Method and device for positioning estimation of user equipment based on artificial intelligence

Abstract

A method is disclosed that introduces a new AI-based positioning-related functionality at an NG-RAN node to enable a UE to select between AI and non-AI positioning models for UE position estimation and / or to enable the UE to select a suitable AI model among different AI positioning models according to an indication provided by the UE. The method also defines a measurement criterion for selecting an AI or non-AI model for UE positioning estimation, and defines a related signaling flow to achieve correct interaction between different NR positioning related nodes.

Description

Technical Field

[0001] The present application relates to the field of wireless communication systems, and more specifically, to a method and apparatus for direct positioning estimation based on artificial intelligence / machine learning (AI / ML). More specifically, the present application relates to enhancing radio access network (RAN) signaling and processes in new radio (NR) specifications to support AI-based direct positioning methods, thereby improving the accuracy of user equipment (UE) position estimation. Background Art

[0002] At the 3GPP RAN#94 meeting, a new study item (SI) on artificial intelligence / machine learning (AI / ML) for NR air interface was approved, with the main goal of exploring how to better support AI / ML algorithms by enhancing air interface functions to improve performance and / or reduce complexity / overhead. The goal of this study item is to study several carefully selected application scenarios, such as CSI feedback, beam management, and positioning accuracy improvement, and identify areas where AI / ML can improve air interface functional performance.

[0003] Regarding the application scenarios of positioning enhancement, a consensus was reached at the 3GPP RAN1#109 meeting to study two AI / ML-based positioning method options in the NR Release-18 specification. The first is a direct AI / ML positioning method, in which the AI / ML model will replace the existing positioning method to provide the final UE location estimate. The second is an indirect AI / ML positioning method or an AI-assisted method, in which the AI ​​model is used to assist the existing positioning method to improve the accuracy of the UE location estimate. In addition, it was decided at the meeting to further study the potential regulatory impact of the AI / ML positioning method and provide relevant inputs, including the indication / configuration aspects of the AI / ML model, such as auxiliary signaling and processes, including model configuration, model activation / deactivation, model recovery / termination, and model selection.

[0004] For the direct AI / ML positioning method, it was proposed in multiple contributions submitted to the 3GPP RAN1#109 meeting that this option may face some technical challenges. These challenges include: the introduction of new types of positioning measurements may lead to increased signaling overhead or complexity issues; the generalization ability of the AI ​​model when changing UE scenarios; backward compatibility issues with existing NR positioning methods; and high requirements for processing power or computing resources in the entity deploying direct AI / ML positioning. Therefore, corresponding devices, methods, processes, or signaling enhancements are required to effectively integrate this direct AI / ML positioning model in the NR specification while taking into account the above technical challenges. Summary of the invention

[0005] The purpose of this application is to propose a method and device for a positioning model based on direct artificial intelligence / machine learning (AI / ML) for use in user equipment (UE) position estimation.

[0006] In a first aspect of the present application, a method based on a direct AI / ML positioning model for user equipment (UE) position estimation is provided, which is performed by a communication network system, including: deploying direct AI positioning related functions or information elements in a radio access network (RAN) entity, an access and mobility management function (AMF) and / or a location management function (LMF) entity; the direct AI positioning related functions allow the node responsible for UE position estimation (such as UE or LMF) to select a suitable AI / ML model between different AI models, and / or adaptively select between direct AI positioning methods and non-AI positioning methods based on a set of parameters or configurations in the communication network system entity; the parameter set or indication includes at least one of the following parameters: performance error of an existing AI or non-AI positioning model; processing capability limitations of an AI positioning model deployment entity (e.g., UE type information); the positioning accuracy level required by an application (i.e., the UE position estimation requirement requested by the application); the processing load, overhead or computing resource availability status of the AI ​​model deployment entity.

[0007] In a second aspect of the present application, a communication network system is provided, comprising: a memory; a transceiver; a processor coupled to the memory and the transceiver; wherein the processor is configured to execute the above method.

[0008] In a third aspect of the present application, a non-transitory machine-readable storage medium stores instructions thereon, and when a computer executes the instructions, the instructions cause the computer to execute the above method.

[0009] In a fourth aspect of the present application, a chip includes a processor configured to call and run a computer program stored in a memory so that a device equipped with the chip executes the above method.

[0010] In a fifth aspect of the present application, a computer-readable storage medium stores a computer program, wherein the computer program enables a computer to execute the above method.

[0011] In a sixth aspect of the present application, a computer program product comprises a computer program, wherein the computer program enables a computer to execute the above method.

[0012] In a seventh aspect of the present application, a computer program is provided, wherein the computer program enables a computer to execute the above method. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present application or related technologies, various embodiments will be described below, and the accompanying drawings will be briefly introduced. Obviously, these drawings are only some embodiments of the present application, and ordinary technicians in this field can obtain other drawings based on these drawings without exceeding the scope of the present application.

[0014] Figure 1 This is a schematic diagram of an example of an NR positioning system architecture with different AI positioning model positions and collaboration options according to an embodiment of the present application.

[0015] Figure 2 It is a schematic diagram of an example of a direct AI positioning and AI-assisted positioning method according to an embodiment of the present application.

[0016] Figure 3 This is a schematic diagram of an NR positioning system architecture example according to an embodiment of the present application, in which the direct AI-related positioning function is located in the gNB.

[0017] Figure 4 This is a schematic diagram of an NR positioning system architecture example according to an embodiment of the present application, in which direct AI positioning related functions are located in AMF / LMF.

[0018] Figure 5 This is a schematic diagram of an example of an NR positioning system architecture assuming no UE-network collaboration according to an embodiment of the present application, in which the direct AI model is located on the UE side and the AI ​​positioning-related functions are located on the gNB or AMF / LMF side.

