Positioning method and apparatus, network-side device, and terminal

Abstract

The application discloses a positioning method and device, a network side equipment and a terminal, and belongs to the technical field of communication. The positioning method of the application comprises the following steps: a terminal receives AI model information from a network side equipment; and the terminal executes a positioning process according to the AI model information. The AI model information comprises configuration information of N AI models and an association relationship between the N AI models and positioning reference signal (PRS) ports, wherein N is a positive integer greater than or equal to 1.

Description

Technical Field

[0001] This application belongs to the field of communication technology, specifically relating to a positioning method, device, network-side equipment, and terminal. Background Technology

[0002] The Positioning Reference Signal (PRS) is a reference signal (RS) used for downlink positioning. In a wireless network, transmission devices (e.g., base station equipment) can transmit the PRS. Terminals process the measurements of the PRS transmitted by any base station equipment using a unified processing method, thereby achieving terminal positioning.

[0003] However, different transmission devices have different channel characteristics when transmitting PRS. It is difficult to achieve accurate terminal positioning by using a uniform processing method to process PRS measurements from different transmission devices. Summary of the Invention

[0004] This application provides a positioning method, apparatus, network-side device, and terminal, which can solve the problem that existing downlink positioning methods are difficult to accurately locate the terminal because they use a uniform processing method to process PRS measurements from different transmission devices.

[0005] Firstly, a positioning method is provided, including:

[0006] The terminal receives AI model information from network-side devices;

[0007] The terminal executes a positioning process based on the AI ​​model information, which includes: configuration information of N AI models and the association between the N AI models and the positioning reference signal PRS port, where N is a positive integer greater than or equal to 1.

[0008] Secondly, a positioning method is provided, including:

[0009] The network-side device sends AI model information to the terminal, so that the terminal can perform a positioning process based on the AI ​​model information;

[0010] The AI ​​model information includes: configuration information of N AI models, and the association between the N AI models and the positioning reference signal (PRS) port, where N is a positive integer greater than or equal to 1.

[0011] Thirdly, a positioning device is provided, comprising:

[0012] The receiving module is used to receive AI model information from network-side devices;

[0013] The positioning module is used to execute the positioning process based on the AI ​​model information. The AI ​​model information includes: configuration information of N AI models and the association relationship between the N AI models and the positioning reference signal PRS port, where N is a positive integer greater than or equal to 1.

[0014] Fourthly, a positioning device is provided, comprising:

[0015] The model information sending module is used to send AI model information to the terminal so that the terminal can execute the positioning process based on the AI ​​model information;

[0016] The AI ​​model information includes: configuration information of N AI models, and the association between the N AI models and the positioning reference signal (PRS) port, where N is a positive integer greater than or equal to 1.

[0017] Fifthly, a terminal is provided, comprising 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 positioning method as described in the first aspect.

[0018] In a sixth aspect, a network-side device is provided, 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 positioning method as described in the second aspect.

[0019] In a seventh aspect, a positioning system is provided, comprising: a network-side device and a terminal, wherein the terminal is configured to perform the steps of the positioning method as described in the first aspect above, and the network-side device is configured to perform the steps of the positioning method as described in the second aspect above.

[0020] Eighthly, 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 positioning method as described in the first aspect, or implement the steps of the positioning method as described in the second aspect.

[0021] In a ninth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being used to run a program or instructions to implement the positioning method as described in the first aspect, or to implement the positioning method as described in the second aspect.

[0022] In a tenth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the positioning method as described in the first or second aspect.

[0023] In this embodiment, the network-side device sends configuration information of N AI models and the association between the N AI models and PRS ports to the terminal, enabling the terminal to configure the N AI models according to the configuration information. Based on the association between each AI model and the PRS port, the terminal measures the PRS of the PRS port associated with each AI model in a targeted manner, so that the N AI models can process the measurement of their associated PRS separately, thereby improving the positioning accuracy of the terminal. Attached Figure Description

[0024] Figure 1 This is a block diagram of a wireless communication system applicable to embodiments of this application;

[0025] Figure 2 This is a schematic diagram of the neural network in an embodiment of this application;

[0026] Figure 3 This is a schematic diagram of a neuron in a neural network according to an embodiment of this application;

[0027] Figure 4 This is a flowchart of a positioning method in an embodiment of this application;

[0028] Figure 5 This is a flowchart of another positioning method in the embodiments of this application;

[0029] Figure 6 This is a schematic diagram of the PRS pattern under the combination of 2 symbols and Comb 2 in the embodiments of this application;

