Positioning method based on artificial intelligence ai model and communication device

Abstract

The application discloses a positioning method based on an artificial intelligence (AI) model and a communication device, and belongs to the field of communication technologies. The positioning method based on the AI model comprises the following steps: a first communication device acquires first information associated with AI model related information; the first communication device determines target information according to the first information, wherein the target information comprises at least one of the following: a target AI model, validity information of the AI model related information or feedback information obtained by positioning based on the target AI model; and the first information is used for representing an effective application range of the AI model related information, and the AI model related information comprises at least one of the following: an AI model, AI model parameters, input of the AI model and output of the AI model.

Description

Technical Field

[0001] This application belongs to the field of communication technology, specifically relating to a positioning method and communication device based on an artificial intelligence (AI) model. Background Technology

[0002] As positioning technology matures, more and more terminal devices with positioning capabilities are emerging. To improve positioning efficiency, artificial intelligence (AI) models can be used to acquire positioning data. However, the measurement data and requirements used for positioning change over time; that is, the AI ​​model used may no longer meet the needs of the actual scenario, resulting in positioning results that do not meet the requirements of the real-world scenario. Therefore, it is urgent for those skilled in the art to implement an AI model-based positioning solution that meets the needs of real-world scenarios. Summary of the Invention

[0003] This application provides a positioning method and communication device based on an artificial intelligence (AI) model, which can solve the problem that the positioning results based on the AI ​​model do not meet the needs of actual scenarios.

[0004] Firstly, a positioning method based on an artificial intelligence (AI) model is provided, applied to a first communication device. This method includes:

[0005] The first communication device acquires first information associated with the AI ​​model;

[0006] The first communication device determines target information based on the first information, and the target information includes at least one of the following: a target AI model, validity information related to the AI ​​model, or feedback information obtained by positioning based on the target AI model;

[0007] The first information is used to indicate the effective scope of application of the AI ​​model-related information, which includes at least one of the following: AI model, AI model parameters, AI model input, and AI model output.

[0008] Secondly, an AI-based positioning method is provided for a second communication device. This method includes:

[0009] The second communication device receives target information sent by the first communication device, the target information including at least one of the following: a target AI model, validity information related to the AI ​​model, or feedback information obtained by positioning based on the target AI model;

[0010] The target information is determined based on first information associated with AI model-related information. The first information is used to indicate the effective scope of application of the AI ​​model-related information. The AI ​​model-related information includes at least one of the following: AI model, AI model parameters, AI model input, and AI model output.

[0011] Thirdly, an AI model-based positioning device is provided, comprising:

[0012] The acquisition module is used to acquire the first information associated with the AI ​​model.

[0013] The processing module is configured to determine target information based on the first information, wherein the target information includes at least one of the following: a target AI model, validity information related to the AI ​​model, or feedback information obtained by positioning based on the target AI model;

[0014] The first information is used to indicate the effective scope of application of the AI ​​model-related information, which includes at least one of the following: AI model, AI model parameters, AI model input, and AI model output.

[0015] Fourthly, an AI model-based positioning device is provided, comprising:

[0016] The receiving module is used to receive target information sent by the first communication device, wherein the target information includes at least one of the following: a target AI model, validity information related to the AI ​​model, or feedback information obtained by positioning based on the target AI model;

[0017] The target information is determined based on first information associated with AI model-related information. The first information is used to indicate the effective scope of application of the AI ​​model-related information. The AI ​​model-related information includes at least one of the following: AI model, AI model parameters, AI model input, and AI model output.

[0018] Fifthly, a first communication device is provided, the first communication device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first aspect.

[0019] In a sixth aspect, a first communication device is provided, including a processor and a communication interface, wherein the communication interface is used to acquire first information associated with AI model-related information; the processor is used to determine target information based on the first information, the target information including at least one of the following: a target AI model, validity information of the AI ​​model-related information, or feedback information obtained by positioning based on the target AI model; the first information is used to indicate the effective applicability range of the AI ​​model-related information, the AI ​​model-related information including at least one of the following: an AI model, AI model parameters, AI model inputs, and AI model outputs.

[0020] In a seventh aspect, a second communication device is provided, the second communication device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the second aspect.

[0021] Eighthly, a second communication device is provided, including a processor and a communication interface, wherein the communication interface is used to receive target information sent by a first communication device, the target information including at least one of the following: a target AI model, validity information of the AI ​​model-related information, or feedback information obtained by positioning based on the target AI model; the target information is determined based on first information associated with the AI ​​model-related information, the first information being used to indicate the effective applicability range of the AI ​​model-related information, the AI ​​model-related information including at least one of the following: an AI model, AI model parameters, AI model inputs, and AI model outputs.

[0022] A ninth aspect provides a communication system comprising: a first communication device and a second communication device, wherein the first communication device is configured to perform the steps of the AI ​​model-based positioning method as described in the first aspect, and the second communication device is configured to perform the steps of the AI ​​model-based positioning method as described in the second aspect.

[0023] In a tenth aspect, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect, or implement the steps of the method described in the second aspect.

[0024] Eleventhly, a chip is provided, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect, or to implement the method as described in the second aspect.

[0025] In a twelfth aspect, a computer program / program product is provided, which is stored in a storage medium and executed by at least one processor to implement the steps of the AI ​​model-based localization method as described in the first or second aspect.

[0026] In this embodiment, the first communication device acquires first information associated with AI model-related information; the first communication device determines target information based on the first information, the target information including at least one of the following: target AI model, validity information of AI model-related information, or feedback information obtained by positioning based on the target AI model. Since the first information is used to represent the effective applicable scope of AI model-related information, determining target information based on the first information can make the positioned AI model more in line with the actual scenario requirements, and can also update the AI ​​model and / or AI model parameters based on the determined target information, so that the positioning result obtained based on the updated AI model is more accurate. Attached Figure Description

[0027] Figure 1 This is a structural diagram of a wireless communication system to which the embodiments of this application can be applied;

[0028] Figure 2 This is one of the AI ​​model principle block diagrams of the AI ​​model-based localization method provided in the embodiments of this application;

[0029] Figure 3 This is the second block diagram of the AI ​​model principle of the localization method based on the AI ​​model provided in the embodiments of this application;

[0030] Figure 4 This is one of the flowcharts illustrating the AI ​​model-based localization method provided in the embodiments of this application;

[0031] Figure 5 This is one of the interactive flow diagrams of the AI ​​model-based localization method provided in the embodiments of this application;

[0032] Figure 6 This is the second schematic diagram of the interaction process of the AI ​​model-based localization method provided in the embodiments of this application;

[0033] Figure 7 This is the third schematic diagram of the interaction process of the AI ​​model-based localization method provided in the embodiments of this application;

[0034] Figure 8 This is one of the schematic diagrams illustrating the parameter range of the AI ​​model-based localization method provided in the embodiments of this application;

[0035] Figure 9 This is the second schematic diagram illustrating the parameter range of the AI ​​model-based localization method provided in the embodiments of this application;

[0036] Figure 10 This is the fourth schematic diagram of the interaction process of the AI ​​model-based localization method provided in the embodiments of this application;

[0037] Figure 11 This is the fifth schematic diagram of the interaction process of the AI ​​model-based localization method provided in the embodiments of this application;

[0038] Figure 12 This is the sixth schematic diagram of the interaction flow of the AI ​​model-based localization method provided in the embodiments of this application.

[0039] Figure 13 This is one of the structural schematic diagrams of the AI ​​model-based positioning device provided in the embodiments of this application.

[0040] Figure 14 This is a second schematic diagram of the structure of the AI ​​model-based positioning device provided in the embodiments of this application;

[0041] Figure 15 This is a schematic diagram of the structure of the communication device provided in the embodiments of this application;

[0042] Figure 16 This is a schematic diagram of the hardware structure of the terminal provided in the embodiments of this application;

[0043] Figure 17 This is a schematic diagram of the network-side device according to an embodiment of this application;

[0044] Figure 18 This is another structural schematic diagram of the network-side device according to an embodiment of this application. Detailed Implementation

[0045] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0046] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0047] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, 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), and other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and NR terminology is used in most of the following description; however, these technologies can also be applied to applications beyond NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0048] Figure 1This diagram illustrates a block diagram of a wireless communication system applicable to embodiments of this application. The wireless communication system includes a terminal 11 and a network-side device 12. Terminal 11 can be a mobile phone, tablet computer, laptop computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, vehicle-mounted device (VUE), pedestrian terminal (PUE), smart home (home devices with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game console, personal computer (PC), ATM, or self-service machine, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. It should be noted that the specific type of terminal 11 is not limited in this embodiment. Network-side equipment 12 may include access network equipment or core network equipment. Access network equipment 12 may also be referred to as radio access network equipment, radio access network (RAN), radio access network function, or radio access network unit. Access network equipment 12 may include base stations, WLAN access points, or WiFi nodes, etc. Base stations may be referred to as Node B, evolved Node B (eNB), access point, base transceiver station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), home B node, home evolved B node, Transmitting Receiving Point (TRP), or any other suitable term in the field, as long as the same technical effect is achieved. The base station is not limited to specific technical terms. It should be noted that in this application embodiment, only a base station in an NR system is used as an example for description, and the specific type of base station is not limited.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 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 (or L-NEF), Binding Support Function (BSF), and Application Function. Functions include Location Management Function (LMF), Enhanced Service Mobile Location Center (E-SMLC), and Network Data Analytics Function (NWDAF). It should be noted that this application embodiment only uses core network equipment in the NR system as an example for description, and does not limit the specific type of core network equipment.

[0049] AI has been widely applied in various fields. AI models can be implemented in various ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. This application uses neural networks as an example for illustration, but does not limit the specific type of AI model. A neural network consists of neurons, where a1, a2, ... a... KLet w be the input, b be the weights (multiplicative coefficients), and σ(.) be the activation function. Common activation functions include Sigmoid, tanh, and Rectified Linear Unit (ReLU). The parameters of a neural network are optimized using optimization algorithms. Optimization algorithms are a class of algorithms that help us minimize or maximize an objective function (sometimes called a loss function). The objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we build a neural network model f(.). With the model, we can obtain the predicted output f(x) based on the input x, and calculate the difference between the predicted value and the true value (f(x) - Y), which is the loss function. Our goal is to find suitable w and b that minimize the value of the above loss function. The smaller the loss value, the closer our model is to the reality.

[0050] Most common optimization algorithms are based on the error back propagation (BP) algorithm. The basic idea of ​​the BP algorithm is that the learning process consists of two parts: forward propagation of the signal and backward propagation of the error. During forward propagation, the input sample is introduced from the input layer, processed layer by layer by the hidden layers, and then propagated to the output layer. If the actual output of the output layer does not match the expected output, the process transitions to the error back propagation stage. Error back propagation involves propagating the output error back to the input layer layer by layer through the hidden layers, distributing the error to all units in each layer, thus obtaining the error signal of each unit. This error signal serves as the basis for adjusting the weights of each unit. This process of adjusting the weights through forward and backward propagation is repeated continuously. This continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the predetermined number of learning iterations is reached.

[0051] Common optimization algorithms include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov (named after the inventor, specifically stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), Adadelta, root mean square propagation (RMSprop), and adaptive momentum estimation (Adam).

[0052] During error backpropagation, these optimization algorithms calculate the gradient based on the error / loss obtained from the loss function with respect to the current neuron, add the learning rate, previous gradients / derivatives / partial derivatives, etc., and then pass the gradient to the previous layer.

[0053] The method of this application embodiment can be applied to positioning scenarios, such as positioning based on AI models. Since the measurement environment and requirements change over time, the positioning results obtained by the AI ​​model may no longer meet the current requirements over time. Therefore, the method of this application embodiment can determine whether the current AI model is effective based on the actual situation, and update the AI ​​model and / or AI model parameters based on the determination, so that the AI ​​positioning results meet the performance indicators.

[0054] In one embodiment, such as Figure 2 , Figure 3 The diagram shown illustrates the principle of AI model application. AI model application (AIinference) is the process of obtaining output based on the AI ​​model, its parameters, and the current input data.

[0055] The AI ​​model-based localization method provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0056] Figure 4 This is one of the flowcharts illustrating the AI ​​model-based localization method provided in this application. For example... Figure 4 As shown, the method provided in this embodiment includes:

[0057] Step 101: The first communication device acquires first information associated with the AI ​​model-related information;

[0058] The first piece of information is used to indicate the effective scope of application of AI model-related information, which includes at least one of the following: AI model, AI model parameters, AI model input, and AI model output.

[0059] Specifically, the first information is associated with AI model-related information. The first information indicates the effective scope of application of AI model-related information, such as the effective range of input, the effective range of output, the validity conditions, etc.

[0060] It is worth noting that the AI ​​model-related information only ensures that the selected, specific AI model can be understood and confirmed by the first communication device and other communication devices; the specific transmission format and method are not limited here. The AI ​​model-related information is also used to protect the corresponding features of the AI ​​model.

[0061] Optionally, the first communication device may obtain AI model-related information and first information associated with AI model-related information from the second communication device (e.g., a model management device, a network-side device (such as NWDAF), a positioning server (such as LMF, E-SMLC)).

[0062] It is worth noting that the first information may be included in the AI ​​model-related information, transmitted together with the AI ​​model-related information, or transmitted independently of the AI ​​model-related information, but associated with the AI ​​model's recognition information and the first information.

[0063] Step 102: The first communication device determines the target information based on the first information. The target information includes at least one of the following: the target AI model, the validity information of the AI ​​model-related information, or the feedback information obtained by positioning based on the target AI model.

[0064] Specifically, target information can be determined based on the effective applicability range of the parameters in the first information. For example, the first information associated with the relevant information of the AI ​​model can determine the effective applicability range of the relevant information of the AI ​​model, indicating that the relevant information of the AI ​​model is effective in a specific scenario and a specific region. For another example, assuming the output of the AI ​​model is within the effective applicability range of the parameters in the first information, it indicates that the output of the AI ​​model is effective. Yet another example is assuming the input of the AI ​​model is within the effective applicability range of the parameters in the first information, indicating that the input and output of the AI ​​model are effective, or that the AI ​​model itself is effective.

