Ai model-based positioning method and apparatus, device, and readable storage medium

Abstract

The present application relates to the field of communications, and discloses an AI model-based positioning method and apparatus, a device, and a readable storage medium. The method in embodiments of the present application comprises: a first device receives target information, wherein the first device is a first terminal or a positioning reference device, an AI model is deployed on the first device, the AI model is used for acquiring positioning related information, and the target information comprises AI model related information.

Description

Positioning method, device, equipment and readable storage medium based on AI model

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on November 23, 2023, with application number 202311581766.9 and invention name “Positioning method, device, equipment and readable storage medium based on AI model”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application belongs to the field of communication technology, and specifically relates to a positioning method, apparatus, device and readable storage medium based on an AI model. Background Art

[0003] In related technologies, it is considered to deploy artificial intelligence (AI) models on positioning reference units (PRUs) and terminals, and use AI models to locate the terminals. In this case, how to improve the positioning accuracy of the terminals is an urgent problem that needs to be solved. Summary of the Invention

[0004] The embodiments of the present application provide a positioning method, apparatus, device, and readable storage medium based on an AI model, which can realize terminal positioning based on an AI model.

[0005] In a first aspect, a positioning method based on an AI model is provided, the method comprising: a first device receiving target information, the first device being a first terminal or a positioning reference device, an AI model being deployed on the first device, the AI ​​model being used to obtain positioning-related information, and the target information including AI model-related information.

[0006] In a second aspect, a positioning method based on an AI model is provided, the method comprising: a network side device sends target information to a first device, the first device is a first terminal or a positioning reference device, an AI model is deployed on the first device, the AI ​​model is used to obtain positioning-related information, and the target information includes AI model-related information.

[0007] In a third aspect, a positioning device based on an AI model is provided, comprising:

[0008] A communication unit is used to receive target information. An AI model is deployed on the positioning device, and the AI ​​model is used to obtain positioning-related information. The target information includes AI model-related information. The positioning device is a first terminal or a positioning reference device.

[0009] In a fourth aspect, a positioning device based on an AI model is provided, comprising:

[0010] A communication unit is used to send target information to a first device, where the first device is a first terminal or a positioning reference device. An AI model is deployed on the first device, and the AI ​​model is used to obtain positioning-related information. The target information includes AI model-related information.

[0011] In a fifth aspect, a communication device is provided, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the first aspect or the second aspect are implemented.

[0012] In a sixth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented.

[0013] In the seventh aspect, a wireless communication system is provided, including: a first device and a network side device, wherein the first device can be used to execute the steps of the method described in the first aspect, and the network side device can be used to execute the steps of the method described in the second aspect.

[0014] In an eighth aspect, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect, or to implement the method described in the second aspect.

[0015] In a ninth aspect, a computer program / program product is provided, wherein the computer program / program product is stored in a storage medium, and the program / program product is executed by at least one processor to implement the steps of the positioning method as described in the first aspect or the second aspect.

[0016] In an embodiment of the present application, the network side device can send AI model related information to the first device (for example, the first terminal (i.e., the terminal to be located, or the target terminal), the positioning reference device), so that the first device can obtain positioning related information based on the AI ​​model related information, thereby improving the positioning accuracy of the terminal positioning based on the AI ​​model. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0018] FIG2 is a schematic diagram of a neuron structure.

[0019] FIG3 is a schematic diagram of a neural network.

[0020] FIG4 is a schematic diagram of an AI model-based positioning method provided in an embodiment of the present application.

[0021] Figure 5 is a schematic diagram of another positioning method based on an AI model provided in an embodiment of the present application.

[0022] FIG6 is a schematic diagram of a positioning device provided in an embodiment of the present application.

[0023] FIG7 is a schematic diagram of another positioning device provided in an embodiment of the present application.

[0024] FIG8 is a schematic diagram of a communication device provided in an embodiment of the present application.

[0025] FIG9 is a hardware structure diagram of a terminal provided in an embodiment of the present application.

[0026] FIG10 is a hardware structure diagram of a network-side device provided in an embodiment of the present application.

[0027] FIG11 is a hardware structure diagram of another network-side device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will be combined with the accompanying drawings in the embodiments of this application to clearly describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0029] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same type, and do not limit the number of objects, for example, the first object can be one or more. In addition, "or" in this application represents at least one of the connected objects. For example, "A or B" covers three options, namely, Option 1: including A but not including B; Option 2: including B but not including A; Option 3: including both A and B. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0030] The term "indication" in this application can be either a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, the operation to be performed, or the requested result, etc. in the instruction sent; an indirect indication can be understood as the receiver determining the corresponding information based on the instruction sent by the sender, or making a judgment and determining the operation to be performed or the requested result, etc. based on the judgment result.

[0031] It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used for the systems and radio technologies mentioned above, as well as for other systems and radio technologies. The following description describes a New Radio (NR) system for example purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th Generation (6G) communication systems.

[0032] FIG1 is a block diagram of a wireless communication system applicable to an embodiment of the present application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 may be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile internet device (MID), an augmented reality (AR), a virtual reality (VR) device, a robot, a wearable device (Wearable Device), an aircraft (Flight Vehicle), a vehicle-mounted device (VUE), a ship-mounted device, a pedestrian user equipment (PUE), a smart home (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), a game console, a personal computer (PC), an ATM, or a self-service machine, or other terminal-side devices. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle-mounted device can also be called a vehicle-mounted terminal, vehicle-mounted controller, vehicle-mounted module, vehicle-mounted component, vehicle-mounted chip or vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application.

[0033] A terminal may also be called user equipment (UE), terminal device, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.

[0034] The network-side device 12 may include an access network device or a core network device, wherein the access network device may also be referred to as a radio access network (RAN) device, a radio access network function, or a radio access network unit. The access network device may include a base station, a wireless local area network (WLAN) access point (AS), or a wireless fidelity (WiFi) node. Among them, the base station can be referred to as Node B (NB), Evolved Node B (eNB), the next generation Node B (gNB), New Radio Node B (NR Node B), access point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B (home evolved Node B), Transmission Reception Point (TRP) or other appropriate terms in the field. As long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary. It should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.

[0035] The core network equipment may include but is not limited to at least one of the following: core network node, core network function, mobility management entity (MME), access mobility management function (AMF), session management function (SMF), user plane function (UPF), policy control function (PCF), policy and charging rules function unit (PCRF), edge application service discovery function (EASDF), unified data management (UDM), unified data repository (UDR), home subscriber server (HSS), centralized network configuration (CNC), network storage function (NRF), network exposure function (NEF), local NEF (L-NEF), binding support function (BSF), application function ( Function, AF), Location Management Function (LMF), positioning server, etc. It should be noted that in the embodiment of the present application, only the core network device in the NR system is introduced as an example, and the specific type of the core network device is not limited.But not limited to at least one of the following: core network node, core network function, Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized Network Configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (L-NEF), Binding Support Function (BSF), Application Function (AF), etc. It should be noted that in the embodiments of this application, only the core network equipment in the NR system is introduced as an example, and the specific type of the core network equipment is not limited.

[0036] To facilitate understanding of the embodiments of the present application, a Position Reference Unit (PRU) related to the present application is described.

[0037] By sending and receiving NR positioning reference signals and combining them with the known position-related information of the PRU, some errors in the positioning process can be removed, such as TRP position error, TRP phase and group delay, positioning reference signal group delay and / or phase error, etc.

[0038] To facilitate understanding of the embodiments of the present application, the positioning method based on simultaneous measurement related to the present application is described.

[0039] In some embodiments, a network side device, such as an LMF or a positioning server (Location Server, or service terminal), can send first time window information (i.e., measurement time window information) to the target terminal and PRU to instruct the target terminal and PRU to measure the signals used for positioning (e.g., positioning reference signals (PRS)) within the first time window.

[0040] In some embodiments, the first time window information sent by the LMF or positioning server to the target terminal and PRU is the same, and it is expected that the target terminal and PRU can simultaneously measure the PRS sent by the same device (e.g., TRP) within the first time window.

[0041] In some embodiments, the first time window information includes at least one of the following:

[0042] The length of the first time window, the period of the first time window, and the starting position of the first time window.

[0043] In order to understand the embodiments of the present application, the positioning method related to the present application is explained.

[0044] UE-based positioning method: LMF can collect the measurement results and / or location information of the PRU, and further forward the measurement results and / or location information of the PRU to the target terminal. The target terminal can determine its own location based on the measurement results and / or location information of the PRU.

[0045] UE-assisted or LMF-based positioning method: The PRU can report measurement results and / or location information to the LMF, and the target terminal also reports measurement results to the LMF. The LMF calculates the location of the target terminal based on the collected measurement results and / or the location information of the PRU.

[0046] The measurement results of the PRU may optionally include carrier phase measurement results, reference signal time difference (RSTD) measurement results, reference signal received power (RSRP), etc. Furthermore, the measurement results may be associated with at least one of the identification information of the measurement target and the measurement time. The identification information of the measurement target is the identification information of the TRP and / or signal corresponding to the measurement result of the PRU, such as the TRP ID, PRS identification information, etc.

[0047] To facilitate understanding of the embodiments of the present application, the AI ​​technology related to the present application is explained.

[0048] AI technology has been widely applied in various fields. Integrating AI technology into wireless communication networks to improve technical indicators such as throughput, latency, and user capacity is a key task for future wireless communication networks. AI models can be implemented in various ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. The following uses neural networks as an example, but does not limit the specific type of AI module. A neural network is a computational model composed of multiple interconnected neuron nodes. The connections between nodes represent the weighted values ​​from input signals to output signals, called weights. Each node performs a weighted summation (SUM) of different input signals and outputs them through a specific activation function (f). Figure 2 is a schematic diagram of a neuron structure, where a1, a2, …, an represent inputs, w1, w2, …, wn represent weights (multiplicative coefficients), b represents bias (additive coefficient), σ represents the activation function, and y represents the output. Here, z = a1*w1+a2*w2+ …+an*wn+b. Common activation functions include Sigmoid, tanh, ReLU (Rectified Linear Unit), etc.

[0049] A typical neural network, shown in Figure 3, consists of an input layer, hidden layers, and an output layer. Different connections, weights, and activation functions among multiple neurons can produce different outputs, thereby fitting the mapping relationship from input to output. Each node in the previous level is connected to all nodes in the next level. This neural network is a fully connected neural network, also known as a deep neural network (DNN).

[0050] Deep learning utilizes deep neural networks with multiple hidden layers, significantly improving the network's ability to learn features and fitting complex, nonlinear mappings from input to output. Consequently, it has found widespread application in speech and image processing. In addition to deep neural networks, deep learning also includes other commonly used basic structures such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) for different tasks.

[0051] Neural network parameters are optimized using a gradient optimization algorithm. Gradient optimization algorithms are a class of algorithms that minimize or maximize an objective function (also known as a loss function), which is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, a neural network model f(.) can be constructed. With this model, the output f(x) can be predicted based on the input x, and the difference between the predicted value and the true value (f(x) - Y) can be calculated. This is the loss function. Our goal is to find the appropriate values ​​W and b to minimize the loss function. The smaller the loss value, the closer our model is to the true value.

[0052] Common optimization algorithms currently used include those based on the back propagation (BP) algorithm. The basic concept of the BP algorithm is that the learning process consists of two steps: forward propagation of signals and back propagation of errors. During forward propagation, input samples are passed from the input layer, processed layer by layer by each hidden layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, the error begins back propagation. Back propagation involves propagating the output error back through the hidden layers to the input layer layer by layer in some form, distributing the error to all units in each layer. This error signal is then generated for each unit in each layer, which serves as the basis for correcting the weights of each unit. This process of adjusting the weights of each layer through forward propagation of signals and back propagation of errors is repeated over and over again. This process of continuous weight adjustment is the network's learning and training process. This process continues until the error in the network output is reduced to an acceptable level, or until a pre-set number of learning cycles is reached.

