Information interaction method and device

Abstract

The embodiment of the invention provides an information interaction method and device. The method comprises the steps that first equipment sends a model related information request and / or an entity related information request used for optimizing wireless positioning AI / ML model training to second equipment; and the first device receives model related information feedback and / or entity related information feedback sent by the second device.

Description

Information interaction method and device Technical Field

[0001] The present application relates to the field of communication technology. Background Art

[0002] With the commercialization of fifth-generation (5G) communications, and particularly the large-scale deployment of the Industrial Internet, the demand for positioning terminal devices in wireless communications has increased significantly. Traditional wireless positioning relies on a variety of technologies, of which those directly related to 5G NR (New Radio) primarily rely on channel measurement between network entities and terminals. These methods, such as TDOA (Time Difference of Arrival), E-CID (Enhanced Cell ID), and Multi-RTT (Multi-Round-Trip Time), all have inherent flaws, resulting in poor positioning accuracy for terminal devices in various wireless environments or scenarios. This is particularly true in wireless environments with severe non-line-of-sight (NLOS) conditions, such as indoor factories (InF), where the errors of traditional positioning methods are extremely large and often unacceptable.

[0003] The fundamental reason is that positioning methods based on wireless channel measurement are only effective in line-of-sight (LOS) environments. The wireless channel measurement values ​​obtained in non-line-of-sight environments have a large deviation from the ideal value. The accuracy of the terminal positioning result directly depends on this measurement value. Therefore, the measurement error will lead to the error of the final terminal positioning result.

[0004] In recent years, artificial intelligence and machine learning (AI / ML) technologies, represented by deep learning, have developed rapidly and, due to their powerful nonlinear fitting capabilities, have been applied in various research and commercial fields. Similarly, the performance of AI-based wireless positioning evaluation has significantly improved compared to traditional methods.

[0005] However, due to the complexity and variability of wireless communication environments and the inherent characteristics of big data-based AI / ML models used for wireless positioning, the generalization performance of AI / ML models (the consistency of inference operations using the same model in different environments) is poor. When the performance of AI / ML models cannot achieve high positioning accuracy in current wireless environments, or is insufficient to meet the accuracy requirements of current wireless applications for terminals, one solution is to perform different types of customized training on the AI / ML models, including retraining, fine-tuning, or partial update training.

[0006] Regardless of performance, traditional positioning methods rely on fixed mathematical models and computational processes, making it impossible to improve positioning accuracy through real-time algorithmic improvements. AI / ML models, on the other hand, are data-driven. By feeding the model different training data sets or adjusting model training parameters, positioning accuracy can be improved to a certain extent in a targeted manner.

[0007] It should be noted that the above introduction to the technical background is merely intended to provide a clear and complete description of the technical solutions of this application and facilitate understanding by those skilled in the art. Simply because these solutions are described in the background technology section of this application, it should not be assumed that the above technical solutions are well known to those skilled in the art.

[0008] Summary of the Invention

[0009] However, the inventors discovered that the wireless positioning process defined in the current 3GPP protocol does not involve the relevant concepts of AI / ML models. The customization of the training process needs to follow the lifecycle management process of the AI / ML model. The duration, resource usage, and parameter configuration of the AI / ML model training are directly related to the training accuracy. The positioning accuracy requirements and available resources in each scenario are not static, but are dynamically adjusted as the environment changes. Therefore, the network entities involved in positioning need to conduct a series of information exchanges to select the optimal solution for model training in terms of positioning accuracy, positioning delay, resource usage, and transmission overhead. This series of information exchanges is not clearly defined in the current protocol.

[0010] To address at least one of the above-mentioned problems, an embodiment of the present application provides an information interaction method and device, which enables information interaction between network entities involved in positioning, and between network entities and terminals, thereby realizing customized training for optimizing wireless positioning AI / ML models and obtaining more accurate positioning results.

[0011] According to one aspect of an embodiment of the present application, there is provided an information interaction method, including:

[0012] The first device sends a model-related information request and / or an entity-related information request for optimizing the wireless positioning AI / ML model to the second device; and

[0013] The first device receives model-related information feedback and / or entity-related information feedback sent by the second device.

[0014] According to another aspect of an embodiment of the present application, there is provided an information interaction apparatus, configured on a first device, the information interaction apparatus comprising:

[0015] A sending unit, which sends a model-related information request and / or an entity-related information request for optimizing the wireless positioning AI / ML model to the second device; and

[0016] A receiving unit receives model-related information feedback and / or entity-related information feedback sent by the second device.

[0017] According to another aspect of an embodiment of the present application, there is provided an information interaction method, including:

[0018] The second device receives a model-related information request and / or an entity-related information request for optimizing the wireless positioning AI / ML model from the first device; and

[0019] The second device sends model-related information feedback and / or entity-affiliation-related information feedback to the first device.

[0020] According to another aspect of an embodiment of the present application, an information interaction apparatus is provided, configured on a second device, the information interaction apparatus comprising:

[0021] a receiving unit configured to receive a model-related information request and / or an entity-related information request for optimizing a wireless positioning AI / ML model from a first device; and

[0022] A sending unit, which sends model-related information feedback and / or entity-related information feedback to the first device.

[0023] According to another aspect of an embodiment of the present application, a communication system is provided, including:

[0024] A first device that sends a model-related information request and / or an entity-related information request for optimizing a wireless positioning AI / ML model; and receives model-related information feedback and / or entity-related information feedback;

[0025] The second device receives the model-related information request and / or the entity-related information request; and sends the model-related information response and / or the entity-related information feedback.

[0026] One of the beneficial effects of the embodiments of the present application is that: a first device sends a model-related information request and / or entity-related information request for optimizing a wireless positioning AI / ML model to a second device; and the first device receives model-related information feedback and / or entity-related information feedback sent by the second device. As a result, information exchange can be carried out between network entities involved in positioning and / or between network entities and terminals, thereby realizing relevant model training for optimizing the wireless positioning AI / ML model, making the AI / ML model used for wireless positioning better in performance or generalization, thereby obtaining more accurate positioning results.

[0027] With reference to the following description and accompanying drawings, specific embodiments of the present application are disclosed in detail, indicating the manner in which the principles of the present application can be employed. It should be understood that the embodiments of the present application are not limited in scope. Within the spirit and scope of the appended claims, the embodiments of the present application include many variations, modifications and equivalents.

[0028] Features described and / or illustrated with respect to one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.

[0029] It should be emphasized that the term "include / comprising" when used herein refers to the presence of features, integers, steps or components, but does not exclude the presence or addition of one or more other features, integers, steps or components. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The elements and features described in one figure or one embodiment of the present application can be combined with the elements and features shown in one or more other figures or embodiments. In addition, in the accompanying drawings, similar reference numerals represent corresponding parts in several figures and can be used to indicate corresponding parts used in more than one embodiment.

[0031] The included drawings are used to provide a further understanding of the embodiments of the present application, which constitute a part of the specification, are used to illustrate the implementation methods of the present application, and together with the text description, explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without inventive work. In the drawings:

[0032] FIG1 is a schematic diagram of an application scenario of an embodiment of the present application;

[0033] FIG2 is a schematic diagram of an information interaction method according to an embodiment of the present application;

[0034] FIG3 is another schematic diagram of the information interaction method according to an embodiment of the present application;

[0035] FIG4 is another schematic diagram of the information interaction method according to an embodiment of the present application;

[0036] FIG5 is another schematic diagram of the information interaction method according to an embodiment of the present application;

[0037] FIG6 is another schematic diagram of the information interaction method according to an embodiment of the present application;

[0038] FIG7 is a schematic diagram of an information interaction device according to an embodiment of the present application;

[0039] FIG8 is another schematic diagram of the information interaction device according to an embodiment of the present application;

[0040] FIG9 is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0041] The above and other features of the present application will become apparent through the following description with reference to the accompanying drawings. In the description and the accompanying drawings, specific embodiments of the present application are disclosed in detail, which illustrate some embodiments in which the principles of the present application can be adopted. It should be understood that the present application is not limited to the described embodiments. On the contrary, the present application includes all modifications, variations and equivalents that fall within the scope of the appended claims.

[0042] In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish different elements from the name, but do not indicate the spatial arrangement or temporal order of these elements, and these elements should not be limited by these terms. The term "and / or" includes any one and all combinations of one or more of the associated listed terms. The terms "comprising", "including", "having", etc. refer to the presence of the stated features, elements, components or components, but do not exclude the presence or addition of one or more other features, elements, components or components.

[0043] In the embodiments of this application, the singular forms "a," "the," etc. include plural forms and should be broadly understood to mean "a" or "a type" rather than being limited to "one." Furthermore, the term "said" should be understood to include both singular and plural forms, unless the context clearly indicates otherwise. Furthermore, the term "according to" should be understood to mean "at least in part based on...", and the term "based on" should be understood to mean "at least in part based on...", unless the context clearly indicates otherwise.

[0044] In the embodiments of the present application, the term "communication network" or "wireless communication network" may refer to a network that complies with any of the following communication standards, such as Long Term Evolution (LTE), enhanced Long Term Evolution (LTE-A, LTE-Advanced), Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), etc.

[0045] Furthermore, communication between devices in the communication system may be carried out according to communication protocols of any stage, for example, including but not limited to the following communication protocols: 1G (generation), 2G, 2.5G, 2.75G, 3G, 4G, 4.5G and future 5G, New Radio (NR), etc., and / or other currently known or future communication protocols to be developed.