[0065] In another embodiment, it is assumed that there are multiple AI models, and each AI model is associated with corresponding first information. Based on the first information, one or more AI models among the multiple AI models are determined as the target AI model.

[0066] For example, feedback information may include validity information, the target AI model, the input of the AI ​​model, the output of the AI ​​model, and measurement information from the terminal.

[0067] Optionally, the feedback information corresponds to the first information.

[0068] Optionally, the first communication device can send feedback information to the second communication device, which can update the AI ​​model and / or AI model parameters based on the feedback information.

[0069] Optionally, the first communication device includes at least one of the following: a Location Management Function (LMF) network element and an evolved device of the LMF network element;

[0070] Location server;

[0071] Network Data Analytics Function (NWDAF) network element;

[0072] Other network-side devices;

[0073] terminal;

[0074] Actor (monitoring equipment).

[0075] Other network-side equipment includes access network equipment, as well as equipment other than the core network elements mentioned above.

[0076] In this embodiment, the first communication device acquires first information associated with AI model-related information. Based on the first information, the first communication device determines target information, which includes at least one of the following: a target AI model, validity information of AI model-related information, or feedback information obtained from positioning based on the target AI model. Since the first information is used to represent the effective applicable scope of AI model-related information, determining the target information based on the first information can make the positioned AI model more in line with the actual scenario requirements. It can also update the AI ​​model and / or AI model parameters based on the determined target information, making the positioning result obtained based on the updated AI model more accurate.

[0077] Optionally, the validity information may include at least one of the following:

[0078] Validity indication information is used to indicate whether information related to the AI ​​model is valid;

[0079] Effectiveness;

[0080] Valid level;

[0081] Reasons for failure;

[0082] Reliability indication information is used to indicate whether the results obtained from positioning based on the target AI model are reliable;

[0083] Reliability level;

[0084] Reliability level.

[0085] The validity indication information can be indicated by at least one bit, for example, 0 indicates invalid and 1 indicates valid.

[0086] Reliability indication information is similar to validity indication information.

[0087] The degree of validity can be represented by at least one bit, such as the degree of validity between 0 and 1.

[0088] Optionally, the input and / or output of the AI ​​model include at least one of the following:

[0089] Terminal positioning signal measurement information; terminal location information; error information; channel impulse response (CIR); first path power; first path delay; first path time of arrival (TOA); first path reference signal time difference (RSTD); first path angle of arrival; first path antenna subcarrier phase difference; multipath power; multipath delay; multipath TOA; multipath RSTD; multipath angle of arrival; multipath antenna subcarrier phase difference; average excess delay; root mean square delay spread; coherence bandwidth;

[0090] Error information includes at least one of the following: position error value, measurement error value, AI model error value, or AI model parameter error value.

[0091] In one embodiment, the method further includes:

[0092] The first communication device acquires second information from the target terminal; the second information is used to represent the location-related information acquired by the target terminal.

[0093] Step 102 can be achieved in the following way:

[0094] The first communication device determines the target information based on the first information and the second information.

[0095] Specifically, the first information is used to indicate the effective scope of application of AI model-related information, and the second information is used to indicate the location-related information obtained by the target terminal, such as the terminal's measurement information, the terminal's location information, etc.; wherein, the target terminal can be a terminal that needs to be located.

[0096] The first communication device determines, based on the first information and the second information, at least one of the following: the target AI model, the validity information related to the AI ​​model, or the feedback information obtained by positioning based on the target AI model.

[0097] In the above embodiments, the first communication device acquires the second information of the target terminal; the first communication device determines the target information based on the first information and the second information, the target information including at least one of the following: the target AI model, the validity information of the AI ​​model-related information, or the feedback information obtained by positioning based on the target AI model. Since the first information is used to represent the effective applicable scope of the AI ​​model-related information, and the second information represents the positioning-related information acquired by the target terminal; determining the target information based on the first information and the second information can make the positioning AI model more in line with the actual scenario requirements, and can also update the AI ​​model and / or AI model parameters based on the determined target information, so that the positioning result obtained based on the updated AI model is more accurate.

[0098] In one embodiment, the step "the first communication device determines the target information based on the first information and the second information" may include:

[0099] The first communication device determines the target information based on the values ​​of the parameters in the second information and the range of the corresponding parameters in the first information.

[0100] For example, such as Figure 5 As shown, the first communication device determines the target information, such as the validity information, based on the first information, and feeds it back to the model management device. The model management device then trains and updates the model based on the information fed back by the first communication device.

[0101] Optionally, when validity information is used to indicate that AI model-related information is invalid, the second communication device can be a model management device, a data management device, or a validity function verification module (e.g., Actor).

[0102] When validity information is used to indicate that the AI ​​model-related information is valid, the second communication device is at least one of the following: a model management device, an LMF, an NWDAF, or a validity function verification module (e.g., an Actor).

[0103] For example, if the first communication device is an LMF, such as Figure 6 As shown, the LMF and model management device can be the same device or different devices;

[0104] Optionally, the LMF and model application modules can be on one device or on different devices.

[0105] For example, if the first communication device is a terminal, such as Figure 7 As shown, the terminal uses an AI model to locate itself and determine the validity of the information.

[0106] Optionally, the first information includes at least one of the following: cell information; area information; effective time information; scene information; signal-to-interference-plus-noise ratio (SINR) range;

[0107] The community information includes at least one of the following:

[0108] Identification information for one or more cells;

[0109] Identification information of one or more base stations;

[0110] Identification information of one or more Transmission Reception Points (TRPs);

[0111] Community list information;

[0112] Cell frequency domain range information; for example, frequency band identifier (ID);

[0113] The region information includes at least one of the following:

[0114] Region identification information; distance range information; reference point information corresponding to the distance range;

[0115] The valid time information includes at least one of the following:

[0116] Timer duration;

[0117] Timer start time;

[0118] The scene information includes at least one of the following:

[0119] Line-of-sight (LOS) scenes; non-line-of-sight (NLOS) scenes; complex scenes; indoor scenes; outdoor scenes.

[0120] Optionally, complex scenarios may include mixed scenarios of multiple scenarios, and NLOS scenarios may also include NLOS harsh scenarios.

[0121] Among them, the distance range information is, for example, how many distances from a certain reference point it is valid within, such as within 500m.

[0122] Optionally, the second information includes at least one of the following: the target terminal's location information, cell information, area information, timer information, scene information, and the SINR measured by the target terminal;

[0123] Among them, the cell information is at least one of the following information of the serving cell, reference cell, or cell with the strongest reference signal received power (RSRP) of the target terminal, and the at least one information includes: identification information and frequency domain information;

[0124] Among them, the regional information is the regional identification information of the target terminal;

[0125] The scene information refers to the scene information where the target terminal is located.

[0126] Optionally, the location information is obtained through at least one of the following methods, wherein at least one method includes:

[0127] Observed Time Deviation of Arrival (OTDOA), Global Navigation Satellite System (GNSS), downlink time difference of arrival, uplink time difference of arrival, uplink Bluetooth Angle of Arrival (AoA), Bluetooth Angle of Departure (AoD), Bluetooth, sensors, or Wi-Fi.

[0128] Specifically, the first communication device receives first information and AI model-related information. The first information is used to indicate the effective scope of application of the AI ​​model-related information, such as the effective cell, effective area, effective time, effective scenario, and / or effective SINR range of the AI ​​model-related information.

[0129] The second information may be at least one of the following: the target terminal's location information, cell information, area information, timer information, scene information, and the SINR measured by the target terminal.

[0130] The target information is determined based on the parameter values ​​in the second information and the range of the corresponding parameters in the first information. For example, the value of each parameter in the second information is compared with the range of the corresponding parameter in the first information. If the value of the parameter in the second information is within the range of the corresponding parameter in the first information, it indicates that the AI ​​model information is effective. This could mean that all parameters in the second information are within the range of the corresponding parameters in the first information, or that the values ​​of most parameters are within the range of the corresponding parameters in the first information, or even if the values ​​of some parameters are outside the range of the corresponding parameters in the first information, but the deviation from that range is not significant, the AI ​​model information can still be considered effective.

[0131] In one embodiment, determining validity information includes at least one of the following:

[0132] If the value of the parameter in the second information is within the range of the corresponding parameter in the first information, the relevant information of the AI ​​model is valid.

[0133] If the first communication device determines that the cell information of the target terminal does not fall within the scope of the cell information in the first information, the relevant information of the AI ​​model becomes invalid.

[0134] If the first communication device determines that the target terminal's timer has expired, the AI ​​model's related information has become invalid or has timed out.

[0135] If the first communication device determines that the scene information of the target terminal does not fall within the scope of the scene information in the first information, the relevant information of the AI ​​model becomes invalid.

[0136] If the first communication device determines that the location of the target terminal is not within the location range corresponding to the cell information and / or area information in the first information, the relevant information of the AI ​​model becomes invalid.

[0137] Specifically, if the parameter value in the second information is within the range of the corresponding parameter in the first information, then the AI ​​model-related information is valid; if the parameter value in the second information is outside the range of the corresponding parameter in the first information, then the AI ​​model-related information is invalid. Examples include the following situations:

[0138] The target terminal's cell information does not fall within the scope of the cell information in the first information, rendering the AI ​​model's relevant information invalid.

[0139] If the target terminal's regional information does not fall within the scope of the regional information in the first information, the AI ​​model's relevant information becomes invalid.

[0140] The timer on the target terminal times out, and the AI ​​model-related information becomes invalid or times out;

[0141] If the scene information of the target terminal does not fall within the scope of the scene information in the first information, the relevant information of the AI ​​model becomes invalid.

[0142] If the location of the target terminal is not within the location range corresponding to the cell information and / or area information in the first information, the relevant information of the AI ​​model will become invalid.

[0143] If the SINR measured by the target terminal is not within the SINR range of the first information, the relevant information of the AI ​​model becomes invalid.

[0144] Optionally, the timer of the target terminal satisfies at least one of the following conditions:

[0145] The timer duration is the same as the timer duration in the first message;

[0146] The timer starts counting from the timer start time in the first message;

[0147] The timer restarts when the AI ​​model and / or AI model parameters are updated.

[0148] Optionally, the feedback information is determined based on the validity information, including the following cases:

[0149] If validity information is used to indicate that information related to the AI ​​model is valid, the feedback information should at least include the AI ​​model's output; or,

[0150] If the validity information is used to indicate that the AI ​​model-related information is invalid, the feedback information includes at least one of the following: cause of error; second information; validity information; AI model request; AI model update request; data collection request.

[0151] Specifically, after determining the validity information, the content of the feedback information can be determined based on the validity information. For example, when the AI ​​model-related information is valid, the feedback information shall at least include the output of the AI ​​model; or, when the AI ​​model-related information is invalid, the feedback information may include at least one of the following: error cause; second information; validity information; AI model request; AI model update request; data collection request, which can be used to train, select, and update the AI ​​model.

[0152] Optionally, the feedback information includes at least one of the following:

[0153] If the value of the parameter in the second information falls within the range of the corresponding parameter in the first information, the feedback information includes the second information; or,

[0154] If the value of a parameter in the second information is not within the range of the corresponding parameter in the first information, the feedback information includes the second information.

[0155] If the first communication device determines that the cell information of the target terminal does not fall within the scope of the cell information in the first information, the feedback information includes the cell information of the target terminal;

[0156] If the target terminal's region information does not fall within the scope of the region information in the first information, the feedback information includes the target terminal's region information.

[0157] If the first communication device determines that the scene information of the target terminal does not fall within the scope of the scene information in the first information, the feedback information includes the scene information of the target terminal;

[0158] If the location of the target terminal is not within the location range corresponding to the cell information and / or area information in the first information, the feedback information includes the location information of the target terminal;

[0159] If the SINR measured by the target terminal is not within the SINR range in the first information, the feedback information includes the SINR measured by the target terminal.

[0160] If the first communication device determines that the target terminal's timer has timed out, the feedback information includes the target terminal's timer information, such as the timer duration and start time.

[0161] Optionally, if the value of the parameter in the second information is within the first range of the corresponding parameter in the first information, the target AI model is the AI ​​model corresponding to the first range of the first information.

[0162] Optionally, the feedback information includes: the target AI model.

[0163] Specifically, if the parameters in the first information have multiple valid applicable ranges, different valid applicable ranges can correspond to different AI models and / or AI model parameters.

[0164] If the value of a parameter in the second information falls within a certain first range of the corresponding parameter in the first information, the target AI model can be the AI ​​model corresponding to that first range.

[0165] Optionally, the method further includes:

[0166] The first communication device receives multiple pre-configured AI models and / or AI model parameters, as well as first information corresponding to the AI ​​models and / or AI model parameters.

[0167] Optionally, the method further includes:

[0168] The first communication device obtains the AI ​​model corresponding to the first range of the first information from multiple pre-configured AI models based on the first range of the first information.

[0169] Alternatively, as another implementation, the feedback information includes at least one of the following: validity information, second information, first measurement information, and the output of the AI ​​model;

[0170] The first measurement information includes at least one of the following:

[0171] Signal measurement information; location information; error value; channel impulse response (CIR) information; power-delay profile (PDP) information.

[0172] The error value includes at least one of the following: position error value, measurement error value.

[0173] The CIR information includes, for example, time-domain or frequency-domain impulse response information, or processing information of time-domain or frequency-domain impulse response information (such as truncation information), and may include CIR information of a single antenna or multiple antennas.