[0053] Common optimization algorithms may include, but are not limited to, gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum, Nesterov (name of the inventor, specifically stochastic gradient descent with momentum), Adagrad (ADAptive GRADient descent), Adadelta, RMSprop (root mean square prop), Adam (Adaptive Moment Estimation), etc.

[0054] When these optimization algorithms backpropagate errors, they calculate the derivative / partial derivative of the current neuron based on the error / loss obtained by the loss function, add the influence of the learning rate, the previous gradient / derivative / partial derivative, etc., obtain the gradient, and pass the gradient to the previous layer.

[0055] In some scenarios, consider introducing AI models into positioning scenarios to improve positioning accuracy. In positioning scenarios based on simultaneous measurement, how to introduce AI models? For both devices participating in simultaneous measurement, if the models used are significantly different, additional errors caused by the differences in AI models will be introduced, thereby reducing the performance gain brought by simultaneous measurement.

[0056] The following describes in detail the AI ​​model-based positioning method provided in the embodiments of the present application through some embodiments and their application scenarios in conjunction with the accompanying drawings.

[0057] FIG4 is a schematic interactive diagram of a positioning method based on an AI model provided in an embodiment of the present application. As shown in FIG4 , the method 400 may include at least part of the following:

[0058] S401, the network side device sends target information to the first device;

[0059] Accordingly, the first device receives target information from the network-side device;

[0060] Among them, the first device is a first terminal or a positioning reference device, and an AI model is deployed on the first device. The AI ​​model is used to obtain positioning-related information, and the target information includes AI model-related information.

[0061] Further, S402, the first device uses the AI ​​model related information in the target information to obtain positioning related information.

[0062] In some embodiments, the first device may be a first terminal or a positioning reference device, wherein the first terminal may be a terminal to be positioned, or referred to as a target UE.

[0063] In the embodiments of the present application, a positioning reference device may refer to a device for which location-related information is known. The location-related information may include, but is not limited to, direction information, distance information, at least one of absolute position and relative position. The positioning reference device may be, for example, a PRU, an anchor UE, a reference UE, etc.

[0064] In some embodiments, the first terminal and the positioning reference device are receiving devices of the reference signal.

[0065] In the embodiment of the present application, the reference signal may refer to a signal used for positioning, for example, including but not limited to PRS, CSI-RS, etc. The following description takes the reference signal as PRS as an example, but the present application is not limited to this.

[0066] In some embodiments, the first terminal and the positioning reference device may measure the PRS based on the same or similar PRS measurement configuration (eg, measurement time window, or PRS configuration information (eg, including sequence information), etc.).

[0067] For example, the time window used by the first terminal for PRS measurement and the time window used by the positioning reference device for PRS measurement may be the same, partially overlap, or be adjacent. For example, the network-side device may schedule the first terminal and the positioning reference device to perform PRS measurement in the same time slot or adjacent time slots.

[0068] In some embodiments, the first terminal may measure the PRS based on the first time window information, and the positioning reference device may also measure the PRS based on the first time window information, where the first time window information is used to indicate that the PRS is to be measured within the first time window. That is, the first terminal and the positioning reference device may measure the PRS based on the same time window, thereby enabling terminal positioning based on simultaneous measurements.

[0069] In some embodiments, the first time window information includes but is not limited to at least one of the following:

[0070] The length of the first time window, the period of the first time window, and the starting position of the first time window.

[0071] In some embodiments of the present application, S401 may specifically include:

[0072] When the first terminal and the positioning reference device measure the PRS based on the first time window information, the network side device sends target information to the first device, wherein the first device is the first terminal or the positioning reference device, an AI model is deployed on the first device, the AI ​​model is used to obtain positioning-related information, and the target information includes AI model-related information.

[0073] That is, in the scenario where terminal positioning is performed through simultaneous measurement in combination with the AI ​​model, the network-side device can send model-related information to both parties participating in the simultaneous measurement to assist the two parties participating in the simultaneous measurement to obtain positioning-related information through the AI ​​model based on the model-related information, thereby improving the positioning accuracy of simultaneous measurement based on the AI ​​model.

[0074] Optionally, the first time window information may be indicated by the network side device to the first terminal and the positioning reference device, and the first time window information indicated by the network side device to the first terminal and the positioning reference device is the same, and it is expected that the positioning reference device and the first terminal can simultaneously measure the PRS sent by the same sending end device within the first time window.

[0075] In some embodiments, the network side device may be an LMF, a positioning server (such as a service terminal), a base station, or other functional entities capable of providing positioning services, etc., which is not limited in this application.

[0076] It should be understood that the present application does not limit the positioning method used to locate the first terminal, for example, a positioning method based on signal arrival time, a positioning method based on signal arrival angle, a positioning method based on received signal strength, a positioning method based on signal arrival time difference (i.e., receive-transmit time difference (Rx-Tx time difference)), etc.

[0077] In some embodiments, based on different positioning methods, the PRS measurement results include but are not limited to at least one of the following:

[0078] Channel impulse response (CIR);

[0079] Power Delay Profile (PDP) of the channel;

[0080] Delay Profile (DP) of the channel;

[0081] Rx-Tx time difference;

[0082] Reference Signal Time Difference (RSTD);

[0083] Reference signal strength, such as reference signal receiving power (RSRP), reference signal receiving quality (RSRQ), and received signal strength indication (RSSI);

[0084] Angle of Arrival (AoA);

[0085] Time of arrival (ToA);

[0086] Line of Sight / Non-Line of Sight (LOS / NLOS identification) information.

[0087] Carrier phase measurement information, such as received signal channel power (RSCP) and reference signal carrier phase difference (RSCPD).

[0088] In some embodiments, an AI model is deployed on the first device, and the AI ​​model can obtain positioning-related information. The positioning-related information can be the final positioning result (e.g., the location information of the first terminal), or it can also be an intermediate processing result used to determine the final positioning result, such as measurement error information, where the measurement error information can be determined based on the measurement result of the positioning reference device on the PRS and the location information of the positioning reference device, or it can also be a processed measurement result. For example, if the first measurement result is PDP or CIR, the second measurement result can be time information between the transmitting node and the first device, such as TOA, RSTD, etc., obtained based on the first measurement result. For another example, if the first measurement result is PDP or CIR, the second measurement result can be whether the distance between the transmitting node and the first device is LOS or NLoS, obtained based on the first measurement result. For another example, if the first measurement result is PDP or CIR, the second location information is the location information of the first device obtained based on the first measurement result.

[0089] That is to say, in the embodiments of the present application, positioning can be performed directly based on the AI ​​model (direct AI positioning or AI-Based positioning), or positioning can be performed with the assistance of the AI ​​model (AI assisted positioning).

[0090] Optionally, for AI-assisted positioning, the first terminal may determine the final positioning result based on the intermediate processing result obtained, that is, obtain the second position result based on AI. Alternatively, the intermediate processing result may be sent to another device (e.g., LMF or positioning server), and the other device may determine the final positioning result based on the intermediate processing result, that is, obtain the second measurement result based on AI and report the second measurement result to the other device.

[0091] It should be understood that this application does not limit the number of AI models deployed on the first device. For example, the number of AI models used to implement the positioning function can be one or more.

[0092] In some embodiments of the present application, S401 may specifically include:

[0093] When the first terminal and the positioning reference device measure the PRS based on the first time window information, the network side device sends target information to the first device, wherein the first device is the first terminal or the positioning reference device, an AI model is deployed on the first device, the AI ​​model is used to obtain positioning-related information, the target information includes AI model-related information, and at least one of the information included in the target information is associated with the first time window information.

[0094] It should be noted that in the embodiments of the present application, the AI ​​model may also be referred to as an AI unit, an ML (machine learning) model, an ML unit, an AI structure, an AI function, an AI feature, a machine learning model, a neural network, a neural network function, a neural network function, etc., or an AI model may also refer to a processing unit that can implement specific algorithms, formulas, processing procedures, capabilities, etc. related to AI, or an AI model may be a processing method, algorithm, function, module or unit for a specific data set, or an AI model may be a processing method, algorithm, function, module or unit running on AI / ML related hardware such as a graphics processing unit (GPU), a neural network processing unit (NPU), a tensor processing unit (TPU), an application specific integrated circuit (ASIC), etc. This application does not make specific limitations on this.

[0095] In some embodiments, AI model related information may include but is not limited to configuration related to AI model usage, configuration related to AI model monitoring, positioning related information obtained using the AI ​​model, monitoring information of the AI ​​model, etc.

[0096] In some embodiments of the present application, the network-side device can indicate the same AI model-related information (such as configuration related to AI model usage, configuration related to AI model monitoring, etc.) to the first terminal and the positioning reference device. In this way, the first terminal and the positioning reference device can use and / or monitor the model based on the same configuration, thereby ensuring the performance gain brought about by using the AI ​​model to achieve positioning based on simultaneous measurements. It is understandable that the same configuration includes at least partial similarity, such as using the same AI function, such as using the same monitoring function, etc.

[0097] In this case, this application does not limit the sending device of the AI ​​model related information, as long as it can ensure that the AI ​​model related information indicated to the first terminal is consistent with the AI ​​model related information indicated to the positioning reference device.

[0098] The following describes the specific content of the AI ​​model related information in conjunction with Example 1.

[0099] Embodiment 1: The target information may include first information, and the first information includes model-related information.

[0100] In some embodiments, the first information includes at least one of the following:

[0101] Model configuration of AI models;

[0102] Input configuration of the AI ​​model;

[0103] Output configuration of AI models;

[0104] Configuration related to the first measurement result;

[0105] configuration related to the second measurement result;

[0106] Monitoring configuration of AI models;

[0107] Monitoring results of the AI ​​model.

[0108] The first measurement result is a measurement result that has not been processed by the AI ​​model, and the second measurement result is a measurement result that has been processed by the AI ​​model.

[0109] It should be understood that the first measurement result may include a known measurement result for positioning, or may also include a measurement result for positioning newly added as the standard evolves, and this application does not limit this.

[0110] Illustratively, the first measurement result includes at least one of the following:

[0111] CIR, PDP, DPSD, Rx-Tx time difference, RSTD, AoA, ToA, LOS / NLOS identification.

[0112] In some embodiments, the second measurement result is a measurement result obtained by applying an AI-related function, or a measurement result obtained by processing an AI model.

[0113] Optionally, the second measurement result includes at least one of the following:

[0114] Compressed CIR, PDP, DPSD;

[0115] Time information: such as TOA, RSTD, or Rx-Tx time difference

[0116] AoA;

[0117] LOS / NLOS identification.

[0118] In some embodiments, the model configuration of the AI ​​model can be used by the first terminal to determine the AI ​​model to use. The network-side device can indicate the same model configuration to the first terminal and the positioning reference device, so that the first terminal and the positioning reference device use the same AI model or an AI model with the same function to obtain positioning-related information.

[0119] Exemplarily, the model configuration of the AI ​​model includes but is not limited to at least one of the following:

[0120] Identification information of the AI ​​model;

[0121] Functional information of AI models;

[0122] Parameter information of the AI ​​model;

[0123] Update information of AI models;

[0124] Use cases for AI models;

[0125] Dataset information associated with the AI ​​model.

[0126] In some embodiments, the identification information of the AI ​​model is used by the first device to identify which model to use. The network-side device can enable the first terminal and the positioning reference device to use the same AI model to obtain positioning-related information by indicating the same model identifier to the first terminal and the positioning reference device.

[0127] Optionally, the identification information of the AI ​​model may be, for example, an AI model identifier (model ID), an AI structure identifier, an AI algorithm identifier, or an identifier of a specific data set associated with the AI ​​model, or an identifier of a specific scenario, environment, channel feature, or device related to AI / ML, or an identifier of an AI / ML-related function, feature, capability, or module. The present invention does not specifically limit this.

[0128] For example, multiple AI models are stored on the first device, and each AI model corresponds to corresponding identification information. The first device can select the corresponding AI model for positioning according to the identification information of the AI ​​model indicated by the network side device.