[0019] Figure 6 This is a schematic diagram of an example of an NR positioning system architecture assuming no UE-network collaboration according to an embodiment of the present application, in which a direct AI positioning model is located on the gNB side, and AI positioning-related functions are located on the gNB or AMF / LMF side.

[0020] Figure 7 This is a schematic diagram of an example of an NR positioning system architecture assuming no UE-network collaboration according to an embodiment of the present application, in which the direct AI model is located in the LMF / AMF and the AI ​​positioning-related functions are located in the gNB or AMF / LMF end.

[0021] Figure 8 This is an example of the NR positioning system architecture under the collaborative option of transmitting the AI ​​model from gNB to UE as shown in the embodiment of the present application.

[0022] Fig. 9 This is a schematic diagram of an example of an NR positioning system architecture under the collaborative option of transmitting an AI model from LMF to UE as shown in an embodiment of the present application.

[0023] Fig.10 It is a schematic diagram of an example of providing an AI model indication in an RRC signaling response of a location measurement indication from a UE to a gNB according to an embodiment of the present application.

[0024] Fig.11 This is a schematic diagram of an example of providing an AI model indication when the LMF sends a positioning information NR-PPa signaling request to the gNB according to an embodiment of the present application.

[0025] Fig.12 This is a schematic diagram of an example of RRC signaling configuration 0 / 1 for transmitting relevant information from the gNB to the UE exchange model as shown in an embodiment of the present application.

[0026] Fig.13 This is a schematic diagram of an example of providing model transmission related information in a positioning information response or an update message NR-PPa signaling response sent by the gNB to the LMF according to an embodiment of the present application.

[0027] Fig.14 It is a block diagram of a communication network system according to an embodiment of the present application.

[0028] Fig.15 It is a flowchart of a method based on a direct AI / ML positioning model for user equipment (UE) position estimation according to an embodiment of the present application.

[0029] Fig.16 It is a block diagram of a wireless communication system according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] The technical content, structural features, objectives and effects of the present application are described in detail below in conjunction with the accompanying drawings. Specifically, the terms in the embodiments of the present application are only used to describe the purpose of specific embodiments, and are not intended to limit the present application.

[0031] At the 3GPP RAN#94 meeting, a new study item (SI) on AI / ML for NR air interface was approved, with the main goal of exploring ways to better support AI / ML algorithms by enhancing air interface functions to improve performance and / or reduce complexity / overhead. The goal of this study item is to focus on studying several carefully selected application scenarios, such as channel state information (CSI) feedback, beam management, and positioning accuracy enhancement, to identify areas where AI / ML can improve the performance of air interface functions, and to study a general AI / ML framework, including the functional requirements of the AI / ML architecture and the regulatory impact required to implement AI / ML technology to improve air interface performance. Regarding NR AI positioning accuracy enhancement, a consensus was reached at the 3GPP RAN1#109 meeting to further study the deployment locations of different AI positioning models, such as: the AI ​​model is located on a single side or a single entity (UE, gNB or LMF), that is, training and reasoning are performed on a single end; some AI models are deployed on a single side, that is, training and reasoning are mainly performed on the network or UE side, but additional signaling or process optimization is required between the two ends, and may be combined with the existing signaling framework. In addition, a consensus was reached at the meeting to consider different levels of network and UE collaboration, such as: no collaboration; signaling-based collaboration (without model transmission); signaling-based collaboration (with model transmission) (see Figure 1 ). At the same time, it was decided to further study the applicability of AI / ML model generalization in NR positioning.

[0032] In addition to the above agreements, a consensus was reached at the RAN1#109 meeting to further study the following AI / ML-based positioning enhancement technologies, including: a) Direct AI positioning: Using AI positioning methods to replace existing positioning methods, and using new types of measurement data and / or measurement reports to estimate UE position, including: signal amplitude or power; time of arrival (TOA); angle of arrival (AoA); channel impulse response (CIR); beam index; transmission and reception point (TRP) index; reflection order of signals received from multiple TRPs (see Figure 2b) Indirect or AI-assisted positioning: AI is used as an auxiliary means to optimize the existing positioning method to improve the accuracy of UE position estimation. By extracting intermediate features from the measurement data and / or measurement reports, such as: downlink-reference signal timing difference (DL-RSTD); downlink departure angle (DL-angle of departure, DL-AoD); uplink relative time of arrival (UL-RTOA); uplink sounding reference signal-reference signal received power (UL SRS-RSRP); downlink positioning reference signal RSRP (DL PRS-RSRP); UE receive-transmit time difference (UERx-Tx Time Difference); gNB receive-transmit time difference (gNB Rx-Tx Time Difference); uplink angle of arrival (UL-AOA), departure angle (AoD) or zenith angle of arrival (ZOA) (calculated for each path); then, the final UE position is estimated based on the extracted intermediate features (see Figure 2 ).

[0033] In this report, we focus on the direct AI-based positioning method because this method may require the introduction of new measurement methods and / or additional information exchanges or processes, which may increase system overhead and / or increase system complexity, thereby reducing network efficiency. In addition, this method also has the following problems: Since the training of AI / ML models is usually highly dependent on specific scenarios or geographical distribution, the adaptability of the model may be limited when the scenario changes. The direct AI positioning method may be difficult to be compatible with current non-AI positioning standards. The computational requirements of the direct AI positioning model may exceed the processing power or computing resources of entities such as UE, gNB or LMF. Therefore, it is not clear how to integrate the direct AI / ML positioning model into the NR specification while maintaining a balance between the following factors: signaling overhead, system complexity, generalization ability of the AI ​​model, backward compatibility issues, processing power or computing resource availability of the entity running the AI ​​model, and the positioning accuracy level that can be achieved by the direct AI positioning method in UE position estimation. In response to the above technical challenges, some embodiments of the present application propose a method for effectively integrating the direct AI positioning model while taking into account the above technical factors.

