, a gNB. The LMF entity is, for example, network 130 shown in Figure 1A.

[0107] Method 1: Non-AI positioning and AI positioning run simultaneously;

[0108] In some embodiments of the present application, the positioning method also includes after the positioning service is turned on, the UE receives a non-AI positioning information request and / or an AI positioning information request sent by the LMF entity through the signaling, wherein the non-AI positioning information request instructs the UE to use a non-AI positioning positioning method to obtain the position and / or obtain the measurement information required for non-AI positioning and provide a first result to the LMF entity, and the AI ​​positioning information request instructs the UE to use an AI method to infer the position and / or measurement information and provide a second result to the LMF entity. In some embodiments of the present application, the AI ​​positioning information request also indicates at least one of the following measurement quantities: line-of-sight LOS / non-line-of-sight NLOS indication hard value, LOS / NLOS indication soft value, arrival time hard value, arrival time soft value, reference signal time difference RSTD hard value, RSTD soft value, angle of departure AoD hard value, AoD soft value, positioning reference signal received power PRS RSRP hard value, PRS RSRP soft value, reference signal received multipath power PRS RSRPP hard value, PRS RSRPP soft value, UE side Rx-Tx time difference hard value or UE side Rx-Tx time difference soft value, wherein the hard value represents a determined value and the soft value represents a probability distribution.

[0109] In some embodiments of the present application, the signaling is Long Term Evolution Positioning Protocol (LPP) signaling.

[0110] Exemplarily, as shown in FIG2C , in some embodiments of the present application, the positioning method includes mode 1: non-AI positioning and AI positioning are run simultaneously.

[0111] Figure 2C is a flow chart of a positioning method for a user equipment UE side model provided in an embodiment of the present application. As shown in Figure 2C, the positioning method for a user equipment UE side model includes at least one of the following steps: Step 1: After the positioning service is turned on, the LMF entity requests non-AI positioning information and / or requests AI positioning information from the UE through LPP signaling, wherein the request for non-AI positioning information instructs the UE to obtain the position and / or obtain the measurement information required for the non-AI positioning method and provide the result to the LMF entity, and the request for AI positioning information instructs the UE to infer the position and / or measurement information using the AI ​​method and provide the result to the LMF entity. Whether the LMF entity requests only non-AI positioning information or AI positioning information or requests both non-AI positioning information and AI positioning information depends on the purpose of collecting positioning information. If the LMF entity is used for positioning services, only non-AI positioning information or AI positioning information needs to be requested. If the LMF entity needs to perform model monitoring, both non-AI positioning information and AI positioning information need to be requested to obtain the performance of the non-AI positioning method and the AI ​​positioning method. When requesting AI positioning information, you can optionally indicate at least one of the following measurement quantities: Line of Sight (LOS) / Non Line of Sight (NLOS) indication hard value, LOS / NLOS indication soft value, arrival time hard value, arrival time soft value, Reference Signal Time Difference (RSTD) hard value, RSTD soft value, Angle of Departure (AoD) hard value, AoD soft value, Positioning Reference Signal (PRS) received power (RSRP) hard value, PRS RSRP soft value, PRS Reference Signal Received Path Power (RSRPP) hard value, PRS RSRPP soft value, UE side receive transmit (Rx-Tx) time difference hard value, or UE side Rx-Tx time difference soft value. When the measurement quantity is associated with arrival time, RSTD, AoD, RSRP, RSRPP, and UE-side Rx-Tx time difference, the hard value represents the determined value, and the soft value represents the probability distribution (likelihood function). When the measurement quantity is associated with LOS / NLOS indication, the hard value indicates the use of 0 and 1 to indicate LOS and NLOS, and the soft value indicates the use of probability to indicate LOS.

[0112] Based on the above description, the LPP signaling message can be updated as follows:

[0113] Step 2: The UE provides non-AI positioning information and / or AI positioning information to the LMF entity through LPP signaling, where the provided AI positioning information includes the UE location information output by the AI ​​model and / or each TRP inference measurement value (measurement value obtained by AI model inference). If the LMF entity requests AI positioning information and configures the measurement quantity, the configured measurement quantity is reported; otherwise, the reported measurement quantity is selected by the UE independently. If the LMF entity only requests non-AI positioning information or AI positioning information in step 1, the UE only provides the LMF entity with non-AI positioning information (such as the position obtained by the DL-TDOA method, the measurement value required by the DL-TDOA method, and the position obtained by the DL-AoD method) or AI positioning information; if the LMF entity requests both non-AI positioning information and AI positioning information in step 1, the UE provides the LMF entity with both non-AI positioning information and AI positioning information.

[0114] Based on the above description, the LPP signaling message can be updated as follows:

[0115] Method 2: Non-AI positioning and AI positioning are not run at the same time:

[0116] Option 1: UE autonomous implementation:

[0117] In some embodiments of the present application, the UE receives first configuration information sent by the LMF entity through the signaling, and the first configuration information is related to the switching of positioning methods. In some embodiments of the present application, the first configuration information includes a switching positioning method permission, and the switching positioning method permission instructs the UE to switch between non-AI positioning and AI positioning. In some embodiments of the present application, the switching condition between non-AI positioning and AI positioning is set based on the UE. In some embodiments of the present application, when the switching positioning method permission instructs the UE to switch between non-AI positioning and AI positioning, the UE also receives at least one of the following measurement quantities: a hard value of LOS / NLOS indication, a soft value of LOS / NLOS indication, a hard value of arrival time, a soft value of arrival time, a hard value of RSTD, a soft value of RSTD, a hard value of AoD, a soft value of AoD, a hard value of PRS RSRP, a soft value of PRS RSRP, a hard value of PRS RSRPP, a soft value of PRS RSRPP, a hard value of UE-side Rx-Tx time difference, or a soft value of UE-side Rx-Tx time difference. In some embodiments of the present application, the AI ​​positioning information provided by the UE includes the UE location information output by the AI ​​model and / or the TRP inference measurement values ​​of the transmitting and receiving points corresponding to the measurement quantities indicated by the AI ​​positioning information request. In some embodiments of the present application, the positioning method further includes the UE providing non-AI positioning information to the LMF entity through the signaling and feeding back a fallback type.

[0118] Exemplarily, as shown in FIG2D , in some embodiments of the present application, the positioning method includes Mode 2: Non-AI positioning and AI positioning are not run simultaneously Option 1: UE autonomous implementation.

[0119] Figure 2D is a flow chart of the positioning method of the user equipment UE side model provided in an embodiment of the present application. As shown in Figure 2D, the positioning method of the user equipment UE side model includes at least one of the following steps: Step 1: After the positioning service is turned on, the LMF entity authorizes the UE to switch the positioning method through LPP signaling, that is, instructs the UE to switch between non-AI positioning and AI positioning, and the switching conditions are based on the UE's autonomous settings. When the LMF entity permits the UE to switch the positioning method, it may optionally indicate at least one of the following measurement quantities: LOS / NLOS indication hard value, LOS / NLOS indication soft value, arrival time hard value, arrival time soft value, RSTD hard value, RSTD soft value, AoD hard value, AoD soft value, PRS RSRP hard value, PRS RSRP soft value, PRS RSRPP hard value, PRS RSRPP soft value, UE-side Rx-Tx time difference hard value, or UE-side Rx-Tx time difference soft value. If the measurement quantity is not indicated, when the UE switches from the non-AI positioning method to the AI ​​positioning method, the same measurement quantity as the non-AI positioning is used. If the measurement quantity is indicated, when the UE switches from the non-AI positioning method to the AI ​​positioning method, all indicated measurement quantities are used to obtain more types of measurement values ​​through AI positioning.

[0120] Based on the above description, the LPP signaling message can be updated as follows:

[0121] Step 2: After the UE meets the conditions for switching the positioning method, such as being unable to receive GNSS signals, the base station side transmit timing error group (Tx Timing Error Group, Tx TEG), network synchronization error and other auxiliary information provided by the LMF entity does not meet the AI ​​model generalization conditions, the AI ​​positioning method is used to infer the UE position and / or measurement value, and the AI ​​positioning information is provided to the LMF entity through LPP signaling. The provided AI positioning information includes the UE position information output by the AI ​​model and / or the inferred measurement value corresponding to each TRP (if the LMF entity indicates the measurement quantity, all the indicated measurement quantities must be used, otherwise the same measurement quantities as non-AI positioning are used).

[0122] Step 3: After the UE meets the predefined conditions for falling back to non-AI positioning, such as being able to receive GNSS signals within a period of time, it uses non-AI positioning methods to perform measurements and / or position estimation, and provides non-AI positioning information to the LMF entity through LPP signaling, and at the same time feedbacks the fallback type, that is, the mechanism based on which the UE falls back to non-AI positioning. If the fallback type is monitoring, it means that the UE falls back to non-AI positioning after comparing the performance of non-AI positioning and AI positioning through monitoring. If the fallback type is non-monitoring, it means that the UE falls back to non-AI positioning after meeting predefined conditions such as being able to receive GNSS signals (that is, not using monitoring indicators). Non-AI positioning Non-AI positioning Therefore, the LPP signaling message can be updated as follows:

[0123] Option 2: LMF entity configuration:

[0124] In some embodiments of the present application, the UE receives the first configuration information sent by the LMF entity through the signaling, and the first configuration information is related to the switching of the positioning method. In some embodiments of the present application, the first configuration information includes relevant information for switching the positioning method, and the relevant information for switching the positioning method instructs the UE to switch between non-AI positioning and AI positioning. In some embodiments of the present application, the relevant information for switching the positioning method includes at least one of the following: a condition for switching AI positioning, a measurement amount, a fallback condition for non-AI positioning, or a duration of a fallback condition. In some embodiments of the present application, the condition for switching AI positioning instructs the UE to switch from the non-AI positioning to the AI ​​positioning when a specified condition is met, and the switching condition includes at least one of the following: no global navigation satellite system GNSS signal, NLOS ratio, number of multipaths, or dense multipaths.

[0125] In some embodiments of the present application, if the switching condition includes the absence of a GNSS signal, the switching condition instructs the UE to switch to the AI ​​positioning mode if it cannot receive a GNSS signal. In some embodiments of the present application, if the switching condition includes the NLOS ratio, the switching condition indicates a threshold for the NLOS ratio, and the UE switches to the AI ​​positioning mode when the calculated NLOS ratio exceeds the threshold. In some embodiments of the present application, if the switching condition includes the number of multipaths, the switching condition indicates a threshold for the number of multipaths, and the UE switches to the AI ​​positioning mode when the calculated number of multipaths exceeds the threshold. In some embodiments of the present application, if the switching condition includes dense multipaths, the switching condition instructs the UE to switch to the AI ​​positioning mode if the multipaths are dense. In some embodiments of the present application, the AI ​​positioning information includes UE location information output by an AI model and / or TRP inferred measurement values ​​of the transmitting and receiving points corresponding to the measurement quantities indicated in the AI ​​positioning information request. In some embodiments of the present application, the positioning method further includes the UE providing non-AI positioning information to the LMF entity through the signaling and feeding back a fallback type.

[0126] Exemplarily, as shown in FIG2E , in some embodiments of the present application, the positioning method includes Mode 2: Non-AI positioning and AI positioning are not run simultaneously Option 2: LMF entity configuration.

[0127] FIG2E is a flow chart of a positioning method for a user equipment (UE)-side model provided in an embodiment of the present application. As shown in FIG2E , the positioning method for the user equipment (UE)-side model includes at least one of the following steps: Step 1: After the positioning service is enabled, the LMF entity configures the UE with at least one of the following information related to switching positioning modes via LPP signaling: conditions for switching to AI positioning, measurement quantities, fallback conditions for non-AI positioning, or the duration of the fallback conditions. The conditions for switching to AI positioning are configured by the LMF entity to the UE, instructing the UE to switch to the AI ​​positioning mode when the specified conditions are met. The switching conditions include at least one of the following: no GNSS signal, NLOS ratio, number of multipaths, or dense multipaths. If the no GNSS signal condition exists, the UE is instructed to switch to the AI ​​positioning mode if it cannot receive a GNSS signal. The NLOS ratio indicates a threshold for the NLOS ratio. If this condition exists, the UE is instructed to switch to the AI ​​positioning mode when the calculated NLOS ratio exceeds the threshold. The NLOS ratio is calculated based on UE autonomous implementation, for example, by calculating and averaging the LOS / NLOS indications corresponding to each TRP. The multipath number indicates the threshold value of the multipath number. If this condition exists, it indicates that the UE can switch to the AI ​​positioning mode when the calculated multipath number exceeds the threshold. The calculation of the multipath number is based on UE autonomous implementation, such as calculating the multipath number corresponding to each TRP through a parameter estimation algorithm and then obtaining the maximum value or average value. If the condition of dense multipath exists, it indicates that the UE can switch to the AI ​​positioning mode under the condition of dense multipath. The determination of dense multipath is based on UE autonomous implementation, such as combining LiDAR map to determine whether the first arriving multipath can be distinguished.

[0128] The LMF entity can select at least one of the above conditions for configuration. The UE must meet all configured conditions before switching to AI positioning. In addition, the fallback condition indicates the conditions that the UE must meet to fall back to non-AI positioning. The fallback condition can be that all configured conditions for switching to AI positioning are not met, or that any configured conditions for switching to AI positioning are not met. The duration of the fallback condition indicates how long the UE must meet and maintain the configured fallback condition before falling back to non-AI positioning.

[0129] Based on the above description, the LPP signaling message can be updated as follows:

[0130] Step 2: After the UE meets the conditions for switching to AI positioning, it uses AI positioning to infer the UE position and / or measurement values, and provides AI positioning information to the LMF entity through LPP signaling. The provided AI positioning information includes the UE position information output by the AI ​​model and / or the inferred measurement values ​​of each TRP (if the LMF entity indicates the measurement quantity, all the indicated measurement quantities must be used; otherwise, the same measurement quantities as those for non-AI positioning are used).

[0131] Step 3: After the UE meets the fallback conditions and maintains the specified time, it uses the non-AI positioning method to perform measurement and / or position estimation, and provides non-AI positioning information to the LMF entity through LPP signaling, and at the same time feedbacks the fallback type, that is, the mechanism based on which the UE falls back to non-AI positioning. If the fallback type is monitoring, it means that the UE falls back to non-AI positioning after comparing the performance of non-AI positioning and AI positioning through monitoring. If the fallback type is non-monitoring, it means that the UE falls back to non-AI positioning after meeting the configured fallback conditions. Non-AI positioning Non-AI positioning

[0132] Option 3: LMF entity indication:

[0133] In some embodiments of the present application, the positioning method further includes, during the positioning service process, the UE providing UE-side auxiliary information to the LMF entity through the signaling. In some embodiments of the present application, the UE-side auxiliary information includes at least one of the following: a GNSS indicator, a multipath number, or a resolvable multipath indicator, which is used to assist the LMF entity in determining the conditions for switching AI positioning. In some embodiments of the present application, the UE receives the non-AI positioning positioning information request or the AI ​​positioning information request sent by the LMF entity based on the UE-side auxiliary information. In some embodiments of the present application, the UE reports the result of non-AI positioning, and according to the UE-side auxiliary information, if the switching condition is met, the UE receives the AI ​​positioning positioning information request sent by the LMF entity through the signaling, and the AI ​​positioning positioning information request instructs the UE to switch to AI positioning and reports the result output by the AI ​​model. In some embodiments of the present application, the UE reports the result of AI positioning. According to the UE-side auxiliary information, if the fallback condition is met, the UE receives the non-AI positioning information request sent by the LMF entity through the signaling. The non-AI positioning information request instructs the UE to fall back to the non-AI positioning positioning method and reports the output result.

[0134] Exemplarily, as shown in FIG2F , in some embodiments of the present application, the positioning method includes Mode 2: Non-AI positioning and AI positioning are not run simultaneously and Option 3: LMF entity indication.

[0135] Figure 2F is a flow chart of the positioning method of the user equipment UE side model provided in an embodiment of the present application. As shown in Figure 2F, the positioning method of the user equipment UE side model includes at least one of the following steps: Step 1: During the positioning service process, the UE provides UE-side auxiliary information to the LMF entity through LPP signaling. The information provided includes a GNSS indicator, a multipath number, and a resolvable multipath indicator to assist the LMF entity in determining the conditions for switching AI positioning. The GNSS indicator indicates whether the UE can receive the GNSS signal. The parameter is represented in the form of a Boolean value, such as 0 indicating that the UE cannot receive the GNSS signal, and 1 indicating that the UE can receive the GNSS signal. The multipath number represents a statistic of the multipath number corresponding to each TRP calculated by the UE, such as the average value and the maximum value. The resolvable multipath indicator indicates whether the UE can distinguish the first arriving multipath. The parameter is represented in the form of a Boolean value, such as 0 indicating that it cannot be distinguished by the UE, and 1 indicating that it can be distinguished by the UE.

[0136] Based on the above description, the LPP signaling message can be updated as follows:

[0137] Step 2: If the UE reports the result of non-AI positioning, the LMF entity determines the conditions for switching to AI positioning based on the auxiliary information reported by the UE. If the switching conditions are met, the LMF entity requests AI positioning information from the UE through LPP signaling, that is, instructs the UE to switch to AI positioning, and reports the results output by the AI ​​model. If the UE reports the result of AI positioning, the LMF entity determines the conditions for falling back to non-AI positioning based on the auxiliary information reported by the UE. If the fallback conditions are met, the LMF entity requests non-AI positioning information from the UE through LPP signaling, that is, instructs the UE to fall back to non-AI positioning, and reports the output results.

[0138] Method 3: Dynamic operation of non-AI positioning and AI positioning:

[0139] Option 1: UE autonomous implementation:

[0140] In some embodiments of the present application, the positioning method also includes that during the positioning service process, the UE receives the second configuration information sent by the LMF entity through the signaling, and the second configuration information is used to instruct the UE to switch between the first mechanism and the second mechanism. The first mechanism refers to that the non-AI positioning positioning mode and the AI ​​positioning mode are not running at the same time, and the second mechanism refers to that the non-AI positioning positioning mode and the AI ​​positioning mode are running at the same time. In some embodiments of the present application, the second configuration information includes a switching indication of the positioning operation mechanism, which is used to indicate whether the UE is allowed to switch between the first mechanism and the second mechanism. In some embodiments of the present application, the switching condition of the positioning operation mechanism is based on the autonomous setting of the UE. In some embodiments of the present application, the positioning method also includes that the UE feeds back the current positioning operation mechanism to the LMF entity through the signaling.