[0129] In some embodiments, the function information of the AI ​​model indicates, for example, the function of the AI ​​model. The network-side device indicates the same model function to the first terminal and the positioning reference device, so that the first terminal and the positioning reference device can use the same AI model to obtain positioning-related information.

[0130] For example, multiple AI models are stored on the first device, each AI model has a corresponding function, and the first device can select an AI model that meets the functional information of the AI ​​model indicated by the network side device for positioning.

[0131] Optionally, the function information of the AI ​​model may, for example, indicate that the AI ​​model supports positioning, supports beam management, supports CSI feedback, etc. Optionally, the function information of the AI ​​model may also indicate a specific positioning method supported by the AI ​​model, such as support for AI-assisted positioning, or support for direct AI-based positioning (direct AI positioning), etc.

[0132] Optionally, the model configuration of the AI ​​model includes data set information associated with the AI ​​model. For example, the target AI model used can be determined based on the data set currently acquired by the first terminal, that is, the target AI model is an AI model associated with the acquired data set.

[0133] In some embodiments, the parameter information of the AI ​​model may include, but is not limited to, the structural type information of the AI ​​model (such as CNN or RNN, etc.), the structural information of the AI ​​model (such as the number of layers of the AI ​​model, including specific layers, such as input layer, hidden layer, output layer, etc.), and the model parameters of the AI ​​model (such as the parameters of each layer of the AI ​​model, the gradient information of the model). For example, there are multiple AI models stored on the first device, and each AI model corresponds to a structural type. The first device can select the AI ​​model of the corresponding structural type according to the structural type information of the AI ​​model indicated by the network side device for positioning. For another example, there are multiple AI models stored on the first device, and each AI model corresponds to a set of structures. The first device can select the AI ​​model of the corresponding structure according to the structural information of the AI ​​model indicated by the network side device for positioning.

[0134] In some embodiments, the AI ​​model update information may include at least one of the following: AI model usage conditions, application scenario information, update cycle, functional information of the AI ​​model applicable to the current scenario, and information associated with the functional information. By indicating the same model update information to the first terminal and the positioning reference device, the network-side device can enable the first terminal and the positioning reference device to update the model based on the update information, thereby ensuring consistency between the models on the first terminal and the positioning reference device.

[0135] Optionally, the model configuration of the AI ​​model includes a usage scenario of the AI ​​model. For example, the target AI model to be used can be determined based on the scenario of the current first terminal.

[0136] Optionally, the use conditions of the AI ​​model are associated with certain communication indicators, for example, the AI ​​model can be used when the communication indicators meet certain conditions. Optionally, the communication indicators can be indicators related to channel quality, such as RSRP, RSRQ, signal-to-noise ratio (SNR) or signal to interference plus noise ratio (SINR). For example, the AI ​​model can be used when RSRP, RSRQ, SNR or SINR is within a certain range.

[0137] Optionally, the usage scenarios of the AI ​​model include, for example, the cell identifier, TRP identifier, data set identifier, sidelink (SL) positioning identifier (i.e., the AI ​​model is applicable to SL positioning), downlink (DL) positioning identifier (i.e., the AI ​​model is applicable to DL positioning), etc.

[0138] In some embodiments, the input configuration of the AI ​​model is used to indicate information related to the AI ​​model input, and the output configuration of the AI ​​model is used to indicate information related to the AI ​​model output. By indicating the same input configuration and / or output configuration to the first terminal and the positioning reference device, the network-side device can ensure that the first terminal and the positioning reference device use the same input configuration and / or output configuration when using the AI ​​model to obtain positioning-related information, thereby ensuring consistency in the AI ​​model output information.

[0139] Optionally, the input configuration may include which information can be used as input to the AI ​​model, or a method for selecting the input to the AI ​​model, for example, using the measurement result corresponding to the signal indicated in the target information as the input to the AI ​​model, or prioritizing the measurement result corresponding to the PRS indicated in the target information as a candidate for the input to the AI ​​model. Optionally, the input configuration may also include the type of input to the AI ​​model, for example, using the measurement result type indicated by the target information as the input to the AI ​​model.

[0140] Exemplarily, the input configuration of the AI ​​model includes but is not limited to at least one of the following:

[0141] The preprocessing method of the AI ​​model's input information, the format of the AI ​​model's input information, the type of the AI ​​model's input information, the size of the AI ​​model's input information, the identification information of the transmitting device associated with the AI ​​model's input information, and the identification information of the reference signal associated with the AI ​​model's input information.

[0142] Optionally, the preprocessing method of the input information of the AI ​​model may include, but is not limited to, whether to preprocess the input information, and the target preprocessing method used, such as truncation, extraction, quantization, etc. For example, if the truncation length of the input information of the AI ​​model configured in the target information is 32, the input information of the AI ​​model is a measurement result, and the length of the measurement result corresponding to a reference signal is 32 or less. For another example, if the indicated preprocessing method is quantization of 4 bits, the information reported at each time point is quantized using 4 bits. Optionally, the quantization method can be fixed-length quantization or variable-length quantization.

[0143] Optionally, the type of input information of the AI ​​model, such as TRP ID, measurement result, antenna ID, etc. Optionally, if the input information of the AI ​​model includes TRP ID or PRS identification information, it means that the input information of the AI ​​model is expected to include the measurement result associated with the above-mentioned TRP ID or PRS identification information as input. Optionally, if the type of input information of the AI ​​model indicates a specific measurement result (such as PDP or RSTD), it means that the input information of the AI ​​model is expected to be the measurement result of the above-mentioned specified type.

[0144] Optionally, the size of the input information of the AI ​​model may refer to the size of the input information, such as the number of TRPs, the number of antennas, the number of measurement results, etc. For example, if the number of TRPs is 8, the number of antennas is 1, the type of input information of the AI ​​model is a measurement result, the type of measurement result is PDP, and each TRP includes a maximum of 4 PDPs. Then the input information of the AI ​​model is 8*4 PDPs. If the preprocessing method of the input information of the AI ​​model is to specify that the truncation length of the PDP is 32, then the dimension of the input information of the AI ​​model is 8*4*32. (The size and order of the above information are only examples, but the present application is not limited to this.

[0145] Optionally, the format of the input information of the AI ​​model is used to indicate the composition and sorting of each piece of input information. For example, the format of the input information can be three-dimensional data: TRP ID*measurement result*antenna ID, or TRP ID*PRS ID*measurement result, etc.

[0146] Optionally, the identification information of the transmitting device associated with the input information of the AI ​​model is used to identify the transmitting device of the PRS corresponding to the measurement result associated with the input information. For example, the identification information may include one TRP ID, or may include multiple TRP IDs.

[0147] Optionally, the identification information of the PRS associated with the input information of the AI ​​model is used to identify the PRS corresponding to the measurement result associated with the input information. For example, the identification information may include a PRS ID, or may include multiple PRS IDs. The identification information of the PRS specifically includes: a PRX resource set ID (PRS resource set ID) and / or a PRS resource ID (PRS resource ID). That is, the PRS ID includes a PRS resource set ID and / or a PRS resource ID.

[0148] Exemplarily, the output configuration of the AI ​​model includes but is not limited to at least one of the following:

[0149] The post-processing method of the output information of the AI ​​model, the format of the output information of the AI ​​model, the type of the output information of the AI ​​model, the size of the output information of the AI ​​model, the identification information of the sending device associated with the output information of the AI ​​model, and the identification information of the PRS associated with the input information of the AI ​​model.

[0150] Optionally, the post-processing method of the output information may include but is not limited to whether to post-process the output information and the target post-processing method to be adopted, for example, decompression, extraction, etc. of the output information.

[0151] Optionally, the type of output information of the AI ​​model is, for example, a positioning result (e.g., position information), measurement error information, or a measurement result. Optionally, the type of the output information may indicate position information or a measurement result, and the measurement result may further be one or more of RSTD, ToA, Rx-Tx time difference, and carrer phase measurement.

[0152] Optionally, the size of the output information of the AI ​​model may refer to the size of the output information. For example, if the output information type is RSTD, the number of RSTDs may be indicated, such as being the same as the number of input information to the AI ​​model. For example, if the input is number of TRPs * number of PRS signals * PDPs, the output is number of TRPs * number of PRS signals * RSTDs. For example, if the output is 1 / N of the input, and the input is number of TRPs * number of PRS signals * PDPs, the output is number of TRPs * number of PRS signals / N * PDPs.

[0153] Optionally, the format of the output information of the AI ​​model is used to indicate the composition and sorting of the output information. For example, the format of the output information can be three-dimensional data: TRP ID*positioning result*antenna ID, or TRP ID*PRS ID*positioning result, etc.

[0154] Optionally, the identification information of the transmitting device associated with the output information of the AI ​​model is used to identify the transmitting device of the PRS corresponding to the measurement result associated with the output information. For example, the identification information may include one TRP ID, or may include multiple TRP IDs.

[0155] Optionally, the identification information of the PRS associated with the output information of the AI ​​model is used to identify the PRS corresponding to the measurement result associated with the output information. For example, the identification information may include a PRS ID, or may include multiple PRS IDs. The identification information of the PRS specifically includes: a PRS resource set ID (PRS resource set ID) and / or a PRS resource ID (PRS resource ID). That is, the PRS ID includes a PRS resource set ID and / or a PRS resource ID.

[0156] In some embodiments, the network side device may indicate the same configuration related to the first measurement result to the first terminal and the positioning reference device, which is conducive to ensuring that the first terminal and the positioning reference device measure the PRS based on the same configuration to obtain the first measurement result.

[0157] Exemplarily, the configuration related to the first measurement result includes but is not limited to at least one of the following:

[0158] Identification information of the PRS transmitter corresponding to the measurement result;

[0159] Identification information of the PRS corresponding to the measurement result;

[0160] identification information of the cell;

[0161] Timestamp information corresponding to the measurement results;

[0162] Measurement result reporting configuration.

[0163] Optionally, the identification information of the PRS transmitting device corresponding to the measurement result is used to identify the PRS transmitting device. For example, the identification information may include a TRP ID, or may include multiple TRP IDs. For example, the first device may measure the PRS transmitted by one or more TRPs associated with the identification information to obtain a first measurement result.

[0164] Optionally, the identification information of the PRS corresponding to the measurement result may be used to identify one or more PRSs. For example, the first device may measure the one or more PRSs associated with the identification information to obtain a first measurement result.

[0165] Optionally, the identification information of the cell identifies the cell, for example, the identification information may be a cell identifier (Cell ID), indicating that the first measurement result is obtained by measuring the PRS sent by the TRP in the cell.

[0166] Optionally, the reporting configuration of the measurement result may include but is not limited to at least one of the following:

[0167] Reporting format of measurement results;

[0168] The reporting time of the measurement results, such as the reporting cycle;

[0169] Quantitative information of the measurement results;

[0170] The number of signal samples corresponding to the measurement result, that is, the number of reference signals measured to obtain the measurement result;

[0171] The time window information corresponding to the measurement result, that is, the time window in which the reference signal is measured to obtain the measurement result;

[0172] The reporting type of the measurement result, for example, the reporting type can be the first measurement result or the second measurement result, and can be further divided into RSTD, AoA, RSRP, RSRQ, SINR, Rx-Tx time difference, carrier phase and other types.

[0173] In some embodiments, the network side device can indicate the same configuration related to the second measurement result to the first terminal and the positioning reference device, which is conducive to ensuring that the first terminal and the positioning reference device measure the PRS based on the same configuration, and process the measurement results based on the AI ​​model to obtain the second measurement result.

[0174] In some embodiments, the configuration related to the second measurement result includes at least one of the following:

[0175] Identification information of the transmitting device of the reference signal corresponding to the measurement result;

[0176] Identification information of the reference signal corresponding to the measurement result;

[0177] identification information of the cell;

[0178] AI model enabling information;

[0179] Configuration of preprocessing of measurement results;

[0180] Output configuration of measurement results;

[0181] Measurement result reporting configuration.

[0182] In some embodiments, the second measurement result includes at least one of the following:

[0183] Rx-Tx time difference, RSTD, AoA, ToA, LOS / NLOS identification, carrier phase.