[0174] In the above embodiments, the first communication device determines target information based on the first information and the second information. The target information includes at least one of the following: a target AI model, validity information of AI model-related information, or feedback information obtained by positioning based on the target AI model. Determining the target information based on the parameter values ​​in the second information and the range of the corresponding parameters in the first information can make the positioning AI model more in line with the actual scenario requirements. It can also update the AI ​​model and / or AI model parameters based on the determined target information, so that the positioning result obtained based on the updated AI model is more accurate.

[0175] In another embodiment, the second information includes second measurement information obtained by the target terminal, and the step "the first communication device determines the target information based on the first information and the second information" can also be implemented through the following steps:

[0176] When the second measurement information is the measurement information obtained from a single measurement, the first communication device determines the target information based on the values ​​of the parameters in the second measurement information and the range of the corresponding parameters in the first information. It is worth noting that, in one case, the single measurement can be understood as the smoothed result of M (M can be at least 1, 2, 3, or 4) measurement instances.

[0177] When the second measurement information is obtained from multiple measurements, the first communication device determines the target information based on the consistency between the distribution of parameters in the second measurement information and the distribution of corresponding parameters in the first information.

[0178] Specifically, the first communication device receives first information and AI model-related information. The first information is used to indicate the effective applicable range of the AI ​​model-related information. In this embodiment, it can specifically indicate the effective applicable range of the input data in which the AI ​​model-related information is obtained, such as SINR range, mean and variance of noise, mean and variance of absolute time, mean and variance of delay spread, mean and variance of angle spread, etc. In other words, the AI ​​model-related information is only valid for input data that is within the above-mentioned effective applicable range.

[0179] In this embodiment, the effective applicable range of the output data containing AI model-related information can be specifically defined, such as the SINR range, the mean and variance of noise, the mean and variance of absolute time, the mean and variance of time delay spread, the mean and variance of angle spread, etc. Another example is the range of measurement and location information. In other words, AI model-related information is only valid for output data within the aforementioned effective applicable range. For instance, if the output measurement and location information exceeds the effective applicable range, it is invalid.

[0180] The second information may be the second measurement information obtained by the target terminal, including at least one of the following: signal-to-interference-plus-noise ratio (SINR) range, noise value, absolute time value introduced by NLOS, delay spread value, angle spread value, mean and variance of SINR, mean and variance of noise, mean and variance of absolute time introduced by NLOS, mean and variance of delay spread, and mean and variance of angle spread.

[0181] One implementation method:

[0182] When the second measurement information is obtained from a single measurement, the first communication device determines the target information based on the parameter values ​​in the second measurement information and the range of the corresponding parameters in the first information. For example, the value of each parameter in the second measurement information is compared with the range of the corresponding parameters in the first information. If the value of the parameter in the second measurement information is within the range of the corresponding parameters in the first information, it indicates that the AI ​​model-related information is valid. This could mean that all parameters in the second measurement information are within the range of the corresponding parameters in the first information, or that the values ​​of most parameters are within the range of the corresponding parameters in the first information, or even if the values ​​of some parameters are outside the range of the corresponding parameters in the first information, but the deviation from that range is not significant, the AI ​​model-related information can still be considered valid.

[0183] like Figure 8 As shown, for example, the absolute time at C1, C2 and C3 is inconsistent with the range of the parameter in the first information. C2 is closer to the range of the parameter in the first information. Therefore, it can be considered that the AI ​​model related information corresponding to C2 is valid, while the information corresponding to C2 and C3 is invalid. Therefore, the validity of C1, C2 and C3 is different, and the errors of C1, C2 and C3 are inconsistent.

[0184] It is worth noting that the failure can be understood as a description of the degree of validity, such as the degree of deviation of C2 from the first information, which can be represented as validity information. Further, in one embodiment, it can be represented as C2 - mean / validity range.

[0185] Another implementation method:

[0186] When the second measurement information is obtained from multiple measurements, the first communication device determines the target information based on the consistency between the distribution of parameters in the second measurement information and the distribution of corresponding parameters in the first information. For example, the distribution of each parameter in the second measurement information is compared with the distribution of the corresponding parameter in the first information. If the distribution of parameters in the second measurement information is consistent with the distribution of corresponding parameters in the first information, it indicates that the AI ​​model-related information is effective. This could mean that the distribution of all parameters in the second measurement information is consistent with the distribution of corresponding parameters in the first information, or that the distribution of most parameters is consistent with the distribution of corresponding parameters in the first information. Even if the distribution of individual parameters is inconsistent with the distribution of corresponding parameters in the first information, but the deviation is not significant, the AI ​​model-related information can still be considered effective.

[0187] like Figure 9 As shown, the distribution of a certain parameter in the second measurement information differs greatly from the distribution of the corresponding parameter in the first information, with only a small overlap. Therefore, it can be considered that the relevant information of the AI ​​model is invalid.

[0188] It should be noted that the failure can be understood as a description of the degree of validity. For example, the degree of deviation between the distribution of a certain parameter in the second measurement information and the first information can be represented as validity information.

[0189] In the above embodiments, the target information is determined based on the values ​​of the parameters in the second measurement information and the range of the corresponding parameters in the first information, and / or the target information is determined based on the distribution of the parameters in the second measurement information and the distribution of the corresponding parameters in the first information. This can make the AI ​​model for positioning more in line with the actual scenario requirements, and can also update the AI ​​model and / or AI model parameters based on the determined target information, so that the positioning results obtained based on the updated AI model are more accurate.

[0190] For example, such as Figure 10 As shown, the first communication device (e.g., a terminal) determines the target information, such as the validity information, based on the first information and the second measurement information, and feeds it back to the model management device (e.g., a network-side device). The model management device then trains and updates the model based on the information fed back by the first communication device.

[0191] For example, such as Figure 11 As shown, the first communication device can be an LMF (Model Management Module), and the model management device and the LMF can be the same device or different devices. Optionally, the LMF and the model application module can be on the same device or on different devices.

[0192] Optionally, the first information includes at least one of the following:

[0193] SINR range;

[0194] The range of noise;

[0195] The mean and / or variance of the noise distribution;

[0196] The absolute time range introduced by NLOS or the mean and / or variance of the absolute time introduced by NLOS;

[0197] The range of delay spread or the mean and / or variance of delay spread;

[0198] The range of the angular expansion or the mean and / or variance of the angular expansion;

[0199] The scope of the first measurement information;

[0200] The mean and / or variance of the first measurement information.

[0201] Optionally, the absolute time introduced by NLOS is the time information obtained by the AI ​​model minus the time information obtained by the non-AI model;

[0202] Delay spread, angle spread, and noise distribution are feature information obtained based on the first measurement information or the output of the AI ​​model.

[0203] Specifically, time information includes, for example, RSTD, TOA, Rx-Tx, timer information, etc.

[0204] Optionally, the second measurement information includes at least one of the following:

[0205] Signal-to-interference-plus-noise ratio (SINR) range, noise value, absolute time value introduced by NLOS, time delay spread, angle spread, mean and variance of SINR, mean and variance of noise, mean and variance of absolute time value introduced by NLOS, mean and variance of time delay spread, mean and variance of angle spread;

[0206] The SINR range and the mean and variance of the SINR are obtained based on the SINR of at least one of the following:

[0207] The noise value and the noise mean and variance are obtained from the noise values ​​of at least one of the following: the measurement channel, the measurement signal, or the first measurement information.

[0208] Optionally, the first measurement information includes at least one of the following:

[0209] Signal measurement information; location information; error value; channel impulse response (CIR) information; power delay spectrum (PDP) information.

[0210] The error value includes at least one of the following: position error value, measurement error value.

[0211] Optionally, the signal measurement information includes at least one of the following:

[0212] Reference Signal Time Difference (RSTD) measurement results, round-trip delay measurement results, angle of arrival (AOA) measurement results, angle of departure (AOD) measurement results, reference signal received power (RSRP), multipath measurement information, and line-of-sight (LOS) indication information;

[0213] Optionally, the multipath measurement information includes at least one of the following:

[0214] The power of the first path, the delay of the first path, the time of arrival (TOA) of the first path, the reference signal time difference (RSTD) of the first path, the phase difference of the antenna subcarriers of the first path, the phase of the antenna subcarriers of the first path, the power of the multipath, the delay of the multipath, the TOA, the RSTD of the multipath, the phase difference of the antenna subcarriers of the multipath or the phase of the antenna subcarriers of the multipath.

[0215] Optionally, the validity information is determined, including at least one of the following:

[0216] If the value of the parameter in the second measurement information is within the range of the corresponding parameter in the first information, the relevant information of the AI ​​model is valid;

[0217] If the value of at least one parameter in the second measurement information is outside the range of the corresponding parameter in the first information, the relevant information of the AI ​​model becomes invalid.

[0218] If the distribution of parameters in the second measurement information is consistent with the distribution of corresponding parameters in the first information, the relevant information of the AI ​​model is valid;

[0219] If the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, the relevant information of the AI ​​model becomes invalid.

[0220] Specifically, the values ​​of the parameters in the second measurement information are compared with the range of the corresponding parameters in the first information. If the values ​​of the parameters in the second measurement information are within the range of the corresponding parameters in the first information, it indicates that the AI ​​model's relevant information is effective. This could mean that all parameters in the second measurement information are within the range of the corresponding parameters in the first information, or that the values ​​of most parameters are within the range of the corresponding parameters in the first information, or even if the values ​​of some parameters are outside the range of the corresponding parameters in the first information, but the deviation from that range is not significant, the AI ​​model's relevant information can still be considered effective. Or,

[0221] If the value of at least one parameter in the second measurement information is outside the range of the corresponding parameter in the first information, or if the values ​​of all parameters in the second measurement information are outside the range of the corresponding parameter in the first information, then the relevant information of the AI ​​model is invalid.

[0222] The distribution of each parameter in the second measurement information is compared with the distribution of the corresponding parameter in the first information. If the distribution of the parameter in the second measurement information is consistent with the distribution of the corresponding parameter in the first information, it indicates that the AI ​​model information is effective. This could mean that the distribution of all parameters in the second measurement information is consistent with the distribution of the corresponding parameter in the first information, or that the distribution of most parameters is consistent with the distribution of the corresponding parameter in the first information, or even if the distribution of some parameters is inconsistent with the distribution of the corresponding parameter in the first information, but the deviation is not significant, the AI ​​model information can still be considered effective. Or,

[0223] If the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, or if the distribution of all parameters in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, it indicates that the relevant information of the AI ​​model is invalid.

[0224] Furthermore, if the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, and if the distribution of the parameter in the second measurement information does not satisfy the condition threshold information, the relevant information of the AI ​​model becomes invalid.

[0225] Optionally, the condition threshold information includes at least one of the following:

[0226] The absolute time corresponding to the σ principle, 2σ principle, or 3σ principle in a normal distribution;

[0227] The time delay spread corresponding to the σ principle, 2σ principle, or 3σ principle;

[0228] The angle extension values ​​corresponding to the σ principle, 2σ principle, or 3σ principle;

[0229] The maximum difference between the mean of the parameter in the second measurement information and the mean of the corresponding parameter in the first information;

[0230] The maximum variance between the mean of the parameter in the second measurement information and the mean of the corresponding parameter in the first information;

[0231] The maximum difference between the mean of the parameter in the second measurement information and the variance of the corresponding parameter in the first information;

[0232] The maximum variance between the mean of the parameter in the second measurement information and the variance of the corresponding parameter in the first information.

[0233] Among them, the σ principle: the probability of the value being distributed in (μ-σ, μ+σ) is 0.6526; the 2σ principle: the probability of the value being distributed in (μ-2σ, μ+2σ) is 0.9544; the 3σ principle: the probability of the value being distributed in (μ-3σ, μ+3σ) is 0.9974.

[0234] In the normal distribution, σ represents the standard deviation and μ represents the mean.

[0235] Optionally, the feedback information includes at least one of the following: validity information, second measurement information, input of the AI ​​model, output of the AI ​​model, AI model recognition information, and AI model update request.

[0236] Optionally, an AI model update request may include at least one of the following:

[0237] The AI ​​model's identifier ID, the AI ​​model and / or AI model parameters that satisfy the second measurement information distribution, and the AI ​​model and / or AI model parameters.

[0238] In one embodiment, the first information is obtained based on the test set and validation set of the AI ​​model, including at least one of the following:

[0239] The first piece of information is the feature information obtained from the input data of the AI ​​model's test and validation sets;

[0240] The first piece of information is the feature information obtained from the output data of the AI ​​model's test set and validation set;

[0241] The first piece of information is the feature information obtained from the input and output data of the AI ​​model's test and validation sets.

[0242] The test set can be the second set of information, and the validation set can be the first set of information.

[0243] In one embodiment, the second measurement information is feature information obtained based on the first measurement information; or,

[0244] The second measurement information is the feature information obtained from the output of the AI ​​model.

[0245] In one embodiment, the second measurement information is feature information obtained based on the first measurement information and the output of the AI ​​model.

[0246] In one embodiment, the first communication device can send target information to the second communication device, for example, send feedback information to the second communication device, and the second communication device can update the AI ​​model and / or AI model parameters based on the feedback information.

[0247] Optionally, the method further includes:

[0248] The first communication device receives the updated AI model and / or AI model parameters, as well as the first information corresponding to the AI ​​model and / or AI model parameters.

[0249] In one embodiment, the AI ​​model includes at least one of the following:

[0250] AI model types;

[0251] AI model structure.

[0252] Among them, AI model types include: CNN, unsupervised, semi-supervised, supervised, RNN, LSTM, and the first communication device using AI for localization or the first communication device only needing to perform some operations when using AI for localization.

[0253] The AI ​​model structure includes, for example:

[0254] A list of neural networks, including at least one of the following: neuron type for each neural network, neuron weights and biases for each neural network;

[0255] Loss function, optimization function type;

[0256] The location and size of pooling and convolutional layers;

[0257] Neural networks, such as fully connected neural networks, convolutional neural networks, recurrent neural networks, residual networks, etc.