[0141] Exemplarily, as shown in FIG2G , in some embodiments of the present application, the positioning method includes mode 3: non-AI positioning and option 1 of dynamic operation of AI positioning: UE autonomous implementation.

[0142] Figure 2G is a flow chart of the positioning method of the user equipment UE side model provided in an embodiment of the present application. As shown in Figure 2G, the positioning method of the user equipment UE side model includes at least one of the following steps: Step 1: After the positioning service is turned on, the LMF entity indicates to the UE through LPP signaling whether to switch the positioning operation mechanism, that is, whether the UE is allowed to switch between the mechanisms in which non-AI positioning and AI positioning are not run at the same time and non-AI positioning and AI positioning are run at the same time. It can be indicated in the form of a Boolean value, such as 0 indicates that switching is not allowed, and 1 indicates that the UE is allowed to switch. The switching conditions are based on the UE's autonomous settings.

[0143] Based on the above description, the LPP signaling message can be updated as follows:

[0144] Step 2: If the LMF entity indicates that the UE is allowed to switch between different positioning operation mechanisms, after the UE switches the positioning mechanism, it needs to feedback the current positioning operation mechanism to inform the LMF entity that the positioning operation mechanism has switched. After receiving the positioning operation mechanism feedback from the UE, the LMF entity can use method 1 or method 2 to indicate the positioning on the UE side based on the current positioning operation mechanism.

[0145] Based on the above description, the LPP signaling message can be updated as follows:

[0146] Option 2: LMF entity indication:

[0147] In some embodiments of the present application, the positioning method further includes, during the positioning service process, the UE receiving, through the signaling, second configuration information sent by the LMF entity, the second configuration information being used to instruct the UE to switch between the first mechanism and the second mechanism, the first mechanism being that the non-AI positioning positioning mode and the AI ​​positioning mode are not run at the same time, and the second mechanism being that the non-AI positioning positioning mode and the AI ​​positioning mode are run simultaneously. In some embodiments of the present application, the second configuration information includes an indication of a positioning operation mechanism, and the indication of the positioning operation mechanism is used to indicate the use of the first mechanism or the second mechanism.

[0148] Exemplarily, as shown in FIG2H , in some embodiments of the present application, the positioning method includes Mode 3: Non-AI positioning and Option 2 of AI positioning dynamic operation: LMF entity indication.

[0149] FIG2H is a flow chart of a positioning method for a user equipment (UE) side model according to an embodiment of the present application. As shown in FIG2G , the positioning method for the user equipment (UE) side model includes at least one of the following steps: Step 1: During the positioning service process, the LMF entity instructs the UE via LPP signaling which positioning operation mechanism to adopt. The LMF entity may instruct the UE side positioning method using either Mode 1 or Mode 2 based on the indicated positioning operation mechanism.

[0150] Based on the above description, the LPP signaling message can be updated as follows:

[0151] Second embodiment: Operation mechanism of base station-side model AI positioning

[0152] The second embodiment can be implemented independently. In some embodiments of this application, the second embodiment can also be combined with other embodiments. For example, the second embodiment can be implemented in combination with the first embodiment, the third embodiment, the fourth embodiment, the fifth embodiment, the sixth embodiment, and / or the seventh embodiment. These embodiments can be implemented sequentially or in parallel, and this application is not limited thereto.

[0153] Figure 3A is a flow chart of the positioning method of the base station side model provided in an embodiment of the present application. As shown in Figure 3A, the positioning method of the base station side model is executed on the base station and includes at least one of the following operations: Operation 301A: After the positioning service is turned on, the base station receives a measurement request sent by the positioning management function LMF entity through signaling. The measurement request instructs the base station to obtain measurement information and provide measurement results to the LMF entity. The measurement request also indicates the sending and receiving point TRP measurement quantities and the measurement method corresponding to the TRP measurement quantities. Operation 302A: The base station initiates a measurement response or measurement report to the LMF entity through the signaling. The content of the measurement response or the measurement report includes the TRP measurement value corresponding to the measurement quantity and / or the measurement method used to obtain the measurement value.

[0154] Through the above technical solution, a base station receives a measurement request from a location management function (LMF) entity and initiates a measurement response or measurement report to the LMF entity. This improves the positioning method under the base station-side model, reduces base station energy consumption, and / or improves the stability of the model operation.

[0155] Figure 3B is a flow chart of the positioning method of the base station side model provided in an embodiment of the present application. As shown in Figure 3B, the positioning method of the base station side model is executed in the positioning management function LMF entity, and includes at least one of the following operations: Operation 301B: After the positioning service is turned on, the LMF entity sends a measurement request to the base station through signaling. The measurement request instructs the base station to obtain measurement information and provide measurement results to the LMF entity, and the measurement request also indicates the sending and receiving point TRP measurement quantities and the measurement method corresponding to the TRP measurement quantities. Operation 302B: The LMF entity receives a measurement response or measurement report provided by the base station through the signaling. The content of the measurement response or the measurement report includes the TRP measurement value corresponding to the measurement quantity and / or the measurement method used to obtain the measurement value.

[0156] Through the above technical solution, the LMF entity sends a measurement request to the base station, and the LMF entity receives a measurement response or measurement report provided by the base station. In this way, the positioning method under the base station side model can be improved, the energy consumption of the base station can be reduced, and / or the stability of the model operation can be improved.

[0157] Specifically, the UE is, for example, the user equipment 120 shown in FIG1A . The base station is, for example, the base station 110 shown in FIG1A . The base station 110 is, for example, a gNB. The LMF entity is, for example, the network 130 shown in FIG1A .

[0158] Method 1: Non-AI positioning and AI positioning run simultaneously:

[0159] In some embodiments of the present application, the TRP measurement includes at least one of the following: a hard value of the base station-side receive and transmit Rx-Tx time difference, a hard value of the reference signal received power (RSRP), a hard value of the relative time of arrival (RTOA), a hard value of the angle of arrival (AoA), multiple hard values ​​of the angle of arrival (AoA), a hard value of the reference signal received multipath power (RSRPP), a hard value of the line-of-sight (LOS) / non-line-of-sight (NLOS) indication, a soft value of the LOS / NLOS indication, a soft value of the base station-side Rx-Tx time difference, a soft value of the RSRP, a soft value of the RTOA, a soft value of the AoA, multiple soft values ​​of the AoA, and a soft value of the RSRPP. Hard values ​​represent deterministic values, and soft values ​​represent probability distributions. In some embodiments of the present application, the measurement method includes a non-AI positioning method and / or an AI positioning method. In some embodiments of the present application, the signaling is NR Positioning Protocol A (NRPPa) signaling. In some embodiments of the present application, the base station receives third configuration information sent by the LMF entity via the signaling, where the third configuration information is related to positioning method switching.

[0160] Exemplarily, as shown in FIG3C , in some embodiments of the present application, the positioning method includes mode 1: non-AI positioning and AI positioning are run simultaneously.

[0161] FIG3C is a flow chart of the positioning method of the base station side model provided in an embodiment of the present application. As shown in FIG3C , the positioning method of the base station side model includes at least one of the following steps: Step 1: After the positioning service is turned on, the LMF entity sends a measurement request to the base station through NRPPa signaling to instruct the base station to obtain measurement information and provide the measurement results to the LMF entity. The measurement request needs to indicate the required TRP measurement quantity and the measurement method corresponding to each measurement quantity. The TRP measurement quantity includes the base station side Rx-Tx time difference hard value, the Reference Signal Receiving Power (RSRP) hard value, the relative time of arrival (RTOA) hard value, the angle of arrival (AoA) hard value, multiple AoA hard values, and the reference signal received multipath power (RSRP). The measurement parameters include hard values ​​(for example, Power, RSRPP), hard values ​​for LOS / NLOS indication, soft values ​​for LOS / NLOS indication, soft values ​​for base station-side Rx-Tx time difference, soft values ​​for RSRP, soft values ​​for RTOA, soft values ​​for AoA, multiple soft values ​​for AoA, and soft values ​​for RSRPP. When the measurement quantity is associated with base station-side Rx-Tx time difference, RSRP, RTOA, AoA, multiple AoA, or RSRPP, the hard value represents a deterministic value, and the soft value represents a probability distribution (likelihood function). When the measurement quantity is associated with LOS / NLOS indication, the hard value indicates LOS and NLOS using 0 and 1, while the soft value indicates LOS using a probabilistic form. Furthermore, measurement methods include traditional methods and / or AI methods. When the TRP measurement quantity is a soft value for LOS / NLOS indication, a soft value for RTOA, a soft value for AoA, soft values ​​for base station-side Rx-Tx time difference, RSRP, multiple soft values ​​for AoA, or soft values ​​for RSRPP, the AI ​​method must be configured. Whether the LMF entity requests only traditional measurement results or AI reasoning results or both traditional measurement results and AI reasoning results depends on the purpose of collecting positioning information. If the LMF entity is used for positioning services, it only needs to request traditional measurement results or AI reasoning results. If the LMF entity needs to perform model monitoring, it needs to request both traditional measurement results and AI reasoning results to obtain the performance of non-AI positioning methods and AI positioning methods.

[0162] According to the above description, the NRPPa signaling message can be updated as follows:

[0163] Step 2: The base station initiates a measurement response (Measurement Response) or measurement report (Measurement Report) to the LMF entity through NRPPa signaling, which includes the measurement values ​​of each TRP corresponding to the measurement quantity requested by the LMF entity, as well as the measurement method used to obtain the measurement value. If the LMF entity only requests traditional measurement results or AI reasoning results in step 1, the base station only provides the LMF entity with traditional measurement results (such as UL-RTOA, UL-AoA) or AI reasoning results; if the LMF entity requests both traditional measurement results and AI reasoning results in step 1, the base station provides both traditional measurement results and AI reasoning results to the LMF entity.

[0164] According to the above description, the NRPPa signaling message can be updated as follows:

[0165] Method 2: Non-AI positioning and AI positioning are not run at the same time:

[0166] Option 1: Base station autonomous implementation:

[0167] In some embodiments of the present application, the base station receives third configuration information sent by the LMF entity through the signaling, and the third configuration information is related to the switching of the positioning method. In some embodiments of the present application, the third configuration information includes a switching positioning method permission, and the switching positioning method permission instructs the base station to switch between the non-AI positioning positioning method and the AI ​​positioning method. In some embodiments of the present application, the switching conditions between the non-AI positioning positioning method and the AI ​​positioning method are based on autonomous settings of the base station. In some embodiments of the present application, when the switching positioning method permits the base station to switch between a non-AI positioning mode and an AI positioning mode, at least one of the following TRP inference values ​​is also indicated: a base station-side Rx-Tx time difference hard value, RSRP hard value, RTOA hard value, AoA hard value, multiple AoA hard values, RSRPP hard value, LOS / NLOS indication hard value, LOS / NLOS indication soft value, base station-side Rx-Tx time difference soft value, RSRP soft value, RTOA soft value, AoA soft value, multiple AoA soft values, or RSRPP soft value, where hard values ​​represent deterministic values ​​and soft values ​​represent probability distributions. In some embodiments of the present application, the positioning method further includes the base station initiating a response or reporting of an inference measurement value to the LMF entity via the signaling, where the inference measurement value includes a TRP measurement value output by a model. In some embodiments of the present application, the positioning method further includes the base station reporting the non-AI positioning measurement value to the LMF entity via the signaling and providing feedback on the fallback type.

[0168] Exemplarily, as shown in FIG3D , in some embodiments of the present application, the positioning method includes Mode 2: Non-AI positioning and AI positioning are not run simultaneously Option 1: Autonomous implementation by the base station.

[0169] Figure 3D is a flow chart of the positioning method of the base station side model provided in an embodiment of the present application. As shown in Figure 3D, the positioning method of the base station side model includes at least one of the following steps: Step 1: After the positioning service is turned on, the LMF entity authorizes the base station to switch the positioning method through NRPPa signaling, that is, to instruct the base station to switch between non-AI positioning and AI positioning, and the switching conditions are based on the autonomous setting of the base station. When the LMF entity authorizes the base station to switch the positioning method, it can indicate at least one of the following TRP inference quantities (measurement quantities using the AI ​​positioning method): the base station side receiving and sending Rx-Tx time difference hard value, reference signal received power RSRP hard value, relative arrival time RTOA hard value, angle of arrival AoA hard value, multiple AoA hard values, reference signal received multipath power RSRPP hard value, line-of-sight LOS / non-line-of-sight NLOS indication hard value, LOS / NLOS indication soft value, base station side Rx-Tx time difference soft value, RSRP soft value, RTOA soft value, AoA soft value, multiple AoA soft values ​​or RSRPP soft value. When the inference quantity is associated with Rx-Tx time difference, RSRP, RTOA, AoA, multiple AoAs, or RSRPP, the hard value represents the deterministic value, and the soft value represents the probability distribution (likelihood function). When the inference quantity is associated with LOS / NLOS indication, the hard value indicates the use of 0 and 1 to indicate LOS and NLOS, and the soft value indicates the use of probability to indicate LOS. If the LMF entity does not indicate the TRP inference quantity, when the base station switches from a non-AI positioning method to an AI positioning method, the measurement quantity used during non-AI positioning is used. If the LMF entity indicates the TRP inference quantity, when the base station switches from a non-AI positioning method to an AI positioning method, all the indicated inference quantities are used to obtain more types of measurement values ​​through AI positioning.

[0170] According to the above description, the NRPPa signaling message can be updated as follows:

[0171] Step 2: After the base station meets the conditions for switching the positioning method, for example, the NLOS environment, the UE-side Tx TEG and other auxiliary information provided by the UE do not meet the generalization conditions of the AI ​​model, and the AI ​​positioning method is used to infer the measurement value, and the inferred measurement value response or report is initiated to the LMF entity through NRPPa signaling. The inferred measurement value is the measurement value output by each TRP model (if the LMF entity indicates the TRP inference amount, all the inference amounts indicated by it must be used, otherwise the measurement amount during non-AI positioning is used).

[0172] Step 3: After the base station meets the predefined conditions for falling back to non-AI positioning, such as being in an LOS environment for a period of time, it uses the non-AI positioning method to perform measurements and reports the measurement values ​​(measurement values ​​output by the non-AI positioning method) to the LMF entity through NRPPa signaling. At the same time, the fallback type is fed back, that is, the mechanism based on which the base station falls back to non-AI positioning. If the fallback type is monitoring, it means that the base station falls back to non-AI positioning after comparing the performance of non-AI positioning and AI positioning through monitoring. If the fallback type is non-monitoring, it means that the base station falls back to non-AI positioning after meeting the predefined LOS environment and other conditions (that is, without using monitoring indicators).

[0173] According to the above description, the NRPPa signaling message can be updated as follows:

[0174] Option 2: LMF entity configuration:

[0175] In some embodiments of the present application, the base station receives the third configuration information sent by the LMF entity through the signaling, and the third configuration information is related to the switching of the positioning method. In some embodiments of the present application, the third configuration information includes relevant information for switching the positioning method, and the relevant information for switching the positioning method instructs the base station to switch between the non-AI positioning positioning method and the AI ​​positioning method. In some embodiments of the present application, the relevant information for switching the positioning method includes at least one of the following: the condition for switching AI positioning, the TRP inference amount, the fallback condition for non-AI positioning, or the duration of the fallback condition. In some embodiments of the present application, the condition for switching AI positioning instructs the base station to switch from the non-AI positioning positioning method to the AI ​​positioning method when a specified condition is met, and the switching condition includes at least one of the following: NLOS environment, number of multipaths, or dense multipath.

[0176] In some embodiments of the present application, if the switching condition includes the NLOS environment, the switching condition instructs the base station to switch to the AI ​​positioning mode under the condition of the NLOS environment. In some embodiments of the present application, if the switching condition includes the number of multipaths, the switching condition indicates the threshold of the number of multipaths, and instructs the base station to switch to the AI ​​positioning mode when the calculated number of multipaths exceeds the threshold. In some embodiments of the present application, if the switching condition includes the dense multipath, the switching condition instructs the base station to switch to the AI ​​positioning mode under the condition that the multipaths are dense. In some embodiments of the present application, the positioning method also includes the base station initiating a response or reporting of an inference measurement value to the LMF entity through the signaling, wherein the inference measurement value includes a TRP measurement value output by the model. In some embodiments of the present application, the positioning method also includes the base station reporting a non-AI positioning measurement value to the LMF entity through the signaling, and feeding back a fallback type.

[0177] Exemplarily, as shown in FIG3E , in some embodiments of the present application, the positioning method includes Mode 2: Non-AI positioning and AI positioning are not run simultaneously Option 2: LMF entity configuration.

[0178] Figure 3E is a flow chart of the positioning method of the base station side model provided in an embodiment of the present application. As shown in Figure 3E, the positioning method of the base station side model includes at least one of the following steps: Step 1: After the positioning service is turned on, the LMF entity configures the base station with the following relevant information for switching the positioning mode through NRPPa signaling: the conditions for switching AI positioning, the TRP inference amount, the fallback conditions for non-AI positioning, or the duration of the fallback conditions. The switching condition is configured by the LMF entity to the base station to instruct the base station to switch to the AI ​​positioning mode when the specified conditions are met. The switching condition includes at least one of the following: NLOS environment, multipath number, or dense multipath. If the condition of the NLOS environment exists, it indicates that the base station can switch to the AI ​​positioning mode under the condition of the NLOS environment, wherein the judgment of the NLOS environment is based on the autonomous implementation of the base station (main TRP). The multipath number indicates the threshold of the multipath number. If this condition exists, it indicates that the base station can switch to the AI ​​positioning mode when the calculated multipath number exceeds the threshold, wherein the calculation of the multipath number is based on the autonomous implementation of the base station (main TRP), such as calculating the multipath number through a parameter estimation algorithm. If the conditions of dense multipath exist, the base station is instructed to switch to the AI ​​positioning mode under the conditions of dense multipath. The determination of dense multipath is based on the autonomous implementation of the base station (main TRP), such as combining with ISAC to determine whether the first arriving multipath can be distinguished.

[0179] The LMF entity can select at least one of the above conditions for configuration. The base station must meet all configured conditions before switching to AI positioning. In addition, the fallback condition indicates the conditions that the base station must meet to fall back to non-AI positioning. The fallback condition can be that all configured conditions for switching to AI positioning are not met, or that any configured conditions for switching to AI positioning are not met. The duration of the fallback condition indicates how long the base station must meet and maintain the configured fallback condition before falling back to non-AI positioning.