[0046] In the embodiments of the present application, the term "network device" refers to, for example, a device in a communication system that connects a terminal device to the communication network and provides services to the terminal device. Network devices may include, but are not limited to, the following devices: base station (BS), access point (AP), transmission reception point (TRP), broadcast transmitter, mobile management entity (MME), gateway, server, radio network controller (RNC), base station controller (BSC), etc.

[0047] Base stations may include, but are not limited to, NodeB (NB), evolved NodeB (eNodeB or eNB), 5G base stations (gNB), IAB hosts, and the like. They may also include remote radio heads (RRHs), remote radio units (RRUs), relays, or low-power nodes (e.g., femto, pico, etc.). The term "base station" may include some or all of their functions, and each base station may provide communication coverage for a specific geographic area. The term "cell" may refer to a base station and / or its coverage area, depending on the context in which the term is used.

[0048] In the embodiments of the present application, the term "user equipment" (UE) refers to, for example, a device that accesses a communication network through a network device and receives network services, and may also be referred to as "terminal equipment" (TE). Terminal equipment may be fixed or mobile, and may also be referred to as a mobile station (MS), terminal, user, subscriber station (SS), access terminal (AT), station, etc.

[0049] Terminal devices may include, but are not limited to, the following devices: cellular phones, personal digital assistants (PDAs), wireless modems, wireless communication devices, handheld devices, machine-type communication devices, laptop computers, cordless phones, smartphones, smart watches, digital cameras, etc.

[0050] For another example, in scenarios such as the Internet of Things (IoT), the terminal device can also be a machine or device for monitoring or measurement, including but not limited to: machine type communication (MTC) terminal, vehicle-mounted communication terminal, device-to-device (D2D) terminal, machine-to-machine (M2M) terminal, and so on.

[0051] The following describes the scenarios of the embodiments of the present application through examples, but the present application is not limited thereto.

[0052] FIG1 is a schematic diagram of a communication system according to an embodiment of the present application, schematically illustrating a situation using a terminal device and a network device as an example. As shown in FIG1 , a communication system 100 may include a network device 101, a terminal device 102, and a positioning server 103. For simplicity, FIG1 illustrates only one terminal device and one network device as an example, but the embodiments of the present application are not limited thereto.

[0053] In the embodiment of the present application, existing services or future services can be transmitted between the network device 101 and the terminal device 102. For example, these services may include, but are not limited to, enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable and low-latency communication (URLLC), etc.

[0054] It is worth noting that Figure 1 shows that the terminal device 102 is within the coverage of the network device 101, but the present application is not limited to this. The terminal device 102 may not be within the coverage of the network device 101. In addition, Figure 1 takes the deployment of the positioning server 103 as an example, and the AI ​​model can be run in the positioning server 103 to obtain the positioning result; however, the present application is not limited to this. The positioning server 103 can be deployed in the core network, in the network device 102 (such as a base station), or in the terminal device 103; the embodiments of the present application do not limit these situations.

[0055] In the embodiments of the present application, the terminal device to be located may be referred to as a target device, and the function of the positioning server may be referred to as a Location Management Function (LMF). The LMF may be a network entity that locates and manages the terminal, or a location server with a location management function may be referred to as an LMF. Alternatively, a location server may refer to an entity including the LMF that has positioning calculation and management functions. For details on these concepts and positioning, please refer to the relevant art.

[0056] In an embodiment of the present application, the AI / ML model for positioning can be deployed on a network device or on a terminal device. The usual situation of model training includes: in the early stage of training, the longer the training time and the more rounds, the higher the improvement in model accuracy, and after multiple rounds of training (EPOCH), the performance tends to be stable. In some cases, the performance will show irregular fluctuations or regression. Therefore, the cost required for model training and the gain obtained complement each other, and they need to interact, compare, and comprehensively judge with each other to select the best model training solution under the current scenario requirements.

[0057] The costs required for model training mainly include: time cost and resource cost.

[0058] The time cost mainly refers to the time required for model training. Its determining factors mainly include: the available software and hardware resources that the model training entity can allocate (such as software version, available algorithms, hardware capabilities, etc.), the characteristics of the model itself (such as the number of neurons in the model, the structure of the model, the characteristics of the backbone network, etc.), the model training parameter configuration (such as loss function, learning rate, batch data size, etc.), and the degree of correlation between the data sets used for model fine-tuning training and initial training (or, the last or previous training).

[0059] Resource costs include the wireless time and frequency resources and air interface resources required for the entire training process. For example, the measurement window configured during training, the time and frequency resources occupied by reference signals and measurement reporting, and the air interface resources occupied by signaling interactions involved in data collection and model management.

[0060] As can be seen, the optimization and management of the model training process is subject to multiple constraints. This diverse information cannot be fully acquired and independently judged by a single network entity; instead, signaling interaction between various network entities over the air interface is required. Furthermore, some information is causally related, requiring a signaling interaction process to address these causal relationships and ultimately achieve the optimal solution.

[0061] Embodiments of the first aspect

[0062] The present application provides an information interaction method, which is described from the perspective of a first device. The first device may be a network device (such as a base station), a terminal device (such as a target device or other terminal), or a location server with LMF functionality.

[0063] FIG2 is a schematic diagram of an information interaction method according to an embodiment of the present application. As shown in FIG2 , the method includes:

[0064] 201. The first device sends a model-related information request and / or an entity-related information request for optimizing a wireless positioning AI / ML model to the second device.

[0065] 202. The first device receives model-related information feedback and / or entity-related information feedback sent by the second device.

[0066] It is worth noting that FIG2 above is merely a schematic illustration of an embodiment of the present application, and the present application is not limited thereto. For example, the execution order of the various operations may be appropriately adjusted, and other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above description, and are not limited to the description of FIG2 above.

[0067] In some embodiments, the first device is a location server, and the second device is a terminal device; the location server sends the model attachment related information request to the terminal device through LPP (LTE Positioning Protocol) signaling, and the terminal device sends the model attachment related information feedback to the location server through LPP signaling.

[0068] For example, the UE (target device) transmits the attributes of the local model to the LMF (location server) through LPP signaling.

[0069] In some embodiments, the first device is a location server, and the second device is a base station or a network device; the location server sends the model-related information request to the base station through NRPPa (NR Positioning Protocol A) signaling, and the base station sends the model-related information feedback to the location server through NRPPa signaling.

[0070] For example, the gNB passes the attributes of the local model to the LMF (location server) through NRPPa signaling.

[0071] In some embodiments, the first device is a base station or a network device, and the second device is a terminal device; the base station or the network device sends the model-related information request to the terminal device through radio resource control (RRC) signaling, and the terminal device sends the model-related information feedback to the base station or the network device through RRC signaling.

[0072] For example, the UE (or target device) transmits the attributes of the local model to the gNB via RRC signaling.

[0073] In some embodiments, the first device receives a request message for starting training sent by the second device.

[0074] Figure 3 is an example diagram of an information exchange method according to an embodiment of the present application. For example, an AI / ML model can be deployed on the UE side, the calculation and model monitoring modules can also be deployed on the UE side, and the model training module can be deployed on the LMF side. Figure 3 shows an example of how model attributes are transferred between the UE and the LMF.

[0075] As shown in Figure 3, after the UE determines to start training (301), it can send a request message to start training to the LMF (302). The LMF sends a model-related information request for optimizing the wireless positioning AI / ML model to the UE (303); in addition, the LMF receives model-related information feedback sent by the UE (304).

[0076] For example, the UE performs model supervision (or monitoring) and determines to start the model training process; the UE requests the LMF to start the training process through LPP signaling; the LMF sends the required model information to the UE through the relevant information request process specified in the relevant protocol.

[0077] It is worth noting that FIG3 above is merely a schematic illustration of an embodiment of the present application, and the present application is not limited thereto. For example, the execution order of the various operations may be appropriately adjusted, and other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above description, and are not limited to the description of FIG3 above.

[0078] In some embodiments, the model-related information (or also referred to as model capability information, model-related information, training-specific information, etc., used to provide assistance for model training) request and / or the model-related information feedback includes: neural network model basic information and / or neural network model related information.

[0079] For example, the basic information of the neural network model includes at least one of the following: model size information, model type information, model format information, model layer information, model required storage space information, number of neurons in each layer, neuron organization information, and neuron arrangement information; the neural network model related information includes model encoding method information and / or model storage format information.

[0080] In some embodiments, the model-related information request and / or the model-related information feedback includes at least one of the following: model input information, statistical information corresponding to model input data, model output information, statistical information corresponding to model output data or other data.

[0081] For example, the model input information includes at least one of the following: model input type, time used for model training, and input status.

[0082] For example, the statistical information corresponding to the model input data includes at least one of the following: global power distribution information of the channel impulse response (CIR), partial power distribution information of the CIR, global time distribution information of the channel impulse response (CIR), partial time distribution information of the CIR, CIR average power information, CIR maximum power information, CIR first peak information, non-radio intervention technology (NON-RAT) method information, NON-RAT method delay information, reference signal received power (RSRP) information based on reference signal measurement, and RSRP distribution statistical information.