[0034] In order to strike a balance between the above technical factors and the positioning accuracy that can be achieved by the direct AI-based positioning estimation model, this application proposes to introduce direct AI positioning related functions or information elements in the existing NR specification, such as deployed in the gNB and / or AMF / LMF entity. The role of this function is to act as a management entity for the AI / ML positioning model, responsible for the indication / configuration of the AI / ML model, including: activation / deactivation of the AI ​​model; recovery / termination of the model; selection of the model; transmission of the model; applicable to the management of different model deployment entities and collaboration levels, regardless of which entity the model is deployed in (such as UE, gNB or LMF), or what degree of collaboration is required between these entities. The main goal of the direct AI positioning related function is to allow the node responsible for UE position estimation (such as UE or LMF) to select a suitable model between different AI / ML positioning models; to allow adaptive selection between direct AI / ML positioning methods and non-AI positioning methods to achieve UE position estimation. The selection of the AI ​​model can be determined by the node responsible for positioning estimation (such as UE, gNB or LMF) based on existing parameters or configurations; explicit or implicit indication, transmitted through signaling messages from the final position estimation node. The parameters or indications for AI model selection may include at least one of the following factors: performance errors of existing AI or non-AI positioning models; processing capability limitations of the AI ​​positioning model deployment entity (gNB, UE, LMF) (such as UE type information); the positioning accuracy level required by the application (i.e., the accuracy requirements of UE position estimation); the processing load, overhead, or computing resource availability status of the AI ​​positioning model deployment entity (such as gNB, UE or LMF).

[0035] In order to support different direct AI / ML positioning model location options and different levels of collaboration, this application discloses or defines different levels of procedures and interactive signaling between the UE, LMF, and the relevant AI direct positioning functions at the gNB or LMF. The details of these signaling and procedures are provided in the following embodiments.

[0036] Embodiment 1: Consider the signaling and process of direct AI positioning function located in gNB.

[0037] Considering that the direct AI positioning function is located in the gNB, the processes and interactions between the AI ​​direct positioning related functions at the UE, LMF and gNB can be as follows: Figure 3 as shown and described below:

[0038] The UE or core network (CN) entity (e.g., 5G location server) sends the UE's positioning or location service request to the entity responsible for the final position estimation or calculation (i.e., location management function LMF).

[0039] The LMF entity forwards or initiates a position estimation process request to the NG-RAN node or gNB (e.g., via an NR-PPa signaling request), which may contain an explicit or implicit indication of at least one of the above-mentioned AI-related positioning parameters.

[0040] Based on this indication or internal NG-RAN node configuration, the node may request the UE (e.g., via RRC signaling configuration) to provide location information, including an explicit indication that AI-based positioning methods are enabled or supported, or an implicit indication based on the above parameters (or a request for new measurements to support the AI ​​model at the gNB or LMF), or an indication of whether it has an AI positioning model or needs to transmit the model from the LMF or gNB.

[0041] The UE may respond to the gNB request by providing a SIGNALING CONFIGURATION 0 RESPONSE message containing an explicit or implicit indication of AI model support and / or model transmission information.

[0042] Based on the indication signaling configuration 0 response message from the UE, or the indication provided by the LMF to the gNB, the gNB or the AI-based related positioning function at the gNB may decide to provide / configure one of the following through signaling configuration 1: positioning reference signal (PRS) or positioning sounding reference signal (SRS) measurement gap configuration, measurement object and / or measurement indication configuration to support AI-based or non-AI positioning methods; or, the gNB may provide a combination of these two types of configurations based on the indication to ensure other requirements (such as ensuring a certain positioning KPI, reducing signaling overhead, or ensuring fallback to a non-AI model to allow selection between different AI positioning models when the UE scenario or conditions change). In addition, the gNB may also configure the transmission of AI positioning reasoning model information / configuration to the UE, or transmit reasoning input data to the UE before transmitting AI-related measurement objects, indications or gap configurations. In another scheme, the gNB may transmit AI / non-AI related information to the LMF through the interface connecting the NG-RAN node and the AMF (i.e., NR-PPa signaling response) and the AI / non-AI related measurement data received from the UE for final position calculation. Optionally, the gNB may exchange AI / non-AI positioning support information related to the UE with another RAN node through the X2 / Xn interface to support non-AI or AI positioning methods on that node.

[0043] Based on the measurement gaps configured by the NG-RAN node, the UE may perform AI / non-AI related measurements as described below and report them back to the gNB.

[0044] Direct AI is based on measurements such as amplitude, time of arrival (TOA), angle of arrival (AoA), channel impulse response (CIR), beam index, TRP index, power and / or signal reflection order of signals received from a gNB or multiple gNBs.

[0045] Alternatively, non-AI-based measurements, such as downlink RSTD and uplink RTOA, downlink PRS-RSRP and uplink SRS-RSRP, UE transmit / receive time difference (Rx-Tx) and gNB transmit / receive time difference (Rx-Tx), and uplink AoA, ZoA or AoD values ​​on each path.

[0046] After receiving the signaling configuration 1 from the gNB, the UE may send a response message containing a measurement report to the gNB or LMF via a signaling response 1 for final position estimation; alternatively, if the AI ​​model has been deployed on the UE side or transmitted from the LMF or gNB to the UE, the UE may perform position estimation or inference locally.

[0047] Example 2: Considering the signaling and process of direct AI positioning function located in LMF:

[0048] When the direct AI positioning function is located in the LMF, the process and interaction between the UE, LMF and the AI ​​direct positioning related functions at the LMF can be as follows: Figure 4 ) and as follows:

[0049] The UE or core network (CN) entity (e.g., 5G location server) sends the UE's positioning or location service request to the entity responsible for the final location estimation or calculation (i.e., location management function LMF).