[0180] According to the above description, the NRPPa signaling message can be updated as follows:

[0181] Step 2: After the base station meets the conditions for switching to AI positioning, it uses AI positioning to perform measurement value inference, and initiates a response or report of the inferred measurement value to the LMF entity through NRPPa signaling, where the inferred measurement value is the measurement value output by each TRP (if the LMF entity indicates the TRP inference amount, all the inference amounts indicated by it must be used, otherwise the measurement amount during non-AI positioning is used).

[0182] Step 3: After the base station meets the fallback conditions and maintains the specified time, it uses the non-AI positioning method to perform measurements, and initiates the reporting of traditional measurement values ​​to the LMF entity through NRPPa signaling, and at the same time feedbacks the fallback type, that is, the mechanism based on which the base station falls back to non-AI positioning. If the fallback type is monitoring, it means that the base station falls back to non-AI positioning after comparing the performance of non-AI positioning and AI positioning through monitoring. If the fallback type is non-monitoring, it means that the base station falls back to non-AI positioning after meeting the configured fallback conditions.

[0183] Option 3: LMF entity indication:

[0184] In some embodiments of the present application, the positioning method further includes, during the positioning service process, the base station providing base station-side auxiliary information to the LMF entity through the signaling. In some embodiments of the present application, the base station-side auxiliary information includes the number of multipaths and / or a resolvable multipath indicator, which is used to assist the LMF entity in determining the conditions for switching AI positioning. In some embodiments of the present application, the base station receives the non-AI positioning measurement request or the AI ​​positioning measurement request sent by the LMF entity through the signaling.

[0185] Exemplarily, as shown in FIG3F , in some embodiments of the present application, the positioning method includes Mode 2: Non-AI positioning and AI positioning are not run simultaneously and Option 3: LMF entity indication.

[0186] Figure 3F is a flow chart of the positioning method of the base station side model provided in an embodiment of the present application. As shown in Figure 3F, the positioning method of the base station side model includes at least one of the following steps: Step 1: During the positioning service process, the base station provides base station side auxiliary information to the LMF entity through NRPPa signaling. The information provided includes the number of multipaths and / or the resolvable multipath indicator to assist the LMF entity in determining the switching AI positioning conditions. The number of multipaths indicates the number of multipaths calculated by the base station (main TRP). The resolvable multipath indicator indicates whether the base station (main TRP) can distinguish the first arriving multipath, and the parameter is represented in the form of a Boolean value, such as 0 means that it cannot be distinguished by the UE, and 1 means that it can be distinguished by the UE.

[0187] According to the above description, the NRPPa signaling message can be updated as follows:

[0188] Step 2: If the base station reports the traditional measurement results, the LMF entity determines the conditions for switching to AI positioning based on the auxiliary information reported by the base station. If the switching conditions are met, the LMF entity initiates an AI measurement request to the base station through NRPPa signaling, instructing the base station to switch to AI positioning and report the results output by the AI ​​model. If the base station reports the AI ​​inference results, the LMF entity determines the conditions for falling back to non-AI positioning based on the auxiliary information reported by the base station. If the fallback conditions are met, the LMF entity initiates a traditional measurement request to the base station through NRPPa signaling to instruct the base station to fall back to non-AI positioning and report the measurement results.

[0189] Method 3: Dynamic operation of non-AI positioning and AI positioning:

[0190] Option 1: UE autonomous implementation:

[0191] In some embodiments of the present application, the positioning method further includes, during the positioning service process, the base station receives, through the signaling, fourth configuration information sent by the LMF entity, and the fourth configuration information is used to instruct the base station to switch between the first mechanism and the second mechanism. The first mechanism refers to non-AI positioning and AI positioning not running at the same time, and the second mechanism refers to the non-AI positioning and the AI ​​positioning running at the same time. In some embodiments of the present application, the fourth configuration information includes a switching indication of the positioning operation mechanism, which is used to indicate whether the base station is allowed to switch between the first mechanism and the second mechanism. In some embodiments of the present application, the switching condition of the positioning operation mechanism is based on the autonomous setting of the base station. In some embodiments of the present application, the positioning method further includes, through the signaling, the base station feedbacks the current positioning operation mechanism to the LMF entity.

[0192] Exemplarily, as shown in FIG3G , in some embodiments of the present application, the positioning method includes mode 3: non-AI positioning and option 1 of AI positioning dynamic operation: UE autonomous implementation.

[0193] Figure 3G is a flow chart of the positioning method of the base station side model provided in an embodiment of the present application. As shown in Figure 3G, the positioning method of the base station side model includes at least one of the following steps: Step 1: After the positioning service is turned on, the LMF entity instructs the base station through NRPPa signaling to switch the positioning operation mechanism, that is, whether the base station is allowed to switch between the mechanisms of non-AI positioning and AI positioning running at different times and non-AI positioning and AI positioning running at the same time. It can be indicated in the form of a Boolean value, such as 0 means that switching is not allowed, and 1 means that the base station is allowed to switch. The switching conditions are based on the autonomous setting of the base station.

[0194] According to the above description, the NRPPa signaling message can be updated as follows:

[0195] Step 2: If the LMF entity indicates that the base station is allowed to switch between different positioning mechanisms, after the base station switches the positioning mechanism, it must feedback the current positioning operation mechanism to inform the LMF entity of the positioning operation mechanism switch. After receiving the positioning operation mechanism feedback from the base station, the LMF entity can use Method 1 or Method 2 to indicate the positioning method on the base station side based on the current positioning mechanism.

[0196] According to the above description, the NRPPa signaling message can be updated as follows:

[0197] Option 2: LMF entity indication:

[0198] In some embodiments of the present application, the positioning method further includes, during the positioning service process, the base station receiving, through the signaling, fourth configuration information sent by the LMF entity, the fourth configuration information being used to instruct the base station to switch between a first mechanism and a second mechanism, the first mechanism being that non-AI positioning and AI positioning are not run simultaneously, and the second mechanism being that the non-AI positioning and the AI ​​positioning are run simultaneously. In some embodiments of the present application, the fourth configuration information includes an indication of a positioning operation mechanism, and the indication of the positioning operation mechanism is used to indicate the use of the first mechanism or the second mechanism.

[0199] Exemplarily, as shown in FIG3H , in some embodiments of the present application, the positioning method includes Mode 3: non-AI positioning and Option 2 of AI positioning dynamic operation: LMF entity indication.

[0200] FIG3H is a flow chart of a positioning method for a base station-side model provided in an embodiment of the present application. As shown in FIG3H , the positioning method for the base station-side model includes at least one of the following steps: Step 1: During the positioning service process, the LMF entity instructs the base station via NRPPa signaling which positioning operation mechanism to adopt. The LMF entity may instruct the base station-side positioning method using either Mode 1 or Mode 2 based on the indicated positioning operation mechanism.

[0201] According to the above description, the NRPPa signaling message can be updated as follows:

[0202] Third embodiment: reporting the monitoring indicator solution results of the UE-side model:

[0203] The third embodiment can be implemented independently. In some embodiments of this application, the third embodiment can also be combined with other embodiments. For example, the third embodiment can be implemented in combination with the first embodiment, the second embodiment, the fourth embodiment, the fifth embodiment, the sixth embodiment, and / or the seventh embodiment. These embodiments can be implemented sequentially or in parallel, and this application is not limited thereto.

[0204] Figure 4A is a flow chart of the method for reporting monitoring data related to positioning of the user equipment UE side model provided in an embodiment of the present application. As shown in Figure 4A, the method for reporting monitoring data related to positioning of the user equipment UE side model is executed on the UE and includes at least one of the following operations: Operation 401A: When the monitoring indicator solution is performed on the UE and the model monitoring is performed on the positioning management function LMF entity, the UE reports the monitoring indicator solution result to the LMF entity through signaling.

[0205] Through the above technical solution, the UE reports the monitoring indicator solution result to the LMF entity. In this way, the positioning-related monitoring data reporting positioning method under the user equipment side model can be improved and / or the stability of the model operation can be improved.

[0206] Figure 4B is a flow chart of the method for reporting monitoring data related to positioning of the user equipment UE side model provided in an embodiment of the present application. As shown in Figure 4B, the method for reporting monitoring data related to positioning of the user equipment UE side model is executed in the positioning management function LMF entity, and includes at least one of the following operations: Operation 401B: When the monitoring indicator solution is performed on the UE and the model monitoring is performed on the LMF entity, the LMF entity receives the monitoring indicator solution result reported by the UE through the signaling.

[0207] Through the above technical solution, the LMF entity receives the monitoring indicator solution results reported by the UE. In this way, the positioning-related monitoring data reporting method under the user equipment side model can be improved and / or the stability of the model operation can be improved.

[0208] Specifically, the UE is, for example, the user equipment 120 shown in FIG1A . The base station is, for example, the base station 110 shown in FIG1A . The base station 110 is, for example, a gNB. The LMF entity is, for example, the network 130 shown in FIG1A .

[0209] In some embodiments of the present application, the signaling is Long Term Evolution Positioning Protocol LPP signaling. In some embodiments of the present application, the monitoring indicator solution result is carried in a message providing the monitoring indicator solution result or in a message providing positioning information. In some embodiments of the present application, for each model or model group participating in the monitoring, the monitoring indicator solution result includes at least one of the following: position error, velocity / acceleration error, measurement value error, position output standard deviation / variance, measurement value standard deviation / variance, or model identifier ID list. In some embodiments of the present application, the measurement value error includes at least one of the following: arrival time error, reference signal time difference RSTD error, angle of departure AoD error, or F1-score of LOS / NLOS indication. In some embodiments of the present application, the measurement value standard deviation / variance includes at least one of the following: arrival time standard deviation / variance, RSTD standard deviation / variance, or AoD standard deviation / variance.

[0210] Figure 4C is a flow chart of a method for reporting monitoring data related to positioning of a user equipment UE side model provided in an embodiment of the present application. As shown in Figure 4C, the method for reporting monitoring data related to positioning of a user equipment UE side model includes at least one of the following operations: If the monitoring indicator solution is performed on the UE side, and the model monitoring is performed on the LMF entity side, the UE needs to report the monitoring indicator solution result to the LMF entity through LPP signaling. A new message providing the monitoring indicator solution result may be added or reported in the original message providing positioning information. For each model or model group involved in monitoring, its monitoring indicators include at least one of the following: position error, velocity / acceleration error, measurement value error, position output standard deviation / variance, measurement value standard deviation / variance, or model identifier ID list. Explanations of these parameters are as follows:

[0211] Position Error: When GNSS signals are available and the system is in a Loss of Service (LOS) environment, GNSS accuracy can be assumed. The true location tag can be obtained from the GNSS coordinates. The metric used is the error between the estimated position and the true location tag. For convenience, the distance between the two locations can be used as the metric. Position error is expressed as an integer, for example, in the range {0, 1, …, 1000}, in cm. If the error 0 ≤ e < 1, the value is 0. Similarly, if the error e ≥ 1000, the value is 1000. Velocity / Acceleration Error: Velocity / acceleration is obtained from the position output by model inference at multiple moments. The number of required positions and the time interval (multiple positions can be used to average velocity / acceleration) are implemented independently by the UE. The corresponding true location tag comes from the UE's built-in sensors (such as the accelerometer). The metric used is the error between the true location tag and the estimated velocity / acceleration. The speed / acceleration error is indicated in the form of an integer. For example, the integer range is {0, 1, ..., 20}. When the indicator is speed error, the unit is km / h. When the indicator is acceleration error, the unit is m / s. 2 If the error 0≤e<1, then take 0, and so on, if the error e≥20, then take 20. The measurement value error includes at least one of the following monitoring indicators:

[0212] Arrival time error: When GNSS signals are available and the system is in a Loss of System (LOS) environment, it is assumed that GNSS is accurate and the true time of arrival tag can be obtained from the GNSS position coordinates and the TRP coordinates. The measurement metric is the error between the estimated time of arrival and the true time of arrival tag. If the model architecture is AI / ML-assisted positioning (single TRP input, single model) or AI / ML-assisted positioning (multiple TRP inputs), the reported result is the error statistic (such as maximum value, average value) between the estimated time of arrival and the true time of arrival tag for all TRPs under single or multiple monitoring. The metric is indicated in the form of an integer, such as the integer range {0,1,…,10}, in nanoseconds. If the metric 0≤s<1, then it is 0, and so on. If the metric s≥10, then it is 10. If the model architecture is AI / ML-assisted positioning (single TRP input, multiple models), the reported result is the error between the arrival time estimate corresponding to each TRP under a single monitoring and the true arrival time label, or the error statistics (such as maximum value, average value) between the arrival time estimate corresponding to each TRP and the true arrival time label under multiple monitoring. The representation of the measurement indicator corresponding to each TRP is as described above.

[0213] RSTD error: When GNSS signals are available and the system is in a Loss of System (LOS) environment, GNSS accuracy can be assumed. The RSTD true label can be obtained using the GNSS position coordinates and the TRP coordinates. The measurement metric is the error between the RSTD estimate and the RSTD true label. If the model architecture is AI / ML-assisted positioning (single TRP input, single model) or AI / ML-assisted positioning (multiple TRP inputs), the reported result is the error statistic (e.g., maximum or average) between the RSTD estimate and the RSTD true label for all TRPs under single or multiple monitoring. This metric is expressed as an integer, for example, in the range {0, 1, ..., 10}, in nanoseconds. If the metric 0 ≤ s < 1, then 0 is used. Similarly, if the metric s ≥ 10, then 10 is used. If the model architecture is AI / ML-assisted positioning (single TRP input, multiple models), the reported result can be the error between the RSTD estimate corresponding to each TRP under a single monitoring and the RSTD true label, or the error statistics (such as maximum value, average value) between the RSTD estimate corresponding to each TRP and the RSTD true label under multiple monitoring. The representation of the measurement indicator corresponding to each TRP is as described above.

[0214] AoD error: When GNSS signals are available and in a Loss of System (LOS) environment, it can be assumed that GNSS is accurate and the true AoD label can be obtained from the GNSS position coordinates and TRP coordinates. The measurement metric is the error between the AoD estimate and the true AoD label. If the model architecture is AI / ML-assisted positioning (single TRP input, single model) or AI / ML-assisted positioning (multiple TRP inputs), the reported result is the error statistic (such as maximum or average) between the AoD estimate and the true AoD label for all TRPs under single or multiple monitoring. The metric is expressed as an integer, for example, in the range {0,1,…,10}, with units of deg. If the metric 0≤s<1, it is 0, and so on, if the metric s≥10, it is 10. If the model architecture is AI / ML-assisted positioning (single TRP input, multiple models), the reported result can be the error between the AoD estimate and the AoD true label corresponding to each TRP under a single monitoring, or the error statistics (such as maximum value, average value) between the AoD estimate and the AoD true label corresponding to each TRP under multiple monitoring. The representation of the measurement indicator corresponding to each TRP is as described above.

[0215] F1-score error for LOS / NLOS indications: When GNSS signals are available and the vehicle is in a Loss of System (LOS) environment, GNSS accuracy can be assumed. The true labels for LOS / NLOS indications can be obtained using GNSS position coordinates, TRP position coordinates, and digital maps (using technologies such as LiDAR and ISAC). Multiple samples (true labels) generated through multiple monitoring sessions can be measured using the F1-score, a metric used to evaluate classification performance. The value range is [0, 1], with higher values ​​indicating better model performance. If the model architecture is AI / ML-assisted positioning (single TRP input, single model) or AI / ML-assisted positioning (multiple TRP inputs), the reported result is the F1-score calculated from the estimated LOS / NLOS indications and the true labels for all TRPs. This metric is explicitly indicated, with options such as {0, dot2, dot4, …, 1}. If 0 ≤ s < 0.2, the value is 0, and so on. If s = 1, the value is 1. If the model architecture is AI / ML-assisted positioning (single TRP input, multiple models), the reported result is the LOS / NLOS indicator F1-score corresponding to each TRP, where the measurement indicator representation corresponding to each TRP is as described above.

[0216] Standard deviation / variance of position output: The output of a suitable model should be stable in continuous time. If there are outliers, it indicates that the performance of the model is not good. According to the form of the output position, the standard deviation or variance of multiple positions of the model inference output within a shorter moving distance is calculated, which is implemented independently by the UE. For example, taking the Cartesian coordinate system as an example, the standard deviation or variance of the three dimensions can be calculated separately, and the statistics of the three-dimensional indicators (such as the average and the maximum value) can be calculated. The smaller the value, the better the performance of the model. The standard deviation / variance of the position output is indicated in the form of an integer. For example, the integer range can be {0,1,…,10}. When the indicator is the standard deviation, the unit is m, and when the indicator is the variance, the unit is m. 2 , if the standard deviation / variance 0≤s<1, then take 0, and so on, if the standard deviation / variance s≥10, then take 10.

[0217] The standard deviation / variance of the measured value includes at least one of the following monitoring indicators:

[0218] Arrival time standard deviation / variance: The measurement indicator is the standard deviation / variance of the arrival time estimate within a shorter moving distance. If the model architecture is AI / ML-assisted positioning (single TRP input, single model) or AI / ML-assisted positioning (multiple TRP inputs), the reported result is the statistic (such as maximum value, average value) of the standard deviation / variance of the arrival time within the shorter moving distance corresponding to all TRPs. The indicator is indicated in the form of an integer, such as the integer range {0,1,…,10}. When the indicator is standard deviation, the unit is ns, and when the indicator is variance, the unit is ns 2 If the standard deviation / variance 0≤s<1, then the value is 0. Similarly, if the standard deviation / variance s≥10, then the value is 10. If the model architecture is AI / ML-assisted positioning (single TRP input, multiple models), the reported result is the standard deviation / variance of the estimated arrival time within the shorter moving distance corresponding to each TRP, where the measurement indicator representation of each TRP is as described above.

[0219] RSTD standard deviation / variance: The measurement indicator is the standard deviation / variance of the RSTD estimate within a shorter moving distance. If the model architecture is AI / ML-assisted positioning (single TRP input, single model) or AI / ML-assisted positioning (multiple TRP inputs), the reported result is the statistic (such as maximum value, average value) of the standard deviation / variance of the RSTD estimate within the shorter moving distance corresponding to all TRPs. The indicator is indicated in the form of an integer, such as the integer range {0,1,…,10}. When the indicator is standard deviation, the unit is ns, and when the indicator is variance, the unit is ns 2 If the standard deviation / variance 0≤s<1, then the value is 0. Similarly, if the standard deviation / variance s≥10, then the value is 10. If the model architecture is AI / ML-assisted positioning (single TRP input, multiple models), the reported result is the standard deviation / variance of the RSTD estimate within the shorter moving distance corresponding to each TRP, where the measurement indicator representation of each TRP is as described above.