[0083] For example, the statistical information corresponding to the model output data or other data includes at least one of the following: non-line-of-sight (NLOS) probability distribution information of each propagation path between the network device and the terminal device pair, NLOS probability ratio information, line-of-sight (LOS) probability distribution information, LOS probability ratio information, arrival time (TOA) absolute distribution information corresponding to each propagation path, TOA relative distribution information, reference signal time difference (RSTD) statistical distribution information calculated from the reference source, and accuracy information of physical quantities measured in each channel.

[0084] In some embodiments, the model-related information request and / or the model-related information feedback include at least one of the following: model gradient optimization configuration algorithm information, model test accuracy information, model learning rate information, model convergence time information, and model loss function information.

[0085] The above is an exemplary description of model-related information request and / or model-related information feedback, but the present application is not limited thereto. For example, other information may also be included. In addition, one of the information may be used according to actual needs, or the above information may be arbitrarily combined.

[0086] In some embodiments, the interaction content can be specified by enhanced signaling of request capability. For example, taking LPP signaling as an example, the LMF can specify the interaction content by enhanced signaling of request capability, and the UE reports the capability according to the requirement.

[0087] For example, as shown in Table 1 below, for the interaction of model-related information, RequestCapabilities / ProvideCapabilities in the existing protocol is used as the framework; for another example, as shown in Table 2 below, for the interaction of model-related information, a new AI / ML model-specific IE can also be used.

[0088] Table 1

[0089]

[0090]

[0091] Table 2

[0092]

[0093] In some embodiments, an example of an IE for model-related information interaction is shown in Table 3 below, corresponding to the case of information interaction accompanied by the model ID, for example, an example of an IE for model-related information interaction transmitted together with the model ID is as follows:

[0094] Table 3

[0095]

[0096]

[0097]

[0098] In some embodiments, an example of an IE for model-related information interaction is shown in Table 4 below. For example, an example of an IE for model additional information interaction, for example, transmitted as model additional information, is as follows:

[0099] Table 4

[0100]

[0101] Tables 3 and 4 are only examples of some situations in which model-related information is exchanged, and the present application is not limited thereto. The specific contents of Tables 3 and 4 may include each other, and other forms may be used to exchange model-related information, which is not limited in the present application.

[0102] Another IE example of model-related information interaction is shown in Table 5 below, which is explained using model input information as an example.

[0103] Table 5

[0104]

[0105]

[0106] Another IE example of model-related information interaction is shown in Table 6 below, which uses CIR information as an example.

[0107] Table 6

[0108]

[0109] Another IE example of model-related information interaction is shown in Table 7 below, which takes NON-RAT information as an example.

[0110] Table 7

[0111]

[0112] The above examples illustrate the interaction of model-related information, but the present application is not limited thereto. New IEs may be defined or other IEs may be reused to interact with model-related information.

[0113] The above schematically illustrates the interaction of model-related information. The following describes the interaction of entity-related information.

[0114] In some embodiments, the first device is a location server and the second device is a terminal device; the location server sends an entity-related information request of the location server to the terminal device via LPP signaling, and the terminal device sends the entity-related information feedback to the location server via LPP signaling.

[0115] For example, the LMF (location server) sends the inherent attributes of its own entity or the attributes corresponding to the model to the UE (target device) through LPP signaling.

[0116] In some embodiments, the first device is a location server, and the second device is a base station or a network device; the location server sends an entity-related information request of the location server to the base station or the network device through NRPPa signaling, and the base station or the network device sends the entity-related information feedback to the location server through NRPPa signaling.

[0117] For example, the LMF (location server) sends the inherent attributes of its own entity or the attributes corresponding to the model to the gNB through NRPPa signaling.

[0118] In some embodiments, the first device is a base station or a network device, and the second device is a terminal device; the base station or network device sends an entity-related information request of the base station or network device to the terminal device through RRC signaling or downlink control information (DCI), and the terminal device sends the entity-related information feedback to the base station or network device through RRC signaling.

[0119] For example, the gNB transmits its own entity's inherent attributes or attributes corresponding to the model to the UE (target device) through signaling such as RRC / DCI.

[0120] In some embodiments, the first device is a base station or a network device, and the second device is a location server; the base station or network device sends an entity-related information request of the base station or network device to the location server through NRPPa signaling, and the location server sends the entity-related information feedback to the base station or network device through NRPPa signaling.

[0121] For example, gNB sends the inherent attributes of its own entity or the attributes corresponding to the model to LMF (location server) through NRPPa signaling.

[0122] In some embodiments, the first device receives a request message for starting training sent by the second device.

[0123] Figure 4 is an example diagram of an information exchange method according to an embodiment of the present application. For example, an AI / ML model can be deployed on the UE side, a calculation and model monitoring module can also be deployed on the UE side, and a training module can be deployed on the LMF side. Figure 4 shows an example of how entity attributes are transferred between the UE and the LMF.

[0124] As shown in Figure 4, after the UE determines to start training (401), it can send a request message to start training to the LMF (402). The LMF sends an entity-related information request (403) to the UE for optimizing the wireless positioning AI / ML model; in addition, the LMF receives entity-related information feedback (404) sent by the UE.

[0125] It is worth noting that FIG4 above is merely a schematic illustration of an embodiment of the present application, and the present application is not limited thereto. For example, the execution order of the various operations may be appropriately adjusted, and other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above description, and are not limited to the description of FIG4 above.

[0126] In some embodiments, the entity-related information (or entity capability information, entity ancillary information, training-specific information, etc., used to assist model training) request includes at least one of the following: hardware capability information, entity status information, model training software version information, training permission information, training adjustment information, and training rejection information. This application is not limited to this, and any combination of the above information may be used, or other information may also be included.

[0127] For example, the UE performs model supervision and determines whether to start the training process; the LMF transmits local entity information to the UE, and the content transmitted may include: local software and hardware resource information or local comprehensive time-frequency resource allocation information; comprehensive judgments and suggestions are made based on the above capabilities. For example, if the hardware capability requirements are too high, a signaling to refuse to start training can be directly sent.

[0128] In some embodiments, the entity-related information feedback includes at least one of the following: training data collection information, data configuration information, training re-request information, information requesting to send more entity capabilities, information requesting to initiate model selection, and information requesting to initiate a fallback. The present application is not limited thereto, and any combination of the above information may be used, or other information may be included.

[0129] For example, the FEEDBACK performed by the UE based on the relevant information of the LMF may include: management signaling of the training process, such as suspension, termination, etc.; data collection configuration signaling corresponding to the training process; and signaling of other comprehensive capabilities.

[0130] In some embodiments, the interaction content can be specified by enhanced signaling of request capability. For example, taking LPP signaling as an example, the LMF can specify the interaction content by enhanced signaling of request capability, and the UE reports the capability according to the requirement.

[0131] In the manner shown in Table 1, an example of an IE for entity-related information interaction is shown in Table 8:

[0132] Table 8

[0133]

[0134]

[0135] The above examples illustrate the interaction of entity-related information, but the present application is not limited thereto. New IEs may be defined or other IEs may be reused to perform entity-related information interaction.

[0136] The above schematically illustrates the interaction between model-related information and entity-related information. The following describes the interaction between auxiliary information.

[0137] In some embodiments, the first device sends auxiliary information for AI / ML model training to the second device; and the first device receives feedback information sent by the second device.

[0138] In some embodiments, the first device is a location server, and the second device is a terminal device; the location server sends the auxiliary information to the terminal device through LPP signaling, and the terminal device sends the feedback information to the location server through LPP signaling.

[0139] For example, the LMF (location server) transmits assistance information or decision information to the UE (target device) through LPP signaling.

[0140] In some embodiments, the first device is a location server, and the second device is a base station or a network device; the location server sends the auxiliary information to the base station through NRPPa signaling, and the base station or network device sends the feedback information to the location server through NRPPa signaling.

[0141] For example, the LMF (location server) delivers assistance information or decision information to the gNB through NRPPa signaling.

[0142] In some embodiments, the first device is a base station or a network device, and the second device is a terminal device; the base station or network device sends the auxiliary information to the terminal device through RRC signaling or DCI, and the terminal device sends the feedback information to the base station or network device through RRC signaling.

[0143] For example, the gNB transmits auxiliary information or decision information to the UE (target device) through signaling such as RRC / DCI.

[0144] In some embodiments, the first device is a base station or a network device, and the second device is a location server; the base station or the network device sends the auxiliary information to the location server through NRPPa signaling, and the location server sends the feedback information to the base station or the network device through NRPPa signaling.

[0145] For example, gNB transmits auxiliary information or decision information to LMF (location server) through NRPPa signaling.

[0146] In some embodiments, the interaction of auxiliary information can be performed independently or in combination with the aforementioned interaction of model-related information and / or entity-related information. For example, the first device can perform a comprehensive estimation or calculation based on the collected model-related information and entity-related information, and transmit the additional auxiliary information to the second device, thereby assisting in functions such as training data collection or supervision.

[0147] Figure 5 is another example diagram of the information exchange method according to an embodiment of the present application. For example, the AI / ML model can be deployed on the UE side, the calculation and model monitoring module can also be deployed on the UE side, and the model training module can be deployed on the LMF side. Figure 5 shows an example of auxiliary information transmission between the UE and the LMF.