[0050] The LMF entity forwards or initiates a position estimation process request to the gNB (e.g., via NR-PPa signaling request), or may optionally send a request to the UE (e.g., via non-access stratum (NAS) signaling). The request may contain a request or query regarding support or activation / deactivation of the direct AI positioning method on a RAN entity (e.g., gNB or UE).

[0051] Based on the request of the LMF entity, the gNB may request the UE (e.g., via RRC signaling configuration 0) to provide location information, including an explicit indication about enabling or supporting direct AI based positioning methods, or an implicit indication based on the above parameters; whether new measurement data needs to be provided to support the direct AI model at the gNB or LMF; and an indication of whether the UE has an AI positioning model, or whether the model needs to be transmitted from the LMF or gNB.

[0052] The UE may respond to the gNB's request by providing a SIGNALING CONFIGURATION 0 RESPONSE message containing an explicit or implicit indication of AI model support / activation / deactivation and / or model transmission information.

[0053] Based on the Signaling Configuration 0 response message provided by the UE and the indication provided by the LMF to the gNB, the gNB may decide to provide / configure through Signaling Configuration 1: Positioning Reference Signal (PRS) or Positioning Sounding Reference Signal (SRS) measurement gap configuration; Measurement object and / or measurement indication configuration for AI or non-AI based positioning methods; or, the gNB may provide a combination of these two types of configurations to ensure other requirements (such as ensuring positioning\KPI, reducing signaling overhead, ensuring fallback to non-AI model when conditions change, or allowing selection between different AI positioning models). In addition, the gNB may instruct the LMF to transmit AI positioning reasoning model information / configuration, or transmit reasoning input data to the UE before transmitting AI-related measurement objects, indications or gap configurations. In another scheme, the gNB may transmit AI / non-AI related information to the LMF through the interface connecting the NG-RAN node and the AMF (i.e., NR-PPa signaling response) and AI / non-AI related measurement data received from the UE to support model transmission and / or final position calculation. Optionally, the gNB may exchange UE-related AI / non-AI positioning support information with another RAN node via the X2 / Xn interface to support non-AI or AI positioning methods on that node.

[0054] Based on the measurement gaps configured by the NG-RAN node, the UE may perform AI / non-AI related measurements as described below and report them back to the gNB or to the LMF via non-access stratum (NAS) signaling.

[0055] Direct AI is based on measurements such as amplitude, time of arrival (TOA), angle of arrival (AoA), channel impulse response (CIR), beam index, TRP index, power and / or signal reflection order of signals received from a gNB or multiple gNBs.

[0056] Non-AI based measurements, such as downlink RSTD and uplink RTOA, downlink PRS-RSRP and uplink SRS-RSRP, UE transmit / receive time difference (Rx-Tx) and gNB transmit / receive time difference (Rx-Tx), uplink AoA, ZoA or AoD values ​​on each path.

[0057] After receiving the signaling configuration 1 from the gNB, the UE may send a response message containing a measurement report to the gNB or LMF through a signaling response 1 to make a final position estimate; or, if the AI ​​model has been deployed on the UE side or transmitted from the LMF or gNB to the UE, the UE may perform position estimation or inference locally.

[0058] Embodiment 3: No UE-network collaboration, direct AI positioning model is located at the UE end.

[0059] This embodiment is suitable for scenarios where high positioning accuracy is required and the AI ​​model is deployed on the UE side, such as Figure 5 As shown. In this case, the direct AI related functions may be located in the gNB or LMF. In this scenario, the gNB instructs the UE to make measurements and provides instructions to the UE to do one of the following: run the AI ​​model to estimate the position and return the estimated position result; optionally, provide the parameters required for the position calculation to the LMF; or, directly provide the measurement data to the LMF so that the LMF can calculate the final UE position. The LMF then provides the final position estimate result to the entity requesting the UE position.

[0060] Embodiment 4: No UE-network collaboration, direct AI positioning model located at the gNB end.

[0061] This embodiment is also applicable to scenarios where high positioning accuracy is required and the AI ​​model is deployed on the gNB side, such as Figure 6 As shown. In this case, the direct AI related functions may be located in the gNB or LMF. In this scenario, the gNB or LMF instructs the UE to make measurements and reports the measurement results back to the gNB. Based on the measurement results, the gNB may do one of the following: run the AI ​​model for position reasoning and provide the final position estimate to the LMF; or directly provide the measurement data to the LMF so that the LMF can calculate / estimate the final position through traditional positioning methods. The LMF then provides the final position estimate to the entity requesting the UE position.

[0062] Embodiment 5: No UE-network collaboration, direct AI positioning model is located at the LMF end.

[0063] This embodiment is also applicable to scenarios where high positioning accuracy is required and the AI ​​model is deployed on the LMF side, such as Figure 7 As shown. In this case, the direct AI related functions may be located in the gNB or LMF. In this scenario, the gNB or LMF instructs the UE to make measurements and report back to the gNB, and the gNB then transmits the measurement data to the LMF along with an indication of the AI / non-AI model to use. Based on the indication, the LMF can perform positioning calculations with AI or non-AI. The UE then provides the final position estimate to the entity that requested the UE's position.

[0064] Embodiment 6: Collaboration option transmits AI model from gNB to UE.

[0065] This embodiment is applicable to scenarios where the positioning accuracy requirement is high, but the UE itself does not have an AI model, but supports the AI ​​model, and the delay allows the download of the AI ​​model, such as Figure 8 As shown. In this case, the gNB may instruct the UE to provide information related to the AI ​​model transmission. The gNB then transmits the required direct AI positioning AI model to the UE and configures the UE to perform AI measurement gap / object-based measurements. The gNB then instructs the UE to perform measurements and / or calculate the required position or provide AI-based data to the LMF for final position estimation.

[0066] Embodiment 7: Collaboration option transmits AI model from network to UE.