[0030] Figure 7 This is a schematic diagram of the PRS pattern under the combination of 4 symbols and Comb 4 in the embodiments of this application;

[0031] Figure 8 This is a schematic diagram of the PRS pattern under the combination of 6 symbols and Comb 6 in the embodiments of this application;

[0032] Figure 9 This is a schematic diagram of the PRS pattern under the combination of 12 symbols and Comb 12 in the embodiments of this application;

[0033] Figure 10 This is a structural block diagram of a positioning device according to an embodiment of this application;

[0034] Figure 11 This is a structural block diagram of another positioning device in the embodiments of this application;

[0035] Figure 12This is a structural block diagram of a communication device according to an embodiment of this application;

[0036] Figure 13 This is a structural block diagram of a terminal device according to an embodiment of this application;

[0037] Figure 14 This is a structural block diagram of a terminal according to an embodiment of this application;

[0038] Figure 15 This is a structural block diagram of a network-side device in an embodiment of this application. Detailed Implementation

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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 device 11 and a network-side device 12. The terminal device 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 device 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), and Binding Support Function. Support Function (BSF), Application Function (AF), etc. It should be noted that this application embodiment only uses the core network equipment in the NR system as an example for description, and does not limit the specific type of core network equipment.

[0043] The positioning method provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0044] Firstly, see [the following] Figure 4 The diagram shown is an implementation flowchart of a positioning method provided in this application embodiment. The method may include the following steps:

[0045] Step 401: The terminal receives AI model information from the network-side device.

[0046] In this embodiment of the application, the terminal may be Figure 1The terminal device 11 in the text, for example of which can be found in the previous text, will not be repeated here.

[0047] Step 402: The terminal executes the positioning process according to the AI ​​model information, wherein the AI ​​model information includes: configuration information of N AI models and the association between the N AI models and the positioning reference signal PRS port.

[0048] As one possible implementation, the configuration information of the N AI models is determined based on the N AI models trained by the network-side device, and the association between the N AI models and the Positioning Reference Signal (PRS) port is determined based on the training samples corresponding to the N AI models, where N is a positive integer greater than or equal to 1.

[0049] The configuration information for the aforementioned AI model can be obtained by training an initial AI model using network-side devices. This initial AI model can be any of the following artificial intelligence models: fully connected neural network, convolutional neural network, decision tree, support vector machine, or Bayesian classifier. Taking a neural network model as an example, its schematic diagram is shown below. Figure 2 As shown. Furthermore, neural networks are composed of neurons, and a schematic diagram of a neuron is shown below. Figure 3 As shown. Among them, in Figure 3 In the middle, a1, a2, ... a K σ represents the input, w represents the weights (i.e., multiplicative coefficients), b represents the bias (i.e., additive coefficients), and σ(.) represents the activation function. Activation functions include Sigmoid (maps variables to between 0 and 1), tanh (shifts and shrinks the Sigmoid), and Rectified Linear Unit (ReLU), etc.

[0050] Furthermore, taking neural network models as an example, the process of training a model on the network side can be as follows: the parameters of the neural network are optimized using gradient optimization algorithms. Gradient optimization algorithms are a class of algorithms that minimize or maximize an objective function (sometimes called a loss function), and the objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, a neural network model f(.) can be constructed. Then, based on the input x, the predicted output f(x) can be obtained, and the difference between the predicted value and the true value (f(x)-Y) can be calculated, which is the loss function. The optimization objective of the gradient optimization algorithm is to find suitable w (i.e., weights) and b (i.e., biases) to minimize the value of the above loss function. The smaller the loss value, the closer the model is to the reality.

[0051] The optimization algorithm can be based on the error back propagation (BP) algorithm. The basic idea of ​​the BP algorithm is that the learning process consists of two processes: 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 in a certain form, distributing the error to all units in each layer, thereby 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 of each layer through forward and backward propagation is repeated continuously. The continuous adjustment of the 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.

[0052] In addition, optimization algorithms may include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov (a type of stochastic gradient descent algorithm with momentum), adaptive gradient descent (Adagrad), Adadelta (an extension of Adagrad), root mean square prop (RMSprop), and adaptive momentum estimation (Adam).

[0053] 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.

[0054] As can be seen from the above, in this embodiment of the application, after the network-side device trains the initial AI model and obtains the trained AI model, it can send the relevant information of the trained N AI models as the configuration information of the N AI models to the terminal, so that the terminal can deploy the corresponding N AI models locally on the terminal according to the configuration information of the N AI models, where N is a positive integer greater than or equal to 1.