[0258] The network structure of an AI model can also be a combination of multiple smaller networks, such as fully connected + convolution, convolution + residual, etc.

[0259] The network structure of an AI model can also include: the number of hidden layers; the connection method between the input layer and the hidden layer, the connection method between multiple hidden layers, the connection method between the hidden layer and the output layer, and the number of neurons in each layer.

[0260] In another embodiment, the AI ​​model includes at least one of the following:

[0261] A list of neural networks, including at least one of the following: neuron type for each neural network, neuron weights and biases for each neural network;

[0262] Hyperparameter information;

[0263] Loss function information.

[0264] Among them, hyperparameter information includes parameters external to the AI ​​model, such as pooling size, batch size (representing the number of samples selected in one training session), iteration method, learning rate, optimization function selection, loss function selection, and other information.

[0265] Optionally, the AI ​​parameters include at least one of the following:

[0266] Hyperparameter information;

[0267] AI model description parameter information;

[0268] Weight information of the AI ​​model;

[0269] Initial parameters of the AI ​​model.

[0270] Among them, AI model description parameter information includes, for example, the input format of AI model parameters and the output format of AI model parameters.

[0271] The initial parameters of the AI ​​model are used to iterate over information related to the target AI model.

[0272] Figure 12 This is the second schematic diagram of the interaction flow of the AI ​​model-based localization method provided in the embodiments of this application. For example... Figure 12 As shown, the method provided in this embodiment includes:

[0273] Step 201: The second communication device receives target information sent by the first communication device. The target information includes at least one of the following: a target AI model, validity information related to the AI ​​model, or feedback information obtained by positioning based on the target AI model.

[0274] The target information is determined based on first information associated with AI model-related information. The first information is used to indicate the effective scope of application of the AI ​​model-related information. The AI ​​model-related information includes at least one of the following: AI model, AI model parameters, AI model input, and AI model output.

[0275] Optionally, the method further includes:

[0276] The second communication device sends the AI ​​model-related information and the first information associated with the AI ​​model-related information to the first communication device.

[0277] Optionally, the method further includes:

[0278] The second communication device sends multiple pre-configured AI models and / or AI model parameters, as well as first information corresponding to the AI ​​models and / or AI model parameters, to the first communication device.

[0279] Optionally, the method further includes:

[0280] The second communication device sends second information to the first communication device, the second information being used to represent the location-related information obtained by the terminal.

[0281] Optionally, the first information includes at least one of the following: cell information; area information; effective time information; scene information; signal-to-interference-plus-noise ratio (SINR) range;

[0282] The cell information includes at least one of the following:

[0283] Identification information for one or more cells;

[0284] Identification information of one or more base stations;

[0285] Identification information of one or more Transmitter Receiving Points (TRPs);

[0286] Community list information;

[0287] Cell frequency domain range information;

[0288] The region information includes at least one of the following:

[0289] Region identification information; distance range information; reference point information corresponding to the distance range;

[0290] The effective time information includes at least one of the following:

[0291] Timer duration;

[0292] Timer start time;

[0293] The scene information includes at least one of the following:

[0294] Line-of-sight (LOS) scenes; non-line-of-sight (NLOS) scenes; complex scenes; indoor scenes; outdoor scenes.

[0295] Optionally, the second information includes at least one of the following: the location information, cell information, area information, timer information, scene information, and SINR measured by the target terminal;

[0296] The cell information is at least one of the following: the serving cell, the reference cell, or the cell with the strongest reference signal received power (RSRP) of the target terminal. The at least one piece of information includes: identification information and frequency domain information.

[0297] The region information refers to the region identification information of the target terminal.

[0298] The scene information refers to the scene information in which the target terminal is located.

[0299] Optionally, if the value of the parameter in the second information is within the range of the corresponding parameter in the first information, the AI ​​model-related information is valid.

[0300] Optionally, if the value of a parameter in the second information is outside the range of the corresponding parameter in the first information, the AI ​​model-related information becomes invalid.

[0301] Optionally, the feedback information includes at least one of the following: the validity information, the second information, the first measurement information, and the output of the AI ​​model;

[0302] The first measurement information includes at least one of the following:

[0303] Signal measurement information; location information; error value; channel impulse response (CIR) information; power delay spectrum (PDP) information.

[0304] Optionally, the second information includes second measurement information obtained by the target terminal, wherein the AI ​​model-related information is valid if the value of the parameter in the second measurement information is within the range of the corresponding parameter in the first information; and / or;

[0305] If the value of at least one parameter in the second measurement information is outside the range of the corresponding parameter in the first information, the AI ​​model-related information becomes invalid.

[0306] Optionally, the second information includes second measurement information obtained by the target terminal, wherein the AI ​​model-related information is valid if the distribution of parameters in the second measurement information is consistent with the distribution of corresponding parameters in the first information; and / or;

[0307] If the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, the relevant information of the AI ​​model becomes invalid.

[0308] Optionally, if the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, the AI ​​model-related information becomes invalid, including:

[0309] If the distribution of parameters in the second measurement information does not meet the condition threshold information as in the distribution of corresponding parameters in the first information, the relevant information of the AI ​​model becomes invalid.

[0310] Optionally, the condition threshold information includes at least one of the following:

[0311] The absolute time corresponding to the σ principle, 2σ principle, or 3σ principle in a normal distribution;

[0312] The time delay spread corresponding to the σ principle, 2σ principle, or 3σ principle;

[0313] The angle extension values ​​corresponding to the σ principle, 2σ principle, or 3σ principle;

[0314] The maximum difference between the mean of the parameter in the second measurement information and the mean of the corresponding parameter in the first information;

[0315] The maximum variance between the mean of the parameter in the second measurement information and the mean of the corresponding parameter in the first information;

[0316] The maximum difference between the mean of the parameter in the second measurement information and the variance of the corresponding parameter in the first information;

[0317] The maximum variance between the mean of the parameter in the second measurement information and the variance of the corresponding parameter in the first information.

[0318] Optionally, the second measurement information includes at least one of the following:

[0319] Signal-to-interference-plus-noise ratio (SINR) range, noise value, absolute time value introduced by NLOS, time delay spread, angle spread, mean and variance of SINR, mean and variance of noise, mean and variance of absolute time value introduced by NLOS, mean and variance of time delay spread, mean and variance of angle spread;

[0320] The SINR range and the SINR mean and variance are obtained based on the SINR of at least one of the following:

[0321] The noise value, noise mean, and variance are obtained from the noise values ​​of at least one of the following:

[0322] The at least one piece of information includes: a measurement channel, a measurement signal, or first measurement information.

[0323] Optionally, the first measurement information includes at least one of the following:

[0324] Signal measurement information; location information; error value; channel impulse response (CIR) information; power delay spectrum (PDP) information.

[0325] Optionally, the feedback information includes at least one of the following: the validity information, the second measurement information, the input of the AI ​​model, the output of the AI ​​model, the AI ​​model recognition information, and the AI ​​model update request.

[0326] It is worth noting that the input to the AI ​​model can be the current input to the AI ​​model, or it can be an input or input distribution determined based on multiple inputs, thus hoping that the other end will provide an AI model and parameters that satisfy this input.

[0327] It is worth noting that the output of the AI ​​model can be the current output of the AI ​​model, or it can be the output or output distribution determined based on multiple inputs, thus hoping that the other end will provide an AI model and parameters that satisfy this output.

[0328] It is worth noting that the input and output of the AI ​​model can be the current input and output of the AI ​​model, or it can be the input and output or the input and output distribution determined based on multiple inputs and outputs, so that the other end can provide an AI model and parameters that satisfy the input and output.

[0329] It is worth noting that the second measurement information can be obtained from a single measurement or it can be a distribution of second measurement information determined by multiple inputs.

[0330] Optionally, the first information includes at least one of the following:

[0331] SINR range;

[0332] The range of noise;

[0333] The mean and / or variance of the noise distribution;

[0334] The absolute time range introduced by NLOS or the mean and / or variance of the absolute time introduced by NLOS;

[0335] The range of delay spread or the mean and / or variance of delay spread;

[0336] The range of the angular expansion or the mean and / or variance of the angular expansion;

[0337] The scope of the first measurement information;

[0338] The mean and / or variance of the first measurement information.

[0339] Optionally, the second communication device includes at least one of the following:

[0340] terminal;

[0341] Model management equipment;

[0342] Network-side equipment.

[0343] The method in this embodiment is similar in its specific implementation process and technical effects to the method embodiment on the first communication device side. For details, please refer to the detailed description in the method embodiment on the first communication device side, which will not be repeated here.

[0344] The AI ​​model-based positioning method provided in this application can be executed by an AI model-based positioning device. This application uses an AI model-based positioning device executing the AI ​​model-based positioning method as an example to illustrate the AI ​​model-based positioning device provided in this application.

[0345] Figure 13 This is one of the structural schematic diagrams of the AI ​​model-based positioning device provided in this application. For example... Figure 13 As shown, the AI ​​model-based positioning device provided in this embodiment includes:

[0346] The acquisition module 210 is used to acquire first information associated with AI model-related information;

[0347] Processing module 220 is configured to determine target information based on the first information, wherein the target information includes at least one of the following: a target AI model, validity information related to the AI ​​model, or feedback information obtained by positioning based on the target AI model;

[0348] The first information is used to indicate the effective scope of application of the AI ​​model-related information, which includes at least one of the following: AI model, AI model parameters, AI model input, and AI model output.

[0349] Optionally, the acquisition module 210 is further configured to:

[0350] Obtain second information about the target terminal; the second information is used to represent the location-related information obtained by the target terminal.

[0351] The processing module 220 is specifically used for:

[0352] The target information is determined based on the first information and the second information.

[0353] Optionally, the first information includes at least one of the following: cell information; area information; effective time information; scene information; signal-to-interference-plus-noise ratio (SINR) range;

[0354] The cell information includes at least one of the following:

[0355] Identification information for one or more cells;

[0356] Identification information of one or more base stations;

[0357] Identification information of one or more Transmitter Receiving Points (TRPs);

[0358] Community list information;

[0359] Cell frequency domain range information;

[0360] The region information includes at least one of the following:

[0361] Region identification information; distance range information; reference point information corresponding to the distance range;

[0362] The effective time information includes at least one of the following:

[0363] Timer duration;

[0364] Timer start time;

[0365] The scene information includes at least one of the following:

[0366] Line-of-sight (LOS) scenes; non-line-of-sight (NLOS) scenes; complex scenes; indoor scenes; outdoor scenes.

[0367] Optionally, the second information includes at least one of the following: the location information, cell information, area information, timer information, scene information, and SINR measured by the target terminal;

[0368] The cell information is at least one of the following: the serving cell, the reference cell, or the cell with the strongest reference signal received power (RSRP) of the target terminal. The at least one piece of information includes: identification information and frequency domain information.

[0369] The region information refers to the region identification information of the target terminal.

[0370] The scene information refers to the scene information in which the target terminal is located.

[0371] Optionally, the processing module 220 is specifically used for:

[0372] The first communication device determines the target information based on the values ​​of the parameters in the second information and the range of the corresponding parameters in the first information.

[0373] Optionally, if the value of the parameter in the second information is within the range of the corresponding parameter in the first information, the AI ​​model-related information is valid.

[0374] Optionally, if the value of the parameter in the second information is within the range of the corresponding parameter in the first information, the feedback information includes the second information; or,

[0375] If the value of a parameter in the second information is not within the range of the corresponding parameter in the first information, the feedback information includes the second information.

[0376] Optionally, if the first communication device determines that the cell information of the target terminal does not fall within the scope of the cell information in the first information, the AI ​​model-related information becomes invalid.

[0377] Optionally, if the first communication device determines that the cell information of the target terminal does not fall within the range of cell information in the first information, the feedback information includes the cell information of the target terminal.

[0378] Optionally, if the first communication device determines that the timer of the target terminal has expired, the AI ​​model-related information becomes invalid or expires.

[0379] Optionally, the timer satisfies at least one of the following conditions:

[0380] The duration of the timer is the same as the timer duration in the first information;

[0381] The timer starts counting from the timer start time in the first information;

[0382] The timer restarts when the AI ​​model and / or AI model parameters are updated.

[0383] Optionally, if the first communication device determines that the scene information of the target terminal does not fall within the scope of the scene information in the first information, the AI ​​model-related information becomes invalid.

[0384] Optionally, if the first communication device determines that the location of the target terminal is not within the location range corresponding to the cell information and / or area information in the first information, the AI ​​model-related information becomes invalid.

[0385] Optionally, if the value of the parameter in the second information is within a first range of the corresponding parameter in the first information, the target AI model is the AI ​​model corresponding to the first range of the first information.

[0386] Optionally, the acquisition module 310 is also used for:

[0387] Receive multiple pre-configured AI models and / or AI model parameters, as well as first information corresponding to the AI ​​models and / or AI model parameters.

[0388] Optionally, the acquisition module 310 is also used for:

[0389] The first communication device obtains the AI ​​model corresponding to the first range of the first information from a plurality of pre-configured AI models based on the first range of the first information.

[0390] Optionally, the feedback information includes the target AI model.

[0391] Optionally, the feedback information is determined based on the validity information and includes:

[0392] If the validity information is used to indicate that the AI ​​model-related information is valid, the feedback information shall at least include the output of the AI ​​model;

[0393] If the validity information is used to indicate that the AI ​​model-related information is invalid, the feedback information includes at least one of the following: error cause; second information; validity information; AI model request; AI model update request; data collection request.

[0394] Optionally, the feedback information includes at least one of the following: the validity information, the second information, the first measurement information, and the output of the AI ​​model;

[0395] The first measurement information includes at least one of the following:

[0396] Signal measurement information; location information; error value; channel impulse response (CIR) information; power delay spectrum (PDP) information.