[0148] As shown in Figure 5, after the UE determines to start model training (501), it can send a request message to start training to the LMF (502). The LMF sends a model-related information request and / or entity-related information request (503) to the UE for optimizing the wireless positioning AI / ML model; in addition, the LMF receives model-related information feedback and / or entity-related information feedback sent by the UE (504).

[0149] As shown in FIG5 , the LMF sends auxiliary information ( 505 ) for optimizing the wireless positioning AI / ML model to the UE; in addition, the LMF receives feedback information ( 506 ) sent by the UE.

[0150] For example, the UE performs model supervision and determines to start the model training process; the LMF and the UE exchange information; the LMF obtains auxiliary information that can be used to support data collection or model optimization training based on the reported and locally known relevant information and passes it to the UE.

[0151] It is worth noting that FIG5 above is merely a schematic illustration of an embodiment of the present application, and the present application is not limited thereto. For example, the execution order of the various operations may be appropriately adjusted, and other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above description, and are not limited to the description of FIG5 above.

[0152] In some embodiments, the auxiliary information includes at least one of the following: the time required for model training, the resource consumption required for model training, the accuracy that can be achieved by model training, the time required for data collection, model training strategy configuration information, training time estimation information, training accuracy estimation information, training data collection time estimation information, and training resource estimation information. The present application is not limited to this, and any combination of the above information may be used, or other information may also be included.

[0153] For example, the auxiliary information may include: the time required for model training to complete (single or multiple rounds); the resource overhead required for model training; the approximate model accuracy achievable through model training; and the approximate time required for data collection. Based on the received auxiliary information, the UE configures data collection or model training or performs other signaling interactions.

[0154] In some embodiments, assistance information interaction can be achieved through RequestAssistanceData and ProvideAssistanceData. An example of IE for assistance information interaction is shown in Table 9 below:

[0155] Table 9

[0156]

[0157]

[0158] In some embodiments, auxiliary information interaction can be achieved through ModelTrainingAssistanceInfo. An example of IE for auxiliary information interaction is shown in Table 10 below:

[0159] Table 10

[0160]

[0161] The above examples illustrate auxiliary information interaction, but the present application is not limited thereto. New IEs may be defined or other IEs may be reused to perform auxiliary information interaction.

[0162] The above schematically illustrates the interaction of auxiliary information. The following further illustrates the interaction of online data.

[0163] In some embodiments, the first device receives request information sent by the second device for requesting online data collection; and the first device performs resource configuration according to the request information.

[0164] In some embodiments, the first device receives feedback information sent by the second device; wherein the second device generates the feedback information after performing reference signal measurement according to the resource configuration.

[0165] In some embodiments, the interaction of online data may be performed independently or in combination with the aforementioned model-related information interaction and / or entity-related information interaction.

[0166] Figure 6 is another example diagram of the information exchange method according to an embodiment of the present application. For example, the AI / ML model can be deployed on the UE side, the calculation and model monitoring module can also be deployed on the UE side, and the model training module can be deployed on the LMF side. Figure 6 shows an example of online data transmission between the UE and the LMF.

[0167] As shown in Figure 6, after the UE determines to start training (601), it can send a request message to start training to the LMF (602). The LMF sends a model-related information request and / or entity-related information request for optimizing the wireless positioning AI / ML model to the UE (603); in addition, the LMF receives model-related information feedback and / or entity-related information feedback sent by the UE (604).

[0168] As shown in Figure 6, the UE sends a request message for online data collection to the LMF (605); the LMF configures resources for the UE (606), for example, by sending information to coordinate RSs to the gNB and the UE; the UE performs measurements based on the RSs (607), which are, for example, sent by the gNB to the UE based on the configuration information; in addition, the LMF receives feedback information sent by the UE (608).

[0169] It is worth noting that FIG6 above is merely a schematic illustration of an embodiment of the present application, and the present application is not limited thereto. For example, the execution order of the various operations may be appropriately adjusted, and other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above description, and are not limited to the description of FIG6 above.

[0170] In some embodiments, the request information further includes at least one of the following: expected sample data volume information, data dimension information, data collection duration threshold information, expected data accuracy information, reference signal configuration information for data collection, and reference signal selection information for data collection. The present application is not limited thereto, and any combination of the above information may be used, or other information may be included.

[0171] In some embodiments, the feedback information includes at least one of the following: data collection termination information, data re-collection information, data collection failure information, initiation model selection information, initiation rollback information. The present application is not limited thereto, and any combination of the above information may be used, or other information may also be included.

[0172] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0173] According to an embodiment of the present application, a first device sends a model-related information request and / or entity-related information request for optimizing a wireless positioning AI / ML model to a second device; and the first device receives model-related information feedback and / or entity-related information feedback sent by the second device. As a result, information exchange can be performed between network entities involved in positioning and / or between network entities and terminals, thereby enabling customized training for optimizing wireless positioning AI / ML models. The AI / ML models used for wireless positioning have better performance or better generalization, thereby enabling more accurate positioning results.

[0174] Embodiments of the second aspect

[0175] The embodiment of the present application provides an information interaction method, which is described from the perspective of the second device. The embodiment of the second aspect corresponds to the embodiment of the first aspect, and the same contents are not repeated here.

[0176] In an embodiment of the present application, the second device receives a model-related information request and / or an entity-related information request for optimizing the wireless positioning AI / ML model from the first device; and the second device sends model-related information feedback and / or entity-related information feedback to the first device.

[0177] In some embodiments, the first device is a location server and the second device is a terminal device; the location server sends the model-related information request to the terminal device via LPP signaling, and the terminal device sends the model-related information feedback to the location server via LPP signaling.

[0178] In some embodiments, the first device is a location server, and the second device is a base station or a network device; the location server sends the model-related information request to the base station through NRPPa signaling, and the base station sends the model-related information feedback to the location server through NRPPa signaling.

[0179] In some embodiments, the first device is a base station or a network device, and the second device is a terminal device; the base station or the network device sends the model-related information request to the terminal device through RRC signaling, and the terminal device sends the model-related information feedback to the base station or the network device through RRC signaling.

[0180] In some embodiments, the method further includes: the second device sending a request message to start training to the first device.

[0181] In some embodiments, the model-related information request and / or the model-related information feedback includes: neural network model basic information and / or neural network model related information.

[0182] In some embodiments, the basic information of the neural network model includes at least one of the following: model size information, model type information, model format information, model layer information, model storage space required information, number of neurons in each layer information, neuron organization information, and neuron arrangement information;

[0183] The neural network model related information includes model encoding method information and / or model storage format information.

[0184] In some embodiments, the model-related information request and / or the model-related information feedback includes at least one of the following: model input information, statistical information corresponding to model input data, model output information, statistical information corresponding to model output data or other data.

[0185] In some embodiments, the model input information includes at least one of the following: model input type, time used for model training, and input status.

[0186] In some embodiments, the statistical information corresponding to the model input data includes at least one of the following: global power distribution information of a channel impulse response (CIR), partial power distribution information of the CIR, global time distribution information of a channel impulse response (CIR), partial time distribution information of the CIR, CIR average power information, CIR maximum power information, CIR first peak information, NON-RAT method information, NON-RAT method delay information, RSRP information based on reference signal measurement, and RSRP distribution statistics;

[0187] The statistical information corresponding to the model output data or other data includes at least one of the following: non-line of sight (NLOS) probability distribution information of each propagation path between the network device and the terminal device pair, NLOS probability ratio information, line of sight (LOS) probability distribution information, LOS probability ratio information, arrival time (TOA) absolute distribution information corresponding to each propagation path, TOA relative distribution information, reference signal time difference (RSTD) statistical distribution information calculated from a reference source, and accuracy information of physical quantities measured in each channel.

[0188] In some embodiments, the model-related information request and / or the model-related information feedback include at least one of the following: model gradient optimization configuration algorithm information, model test accuracy information, model learning rate information, model convergence time information, and model loss function information.

[0189] In some embodiments, the first device is a location server and the second device is a terminal device; the location server sends an entity-related information request of the location server to the terminal device via LPP signaling, and the terminal device sends the entity-related information feedback to the location server via LPP signaling.

[0190] In some embodiments, the first device is a location server, and the second device is a base station or a network device; the location server sends an entity-related information request of the location server to the base station or the network device through NRPPa signaling, and the base station or the network device sends the entity-related information feedback to the location server through NRPPa signaling.

[0191] In some embodiments, the first device is a base station or a network device, and the second device is a terminal device; the base station or network device sends an entity-related information request of the base station or network device to the terminal device through RRC signaling or DCI, and the terminal device sends the entity-related information feedback to the base station or network device through RRC signaling.

[0192] In some embodiments, the first device is a base station or a network device, and the second device is a location server; the base station or network device sends an entity-related information request of the base station or network device to the location server through NRPPa signaling, and the location server sends the entity-related information feedback to the base station or network device through NRPPa signaling.

[0193] In some embodiments, the method further includes: the second device sending a request message to start training to the first device.

[0194] In some embodiments, the entity-related information request includes at least one of the following: hardware capability information, entity status information, model training software version information, allow training information, adjust training information, and reject training information.

[0195] In some embodiments, the entity-related information feedback includes at least one of the following: training data collection information, data configuration information, training re-request information, information requesting to send more entity capabilities, information requesting to initiate model selection, and information requesting to initiate rollback.

[0196] In some embodiments, the method further includes: the second device receiving auxiliary information for AI / ML model training from the first device; and the second device sending feedback information to the first device.