[0220] AoD standard deviation / variance: The measurement indicator is the standard deviation / variance of the AoD estimate within a shorter moving distance. If the model architecture is AI / ML-assisted positioning (single TRP input, single model) or AI / ML-assisted positioning (multiple TRP inputs), the reported result is the statistic (such as maximum value, average value) of the standard deviation / variance of the AoD estimate within the shorter moving distance corresponding to all TRPs. The indicator is indicated in the form of an integer, such as the integer range {0,1,…,10}. When the indicator is standard deviation, the unit is degree, and when the indicator is variance, the unit is deg 2If the standard deviation / variance 0≤s<1, then the value is 0. Similarly, if the standard deviation / variance s≥10, then the value is 10. If the model architecture is AI / ML-assisted positioning (single TRP input, multiple models), the reported result is the standard deviation / variance of the AoD estimate within the shorter moving distance corresponding to each TRP, where the measurement indicator representation of each TRP is as described above.

[0221] Model Identifier ID List: This parameter indicates the model ID of the model (group) corresponding to the monitoring indicator solution. If the model architecture is AI / ML-assisted positioning (single TRP input, multiple models), the number of model IDs in the Model ID List equals the number of models in the model group, and the order of the model IDs matches the order of the corresponding model results in the monitoring solution. For other model architectures, the number of model ID list elements is 1.

[0222] Fourth embodiment: reporting of monitoring and solution results of the base station side model:

[0223] The fourth embodiment can be implemented independently. In some embodiments of the present application, the fourth embodiment can also be combined with other embodiments. For example, the fourth embodiment can be implemented in combination with the first embodiment, the second embodiment, the third embodiment, the fifth embodiment, the sixth embodiment, and / or the seventh embodiment. These embodiments can be implemented sequentially or in parallel, and the present application is not limited thereto.

[0224] Figure 5A is a flow chart of the method for reporting monitoring data related to positioning of the base station side model provided in an embodiment of the present application. As shown in Figure 5A, the method for reporting monitoring data related to positioning of the base station side model is executed on the base station and includes at least one of the following operations: Operation 401A: When the monitoring indicator solution is performed on the base station and the model monitoring is performed on the positioning management function LMF entity, the base station reports the monitoring indicator solution result to the LMF entity through signaling.

[0225] Through the above technical solution, the base station reports the monitoring indicator solution result to the LMF entity. In this way, the positioning-related monitoring data reporting positioning method under the base station side model can be improved and / or the stability of the model operation can be improved.

[0226] Figure 5B is a flow chart of the method for reporting monitoring data related to positioning of the base station side model provided in an embodiment of the present application. As shown in Figure 5B, the method for reporting monitoring data related to positioning of the base station side model is executed in the positioning management function LMF entity, and includes at least one of the following operations: Operation 501B: When the monitoring indicator solution is performed in the base station and the model monitoring is performed in the LMF entity, the LMF entity receives the monitoring indicator solution result reported by the base station through the signaling.

[0227] Through the above technical solution, the LMF entity receives the monitoring indicator solution reported by the base station. In this way, the positioning-related monitoring data reporting method under the base station side model can be improved and / or the stability of the model operation can be improved.

[0228] Specifically, the UE is, for example, the user equipment 120 shown in FIG1A . The base station is, for example, the base station 110 shown in FIG1A . The base station 110 is, for example, a gNB. The LMF entity is, for example, the network 130 shown in FIG1A .

[0229] In some embodiments of the present application, the signaling is NR Positioning Protocol A NRPPa signaling. In some embodiments of the present application, the monitoring indicator solution result is carried in a monitoring indicator solution report message or in a measurement report message. In some embodiments of the present application, for each model or model group participating in the monitoring, the monitoring indicator solution result includes a measurement value error and / or a measurement value standard deviation / variance. In some embodiments of the present application, the measurement value error includes at least one of the following: relative time of arrival RTOA error, angle of arrival AoA error, and F1-score indicated by LOS / NLOS.

[0230] In some embodiments of the present application, the measurement value standard deviation / variance includes relative time of arrival RTOA standard deviation / variance and / or angle of arrival AoA standard deviation / variance.

[0231] Figure 5C is a flow chart of the method for reporting monitoring data related to positioning of the base station side model provided in an embodiment of the present application. As shown in Figure 5C, the method for reporting monitoring data related to positioning of the base station side model includes at least one of the following operations: If the monitoring indicator solution is performed on the base station side, and the model monitoring is performed on the LMF entity side, the base station needs to report the results of the monitoring indicator solution to the LMF entity through NRPPa signaling. A new monitoring indicator solution reporting message may be added or reported in the original measurement reporting message. For each model or model group involved in monitoring, its monitoring indicators include measurement value error and / or measurement value standard deviation / variance. The explanation of the parameters is as follows:

[0232] The measurement error includes at least one of the following monitoring indicators:

[0233] RTOA error: When the UE can receive GNSS signals and is in a LOS environment, it can be assumed that GNSS is accurate and the true label of RTOA can be obtained through the UE GNSS position coordinates (or known PRU position coordinates) and TRP coordinates. The measurement indicator is the error between the RTOA estimate and the true label of RTOA. If the model architecture is AI / ML assisted positioning (single TRP input, single model), the reported result is the error statistic (such as maximum value, average value) between the RTOA estimate and the true label of RTOA corresponding to all TRPs under single or multiple monitoring. The indicator is indicated in the form of an integer, such as the integer range {0,1,…,10}, the unit is ns, if the indicator 0≤s<1, then take 0, and so on, if the indicator s≥10, then take 10. If the model architecture is AI / ML-assisted positioning (single TRP input, multiple models), the reported result can be the error between the RTOA estimate corresponding to each TRP under a single monitoring and the RTOA true label, or the error statistics (such as maximum value, average value) between the RTOA estimate corresponding to each TRP under multiple monitoring and the RTOA true label, where the representation of the measurement indicator corresponding to each TRP is as described above.

[0234] AoA error: When the UE can receive GNSS signals and is in a Loss of System (LOS) environment, it can be assumed that GNSS is accurate and the true AoA label can be obtained through the UE GNSS position coordinates (or known PRU position coordinates) and the TRP coordinates. The measurement indicator is the error between the AoA estimate and the true AoA label. If the model architecture is AI / ML-assisted positioning (single TRP input, single model), the reported result is the error statistic (such as maximum value, average value) between the AoA estimate and the true AoA label for all TRPs under single or multiple monitoring. The indicator is expressed as an integer, for example, in the range {0,1,…,10}, in degrees. If the indicator 0≤s<1, it is 0, and so on. If the indicator s≥10, it is 10. If the model architecture is AI / ML-assisted positioning (single TRP input, multiple models), the reported result can be the error between the AoA estimate and the AoA true label corresponding to each TRP under a single monitoring, or the error statistics (such as maximum value, average value) between the AoA estimate and the AoA true label corresponding to each TRP under multiple monitoring. The representation of the measurement indicator corresponding to each TRP is as described above.

[0235] F1-score of LOS / NLOS indications: When the UE can receive GNSS signals and is in a Loss of View (LOS) environment, GNSS accuracy can be assumed. The true label of the LOS / NLOS indication can be obtained using the UE GNSS position coordinates (or known PRU position coordinates), the TRP position coordinates, and a digital map (incorporating technologies such as LiDAR and ISAC). Multiple samples (true labels) generated through multiple monitoring cycles can be measured using the F1-score, which can be used to evaluate classification performance. The value range is [0, 1], with larger values ​​indicating better model performance. If the model architecture is AI / ML-assisted positioning (single TRP input, single model), the reported result is the F1-score calculated by the estimated and true labels of the LOS / NLOS indications corresponding to all TRPs. The indicator is indicated in the form of an explicit indicator, such as {0, dot2, dot4, ..., 1}. If the indicator 0≤s<0.2, it is taken as 0, and so on. If the indicator s=1, it is taken as 1, or the F1-score of the LOS / NLOS indication corresponding to each TRP is reported, where the representation of the measurement indicator corresponding to each TRP is as described above. If the model architecture is AI / ML-assisted positioning (single TRP input, multiple models), the reported result is the F1-score of the LOS / NLOS indication corresponding to each TRP, where the representation of the measurement indicator corresponding to each TRP is as described above.

[0236] Standard deviation / variance of measured values: The output of a suitable model should be stable over a continuous period of time. If there are outliers, it indicates that the model's performance is not good. This includes at least one of the following monitoring indicators:

[0237] RTOA standard deviation / variance: The metric is the standard deviation / variance of the RTOA estimate within the UE's short range of motion. If the model architecture is AI / ML-assisted positioning (single TRP input, single model), the reported result is the statistic (e.g., maximum value, average value) of the standard deviation / variance of the RTOA estimate within the UE's short range of motion for all TRPs. This metric is expressed as an integer, for example, in the range {0, 1, ..., 10}. When the metric is the standard deviation, the unit is ns; when the metric is the variance, the unit is ns^2. If the standard deviation / variance 0≤s<1, the value is 0. Similarly, if the standard deviation / variance s≥10, the value is 10. If the model architecture is AI / ML-assisted positioning (single TRP input, multiple models), the reported result is the standard deviation / variance of the RTOA estimate within the UE's short range of motion for each TRP. The metric representation for each TRP is as described above.

[0238] AoA standard deviation / variance: The measurement indicator is the standard deviation / variance of the AoA estimate within the shortest moving distance of the UE. If the model architecture is AI / ML assisted positioning (single TRP input, single model), the reported result is the statistic (such as maximum value, average value) of the standard deviation / variance of the AoA estimate within the short moving distance of the UE corresponding to all TRPs. The indicator is indicated in the form of an integer, such as the integer range {0,1,…,10}. When the indicator is standard deviation, the unit is deg, and when the indicator is variance, the unit is deg 2 If the standard deviation / variance 0≤s<1, then it is set to 0. Similarly, if the standard deviation / variance s≥10, then it is set to 10. If the model architecture is AI / ML-assisted positioning (single TRP input, multiple models), the reported result is the standard deviation / variance of the AoA estimation within the shorter moving distance of the UE corresponding to each TRP, where the measurement indicator representation of each TRP is as described above.

[0239] Model Identifier ID List: This parameter indicates the model ID of the model (group) corresponding to the monitoring indicator solution. If the model architecture is AI / ML-assisted positioning (single TRP input, multiple models), the number of model IDs in the Model ID List equals the number of models in the model group, and the order of the model IDs matches the order of the corresponding model results in the monitoring indicator solution. If the model architecture is AI / ML-assisted positioning (single TRP input, single model), the number of elements in the Model ID List is 1.

[0240] Fifth embodiment: Model transfer request of UE side model:

[0241] The fifth embodiment can be implemented independently. In some embodiments of the present application, the fifth embodiment can also be combined with other embodiments. For example, the fifth embodiment can be implemented in combination with the first embodiment, the second embodiment, the third embodiment, the fourth embodiment, the sixth embodiment, and / or the seventh embodiment. These embodiments can be implemented sequentially or in parallel, and the present application is not limited thereto.

[0242] Figure 6A is a flow chart of the positioning-related model transfer method of the user equipment UE side model provided in an embodiment of the present application. As shown in Figure 6A, the positioning-related model transfer method of the user equipment UE side model is executed on the UE and includes at least one of the following operations: Operation 601A: The UE receives a model transfer trigger condition configured by the positioning management function LMF entity through signaling, wherein the model transfer trigger condition indicates that the UE initiates a model transfer request when a specified condition is met; Operation 602A: After the UE determines through model monitoring that the model transfer trigger condition is met, the UE requests a model transfer to the LMF entity through the signaling.

[0243] Through the above technical solution, the UE receives the model transfer trigger condition configured by the location management function LMF entity, and the UE requests the model transfer from the LMF entity. In this way, the positioning-related model transfer method under the user equipment side model can be improved and / or the stability of the model operation can be enhanced.

[0244] Figure 6B is a flow chart of the positioning-related model transfer method of the user equipment UE side model provided in an embodiment of the present application. As shown in Figure 6B, the positioning-related model transfer method of the user equipment UE side model is executed in the positioning management function LMF entity, and includes at least one of the following operations: Operation 601B: The LMF entity sends a model transfer trigger condition to the UE through signaling, wherein the model transfer trigger condition indicates that a model transfer request is initiated when a specified condition is met; Operation 602B: After the UE determines that the model transfer trigger condition is met through model monitoring, the LMF entity receives the UE's request for model transfer through the signaling.

[0245] Through the above technical solution, the LMF entity sends a model transfer trigger condition to the UE, and the LMF entity receives the UE's request for model transfer. In this way, the positioning-related model transfer method under the user equipment side model can be improved and / or the stability of the model operation can be improved.

[0246] Specifically, the UE is, for example, the user equipment 120 shown in FIG1A . The base station is, for example, the base station 110 shown in FIG1A . The base station 110 is, for example, a gNB. The LMF entity is, for example, the network 130 shown in FIG1A .

[0247] In some embodiments of the present application, the signaling is Long Term Evolution Positioning Protocol LPP signaling. In some embodiments of the present application, the model transfer triggering condition includes at least one of the following: maximum position error, maximum measurement value error, maximum coefficient of variation CV, maximum distance between the current estimated position and the previous position, or maximum difference between the current measurement value and the previous measurement value. In some embodiments of the present application, the maximum measurement value error includes at least one of the following: maximum arrival time error, maximum reference signal time difference RSTD error, or maximum angle of departure AoD error. In some embodiments of the present application, the maximum difference between the current measurement value and the previous measurement value includes at least one of the following: maximum difference between the current arrival time and the previous arrival time, maximum difference between the current RSTD and the previous RSTD, or maximum difference between the current AoD and the previous AoD. In some embodiments of the present application, the parameters provided during the model transfer request include at least one of the following: monitoring indicator solution results, model architecture, model flexibility, model type, area type, or positioning method. In some embodiments of the present application, the monitoring indicator solution results include at least one of the following: position error, arrival time error, RSTD error, AoD error, position variation coefficient, arrival time variation coefficient, RSTD variation coefficient, AoD variation coefficient, the difference between the current output position and the previous position, the difference between the current output arrival time and the previous arrival time, the difference between the current output RSTD and the previous RSTD, or the difference between the current output AoD and the previous AoD.

[0248] Figure 6C is a flow chart of a positioning-related model transfer method for a user equipment UE side model provided in an embodiment of the present application. As shown in Figure 6C, the positioning-related model transfer method for the user equipment UE side model includes at least one of the following steps: Step 1: The LMF entity configures a model transfer trigger condition to the UE through LPP signaling to indicate that the UE can initiate a model transfer request when the specified conditions are met. The trigger condition includes at least one of the following: maximum position error, maximum measurement value error, maximum coefficient of variation (CV), the maximum distance between the current estimated position and the previous position, or the maximum difference between the current measurement value and the previous measurement value. The explanation of each condition is as follows: Maximum position error: This parameter indicates the maximum error between the position estimate and the true position tag. The threshold is indicated in the form of an integer, for example, the integer range can be {1, 2, ..., 1000}, in cm. The UE can compare the distance between the position estimate and the true position tag with the threshold;

[0249] Maximum measurement error: This parameter indicates the maximum error between the estimated measurement value and the true measurement label, including at least one of the following trigger conditions:

[0250] Maximum arrival time error: This value is expressed in integers, indicating the maximum error between the estimated arrival time and the true arrival time label. For example, the range of possible integers is {1, 2, ..., 1000}, and the unit is ns.

[0251] Maximum RSTD error: Indicates the maximum error between the RSTD estimate and the RSTD true label in the form of an integer. For example, the integer range is {1, 2, ..., 1000}, and the unit is ns.

[0252] Maximum AoD error: This is an integer indicating the maximum error between the AoD estimate and the true AoD label. For example, the integer range is {1, 2, …, 300}, and the unit is minutes.

[0253] The UE may compare the maximum value of the error between the estimated measurement value and the true tag of the measurement value corresponding to all TRPs under single or multiple monitoring with the corresponding threshold;

[0254] Maximum coefficient of variation: The coefficient of variation is defined as the ratio of the standard deviation to the mean, which removes the influence of magnitude and facilitates threshold setting. This parameter is indicated as an integer, for example, in the range of {1, 2, ..., 15}, expressed in %. Different thresholds can be configured for different output parameters (such as location, arrival time, RSTD, AoD) and / or the same threshold can be configured for different parameters. The UE can compare the maximum value of the CV output of all TRPs under multiple monitoring with the threshold;

[0255] Maximum distance between the current estimated position and the previous position: This parameter is the radius of the circle centered at the previous position. The LMF entity can be configured based on the UE speed. The threshold of this parameter is indicated by an integer, for example, in the range of {1, 2, ..., 1000}, in mm. The UE can compare the distance between the model output position and the previous position with the threshold;

[0256] The maximum difference between the current measurement value and the previous measurement value: includes at least one of the following trigger conditions:

[0257] Maximum difference between the current arrival time and the previous arrival time: This value is expressed in integers, indicating the maximum difference between the current arrival time estimate and the previous arrival time. For example, the range of possible integers is {1, 2, ..., 1000}, and the unit is ns.

[0258] Maximum difference between the current RSTD and the previous RSTD: This value is expressed in integers, indicating the maximum difference between the current RSTD estimate and the previous RSTD. For example, the range of possible integers is {1, 2, ..., 1000}, and the unit is ns.

[0259] Maximum difference between the current AoD and the previous AoD: This value is expressed in integers, indicating the maximum difference between the current AoD estimate and the previous AoD. For example, the range of possible integers is {1, 2, …, 300}, in minutes.

[0260] The UE may compare the maximum value of the error between the current measurement value and the previous measurement value corresponding to all TRPs with the corresponding threshold.