[0397] Optionally, the second information includes the second measurement information obtained by the target terminal, and the processing module 220 is specifically used for:

[0398] When the second measurement information is the measurement information obtained from a single measurement, the first communication device determines the target information based on the values ​​of the parameters in the second measurement information and the range of the corresponding parameters in the first information;

[0399] When the second measurement information is obtained from multiple measurements, the first communication device determines the target information based on the consistency between the distribution of parameters in the second measurement information and the distribution of corresponding parameters in the first information.

[0400] Optionally, if the value of the parameter in the second measurement information is within the range of the corresponding parameter in the first information, the relevant information of the AI ​​model is valid;

[0401] If the value of at least one parameter in the second measurement information is outside the range of the corresponding parameter in the first information, the AI ​​model-related information becomes invalid.

[0402] Optionally, if the distribution of parameters in the second measurement information is consistent with the distribution of corresponding parameters in the first information, the AI ​​model-related information is valid;

[0403] If the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, the relevant information of the AI ​​model becomes invalid.

[0404] Optionally, if the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, the AI ​​model-related information becomes invalid, including:

[0405] If the distribution of parameters in the second measurement information does not meet the condition threshold information as in the distribution of corresponding parameters in the first information, the relevant information of the AI ​​model becomes invalid.

[0406] Optionally, the condition threshold information includes at least one of the following:

[0407] The absolute time corresponding to the σ principle, 2σ principle, or 3σ principle in a normal distribution;

[0408] The time delay spread corresponding to the σ principle, 2σ principle, or 3σ principle;

[0409] The angle extension values ​​corresponding to the σ principle, 2σ principle, or 3σ principle;

[0410] The maximum difference between the mean of the parameter in the second measurement information and the mean of the corresponding parameter in the first information;

[0411] The maximum variance between the mean of the parameter in the second measurement information and the mean of the corresponding parameter in the first information;

[0412] The maximum difference between the mean of the parameter in the second measurement information and the variance of the corresponding parameter in the first information;

[0413] The maximum variance between the mean of the parameter in the second measurement information and the variance of the corresponding parameter in the first information.

[0414] Optionally, the second measurement information includes at least one of the following:

[0415] Signal-to-interference-plus-noise ratio (SINR) range, noise value, absolute time value introduced by NLOS, time delay spread, angle spread, mean and variance of SINR, mean and variance of noise, mean and variance of absolute time value introduced by NLOS, mean and variance of time delay spread, mean and variance of angle spread;

[0416] The SINR range and the SINR mean and variance are obtained based on the SINR of at least one of the following:

[0417] The noise value, noise mean, and variance are obtained from the noise values ​​of at least one of the following:

[0418] The at least one piece of information includes: a measurement channel, a measurement signal, or first measurement information.

[0419] Optionally, the first measurement information includes at least one of the following:

[0420] Signal measurement information; location information; error value; channel impulse response (CIR) information; power delay spectrum (PDP) information.

[0421] Optionally, the signal measurement information includes at least one of the following:

[0422] Reference signal time difference (RSTD) measurement results, round-trip time delay (RTD) measurement results, angle of arrival (AOA) measurement results, angle of departure (AOD) measurement results, reference information received power (RSRP), multipath measurement information, and line-of-sight (LOS) indication information;

[0423] The multipath measurement information includes at least one of the following:

[0424] The power of the first path, the delay of the first path, the time of arrival (TOA) of the first path, the reference signal time difference (RSTD) of the first path, the phase difference of the antenna subcarriers of the first path, the phase of the antenna subcarriers of the first path, the power of the multipath, the delay of the multipath, the TOA, the RSTD of the multipath, the phase difference of the antenna subcarriers of the multipath or the phase of the antenna subcarriers of the multipath.

[0425] Optionally, the second measurement information may also include the first measurement information.

[0426] Optionally, the feedback information includes at least one of the following: the validity information, the second measurement information, the input of the AI ​​model, the output of the AI ​​model, the AI ​​model recognition information, and the AI ​​model update request.

[0427] Optionally, the first information includes at least one of the following:

[0428] SINR range;

[0429] The range of noise;

[0430] The mean and / or variance of the noise distribution;

[0431] The absolute time range introduced by NLOS or the mean and / or variance of the absolute time introduced by NLOS;

[0432] The range of delay spread or the mean and / or variance of delay spread;

[0433] The range of the angular expansion or the mean and / or variance of the angular expansion;

[0434] The scope of the first measurement information;

[0435] The mean and / or variance of the first measurement information.

[0436] Optionally, the first information is obtained from the test set and validation set of the AI ​​model, including at least one of the following:

[0437] The first information is feature information obtained from the input data of the test set and validation set of the AI ​​model;

[0438] The first piece of information is feature information obtained from the output data of the test set and validation set of the AI ​​model;

[0439] The first piece of information is feature information obtained from the input and output data of the test and validation sets of the AI ​​model.

[0440] Optionally, the second measurement information is feature information obtained based on the first measurement information; and / or,

[0441] The second measurement information is feature information obtained based on the output of the AI ​​model.

[0442] Optionally, the absolute time introduced by the NLOS is the time information obtained by the AI ​​model minus the time information obtained by the non-AI model;

[0443] The time delay spread, angle spread, and noise distribution are feature information obtained based on the first measurement information or the output of the AI ​​model.

[0444] Optionally, the input and / or output of the AI ​​model include at least one of the following:

[0445] The target terminal's positioning signal measurement information; the target terminal's location information; error information; channel impulse response (CIR); first path power; first path delay; first path time of arrival (TOA); first path reference signal time difference (RSTD); first path angle of arrival; first path antenna subcarrier phase difference; multipath power; multipath delay; multipath TOA; multipath RSTD; multipath angle of arrival; multipath antenna subcarrier phase difference; average excess delay; root mean square delay spread; coherence bandwidth;

[0446] The error information includes at least one of the following: position error value, measurement error value, AI model error value, or AI model parameter error value.

[0447] Optionally, the AI ​​model update request includes at least one of the following:

[0448] The AI ​​model's identifier ID, the AI ​​model and / or AI model parameters that satisfy the second measurement information distribution, and the AI ​​model and / or AI model parameters.

[0449] Optionally, the AI ​​model includes at least one of the following:

[0450] AI model types;

[0451] AI model structure.

[0452] Optionally, the AI ​​model includes at least one of the following:

[0453] A list of neural networks, including at least one of the following: neuron type for each neural network, neuron weights and biases for each neural network;

[0454] Hyperparameter information;

[0455] Loss function information.

[0456] Optionally, the AI ​​parameters include at least one of the following:

[0457] Hyperparameter information;

[0458] AI model description parameter information;

[0459] Weight information of the AI ​​model;

[0460] Initial parameters of the AI ​​model.

[0461] Optionally, the validity information may include at least one of the following:

[0462] Validity indication information is used to indicate whether the relevant information of the AI ​​model is valid;

[0463] Effectiveness;

[0464] Valid level;

[0465] Reasons for failure;

[0466] Reliability indication information is used to indicate whether the results obtained from positioning based on the target AI model are reliable;

[0467] Reliability level;

[0468] Reliability level.

[0469] Optionally, the acquisition module 310 is further configured to:

[0470] Receive updated AI model and / or AI model parameters, as well as first information corresponding to the AI ​​model and / or AI model parameters.

[0471] Optionally, the location information is obtained through at least one of the following methods, wherein the at least one method includes:

[0472] OTDOA (Time Difference of Arrival) positioning method, GNSS (Global Navigation Satellite System), downlink time difference of arrival, uplink time difference of arrival, uplink Bluetooth angle of arrival (AoA), Bluetooth angle of departure (AoD), Bluetooth, sensor or Wi-Fi.

[0473] Optionally, the first communication device includes at least one of the following:

[0474] Location management function (LMF) network element and the evolved equipment of the LMF network element;

[0475] Location server;

[0476] Network data analysis function NWADF network element;

[0477] Network-side equipment;

[0478] terminal;

[0479] Actor (monitoring equipment).

[0480] The apparatus of this embodiment can be used to execute the method of any of the aforementioned terminal-side method embodiments. Its specific implementation process and technical effects are similar to those of the terminal-side method embodiments. For details, please refer to the detailed description in the terminal-side method embodiments, which will not be repeated here.

[0481] Figure 14 This is the second structural schematic diagram of the AI-based positioning device provided in this application. Figure 14As shown, the AI ​​model-based positioning device provided in this embodiment includes:

[0482] The receiving module 310 is used to receive target information sent by the first communication device, the target information including at least one of the following: a target AI model, validity information related to the AI ​​model, or feedback information obtained by positioning based on the target AI model;

[0483] The target information is determined based on first information associated with AI model-related information. The first information is used to indicate the effective scope of application of the AI ​​model-related information. The AI ​​model-related information includes at least one of the following: AI model, AI model parameters, AI model input, and AI model output.

[0484] Optionally, it also includes:

[0485] The sending module 320 is used to send the AI ​​model-related information and the first information associated with the AI ​​model-related information to the first communication device.

[0486] Optionally, the sending module 320 is further configured to:

[0487] Send multiple pre-configured AI models and / or AI model parameters, along with first information corresponding to the AI ​​models and / or AI model parameters, to the first communication device.

[0488] Optionally, the sending module 320 is further configured to:

[0489] Send a second message to the first communication device, the second message being used to represent the location-related information obtained by the terminal.

[0490] Optionally, the first information includes at least one of the following: cell information; area information; effective time information; scene information; signal-to-interference-plus-noise ratio (SINR) range;

[0491] The cell information includes at least one of the following:

[0492] Identification information for one or more cells;

[0493] Identification information of one or more base stations;

[0494] Identification information of one or more Transmitter Receiving Points (TRPs);

[0495] Community list information;

[0496] Cell frequency domain range information;

[0497] The region information includes at least one of the following:

[0498] Region identification information; distance range information; reference point information corresponding to the distance range;

[0499] The effective time information includes at least one of the following:

[0500] Timer duration;

[0501] Timer start time;

[0502] The scene information includes at least one of the following:

[0503] Line-of-sight (LOS) scenes; non-line-of-sight (NLOS) scenes; complex scenes; indoor scenes; outdoor scenes.

[0504] Optionally, the second information includes at least one of the following: the location information, cell information, area information, timer information, scene information, and SINR measured by the target terminal;

[0505] The cell information is at least one of the following: the serving cell, the reference cell, or the cell with the strongest reference signal received power (RSRP) of the target terminal. The at least one piece of information includes: identification information and frequency domain information.

[0506] The region information refers to the region identification information of the target terminal.

[0507] The scene information refers to the scene information in which the target terminal is located.

[0508] Optionally, if the value of the parameter in the second information is within the range of the corresponding parameter in the first information, the AI ​​model-related information is valid.

[0509] Optionally, if the value of a parameter in the second information is outside the range of the corresponding parameter in the first information, the AI ​​model-related information becomes invalid.

[0510] Optionally, the feedback information includes at least one of the following: the validity information, the second information, the first measurement information, and the output of the AI ​​model;

[0511] The first measurement information includes at least one of the following:

[0512] Signal measurement information; location information; error value; channel impulse response (CIR) information; power delay spectrum (PDP) information.

[0513] Optionally, the second information includes second measurement information obtained by the target terminal, wherein the AI ​​model-related information is valid if the value of the parameter in the second measurement information is within the range of the corresponding parameter in the first information; and / or;

[0514] If the value of at least one parameter in the second measurement information is outside the range of the corresponding parameter in the first information, the AI ​​model-related information becomes invalid.

[0515] Optionally, the second information includes second measurement information obtained by the target terminal, wherein the AI ​​model-related information is valid if the distribution of parameters in the second measurement information is consistent with the distribution of corresponding parameters in the first information; and / or;

[0516] If the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, the relevant information of the AI ​​model becomes invalid.

[0517] Optionally, if the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, the AI ​​model-related information becomes invalid, including:

[0518] If the distribution of parameters in the second measurement information does not meet the condition threshold information as in the distribution of corresponding parameters in the first information, the relevant information of the AI ​​model becomes invalid.

[0519] Optionally, the condition threshold information includes at least one of the following:

[0520] The absolute time corresponding to the σ principle, 2σ principle, or 3σ principle in a normal distribution;

[0521] The time delay spread corresponding to the σ principle, 2σ principle, or 3σ principle;

[0522] The angle extension values ​​corresponding to the σ principle, 2σ principle, or 3σ principle;

[0523] The maximum difference between the mean of the parameter in the second measurement information and the mean of the corresponding parameter in the first information;

[0524] The maximum variance between the mean of the parameter in the second measurement information and the mean of the corresponding parameter in the first information;

[0525] The maximum difference between the mean of the parameter in the second measurement information and the variance of the corresponding parameter in the first information;

[0526] The maximum variance between the mean of the parameter in the second measurement information and the variance of the corresponding parameter in the first information.

[0527] Optionally, the second measurement information includes at least one of the following:

[0528] Signal-to-interference-plus-noise ratio (SINR) range, noise value, absolute time value introduced by NLOS, time delay spread, angle spread, mean and variance of SINR, mean and variance of noise, mean and variance of absolute time value introduced by NLOS, mean and variance of time delay spread, mean and variance of angle spread;

[0529] The SINR range and the SINR mean and variance are obtained based on the SINR of at least one of the following:

[0530] The noise value, noise mean, and variance are obtained from the noise values ​​of at least one of the following:

[0531] The at least one piece of information includes: a measurement channel, a measurement signal, or first measurement information.

[0532] Optionally, the first measurement information includes at least one of the following:

[0533] Signal measurement information; location information; error value; channel impulse response (CIR) information; power delay spectrum (PDP) information.

[0534] Optionally, the feedback information includes at least one of the following: the validity information, the second measurement information, the input of the AI ​​model, the output of the AI ​​model, the AI ​​model recognition information, and the AI ​​model update request.