[0055] After receiving configuration information for N AI models from the network-side device, the terminal can deploy N AI models locally based on this configuration information. The positioning function is then achieved by measuring the PRS (Pulse Responsibility) of the PRS ports associated with each AI model. The measurement is obtained by the terminal measuring the PRS emitted by the specific PRS port associated with each AI model, based on the association between each AI model and its PRS port. This specific PRS port can be one or more PRS ports of a single TRP (Transfer Reference Point), or it can be PRS ports of multiple TRPs. For example, assuming the specific TRP group associated with an AI model contains N TRPs, the number of ports used by each TRP to send PRS can be represented as {M_1, M_2, ..., M_N}, where N, M_1, M_2, ..., M_N are all positive integers greater than or equal to 1. This application embodiment does not limit the number of PRS ports associated with the AI ​​models or the TRPs to which each PRS port belongs.

[0056] For example, the PRS port associated with the configured AI model can be one or more PRS ports of a single TPR, or it can be the PRS ports of multiple TRPs, which can come from the serving cell or a non-serving cell. After the terminal device completes the configuration of multiple AI models according to the AI ​​model information, it can measure the PRS transmitted by the corresponding PRS ports of the multiple TRPs, and then combine the AI ​​model and the measurement results of multiple PRSs to realize the reporting of positioning measurements or to perform positioning calculations.

[0057] As one possible implementation, before the terminal executes the positioning process, it further includes:

[0058] The terminal configures N AI models according to the configuration information of the AI ​​models;

[0059] The terminal executes a positioning process, including:

[0060] The terminal measures the positioning reference signal associated with each of the N AI models according to the correlation between the N AI models and the positioning reference signal PRS port, and obtains N measurement quantities, the N measurement quantities including the channel impulse response corresponding to the PRS port associated with each of the N AI models;

[0061] The terminal inputs the N measurements into their respective associated AI models to obtain positioning information output by the N AI models for the terminal, and then returns the N positioning information to the network-side device.

[0062] The input to the AI ​​model (i.e., the measurement quantity associated with the AI ​​model) includes the measurement information of the PRS emitted by each PRS port associated with it. This measurement information can be the channel impulse response (which describes the channel characteristics; each PRS port associated with the AI ​​model corresponds to a channel impulse response), or other parameters determined based on the PRS measurement results. The output of the AI ​​model (i.e., the location information) can be the location information of the terminal, or intermediate parameters used to calculate the location information of the terminal. For example, the location information can be the signal arrival time of the PRS associated with the AI ​​model. This application embodiment does not impose specific limitations on the input and output of the AI ​​model.

[0063] As can be seen from steps 401 to 402 above, in this embodiment of the application, the network-side device sends the configuration information of N AI models and the association relationship between the N AI models and the PRS port to the terminal, so that the terminal can configure the N AI models according to the configuration information of the N AI models. The terminal measures the PRS of the PRS port associated with each AI model in a targeted manner according to the association relationship between each AI model and the PRS port, so that the N AI models can process the measurement of the PRS associated with them respectively, thereby improving the positioning accuracy of the terminal.

[0064] In this embodiment, considering the different channel characteristics of PRS transmission through different PRS ports, the network-side device trains N AI models to process the measurements transmitted through different PRS ports. To enable the terminal to use the adapted AI model to process the measurements transmitted through each PRS port, the network-side device, in addition to sending configuration information for the terminal to configure the N AI models locally, also sends the association relationships between the N AI models and the positioning reference signal (PRS) ports. This allows the terminal to clearly identify which PRS port each of the locally configured N AI models is associated with. The specific content of the association relationships sent by the network-side device to the terminal depends on whether the PRS ports are numbered repeatedly. If the PRS ports are numbered repeatedly, the network-side device sends a first association relationship and a second association relationship to the terminal. If the PRS ports are not numbered repeatedly, the network-side device only sends the first association relationship to the terminal. This embodiment does not specifically limit the specific content of the association relationships sent by the network-side device to the terminal, as long as the terminal can determine the uniquely associated PRS port for each local AI model based on the association relationships. Specific details are as follows:

[0065] In the case of repeated PRS port numbering, the association between the N AI models and the positioning reference signal PRS port includes: a first association between the N AI models and the TRP group, and a second association between the N AI models and the PRS port group;

[0066] When the PRS ports are not numbered repeatedly, the association between the N AI models and the positioning reference signal PRS ports includes: the second association between the N AI models and the PRS port group;

[0067] Each AI model is associated with a TRP group that includes one or more TRPs, and each AI model is associated with a PRS port group that includes one or more PRS ports.