[0197] In some embodiments, the first device is a location server, and the second device is a terminal device; the location server sends the auxiliary information to the terminal device through LPP signaling, and the terminal device sends the feedback information to the location server through LPP signaling.

[0198] In some embodiments, the first device is a location server, and the second device is a base station or a network device; the location server sends the auxiliary information to the base station through NRPPa signaling, and the base station or network device sends the feedback information to the location server through NRPPa signaling.

[0199] In some embodiments, the first device is a base station or a network device, and the second device is a terminal device; the base station or network device sends the auxiliary information to the terminal device through RRC signaling or DCI, and the terminal device sends the feedback information to the base station or network device through RRC signaling.

[0200] In some embodiments, the first device is a base station or a network device, and the second device is a location server; the base station or the network device sends the auxiliary information to the location server through NRPPa signaling, and the location server sends the feedback information to the base station or the network device through NRPPa signaling.

[0201] In some embodiments, the auxiliary information includes at least one of the following: the time required for model training, the resource overhead required for model training, the accuracy that can be achieved by model training, the time required for data collection, model training strategy configuration information, training time estimation information, training accuracy estimation information, training data collection time estimation information, and training resource estimation information.

[0202] In some embodiments, the method further includes: the second device sending request information for requesting online data collection to the first device; wherein the first device performs resource configuration according to the request information.

[0203] In some embodiments, the request information also includes at least one of the following: expected sample data volume information, data dimension information, data collection time threshold information, expected data accuracy information, reference signal configuration information for data collection, and reference signal selection information for data collection.

[0204] In some embodiments, the method further includes: the second device generating feedback information after performing reference signal measurement according to the resource configuration; and the second device sending the feedback information to the first device.

[0205] In some embodiments, the feedback information includes at least one of the following: data collection termination information, data re-collection information, data collection failure information, initiation model selection information, and initiation rollback information.

[0206] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0207] According to an embodiment of the present application, a first device sends a model-related information request and / or entity-related information request for optimizing a wireless positioning AI / ML model to a second device; and the first device receives model-related information feedback and / or entity-related information feedback sent by the second device. As a result, information exchange can be performed between network entities involved in positioning and / or between a network entity and a terminal, thereby enabling customized training for optimizing the wireless positioning AI / ML model. The AI / ML model used for wireless positioning has better performance or better generalization, thereby enabling more accurate positioning results.

[0208] Embodiments of the third aspect

[0209] An embodiment of the present application provides an information interaction device, which may be, for example, the aforementioned first device, or may be one or more components or assemblies configured on the first device.

[0210] Figure 7 is a schematic diagram of the information interaction device of an embodiment of the present application. Since the principle of solving the problem by the information interaction device is the same as the method of the embodiment of the first aspect, its specific implementation can refer to the embodiment of the first aspect, and the same content will not be repeated.

[0211] As shown in FIG7 , the information interaction device 700 of the embodiment of the present application includes:

[0212] A sending unit 701 (or transmitter) sends a model-related information request and / or an entity-related information request for optimizing a wireless positioning AI / ML model to a second device; and

[0213] The receiving unit 702 (or called a receiver) receives the model-related information feedback and / or entity-related information feedback sent by the second device.

[0214] In some embodiments, the first device is a location server, and the second device is a terminal device; the location server sends the model-related information request to the terminal device via LPP signaling, and the terminal device sends the model-related information feedback to the location server via LPP signaling;

[0215] Alternatively, the first device is a location server, and the second device is a base station or a network device; the location server sends the model related information request to the base station through NRPPa signaling, and the base station sends the model related information feedback to the location server through NRPPa signaling;

[0216] Alternatively, the first device is a base station or a network device, and the second device is a terminal device; the base station or the network device sends the model-related information request to the terminal device through RRC signaling, and the terminal device sends the model-related information feedback to the base station or the network device through RRC signaling.

[0217] In some embodiments, the receiving unit 702 further receives a request message for starting training sent by the second device.

[0218] In some embodiments, the model-related information request and / or the model-related information feedback includes: neural network model basic information and / or neural network model related information.

[0219] In some embodiments, the basic information of the neural network model includes at least one of the following: model size information, model type information, model format information, model layer information, model storage space required information, number of neurons in each layer information, neuron organization information, and neuron arrangement information;

[0220] The neural network model related information includes model encoding method information and / or model storage format information.

[0221] In some embodiments, the model-related information request and / or the model-related information feedback includes at least one of the following: model input information, statistical information corresponding to model input data, model output information, statistical information corresponding to model output data or other data.

[0222] In some embodiments, the model input information includes at least one of the following: model input type, time used for model training, and input status.

[0223] In some embodiments, the statistical information corresponding to the model input data includes at least one of the following: global power distribution information of a channel impulse response (CIR), partial power distribution information of the CIR, global time distribution information of a channel impulse response (CIR), partial time distribution information of the CIR, CIR average power information, CIR maximum power information, CIR first peak information, NON-RAT method information, NON-RAT method delay information, RSRP information based on reference signal measurement, and RSRP distribution statistics;

[0224] The statistical information corresponding to the model output data or other data includes at least one of the following: non-line of sight (NLOS) probability distribution information of each propagation path between the network device and the terminal device pair, NLOS probability ratio information, line of sight (LOS) probability distribution information, LOS probability ratio information, arrival time (TOA) absolute distribution information corresponding to each propagation path, TOA relative distribution information, reference signal time difference (RSTD) statistical distribution information calculated from a reference source, and accuracy information of physical quantities measured in each channel.

[0225] In some embodiments, the model-related information request and / or the model-related information feedback include at least one of the following: model gradient optimization configuration algorithm information, model test accuracy information, model learning rate information, model convergence time information, and model loss function information.

[0226] In some embodiments, the first device is a location server, and the second device is a terminal device; the location server sends an entity-related information request of the location server to the terminal device through LPP signaling, and the terminal device sends the entity-related information feedback to the location server through LPP signaling;

[0227] Alternatively, the first device is a location server, and the second device is a base station or a network device; the location server sends an entity related information request of the location server to the base station or the network device through NRPPa signaling, and the base station or the network device sends the entity related information feedback to the location server through NRPPa signaling;

[0228] Alternatively, the first device is a base station or a network device, and the second device is a terminal device; the base station or the network device sends an entity related information request of the base station or the network device to the terminal device through RRC signaling or DCI, and the terminal device sends the entity related information feedback to the base station or the network device through RRC signaling;

[0229] Alternatively, the first device is a base station or a network device, and the second device is a location server; the base station or network device sends an entity-related information request of the base station or network device to the location server through NRPPa signaling, and the location server sends the entity-related information feedback to the base station or network device through NRPPa signaling.

[0230] In some embodiments, the receiving unit 702 further receives a request message for starting training sent by the second device.

[0231] In some embodiments, the entity-related information request includes at least one of the following: hardware capability information, entity status information, model training software version information, allow training information, adjust training information, and reject training information;

[0232] The entity-related information feedback includes at least one of the following: training data collection information, data configuration information, training re-request information, information requesting to send more entity capabilities, information requesting to initiate model selection, and information requesting to initiate rollback.

[0233] In some embodiments, the sending unit 701 further sends auxiliary information for AI / ML model training to the second device; and the receiving unit 702 further receives feedback information sent by the second device.

[0234] In some embodiments, the first device is a location server, and the second device is a terminal device; the location server sends the auxiliary information to the terminal device through LPP signaling, and the terminal device sends the feedback information to the location server through LPP signaling;

[0235] Alternatively, the first device is a location server, and the second device is a base station or a network device; the location server sends the auxiliary information to the base station through NRPPa signaling, and the base station or network device sends the feedback information to the location server through NRPPa signaling;

[0236] Alternatively, the first device is a base station or a network device, and the second device is a terminal device; the base station or the network device sends the auxiliary information to the terminal device through RRC signaling or DCI, and the terminal device sends the feedback information to the base station or the network device through RRC signaling;

[0237] Alternatively, the first device is a base station or a network device, and the second device is a location server; the base station or the network device sends the auxiliary information to the location server through NRPPa signaling, and the location server sends the feedback information to the base station or the network device through NRPPa signaling.

[0238] In some embodiments, the auxiliary information includes at least one of the following: the time required for model training, the resource overhead required for model training, the accuracy that can be achieved by model training, the time required for data collection, model training strategy configuration information, training time estimation information, training accuracy estimation information, training data collection time estimation information, and training resource estimation information.

[0239] In some embodiments, the receiving unit 702 further receives request information sent by the second device for requesting online data collection; and the first device performs resource configuration according to the request information.

[0240] In some embodiments, the request information also includes at least one of the following: expected sample data volume information, data dimension information, data collection time threshold information, expected data accuracy information, reference signal configuration information for data collection, and reference signal selection information for data collection.

[0241] In some embodiments, the receiving unit 702 further receives feedback information sent by the second device; wherein the second device generates the feedback information after performing reference signal measurement according to the resource configuration.

[0242] In some embodiments, the feedback information includes at least one of the following: data collection termination information, data re-collection information, data collection failure information, initiation model selection information, and initiation rollback information.

[0243] In addition, for the sake of simplicity, FIG7 only illustrates the connection relationship or signal direction between various components or modules. However, it should be clear to those skilled in the art that various related technologies such as bus connection can be used. The above-mentioned components or modules can be implemented by hardware facilities such as processors, memories, transmitters, and receivers; the implementation of this application is not limited to this.