[0261] The LMF entity selects at least one of the above conditions for configuration. If any of the conditions are not met (the calculated parameters exceed the corresponding threshold) for all models (including non-AI positioning methods), it means that the performance of all models is poor, and the UE can trigger a model transfer request. Step 2: After the UE determines through model monitoring that the trigger condition configured by the LMF entity is met, it requests model transfer to the LMF entity through LPP signaling. The parameters provided during the request include at least one of the following: monitoring indicator solution results, model architecture, model flexibility, model type, area type or positioning method, to assist the LMF entity in selecting a model. The explanation of each parameter is as follows;

[0262] Monitoring indicator solution results: Parameters output by each model (group) corresponding to the trigger conditions configured by the LMF entity, including at least one of the following monitoring indicator solution results:

[0263] Position error: It is expressed in the form of an integer, for example, the integer range can be {0, 1, 2, ..., 1000}, and the unit is cm. If the error 0≤e<1, it is 0. Similarly, if the error e≥1000, it is 1000.

[0264] Arrival time error: It is expressed as an integer, for example, in the range of {0, 1, 2, ..., 1000}, in nanoseconds. If the error 0 ≤ e < 1, the value is 0. Similarly, if the error e ≥ 1000, the value is 1000.

[0265] RSTD error: It is expressed as an integer, for example, in the range of {0, 1, 2, ..., 1000}, in nanoseconds. If the error 0 ≤ e < 1, the value is 0. Similarly, if the error e ≥ 1000, the value is 1000.

[0266] AoD error: It is expressed in the form of an integer, for example, the integer range can be {0, 1, 2, ..., 300}, and the unit is minutes. If the error 0≤e<1, it is 0. Similarly, if the error e≥300, it is 300.

[0267] Position coefficient of variation: It is expressed in the form of an integer, for example, the integer range can be {0, 1, 2, ..., 15}, and the unit is %. If the coefficient of variation 0≤CV<1, it is taken as 0. Similarly, if the coefficient of variation CV≥15, it is taken as 15.

[0268] Arrival time variation coefficient: It is expressed in the form of an integer, for example, the integer range can be {0, 1, 2, ..., 15}, and the unit is %. If the coefficient of variation 0≤CV<1, it is 0. Similarly, if the coefficient of variation CV≥15, it is 15.

[0269] RSTD coefficient of variation: It is expressed in the form of an integer, for example, the integer range is {0, 1, 2, ..., 15}, and the unit is %. If the coefficient of variation 0≤CV<1, it is 0. Similarly, if the coefficient of variation CV≥15, it is 15.

[0270] AoD coefficient of variation: It is expressed in the form of an integer, for example, the integer range can be {0, 1, 2, ..., 15}, and the unit is %. If the coefficient of variation 0≤CV<1, it is 0. Similarly, if the coefficient of variation CV≥15, it is 15.

[0271] The difference between the current output position and the previous position is expressed in the form of an integer. For example, the integer range is {0, 1, 2, ..., 1000}, and the unit is mm. If the difference 0≤e<1, then 0 is taken. Similarly, if the difference e≥1000, then 1000 is taken.

[0272] The difference between the current output arrival time and the previous arrival time is expressed as an integer, for example, in the range of {0, 1, 2, ..., 1000}, in nanoseconds. If the difference 0 ≤ e < 1, the value is 0. Similarly, if the difference e ≥ 1000, the value is 1000.

[0273] The difference between the current output RSTD and the previous RSTD is expressed as an integer, for example, in the range of {0, 1, 2, ..., 1000}, in nanoseconds. If the difference 0 ≤ e < 1, the value is 0. Similarly, if the difference e ≥ 1000, the value is 1000.

[0274] The difference between the current output AoD and the previous AoD is expressed as an integer, for example, in the range of {0, 1, 2, ..., 300}, in minutes. If the difference 0 ≤ e < 1, the value is 0. Similarly, if the difference e ≥ 300, the value is 300.

[0275] Model Architecture: The model architecture includes at least one of the following: AI / ML direct positioning, AI / ML-assisted positioning (multiple TRP inputs), AI / ML-assisted positioning (single TRP input, single model), or AI / ML-assisted positioning (single TRP input, multiple models). A bitmap is used to indicate the required model architecture. Each bit corresponds to a model architecture. If a bit is 1, it indicates that the model architecture corresponding to that bit is required. If a new model architecture is proposed, the number of bits can be increased.

[0276] Figure 6D is a schematic diagram of AI / ML direct positioning provided in an embodiment of the present application. Figure 6E is a schematic diagram of AI / ML assisted positioning (multiple TRP inputs) provided in an embodiment of the present application. Figure 6F is a schematic diagram of AI / ML assisted positioning (single TRP input, single model) provided in an embodiment of the present application. Figure 6G is a schematic diagram of AI / ML assisted positioning (single TRP input, multiple models) provided in an embodiment of the present application. Model flexibility: This parameter indicates whether the number of TRPs input to the model can be changed. The required model flexibility is indicated in the form of a bitmap. For example, the first bit indicates that the number of TRPs is fixed, and the second bit indicates that the number of TRPs can be changed. If the bit is 1, it means that the model flexibility corresponding to the bit is required. This parameter exists when the model architecture parameters indicate AI / ML direct positioning or AI / ML assisted positioning (multiple TRP inputs), and is default in other cases.

[0277] Model type: The model type includes at least one of the following: region-specific model, UE-specific model or hybrid model. The required model type is indicated in the form of a bitmap. Each bit corresponds to a model type. If the bit is 1, it means that the model type corresponding to the bit is required. If there is a new model type, the number of bits can be increased.

[0278] Region Type: This parameter specifies at least one of the following: base station level, cell level, beam level, or cell portion level. This parameter uses a bitmap to indicate the desired region type, with each bit corresponding to a region type. A bit set to 1 indicates that the region type is required. The number of bits may be increased if new region types are specified. This parameter is present only if the Model Type parameter indicates a region-specific model or a hybrid model; it is default otherwise.

[0279] Positioning method: If the UE requires an area-specific model or a hybrid model, and the model monitoring shows that the performance of all models on the UE side is poor, the location information output by the UE or LMF entity is unreliable and other positioning methods need to be used for re-positioning. Positioning methods include E-CID and / or AI positioning. The UE can use a bitmap to indicate the positioning methods that can be used by the LMF entity based on factors such as NLOS and dense multipath. Each bit corresponds to a positioning method. If the bit is 1, it means that the LMF entity can use the positioning method corresponding to the bit. If there is a new positioning method, the number of bits can be increased. This parameter exists when the model type parameter indicates an area-specific model or a hybrid model, and is default in other cases.

[0280] Sixth embodiment: Model transfer request of base station side model:

[0281] The sixth embodiment can be implemented independently. In some embodiments of the present application, the sixth embodiment can also be combined with other embodiments. For example, the sixth embodiment can be implemented in combination with the first embodiment, the second embodiment, the third embodiment, the fourth embodiment, the fifth embodiment, the sixth embodiment, and / or the seventh embodiment. These embodiments can be implemented in sequence or in parallel, and the present application is not limited thereto. Figure 7A is a flow chart of a positioning-related model transfer method for a base station side model provided in an embodiment of the present application. As shown in Figure 7A, the positioning-related model transfer method for a base station side model is executed on the base station and includes at least one of the following operations: Operation 701A: The base station receives a model transfer trigger condition configured by a positioning management function LMF entity through signaling, wherein the model transfer trigger condition indicates that the base station initiates a model transfer request when a specified condition is met; Operation 701B: After the base station determines that the model transfer trigger condition is met through model monitoring, the base station requests model transfer from the LMF entity through the signaling.

[0282] Through the above technical solution, the base station receives the model transfer trigger condition configured by the location management function LMF entity, and the base station requests the model transfer from the LMF entity. In this way, the positioning-related model transfer method under the base station side model can be improved and / or the stability of the model operation can be enhanced.

[0283] Figure 7B is a flow chart of the positioning-related model transfer method of the base station side model provided in an embodiment of the present application. As shown in Figure 7B, the positioning-related model transfer method of the base station side model is executed in the positioning management function LMF entity, and includes at least one of the following operations: Operation 701B: The LMF entity configures the model transfer trigger condition to the base station through signaling, wherein the model transfer trigger condition indicates that a model transfer request is initiated when a specified condition is met; Operation 702B: After the base station determines that the model transfer trigger condition is met through model monitoring, the LMF entity receives the model transfer request from the base station through the signaling.

[0284] Through the above technical solution, the LMF entity configures the model transfer trigger condition to the base station, and the LMF entity receives the model transfer request from the base station. In this way, the positioning-related model transfer method under the base station side model can be improved and / or the stability of the model operation can be improved. In some embodiments of the present application, the signaling is NR Positioning Protocol A NRPPa signaling. In some embodiments of the present application, the model transfer trigger condition includes at least one of the following: maximum measurement value error, maximum coefficient of variation CV, or maximum difference between the current measurement value and the previous measurement value. In some embodiments of the present application, the maximum measurement value error includes the maximum relative time of arrival RTOA error and / or the maximum angle of arrival AoA error. In some embodiments of the present application, the maximum difference between the current measurement value and the previous measurement value includes the maximum difference between the current RTOA and the previous RTOA and / or the maximum difference between the current AoA and the previous AoA. In some embodiments of the present application, the parameters provided during the model transfer request include at least one of the following: monitoring indicator solution result, LMF measurement identifier ID, radio access network RAN ​​measurement ID, model architecture, model type, area type, or positioning method. In some embodiments of the present application, the monitoring indicator solution result includes at least one of the following: RTOA error, AoA error, RTOA coefficient of variation, AoA coefficient of variation, the difference between the current output RTOA and the previous RTOA, or the difference between the current output AoA and the previous AoA.

[0285] Specifically, the UE is, for example, the user equipment 120 shown in FIG1A . The base station is, for example, the base station 110 shown in FIG1A . The base station 110 is, for example, a gNB. The LMF entity is, for example, the network 130 shown in FIG1A .

[0286] FIG7C is a flow chart of a positioning-related model transfer method for a base station side model provided in an embodiment of the present application. As shown in FIG7C , the positioning-related model transfer method for a base station side model includes at least one of the following steps: Step 1: The LMF entity configures a model transfer trigger condition to the base station through NRPPa signaling to indicate that the base station can initiate a model transfer request when the specified conditions are met. The trigger condition includes at least one of the following: maximum measurement value error, maximum coefficient of variation (CV), or maximum difference between the current measurement value and the previous measurement value. The explanation of each condition is as follows:

[0287] Maximum measurement error: This parameter indicates the maximum error between the estimated measurement value and the true label of the measurement value. Different indication forms can be used for different measurement quantities, such as:

[0288] RTOA error: It is an integer indicating the maximum error between the RTOA estimate and the true RTOA label. For example, the integer range is {1, 2, …, 1000}, and the unit is ns.

[0289] AoA error: It is an integer indicating the maximum error between the AoA estimate and the true AoA label. For example, the integer range is {1, 2, ..., 300}, and the unit is minutes.

[0290] The base station (main TRP) can compare the maximum value of the error between the estimated measurement values ​​and the true labels of the measurement values ​​corresponding to all TRPs under single or multiple monitoring with the corresponding threshold.

[0291] Maximum Coefficient of Variation: The coefficient of variation is defined as the ratio of the standard deviation to the mean. It removes the effects of magnitude and facilitates threshold setting. This parameter is expressed as an integer, for example, in the range {1, 2, …, 15}, expressed in percent. Different thresholds can be configured for different output parameters (such as RTOA and AoA), and / or the same threshold can be configured for different parameters. The base station (master TRP) can compare the maximum value of the CV output from all TRPs over multiple monitoring cycles with the threshold.

[0292] The maximum difference between the current measurement value and the previous measurement value: includes at least one of the following trigger conditions:

[0293] Maximum difference between the current RTOA and the previous RTOA: This value is expressed in ns and is in the form of an integer. For example, the range of integers is {1, 2, …, 1000}.

[0294] Maximum difference between the current AoA and the previous AoA: This value is expressed in integers, indicating the maximum difference between the current AoA estimate and the previous AoA. For example, the value can be an integer in the range of {1, 2, ..., 300}, in minutes.

[0295] The base station (master TRP) may compare the maximum value of the error between the current estimated measurement value and the previous measurement value corresponding to all TRPs with the corresponding threshold value.

[0296] The LMF entity selects at least one of the above conditions for configuration. If any of the conditions are not met for all models (including traditional methods) (the calculated parameters exceed the corresponding threshold), it means that the performance of all models is poor, and the base station can trigger a model transfer request. Step 2: After the base station determines through model monitoring that the trigger condition configured by the LMF entity is met, it requests model transfer from the LMF entity through NRPPa signaling. The parameters provided during the request include at least one of the following: monitoring indicator solution results, LMF entity measurement ID, radio access network RAN ​​measurement ID, model architecture, model type, area type or positioning method, to assist the LMF entity in selecting a model. The explanation of each parameter is as follows;

[0297] Monitoring indicator solution results: Parameters output by each model (group) corresponding to the trigger conditions configured by the LMF entity, including at least one of the following monitoring indicator solution results:

[0298] RTOA error: It is expressed in the form of an integer, for example, the integer range can be {0, 1, 2, ..., 1000}, the unit is ns. If the error 0≤e<1, it is 0. Similarly, if the error e≥1000, it is 1000.

[0299] AoA error: It is expressed in the form of an integer. For example, the integer range is {0, 1, 2, ..., 300}, and the unit is minutes. If the error 0≤e<1, it is 0. Similarly, if the error e≥300, it is 300.

[0300] RTOA coefficient of variation: It is expressed in the form of an integer, for example, the integer range can be {0,1,2,…,15}, and the unit is %. If the coefficient of variation 0≤CV<1, it is taken as 0. Similarly, if the coefficient of variation CV≥15, it is taken as 15.

[0301] AoA coefficient of variation: It is expressed in the form of an integer, for example, the integer range can be {0, 1, 2, ..., 15}, and the unit is %. If the coefficient of variation 0≤CV<1, it is 0. Similarly, if the coefficient of variation CV≥15, it is 15.

[0302] The difference between the current output RTOA and the previous RTOA is expressed as an integer, for example, in the range of {0, 1, 2, ..., 1000}, in nanoseconds. If the difference 0 ≤ e < 1, the value is 0. Similarly, if the difference e ≥ 1000, the value is 1000.

[0303] The difference between the current output AoA and the previous AoA is expressed as an integer, for example, in the range of {0, 1, 2, ..., 300}, in minutes. If the difference 0 ≤ e < 1, the value is 0. Similarly, if the difference e ≥ 300, the value is 300.

[0304] LMF Entity Measurement ID: This parameter indicates the LMF Entity Measurement ID corresponding to the requested model. This parameter is expressed as an integer, for example, in the range {1, 2, ..., 65536}.

[0305] RAN measurement ID: This parameter indicates the RAN measurement ID corresponding to the requested model. This parameter is expressed as an integer, for example, in the range of {1, 2, ..., 65536}.

[0306] Model Architecture: The model architecture includes at least one of the following: AI / ML direct positioning, AI / ML-assisted positioning (multiple TRP inputs), AI / ML-assisted positioning (single TRP input, single model), or AI / ML-assisted positioning (single TRP input, multiple models). A bitmap is used to indicate the required model architecture, with each bit corresponding to a model architecture. If a bit is 1, the corresponding model architecture is required. The number of bits can be increased if a new model architecture is required.

[0307] Model type: The model type includes at least one of the following: region-specific model, UE-specific model, and hybrid model. The required model type is indicated in the form of a bitmap. Each bit corresponds to a model type. If the bit is 1, it means that the model type corresponding to the bit is required. If there is a new model type, the number of bits can be increased.

[0308] Region Type: This parameter specifies at least one of the following: base station level, cell level, beam level, or cell portion level. This parameter is a bitmap indicating the desired region type, with each bit corresponding to a region type. A bit set to 1 indicates that the region type is required. The number of bits may be increased if new region types are specified. This parameter is present only if the Model Type parameter indicates region-specific or mixed; it is default otherwise.

[0309] Positioning method: If the base station requires a region-specific model or a hybrid model, and the model monitoring shows that the performance of all models on the base station side is poor, the location information output by the LMF entity is unreliable and other positioning methods need to be used for re-positioning. Positioning methods include E-CID and / or AI positioning. The base station can use a bitmap to indicate the positioning methods that can be used by the LMF entity based on factors such as NLOS and dense multipath. Each bit corresponds to a positioning method. If the bit is 1, it means that the LMF entity can use the positioning method corresponding to the bit. If there is a new positioning method, the number of bits can be increased. This parameter exists when the model type parameter indicates a region-specific model or a hybrid model, and is default in other cases.

[0310] Seventh embodiment: reporting of AI positioning capabilities:

[0311] The seventh embodiment can be implemented independently. In some embodiments of the present application, the seventh embodiment can also be combined with other embodiments. For example, the seventh embodiment can be combined with the first embodiment, the second embodiment, the third embodiment, the fourth embodiment, the fifth embodiment, and / or the sixth embodiment. These embodiments can be implemented in sequence or in parallel, and the present application is not limited thereto.

[0312] Figure 8A is a flow chart of the UE positioning capability assistance method of the user equipment UE side model provided in an embodiment of the present application. As shown in Figure 8A, the UE positioning capability assistance method of the user equipment UE side model is executed on the UE and includes at least one of the following operations: Operation 801A: The UE reports the AI ​​positioning capability to the network side device through signaling, wherein the AI ​​positioning capability is used to assist the network side device in selecting a model.

[0313] Through the above technical solution, the UE reports its AI positioning capabilities to the network side equipment. This can improve the UE positioning capability assistance method under the user equipment side model and / or enhance the stability of the model operation.

[0314] Figure 8B is a flow chart of the UE positioning capability assistance method of the user equipment UE side model provided in an embodiment of the present application. As shown in Figure 8B, the UE positioning capability assistance method of the user equipment UE side model is executed on the network side device and includes at least one of the following operations: Operation 801B: The network side device receives the AI ​​positioning capability reported by the UE through signaling, wherein the AI ​​positioning capability is used to assist the network side device in selecting a model.

[0315] Through the above technical solution, the network-side device receives the AI ​​positioning capability reported by the UE. In this way, the UE positioning capability assistance method under the user equipment side model can be improved and / or the stability of the model operation can be enhanced.

[0316] Specifically, the UE is, for example, the user equipment 120 shown in FIG1A . The base station is, for example, the base station 110 shown in FIG1A . The base station 110 is, for example, a gNB. The LMF entity is, for example, the network 130 shown in FIG1A .