[0068] With PRS ports having unique numbers, each PRS port can be identified by querying the numbers of each PRS port belonging to the PRS port group, based solely on the association between the AI ​​model and the PRS port group.

[0069] In the case of duplicate PRS port numbers, different PRS ports belonging to different TRPs may have the same number, but different PRS ports belonging to the same TRP may have different numbers. Therefore, based on the association between the AI ​​model and the PRS port group, as well as the association between the AI ​​model and the TRP group, the PRS ports associated with the AI ​​model can be found by using the numbers of each PRS port associated with the AI ​​model and the TRP to which each PRS port belongs.

[0070] Optionally, the first association between the N AI models and the TRP group includes at least one of the following:

[0071] Item A-1: ​​The association between each AI model and the identification information of the TRP group;

[0072] Item A-2: The relationship between each AI model and the configuration information of the TRP group.

[0073] For item A-1, the identification information of the TRP group can be the numerical ID of the TRP group. That is, each TRP is pre-grouped, and then an ID is assigned to each TRP group. An association table is built based on the correspondence between the ID of the TRP group and the TRPs in the TRP group. In this way, the network-side device can send only the identification information of the TRP group to the terminal. When the terminal receives the ID of the TRP group, it can determine which TRPs are in the TRP group by querying the aforementioned association table. For example, if the ID of the TRP group is A1, it can be found by looking up the table that there are TRP1 and TRP2 in the TRP group (TRP1 and TRP2 refer to two different TRPs).

[0074] For item A-2, the configuration information of the TRP group is used to describe the relevant information of each TRP within the TRP group.

[0075] Optionally, the configuration information of the TRP group includes at least one of the following:

[0076] The quantity information of TRPs within the TRP group;

[0077] The identification information of each TRP within the TRP group;

[0078] The location information of each TRP within the TRP group.

[0079] The identification information of each TRP within a TRP group can be used by the terminal to determine the TRP associated with the AI ​​model and related information of that TRP. The identification information of a TRP can be a numerical ID of the TRP, and the IDs of each TRP are unique. For example, if TRP1 is assigned ID 1 and TRP2 is assigned ID 2, then the identification information of each TRP within the TRP group containing TRP1 and TRP2 will be 1 and 2, respectively.

[0080] In the case of duplicate PRS port numbers, the network-side device sends three types of identification information to the terminal: the identification information of each TRP within the TRP group, the identification information of each PRS port within the PRS port group, and the identification information of the TRP to which each PRS port within the PRS port group belongs. This allows the terminal to analyze the aforementioned three types of identification information to obtain the local ID of the PRS port and its associated TRP, thereby uniquely determining the PRS port associated with each locally configured AI model. It is understandable that, if an association table is pre-built based on the correspondence between the TRP group ID and the TRPs within the TRP group, the "identification information of each TRP within the TRP group" in the aforementioned three types of identification information can be replaced with the "ID of the TRP group".

[0081] In one possible implementation, an association table can be pre-built based on the TRP's identification information and related information (including but not limited to at least one of the following: the TRP's location information and the PRS port contained in the TRP). In this way, the network-side device can send only the TRP's identification information to the terminal. The terminal can obtain the related information associated with the TRP's identification information by querying the aforementioned association table based on the TRP's identification information sent by the network-side device, thereby simplifying the information interaction between the network-side device and the terminal.

[0082] The location information of each TRP within a TRP group can be used as a reference point for terminal positioning. This location information can be physical location information such as the coordinates of the TRP. The network-side device sends the location of the TRP associated with the AI ​​model to the terminal, enabling the terminal to use the location of the TRP as a reference point and, in conjunction with the output of the AI ​​model, determine its own location. For example, when the output of the AI ​​model is the signal arrival time of the associated PRS, the distance between the terminal and the TRP can be determined based on the signal arrival time, and then the coordinates of the terminal can be determined based on the distance and the coordinates of the TRP.

[0083] The number of TRPs within a TRP group can be used by the terminal to select the TRP group and AI model for positioning. For example, in scenarios requiring high-precision positioning, a TRP group with no less than 3 TRPs and its associated AI model can be selected to position the terminal and obtain high-precision positioning information.