[0244] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0245] According to an embodiment of the present application, a first device sends a model-related information request and / or entity-related information request for optimizing a wireless positioning AI / ML model to a second device; and the first device receives model-related information feedback and / or entity-related information feedback sent by the second device. As a result, information exchange can be performed between network entities involved in positioning and / or between a network entity and a terminal, thereby enabling customized training for optimizing the wireless positioning AI / ML model. The AI / ML model used for wireless positioning has better performance or better generalization, thereby enabling more accurate positioning results.

[0246] Embodiments of the fourth aspect

[0247] An embodiment of the present application provides an information interaction device, which may be, for example, the aforementioned second device, or may be one or more components or assemblies configured on the second device.

[0248] Figure 8 is a schematic diagram of the information interaction device of an embodiment of the present application. Since the principle of solving the problem by the information interaction device is the same as the method of the embodiment of the second aspect, its specific implementation can refer to the embodiments of the first and second aspects, and the same contents will not be repeated.

[0249] As shown in FIG8 , the information interaction device 800 of the embodiment of the present application includes:

[0250] A receiving unit 801 receives a model-related information request and / or an entity-related information request for optimizing a wireless positioning AI / ML model from a first device; and

[0251] A sending unit 802 sends model-related information feedback and / or entity-related information feedback to the first device.

[0252] In addition, for the sake of simplicity, FIG8 only illustrates the connection relationship or signal direction between various components or modules. However, it should be clear to those skilled in the art that various related technologies such as bus connection can be used. The above-mentioned components or modules can be implemented by hardware facilities such as processors, memories, transmitters, and receivers; the implementation of this application is not limited to this.

[0253] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0254] According to an embodiment of the present application, a first device sends a model-related information request and / or entity-related information request for optimizing a wireless positioning AI / ML model to a second device; and the first device receives model-related information feedback and / or entity-related information feedback sent by the second device. As a result, information exchange can be performed between network entities involved in positioning and / or between a network entity and a terminal, thereby enabling customized training for optimizing the wireless positioning AI / ML model. The AI / ML model used for wireless positioning has better performance or better generalization, thereby enabling more accurate positioning results.

[0255] Embodiments of the fifth aspect

[0256] An embodiment of the present application provides a communication system. Figure 1 is a schematic diagram of the communication system of the embodiment of the present application. As shown in Figure 1, the communication system 100 includes a network device 101, a terminal device 102 and a positioning server 103. For simplicity, Figure 1 only uses one network device and one terminal device as an example for illustration, but the embodiment of the present application is not limited to this.

[0257] In some embodiments, the communication system includes:

[0258] A first device that sends a model-related information request and / or an entity-related information request for optimizing a wireless positioning AI / ML model; and receives model-related information feedback and / or entity-related information feedback;

[0259] The second device receives the model-related information request and / or the entity-related information request; and sends the model-related information feedback and / or the entity-related information feedback.

[0260] An embodiment of the present application further provides an electronic device, which is, for example, the aforementioned first device or second device.

[0261] Figure 9 is a schematic diagram of the electronic device according to an embodiment of the present application. As shown in Figure 9, electronic device 900 may include a processor 910 (e.g., a central processing unit (CPU)) and a memory 920 coupled to processor 910. Memory 920 may store various data and may also store an information processing program 930, which is executed under the control of processor 910.

[0262] For example, the processor 910 may be configured to execute a program to implement the information interaction method as described in the embodiment of the first aspect. For example, the processor 910 may be configured to perform the following control: sending a model-related information request and / or an entity-related information request for optimizing a wireless positioning AI / ML model to a second device; and receiving model-related information feedback and / or entity-related information feedback sent by the second device.

[0263] For another example, the processor 910 may be configured to execute a program to implement the information interaction method as described in the embodiment of the second aspect. For example, the processor 910 may be configured to perform the following control: receiving a model-related information request and / or an entity-related information request for optimizing a wireless positioning AI / ML model from a first device; and sending model-related information feedback and / or entity-related information feedback to the first device.

[0264] In addition, as shown in FIG9 , the electronic device 900 may further include: a transceiver 940 and an antenna 950; wherein, the functions of the above components are similar to those in the prior art and are not further described here. It is worth noting that the electronic device 900 does not necessarily include all the components shown in FIG9 ; in addition, the electronic device 900 may also include components not shown in FIG9 , and reference may be made to the prior art for details.

[0265] An embodiment of the present application also provides a computer-readable program, wherein when the program is executed in a first device, the program enables a computer to execute the information interaction method described in the embodiment of the first aspect in the first device.

[0266] An embodiment of the present application also provides a storage medium storing a computer-readable program, wherein the computer-readable program enables a computer to execute the information interaction method described in the embodiment of the first aspect in a first device.

[0267] An embodiment of the present application also provides a computer-readable program, wherein when the program is executed in a second device, the program enables the computer to execute the information interaction method described in the embodiment of the second aspect in the second device.

[0268] An embodiment of the present application also provides a storage medium storing a computer-readable program, wherein the computer-readable program enables a computer to execute the information interaction method described in the embodiment of the second aspect in a second device.

[0269] The above devices and methods of the present application can be implemented by hardware or by a combination of hardware and software. The present application relates to such a computer-readable program that, when executed by a logic component, enables the logic component to implement the devices or components described above, or enables the logic component to implement the various methods or steps described above. The logic component is, for example, a field programmable logic component, a microprocessor, a processor used in a computer, etc. The present application also relates to a storage medium for storing the above program, such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, etc.

[0270] The method / device described in conjunction with the embodiments of the present application can be directly embodied as hardware, a software module executed by a processor, or a combination of the two. For example, one or more of the functional block diagrams shown in the figure and / or one or more combinations of functional block diagrams can correspond to various software modules of the computer program flow or to various hardware modules. These software modules can respectively correspond to the various steps shown in the figure. These hardware modules can be implemented by solidifying these software modules, for example, using a field programmable gate array (FPGA).

[0271] The software module may be located in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. A storage medium may be coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium; or the storage medium may be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The software module may be stored in the memory of the mobile terminal or in a memory card that can be inserted into the mobile terminal. For example, if the device (such as a mobile terminal) uses a large-capacity MEGA-SIM card or a large-capacity flash memory device, the software module may be stored in the MEGA-SIM card or the large-capacity flash memory device.

[0272] One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may be implemented as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or any appropriate combination thereof for performing the functions described in this application. One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0273] The present application has been described above in conjunction with specific embodiments. However, those skilled in the art should understand that these descriptions are merely illustrative and are not intended to limit the scope of protection of the present application. Those skilled in the art may make various modifications and variations to the present application based on the spirit and principles of the present application, and such modifications and variations are also within the scope of the present application.

[0274] Regarding the above implementation methods disclosed in this embodiment, the following additional notes are also disclosed:

[0275] 1. An information interaction method, comprising:

[0276] The first device sends a model-related information request and / or an entity-related information request for optimizing the wireless positioning AI / ML model to the second device; and

[0277] The first device receives model-related information feedback and / or entity-related information feedback sent by the second device.

[0278] 2. The method according to Note 1, wherein the first device is a location server and the second device is a terminal device; the location server sends the model-related information request to the terminal device through LPP signaling, and the terminal device sends the model-related information feedback to the location server through LPP signaling.

[0279] 3. The method according to Note 1, wherein the first device is a location server, and the second device is a base station or a network device; the location server sends the model-related information request to the base station through NRPPa signaling, and the base station sends the model-related information feedback to the location server through NRPPa signaling.

[0280] 4. The method according to Note 1, wherein the first device is a base station or a network device, and the second device is a terminal device; the base station or the network device sends the model-related information request to the terminal device through RRC signaling, and the terminal device sends the model-related information feedback to the base station or the network device through RRC signaling.

[0281] 5. The method according to any one of Notes 2 to 4, wherein the method further comprises:

[0282] The first device receives a request message for starting training sent by the second device.

[0283] 6. The method according to any one of Notes 2 to 5, wherein the model-related information request and / or the model-related information feedback includes: neural network model basic information and / or neural network model related information.

[0284] 7. The method according to Note 6, wherein the basic information of the neural network model includes at least one of the following: model size information, model type information, model format information, model layer information, model storage space required information, number of neurons in each layer, neuron organization information, and neuron arrangement information;

[0285] The neural network model related information includes model encoding method information and / or model storage format information.

[0286] 8. A method according to any one of Notes 2 to 7, wherein the model-related information request and / or the model-related information feedback includes at least one of the following: model input information, statistical information corresponding to model input data, model output information, statistical information corresponding to model output data or other data.

[0287] 9. The method according to Supplementary Note 8, wherein:

[0288] The model input information includes at least one of the following: model input type, model training time, and input status;

[0289] The statistical information corresponding to the model input data includes at least one of the following: global power distribution information of a channel impulse response (CIR), partial power distribution information of the CIR, global time distribution information of a channel impulse response (CIR), partial time distribution information of the CIR, CIR average power information, CIR maximum power information, CIR first peak information, NON-RAT method information, NON-RAT method delay information, RSRP information based on reference signal measurement, and RSRP distribution statistics;

[0290] The statistical information corresponding to the model output data or other data includes at least one of the following: non-line of sight (NLOS) probability distribution information of each propagation path between the network device and the terminal device pair, NLOS probability ratio information, line of sight (LOS) probability distribution information, LOS probability ratio information, arrival time (TOA) absolute distribution information corresponding to each propagation path, TOA relative distribution information, reference signal time difference (RSTD) statistical distribution information calculated from a reference source, and accuracy information of physical quantities measured in each channel.