[0317] In some embodiments of the present application, the AI ​​positioning capability includes at least one of the following: supported positioning modes, support for artificial intelligence AI positioning, support for simultaneous activation of AI positioning and non-AI positioning, supported model input types, support for sampling point screening, the maximum number of screening sampling points, the maximum number of loaded models, the maximum number of activated models, or the maximum number of simultaneously monitored models. In some embodiments of the present application, if the UE supports the AI ​​positioning, the UE sends a message providing capability to the LMF entity, and the message providing capability includes an information element providing AI positioning capability, and the AI ​​positioning capability is carried in the information element. In some embodiments of the present application, the UE positioning capability assistance method further includes the UE receiving an AI positioning capability request sent by the network side device through the signaling.

[0318] In some embodiments of the present application, the UE receives the AI ​​positioning capability request sent by the network side device through the signaling, including the UE receiving the AI ​​positioning capability request sent by the positioning management function LMF entity through long-term evolution positioning protocol LPP signaling. In some embodiments of the present application, the UE receives the AI ​​positioning capability request sent by the network side device through the signaling, including the UE receiving the AI ​​positioning capability request sent by the base station through radio resource control RRC signaling. In some embodiments of the present application, the UE receives a capability request message sent by the LMF entity, and the capability request message includes an information element requesting AI positioning capability, which is used to instruct the UE to report the AI ​​positioning capability. In some embodiments of the present application, after receiving the AI ​​positioning capability request, the UE reports the AI ​​positioning capability to the network side device through the signaling. In some embodiments of the present application, the network side device includes a base station and / or a positioning management function LMF entity.

[0319] Option 1: UE proactively reports:

[0320] Figure 8C is a flow chart of a UE positioning capability assistance method for a user equipment UE side model provided in an embodiment of the present application. As shown in Figure 8C, the UE positioning capability assistance method for the user equipment UE side model includes at least one of the following operations: the UE actively reports the AI ​​positioning capability to the LMF entity through LPP signaling, and the reported capability includes at least one of the following: supported positioning modes, support for AI positioning, support for simultaneous activation of AI positioning and non-AI positioning, supported model input types, support for sampling point screening, maximum number of screening sampling points, maximum number of loaded models, maximum number of activated models, or maximum number of simultaneously monitored models, to assist network side devices (including LMF entities) in selecting models. The explanation of each capability is as follows:

[0321] Supported positioning modes: The AI ​​positioning of the UE side model has two modes: Case 1 (UE-based) and Case 2a (UE-assisted). This parameter indicates the positioning mode supported by the UE with AI capabilities. The optional positioning modes include at least one of the following: non-radio access technology RAT positioning, UE direct positioning, or UE assisted positioning. The supported positioning modes are indicated in the form of a bitmap. For example, a bit of 1 indicates that the UE supports the corresponding positioning mode.

[0322] Support for simultaneous activation of AI positioning and non-AI positioning: This parameter indicates whether the UE supports simultaneous activation of non-AI positioning and AI positioning. It can be indicated explicitly, if supported, then "supported" is indicated, otherwise no indication is given, or a Boolean value is used, such as 1 for support and 0 for non-support;

[0323] Supported model input types: In non-AI positioning, the UE measures the arrival time of the first few multipath signals through PRS. In AI positioning, the model needs to input complete channel samples. Optional model input types include at least one of the following: channel impulse response CIR, power delay profile PDP, delay profile DP, channel frequency domain response CFR, or power spectrum PS. The supported model input types are represented in the form of a bitmap. For example, a bit of 1 indicates that the UE supports the corresponding model input type. If a new model input type is introduced, the number of bits can be increased;

[0324] Support for sampling point screening: In AI positioning, the model also supports inputting channel samples that have been screened by sampling points (for example, filtering the sampling points with the strongest power). This parameter indicates whether the UE supports screening the required sampling points from continuous sampling points as the input of the model. It can be indicated explicitly. If supported, it indicates supported, otherwise no indication is given, or a Boolean value is used, such as 1 for support and 0 for unsupport. If the UE does not support sampling point screening, the bit corresponding to DP in the supported model input type should be 0;

[0325] Maximum number of sample points to be filtered: The number of sample points to be filtered may be limited by performance (depending on the sampling point filtering algorithm). The maximum number of sample points to be filtered supported by the UE is indicated explicitly.

[0326] Maximum number of loaded models: Due to the limited memory of UE, the number of models that can be loaded on the UE side is limited. The maximum number of models supported by the UE is indicated in integer form;

[0327] Maximum number of activated models: Since the operation of AI models consumes computing power, the number of models that can be activated simultaneously is limited by UE performance. The maximum number of activated models supported by the UE is indicated in integer form;

[0328] Maximum number of models monitored simultaneously: Because the operation of AI models and the calculation of monitoring indicators consume computing power, the number of models that can be monitored simultaneously is limited by UE performance. This value is used as an integer to indicate the maximum number of models that the UE supports and can monitor simultaneously.

[0329] The UE proactively sends a message to the LMF entity providing the capability. If the UE supports AI positioning, the message contains an information element providing the AI ​​capability. Otherwise, the information element does not exist and contains the above parameters. Therefore, the LPP signaling can be updated as follows:

[0330] Option 2: Network-side device requests reporting

[0331] Figure 8D is a flow chart of the UE positioning capability assistance method of the user equipment UE side model provided in an embodiment of the present application. As shown in Figure 8D, the UE positioning capability assistance method of the user equipment UE side model is executed on the network side device and includes at least one of the following steps: Step 1: The network side device (including the LMF entity and / or the base station) requests AI positioning capability from the UE, including the LMF entity requesting AI positioning capability from the UE through LPP signaling and / or the base station requesting AI positioning capability from the UE through RRC signaling.

[0332] If the LMF entity needs the UE's AI positioning capability, the LMF entity sends a capability request message to the UE, which contains the AI ​​positioning capability information element to instruct the UE to report the AI ​​positioning capability. Otherwise, the information element is omitted. Therefore, the LPP signaling message can be updated as follows:

[0333] Step 2: If the UE supports AI positioning, the UE reports the AI ​​positioning capability to the network side device after receiving the AI ​​positioning capability request, including reporting the AI ​​positioning capability to the LMF entity through LPP signaling (message providing capability) after receiving the request and / or reporting the AI ​​positioning capability to the base station through RRC signaling (UE capability information). The reported capability parameters are the same as option 1. Otherwise, the UE does not report the AI ​​positioning capability.

[0334] Figure 9 is a schematic structural diagram of a wireless communication device 700 provided in an embodiment of the present application. The wireless communication device can be a user equipment, a base station, or a network element. The wireless communication device 700 shown in Figure 9 includes a processor 710, which can call and execute a computer program from a memory to implement the method in the embodiment of the present application.

[0335] Optionally, as shown in FIG10 , the wireless communication device 700 may further include a memory 720. The processor 710 may call and execute a computer program from the memory 720 to implement the method in the embodiment of the present application. The memory 720 may be a separate device independent of the processor 710 or may be integrated into the processor 710.

[0336] Optionally, as shown in FIG9 , the wireless communication device 700 may further include a transceiver 730. The processor 710 may control the transceiver 730 to communicate with other devices. Specifically, the transceiver 730 may send information or data to other devices or receive information or data sent by other devices. The transceiver 730 may include a transmitter and a receiver. The transceiver 730 may further include one or more antennas.

[0337] Optionally, the wireless communication device 700 may specifically be a base station in an embodiment of the present application, and the wireless communication device 700 may implement the corresponding processes implemented by the base station in each method in the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0338] Optionally, the wireless communication device 700 may specifically be a mobile user device / user device in an embodiment of the present application, and the wireless communication device 700 may implement the corresponding processes implemented by the mobile user device / user device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0339] Optionally, the wireless communication device 700 may specifically be an LMF entity in an embodiment of the present application, and the wireless communication device 700 may implement the corresponding processes implemented by the network element in each method in the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0340] Figure 10 is a schematic structural diagram of a chip according to an embodiment of the present application. The chip 800 shown in Figure 10 includes a processor 810, which can call and run a computer program from a memory to implement the method according to the embodiment of the present application.

[0341] Optionally, as shown in FIG10 , the chip 800 may further include a memory 820. The processor 810 may call and execute computer programs from the memory 820 to implement the methods in the embodiments of the present application. The memory 820 may be a separate device independent of the processor 810 or may be integrated into the processor 810.

[0342] Optionally, the chip 800 may further include an input interface 830. The processor 910 may control the input interface 830 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0343] Optionally, the chip 800 may further include an output interface 840. The processor 810 may control the output interface 840 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0344] Optionally, the chip can be applied to the base station in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the base station in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0345] Optionally, the chip can be applied to the mobile user device / user device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the mobile user device / user device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0346] Optionally, the chip can be applied to the network element in the embodiment of the present application, and the chip can implement the corresponding processes implemented by the mobile network element in each method of the embodiment of the present application. For the sake of brevity, it will not be repeated here.

[0347] Figure 11 is a schematic block diagram of a wireless communication system 100 provided in an embodiment of the present application. As shown in Figure 11, the communication system 100 includes a user equipment 120 and a base station 110. The user equipment 120 can be used to implement the corresponding functions implemented by the user equipment in the above method, and the base station 110 can be used to implement the corresponding functions implemented by the base station in the above method. For the sake of brevity, they are not further described here.

[0348] It should be understood that the processor of the embodiment of the present application may be an integrated circuit chip with signal processing capabilities. In the implementation process, the steps of the above method embodiment can be completed by the integrated logic circuit of the hardware in the processor or the instructions in the form of software. It is understood that the memory in the embodiment of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. It should be noted that the memory of the system and method described herein is intended to include but is not limited to these and any other suitable types of memory. The embodiment of the present application also provides a computer-readable storage medium for storing a computer program.

[0349] Optionally, the computer-readable storage medium may be applied to the base station in the embodiments of the present application, and the computer program causes the computer to execute the corresponding processes implemented by the base station in the various methods in the embodiments of the present application. For the sake of brevity, no further description is given here. Optionally, the computer-readable storage medium may be applied to the mobile user equipment / user equipment in the embodiments of the present application, and the computer program causes the computer to execute the corresponding processes implemented by the mobile user equipment / user equipment in the various methods in the embodiments of the present application. For the sake of brevity, no further description is given here.

[0350] An embodiment of the present application also provides a computer program product, including computer program instructions.

[0351] Optionally, the computer program product may be applied to the base station in the embodiments of the present application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the base station in the various methods of the embodiments of the present application. For the sake of brevity, they are not described in detail here. Optionally, the computer program product may be applied to the mobile user equipment / user equipment in the embodiments of the present application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the mobile user equipment / user equipment in the various methods of the embodiments of the present application. For the sake of brevity, they are not described in detail here.

[0352] The embodiment of the present application also provides a computer program.

[0353] Optionally, the computer program may be applied to the base station in the embodiments of the present application. When the computer program is executed on a computer, the computer executes the corresponding processes implemented by the base station in the various methods of the embodiments of the present application. For the sake of brevity, no further details are given here. Optionally, the computer program may be applied to the mobile user equipment / user equipment in the embodiments of the present application. When the computer program is executed on a computer, the computer executes the corresponding processes implemented by the mobile user equipment / user equipment in the various methods of the embodiments of the present application. For the sake of brevity, no further details are given here.

[0354] 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.

[0355] 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 positioning method for a user equipment (UE) side model, executed on the UE, wherein: The positioning method includes: After the UE receives an indication sent by the positioning management function LMF entity through signaling, it provides non-artificial intelligence AI positioning information and / or AI positioning information to the LMF entity, wherein the AI ​​positioning information includes the UE location information output by the AI ​​model and / or the sending and receiving point TRP inference measurement values.

2. The positioning method according to claim 1, wherein: The positioning method also includes that after the positioning service is turned on, the UE receives a non-AI positioning information request and / or an AI positioning information request sent by the LMF entity through the signaling, wherein the non-AI positioning information request instructs the UE to obtain the position and / or obtain the measurement information required for non-AI positioning using a non-AI positioning positioning method and provide a first result to the LMF entity, and the AI ​​positioning information request instructs the UE to infer the position and / or measurement information using an AI method and provide a second result to the LMF entity.

3. The positioning method according to claim 2, wherein: The AI ​​positioning information request also indicates at least one of the following measurement quantities: line-of-sight LOS / non-line-of-sight NLOS indication hard value, LOS / NLOS indication soft value, arrival time hard value, arrival time soft value, reference signal time difference RSTD hard value, RSTD soft value, angle of departure AoD hard value, AoD soft value, positioning reference signal received power PRS RSRP hard value, PRS RSRP soft value, reference signal received multipath power PRS RSRPP hard value, PRS RSRPP soft value, UE side Rx-Tx time difference hard value or UE side Rx-Tx time difference soft value, where the hard value represents a determined value and the soft value represents a probability distribution.

4. The positioning method according to claim 1, wherein: The signaling is Long Term Evolution Positioning Protocol (LPP) signaling.

5. The positioning method according to claim 1, wherein: The UE receives first configuration information sent by the LMF entity through the signaling, where the first configuration information is related to positioning method switching. The positioning method according to claim 5 , wherein: The first configuration information includes a switching positioning method permission, and the switching positioning method permission instructs the UE to switch between non-AI positioning and AI positioning.

7. The positioning method according to claim 6, wherein: The switching conditions between non-AI positioning and AI positioning are set based on the UE.

8. The positioning method according to claim 6, wherein: When the switching positioning method permits the UE to switch between non-AI positioning and AI positioning, the UE further receives at least one of the following measurement quantities: LOS / NLOS indication hard value, LOS / NLOS indication soft value, arrival time hard value, arrival time soft value, RSTD hard value, RSTD soft value, AoD hard value, AoD soft value, PRS RSRP hard value, PRS RSRP soft value, PRS RSRPP hard value, PRS RSRPP soft value, UE side Rx-Tx time difference hard value, or UE side Rx-Tx time difference soft value.

9. The positioning method according to claim 6, wherein: The AI ​​positioning information provided by the UE includes the UE location information output by the AI ​​model and / or the sending and receiving point TRP inference measurement values ​​corresponding to the measurement amount indicated by the AI ​​positioning information request.

10. The positioning method according to claim 9 further includes the UE providing non-AI positioning information to the LMF entity through the signaling and feeding back a fallback type.

11. The positioning method according to claim 5, wherein: The first configuration information includes relevant information for switching the positioning mode, and the relevant information for switching the positioning mode instructs the UE to switch between non-AI positioning and AI positioning.

12. The positioning method according to claim 11, wherein: The information related to the switching positioning mode includes at least one of the following: a condition for switching to AI positioning, a measurement amount, a fallback condition for non-AI positioning, or a duration of the fallback condition.

13. The positioning method according to claim 12, wherein: The condition for switching AI positioning indicates that the UE switches from the non-AI positioning to the AI ​​positioning when a specified condition is met, and the switching condition includes at least one of the following: no global navigation satellite system GNSS signal, NLOS ratio, multipath number or dense multipath.

14. The positioning method according to claim 13, wherein: If the switching condition includes the absence of a GNSS signal, the switching condition instructs the UE to switch to the AI ​​positioning mode under the condition that the GNSS signal cannot be received.

15. The positioning method according to claim 13, wherein: If the switching condition includes the NLOS ratio, the switching condition indicates a threshold of the NLOS ratio, and the UE switches to the AI ​​positioning mode when the calculated NLOS ratio exceeds the threshold.

16. The positioning method according to claim 13, wherein: If the switching condition includes the multipath number, the switching condition indicates a threshold of the multipath number, and the UE switches to the AI ​​positioning mode when the calculated multipath number exceeds the threshold.

17. The positioning method according to claim 13, wherein: If the switching condition includes the dense multipath, the switching condition instructs the UE to switch to the AI ​​positioning mode under the condition that the multipath is dense.

18. The positioning method according to claim 11, wherein: The AI ​​positioning information provided by the UE includes the UE location information output by the AI ​​model and / or the sending and receiving point TRP inference measurement values ​​corresponding to the measurement amount indicated by the AI ​​positioning information request.

19. The positioning method according to claim 18 further includes the UE providing non-AI positioning information to the LMF entity through the signaling and feeding back a fallback type.

20. The positioning method according to claim 1 further includes, during the positioning service process, the UE providing UE-side auxiliary information to the LMF entity through the signaling.

21. The positioning method according to claim 20, wherein: The UE-side auxiliary information includes at least one of the following: a GNSS indicator, a multipath number, or a resolvable multipath indicator, which is used to assist the LMF entity in determining the conditions for switching AI positioning.

22. The positioning method according to claim 20, wherein: The UE receives the non-AI positioning positioning information request or the AI ​​positioning information request sent by the LMF entity according to the UE-side auxiliary information.

23. The positioning method according to claim 22, wherein: The UE reports the result of non-AI positioning. According to the UE-side auxiliary information, if the switching condition is met, the UE receives the positioning information request for the AI ​​positioning sent by the LMF entity through the signaling. The positioning information request for AI positioning instructs the UE to switch to AI positioning and report the result output by the AI ​​model.

24. The positioning method according to claim 22, wherein: The UE reports the result of AI positioning. According to the UE-side auxiliary information, if the fallback condition is met, the UE receives the non-AI positioning information request sent by the LMF entity through the signaling, and the non-AI positioning information request instructs the UE to fall back to the non-AI positioning positioning method and report the output result.

25. The positioning method according to claim 1 further includes, during the positioning service process, the UE receives second configuration information sent by the LMF entity through the signaling, and the second configuration information is used to instruct the UE to switch between the first mechanism and the second mechanism. The first mechanism refers to the non-AI positioning positioning method and the AI ​​positioning method not running at the same time, and the second mechanism refers to the non-AI positioning positioning method and the AI ​​positioning method running at the same time.

26. The positioning method according to claim 25, wherein: The second configuration information includes a switching indication of a positioning operation mechanism, which is used to indicate whether the UE is allowed to switch between the first mechanism and the second mechanism.

27. The positioning method according to claim 26, wherein: The switching condition of the positioning operation mechanism is based on the autonomous setting of the UE.

28. The positioning method according to claim 26 further includes the UE feeding back the current positioning operation mechanism to the LMF entity through the signaling.

29. The positioning method according to claim 25, wherein: The second configuration information includes an indication of a positioning operation mechanism, where the indication of the positioning operation mechanism is used to indicate whether the first mechanism or the second mechanism is adopted.

30. A positioning method for a base station side model, executed at a base station, wherein: The positioning method includes: After the positioning service is turned on, the base station receives a measurement request sent by the positioning management function LMF entity through signaling, wherein the measurement request instructs the base station to obtain measurement information and provide measurement results to the LMF entity, and the measurement request also indicates the sending and receiving point TRP measurement amounts and the measurement method corresponding to the TRP measurement amounts; The base station initiates a measurement response or a measurement report to the LMF entity through the signaling, wherein the content of the measurement response or the measurement report includes the TRP measurement value corresponding to the measurement quantity and / or the measurement method used to obtain the measurement value.