[0184] In some embodiments, the second measurement result is associated with indication information, which is used to indicate that the second measurement result is a measurement result processed by AI.

[0185] Among them, the specific implementation of the identification information of the reference signal transmitting device corresponding to the measurement result, the identification information of the reference signal identification information cell, and the reporting configuration of the measurement result refers to the implementation method in the configuration related to the first measurement result. For the sake of brevity, it is not repeated here.

[0186] In some embodiments, identification information of a reference signal is associated with the first measurement result and the second measurement result. For example, the first device may report the first measurement result and the second measurement result, where the first measurement result and the second measurement result are associated with the identification information of the same reference signal.

[0187] In some embodiments, the first device may report only one of the first measurement result and the second measurement result. In this case, indication information may be used to indicate whether the reported measurement result is the first measurement result or the second measurement result.

[0188] In some embodiments, the enabling information of the AI ​​model may be used to indicate whether the AI ​​model is enabled, that is, whether the AI ​​model can be used to obtain positioning related information.

[0189] Optionally, the preprocessing configuration of the measurement result may include a configuration adopted for preprocessing the measurement result based on the AI ​​model, for example, including but not limited to at least one of the following:

[0190] The preprocessing method of the measurement results, which may include but is not limited to whether the measurement results are preprocessed and the target preprocessing method used, such as truncation, extraction, quantization, etc.;

[0191] Pre-processing of measurement results, such as converting measurement results into input information in a specific format.

[0192] Optionally, the output configuration of the measurement results may include the configuration of the output information obtained by processing the measurement results based on the AI ​​model, for example, including but not limited to the format of the output information, the post-processing method of the output information, and the reporting method of the output information, such as the reporting time, reporting format, reporting type, etc.

[0193] In some embodiments, the monitoring configuration of the AI ​​model is used by the first device to monitor the AI ​​model. The network-side device can indicate the same monitoring configuration to the first terminal and the positioning reference device, so that the first terminal and the positioning reference device can monitor the AI ​​model based on the same monitoring configuration, which helps ensure that the first terminal and the positioning reference device obtain the performance of the AI ​​model in a timely manner.

[0194] Exemplarily, the monitoring configuration of the AI ​​model includes but is not limited to at least one of the following:

[0195] Whether to conduct AI model monitoring;

[0196] The monitoring methods used to monitor AI models;

[0197] Time window information used for model monitoring (referred to as second time window information for ease of distinction and explanation);

[0198] The monitoring result type of the AI ​​model;

[0199] The monitoring result update cycle of the AI ​​model.

[0200] In some embodiments, the monitoring method used to monitor the AI ​​model may include, for example, monitoring based on network indications, that is, determining the validity of the AI ​​model based on network information; or terminal-based monitoring, that is, determining the validity of the AI ​​model based on terminal information. Optionally, the validity of the AI ​​model is determined by the relationship between the first measurement result and / or location information of the terminal and the output of the AI ​​model. Alternatively, monitoring based on data distribution, such as comparing the relationship between one or more input data of the AI ​​model and the data distribution associated with the AI ​​model to determine the validity of the model, if the deviation between the data exceeds a certain condition, the AI ​​model is considered invalid. Alternatively, the validity of the AI ​​model is determined based on the relationship between the input and output.

[0201] Optionally, the monitoring configuration of the AI ​​model can be indicated together with other configurations of the AI ​​model, or it can be configured separately. For example, the model configuration, input configuration, output configuration, monitoring configuration, etc. of the AI ​​model can be configured by the network side device to the first device when the first device obtains the AI ​​model from the network side device. For another example, the model configuration, input configuration, and output configuration of the AI ​​model can be configured when the first device obtains the AI ​​model from the network side device (such as a base station), and the monitoring configuration of the AI ​​model can be obtained from other devices (such as LMF or positioning terminal).

[0202] For example, if the monitoring of the AI ​​model is determined based on data distribution or the relationship between the input and output of the AI ​​model, the monitoring configuration of the AI ​​model may include: the aforementioned data distribution or the relationship between the input and output of the AI ​​model. Furthermore, the terminal and the PRU use the same data distribution to evaluate the effectiveness of the AI ​​model.

[0203] In some embodiments, the monitoring results of the AI ​​model include but are not limited to at least one of the following:

[0204] Indication of the effectiveness of AI models;

[0205] An indication of the effectiveness of the AI ​​model;

[0206] an indication of a score for the AI ​​model;

[0207] Sorting identifier of AI model;

[0208] Identification information of a valid AI model.

[0209] Optionally, the validity indication of the AI ​​model may be indicated by 1 bit, for example, a value of 0 for the 1 bit indicates that the AI ​​model is invalid, and a value of 1 indicates that the AI ​​model is valid.

[0210] Optionally, the effectiveness of the AI ​​model can be indicated using N bits. Different values ​​of the N bits are used to indicate different effectiveness levels of the AI ​​model. N can be determined based on the number of effectiveness levels. For example, if the effectiveness levels include 100%, 80%, 50%, and 20%, then 2 bits can be used to indicate the effectiveness levels of the four bits. A higher effectiveness level indicates a higher positioning accuracy that can be achieved using the AI ​​model for positioning.

[0211] Optionally, the score indication of the AI ​​model can be used to indicate the performance score of positioning using the AI ​​model, such as the positioning accuracy score. A higher score indicates a higher positioning accuracy that can be achieved using the AI ​​model for positioning. For example, the score indication of the AI ​​model can be indicated using M bits, and different values ​​of the M bits are used to indicate different scores of the AI ​​model. M can be determined based on the number of scores. For example, if the scores include 100, 80, 50, and 20, 2 bits can be used to indicate four-bit scores.

[0212] Optionally, the ranking identifier of the AI ​​model can be used to indicate the effectiveness order, effectiveness degree order, scoring order, etc. of the AI ​​model. The higher the ranking, the higher the effectiveness, the higher the score, or the better the performance of the AI ​​model.

[0213] Optionally, the effective AI model can be determined based on the monitoring results of multiple AI models.

[0214] Optionally, for the first terminal, the monitoring result of the AI ​​model included in the first information may be the monitoring result of the AI ​​model deployed on the positioning reference device, so that the first terminal can obtain the monitoring result of the AI ​​model deployed on the positioning reference device. Furthermore, the first terminal can determine, based on the monitoring result, whether to use the positioning-related information obtained by the positioning reference device using the AI ​​model to assist in the positioning of the first terminal.

[0215] For example, if the monitoring result of the AI ​​model deployed on the positioning reference device shows that the AI ​​model is effective, or the degree of effectiveness is higher than a certain threshold (for example, greater than or equal to 80%), or the score is higher than a certain threshold (for example, higher than 80 points), or the AI ​​model is ranked relatively high and the AI ​​model is an effective AI model, it is determined that the positioning reference device uses the positioning-related information obtained by the AI ​​model to assist in positioning the first terminal. Otherwise, the positioning reference device does not use the positioning-related information obtained by the AI ​​model to assist in positioning the first terminal.

[0216] In other embodiments of the present application, both devices performing simultaneous measurements can obtain information related to the AI ​​model used by the other party, and further determine whether the positioning-related information obtained by the other party is valid based on the information related to the AI ​​model used by the other party, or in other words, whether it can be used to assist in offsetting measurement errors. When the difference between the AI ​​models used by both parties is large, positioning based on positioning-related information obtained from models with large differences will introduce additional errors and reduce the performance gain brought by the AI ​​model. Therefore, when using the positioning-related information provided by the other party for positioning, obtaining information related to the AI ​​model used by the other party, and then assisting in judging the validity of the AI ​​model based on the AI ​​model-related information is beneficial to ensuring the accuracy of positioning based on the AI ​​model.

[0217] The following is another implementation of the target information in the embodiment of the present application in combination with Example 2.

[0218] Example 2:

[0219] In this embodiment 2, the first terminal and / or the positioning reference device may obtain information related to the AI ​​model used by the other party to obtain positioning related information. Optionally, the positioning reference device may also send the measured positioning related information or the positioning related information obtained based on the AI ​​model to the first terminal, so that the first terminal can assist in positioning the first terminal based on the positioning related information.

[0220] Below, in combination with Example 2-1 and Example 2-2, the specific implementation of the AI ​​model related information obtained by the first terminal and the positioning reference device is explained in detail.

[0221] Example 2-1: The first device is a first terminal, and the target information includes second information.

[0222] In some embodiments, the second information includes information related to the AI ​​model used by the positioning reference device.

[0223] In some embodiments, the first terminal can assist in judging the validity of the AI ​​model based on information related to the AI ​​model used by the positioning reference device, such as the similarity between the AI ​​model used by the positioning reference device and the AI ​​model used by the first terminal (for example, whether the functions are the same), and the performance of the AI ​​model used by the positioning reference device, which is conducive to ensuring the accuracy of positioning based on the AI ​​model.

[0224] In some embodiments, the second information includes at least one of the following:

[0225] a first measurement result obtained by the positioning reference device, where the first measurement result is a measurement result that has not been processed by the AI ​​model;

[0226] a second measurement result obtained by the positioning reference device, where the second measurement result is a measurement result processed by the AI ​​model;

[0227] First location information obtained by the positioning reference device, where the first location information is location information that has not been processed by the AI ​​model;

[0228] Second location information obtained by the positioning reference device, where the second location information is location information processed by the AI ​​model;

[0229] The third information is the AI ​​model related information used by the positioning reference device to obtain the positioning related information. For example, the third information includes the AI ​​model related information used by the positioning reference device to obtain at least one of the second measurement result and the second position information.

[0230] For example, the first measurement result may be a measurement result obtained by a positioning reference device through measurement, and the second measurement result may be a measurement result obtained by processing the first measurement result through an AI model.

[0231] In some embodiments, the third information includes at least one of the following:

[0232] Model configuration of the AI ​​model used by the positioning reference device;

[0233] The input configuration of the AI ​​model used by the positioning reference device;

[0234] The output configuration of the AI ​​model used by the positioning reference device;

[0235] Monitoring configuration of the AI ​​model used by the positioning reference device;

[0236] The monitoring results of the AI ​​model obtained by the positioning reference device.

[0237] Among them, the specific implementation of each configuration in the third information refers to the relevant description in the aforementioned embodiment, and for the sake of brevity, it will not be repeated here.

[0238] In some embodiments, the second information may be received by the first terminal from a network-side device, or may be received from a positioning reference device.

[0239] Example 2-2: The first device is a positioning reference device, the target information includes fourth information, and the fourth information includes information related to the AI ​​model used by the first terminal.

[0240] In some embodiments, the positioning reference device can configure the AI ​​model deployed on the positioning reference device based on the information related to the AI ​​model used by the first terminal, and further assist in positioning the first terminal based on the AI ​​model, which is conducive to ensuring the accuracy of positioning based on the AI ​​model.

[0241] In some embodiments, the fourth information includes AI model related information used by the first terminal to obtain at least one of the second measurement result and the second location information, wherein the second measurement result is a measurement result processed by the AI ​​model, and the second location information is location information processed by the AI ​​model.

[0242] In some embodiments, the fourth information includes at least one of the following:

[0243] a model configuration of the AI ​​model used by the first terminal;

[0244] an input configuration of the AI ​​model used by the first terminal;

[0245] an output configuration of the AI ​​model used by the first terminal;

[0246] The monitoring configuration of the AI ​​model used by the first terminal.

[0247] Among them, the specific implementation of each configuration in the fourth information refers to the relevant description in the aforementioned embodiment, and for the sake of brevity, it will not be repeated here.

[0248] In some embodiments, the fourth information may be received by the positioning reference device from the network side device, or may be received from the first terminal side.

[0249] In some embodiments, first time window information used by the first device to measure the PRS is associated with the target information.

[0250] In some specific embodiments, the first time window information is associated with the first information in Example 1.

[0251] For example, the first device performs measurement based on the first time window information to obtain a measurement result, and the measurement result can be processed based on the AI ​​model related information indicated by the first information.