[0291] 10. A method according to any one of Notes 2 to 9, wherein the model-related information request and / or the model-related information feedback includes at least one of the following: model gradient optimization configuration algorithm information, model test accuracy information, model learning rate information, model convergence time information, and model loss function information.

[0292] 11. The method according to Note 1, wherein the first device is a location server and the second device is a terminal device; the location server sends an entity-related information request of the location server to the terminal device through LPP signaling, and the terminal device sends the entity-related information feedback to the location server through LPP signaling.

[0293] 12. The method according to Note 1, wherein the first device is a location server, and the second device is a base station or a network device; the location server sends an entity-related information request of the location server to the base station or the network device through NRPPa signaling, and the base station or the network device sends the entity-related information feedback to the location server through NRPPa signaling.

[0294] 13. The method according to Note 1, wherein the first device is a base station or a network device, and the second device is a terminal device; the base station or the network device sends an entity-related information request of the base station or the network device to the terminal device through RRC signaling or DCI, and the terminal device sends the entity-related information feedback to the base station or the network device through RRC signaling.

[0295] 14. The method according to Note 1, wherein the first device is a base station or a network device, and the second device is a location server; the base station or network device sends an entity-related information request of the base station or network device to the location server through NRPPa signaling, and the location server sends the entity-related information feedback to the base station or network device through NRPPa signaling.

[0296] 15. The method according to any one of Notes 11 to 14, wherein the method further comprises:

[0297] The first device receives a request message for starting training sent by the second device.

[0298] 16. A method according to any one of Notes 11 to 15, wherein the entity-related information request includes at least one of the following: hardware capability information, entity status information, model training software version information, training permission information, training adjustment information, and training rejection information.

[0299] 17. A method according to any one of Notes 11 to 16, wherein the entity-related information feedback includes at least one of the following: training data collection information, data configuration information, training re-request information, information requesting to send more entity capabilities, information requesting to initiate model selection, and information requesting to initiate rollback.

[0300] 18. The method according to any one of Notes 1 to 17, wherein the method further comprises:

[0301] The first device sends auxiliary information for AI / ML model training to the second device; and

[0302] The first device receives feedback information sent by the second device.

[0303] 19. The method according to Note 18, wherein the first device is a location server and the second device is a terminal device; the location server sends the auxiliary information to the terminal device through LPP signaling, and the terminal device sends the feedback information to the location server through LPP signaling.

[0304] 20. The method according to Note 18, wherein the first device is a location server, and the second device is a base station or a network device; the location server sends the auxiliary information to the base station through NRPPa signaling, and the base station or network device sends the feedback information to the location server through NRPPa signaling.

[0305] 21. The method according to Note 18, wherein the first device is a base station or a network device, and the second device is a terminal device; the base station or the network device sends the auxiliary information to the terminal device through RRC signaling or DCI, and the terminal device sends the feedback information to the base station or the network device through RRC signaling.

[0306] 22. The method according to Note 18, wherein the first device is a base station or a network device, and the second device is a location server; the base station or the network device sends the auxiliary information to the location server through NRPPa signaling, and the location server sends the feedback information to the base station or the network device through NRPPa signaling.

[0307] 23. A method according to any one of Notes 18 to 22, wherein the auxiliary information includes at least one of the following: the time required for model training, the resource overhead required for model training, the accuracy that can be achieved by model training, the time required for data collection, model training strategy configuration information, training time estimation information, training accuracy estimation information, training data collection time estimation information, and training resource estimation information.

[0308] 24. The method according to any one of Notes 1 to 23, wherein the method further comprises:

[0309] The first device receives the request information sent by the second device for requesting online data collection; and

[0310] The first device performs resource configuration according to the request information.

[0311] 25. The method according to Note 24, wherein the request information also includes at least one of the following: expected sample data volume information, data dimension information, data collection time threshold information, expected data accuracy information, reference signal configuration information for data collection, and reference signal selection information for data collection.

[0312] 26. The method according to Supplementary Note 24, further comprising:

[0313] The first device receives feedback information sent by the second device; wherein the second device generates the feedback information after performing reference signal measurement according to the resource configuration.

[0314] 27. The method according to Note 26, wherein the feedback information includes at least one of the following: data collection termination information, data re-collection information, data collection failure information, initiation model selection information, and initiation rollback information.

[0315] 28. An information interaction method, comprising:

[0316] The second device receives a model-related information request and / or an entity-related information request for optimizing the wireless positioning AI / ML model from the first device; and

[0317] The second device sends model-related information feedback and / or entity-related information feedback to the first device.

[0318] 29. The method according to Note 28, wherein the first device is a location server and the second device is a terminal device; the location server sends the model-related information request to the terminal device through LPP signaling, and the terminal device sends the model-related information feedback to the location server through LPP signaling.

[0319] 30. The method according to Note 28, wherein the first device is a location server, and the second device is a base station or a network device; the location server sends the model-related information request to the base station through NRPPa signaling, and the base station sends the model-related information feedback to the location server through NRPPa signaling.

[0320] 31. The method according to Note 28, wherein the first device is a base station or a network device, and the second device is a terminal device; the base station or the network device sends the model-related information request to the terminal device through RRC signaling, and the terminal device sends the model-related information feedback to the base station or the network device through RRC signaling.

[0321] 32. The method according to any one of Notes 29 to 31, further comprising:

[0322] The second device sends a request message for starting training to the first device.

[0323] 33. A method according to any one of Notes 29 to 32, wherein the model-related information request and / or the model-related information feedback includes: neural network model basic information and / or neural network model related information.

[0324] 34. The method according to note 33, wherein the basic information of the neural network model includes at least one of the following: model size information, model type information, model format information, model layer information, model storage space required information, number of neurons in each layer, neuron organization information, and neuron arrangement information;

[0325] The neural network model related information includes model encoding method information and / or model storage format information.

[0326] 35. A method according to any one of Notes 29 to 34, wherein the model-related information request and / or the model-related information feedback includes at least one of the following: model input information, statistical information corresponding to model input data, model output information, statistical information corresponding to model output data or other data.

[0327] 36. The method according to Note 35, wherein:

[0328] The model input information includes at least one of the following: model input type, model training time, and input status;

[0329] The statistical information corresponding to the model input data includes at least one of the following: global power distribution information of a channel impulse response (CIR), partial power distribution information of the CIR, global time distribution information of a channel impulse response (CIR), partial time distribution information of the CIR, CIR average power information, CIR maximum power information, CIR first peak information, NON-RAT method information, NON-RAT method delay information, RSRP information based on reference signal measurement, and RSRP distribution statistics;

[0330] The statistical information corresponding to the model output data or other data includes at least one of the following: non-line of sight (NLOS) probability distribution information of each propagation path between the network device and the terminal device pair, NLOS probability ratio information, line of sight (LOS) probability distribution information, LOS probability ratio information, arrival time (TOA) absolute distribution information corresponding to each propagation path, TOA relative distribution information, reference signal time difference (RSTD) statistical distribution information calculated from a reference source, and accuracy information of physical quantities measured in each channel.

[0331] 37. A method according to any one of Notes 29 to 36, wherein the model-related information request and / or the model-related information feedback includes at least one of the following: model gradient optimization configuration algorithm information, model test accuracy information, model learning rate information, model convergence time information, and model loss function information.

[0332] 38. The method according to Note 28, wherein the first device is a location server and the second device is a terminal device; the location server sends an entity-related information request of the location server to the terminal device through LPP signaling, and the terminal device sends the entity-related information feedback to the location server through LPP signaling.

[0333] 39. The method according to Note 28, wherein the first device is a location server, and the second device is a base station or a network device; the location server sends an entity-related information request of the location server to the base station or the network device through NRPPa signaling, and the base station or the network device sends the entity-related information feedback to the location server through NRPPa signaling.

[0334] 40. The method according to Note 28, wherein the first device is a base station or a network device, and the second device is a terminal device; the base station or the network device sends an entity-related information request of the base station or the network device to the terminal device through RRC signaling or DCI, and the terminal device sends the entity-related information feedback to the base station or the network device through RRC signaling.

[0335] 41. The method according to Note 28, wherein the first device is a base station or a network device, and the second device is a location server; the base station or the network device sends an entity-related information request of the base station or the network device to the location server through NRPPa signaling, and the location server sends the entity-related information feedback to the base station or the network device through NRPPa signaling.

[0336] 42. The method according to any one of Notes 38 to 41, further comprising:

[0337] The second device sends a request message for starting training to the first device.

[0338] 43. A method according to any one of Notes 38 to 42, wherein the entity-related information request includes at least one of the following: hardware capability information, entity status information, model training software version information, allowed training information, adjusted training information, and rejected training information.

[0339] 44. A method according to any one of Notes 38 to 43, wherein the entity-related information feedback includes at least one of the following: training data collection information, data configuration information, training re-request information, information requesting to send more entity capabilities, information requesting to initiate model selection, and information requesting to initiate rollback.