31. The positioning method according to claim 30, wherein: The TRP measurement quantity includes at least one of the following: a hard value of the Rx-Tx time difference between reception and transmission on the base station side, a hard value of the reference signal received power RSRP, a hard value of the relative arrival time RTOA, a hard value of the angle of arrival AoA, multiple hard values ​​of AoA, a hard value of the reference signal received multipath power RSRPP, a hard value of the line-of-sight LOS / non-line-of-sight NLOS indication, a soft value of the LOS / NLOS indication, a soft value of the Rx-Tx time difference on the base station side, a soft value of RSRP, a soft value of RTOA, a soft value of AoA, multiple soft values ​​of AoA or a soft value of RSRPP, wherein the hard value represents a determined value and the soft value represents a probability distribution.

32. The positioning method according to claim 30, wherein: The measurement method includes a non-AI positioning method and / or an AI positioning method.

33. The positioning method according to claim 30, wherein: The signaling is NR Positioning Protocol A NRPPa signaling.

34. The positioning method according to claim 30, wherein: The base station receives the third configuration information sent by the LMF entity through the signaling, and the third configuration information is related to the switching of the positioning method.

35. The positioning method according to claim 34, wherein: The third configuration information includes a switching positioning method permission, and the switching positioning method permission instructs the base station to switch between a non-AI positioning method and an AI positioning method.

36. The positioning method according to claim 35, wherein: The switching conditions between the non-AI positioning mode and the AI ​​positioning mode are set autonomously by the base station.

37. The positioning method according to claim 36, wherein: When the switching positioning method permits the base station to switch between a non-AI positioning positioning mode and an AI positioning mode, it also indicates at least one of the following TRP inference quantities: a base station side Rx-Tx time difference hard value, an RSRP hard value, an RTOA hard value, an AoA hard value, multiple AoA hard values, an RSRPP hard value, a LOS / NLOS indication hard value, a LOS / NLOS indication soft value, a base station side Rx-Tx time difference soft value, an RSRP soft value, an RTOA soft value, an AoA soft value, multiple AoA soft values ​​or an RSRPP soft value, wherein the hard value represents a determined value and the soft value represents a probability distribution.

38. The positioning method according to claim 35, further comprising the base station initiating a response or reporting of the inference measurement value to the LMF entity through the signaling, wherein: The inference measurements include TRP measurements output by the model.

39. The positioning method according to claim 38 further includes the base station reporting the non-AI positioning measurement value to the LMF entity through the signaling and feeding back the fallback type.

40. The positioning method according to claim 34, wherein: The third configuration information includes relevant information for switching the positioning mode, and the relevant information for switching the positioning mode instructs the base station to switch between the non-AI positioning mode and the AI ​​positioning mode.

41. The positioning method according to claim 40, wherein: The relevant information of switching the positioning mode includes at least one of the following: a condition for switching AI positioning, a TRP inference amount, a fallback condition for non-AI positioning, or a duration of the fallback condition.

42. The positioning method according to claim 41, wherein: The condition for switching AI positioning indicates that the base station switches from the non-AI positioning mode to the AI ​​positioning mode when a specified condition is met, and the switching condition includes at least one of the following: NLOS environment, multipath number or dense multipath.

43. The positioning method according to claim 42, wherein: If the switching condition includes the NLOS environment, the switching condition instructs the base station to switch to the AI ​​positioning mode under the condition of the NLOS environment.

44. The positioning method according to claim 42, wherein: If the switching condition includes the multipath number, the switching condition indicates a threshold of the multipath number and instructs the base station to switch to the AI ​​positioning mode when the calculated multipath number exceeds the threshold.

45. The positioning method according to claim 42, wherein: If the switching condition includes the dense multipath, the switching condition instructs the base station to switch to the AI ​​positioning mode under the condition that the multipath is dense.

46. ​​The positioning method according to claim 40, further comprising the base station initiating a response or reporting of the inference measurement value to the LMF entity through the signaling, wherein: The inference measurements include TRP measurements output by the model.

47. The positioning method according to claim 46 further includes the base station reporting the non-AI positioning measurement value to the LMF entity through the signaling and feeding back the fallback type.

48. The positioning method according to claim 30 further includes, during the positioning service process, the base station providing base station side auxiliary information to the LMF entity through the signaling.

49. The positioning method according to claim 48, wherein: The base station side auxiliary information includes the number of multipaths and / or a resolvable multipath indicator, which is used to assist the LMF entity in determining the conditions for switching AI positioning.

50. The positioning method according to claim 49, wherein: The base station receives the non-AI positioning measurement request or the AI ​​positioning measurement request sent by the LMF entity through the signaling.

51. The positioning method according to claim 30 further includes, during the positioning service process, the base station receives the fourth configuration information sent by the LMF entity through the signaling, and the fourth configuration information is used to instruct the base station to switch between the first mechanism and the second mechanism, the first mechanism means that non-AI positioning and AI positioning are not running at the same time, and the second mechanism means that the non-AI positioning and the AI ​​positioning are running at the same time.

52. The positioning method according to claim 51, wherein: The fourth configuration information includes a switching indication of a positioning operation mechanism, which is used to indicate whether the base station is allowed to switch between the first mechanism and the second mechanism.

53. The positioning method according to claim 52, wherein: The switching condition of the positioning operation mechanism is based on the autonomous setting of the base station.

54. The positioning method according to claim 52 further includes the base station feeding back the current positioning operation mechanism to the LMF entity through the signaling.

55. The positioning method according to claim 51, wherein: The fourth configuration information includes an indication of a positioning operation mechanism, where the indication of the positioning operation mechanism is used to indicate whether the first mechanism or the second mechanism is adopted.

56. A method for reporting monitoring data related to positioning of a user equipment (UE) side model, executed on the UE, wherein: The positioning-related monitoring data reporting method includes: When the monitoring indicator solution is performed in the UE and the model monitoring is performed in the location management function LMF entity, the UE reports the monitoring indicator solution result to the LMF entity through signaling.

57. The method for reporting positioning-related monitoring data according to claim 56, wherein: The signaling is Long Term Evolution Positioning Protocol (LPP) signaling.

58. The method for reporting positioning-related monitoring data according to claim 56, wherein: The monitoring indicator solution result is carried in a message providing the monitoring indicator solution result or in a message providing positioning information.

59. The method for reporting positioning-related monitoring data according to claim 56, wherein: For each model or model group involved in monitoring, the monitoring indicator solution includes at least one of the following: position error, velocity / acceleration error, measurement value error, position output standard deviation / variance, measurement value standard deviation / variance, or a model identifier ID list.

60. The method for reporting positioning-related monitoring data according to claim 59, wherein: The measurement value error includes at least one of the following: an arrival time error, a reference signal time difference (RSTD) error, an angle of departure (AoD) error, or an F1-score of a LOS / NLOS indication.

61. The method for reporting positioning-related monitoring data according to claim 59, wherein: The measurement value standard deviation / variance includes at least one of the following: arrival time standard deviation / variance, RSTD standard deviation / variance, or AoD standard deviation / variance.

62. A method for reporting monitoring data related to positioning of a base station side model, executed at a base station, wherein: The positioning-related monitoring data reporting method includes: When the monitoring indicator solution is performed in the base station and the model monitoring is performed in the positioning management function LMF entity, the base station reports the monitoring indicator solution result to the LMF entity through signaling.

63. The method for reporting positioning-related monitoring data according to claim 62, wherein: The signaling is NR Positioning Protocol A NRPPa signaling.

64. The method for reporting positioning-related monitoring data according to claim 62, wherein: The monitoring indicator solution result is carried in a monitoring indicator solution report message or a measurement report message.

65. The method for reporting positioning-related monitoring data according to claim 62, wherein: For each model or model group involved in monitoring, the monitoring indicator solution includes a measurement error and / or a measurement standard deviation / variance.

66. The method for reporting positioning-related monitoring data according to claim 65, wherein: The measurement value error includes at least one of the following: a relative time of arrival (RTOA) error, an angle of arrival (AoA) error, or an F1-score of a LOS / NLOS indication.

67. The method for reporting positioning-related monitoring data according to claim 65, wherein: The measurement value standard deviation / variance includes the relative time of arrival RTOA standard deviation / variance and / or the angle of arrival AoA standard deviation / variance.

68. A positioning-related model transfer method for a user equipment (UE) side model, executed on the UE, wherein: The positioning-related model transfer method includes: The UE receives a model transfer trigger condition configured by the positioning management function LMF entity through signaling, wherein the model transfer trigger condition instructs the UE to initiate a model transfer request when a specified condition is met; After the UE determines through model monitoring that the model transfer trigger condition is met, the UE requests model transfer from the LMF entity through the signaling.

69. The positioning-related model transfer method according to claim 68, wherein: The signaling is Long Term Evolution Positioning Protocol (LPP) signaling.

70. The positioning-related model transfer method according to claim 68, wherein: The model transfer triggering condition includes at least one of the following: maximum position error, maximum measurement value error, maximum coefficient of variation CV, maximum distance between the current estimated position and the previous position, or maximum difference between the current measurement value and the previous measurement value.

71. The positioning-related model transfer method according to claim 70, wherein: The maximum measurement value error includes at least one of the following: a maximum arrival time error, a maximum reference signal time difference (RSTD) error, or a maximum angle of departure (AoD) error.

72. The positioning-related model transfer method according to claim 70, wherein: The maximum difference between the current measurement value and the previous measurement value includes at least one of the following: a maximum difference between a current arrival time and a previous arrival time, a maximum difference between a current RSTD and a previous RSTD, or a maximum difference between a current AoD and a previous AoD.

73. The positioning-related model transfer method according to claim 68, wherein: The parameters provided in the model transfer request include at least one of the following: monitoring indicator solution results, model architecture, model flexibility, model type, area type or positioning method.

74. The positioning-related model transfer method according to claim 73, wherein: The monitoring indicator solution result includes at least one of the following: position error, arrival time error, RSTD error, AoD error, position coefficient of variation, arrival time coefficient of variation, RSTD coefficient of variation, AoD coefficient of variation, difference between the current output position and the previous position, difference between the current output arrival time and the previous arrival time, difference between the current output RSTD and the previous RSTD, or difference between the current output AoD and the previous AoD.

75. A positioning-related model transfer method for a base station side model, executed at a base station, wherein: The positioning-related model transfer method includes: The base station receives a model transfer trigger condition configured by the positioning management function LMF entity through signaling, wherein the model transfer trigger condition instructs the base station to initiate a model transfer request when a specified condition is met; After the base station determines through model monitoring that the model transfer trigger condition is met, the base station requests model transfer to the LMF entity through the signaling.

76. The positioning-related model transfer method according to claim 75, wherein: The signaling is NR Positioning Protocol A NRPPa signaling.

77. The positioning-related model transfer method according to claim 75, wherein: The model transfer triggering condition includes at least one of the following: a maximum measurement value error, a maximum coefficient of variation CV, or a maximum difference between a current measurement value and a previous measurement value.

78. The positioning-related model transfer method according to claim 77, wherein: The maximum measurement value error includes a maximum relative time of arrival RTOA error and / or a maximum angle of arrival AoA error.

79. The positioning-related model transfer method according to claim 77, wherein: The maximum difference between the current measurement value and the previous measurement value includes the maximum difference between the current RTOA and the previous RTOA and / or the maximum difference between the current AoA and the previous AoA.

80. The positioning-related model transfer method according to claim 75, wherein: The parameters provided during the model transfer request include at least one of the following: monitoring indicator solution results, LMF entity measurement identifier ID, radio access network RAN ​​measurement ID, model architecture, model type, area type or positioning method.

81. The positioning-related model transfer method according to claim 80, wherein: The monitoring indicator solution result includes at least one of the following: RTOA error, AoA error, RTOA coefficient of variation, AoA coefficient of variation, the difference between the current output RTOA and the previous RTOA, or the difference between the current output AoA and the previous AoA.

82. A UE positioning capability assistance method for a user equipment (UE) side model, executed on the UE, wherein: The UE positioning capability assistance method includes: The UE reports the AI ​​positioning capability to the network side device through signaling, wherein the AI ​​positioning capability is used to assist the network side device in selecting a model.

83. The UE positioning capability assistance method according to claim 82, wherein: The AI ​​positioning capability includes at least one of the following: supported positioning modes, support for artificial intelligence (AI) positioning, support for simultaneous activation of AI positioning and non-AI positioning, supported model input types, support for sampling point filtering, maximum number of filtered sampling points, maximum number of loaded models, maximum number of activated models, or maximum number of simultaneously monitored models.

84. The UE positioning capability assistance method according to claim 82, wherein: The UE sends a capability provision message to the LMF entity, where the capability provision message includes an information element providing AI positioning capability, and the AI ​​positioning capability is carried in the information element.

85. The UE positioning capability assistance method according to claim 82 further includes the UE receiving an AI positioning capability request sent by the network side device through the signaling.

86. The UE positioning capability assistance method according to claim 85, wherein: The UE receiving the AI ​​positioning capability request sent by the network side device through the signaling includes the UE receiving the AI ​​positioning capability request sent by the positioning management function LMF entity through the long term evolution positioning protocol LPP signaling.

87. The UE positioning capability assistance method according to claim 85, wherein: The UE receiving the AI ​​positioning capability request sent by the network side device through the signaling includes the UE receiving the AI ​​positioning capability request sent by the base station through radio resource control RRC signaling.

88. The UE positioning capability assistance method according to claim 85, wherein: The UE receives a capability request message sent by the positioning management function LMF entity, where the capability request message includes an information element requesting AI positioning capability, which is used to instruct the UE to report the AI ​​positioning capability.

89. The UE positioning capability assistance method according to claim 85, wherein: After receiving the AI ​​positioning capability request, the UE reports the AI ​​positioning capability to the network side device through the signaling.

90. The UE positioning capability assistance method according to claim 85, wherein: The network side equipment includes a base station and / or a positioning management function LMF entity.

91. A positioning method for a user equipment UE side model, executed in a location management function LMF entity, wherein: The positioning method includes: After the LMF entity sends an indication to the UE through signaling, it receives non-artificial intelligence AI positioning information and / or AI positioning information provided by the UE, wherein the AI ​​positioning information includes the UE location information output by the AI ​​model and / or the sending and receiving point TRP inference measurement values.

92. The positioning method according to claim 91, wherein: The positioning method also includes that after the positioning service is turned on, the LMF entity sends a non-AI positioning information request and / or an AI positioning information request to the UE through the signaling, wherein the non-AI positioning information request instructs the UE to obtain the position and / or obtain the measurement information required for non-AI positioning using a non-AI positioning positioning method and receive a first result provided by the UE, and the AI ​​positioning information request instructs the UE to infer the position and / or measurement information using an AI method and receive a second result provided by the UE.

93. The positioning method according to claim 92, wherein: The AI ​​positioning information request also indicates at least one of the following measurement quantities: line-of-sight LOS / non-line-of-sight NLOS indication hard value, LOS / NLOS indication soft value, arrival time hard value, arrival time soft value, reference signal time difference RSTD hard value, RSTD soft value, angle of departure AoD hard value, AoD soft value, positioning reference signal received power PRS RSRP hard value, PRS RSRP soft value, reference signal received multipath power PRS RSRPP hard value, PRS RSRPP soft value, UE side Rx-Tx time difference hard value or UE side Rx-Tx time difference soft value, where the hard value represents a determined value and the soft value represents a probability distribution.

94. The positioning method according to claim 91, wherein: The signaling is Long Term Evolution Positioning Protocol (LPP) signaling.

95. The positioning method according to claim 91, wherein: The LMF entity sends first configuration information to the UE through the signaling, where the first configuration information is related to the positioning method switching.

96. The positioning method according to claim 95, wherein: The first configuration information includes a switching positioning method permission, where the switching positioning method permission indicates switching between non-AI positioning and AI positioning.

97. The positioning method according to claim 96, wherein: The switching conditions between non-AI positioning and AI positioning are set based on the UE.

98. The positioning method according to claim 96, wherein: When the switching positioning method permits switching between non-AI positioning and AI positioning, the LMF entity also sends at least one of the following measurement quantities to the UE: LOS / NLOS indication hard value, LOS / NLOS indication soft value, arrival time hard value, arrival time soft value, RSTD hard value, RSTD soft value, AoD hard value, AoD soft value, PRS RSRP hard value, PRS RSRP soft value, PRS RSRPP hard value, PRS RSRPP soft value, UE side Rx-Tx time difference hard value or UE side Rx-Tx time difference soft value.

99. The positioning method according to claim 96, wherein: The AI ​​positioning information provided by the UE includes the UE location information output by the AI ​​model and / or the sending and receiving point TRP inference measurement values ​​corresponding to the measurement amount indicated by the AI ​​positioning information request.

100. The positioning method according to claim 99 further includes the LMF entity receiving non-AI positioning information and feedback fallback type provided by the UE through the signaling.

101. The positioning method according to claim 95, wherein: The first configuration information includes relevant information for switching the positioning mode, and the relevant information for switching the positioning mode indicates switching between non-AI positioning and AI positioning.

102. The positioning method according to claim 101, wherein: The information related to the switching positioning mode includes at least one of the following: a condition for switching to AI positioning, a measurement amount, a fallback condition for non-AI positioning, or a duration of the fallback condition.

103. The positioning method according to claim 102, wherein: The condition for switching AI positioning indicates that the UE switches from the non-AI positioning to the AI ​​positioning when a specified condition is met, and the switching condition includes at least one of the following: no global navigation satellite system GNSS signal, NLOS ratio, multipath number or dense multipath.

104. The positioning method according to claim 103, wherein: If the switching condition includes the absence of a GNSS signal, the switching condition indicates switching to the AI ​​positioning mode under the condition that a GNSS signal cannot be received.

105. The positioning method according to claim 103, wherein: If the switching condition includes the NLOS ratio, the switching condition indicates a threshold of the NLOS ratio, and the system switches to the AI ​​positioning mode when the NLOS ratio exceeds the threshold.

106. The positioning method according to claim 103, wherein: If the switching condition includes the multipath number, the switching condition indicates a threshold of the multipath number, and the system switches to the AI ​​positioning mode when the multipath number exceeds the threshold.