[0084] Optionally, the second association between the N AI models and the PRS port group includes at least one of the following:

[0085] Item B-1: The association between each AI model and the identification information of the PRS port group;

[0086] Item B-2: The relationship between the configuration information of each AI model and the PRS port group.

[0087] For item B-1, the identification information of the PRS port group can be the numerical ID of the PRS port group. That is, each PRS port is pre-grouped, and then an ID is assigned to each PRS port group. An association table is built based on the correspondence between the ID of the PRS port group and the PRS ports in the PRS port group. In this way, the network-side device can send only the identification information of the PRS port group to the terminal. When the terminal receives the ID of the PRS port group, it can determine which PRS ports are in the PRS port group by querying the aforementioned association table. For example, if the ID of the PRS port group is B1, it can be found by looking up the table that there are PRS1 port and PRS2 port in the PRS port group (PRS1 port and PRS2 port refer to two different PRS ports).

[0088] For item B-2, the configuration information of the PRS port group is used to describe the relevant information of each PRS port within the PRS port group.

[0089] Optionally, the configuration information of the PRS port group includes at least one of the following:

[0090] Information on the number of PRS ports within the PRS port group;

[0091] Identification information of each PRS port within the PRS port group;

[0092] The first quasi-co-address information of the PRS ports within the PRS port group;

[0093] The second quasi-co-address information between the PRS port groups;

[0094] Location information of each PRS port within the PRS port group;

[0095] The identification information of the TRP to which each PRS port in the PRS port group belongs.

[0096] The number of PRS ports within a PRS port group can be used by the terminal to select the PRS port group and AI model for positioning. For example, in scenarios requiring high-precision positioning, a PRS port group with no less than 2 PRS ports and its associated AI model can be selected to position the terminal and obtain high-precision positioning information.

[0097] The identification information of each PRS port within a PRS port group can be used by the terminal to determine the PRS port associated with the AI ​​model and related information about that PRS port. The identification information of a PRS port can be a global ID of the PRS port, provided that the PRS ports are not numbered repeatedly. For example, if PRS1 is assigned ID 1 and PRS2 is assigned ID 2, then the identification information of each PRS port within the PRS port group containing PRS1 and PRS2 will be 1 and 2, respectively.

[0098] The identification information of PRS ports can also be provided when PRS ports are numbered repeatedly. The local ID of the PRS port (i.e., the IDs of PRS ports belonging to the same TRP are not repeated, but the IDs of two different ports on two different TRPs may be the same. For example, the ID assigned to PRS1 port belonging to TRP1 is 1, the ID assigned to PRS2 port belonging to TRP1 is 2, and the ID assigned to PRS3 port belonging to TRP2 is 1. In the case of repeated PRS port numbers, in addition to sending the identification information of each PRS port within the PRS port group to the terminal, the network-side device also needs to send the identification information of the TRP to which each PRS port belongs within the PRS port group. This allows the terminal to uniquely identify the PRS port associated with each locally configured AI model using the local ID of the PRS port and its associated TRP.

[0099] In one possible implementation, an association table can be pre-constructed based on the identification information of the PRS port and related information of the PRS port (including but not limited to at least one of the following: the location information of the PRS port, the TRP to which the PRS port belongs, and the quasi-co-address information of the PRS port). In this way, the network-side device can send only the identification information of the PRS port to the terminal. The terminal can obtain the related information associated with the identification information of the PRS port by querying the aforementioned association table based on the identification information of the PRS port sent by the network side, thereby simplifying the information interaction between the network-side device and the terminal.

[0100] The first quasi-co-address information of PRS ports within a PRS port group can be used to indicate two or more PRS ports within the PRS port group that have a quasi-co-address relationship. Two or more PRS ports with a quasi-co-address relationship usually have similar large-scale channel attributes, such as at least one of the following: Doppler frequency shift, Doppler spread, average delay, delay spread, spatial reception parameters, etc., of the channels corresponding to the two or more PRS ports are approximately or identical. Moreover, the physical locations of two or more PRS ports with a quasi-co-address relationship are usually the same or very close. An association table can be pre-built based on two or more PRS ports with a quasi-co-address relationship. In this way, the network-side device can send only the relevant information and the first quasi-co-address information of a single PRS port to the terminal. The terminal can infer the corresponding information of one or more other PRS ports that have a quasi-co-address relationship with the single PRS port through the relevant information (such as physical location, large-scale channel attributes, etc.) and the first quasi-co-address information of the single PRS port sent by the network-side device.