[0252] In some further specific embodiments, the first time window information is associated with the first measurement result in embodiment 2-1.

[0253] For example, the first measurement result is a measurement result obtained by measuring based on the first time window information.

[0254] In some other specific embodiments, the first time window information is associated with the third information or the fourth information in Example 2.

[0255] For example, the measurement result obtained by the positioning reference device based on the first time window information can be processed based on the AI ​​model related information indicated by the third information.

[0256] For another example, the first terminal may process the measurement result obtained by performing measurement based on the first time window information based on the AI ​​model related information indicated by the fourth information.

[0257] In some embodiments of the present application, the method 400 further includes:

[0258] The network side device sends second time window information to the first device, where the second time window information is used to instruct the first device to monitor the AI ​​model within a second time window.

[0259] In some embodiments, the second time window information includes at least one of the following:

[0260] The period of the second time window, the starting position of the second time window, and the length of the second time window.

[0261] Optionally, when the first device only obtains part of the time window information, other information of the second time window may also be specified by the protocol, such as the length or period of the second time window.

[0262] Optionally, the starting position of the second time window may be an offset relative to the starting position of one cycle.

[0263] Optionally, the starting position of the second time window may be time information relative to a reference point, where the reference point may be the last symbol of the scheduling information for the scheduled PRS, or the last symbol of the time slot in which the PRS is scheduled. For example, the starting position may be an offset relative to the reference point.

[0264] In some embodiments of the present application, the second time window information is associated with the target information.

[0265] In some specific embodiments, the second time window information is associated with the first information in Example 1.

[0266] For example, the first device may monitor the AI ​​model determined based on the first information based on the second time window information.

[0267] In some other specific embodiments, the second time window information is associated with the third information or the fourth information in Example 2.

[0268] For example, the positioning reference device can monitor the AI ​​model determined based on the third information based on the second time window information.

[0269] For another example, the first terminal may monitor the AI ​​model determined based on the fourth information based on the second time window information.

[0270] In some embodiments of the present application, when the target information includes identification information of a PRS transmitter device and / or identification information of the PRS, the method 400 further includes:

[0271] The first device measures the identification information of the PRS transmitting device and / or the reference signal associated with the identification information of the PRS based on the first time window information, or preferentially measures the identification information of the PRS transmitting device and / or the reference signal associated with the identification information of the PRS.

[0272] Optionally, both the third information and the fourth information include identification information of the PRS transmitting device and / or identification information of the PRS, and when the identification information included in the third information and the fourth information is the same, it indicates that the first terminal and the positioning reference device measure the same transmitting device and / or PRS within the first time window.

[0273] For example, the third information or the fourth information may include identification information of multiple transmitting end devices, such as a TRP ID list, and the format of the input information of the AI ​​model may be sorted in the order of the TRP IDs in the TRP ID list. Specifically, for example, the input information includes the measurement results corresponding to the PRS sent by each TRP in the TRP ID list.

[0274] For another example, the third information or the fourth information may include identification information of multiple PRSs, such as a PRS ID list, and the format of the input information of the AI ​​model may be sorted in the order of the PRS IDs in the PRS ID list. Specifically, for example, the input information includes the measurement results corresponding to each PRS in the PRS ID list.

[0275] In some embodiments, when the target information includes identification information of a PRS transmitter device and / or identification information of the PRS, the input information of the AI ​​model is related to the identification information of the transmitter device and / or the identification information of the PRS. For example, the input information of the AI ​​model may include measurement results obtained by measuring the PRS associated with the identification information of the transmitter device and / or the identification information of the PRS.

[0276] In some embodiments, when the target information includes a reporting configuration of the measurement result, and the reporting configuration includes a reporting type, the method further includes:

[0277] The first device measures the PRS according to the first time window information to obtain a measurement result of the reporting type.

[0278] For example, if the indicated reporting type is RSTD, the first device may measure the PRS to obtain RSTD; or, if the indicated reporting type is RSRP, the first device may measure the PRS to obtain RSRP.

[0279] In some embodiments, the method 400 further includes:

[0280] If the first device does not obtain a measurement result, or the measurement result does not meet the first condition, measure the identification information of the PRS transmitting device or other reference signals other than the PRS associated with the identification information of the PRS, or set the corresponding measurement result information to predefined information.

[0281] Optionally, that the first device fails to obtain the measurement result may include that the first device fails to receive a PRS, or fails to receive a PRS associated with indicated identification information (eg, a TRP ID or a PRS ID).

[0282] That is, when the first device does not obtain the measurement result or the measurement result does not meet the conditions, the first device can measure other PRSs to obtain the measurement result, or set the corresponding measurement result as predefined information, which can be indicated by the network side device or specified by the protocol.

[0283] In some embodiments, the fact that the measurement result does not meet the first condition can be understood as poor signal quality between the first device and the PRS transmitting device. Therefore, the reliability of the measurement result is low, and positioning based on the measurement result may affect the accuracy of positioning. In this case, the measurement result can be ignored.

[0284] For example, the first condition includes but is not limited to at least one of the following:

[0285] The measurement result is less than the first threshold;

[0286] The channel condition corresponding to the measurement result is non-line-of-sight (NLOS);

[0287] The line-of-sight LOS probability corresponding to the measurement result is less than a second threshold.

[0288] Optionally, the measurement result being less than the first threshold may include, but is not limited to:

[0289] The measured RSRP is less than a first RSRP threshold;

[0290] The measured RSRQ is less than the first RSRQ threshold;

[0291] The measured SINR is less than the first SINR threshold;

[0292] The measured RSSI is less than the first RSSI threshold.

[0293] In some embodiments, the channel condition corresponding to the measurement result is NLOS, or the LOS probability of the measurement result is less than the second threshold, indicating that the first device and the PRS transmitting end device may be blocked, so the measurement result can be ignored.

[0294] In some embodiments of the present application, the method 400 further includes:

[0295] The network-side device obtains fifth information of at least one positioning reference device, where the fifth information includes at least one of a target measurement result obtained by the positioning reference device and target location information of the positioning reference device, the target measurement result information includes at least one second measurement result, and the target location information includes at least one second location information.

[0296] For example, the positioning reference device can use N AI models to obtain the second measurement results and / or second location information, such as obtaining N second measurement results and / or N second location information, and further report N1 second measurement results and / or N1 second location information to the network side device, where N is a positive integer and N1 is less than or equal to N.

[0297] In some embodiments, the fifth information is associated with at least one of the following:

[0298] The identification information of the AI ​​model in the target information and the functional information of the AI ​​model in the target information are associated. For example, the fifth information may be obtained using the AI ​​model indicated in the target information, or obtained using the AI ​​model with the function indicated in the target information.

[0299] For example, N1 second measurement results and / or N1 second location information reported by the positioning reference device are associated with N1 AI models, and each group of second measurement results and / or second location information is obtained using one AI model.

[0300] In some embodiments, the network side device can send the fifth information of the at least one positioning reference device to the first terminal, and the first terminal determines the monitoring results of the associated at least one AI model based on the fifth information of the at least one positioning device, and then determines the target AI model based on the monitoring results of the at least one AI model.

[0301] In other embodiments, the at least one positioning reference device may also send the fifth information directly to the first terminal, and then the first terminal determines the monitoring results of the associated at least one AI model based on the fifth information of the at least one positioning device, and then determines the target AI model based on the monitoring results of the at least one AI model.

[0302] In some embodiments of the present application, the method 400 further includes:

[0303] The network side device determines the monitoring result of at least one AI model associated with the fifth information based on the fifth information of the at least one positioning reference device.

[0304] For example, the network side device can determine the monitoring results of the associated N1 AI models based on the N1 second measurement results and / or N1 second location information reported by the positioning reference device.

[0305] In some embodiments, the network side device can send the monitoring results of at least one AI model to the first terminal, and the first terminal selects the target AI model based on the monitoring results of the at least one model.

[0306] In some further embodiments, the network side device may also select a target AI model from the at least one AI model based on the monitoring results of the at least one AI model, and then send a first indication message to the first terminal, where the first indication message is used to indicate the target AI model used by the first terminal for positioning.

[0307] In some embodiments, the first terminal may also report the fifth information to the network side device. Further, the network side device may determine the target AI model adopted by the first terminal based on the fifth information reported by the first terminal and the fifth information reported by at least one positioning reference device.

[0308] In some embodiments, the network side device can also update the target information based on the monitoring results of at least one AI model and / or the capabilities of the first terminal, such as updating the first information, or updating the second information sent to the first terminal.

[0309] Optionally, the capabilities of the first terminal may include a list of identification information of AI models supported by the first terminal.

[0310] For example, the network side device can select an AI model with better monitoring results and supported by the first terminal as the AI ​​model indicated in the first information or the second information based on the AI ​​model supported by the first terminal and the monitoring results of at least one AI model.

[0311] For example, the network side device obtains the monitoring results of N1 AI models, and the N1 AI models include N2 AI models supported by the first terminal. Then, among the N2 AI models, there are N3 AI models with better monitoring results (for example, effective, higher scores, or higher rankings). Then, the first information or second information sent by the network side device may include identification information of the N3 AI models.

[0312] In some embodiments of the present application, the method 200 further includes:

[0313] The first device sends at least one of the following to the network side device:

[0314] Update information of AI models;

[0315] Obtain relevant information of the target AI model used by the second measurement result or the second position information, such as model configuration (such as gradient information), input data, etc.

[0316] For example, after the first device obtains target information from the network side device, such as the model configuration of the AI ​​model, it can update the AI ​​model and / or update the parameters of the AI ​​model based on the first measurement result obtained and the location information of the first device, and further send the updated information of the AI ​​model to the network side device, so that the subsequent network side device can indicate appropriate target information to the first device based on the updated information of the AI ​​model.

[0317] Below, in combination with Figure 5, taking the network side device as LMF or service terminal as an example, the AI ​​model-based positioning method provided in an embodiment of the present application is explained.

[0318] Example 1:

[0319] The positioning method may include the following steps:

[0320] In step S501, the LMF or service terminal sends first information to a first terminal and a positioning reference device. The first information includes AI model-related information. Thus, the first terminal and the positioning reference device can obtain positioning-related information based on the same AI model-related information, which helps ensure the accuracy of positioning based on the AI ​​model.

[0321] In some embodiments, the first information includes at least one of the following:

[0322] Model configuration of AI models;

[0323] Input configuration of the AI ​​model;

[0324] Output configuration of AI models;

[0325] Configuration related to the first measurement result;

[0326] configuration related to the second measurement result;

[0327] Monitoring configuration of AI models;

[0328] Monitoring results of the AI ​​model.

[0329] The specific implementation of each of the above information can be found in the relevant description of the aforementioned embodiment, and will not be repeated here for the sake of brevity.

[0330] Furthermore, the first terminal or positioning reference device can use the AI ​​model to process the measurement results obtained by measuring the PRS sent by at least one TRP in the TRP list to obtain positioning-related information, such as a second measurement result or second location information.

[0331] Optionally, before S501, it also includes S500: the LMF or the service terminal receives fifth information from at least one positioning reference device, and the fifth information may include positioning-related information obtained by the positioning reference device using at least one AI model, such as a second measurement result or second location information.

[0332] Furthermore, the LMF or the service terminal may determine the content of the first information sent to the first terminal and the positioning reference device based on fifth information obtained from at least one positioning reference device.

[0333] In some embodiments, the LMF or service terminal may further determine monitoring results of at least one AI model based on fifth information obtained from at least one positioning reference device, further select a target AI model based on the monitoring results, and indicate the target AI model to the first terminal. Alternatively, the monitoring results of the at least one AI model may be sent to the first terminal for the first terminal to select a target AI model.