[0535] Optionally, the first information includes at least one of the following:

[0536] SINR range;

[0537] The range of noise;

[0538] The mean and / or variance of the noise distribution;

[0539] The absolute time range introduced by NLOS or the mean and / or variance of the absolute time introduced by NLOS;

[0540] The range of delay spread or the mean and / or variance of delay spread;

[0541] The range of the angular expansion or the mean and / or variance of the angular expansion;

[0542] The scope of the first measurement information;

[0543] The mean and / or variance of the first measurement information.

[0544] Optionally, the second communication device includes at least one of the following:

[0545] terminal;

[0546] Model management equipment;

[0547] Network-side equipment.

[0548] The apparatus of this embodiment can be used to execute the method of any of the aforementioned network-side method embodiments. Its specific implementation process and technical effects are similar to those in the network-side method embodiments. For details, please refer to the detailed description in the network-side method embodiments, which will not be repeated here.

[0549] The AI-based positioning device in this embodiment can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the terminal can include, but is not limited to, the type of terminal 11 listed above; other devices can be servers, network attached storage (NAS), etc., and this embodiment does not impose specific limitations.

[0550] The AI-based positioning device provided in this application embodiment can achieve... Figures 2 to 12 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0551] Optional, such as Figure 15 As shown in the illustration, this application also provides a communication device 1500, including a processor 1501 and a memory 1502. The memory 1502 stores programs or instructions that can run on the processor 1501. For example, when the communication device 1500 is a terminal, the program or instructions executed by the processor 1501 implement the various steps of the above-described AI model-based positioning method embodiment and achieve the same technical effect. When the communication device 1500 is a network-side device, the program or instructions executed by the processor 1501 implement the various steps of the above-described AI model-based positioning method embodiment and achieve the same technical effect. To avoid repetition, further details are omitted here.

[0552] This application embodiment also provides a terminal, including a processor and a communication interface. The communication interface is used to acquire first information associated with AI model-related information. The processor is used to determine target information based on the first information. The target information includes at least one of the following: a target AI model, validity information of the AI ​​model-related information, or feedback information obtained by positioning based on the target AI model. The first information is used to indicate the effective applicability range of the AI ​​model-related information. The AI ​​model-related information includes at least one of the following: an AI model, AI model parameters, AI model inputs, and AI model outputs. This terminal embodiment corresponds to the above-described terminal-side method embodiment. All implementation processes and methods of the above-described method embodiments can be applied to this terminal embodiment and achieve the same technical effect. Specifically, Figure 16 A schematic diagram of the hardware structure of a terminal to implement an embodiment of this application.

[0553] The terminal 1000 includes, but is not limited to, at least some of the following components: radio frequency unit 1001, network module 1002, audio output unit 1003, input unit 1004, sensor 1005, display unit 1006, user input unit 1007, interface unit 1008, memory 1009, and processor 1010.

[0554] Those skilled in the art will understand that the terminal 1000 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 1010 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 16 The terminal structure shown does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0555] It should be understood that, in this embodiment, the input unit 1004 may include a graphics processing unit (GPU) 10041 and a microphone 10042. The GPU 10041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 1006 may include a display panel 10061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 1007 includes at least one of a touch panel 10071 and other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 may include a touch detection device and a touch controller. Other input devices 10072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, joysticks, etc., which will not be described in detail here.

[0556] In this embodiment, the radio frequency unit 1001 receives downlink data from the network-side device and transmits it to the processor 1010 for processing. Additionally, the radio frequency unit 1001 can send uplink data to the network-side device. Typically, the radio frequency unit 1001 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier, and a duplexer.

[0557] The memory 1009 can be used to store software programs or instructions and various data. The memory 1009 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first program or instruction storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback function, image playback function, etc.). Furthermore, the memory 1009 may include volatile memory or non-volatile memory, or both. It may include high-speed random access memory and may also include non-volatile memory, wherein the non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or 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 linked dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1009 in this embodiment includes, but is not limited to, these and any other suitable types of memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0558] Processor 1010 may include one or more processing units; optionally, processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications or instructions, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 1010.

[0559] Among them, the radio frequency unit 1001 is used to acquire first information associated with AI model-related information;

[0560] The processor 1010 is configured to determine target information based on the first information, wherein the target information includes at least one of the following: a target AI model, validity information related to the AI ​​model, or feedback information obtained by positioning based on the target AI model;

[0561] The first information is used to indicate the effective scope of application of the AI ​​model-related information, which includes at least one of the following: AI model, AI model parameters, AI model input, and AI model output.

[0562] In the above embodiments, the radio frequency unit acquires first information associated with AI model-related information; the processor determines target information based on the first information, the target information including at least one of the following: target AI model, validity information of AI model-related information, or feedback information obtained by positioning based on the target AI model. Since the first information is used to represent the effective applicable scope of AI model-related information, determining target information based on the first information can make the positioned AI model more in line with the actual scenario requirements, and can also update the AI ​​model and / or AI model parameters based on the determined target information, so that the positioning result obtained based on the updated AI model is more accurate.

[0563] Optionally, the radio frequency unit 1001 is further configured to:

[0564] Obtain second information about the target terminal; the second information is used to represent the location-related information obtained by the target terminal.

[0565] The processor 1010 is specifically used for:

[0566] The target information is determined based on the first information and the second information.

[0567] Optionally, the first information includes at least one of the following: cell information; area information; effective time information; scene information; signal-to-interference-plus-noise ratio (SINR) range;

[0568] The cell information includes at least one of the following:

[0569] Identification information for one or more cells;

[0570] Identification information of one or more base stations;

[0571] Identification information of one or more Transmitter Receiving Points (TRPs);

[0572] Community list information;

[0573] Cell frequency domain range information;

[0574] The region information includes at least one of the following:

[0575] Region identification information; distance range information; reference point information corresponding to the distance range;

[0576] The effective time information includes at least one of the following:

[0577] Timer duration;

[0578] Timer start time;

[0579] The scene information includes at least one of the following:

[0580] Line-of-sight (LOS) scenes; non-line-of-sight (NLOS) scenes; complex scenes; indoor scenes; outdoor scenes.

[0581] Optionally, the second information includes at least one of the following: the location information, cell information, area information, timer information, scene information, and SINR measured by the target terminal;

[0582] The cell information is at least one of the following: the serving cell, the reference cell, or the cell with the strongest reference signal received power (RSRP) of the target terminal. The at least one piece of information includes: identification information and frequency domain information.

[0583] The region information refers to the region identification information of the target terminal.

[0584] The scene information refers to the scene information in which the target terminal is located.

[0585] Optionally, the processor 1010 is specifically used for:

[0586] The first communication device determines the target information based on the values ​​of the parameters in the second information and the range of the corresponding parameters in the first information.

[0587] Optionally, if the value of the parameter in the second information is within the range of the corresponding parameter in the first information, the AI ​​model-related information is valid.

[0588] Optionally, if the value of the parameter in the second information is within the range of the corresponding parameter in the first information, the feedback information includes the second information; or,

[0589] If the value of a parameter in the second information is not within the range of the corresponding parameter in the first information, the feedback information includes the second information.

[0590] Optionally, if the first communication device determines that the cell information of the target terminal does not fall within the scope of the cell information in the first information, the AI ​​model-related information becomes invalid.

[0591] Optionally, if the first communication device determines that the cell information of the target terminal does not fall within the range of cell information in the first information, the feedback information includes the cell information of the target terminal.

[0592] Optionally, if the first communication device determines that the timer of the target terminal has expired, the AI ​​model-related information becomes invalid or expires.

[0593] Optionally, the timer satisfies at least one of the following conditions:

[0594] The duration of the timer is the same as the timer duration in the first information;

[0595] The timer starts counting from the timer start time in the first information;

[0596] The timer restarts when the AI ​​model and / or AI model parameters are updated.

[0597] Optionally, if the first communication device determines that the scene information of the target terminal does not fall within the scope of the scene information in the first information, the AI ​​model-related information becomes invalid.

[0598] Optionally, if the first communication device determines that the location of the target terminal is not within the location range corresponding to the cell information and / or area information in the first information, the AI ​​model-related information becomes invalid.

[0599] Optionally, if the value of the parameter in the second information is within a first range of the corresponding parameter in the first information, the target AI model is the AI ​​model corresponding to the first range of the first information.

[0600] Optionally, the radio frequency unit 1001 is also used for:

[0601] Receive multiple pre-configured AI models and / or AI model parameters, as well as first information corresponding to the AI ​​models and / or AI model parameters.

[0602] Optionally, the radio frequency unit 1001 is also used for:

[0603] The first communication device obtains the AI ​​model corresponding to the first range of the first information from a plurality of pre-configured AI models based on the first range of the first information.

[0604] Optionally, the feedback information includes the target AI model.

[0605] Optionally, the feedback information is determined based on the validity information and includes:

[0606] If the validity information is used to indicate that the AI ​​model-related information is valid, the feedback information shall at least include the output of the AI ​​model;

[0607] If the validity information is used to indicate that the AI ​​model-related information is invalid, the feedback information includes at least one of the following: error cause; second information; validity information; AI model request; AI model update request; data collection request.

[0608] Optionally, the feedback information includes at least one of the following: the validity information, the second information, the first measurement information, and the output of the AI ​​model;

[0609] The first measurement information includes at least one of the following:

[0610] Signal measurement information; location information; error value; channel impulse response (CIR) information; power delay spectrum (PDP) information.

[0611] Optionally, the second information includes the second measurement information obtained by the target terminal, and the processor 1010 is specifically used for:

[0612] When the second measurement information is the measurement information obtained from a single measurement, the first communication device determines the target information based on the values ​​of the parameters in the second measurement information and the range of the corresponding parameters in the first information;

[0613] When the second measurement information is obtained from multiple measurements, the first communication device determines the target information based on the consistency between the distribution of parameters in the second measurement information and the distribution of corresponding parameters in the first information.

[0614] Optionally, if the value of the parameter in the second measurement information is within the range of the corresponding parameter in the first information, the relevant information of the AI ​​model is valid;

[0615] If the value of at least one parameter in the second measurement information is outside the range of the corresponding parameter in the first information, the AI ​​model-related information becomes invalid.

[0616] Optionally, if the distribution of parameters in the second measurement information is consistent with the distribution of corresponding parameters in the first information, the AI ​​model-related information is valid;

[0617] If the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, the relevant information of the AI ​​model becomes invalid.

[0618] Optionally, if the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, the AI ​​model-related information becomes invalid, including:

[0619] If the distribution of parameters in the second measurement information does not meet the condition threshold information as in the distribution of corresponding parameters in the first information, the relevant information of the AI ​​model becomes invalid.

[0620] Optionally, the condition threshold information includes at least one of the following:

[0621] The absolute time corresponding to the σ principle, 2σ principle, or 3σ principle in a normal distribution;

[0622] The time delay spread corresponding to the σ principle, 2σ principle, or 3σ principle;

[0623] The angle extension values ​​corresponding to the σ principle, 2σ principle, or 3σ principle;

[0624] The maximum difference between the mean of the parameter in the second measurement information and the mean of the corresponding parameter in the first information;

[0625] The maximum variance between the mean of the parameter in the second measurement information and the mean of the corresponding parameter in the first information;

[0626] The maximum difference between the mean of the parameter in the second measurement information and the variance of the corresponding parameter in the first information;

[0627] The maximum variance between the mean of the parameter in the second measurement information and the variance of the corresponding parameter in the first information.

[0628] Optionally, the second measurement information includes at least one of the following:

[0629] Signal-to-interference-plus-noise ratio (SINR) range, noise value, absolute time value introduced by NLOS, time delay spread, angle spread, mean and variance of SINR, mean and variance of noise, mean and variance of absolute time value introduced by NLOS, mean and variance of time delay spread, mean and variance of angle spread;

[0630] The SINR range and the SINR mean and variance are obtained based on the SINR of at least one of the following:

[0631] The noise value, noise mean, and variance are obtained from the noise values ​​of at least one of the following:

[0632] The at least one piece of information includes: a measurement channel, a measurement signal, or first measurement information.

[0633] Optionally, the first measurement information includes at least one of the following:

[0634] Signal measurement information; location information; error value; channel impulse response (CIR) information; power delay spectrum (PDP) information.

[0635] Optionally, the signal measurement information includes at least one of the following:

[0636] Reference signal time difference (RSTD) measurement results, round-trip time delay (RTD) measurement results, angle of arrival (AOA) measurement results, angle of departure (AOD) measurement results, reference information received power (RSRP), multipath measurement information, and line-of-sight (LOS) indication information;

[0637] The multipath measurement information includes at least one of the following:

[0638] The power of the first path, the delay of the first path, the time of arrival (TOA) of the first path, the reference signal time difference (RSTD) of the first path, the phase difference of the antenna subcarriers of the first path, the phase of the antenna subcarriers of the first path, the power of the multipath, the delay of the multipath, the TOA, the RSTD of the multipath, the phase difference of the antenna subcarriers of the multipath or the phase of the antenna subcarriers of the multipath.

[0639] Optionally, the second measurement information may also include the first measurement information.

[0640] Optionally, the feedback information includes at least one of the following: the validity information, the second measurement information, the input of the AI ​​model, the output of the AI ​​model, the AI ​​model recognition information, and the AI ​​model update request.

[0641] Optionally, the first information includes at least one of the following:

[0642] SINR range;

[0643] The range of noise;

[0644] The mean and / or variance of the noise distribution;

[0645] The absolute time range introduced by NLOS or the mean and / or variance of the absolute time introduced by NLOS;

[0646] The range of delay spread or the mean and / or variance of delay spread;

[0647] The range of the angular expansion or the mean and / or variance of the angular expansion;

[0648] The scope of the first measurement information;

[0649] The mean and / or variance of the first measurement information.

[0650] Optionally, the first information is obtained from the test set and validation set of the AI ​​model, including at least one of the following:

[0651] The first information is feature information obtained from the input data of the test set and validation set of the AI ​​model;

[0652] The first piece of information is feature information obtained from the output data of the test set and validation set of the AI ​​model;

[0653] The first piece of information is feature information obtained from the input and output data of the test and validation sets of the AI ​​model.