[0067] This embodiment is applicable to scenarios where the positioning accuracy requirement is high, but the UE itself does not have an AI model, but supports the AI ​​model, and the delay allows the download of the AI ​​model, such as Fig. 9 As shown. In this case, the gNB may instruct the UE to provide AI model transmission related information to the gNB or directly to the LMF through NAS signaling. Subsequently, the gNB requests the LMF to transmit the required direct AI positioning AI model to the UE. In addition, the gNB will also configure the UE to perform AI-based measurement gap / object measurements, and instruct the UE to perform measurements and calculate the final UE position, and then provide the final UE position estimate result to the LMF.

[0068] Embodiment 8: Signaling message and indication.

[0069] In the above method, the UE provides an explicit or implicit indication to the NG-RAN node through the air interface, namely, the RRC signaling response 0 message, which is an RRC signaling message sent by the UE to the gNB through the uplink logical channel. The RRC signaling response 0 message may selectively belong to one of the following categories: a first-category message, such as an uplink information transmission RRC message, a location measurement indication RRC message, and a UE assistance information RRC message. A second-category message, such as a UE information response RRC message, a UE positioning assistance information RRC message (a new RRC message defined for AI positioning integration). The RRC signaling response 0 message may contain the following: Explicit AI positioning model indication information, including: assistance information, such as model error, processing load and / or accuracy level indication, for the gNB or LMF to decide whether to activate or deactivate the AI ​​positioning model (this information is represented in the AI-ModelAssistanceInfo IE field). Directly request activation or deactivation of the AI ​​model (this information is represented in the AI-ModelDirectIndication IE field). AI inference input transmission or AI positioning model transmission request information, including: whether AI model inference input transmission (InferenceInput IE) is required, whether AI positioning model transmission (ModeTransferInfo IE) is required. If model transmission is required, the UE can indicate the requirement and provide the model ID to the gNB. Measurement type indication information, including: what type of measurement the gNB needs to configure for the UE to support AI positioning method or non-AI based positioning method. Relevant information is contained in Non-AIMeasurementInfoList-rel-18IE and AI-MeasurementInfoList-rel-18IE. Based on the indication of the measurement type, the gNB can perform the following operations: configure measurement gaps, configure measurement parameters, and configure one or more measurement objects to support AI or non-AI based positioning methods. In addition, for examples of explicit or implicit indications provided in the location measurement indication RRC message, refer to Fig.10 .

[0070] In the above method, the LMF / AMF entity of the core network provides explicit or implicit indications to the NG-RAN through the NR Positioning Protocol A (NR-PPa) signaling message. The NR-PPa signaling request message can be one of the following types: positioning information request / update message; measurement start request message; positioning activation request message; new NR-PPa signaling message defined for exchanging information related to AI / non-AI positioning methods between LMF / AMF and NG-RAN nodes. The NR-PPa signaling message may contain the following: Explicit AI positioning model indication information, including: auxiliary information, such as model error, processing load and / or accuracy level indication, for gNB or LMF to decide whether to activate or deactivate the AI ​​positioning model (this information is represented in the AI-ModelAssistanceInfo IE field). Directly request activation or deactivation of the AI ​​model (this information is represented in the AI-ModelDirectIndication IE field). AI model inference input transmission or AI positioning model transmission request information, including: whether AI model inference input transmission is required (InferenceInput IE), whether AI positioning model transmission is required (ModeTransferInfo IE), if model transmission is required, UE can indicate the requirement (AImodelTransfer IE) and provide the model ID to gNB (AI-Model-IdIE). For examples of explicit or implicit indications provided in the positioning information request NR-PPa message sent by LMF to NG-RAN node, please refer to Fig.11 .

[0071] In the above method, the NG-RAN node transmits RRC signaling configuration 0 or RRC signaling configuration 1 of the AI ​​model or measurement gap configuration to the UE, which can be in the following forms: RRC setup; RRC reconfiguration; RRC recovery; RRC release; RRC reestablishment; RRC recorded measurement configuration message; new RRC message defined for exchanging AI positioning related information between gNB and UE. The RRC signaling configuration 0 message may include the following: AI positioning activation and deactivation information (this information is represented in the AI-Pos-ModelSupport IE field). AI model inference input configuration (this information is represented in the ModelInferenceInput IE field). AI positioning model transmission configuration information, including: asking the UE whether the AI ​​model needs to be transmitted from the gNB; providing a set of AI models for the UE to select (this information is represented in the ModelTransferInfo IE field). For an example of the RRC signaling configuration 0 message carrying AI positioning related information sent by the gNB to the UE, please refer to Fig.12 .

[0072] In the above method, the NR-PPa signaling response or update message can be used to transmit AI / non-AI model transmission information from the gNB to the LMF. The message can be one of the following types: positioning information response; positioning information update message; a new NR-PPa signaling message defined for exchanging AI / non-AI positioning method related information between the NG-RAN node and the LMF. The NR-PPa signaling response or update message may contain the following: AI positioning activation and deactivation information (this information is represented in the AI-Pos-ModelSupportIE field). AI model inference input configuration (this information is represented in the ModelInferenceInput IE field). AI positioning model transmission configuration information, including: asking whether the AI ​​model needs to be transmitted from the gNB to the specified UE; providing a set of AI models available for the UE to select (this information is represented in the ModelTransferInfo IE field). For an example of an NR-PPa signaling response or update message carrying AI positioning related information sent by the LMF to the gNB or UE, please refer to Fig.13 .