[0340] 45. The method according to any one of Notes 28 to 44, further comprising:

[0341] The second device receives auxiliary information for AI / ML model training from the first device; and

[0342] The second device sends feedback information to the first device.

[0343] 46. ​​The method according to Note 45, wherein the first device is a location server and the second device is a terminal device; the location server sends the auxiliary information to the terminal device through LPP signaling, and the terminal device sends the feedback information to the location server through LPP signaling.

[0344] 47. The method according to Note 45, wherein the first device is a location server, and the second device is a base station or a network device; the location server sends the auxiliary information to the base station through NRPPa signaling, and the base station or network device sends the feedback information to the location server through NRPPa signaling.

[0345] 48. The method according to Note 45, wherein the first device is a base station or a network device, and the second device is a terminal device; the base station or the network device sends the auxiliary information to the terminal device through RRC signaling or DCI, and the terminal device sends the feedback information to the base station or the network device through RRC signaling.

[0346] 49. The method according to Note 45, wherein the first device is a base station or a network device, and the second device is a location server; the base station or the network device sends the auxiliary information to the location server through NRPPa signaling, and the location server sends the feedback information to the base station or the network device through NRPPa signaling.

[0347] 50. A method according to any one of Notes 45 to 49, wherein the auxiliary information includes at least one of the following: the time required for model training, the resource overhead required for model training, the accuracy that can be achieved by model training, the time required for data collection, model training strategy configuration information, training time estimation information, training accuracy estimation information, training data collection time estimation information, and training resource estimation information.

[0348] 51. The method according to any one of Notes 28 to 50, wherein the method further comprises:

[0349] The second device sends a request message for requesting online data collection to the first device; wherein the first device performs resource configuration according to the request message.

[0350] 52. The method according to Note 51, wherein the request information also includes at least one of the following: expected sample data volume information, data dimension information, data collection time threshold information, expected data accuracy information, reference signal configuration information for data collection, and reference signal selection information for data collection.

[0351] 53. The method according to Supplementary Note 51, wherein the method further comprises:

[0352] The second device generates feedback information after performing reference signal measurement according to the resource configuration; and

[0353] The second device sends the feedback information to the first device.

[0354] 54. The method according to Note 53, wherein the feedback information includes at least one of the following: data collection termination information, data re-collection information, data collection failure information, initiation model selection information, and initiation rollback information.

[0355] 55. An information interaction device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the information interaction method as described in any one of Notes 1 to 27.

[0356] 56. An information interaction device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the information interaction method as described in any one of Notes 28 to 54.

Claims

1. An information interaction device, configured in a first device, comprising: A sending unit, which sends a model-related information request and / or an entity-related information request for optimizing the wireless positioning AI / ML model to the second device; as well as A receiving unit receives model-related information feedback and / or entity-related information feedback sent by the second device.

2. The device according to claim 1, wherein: The first device is a location server, and the second device is a terminal device; the location server sends a request for the model related information to the terminal device through LPP signaling, and the terminal device sends feedback of the model related information to the location server through LPP signaling; Alternatively, the first device is a location server, and the second device is a base station or a network device; The location server sends the model related information request to the base station through NRPPa signaling, and the base station sends the model related information feedback to the location server through NRPPa signaling; Alternatively, the first device is a base station or a network device, and the second device is a terminal device; the base station or the network device sends the model-related information request to the terminal device through wireless resource control signaling, and the terminal device sends the model-related information feedback to the base station or the network device through wireless resource control signaling.

3. The device according to claim 2, wherein: The receiving unit also receives request information for starting training sent by the second device.

4. The device according to claim 2, wherein: The model-related information request and / or the model-related information feedback include: neural network model basic information and / or neural network model related information.

5. The device according to claim 4, wherein: The basic information of the neural network model includes at least one of the following: model size information, model type information, model format information, model layer information, model required storage space information, number of neurons in each layer, neuron organization information, and neuron arrangement information; The neural network model related information includes model encoding method information and / or model storage format information.

6. The device according to claim 2, wherein: The model-related information request and / or the model-related information feedback includes at least one of the following: model input information, statistical information corresponding to model input data, model output information, statistical information corresponding to model output data or other data.

7. The device according to claim 6, wherein: The model input information includes at least one of the following: model input type, model training time, and input status; The statistical information corresponding to the model input data includes at least one of the following: global power distribution information of channel impulse response, partial power distribution information of channel impulse response, global time distribution information of channel impulse response, partial time distribution information of channel impulse response, average power information of channel impulse response, maximum power information of channel impulse response, first peak information of channel impulse response, non-radio intervention technical method information, non-radio intervention technical method delay information, reference signal received power information based on reference signal measurement, and distribution statistical information of reference signal received power; The statistical information corresponding to the model output data or other data includes at least one of the following: non-line-of-sight probability distribution information, non-line-of-sight probability ratio information, line-of-sight probability distribution information, line-of-sight probability ratio information of each propagation path between a network device and a terminal device pair, absolute distribution information of arrival time corresponding to each propagation path, relative distribution information of arrival time, statistical distribution information of reference signal time difference calculated from a reference source, and accuracy information of physical quantities measured in each channel.

8. The device according to claim 2, wherein: The model-related information request and / or the model-related information feedback include at least one of the following: model gradient optimization configuration algorithm information, model test accuracy information, model learning rate information, model convergence time information, and model loss function information.

9. The device according to claim 1, wherein: The first device is a location server, and the second device is a terminal device; the location server sends an entity related information request of the location server to the terminal device through LPP signaling, and the terminal device sends the entity related information feedback to the location server through LPP signaling; Alternatively, the first device is a location server, and the second device is a base station or a network device; The location server sends an entity related information request of the location server to the base station or network device through NRPPa signaling, and the base station or network device sends the entity related information feedback to the location server through NRPPa signaling; Alternatively, the first device is a base station or a network device, and the second device is a terminal device; the base station or the network device sends an entity related information request of the base station or the network device to the terminal device through radio resource control signaling or downlink control information, and the terminal device sends the entity related information feedback to the base station or the network device through radio resource control signaling; Alternatively, the first device is a base station or a network device, and the second device is a location server; the base station or the network device sends an entity-related information request of the base station or the network device to the location server through NRPPa signaling, and the location server sends the entity-related information feedback to the base station or the network device through NRPPa signaling.

10. The device according to claim 9, wherein: The receiving unit also receives request information for starting training sent by the second device.

11. The device according to claim 9, wherein: The entity related information request includes at least one of the following: hardware capability information, entity status information, model training software version information, training permission information, training adjustment information, and training rejection information; The entity-related information feedback includes at least one of the following: training data collection information, data configuration information, training re-request information, information requesting to send more entity capabilities, information requesting to initiate model selection, and information requesting to initiate rollback.

12. The device according to claim 1, wherein: The sending unit further sends auxiliary information for AI / ML model training to the second device; and The receiving unit also receives feedback information sent by the second device.

13. The device according to claim 12, wherein: The first device is a location server, and the second device is a terminal device; the location server sends the auxiliary information to the terminal device through LPP signaling, and the terminal device sends the feedback information to the location server through LPP signaling; Alternatively, the first device is a location server, and the second device is a base station or a network device; The location server sends the auxiliary information to the base station through NRPPa signaling, and the base station or network device sends the feedback information to the location server through NRPPa signaling; Alternatively, the first device is a base station or a network device, and the second device is a terminal device; the base station or the network device sends the auxiliary information to the terminal device through radio resource control signaling or downlink control information, and the terminal device sends the feedback information to the base station or the network device through radio resource control signaling; Alternatively, the first device is a base station or a network device, and the second device is a location server; The base station or network device sends the auxiliary information to the location server through NRPPa signaling, and the location server sends the feedback information to the base station or network device through NRPPa signaling.

14. The device according to claim 12, wherein: The auxiliary information includes at least one of the following: the time required for model training, the resource overhead required for model training, the accuracy that can be achieved by model training, the time required for data collection, model training strategy configuration information, training time estimation information, training accuracy estimation information, training data collection time estimation information, and training resource estimation information.

15. The device according to claim 1, wherein: The receiving unit further receives request information sent by the second device for requesting online data collection; and the first device performs resource configuration according to the request information.

16. The device according to claim 15, wherein: The request information also includes at least one of the following: expected sample data volume information, data dimension information, data collection time threshold information, expected data accuracy information, reference signal configuration information for data collection, and reference signal selection information for data collection.

17. The device according to claim 15, wherein: The receiving unit further receives feedback information sent by the second device; wherein the second device generates the feedback information after performing reference signal measurement according to the resource configuration.

18. The device according to claim 17, wherein: The feedback information includes at least one of the following: data collection termination information, data re-collection information, data collection failure information, initiation model selection information, and initiation rollback information.

19. An information interaction device, configured in a second device, the information interaction device comprising: A receiving unit, which receives a model-related information request and / or an entity-related information request for optimizing a wireless positioning AI / ML model from a first device; as well as A sending unit, which sends model-related information feedback and / or entity-related information feedback to the first device.

20. A communication system comprising: A first device that sends a model-related information request and / or an entity-related information request for optimizing a wireless positioning AI / ML model; and receiving model-related information feedback and / or entity-related information feedback; The second device receives the model-related information request and / or the entity-related information request; and sends the model-related information feedback and / or the entity-related information feedback.

Images