[0334] Example 2:

[0335] The positioning method may include the following steps:

[0336] S501, the LMF or service terminal sends a second message to the first terminal and sends a fourth message to the positioning reference device. The second information includes information related to the AI ​​model used by the positioning reference device, and the fourth information includes information related to the AI ​​model used by the first terminal. Thus, the first terminal assists in judging the validity of the AI ​​model based on the information related to the AI ​​model used by the positioning reference device, which is conducive to ensuring the accuracy of positioning based on the AI ​​model. Alternatively, the positioning reference device can configure the AI ​​model on the positioning reference device based on the information related to the AI ​​model used by the first terminal, thereby achieving the purpose of assisting the first terminal in positioning.

[0337] In some embodiments, the second information includes at least one of the following:

[0338] a first measurement result obtained by a positioning reference device;

[0339] a second measurement result obtained by the positioning reference device;

[0340] first position information obtained by the positioning reference device;

[0341] second position information obtained by the positioning reference device;

[0342] The third information is the AI ​​model related information used by the positioning reference device to obtain the positioning related information. For example, the third information includes the AI ​​model related information used by the positioning reference device to obtain at least one of the second measurement result and the second position information.

[0343] In some embodiments, the third information includes at least one of the following:

[0344] Model configuration of the AI ​​model used by the positioning reference device;

[0345] The input configuration of the AI ​​model used by the positioning reference device;

[0346] The output configuration of the AI ​​model used by the positioning reference device;

[0347] Monitoring configuration of the AI ​​model used by the positioning reference device;

[0348] The monitoring results of the AI ​​model obtained by the positioning reference device.

[0349] In some embodiments, the fourth information includes at least one of the following:

[0350] a model configuration of the AI ​​model used by the first terminal;

[0351] an input configuration of the AI ​​model used by the first terminal;

[0352] an output configuration of the AI ​​model used by the first terminal;

[0353] The monitoring configuration of the AI ​​model used by the first terminal.

[0354] The specific implementation of each of the above information can be found in the relevant description of the aforementioned embodiment, and will not be repeated here for the sake of brevity.

[0355] Optionally, before S501, it also includes S500: the LMF or the service terminal receives fifth information from at least one positioning reference device, and the fifth information may include positioning-related information obtained by the positioning reference device using at least one AI model, such as a second measurement result or second location information.

[0356] Furthermore, the LMF or the service terminal may determine the content of the second information sent to the first terminal based on fifth information obtained from at least one positioning reference device.

[0357] In some embodiments, the LMF or service terminal may further determine monitoring results of at least one AI model based on fifth information obtained from at least one positioning reference device, further select a target AI model based on the monitoring results, and indicate the target AI model to the first terminal. Alternatively, the monitoring results of the at least one AI model may be sent to the first terminal for the first terminal to select a target AI model.

[0358] In summary, in an embodiment of the present application, the network side device can send AI model related information to the first device (for example, the first terminal (i.e., the terminal to be located, or the target terminal), the positioning reference device), so that the first device can obtain positioning related information based on the AI ​​model related information, and can realize terminal positioning based on the AI ​​model.

[0359] The above, in combination with Figures 4 and 5, describes in detail the method embodiment of the present application. The following, in combination with Figures 6 to 11, describes in detail the device embodiment of the present application. It should be understood that the device embodiment and the method embodiment correspond to each other, and similar descriptions can refer to the method embodiment.

[0360] The positioning method based on the AI ​​model provided in the embodiment of the present application can be executed by a positioning device based on the AI ​​model. In the embodiment of the present application, the positioning device provided in the embodiment of the present application is described by taking the positioning method based on the AI ​​model performed by the positioning device based on the AI ​​model as an example. Figure 6 shows a schematic block diagram of a positioning device 600 based on the AI ​​model according to an embodiment of the present application. As shown in Figure 6, the positioning device 600 includes:

[0361] The communication unit 610 is used to receive target information. The positioning device 600 is a first terminal or a positioning reference device. An AI model is deployed on the positioning device 600. The AI ​​model is used to obtain positioning-related information. The target information includes AI model-related information.

[0362] In some embodiments, the target information includes first information, and the first information includes at least one of the following:

[0363] Model configuration of AI models;

[0364] Input configuration of the AI ​​model;

[0365] Output configuration of AI models;

[0366] Configuration related to a first measurement result, where the first measurement result is a measurement result not processed by the AI ​​model;

[0367] Configuration related to a second measurement result, where the second measurement result is a measurement result processed by an AI model;

[0368] Monitoring configuration of AI models;

[0369] Monitoring results of the AI ​​model.

[0370] In some embodiments, the positioning device 600 is a first terminal, the target information includes second information, and the second information includes at least one of the following:

[0371] A first measurement result obtained by the positioning reference device, where the first measurement result is a measurement result not processed by the AI ​​model;

[0372] a second measurement result obtained by the positioning reference device, where the second measurement result is a measurement result processed by the AI ​​model;

[0373] First position information obtained by the positioning reference device, where the first position information is position information that has not been processed by the AI ​​model;

[0374] Second position information obtained by the positioning reference device, where the second position information is position information processed by the AI ​​model;

[0375] The third information includes information related to an AI model used by the positioning reference device to obtain at least one of the second measurement result and the second position information.

[0376] In some embodiments, the third information includes at least one of the following:

[0377] Model configuration of the AI ​​model used by the positioning reference device;

[0378] The input configuration of the AI ​​model used by the positioning reference device;

[0379] The output configuration of the AI ​​model used by the positioning reference device;

[0380] Monitoring configuration of the AI ​​model used by the positioning reference device;

[0381] The monitoring results of the AI ​​model obtained by the positioning reference device.

[0382] In some embodiments, the positioning device 600 is a positioning reference device, and the target information includes fourth information, the fourth information including AI model related information used by the first terminal to obtain at least one of the second measurement result and the second location information, the second measurement result is a measurement result processed by the AI ​​model, and the second location information is location information processed by the AI ​​model.

[0383] In some embodiments, the fourth information includes at least one of the following:

[0384] a model configuration of the AI ​​model used by the first terminal;

[0385] an input configuration of the AI ​​model used by the first terminal;

[0386] an output configuration of the AI ​​model used by the first terminal;

[0387] The monitoring configuration of the AI ​​model used by the first terminal.

[0388] In some embodiments, the model configuration of the AI ​​model includes at least one of the following:

[0389] Identification information of the AI ​​model;

[0390] Functional information of AI models;

[0391] Parameter information of the AI ​​model;

[0392] Update information of AI models;

[0393] Use cases for AI models;

[0394] Dataset information associated with the AI ​​model.

[0395] In some embodiments, the input configuration of the AI ​​model includes at least one of the following:

[0396] The preprocessing method of the AI ​​model's input information, the format of the AI ​​model's input information, the type of the AI ​​model's input information, the size of the AI ​​model's input information, the identification information of the transmitting device associated with the AI ​​model's input information, and the identification information of the reference signal associated with the AI ​​model's input information.

[0397] In some embodiments, the output configuration of the AI ​​model includes at least one of the following:

[0398] The post-processing method of the output information of the AI ​​model, the format of the output information of the AI ​​model, the input information type of the AI ​​model, the size of the output information of the AI ​​model, the identification information of the transmitting device associated with the output information of the AI ​​model, and the identification information of the reference signal associated with the input information of the AI ​​model.

[0399] In some embodiments, the configuration related to the first measurement result includes at least one of the following:

[0400] Identification information of the transmitting device of the reference signal corresponding to the measurement result;

[0401] Identification information of the reference signal corresponding to the measurement result;

[0402] identification information of the cell;

[0403] Measurement result reporting configuration.

[0404] In some embodiments, the configuration related to the second measurement result includes at least one of the following:

[0405] Identification information of the transmitting device of the reference signal corresponding to the measurement result;

[0406] Identification information of the reference signal corresponding to the measurement result;

[0407] identification information of the cell;

[0408] AI model enabling information;

[0409] Configuration of preprocessing of measurement results;

[0410] Output configuration of measurement results;

[0411] Measurement result reporting configuration.

[0412] In some embodiments, the monitoring configuration of the AI ​​model includes at least one of the following:

[0413] Whether to conduct AI model monitoring;

[0414] The monitoring methods used to monitor AI models;

[0415] Time window information for model monitoring;

[0416] The monitoring result type of the AI ​​model;

[0417] The monitoring result update cycle of the AI ​​model.

[0418] In some embodiments, the monitoring results of the AI ​​model include at least one of the following:

[0419] Indication of the effectiveness of AI models;

[0420] An indication of the effectiveness of the AI ​​model;

[0421] an indication of a score for the AI ​​model;

[0422] Sorting identifier of AI model;

[0423] Identification information of valid AI models.

[0424] In some embodiments, the communication unit 610 is further configured to:

[0425] receiving first time window information sent by a network-side device, where the first time window information is used to instruct the positioning apparatus 600 to measure a reference signal within the first time window;

[0426] The first time window information includes at least one of the following:

[0427] The period of the first time window, the starting position of the first time window, and the length of the first time window.

[0428] In some embodiments, the first time window information is associated with the target information.

[0429] In some embodiments, when the target information includes identification information of a reference signal transmitter device or identification information of the reference signal, the positioning apparatus 600 further includes:

[0430] A processing unit is used to measure the identification information of the transmitting end device of the reference signal or the reference signal associated with the identification information of the reference signal according to the first time window information, or to preferentially measure the identification information of the transmitting end device of the reference signal or the reference signal associated with the identification information of the reference signal.

[0431] In some embodiments, when the target information includes a reporting configuration of a measurement result, and the reporting configuration includes a reporting type, the positioning apparatus 600 further includes:

[0432] The processing unit is configured to measure the reference signal according to the first time window information to obtain a measurement result of the target reporting type.

[0433] In some embodiments, the positioning device 600 further includes:

[0434] A processing unit is configured to measure other reference signals other than the identification information of the transmitting end device of the reference signal or the reference signal associated with the identification information of the reference signal, or set the corresponding measurement result information as predefined information, when the positioning device 600 does not obtain a measurement result or the measurement result does not satisfy the first condition.

[0435] In some embodiments, the first condition includes at least one of the following:

[0436] The measurement result is less than the first threshold;

[0437] The channel condition corresponding to the measurement result is non-line-of-sight (NLOS);

[0438] The line-of-sight LOS probability corresponding to the measurement result is less than a second threshold.

[0439] In some embodiments, the communication unit 610 is further configured to:

[0440] receiving second time window information sent by a network-side device, where the second time window information is used to instruct the positioning device 600 to monitor the AI ​​model within the second time window;

[0441] The second time window information includes at least one of the following:

[0442] The period of the second time window, the starting position of the second time window, and the length of the second time window.

[0443] In some embodiments, the second time window information is associated with the target information.

[0444] In some embodiments, the positioning device 600 is the first terminal, and the method further includes:

[0445] The first terminal receives fifth information of at least one positioning reference device, the fifth information including at least one of a target measurement result obtained by the positioning reference device and target location information of the positioning reference device, the target measurement result information including at least one second measurement result, and the target location information including at least one second location information.

[0446] In some embodiments, the fifth information of the at least one positioning reference device is received from a network side device, or is received from the at least one positioning reference device.

[0447] In some embodiments, the fifth information is associated with at least one of the following:

[0448] The identification information of the AI ​​model in the target information and the functional information of the AI ​​model in the target information are associated.

[0449] In some embodiments, the positioning device 600 further includes:

[0450] A processing unit is configured to select a target AI model from at least one AI model associated with the fifth information based on the fifth information of the at least one positioning reference device.

[0451] In some embodiments, the communication unit 610 is further configured to: receive monitoring results of at least one AI model;

[0452] A target AI model is selected from the at least one AI model according to a monitoring result of the at least one AI model.

[0453] In some embodiments, the monitoring result of the at least one AI model is received from a network side device, or from at least one positioning reference device.

[0454] In some embodiments, the communication unit 610 is further used to: receive first indication information sent by a network side device, where the first indication information is used to indicate a target AI model used by the first terminal for positioning.

[0455] In some embodiments, when the target information includes identification information of a transmitting device of a reference signal or identification information of the reference signal, the input information of the AI ​​model is related to the identification information of the transmitting device or the identification information of the reference signal.

[0456] Alternatively, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip. The processing unit may be one or more processors.