[0073] Fig.14 It is described that in some embodiments, one or more user equipment (UE) 10, RAN node (e.g., gNB) 20, and network node (e.g., LMF or AMF) 30 communicate in a communication network system 40. According to an embodiment of the present application, the communication network system 40 includes one or more UE 10, RAN node 20, and network node 30 (e.g., LMF or AMF). One or more UE 10 may include a memory 12, a transceiver 13, and a processor 11, wherein the processor 11 is connected to the memory 12 and the transceiver 13. The RAN node 20 may include a memory 22, a transceiver 23, and a processor 21, wherein the processor 21 is connected to the memory 22 and the transceiver 23. The network node 30 may include a memory 32, a transceiver 33, and a processor 31, wherein the processor 31 is connected to the memory 32 and the transceiver 33. The processor 11, 21, or 31 may be configured to perform the proposed functions, processes, and / or methods described in this description. Each layer of the radio interface protocol may be implemented in the processor 11, 21, or 31. The memory 12, 22 or 32 is operatively coupled to the processor 11, 21 or 31 and stores various information for the operation of the processor 11, 21 or 31. The transceiver 13, 23 or 33 is operatively coupled to the processor 11, 21 or 31 and is responsible for transmitting and / or receiving wireless signals.

[0074] The processor 11, 21 or 31 may include an application-specific integrated circuit (ASIC), other chipsets, logic circuits and / or data processing devices. The memory 12, 22 or 32 may include a read-only memory (ROM), a random access memory (RAM), a flash memory, a memory card, a storage medium and / or other storage devices. The transceiver 13, 23 or 33 may include: a baseband circuit for processing radio frequency signals. When the embodiment is implemented in software form, the technology described herein can be implemented using modules (such as procedures, functions, etc.) that perform the functions. These modules can be stored in the memory 12, 22 or 32 and executed by the processor 11, 21 or 31. The memory 12, 22 or 32 can be integrated inside the processor 11, 21 or 31, or located outside the processor 11, 21 or 31, in which case they can be communicated with the processor 11, 21 or 31 by various known methods.

[0075] Fig.15 It is a flowchart of a method based on a direct AI / ML positioning model for user equipment (UE) position estimation according to an embodiment of the present application. Fig.15 In some embodiments, the method includes the following steps: Step 1502: In a radio access network (RAN) entity, an access and mobility management function (AMF) and / or a location management function (LMF) entity, use direct AI positioning related functions or information elements. Step 1504: Perform direct AI positioning related functions so that the node responsible for UE location estimation (e.g., UE or LMF) can select a suitable model from different AI / ML models; adaptively select between direct AI positioning methods and non-AI positioning methods based on a set of parameters or the configuration of the communication network system entity; or adaptively select between AI positioning methods and non-AI positioning methods based on explicit or implicit indications transmitted by the final location estimation node through signaling messages. The parameters or indications include at least one of the following parameters: performance error of existing AI or non-AI positioning models; processing capacity limitations of AI positioning model deployment entities (e.g., UE type information); positioning accuracy level required by applications (i.e., accuracy requirements indicated by applications requesting UE location estimation); processing load, overhead, or computing resource availability status of AI model deployment entities.

[0076] In summary, some embodiments of the present application provide a method that relies on introducing a new AI-based positioning-related function in the NG-RAN or LMF node, which allows the UE to adaptively select between AI and non-AI positioning models, and defines within the function a metric that can be used to select an AI or non-AI positioning model for position estimation, while defining related signaling processes to ensure the correct interaction between the UE, NG-RAN, and LMF entities. The main advantages of the method provided by some embodiments of the present application include: the new method introduces a mechanism that makes the selection of AI or non-AI positioning methods configurable, so that the best balance can be achieved between the level of positioning accuracy and network efficiency, signaling overhead, and the complexity that may be caused by adopting an AI model. The new method provides flexibility, supports AI and non-AI methods, and is able to select between different AI models, or adaptively combine these methods to support each UE to select a suitable model (for example, select the best model with smaller error in the case of multiple models), and is able to fall back to a non-AI model when necessary (for example, when the scene changes cause model performance errors). The new method helps to avoid transmitting unnecessary AI model-related information on multiple network interfaces. For example, when the AI ​​positioning model is located in the UE or LMF, the AI ​​model related information needs to be transmitted on the interface between the UE and the NG-RAN node and the interface between the NG-RAN node and the LMF, and this method can effectively avoid this situation. The new method reuses the existing NR positioning signaling and procedures, thereby minimizing the regulatory impact of the integration of AI in positioning.

[0077] Fig.16 1 is a block diagram of a wireless communication system according to an embodiment of the present application. The embodiments described herein may be implemented in a system using any appropriately configured hardware and / or software. Fig.16 A system 700 is shown, which includes a radio frequency (RF) circuit 710, a baseband circuit 720, an application circuit 730, a memory / storage device 740, a display 750, a camera 760, a sensor 770, and an input / output (I / O) interface 780, which are coupled to each other at least as shown. The application circuit 730 may include circuits, such as but not limited to one or more single-core or multi-core processors. The processor may include any combination of general-purpose processors and special-purpose processors, such as a graphics processor, an application processor. The processor may be coupled to a memory / storage device and configured to execute instructions stored in the memory / storage device to enable various applications and / or operating systems to run on the system.

[0078] While the present disclosure has been described in connection with what is considered to be the most practical and preferred embodiment, it is to be understood that the present disclosure is not limited to the disclosed embodiment, but is intended to cover various arrangements made without departing from the scope of the broadest interpretation of the appended claims.

Claims

1. A method for direct artificial intelligence / machine learning AI / ML positioning model for user equipment UE location estimation, performed by a communication network system, characterized in that: include: A method for UE position estimation based on a direct AI / ML positioning model, adopting direct AI positioning related functions or information elements in a radio access network RAN ​​entity, an access and mobility management function AMF and / or a location management function LMF entity, wherein the direct AI positioning related functions allow the node responsible for UE position estimation to select a suitable AI / ML model between different AI models and / or based on a parameter set or the configuration of the communication network system entity, to adaptively select between a direct AI positioning method or a non-AI positioning method, and / or to select based on explicit or implicit indications transmitted from a node responsible for final position estimation through a signaling message; wherein the parameter set or indication includes at least one of the following parameters: performance errors of existing AI or non-AI positioning models, processing power limitations of an entity deploying an AI positioning model, an indication of the UE position estimation accuracy level required by an application, and / or a processing load, overhead or computing resource availability status of an entity deploying an AI model.