[0654] Optionally, the second measurement information is feature information obtained based on the first measurement information; and / or,

[0655] The second measurement information is feature information obtained based on the output of the AI ​​model.

[0656] Optionally, the absolute time introduced by the NLOS is the time information obtained by the AI ​​model minus the time information obtained by the non-AI model;

[0657] The time delay spread, angle spread, and noise distribution are feature information obtained based on the first measurement information or the output of the AI ​​model.

[0658] Optionally, the input and / or output of the AI ​​model include at least one of the following:

[0659] The target terminal's positioning signal measurement information; the target terminal's location information; error information; channel impulse response (CIR); first path power; first path delay; first path time of arrival (TOA); first path reference signal time difference (RSTD); first path angle of arrival; first path antenna subcarrier phase difference; multipath power; multipath delay; multipath TOA; multipath RSTD; multipath angle of arrival; multipath antenna subcarrier phase difference; average excess delay; root mean square delay spread; coherence bandwidth;

[0660] The error information includes at least one of the following: position error value, measurement error value, AI model error value, or AI model parameter error value.

[0661] Optionally, the AI ​​model update request includes at least one of the following:

[0662] The AI ​​model's identifier ID, the AI ​​model and / or AI model parameters that satisfy the second measurement information distribution, and the AI ​​model and / or AI model parameters.

[0663] Optionally, the AI ​​model includes at least one of the following:

[0664] AI model types;

[0665] AI model structure.

[0666] Optionally, the AI ​​model includes at least one of the following:

[0667] A list of neural networks, including at least one of the following: neuron type for each neural network, neuron weights and biases for each neural network;

[0668] Hyperparameter information;

[0669] Loss function information.

[0670] Optionally, the AI ​​parameters include at least one of the following:

[0671] Hyperparameter information;

[0672] AI model description parameter information;

[0673] Weight information of the AI ​​model;

[0674] Initial parameters of the AI ​​model.

[0675] Optionally, the validity information may include at least one of the following:

[0676] Validity indication information is used to indicate whether the relevant information of the AI ​​model is valid;

[0677] Effectiveness;

[0678] Valid level;

[0679] Reasons for failure;

[0680] Reliability indication information is used to indicate whether the results obtained from positioning based on the target AI model are reliable;

[0681] Reliability level;

[0682] Reliability level.

[0683] Optionally, the radio frequency unit 1001 is further configured to:

[0684] Receive updated AI model and / or AI model parameters, as well as first information corresponding to the AI ​​model and / or AI model parameters.

[0685] Optionally, the location information is obtained through at least one of the following methods, wherein the at least one method includes:

[0686] OTDOA (Time Difference of Arrival) positioning method, GNSS (Global Navigation Satellite System), downlink time difference of arrival, uplink time difference of arrival, uplink Bluetooth angle of arrival (AoA), Bluetooth angle of departure (AoD), Bluetooth, sensor or Wi-Fi.

[0687] Optionally, the first communication device includes at least one of the following:

[0688] Location management function (LMF) network element and the evolved equipment of the LMF network element;

[0689] Location server;

[0690] Network data analysis function NWADF network element;

[0691] Other network-side devices;

[0692] terminal;

[0693] Actor (monitoring equipment).

[0694] This application embodiment also provides a network-side device, including a processor and a communication interface. The communication interface is used to acquire first information associated with AI model-related information. The processor is used to determine target information based on the first information. The target information includes at least one of the following: a target AI model, validity information of the AI ​​model-related information, or feedback information obtained by positioning based on the target AI model. The first information is used to indicate the effective applicability range of the AI ​​model-related information. The AI ​​model-related information includes at least one of the following: an AI model, AI model parameters, AI model inputs, and AI model outputs. This network-side device embodiment corresponds to the above-described first communication device-side or second communication device-side method embodiment. All implementation processes and methods of the above method embodiments can be applied to this network-side device embodiment and can achieve the same technical effects.

[0695] Specifically, embodiments of this application also provide a network-side device. For example... Figure 17 As shown, the network-side device 700 includes: an antenna 71, a radio frequency (RF) device 72, a baseband device 73, a processor 75, and a memory 75. The antenna 71 is connected to the RF device 72. In the uplink direction, the RF device 72 receives information through the antenna 71 and transmits the received information to the baseband device 73 for processing. In the downlink direction, the baseband device 73 processes the information to be transmitted and sends it to the RF device 72. The RF device 72 processes the received information and transmits it through the antenna 71.

[0696] The aforementioned frequency band processing device can be located in the baseband device 73. The method executed by the network-side device in the above embodiments can be implemented in the baseband device 73, which includes a baseband processor 75 and a memory 75.

[0697] The baseband device 73 may include, for example, at least one baseband board on which multiple chips are disposed, such as... Figure 17 As shown, one of the chips is, for example, a baseband processor 75, which is connected to a memory 75 via a bus interface to call the program in the memory 75 and execute the network device operations shown in the above method embodiment.

[0698] The baseband device 73 network-side equipment may also include a network interface 76 for exchanging information with the radio frequency device 72, such as a common public radio interface (CPRI).

[0699] Specifically, the network-side device 700 of this embodiment further includes: instructions or programs stored in a memory 75 and executable on a processor 75, wherein the processor 75 calls the instructions or programs in the memory 75 to execute. Figure 13 or Figure 14 The methods executed by each module shown achieve the same technical effect, and to avoid repetition, they will not be described in detail here.

[0700] This application also provides a network-side device. For example... Figure 18 As shown, the network-side device 700 includes a processor 701, a network interface 702, and a memory 703. The network interface 702 is, for example, a common public radio interface (CPRI).

[0701] Specifically, the network-side device 700 in this application embodiment further includes: instructions or programs stored in memory 703 and executable on processor 701, wherein processor 701 calls the instructions or programs in memory 703 to execute. Figure 13 Alternatively, the methods executed by each module shown in 14 can achieve the same technical effect. To avoid repetition, they will not be described in detail here.

[0702] The first communication device and / or the second communication device can be implemented through the above-described network-side device embodiments.

[0703] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described AI model-based localization method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0704] The processor is the processor in the terminal described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0705] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described AI model-based positioning method embodiment and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0706] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0707] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described AI model-based localization method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0708] This application embodiment also provides a communication system, including: a terminal and a network-side device, wherein the terminal can be used to execute the steps of the AI ​​model-based positioning method as described above, and the network-side device can be used to execute the steps of the AI ​​model-based positioning method as described above.

[0709] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0710] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0711] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A localization method based on an artificial intelligence (AI) model, characterized in that, include: The first communication device acquires first information associated with the AI ​​model; The first communication device determines target information based on the first information, and the target information includes validity information related to the AI ​​model. The first information is used to indicate the effective scope of application of the AI ​​model-related information, which includes at least one of the following: AI model, AI model parameters, AI model input, and AI model output; The method further includes: The first communication device acquires second information from the target terminal; the second information is used to represent the location-related information acquired by the target terminal. The first communication device determines the target information based on the first information, including: The first communication device determines the target information based on the values ​​of the parameters in the second information and the range of the corresponding parameters in the first information.

2. The localization method based on an AI model according to claim 1, characterized in that, The target information also includes: the target AI model and / or feedback information obtained by positioning based on the target AI model.

3. The AI-based localization method according to claim 1 or 2, characterized in that, The first information includes at least one of the following: cell information; area information; effective time information; scene information; signal-to-interference-plus-noise ratio (SINR) range.

4. The localization method based on an AI model according to claim 3, characterized in that, The cell information includes at least one of the following: Identification information for one or more cells; Identification information of one or more base stations; Identification information of one or more Transmitter Receiving Points (TRPs); Community list information; Cell frequency domain range information; The area information includes at least one of the following: Region identification information; distance range information; reference point information corresponding to the distance range; The valid time information includes at least one of the following: Timer duration; Timer start time; Alternatively, the scene information may include at least one of the following: Line-of-sight (LOS) scenes; non-line-of-sight (NLOS) scenes; complex scenes; indoor scenes; outdoor scenes.

5. The localization method based on an AI model according to claim 1, characterized in that, The second information includes at least one of the following: the location information, cell information, area information, timer information, scene information, and SINR measured by the target terminal; The cell information is at least one of the following: the serving cell, the reference cell, or the cell with the strongest reference signal received power (RSRP) of the target terminal. The at least one piece of information includes: identification information and frequency domain information. The region information refers to the region identification information of the target terminal. The scene information refers to the scene information in which the target terminal is located.

6. The localization method based on an AI model according to claim 2, characterized in that, If the value of the parameter in the second information is within the range of the corresponding parameter in the first information, the relevant information of the AI ​​model is valid.

7. The localization method based on an AI model according to claim 2, characterized in that, If the value of the parameter in the second information is within the range of the corresponding parameter in the first information, the feedback information includes the second information; or, If the value of a parameter in the second information is not within the range of the corresponding parameter in the first information, the feedback information includes the second information.

8. The localization method based on an AI model according to claim 1, characterized in that, If the first communication device determines that the cell information of the target terminal does not fall within the scope of the cell information in the first information, the relevant information of the AI ​​model becomes invalid.

9. The localization method based on an AI model according to claim 2, characterized in that, If the first communication device determines that the cell information of the target terminal does not fall within the range of cell information in the first information, the feedback information includes the cell information of the target terminal.

10. The localization method based on an AI model according to claim 2, characterized in that, If the first communication device determines that the timer of the target terminal has expired, the AI ​​model-related information becomes invalid or expires.

11. The localization method based on an AI model according to claim 10, characterized in that, The timer satisfies at least one of the following conditions: The duration of the timer is the same as the timer duration in the first information; The timer starts counting from the timer start time in the first information; The timer restarts when the AI ​​model and / or AI model parameters are updated.

12. The localization method based on an AI model according to claim 2, characterized in that, If the first communication device determines that the scene information of the target terminal does not fall within the scope of the scene information in the first information, the AI ​​model-related information becomes invalid.

13. The localization method based on an AI model according to claim 2, characterized in that, If the first communication device determines that the location of the target terminal is not within the location range corresponding to the cell information and / or area information in the first information, the AI ​​model-related information becomes invalid.

14. The localization method based on an AI model according to claim 2, characterized in that, If the value of a parameter in the second information is within the first range of the corresponding parameter in the first information, then the target AI model is the AI ​​model corresponding to the first range of the first information.

15. The AI-based localization method according to claim 1 or 14, characterized in that, The method further includes: The first communication device receives multiple pre-configured AI models and / or AI model parameters, as well as first information corresponding to the AI ​​models and / or AI model parameters.

16. The localization method based on an AI model according to claim 15, characterized in that, The method further includes: The first communication device obtains the AI ​​model corresponding to the first range of the first information from a plurality of pre-configured AI models based on the first range of the first information.

17. The localization method based on an AI model according to claim 14, characterized in that, The feedback information includes: the target AI model.

18. The localization method based on an AI model according to any one of claims 2, 6, 7, and 10-13, characterized in that, The feedback information, determined based on the validity information, includes: If the validity information is used to indicate that the AI ​​model-related information is valid, the feedback information shall at least include the output of the AI ​​model; If the validity information is used to indicate that the AI ​​model-related information is invalid, the feedback information includes at least one of the following: error cause; the second information; validity information; AI model request; AI model update request; data collection request.

19. The AI-based localization method according to claim 2 or 14, characterized in that, The feedback information includes at least one of the following: the validity information, the second information, the first measurement information, and the output of the AI ​​model; The first measurement information includes at least one of the following: Signal measurement information; location information; error value; channel impulse response (CIR) information; power delay spectrum (PDP) information.

20. The localization method based on an AI model according to claim 2, characterized in that, The second information includes second measurement information obtained by the target terminal, and the method includes: When the second measurement information is the measurement information obtained from a single measurement, the first communication device determines the target information based on the values ​​of the parameters in the second measurement information and the range of the corresponding parameters in the first information; When the second measurement information is obtained from multiple measurements, the first communication device determines the target information based on the consistency between the distribution of parameters in the second measurement information and the distribution of corresponding parameters in the first information.

21. The localization method based on an AI model according to claim 20, characterized in that, If the value of the parameter in the second measurement information is within the range of the corresponding parameter in the first information, the relevant information of the AI ​​model is valid; If the value of at least one parameter in the second measurement information is outside the range of the corresponding parameter in the first information, then the AI ​​model-related information becomes invalid.

22. The localization method based on an AI model according to claim 20, characterized in that, If the distribution of parameters in the second measurement information is consistent with the distribution of corresponding parameters in the first information, the relevant information of the AI ​​model is valid; If the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, the relevant information of the AI ​​model becomes invalid.

23. The localization method based on an AI model according to claim 22, characterized in that, If the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, the AI ​​model-related information becomes invalid, including: If the distribution of parameters in the second measurement information does not meet the condition threshold information as in the distribution of corresponding parameters in the first information, then the relevant information of the AI ​​model becomes invalid.

24. The localization method based on an AI model according to claim 23, characterized in that, The condition threshold information includes at least one of the following: The absolute time corresponding to the σ principle, 2σ principle, or 3σ principle in a normal distribution; The time delay spread corresponding to the σ principle, 2σ principle, or 3σ principle; The angle extension values ​​corresponding to the σ principle, 2σ principle, or 3σ principle; The maximum difference between the mean of the parameter in the second measurement information and the mean of the corresponding parameter in the first information; The maximum variance between the mean of the parameter in the second measurement information and the mean of the corresponding parameter in the first information; The maximum difference between the mean of the parameter in the second measurement information and the variance of the corresponding parameter in the first information; The maximum variance between the mean of the parameter in the second measurement information and the variance of the corresponding parameter in the first information.