[0457] It should be understood that the positioning device 600 according to the embodiment of the present application may correspond to the first device, the first terminal or the positioning reference device in the method embodiment of the present application, and the above-mentioned and other operations and / or functions of each unit in the positioning device 600 are respectively for realizing the corresponding processes of the positioning device 600 in the method embodiment shown in Figures 4 to 5 and achieving the same technical effects. To avoid repetition, they will not be described here.

[0458] FIG9 shows a schematic block diagram of a positioning device 700 based on an AI model according to an embodiment of the present application. As shown in FIG7 , the positioning device 700 includes:

[0459] The communication unit 710 is used to send target information to a first device, where the first device is a first terminal or a positioning reference device. An AI model is deployed on the first device, and the AI ​​model is used to obtain positioning-related information. The target information includes AI model-related information.

[0460] In some embodiments, the target information includes first information, and the first information includes at least one of the following:

[0461] Model configuration of AI models;

[0462] Input configuration of the AI ​​model;

[0463] Output configuration of AI models;

[0464] Configuration related to a first measurement result, where the first measurement result is a measurement result not processed by the AI ​​model;

[0465] Configuration related to a second measurement result, where the second measurement result is a measurement result processed by an AI model;

[0466] Monitoring configuration of AI models;

[0467] Monitoring results of the AI ​​model.

[0468] In some embodiments, the first device is a first terminal, the target information includes second information, and the second information includes at least one of the following:

[0469] A first measurement result obtained by the positioning reference device, where the first measurement result is a measurement result not processed by the AI ​​model;

[0470] a second measurement result obtained by the positioning reference device, where the second measurement result is a measurement result processed by the AI ​​model;

[0471] First position information obtained by the positioning reference device, where the first position information is position information that has not been processed by the AI ​​model;

[0472] Second position information obtained by the positioning reference device, where the second position information is position information processed by the AI ​​model;

[0473] The third information includes information related to an AI model used by the positioning reference device to obtain at least one of the second measurement result and the second position information.

[0474] In some embodiments, the third information includes at least one of the following:

[0475] Model configuration of the AI ​​model used by the positioning reference device;

[0476] The input configuration of the AI ​​model used by the positioning reference device;

[0477] The output configuration of the AI ​​model used by the positioning reference device;

[0478] Monitoring configuration of the AI ​​model used by the positioning reference device;

[0479] The monitoring results of the AI ​​model obtained by the positioning reference device.

[0480] In some embodiments, the first device is a positioning reference device, the target information includes fourth information, the fourth information includes AI model related information used by the first terminal to obtain at least one of the second measurement result and the second location information, the second measurement result is a measurement result processed by the AI ​​model, and the second location information is location information processed by the AI ​​model.

[0481] In some embodiments, the fourth information includes at least one of the following:

[0482] a model configuration of the AI ​​model used by the first terminal;

[0483] an input configuration of the AI ​​model used by the first terminal;

[0484] an output configuration of the AI ​​model used by the first terminal;

[0485] The monitoring configuration of the AI ​​model used by the first terminal.

[0486] In some embodiments, the model configuration of the AI ​​model includes at least one of the following:

[0487] Identification information of the AI ​​model;

[0488] Functional information of AI models;

[0489] Parameter information of the AI ​​model;

[0490] Update information of AI models;

[0491] Use cases for AI models;

[0492] Dataset information associated with the AI ​​model.

[0493] In some embodiments, the input configuration of the AI ​​model includes at least one of the following:

[0494] The preprocessing method of the AI ​​model's input information, the format of the AI ​​model's input information, the type of the AI ​​model's input information, the size of the AI ​​model's input information, the identification information of the transmitting device associated with the AI ​​model's input information, and the identification information of the reference signal associated with the AI ​​model's input information.

[0495] In some embodiments, the output configuration of the AI ​​model includes at least one of the following:

[0496] The post-processing method of the output information of the AI ​​model, the format of the output information of the AI ​​model, the input information type of the AI ​​model, the size of the output information of the AI ​​model, the identification information of the transmitting device associated with the output information of the AI ​​model, and the identification information of the reference signal associated with the input information of the AI ​​model.

[0497] In some embodiments, the configuration related to the first measurement result includes at least one of the following:

[0498] Identification information of the transmitting device of the reference signal corresponding to the measurement result;

[0499] Identification information of the reference signal corresponding to the measurement result;

[0500] identification information of the cell;

[0501] Measurement result reporting configuration.

[0502] In some embodiments, the configuration related to the second measurement result includes at least one of the following:

[0503] Identification information of the transmitting device of the reference signal corresponding to the measurement result;

[0504] Identification information of the reference signal corresponding to the measurement result;

[0505] identification information of the cell;

[0506] AI model enabling information;

[0507] Configuration of preprocessing of measurement results;

[0508] Output configuration of measurement results;

[0509] Measurement result reporting configuration.

[0510] In some embodiments, the monitoring configuration of the AI ​​model includes at least one of the following:

[0511] Whether to conduct AI model monitoring;

[0512] The monitoring methods used to monitor AI models;

[0513] Time window information for model monitoring;

[0514] The type of monitoring results of the AI ​​model;

[0515] The monitoring result update cycle of the AI ​​model.

[0516] In some embodiments, the monitoring results of the AI ​​model include at least one of the following:

[0517] Indication of the effectiveness of AI models;

[0518] An indication of the effectiveness of the AI ​​model;

[0519] an indication of a score for the AI ​​model;

[0520] Sorting identifier of AI model;

[0521] Identification information of a valid AI model.

[0522] In some embodiments, the communication unit 710 is further configured to:

[0523] First time window information is sent to the first device, where the first time window information is used to instruct the first device to measure a reference signal within the first time window.

[0524] In some embodiments, the first time window information includes at least one of the following:

[0525] The period of the first time window, the starting position of the first time window, and the length of the first time window.

[0526] In some embodiments, the first time window information is associated with the target information.

[0527] In some embodiments, the communication unit 710 is further configured to:

[0528] Second time window information is sent to the first device, where the second time window information is used to instruct the first device to monitor the AI ​​model within a second time window.

[0529] In some embodiments, the second time window information includes at least one of the following:

[0530] The period of the second time window, the starting position of the second time window, and the length of the second time window.

[0531] In some embodiments, the communication unit 710 is further configured to:

[0532] Acquire fifth information of at least one positioning reference device, the fifth information including at least one of a target measurement result obtained by the positioning reference device and target position information of the positioning reference device, the target measurement result information including at least one second measurement result, and the target position information including at least one second position information.

[0533] In some embodiments, the fifth information is associated with at least one of the following:

[0534] The identification information of the AI ​​model in the target information and the functional information of the AI ​​model in the target information are associated.

[0535] In some embodiments, the positioning device 700 further includes:

[0536] A processing unit is used to determine, based on the fifth information of the at least one positioning reference device, a monitoring result of at least one AI model associated with the fifth information.

[0537] In some embodiments, the communication unit 710 is further configured to:

[0538] Sending a monitoring result of the at least one AI model to the first terminal; or

[0539] Send fifth information of the at least one positioning reference device to the first terminal.

[0540] In some embodiments, the positioning device 700 further includes:

[0541] A processing unit is configured to select a target AI model from the at least one model based on the monitoring result of the at least one AI model.

[0542] In some embodiments, the communication unit 710 is further configured to:

[0543] Send first indication information to the first terminal, where the first indication information is used to indicate the target AI model used by the first terminal for positioning.

[0544] Optionally, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip.

[0545] It should be understood that the positioning device 700 according to the embodiment of the present application may correspond to the network side device or LMF or service terminal in the method embodiment of the present application, and the above-mentioned and other operations and / or functions of each unit in the positioning device 700 are respectively for realizing the corresponding processes of the network side device or LMF or service terminal in the method embodiment shown in Figures 4 to 5, and achieving the same technical effect. To avoid repetition, they will not be repeated here.

[0546] In some embodiments, the apparatus 600 and apparatus 700 in the embodiments of the present application may be electronic devices, such as electronic devices with an operating system, or components in electronic devices, such as integrated circuits or chips. The electronic device may be a terminal, or may be other devices other than a terminal. For example, the terminal may include but is not limited to the types of terminal 11 listed above, and other devices may be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiments of the present application.

[0547] As shown in Figure 8, an embodiment of the present application also provides a communication device 800, including a processor 801 and a memory 802, wherein the memory 802 stores a program or instruction that can be run on the processor 801. For example, when the communication device 800 is a first device, a first terminal, or a positioning reference device, the program or instruction is executed by the processor 801 to implement the steps performed by the first device, the first terminal, or the positioning reference device in the above-mentioned positioning method embodiment, and can achieve the same technical effect. When the communication device 800 is an LMF, a service terminal, or a network-side device, the program or instruction is executed by the processor 801 to implement the various steps performed by the LMF, the service terminal, or the network-side device in the above-mentioned positioning method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0548] The present application also provides a terminal including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiments shown in Figures 4 and 5. This terminal embodiment corresponds to the aforementioned method embodiment on the first device, first terminal, positioning reference device, or service terminal side. The various implementation processes and implementation methods of the aforementioned method embodiments are applicable to this terminal embodiment and can achieve the same technical effects. Specifically, Figure 9 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application.

[0549] The terminal 900 includes but is not limited to: a radio frequency unit 901, a network module 902, an audio output unit 903, an input unit 904, a sensor 905, a display unit 906, a user input unit 907, an interface unit 908, a memory 909 and at least some of the components of the processor 910.

[0550] Those skilled in the art will appreciate that the terminal 900 may also include a power supply (such as a battery) to power various components. The power supply may be logically connected to the processor 910 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The terminal structure shown in FIG9 does not limit the terminal. The terminal may include more or fewer components than shown, or may combine certain components, or have different component arrangements, which will not be described in detail here.

[0551] It should be understood that in an embodiment of the present application, the input unit 904 may include a graphics processing unit (GPU) 9041 and a microphone 9042, and the graphics processor 9041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 906 may include a display panel 9061, and the display panel 9061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 907 includes a touch panel 9071 and at least one of other input devices 9072. The touch panel 9071 is also called a touch screen. The touch panel 9071 may include two parts: a touch detection device and a touch controller. Other input devices 9072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and an operating stick, which will not be repeated here.

[0552] In the embodiment of the present application, after receiving downlink data from a network-side device, the RF unit 901 may transmit the data to the processor 910 for processing. Furthermore, the RF unit 901 may send uplink data to the network-side device. Typically, the RF unit 901 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, and the like.

[0553] The memory 909 can be used to store software programs or instructions and various data. The memory 909 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 909 may include a volatile memory or a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 909 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0554] Processor 910 may include one or more processing units. Optionally, processor 910 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 910.

[0555] In some embodiments, the processor 910 is used to receive target information, the first device is a first terminal or a positioning reference device, an AI model is deployed on the first device, the AI ​​model is used to obtain positioning-related information, and the target information includes AI model-related information, thereby enabling terminal positioning based on the AI ​​model.

[0556] It can be understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the first device, the first terminal or the positioning reference device or the service terminal in the method embodiment, and achieve the same or corresponding technical effect. To avoid repetition, it will not be repeated here.

[0557] The present application also provides a network-side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiments shown in Figures 4 and 5. This network-side device embodiment corresponds to the aforementioned LMF or network-side device-side method embodiment, and each implementation process and implementation method of the aforementioned method embodiment can be applied to this network-side device embodiment and can achieve the same technical effects.

[0558] Specifically, an embodiment of the present application also provides a network-side device. As shown in Figure 10, the network-side device 1000 includes: an antenna 1001, a radio frequency device 1002, a baseband device 1003, a processor 1004, and a memory 1005. Antenna 1001 is connected to radio frequency device 1002. In the uplink direction, radio frequency device 1002 receives information via antenna 1001 and sends the received information to baseband device 1003 for processing. In the downlink direction, baseband device 1003 processes the information to be transmitted and sends it to radio frequency device 1002. Radio frequency device 1002 processes the received information and sends it through antenna 1001.