2. The method according to claim 1, characterized in that: It also includes adopting different levels of processes and interactions between the UE, the LMF entity and the relevant AI direct positioning functions to support different direct AI positioning options and different levels of collaboration.

3. The method according to claim 2, characterized in that in, The different levels of processes and interactions are adopted between the UE, the LMF entity and the relevant AI direct positioning function, including considering the process of setting the direct AI positioning function on the gNB.

4. The method according to claim 3, characterized in that The process of considering setting the direct AI positioning function in the gNB includes: The UE or the core network CN sends a positioning or location service request of the UE to the LMF entity; The LMF entity forwards or initiates a location estimation procedure request to a next generation radio access network NG-RAN node or the gNB, wherein the location estimation procedure request includes an explicit or implicit indication related to at least one AI positioning parameter; Based on the explicit or implicit indication or the internal configuration of the NG-RAN node, the NG-RAN node requests the UE to provide location information, including: an explicit indication of enabling or supporting an AI positioning method, an implicit indication based on at least one AI positioning parameter, or providing new measurement data to support an AI model of the gNB or the LMF entity, or indicating whether the UE has an AI positioning model or whether a model needs to be obtained from the LMF entity or the gNB; The UE responds to the gNB request by providing a signaling configuration 0 response message including information about AI model support and / or model transmission; Based on the signaling configuration 0 response message from the UE or the indication provided by the LMF entity to the gNB, the gNB or the AI-related positioning function on the gNB determines whether to provide / configure positioning reference signal PRS or positioning sounding reference signal SRS measurement gap configuration, measurement object and / or measurement indication configuration through signaling configuration 1 to support AI or non-AI positioning methods, or select a combination of the two configurations according to the indication to ensure other requirements including positioning KPI, reduce signaling overhead, or ensure fallback to a non-AI model when conditions change, or allow selection between different AI positioning models; Based on the measurement gap configured by the NG-RAN node, the UE performs AI / non-AI related measurements and reports the AI / non-AI related measurement results to the gNB; After receiving the signaling configuration 1 of the gNB, the UE sends a response including a measurement report to the gNB or the LMF entity through a signaling response 1 for final position estimation, or when the AI ​​model is deployed at the UE or transmitted from the LMF entity or the gNB to the UE, the UE performs position estimation or inference locally.

5. The method according to claim 4, characterized in that The gNB is configured to transmit AI positioning reasoning model information / configuration or reasoning input data to the UE before transmitting the AI ​​measurement object, measurement indication or measurement gap configuration.

6. The method according to claim 4, characterized in that The gNB transmits the AI / non-AI related information and AI / non-AI measurement data provided by the UE to the LMF entity through the interface connecting the NG-RAN node and the AMF for final position calculation.

7. The method according to claim 7, characterized in that: The AI / non-AI positioning measurements include: Direct AI measurements, including measuring amplitude, time of arrival TOA, angle of arrival AoA, channel impulse response CIR, beam index, TRP index, power and / or reflection order of signals received from the gNB or gNBs; or Non-AI measurements include DL-RSTD and UL-RTOA, DL PRS-RSRP and UL SRS-RSRP, UE receive-transmit time difference and gNB receive-transmit time difference, DL PRS-RSRPP and UL SRS-RSRPP, and UL-AOA and ZOA values ​​for each path.

8. The method according to claim 6 or 7, characterized in that: The gNB exchanges AI / non-AI positioning support information related to the UE with another RAN node via X2 / Xn to support non-AI or AI positioning methods of other nodes.

9. The method according to claim 2, characterized in that: The different levels of procedures and interactions are adopted between the UE, the LMF entity and the related AI direct positioning function, including considering the process of locating the direct AI positioning function in the LMF entity.

10. The method according to claim 9, characterized in that The process of considering placing the direct AI positioning function in the LMF entity includes: The UE or the core network CN sends a positioning or location service request of the UE to the LMF entity; The LMF entity forwards or initiates a positioning estimation procedure request to the gNB or the UE, wherein the positioning estimation procedure request includes a request or query for supporting or activating / deactivating a direct AI positioning method at a RAN entity; Based on the request from the LMF entity, the gNB requests the UE to provide location information through RRC signaling configuration 0, including an explicit indication of enabling or supporting a direct AI positioning method or an implicit indication based on at least one AI positioning parameter, or a request for providing new measurements for supporting the AI ​​model of the gNB or the LMF entity, or an indication of whether an AI positioning model is available or a model transmission is required from the LMF entity or the gNB; The UE responds to the request of the gNB by providing a SIGNALING CONFIGURATION 0 RESPONSE message including an explicit or implicit indication of AI model support and / or model transmission information; Based on the indication in the signaling configuration 0 response message from the UE or the indication provided by the LMF entity to the gNB, the gNB decides to provide / configure positioning reference signal PRS or positioning sounding reference signal SRS measurement gap configuration, measurement object and / or measurement indication configuration through signaling configuration 1 to support AI or non-AI based positioning methods, or selectively provide both types of configurations in combination according to the indication to ensure that positioning KPIs are included or signaling overhead is reduced, or to ensure fallback to a non-AI model when conditions change, or to allow selection between different AI positioning models; Based on the measurement gap configured by the NG-RAN node, the UE performs the AI / non-AI related measurement and reports the AI / non-AI related measurement result back to the gNB; After receiving the signaling configuration 1 from the gNB, the UE responds to the gNB or the LMF entity through a signaling response 1, providing a response including a measurement report for final position estimation; or in the case where the AI ​​model is deployed on the UE or transmitted from the LMF entity or the gNB to the UE, the UE performs position estimation or inference locally.