25. The localization method based on an AI model according to any one of claims 20-24, characterized in that, The second measurement information includes at least one of the following: Signal-to-interference-plus-noise ratio (SINR) range, noise value, absolute time value introduced by NLOS, time delay spread, angle spread, mean and variance of SINR, mean and variance of noise, mean and variance of absolute time value introduced by NLOS, mean and variance of time delay spread, mean and variance of angle spread; The SINR range and the SINR mean and variance are obtained based on the SINR of at least one of the following: The noise value, noise mean, and variance are obtained from the noise values ​​of at least one of the following: The at least one piece of information includes: a measurement channel, a measurement signal, or first measurement information.

26. The localization method based on an AI model according to claim 25, characterized in that, The first measurement information includes at least one of the following: Signal measurement information; location information; error value; channel impulse response (CIR) information; power delay spectrum (PDP) information.

27. The AI-based localization method according to claim 19 or 26, characterized in that, Signal measurement information includes at least one of the following: Reference signal time difference (RSTD) measurement results, round-trip time delay (RTD) measurement results, angle of arrival (AOA) measurement results, angle of departure (AOD) measurement results, reference information received power (RSRP), multipath measurement information, and line-of-sight (LOS) indication information; The multipath measurement information includes at least one of the following: The power of the first path, the delay of the first path, the time of arrival (TOA) of the first path, the reference signal time difference (RSTD) of the first path, the phase difference of the antenna subcarriers of the first path, the phase of the antenna subcarriers of the first path, the power of the multipath, the delay of the multipath, the TOA, the RSTD of the multipath, the phase difference of the antenna subcarriers of the multipath or the phase of the antenna subcarriers of the multipath.

28. The localization method based on an AI model according to claim 26, characterized in that, The second measurement information also includes the first measurement information.

29. The localization method based on an AI model according to any one of claims 20-24, characterized in that, The feedback information includes at least one of the following: the validity information, the second measurement information, the input of the AI ​​model, the output of the AI ​​model, the AI ​​model recognition information, and the AI ​​model update request.

30. The localization method based on an AI model according to any one of claims 20-24, characterized in that, The first information includes at least one of the following: SINR range; The range of noise; The mean and / or variance of the noise distribution; The absolute time range introduced by NLOS or the mean and / or variance of the absolute time introduced by NLOS; The range of delay spread or the mean and / or variance of delay spread; The range of the angular expansion or the mean and / or variance of the angular expansion; The scope of the first measurement information; The mean and / or variance of the first measurement information.

31. The AI-based localization method according to any one of claims 1-2, 4-14, 16-17, 20-24, 26, and 28, characterized in that, The first piece of information is obtained from the test and validation sets of the AI ​​model, and includes at least one of the following: The first information is feature information obtained from the input data of the test set and validation set of the AI ​​model; The first piece of information is feature information obtained from the output data of the test set and validation set of the AI ​​model; The first piece of information is feature information obtained from the input and output data of the test and validation sets of the AI ​​model.

32. The localization method based on an AI model according to any one of claims 20-24, characterized in that, The second measurement information is feature information obtained based on the first measurement information; and / or, The second measurement information is feature information obtained based on the output of the AI ​​model.

33. The localization method based on an AI model according to claim 30, characterized in that, The absolute time introduced by NLOS is the time information obtained by the AI ​​model minus the time information obtained by the non-AI model; The time delay spread, angle spread, and noise distribution are feature information obtained based on the first measurement information or the output of the AI ​​model.

34. The localization method based on an AI model according to claim 1, characterized in that, The input and / or output of the AI ​​model include at least one of the following: The target terminal's positioning signal measurement information; the target terminal's location information; error information; Channel impulse response (CIR); first path power; first path delay; first path time of arrival (TOA); first path reference signal time difference (RSTD); first path angle of arrival; first path antenna subcarrier phase difference; multipath power; multipath delay; multipath TOA; multipath RSTD; multipath angle of arrival; multipath antenna subcarrier phase difference; average excess delay; root mean square delay spread; coherence bandwidth; The error information includes at least one of the following: position error value, measurement error value, AI model error value, or AI model parameter error value.

35. The localization method based on an AI model according to claim 29, characterized in that, The AI ​​model update request includes at least one of the following: The AI ​​model's identifier ID, the AI ​​model and / or AI model parameters that satisfy the second measurement information distribution, and the AI ​​model and / or AI model parameters.

36. The AI-based localization method according to any one of claims 1-2, 4-14, 16-17, 20-24, 26, 28, and 33-35, characterized in that, The AI ​​model includes at least one of the following: AI model types; AI model structure.

37. The AI-based localization method according to any one of claims 1-2, 4-14, 16-17, 20-24, 26, 28, and 33-35, characterized in that, The AI ​​model includes at least one of the following: A list of neural networks, including at least one of the following: neuron type for each neural network, neuron weights and biases for each neural network; Hyperparameter information; Loss function information.

38. The AI-based localization method according to any one of claims 1-2, 4-14, 16-17, 20-24, 26, 28, and 33-35, characterized in that, The AI ​​model parameters include at least one of the following: Hyperparameter information; AI model description parameter information; Weight information of the AI ​​model; Initial parameters of the AI ​​model.

39. The localization method based on an AI model according to any one of claims 2, 14, and 17, characterized in that, The validity information includes at least one of the following: Validity indication information is used to indicate whether the relevant information of the AI ​​model is valid; Effectiveness; Valid level; Reasons for failure; Reliability indication information is used to indicate whether the results obtained from positioning based on the target AI model are reliable; Reliability level; Reliability level.

40. The AI-based localization method according to any one of claims 1-2, 4-14, 16-17, 20-24, 26, 28, and 33-35, characterized in that, The method further includes: The first communication device receives the updated AI model and / or AI model parameters, as well as first information corresponding to the AI ​​model and / or AI model parameters.

41. The localization method based on an AI model according to any one of claims 5, 26, or 34, characterized in that, The location information is obtained through at least one of the following methods, wherein the at least one method includes: OTDOA (Time Difference of Arrival) positioning method, GNSS (Global Navigation Satellite System), downlink time difference of arrival, uplink time difference of arrival, uplink Bluetooth angle of arrival (AoA), Bluetooth angle of departure (AoD), Bluetooth, sensor or Wi-Fi.

42. The AI-based localization method according to any one of claims 1-2, 4-14, 16-17, 20-24, 26, 28, and 33-35, characterized in that, The first communication device includes at least one of the following: Location management function (LMF) network element and the evolved equipment of the LMF network element; Location server; Network data analysis function NWADF network element; Other network-side devices; terminal; Actor (monitoring equipment).

43. A localization method based on an AI model, characterized in that, include: The second communication device receives target information sent by the first communication device, the target information including validity information related to the AI ​​model; The target information is determined based on first information associated with AI model-related information. The first information is used to indicate the effective scope of application of the AI ​​model-related information. The AI ​​model-related information includes at least one of the following: AI model, AI model parameters, AI model input, and AI model output. The method further includes: The second communication device sends second information to the first communication device, the second information being used to represent the location-related information obtained by the target terminal; The target information is specifically determined based on the values ​​of the parameters in the second information and the range of the corresponding parameters in the first information.

44. The localization method based on an AI model according to claim 43, characterized in that, The method further includes: The second communication device sends the AI ​​model-related information and the first information associated with the AI ​​model-related information to the first communication device.

45. The localization method based on an AI model according to claim 43, characterized in that, The method further includes: The second communication device sends multiple pre-configured AI models and / or AI model parameters, as well as first information corresponding to the AI ​​models and / or AI model parameters.

46. ​​The localization method based on an AI model according to any one of claims 43-45, characterized in that, The first information includes at least one of the following: cell information; area information; effective time information; scene information; signal-to-interference-plus-noise ratio (SINR) range.

47. The localization method based on an AI model according to claim 43, characterized in that, The second information includes at least one of the following: the location information, cell information, area information, timer information, scene information, and SINR measured by the target terminal; The cell information is at least one of the following: the serving cell, the reference cell, or the cell with the strongest reference signal received power (RSRP) of the target terminal. The at least one piece of information includes: identification information and frequency domain information. The region information refers to the region identification information of the target terminal. The scene information refers to the scene information in which the target terminal is located.

48. The localization method based on an AI model according to claim 43, characterized in that, If the value of the parameter in the second information is within the range of the corresponding parameter in the first information, the relevant information of the AI ​​model is valid.

49. The localization method based on an AI model according to claim 43, characterized in that, If the value of a parameter in the second information is outside the range of the corresponding parameter in the first information, the relevant information of the AI ​​model becomes invalid.

50. The localization method based on an AI model according to claim 43, characterized in that, The target information also includes the target AI model or feedback information obtained by positioning based on the target AI model; The feedback information includes at least one of the following: the validity information, the second information, the first measurement information, and the output of the AI ​​model; The first measurement information includes at least one of the following: Signal measurement information; location information; error value; channel impulse response (CIR) information; power delay spectrum (PDP) information.

51. The localization method based on an AI model according to claim 43, characterized in that, The second information includes the second measurement information obtained by the target terminal. If the value of a parameter in the second measurement information is within the range of the corresponding parameter in the first information, the AI ​​model-related information is valid; and / or; If the value of at least one parameter in the second measurement information is outside the range of the corresponding parameter in the first information, the AI ​​model-related information becomes invalid.

52. The localization method based on an AI model according to claim 43, characterized in that, The second information includes the second measurement information obtained by the target terminal. If the distribution of parameters in the second measurement information is consistent with the distribution of corresponding parameters in the first information, the AI ​​model-related information is valid; and / or; If the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, the relevant information of the AI ​​model becomes invalid.

53. The localization method based on an AI model according to claim 52, characterized in that, If the distribution of at least one parameter in the second measurement information is inconsistent with the distribution of the corresponding parameter in the first information, the AI ​​model-related information becomes invalid, including: If the distribution of parameters in the second measurement information does not meet the condition threshold information as in the distribution of corresponding parameters in the first information, the relevant information of the AI ​​model becomes invalid.

54. The localization method based on an AI model according to claim 53, characterized in that, The condition threshold information includes at least one of the following: The absolute time corresponding to the σ principle, 2σ principle, or 3σ principle in a normal distribution; The time delay spread corresponding to the σ principle, 2σ principle, or 3σ principle; The angle extension values ​​corresponding to the σ principle, 2σ principle, or 3σ principle; The maximum difference between the mean of the parameter in the second measurement information and the mean of the corresponding parameter in the first information; The maximum variance between the mean of the parameter in the second measurement information and the mean of the corresponding parameter in the first information; The maximum difference between the mean of the parameter in the second measurement information and the variance of the corresponding parameter in the first information; The maximum variance between the mean of the parameter in the second measurement information and the variance of the corresponding parameter in the first information.

55. The localization method based on an AI model according to any one of claims 51-54, characterized in that, The second measurement information includes at least one of the following: Signal-to-interference-plus-noise ratio (SINR) range, noise value, absolute time value introduced by NLOS, time delay spread, angle spread, mean and variance of SINR, mean and variance of noise, mean and variance of absolute time value introduced by NLOS, mean and variance of time delay spread, mean and variance of angle spread; The SINR range and the SINR mean and variance are obtained based on the SINR of at least one of the following: The noise value, noise mean, and variance are obtained from the noise values ​​of at least one of the following: The at least one piece of information includes: a measurement channel, a measurement signal, or first measurement information.

56. The localization method based on an AI model according to claim 55, characterized in that, The first measurement information includes at least one of the following: Signal measurement information; location information; error value; channel impulse response (CIR) information; power delay spectrum (PDP) information.

57. The localization method based on an AI model according to any one of claims 51-54, characterized in that, The target information also includes the target AI model or feedback information obtained by positioning based on the target AI model; The feedback information includes at least one of the following: the validity information, the second measurement information, the input of the AI ​​model, the output of the AI ​​model, the AI ​​model recognition information, and the AI ​​model update request.

58. The localization method based on an AI model according to any one of claims 51-54, characterized in that, The first information includes at least one of the following: SINR range; The range of noise; The mean and / or variance of the noise distribution; The absolute time range introduced by NLOS or the mean and / or variance of the absolute time introduced by NLOS; The range of delay spread or the mean and / or variance of delay spread; The range of the angular expansion or the mean and / or variance of the angular expansion; The scope of the first measurement information; The mean and / or variance of the first measurement information.

59. The localization method based on an AI model according to any one of claims 43-45, 47-54, and 56, characterized in that, The second communication device includes at least one of the following: terminal; Model management equipment; Network-side equipment.

60. A positioning device for an AI model, characterized in that, include: The acquisition module is used to acquire the first information associated with the AI ​​model. The processing module is used to determine target information based on the first information, wherein the target information includes validity information related to the AI ​​model; The first information is used to indicate the effective scope of application of the AI ​​model-related information, which includes at least one of the following: AI model, AI model parameters, AI model input, and AI model output; The processing module is specifically used for: Obtain second information about the target terminal; the second information is used to represent the location-related information obtained by the target terminal. The target information is determined based on the values ​​of the parameters in the second information and the range of the corresponding parameters in the first information.

61. A positioning device for an AI model, characterized in that, include: A receiving module is used to receive target information sent by a first communication device, wherein the target information includes validity information related to the AI ​​model; The target information is determined based on first information associated with AI model-related information. The first information is used to indicate the effective scope of application of the AI ​​model-related information. The AI ​​model-related information includes at least one of the following: AI model, AI model parameters, AI model input, and AI model output. The device further includes a transmitting module for: Send a second message to the first communication device, the second message being used to represent the location-related information obtained by the target terminal; The target information is specifically determined based on the values ​​of the parameters in the second information and the range of the corresponding parameters in the first information.

62. A first communication device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the AI ​​model-based localization method as described in any one of claims 1 to 42.

63. A second communication device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the AI ​​model-based localization method as described in any one of claims 43 to 59.

64. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions, which, when executed by a processor, implement the AI ​​model-based localization method as described in any one of claims 1 to 42, or implement the steps of the AI ​​model-based localization method as described in any one of claims 43 to 59.

Images