107. The positioning method according to claim 103, wherein: If the switching condition includes the dense multipath, the switching condition indicates switching to the AI ​​positioning mode under the condition that the multipath is dense.

108. The positioning method according to claim 101, wherein: The AI ​​positioning information provided by the UE includes the UE location information output by the AI ​​model and / or the sending and receiving point TRP inference measurement values ​​corresponding to the measurement amount indicated by the AI ​​positioning information request.

109. The positioning method according to claim 108 further includes the LMF entity receiving non-AI positioning information and feedback fallback type provided by the UE through the signaling.

110. The positioning method according to claim 91 also includes, during the positioning service process, the LMF entity receiving UE-side auxiliary information provided by the UE through the signaling.

111. The positioning method according to claim 110, wherein: The UE-side auxiliary information includes at least one of the following: a GNSS indicator, a multipath number, or a resolvable multipath indicator, which is used to assist the LMF entity in determining the conditions for switching AI positioning.

112. The positioning method according to claim 110, wherein: The LMF entity sends the non-AI positioning positioning information request or the AI ​​positioning information request to the UE according to the UE-side auxiliary information.

113. The positioning method according to claim 112, wherein: The LMF entity receives the non-AI positioning result reported by the UE. According to the UE-side auxiliary information, if the switching condition is met, the LMF entity sends the AI ​​positioning positioning information request to the UE through the signaling. The AI ​​positioning positioning information request indicates switching to AI positioning and reports the result output by the AI ​​model.

114. The positioning method according to claim 112, wherein: The LMF entity receives the AI ​​positioning result reported by the UE. According to the UE-side auxiliary information, if the fallback condition is met, the LMF entity sends the non-AI positioning information request to the UE through the signaling, and the non-AI positioning information request indicates the positioning method of falling back to non-AI positioning, and reports the output result.

115. The positioning method according to claim 91 further includes, during the positioning service process, the LMF entity sending second configuration information to the UE through the signaling, the second configuration information being used to indicate the switching between the first mechanism and the second mechanism, the first mechanism being that the non-AI positioning positioning method and the AI ​​positioning method are not running at the same time, and the second mechanism being that the non-AI positioning positioning method and the AI ​​positioning method are running at the same time.

116. The positioning method according to claim 115, wherein: The second configuration information includes a switching indication of a positioning operation mechanism, which is used to indicate whether the UE is allowed to switch between the first mechanism and the second mechanism.

117. The positioning method according to claim 116, wherein: The switching condition of the positioning operation mechanism is based on the autonomous setting of the UE.

118. The positioning method according to claim 116 also includes the LMF entity receiving the current positioning operation mechanism fed back by the UE through the signaling.

119. The positioning method according to claim 115, wherein: The second configuration information includes an indication of a positioning operation mechanism, where the indication of the positioning operation mechanism is used to indicate whether the first mechanism or the second mechanism is adopted.

120. A positioning method for a base station side model, executed in a positioning management function LMF entity, wherein: The positioning method includes: after the positioning service is turned on, the LMF entity sends a measurement request to the base station through signaling, wherein the measurement request instructs the base station to obtain measurement information and provide the measurement result to the LMF entity, and the measurement request further indicates the sending and receiving point TRP measurement quantities and the measurement method corresponding to the TRP measurement quantities; The LMF entity receives the measurement response or measurement report provided by the base station through the signaling, wherein the content of the measurement response or the measurement report includes the TRP measurement value corresponding to the measurement quantity and / or the measurement method used to obtain the measurement value.

121. The positioning method according to claim 120, wherein: The TRP measurement quantity includes at least one of the following: a hard value of the Rx-Tx time difference between reception and transmission on the base station side, a hard value of the reference signal received power RSRP, a hard value of the relative arrival time RTOA, a hard value of the angle of arrival AoA, multiple hard values ​​of AoA, a hard value of the reference signal received multipath power RSRPP, a hard value of the line-of-sight LOS / non-line-of-sight NLOS indication, a soft value of the LOS / NLOS indication, a soft value of the Rx-Tx time difference on the base station side, a soft value of RSRP, a soft value of RTOA, a soft value of AoA, multiple soft values ​​of AoA or a soft value of RSRPP, wherein the hard value represents a determined value and the soft value represents a probability distribution.

122. The positioning method according to claim 120, wherein: The measurement method includes a non-AI positioning method and / or an AI positioning method.

123. The positioning method according to claim 120, wherein: The signaling is NR Positioning Protocol A NRPPa signaling.

124. The positioning method according to claim 120, wherein: The LMF entity sends third configuration information to the base station through the signaling, where the third configuration information is related to the switching of the positioning method.

125. The positioning method according to claim 124, wherein: The third configuration information includes a switching positioning method permission, and the switching positioning method permission instructs the base station to switch between a non-AI positioning method and an AI positioning method.

126. The positioning method according to claim 125, wherein: The switching conditions between the non-AI positioning mode and the AI ​​positioning mode are set autonomously by the base station.

127. The positioning method according to claim 126, wherein: When the switching positioning method permits the switching between the positioning mode of non-AI positioning and the AI ​​positioning mode, it also indicates at least one of the following TRP inference quantities: base station side Rx-Tx time difference hard value, RSRP hard value, RTOA hard value, AoA hard value, multiple AoA hard values, RSRPP hard value, LOS / NLOS indication hard value, LOS / NLOS indication soft value, base station side Rx-Tx time difference soft value, RSRP soft value, RTOA soft value, AoA soft value, multiple AoA soft values ​​or RSRPP soft value, wherein the hard value represents a determined value and the soft value represents a probability distribution.

128. The positioning method according to claim 125, further comprising the LMF entity receiving a response or report of the inference measurement value initiated by the base station through the signaling, wherein: The inference measurements include TRP measurements output by the model.

129. The positioning method according to claim 128 further includes the LMF entity receiving the non-AI positioning measurement value and feedback fallback type reported by the base station through the signaling.

130. The positioning method according to claim 124, wherein: The third configuration information includes relevant information for switching the positioning mode, and the relevant information for switching the positioning mode indicates switching between the non-AI positioning mode and the AI ​​positioning mode.

131. The positioning method according to claim 130, wherein: The relevant information of switching the positioning mode includes at least one of the following: a condition for switching AI positioning, a TRP inference amount, a fallback condition for non-AI positioning, or a duration of the fallback condition.

132. The positioning method according to claim 131, wherein: The condition for switching AI positioning indicates switching from the non-AI positioning mode to the AI ​​positioning mode when a specified condition is met, and the switching condition includes at least one of the following: NLOS environment, multipath number, or dense multipath.

133. The positioning method according to claim 132, wherein: If the switching condition includes the NLOS environment, the switching condition indicates switching to the AI ​​positioning mode under the condition of the NLOS environment.

134. The positioning method according to claim 132, wherein: If the switching condition includes the multipath number, the switching condition indicates a threshold of the multipath number and indicates switching to the AI ​​positioning mode when the multipath number exceeds the threshold.

135. The positioning method according to claim 132, wherein: If the switching condition includes the dense multipath, the switching condition instructs the base station to switch to the AI ​​positioning mode under the condition that the multipath is dense.

136. The positioning method according to claim 130, further comprising the LMF entity receiving a response or report of the inference measurement value initiated by the base station through the signaling, wherein: The inference measurements include TRP measurements output by the model.

137. The positioning method according to claim 136 also includes the LMF entity receiving the non-AI positioning measurement value reported by the base station through the signaling, and feeding back the fallback type.

138. The positioning method according to claim 120 also includes, during the positioning service process, the LMF entity receiving the base station side auxiliary information provided by the base station through the signaling.

139. The positioning method according to claim 138, wherein: The base station side auxiliary information includes the number of multipaths and / or a resolvable multipath indicator, which is used to assist the LMF entity in determining the conditions for switching AI positioning.

140. The positioning method according to claim 139, wherein: The LMF entity sends the non-AI positioning measurement request or the AI ​​positioning measurement request to the base station through the signaling.

141. The positioning method according to claim 120 further includes, during the positioning service process, the LMF entity sending fourth configuration information to the base station through the signaling, and the fourth configuration information is used to instruct the base station to switch between the first mechanism and the second mechanism, the first mechanism means that non-AI positioning and AI positioning are not running at the same time, and the second mechanism means that the non-AI positioning and the AI ​​positioning are running at the same time.

142. The positioning method according to claim 141, wherein: The fourth configuration information includes a switching indication of a positioning operation mechanism, which is used to indicate whether the base station is allowed to switch between the first mechanism and the second mechanism.

143. The positioning method according to claim 142, wherein: The switching condition of the positioning operation mechanism is based on the autonomous setting of the base station.

144. The positioning method according to claim 142 also includes the LMF entity receiving the current positioning operation mechanism fed back by the base station through the signaling.

145. The positioning method according to claim 144, wherein: The fourth configuration information includes an indication of a positioning operation mechanism, where the indication of the positioning operation mechanism is used to indicate whether the first mechanism or the second mechanism is adopted.

146. A method for reporting monitoring data related to positioning of a user equipment UE side model, executed in a positioning management function LMF entity, wherein: The positioning-related monitoring data reporting method includes: When the monitoring indicator solution is performed in the UE and the model monitoring is performed in the LMF entity, the LMF entity receives the monitoring indicator solution result reported by the UE through the signaling.

147. The method for reporting positioning-related monitoring data according to claim 146, wherein: The signaling is Long Term Evolution Positioning Protocol (LPP) signaling.

148. The method for reporting positioning-related monitoring data according to claim 146, wherein: The monitoring indicator solution result is carried in a message providing the monitoring indicator solution result or in a message providing positioning information.

149. The method for reporting positioning-related monitoring data according to claim 146, wherein: For each model or model group involved in monitoring, the monitoring indicator solution includes at least one of the following: position error, velocity / acceleration error, measurement value error, position output standard deviation / variance, measurement value standard deviation / variance or model identifier ID list.

150. The method for reporting positioning-related monitoring data according to claim 149, wherein: The measurement value error includes at least one of the following: an arrival time error, a reference signal time difference (RSTD) error, an angle of departure (AoD) error, or an F1-score of a LOS / NLOS indication.

151. The method for reporting positioning-related monitoring data according to claim 149, wherein: The measurement value standard deviation / variance includes at least one of the following: arrival time standard deviation / variance, RSTD standard deviation / variance, or AoD standard deviation / variance.

152. A method for reporting monitoring data related to positioning of a base station side model, executed in a positioning management function LMF entity, wherein: The positioning-related monitoring data reporting method includes: When the monitoring indicator solution is performed in the base station and the model monitoring is performed in the LMF entity, the LMF entity receives the monitoring indicator solution result reported by the base station through the signaling.

153. The method for reporting positioning-related monitoring data according to claim 152, wherein: The signaling is NR Positioning Protocol A NRPPa signaling.

154. The method for reporting positioning-related monitoring data according to claim 152, wherein: The monitoring indicator solution result is carried in a monitoring indicator solution report message or a measurement report message.

155. The method for reporting positioning-related monitoring data according to claim 152, wherein: For each model or model group involved in monitoring, the monitoring indicator solution includes a measurement error and / or a measurement standard deviation / variance.

156. The method for reporting positioning-related monitoring data according to claim 155, wherein: The measurement value error includes at least one of the following: a relative time of arrival (RTOA) error, an angle of arrival (AoA) error, or an F1-score of a LOS / NLOS indication.

157. The method for reporting positioning-related monitoring data according to claim 155, wherein: The measurement value standard deviation / variance includes the relative time of arrival RTOA standard deviation / variance and / or the angle of arrival AoA standard deviation / variance.

158. A positioning-related model transfer method for a user equipment UE side model, executed in a location management function LMF entity, wherein: The positioning-related model transfer method includes: The LMF entity configures a model transfer trigger condition to the UE through signaling, wherein the model transfer trigger condition instructs the UE to initiate a model transfer request when a specified condition is met; After the UE determines through model monitoring that the model transfer trigger condition is met, the LMF entity receives the UE's request for model transfer through the signaling.

159. The positioning-related model transfer method according to claim 158, wherein: The signaling is Long Term Evolution Positioning Protocol (LPP) signaling.

160. The positioning-related model transfer method according to claim 158, wherein: The model transfer triggering condition includes at least one of the following: maximum position error, maximum measurement value error, maximum coefficient of variation CV, maximum distance between the current estimated position and the previous position, or maximum difference between the current measurement value and the previous measurement value.

161. The positioning-related model transfer method according to claim 160, wherein: The maximum measurement value error includes at least one of the following: a maximum arrival time error, a maximum reference signal time difference (RSTD) error, or a maximum angle of departure (AoD) error.

162. The positioning-related model transfer method according to claim 160, wherein: The maximum difference between the current measurement value and the previous measurement value includes at least one of the following: a maximum difference between a current arrival time and a previous arrival time, a maximum difference between a current RSTD and a previous RSTD, or a maximum difference between a current AoD and a previous AoD.

163. The positioning-related model transfer method according to claim 158, wherein: The parameters provided in the model transfer request include at least one of the following: monitoring indicator solution results, model architecture, model flexibility, model type, area type or positioning method.

164. The positioning-related model transfer method according to claim 163, wherein: The monitoring indicator solution result includes at least one of the following: position error, arrival time error, RSTD error, AoD error, position coefficient of variation, arrival time coefficient of variation, RSTD coefficient of variation, AoD coefficient of variation, difference between the current output position and the previous position, difference between the current output arrival time and the previous arrival time, difference between the current output RSTD and the previous RSTD, or difference between the current output AoD and the previous AoD.

165. A positioning-related model transfer method for a base station side model, executed in a location management function LMF entity, wherein: The positioning-related model transfer method includes: The LMF entity configures a model transfer trigger condition to the base station through signaling, wherein the model transfer trigger condition instructs the base station to initiate a model transfer request when a specified condition is met; After the base station determines through model monitoring that the model transfer triggering condition is met, the LMF entity receives the base station's request for model transfer through the signaling.

166. The positioning-related model transfer method according to claim 165, wherein: The signaling is NR Positioning Protocol A NRPPa signaling.

167. The positioning-related model transfer method according to claim 165, wherein: The model transfer triggering condition includes at least one of the following: a maximum measurement value error, a maximum coefficient of variation CV, or a maximum difference between a current measurement value and a previous measurement value.

168. The positioning-related model transfer method according to claim 167, wherein: The maximum measurement value error includes a maximum relative time of arrival RTOA error and / or a maximum angle of arrival AoA error.

169. The positioning-related model transfer method according to claim 167, wherein: The maximum difference between the current measurement value and the previous measurement value includes the maximum difference between the current RTOA and the previous RTOA and / or the maximum difference between the current AoA and the previous AoA.

170. The positioning-related model transfer method according to claim 165, wherein: The parameters provided during the model transfer request include at least one of the following: monitoring indicator solution results, LMF entity measurement identifier ID, radio access network RAN ​​measurement ID, model architecture, model type, area type or positioning method.

171. The positioning-related model transfer method according to claim 170, wherein: The monitoring indicator solution result includes at least one of the following: RTOA error, AoA error, RTOA coefficient of variation, AoA coefficient of variation, the difference between the current output RTOA and the previous RTOA, or the difference between the current output AoA and the previous AoA.

172. A UE positioning capability assistance method for a user equipment (UE) side model, executed on a network side device, wherein: The UE positioning capability assistance method includes: The network side device receives the AI ​​positioning capability reported by the UE through signaling, wherein the AI ​​positioning capability is used to assist the network side device in selecting a model.

173. The UE positioning capability assistance method according to claim 172, wherein: The AI ​​positioning capability includes at least one of the following: supported positioning modes, support for artificial intelligence AI positioning, support for simultaneous activation of AI positioning and non-AI positioning, supported model input types, support for sampling point filtering, maximum number of filtered sampling points, maximum number of loaded models, maximum number of activated models or maximum number of simultaneously monitored models.

174. The UE positioning capability assistance method according to claim 172, wherein: The positioning management function LMF entity receives the capability provision message sent by the UE, where the capability provision message includes an information element providing AI positioning capability, and the AI ​​positioning capability is carried in the information element.

175. The UE positioning capability assistance method according to claim 172 further includes the network side device sending an AI positioning capability request to the UE through the signaling.

176. The UE positioning capability assistance method according to claim 175, wherein: The network side device sending the AI ​​positioning capability request to the UE through the signaling includes the LMF entity sending the AI ​​positioning capability request to the UE through Long Term Evolution Positioning Protocol LPP signaling.

177. The UE positioning capability assistance method according to claim 175, wherein: The network-side device sending the AI ​​positioning capability request to the UE through the signaling includes a base station sending the AI ​​positioning capability request to the UE through radio resource control RRC signaling.

178. The UE positioning capability assistance method according to claim 175, wherein: The LMF entity sends a capability request message to the UE through the signaling, where the capability request message includes an information element requesting AI positioning capability, which is used to instruct reporting of the AI ​​positioning capability.

179. The UE positioning capability assistance method according to claim 175, wherein: After the network-side device sends the AI ​​positioning capability request to the UE, the network-side device receives the AI ​​positioning capability reported by the UE through the signaling.

180. The UE positioning capability assistance method according to claim 175, wherein: The network side equipment includes a base station and / or a positioning management function LMF entity.

181. A user equipment UE, comprising: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the positioning method as described in any one of claims 1 to 29, the positioning-related monitoring data reporting method as described in any one of claims 56 to 61, the positioning-related model transfer method as described in any one of claims 68 to 74, or the UE positioning capability assistance method as described in any one of claims 82 to 90.

182. A base station comprising: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the positioning method as described in any one of claims 30 to 55, the positioning-related monitoring data reporting method as described in any one of claims 62 to 67, the positioning-related model transfer method as described in any one of claims 75 to 81, or the UE positioning capability assistance method as described in any one of claims 172 to 180.

183. A location management function LMF entity, comprising: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the positioning method as described in any one of claims 91 to 145, the positioning-related monitoring data reporting method as described in any one of claims 146 to 157, the positioning-related model transfer method as described in any one of claims 158 to 171, or the UE positioning capability assistance method as described in any one of claims 172 to 180.

184. A wireless communication device comprising: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the positioning method according to any one of claims 1 to 55 or claims 91 to 145, the positioning-related monitoring data reporting method according to any one of claims 56 to 67 or claims 146 to 157, the positioning-related model transfer method according to any one of claims 68 to 81 or claims 158 to 171, or the UE positioning capability assistance method according to any one of claims 82 to 90 or claims 172 to 180.

Images