11. The method according to claim 2, characterized in that The different levels of procedures and interactions are adopted between the UE, the LMF entity and the related AI direct positioning function, including the process considering no UE-network collaboration and the direct AI positioning model is located at the UE.

12. The method according to claim 11, characterized in that The process considering no UE-network collaboration and the direct AI positioning model being located at the UE includes the gNB instructing the UE to perform measurements and providing instructions to the UE, causing the UE to run a model to estimate a position and return an estimated position, or providing position calculation parameters to the LMF entity, or providing pure measurement data to the LMF entity to calculate the final position of the UE, and the LMF entity providing the final position estimation result to the entity requesting the UE position.

13. The method according to claim 2, characterized in that The different levels of procedures and interactions are adopted between the UE, the LMF entity and the relevant AI direct positioning function, including the process considering no UE-network collaboration and the direct AI positioning model is located in the gNB.

14. The method according to claim 13, characterized in that The process considering the absence of UE-network collaboration and the direct AI positioning model being located at the gNB includes the gNB or the LMF entity instructing the UE to perform measurements and reporting the measurement results back to the gNB, based on the measurement results, the gNB running the AI ​​model for position reasoning and providing the final position estimation result to the LMF entity, or providing pure measurement data to the LMF entity to calculate / estimate the final position using a traditional positioning process, and providing the final position estimation result to the entity requesting the UE position.

15. The method according to claim 2, characterized in that The different levels of procedures and interactions are adopted between the UE, the LMF entity and the related AI direct positioning function, including the process considering no UE-network collaboration and the direct AI positioning model is located in the LMF entity.

16. The method according to claim 15, characterized in that The process considering the absence of UE-network collaboration and the direct AI positioning model being located in the LMF entity includes: the gNB or the LMF entity instructs the UE to perform measurements and reports the measurement results back to the gNB, based on the measurement results, the gNB provides the measurement data and an indication of using the AI / non-AI model to the LMF entity, the LMF entity performs AI or non-AI based position calculations according to the indications, and provides the final position estimation result to the entity requesting the UE position.

17. The method according to claim 2, characterized in that The different levels of procedures and interactions are adopted between the UE, the LMF entity and the relevant AI direct positioning function, including a process considering collaborative options for transmitting the AI ​​model from the gNB to the UE.

18. The method according to claim 17, characterized in that The process of considering the collaborative option of transmitting the AI ​​model from the gNB to the UE includes: the gNB instructing the UE to provide information related to the AI ​​model transmission to the gNB, transmitting the required direct AI positioning AI model to the UE, configuring the UE to perform AI-based measurement interval / measurement object, and instructing the UE to perform measurements and / or calculate the required position, or providing AI-based measurement results to the LMF entity for final position estimation.

19. The method according to claim 2, characterized in that The different levels of procedures and interactions are employed between the UE, the LMF entity and the relevant AI direct positioning function, including a process considering collaborative options for transmitting the AI ​​model from the network to the UE.

20. The method according to claim 19, characterized in that The process of considering the collaborative option of transmitting the AI ​​model from the network to the UE includes: the gNB instructs the UE to provide information related to the AI ​​model transmission to the gNB or directly to the LMF entity through NAS signaling, requesting the LMF entity to transmit the required direct AI positioning AI model to the UE, configuring the UE to perform AI-based measurement interval / measurement object, and instructing the UE to perform measurements and calculate the final UE position, and / or providing the final UE position estimate to the LMF entity.

21. The method according to any one of claims 3 to 20, characterized in that The explicit or implicit indication provided by the UE to the NG-RAN node through the air interface is an RRC signaling configuration 1 response message, and the RRC signaling configuration 1 response message is sent by the UE to the gNB on the uplink logical channel.

22. The method according to claim 21, characterized in that The RRC message is a first-level message, including an uplink information transmission message, a location measurement indication, or UE auxiliary information; or the RRC message is a second-level message, including a UE information response, UE positioning auxiliary information, or a new RRC message defined for AI positioning integration.

23. The method according to any one of claims 3 to 22, characterized in that The explicit or implicit indication provided by the LMF entity of the core network CN to the NG-RAN through the new wireless positioning protocol NR-PPa signaling request is a location information transmission / request process / signaling / message.

24. The method according to claim 23, characterized in that The NR-PPa signaling request message is a positioning information request / update message, a measurement start request message, a positioning activation request message, or a newly defined NR-PPa signaling message for exchanging information related to the AI / non-AI positioning method between the LMF entity and the NG-RAN node.

25. The method according to any one of claims 3 to 24, characterized in that An explicit indication in the message is a direct request to configure the measurement interval and / or provide a configuration to indicate support for AI or non-AI positioning methods, or to provide auxiliary information for indicating the same, or as input for inference or training.

26. The method according to any one of claims 3 to 25, characterized in that The RRC signaling configuration 0 / 1 used for AI model or measurement interval transmission is an RRC setup, reconfiguration, recovery, release, reestablishment, logged measurement configuration message, or a newly defined RRC message.

27. The method according to any one of claims 3 to 26, characterized in that The NR-PPa signaling message used to transmit AI / non-AI model transmission information from the gNB to the LMF entity is a positioning information response message, a positioning information update message, or a newly defined NR-PPa signaling message sent from the gNB to the LMF entity for exchanging information related to the AI / non-AI positioning method between the NG-RAN node and the LMF entity.

28. A communication network system, characterized in that: include: Memory; Transceiver; as well as a processor coupled to the memory and the transceiver; Wherein, the processor is configured to execute the method of any one of claims 1 to 27.

Images