[0559] The method executed by the network-side device in the above embodiment may be implemented in the baseband device 1003 , which includes a baseband processor.

[0560] The baseband device 1003 may, for example, include at least one baseband board, on which multiple chips are arranged, as shown in Figure 10, one of which is, for example, a baseband processor, which is connected to the memory 1005 through a bus interface to call the program in the memory 1005 and execute the network device operations shown in the above method embodiment.

[0561] The network side device may further include a network interface 1006, which is, for example, a Common Public Radio Interface (CPRI).

[0562] In some embodiments, the network side device 1000 of the embodiment of the present application also includes: instructions or programs stored on the memory 1005 and can be run on the processor 1004. The processor 1004 calls the instructions or programs in the memory 1005 to execute the steps performed by the LMF or the network side device in the method embodiments shown in Figures 4 to 5, and achieves the same technical effect. To avoid repetition, they will not be repeated here.

[0563] The embodiment of the present application further provides a network side device. As shown in FIG11 , the network side device 1100 includes: a processor 1101, a network interface 1102, and a memory 1103. The network interface 1102 is, for example, a common public radio interface (CPRI).

[0564] In some embodiments, the network side device 1100 of the embodiment of the present application also includes: instructions or programs stored on the memory 1103 and executable on the processor 1101. The processor 1101 calls the instructions or programs in the memory 1103 to execute the steps performed by the LMF or the network side device in the method embodiments shown in Figures 4 to 5, and can achieve the same technical effect. To avoid repetition, they will not be described here.

[0565] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the method embodiments of Figures 4 to 5 above are implemented, and the same technical effect can be achieved. To avoid repetition, they will not be repeated here.

[0566] The processor is the processor in the first device or the network-side device described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. In some examples, the readable storage medium may be a non-transitory readable storage medium.

[0567] The processors mentioned in the embodiments of the present application may include general-purpose processors, special-purpose processors, etc., such as a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), an artificial intelligence (AI) processor, a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a network processor (NP), a field programmable gate array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc.

[0568] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the method embodiments of Figures 4 to 5 above, and can achieve the same technical effects. To avoid repetition, they will not be repeated here.

[0569] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0570] An embodiment of the present application further provides a computer program / program product, which is stored in a storage medium. The computer program / program product is executed by at least one processor to implement the various processes of the method embodiments of Figures 3 to 7 above, and can achieve the same technical effects. To avoid repetition, they are not described here.

[0571] An embodiment of the present application also provides a communication system, including: a first device and a second device, wherein the first device can be used to execute the steps performed by the first device, the first terminal or the positioning reference device in the positioning method described above, and the second device can be used to execute the steps performed by the second device, LMF, service terminal or network side device in the positioning method described above.

[0572] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0573] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general-purpose hardware platform, or of course, by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes a number of instructions for enabling a terminal or network-side device to execute the methods described in each embodiment of the present application.

[0574] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of this application and the scope of protection of the claims. These implementation methods are all within the protection of this application.

Claims

1. A positioning method based on an artificial intelligence (AI) model, wherein: include: A first device receives target information. The first device is a first terminal or a positioning reference device. An AI model is deployed on the first device. The AI ​​model is used to obtain positioning-related information. The target information includes AI model-related information.

2. The method according to claim 1, wherein: The target information includes first information, and the first information includes at least one of the following: Model configuration for AI models; Input configuration of AI models; Output configuration of AI models; A configuration related to a first measurement result, where the first measurement result is a measurement result that has not been processed by an AI model; A configuration related to a second measurement result, where the second measurement result is a measurement result processed by an AI model; Monitoring configuration of AI models; Monitoring results of the AI ​​model.

3. The method according to claim 1, wherein: The first device is a first terminal, the target information includes second information, and the second information includes at least one of the following: A first measurement result obtained by the positioning reference device, where the first measurement result is a measurement result that has not been processed by the AI ​​model; A second measurement result obtained by the positioning reference device, where the second measurement result is a measurement result processed by the AI ​​model; First position information obtained by the positioning reference device, where the first position information is position information that has not been processed by the AI ​​model; Second position information obtained by the positioning reference device, where the second position information is position information processed by the AI ​​model; The third information includes information related to an AI model used by the positioning reference device to obtain at least one of the second measurement result and the second position information.

4. The method according to claim 3, wherein: The third information includes at least one of the following: Model configuration of the AI ​​model used by the positioning reference device; The input configuration of the AI ​​model used by the positioning reference device; The output configuration of the AI ​​model used by the positioning reference device; Monitoring configuration of the AI ​​model used by the positioning reference device; The monitoring results of the AI ​​model obtained by the positioning reference device.

5. The method according to claim 1 or 3, wherein: The first device is a positioning reference device, the target information includes fourth information, the fourth information includes information related to an AI model used by the first terminal to obtain at least one of a second measurement result and a second location information, the second measurement result is a measurement result processed by the AI ​​model, and the second location information is location information processed by the AI ​​model.

6. The method according to claim 5, wherein: The fourth information includes at least one of the following: A model configuration of an AI model used by the first terminal; An input configuration of an AI model used by the first terminal; an output configuration of the AI ​​model used by the first terminal; The monitoring configuration of the AI ​​model used by the first terminal.

7. The method according to claim 2, 4 or 6, wherein: The model configuration of the AI ​​model includes at least one of the following: Identification information of the AI ​​model; Functional information of AI models; Parameter information of the AI ​​model; Update information of AI models; Use scenarios of AI models; Dataset information associated with the AI ​​model.

8. The method according to claim 2, 4 or 6, wherein: The input configuration of the AI ​​model includes at least one of the following: The preprocessing method of the input information of the AI ​​model, the format of the input information of the AI ​​model, the type of the input information of the AI ​​model, the size of the input information of the AI ​​model, the identification information of the transmitting device associated with the input information of the AI ​​model, and the identification information of the reference signal associated with the input information of the AI ​​model.

9. The method according to claim 2, 4 or 6, wherein: The output configuration of the AI ​​model includes at least one of the following: The post-processing method of the output information of the AI ​​model, the format of the output information of the AI ​​model, the input information type of the AI ​​model, the size of the output information of the AI ​​model, the identification information of the transmitting device associated with the output information of the AI ​​model, and the identification information of the reference signal associated with the input information of the AI ​​model.

10. The method according to claim 2, wherein: The configuration related to the first measurement result includes at least one of the following: Identification information of a transmitting device of a reference signal corresponding to the measurement result; Identification information of the reference signal corresponding to the measurement result; identification information of the cell; Measurement result reporting configuration.

11. The method according to claim 2, wherein: The configuration related to the second measurement result includes at least one of the following: Identification information of a transmitting device of a reference signal corresponding to the measurement result; Identification information of the reference signal corresponding to the measurement result; identification information of the cell; AI model enabling information; Configuration of preprocessing of measurement results; Output configuration of measurement results; Measurement result reporting configuration.

12. The method according to claim 2, 4 or 6, wherein: The monitoring configuration of the AI ​​model includes at least one of the following: Whether to monitor the AI ​​model; The monitoring method used to monitor the AI ​​model; Time window information for model monitoring; The monitoring result type of the AI ​​model; The monitoring result update cycle of the AI ​​model.

13. The method according to claim 2, 4 or 6, wherein: The monitoring results of the AI ​​model include at least one of the following: Indication of effectiveness of AI models; An indication of the effectiveness of the AI ​​model; An indication of a score of the AI ​​model; Sorting identifier of AI model; Identification information of valid AI models.

14. The method according to any one of claims 1 to 13, wherein: The method further comprises: The first device receives first time window information sent by a network side device, where the first time window information is used to instruct the first device to measure a reference signal within the first time window; The first time window information includes at least one of the following: The period of the first time window, the starting position of the first time window, and the length of the first time window.

15. The method according to claim 14, wherein: The first time window information is associated with the target information.

16. The method according to claim 14 or 15, wherein: In a case where the target information includes identification information of a transmitting end device of a reference signal or identification information of the reference signal, the method further includes: The first device measures the identification information of the reference signal sending device or the reference signal associated with the identification information of the reference signal according to the first time window information, or preferentially measures the identification information of the reference signal sending device or the reference signal associated with the identification information of the reference signal.

17. The method according to any one of claims 14 to 16, wherein: In a case where the target information includes a reporting configuration of the measurement result, and the reporting configuration includes a reporting type, the method further includes: The first device measures the reference signal according to the first time window information to obtain a measurement result of the reporting type.

18. The method according to claim 16 or 17, wherein: The method further comprises: When the first device does not obtain a measurement result, or the measurement result does not satisfy the first condition, measure other reference signals other than the identification information of the transmitting device of the reference signal or the reference signal associated with the identification information of the reference signal, or set the corresponding measurement result information as predefined information.

19. The method according to claim 18, wherein: The first condition includes at least one of the following: The measurement result is less than the first threshold; The channel condition corresponding to the measurement result is non-line-of-sight NLOS; The line-of-sight LOS probability corresponding to the measurement result is less than the second threshold.

20. The method according to any one of claims 1 to 19, wherein: The method further comprises: The first device receives second time window information sent by a network side device, where the second time window information is used to instruct the first device to monitor the AI ​​model within the second time window; The second time window information includes at least one of the following: The period of the second time window, the starting position of the second time window, and the length of the second time window.

21. The method according to claim 20, wherein: The second time window information is associated with the target information.

22. The method according to any one of claims 1 to 21, wherein: The first device is the first terminal, and the method further includes: The first terminal receives fifth information of at least one positioning reference device, the fifth information including at least one of a target measurement result obtained by the positioning reference device and target position information of the positioning reference device, the target measurement result information including at least one second measurement result, and the target position information including at least one second position information.

23. The method according to claim 22, wherein: The fifth information of the at least one positioning reference device is received from the network side device, or is received from the at least one positioning reference device.

24. The method according to claim 22 or 23, wherein: The fifth information is associated with at least one of the following: The identification information of the AI ​​model in the target information and the functional information of the AI ​​model in the target information are associated.

25. The method according to any one of claims 22 to 24, wherein: The method further comprises: The first terminal selects a target AI model from at least one AI model associated with the fifth information according to the fifth information of the at least one positioning reference device.

26. The method according to any one of claims 1 to 21, wherein: The first device is the first terminal, and the method further includes: The first terminal receives a monitoring result of at least one AI model; According to the monitoring result of the at least one AI model, a target AI model is selected from the at least one AI model.

27. The method according to claim 26, wherein: The monitoring result of the at least one AI model is received from a network side device, or from at least one positioning reference device.

28. The method according to any one of claims 1 to 21, wherein: The first device is a first terminal, and the method further includes: The first terminal receives first indication information sent by a network side device, where the first indication information is used to indicate a target AI model used by the first terminal for positioning.

29. The method according to any one of claims 1 to 28, wherein: In a case where the target information includes identification information of a transmitting device of a reference signal or identification information of the reference signal, the input information of the AI ​​model is related to the identification information of the transmitting device or the identification information of the reference signal.

30. A positioning method based on an artificial intelligence (AI) model, wherein: include: The network side device sends target information to the first device, where the first device is a first terminal or a positioning reference device. An AI model is deployed on the first device, and the AI ​​model is used to obtain positioning-related information. The target information includes AI model-related information.

31. A positioning device based on an AI model, wherein: include: A communication unit is used to receive target information. An AI model is deployed on the positioning device. The AI ​​model is used to obtain positioning-related information. The target information includes AI model-related information. The positioning device is a first terminal or a positioning reference device.

32. A positioning device based on an AI model, wherein: include: A communication unit is used to send target information to a first device, where the first device is a first terminal or a positioning reference device. An AI model is deployed on the first device, where the AI ​​model is used to obtain positioning-related information, and the target information includes AI model-related information.

33. A communication device, wherein: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 28 or the steps of the method according to claim 29 are implemented.

34. A readable storage medium, wherein: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, it implements the positioning method as described in any one of claims 1-28, or implements the steps of the positioning method as described in claim 29.

Images