[0101] The second quasi-co-address information between PRS port groups can be used to indicate PRS ports belonging to different PRS groups and having a quasi-co-address relationship, i.e., two or more PRS ports that have a quasi-co-address relationship across PRS groups. An association table can be built in advance based on the two or more PRS ports that have a quasi-co-address relationship across PRS groups. In this way, the network-side device can send only the relevant information and the second quasi-co-address information of a single PRS port to the terminal. The terminal can infer the corresponding information of other PRS port groups that have a quasi-co-address relationship with the single PRS port group by using the relevant information of the single PRS port group (such as the physical location of the PRS port in the PRS port group, large-scale channel attributes, etc.) and the second quasi-co-address information sent by the network-side device.

[0102] The location information of each PRS port within the PRS port group can be used as a reference location point for terminal positioning to further improve positioning accuracy. A PRS port is a logical port used to characterize the radio channel state; that is, PRS signals transmitted from the same PRS port experience the same channel conditions. The location information of the PRS port refers to the location of its corresponding physical antenna port. Since there may be a certain distance between the installation location of the TRP and the location of its connected physical antenna port, the physical location of the PRS port, i.e., the location of its corresponding physical antenna port, can be used as a reference during positioning to obtain a more accurate terminal location.

[0103] Optionally, the AI ​​model information further includes: a third association relationship between the N AI models and the PRS resource set, wherein the third association relationship includes at least one of the following:

[0104] Item C-1: The association between each AI model and the identification information of the PRS resource set;

[0105] Item C-2: The association between each AI model and the configuration information of the PRS resource set; wherein, the PRS resource set associated with each AI model includes one or more PRS resources, and the configuration information of the PRS resource contains the information required by the terminal to complete the measurement of the PRS (such as subcarrier spacing, frequency band, comb structure, etc.). Each PRS resource corresponds to a beam of the TRP corresponding to its PRS resource set.

[0106] For item C-1, the identification information of the PRS resource set can be the ID of the PRS resource set. That is, an ID is assigned to a PRS resource set with one or more PRS resources, and an association table is built based on the correspondence between the ID of the PRS resource set and the configuration information of each PRS resource in the PRS resource set. When the terminal receives the ID of the PRS resource set, it can determine the configuration information of each PRS resource in the PRS resource set by looking up the table. For example, if the ID of the PRS resource set is C1, the configuration information of PRS1 resource and PRS2 resource in the PRS resource set can be found by looking up the table (PRS1 resource and PRS2 resource refer to two different PRS resources).

[0107] A positioning frequency layer contains one or more TRPs, each with its own PRS resource set. All these PRS resource sets share the same frequency and OFDM parameter set. A PRS resource set can include multiple PRS resources from the same TRP, with each PRS resource within the set corresponding to a beam of that TRP. In other words, a TRP can include one or more PRS resource sets. By setting identification information for each PRS resource set, the terminal can quickly locate the configuration information of the PRS resources included in each PRS resource set, thereby enabling the measurement of the PRS associated with each PRS resource set.

[0108] For item C-2, the configuration information of the PRS resource set is used to describe the relevant information of each PRS resource within the PRS resource set, such as the frequency domain resources, time domain resources, spatial domain resources (each PRS resource corresponds to a beam of a certain TRP), and PRS port resources corresponding to the PRS resources.

[0109] Optionally, the configuration information of the PRS resource set includes at least one of the following:

[0110] Identification information of the PRS resources associated with the PRS resource set;

[0111] Carrier frequency information associated with the PRS resource set;

[0112] Bandwidth information associated with the PRS resource set;

[0113] Comb structure information associated with the PRS resource set;

[0114] OFDM parameter information associated with the PRS resource set;

[0115] PRS transmission cycle information associated with the PRS resource set;

[0116] The beamwidth associated with the PRS resource set;

[0117] The identification information of the TRP to which each PRS resource belongs within the PRS resource set;

[0118] The identification information of the PRS port to which each PRS resource belongs within the PRS resource set.

[0119] The identification information of PRS resources can be used by the terminal to determine the carrier frequency information, bandwidth information, comb structure information, OFDM parameter information, PRS transmission period information, and beamwidth of the PRS resources associated with the PRS port of the AI ​​model. This information is then used by the terminal to measure the PRS transmitted by the PRS port associated with that PRS resource. The identification information of the PRS resource can be the ID of the PRS resource, and each PRS resource has a unique ID. For example, if the ID assigned to PRS1 is 1 and the ID assigned to PRS2 is 2, then the identification information of the PRS resources associated with the PRS resource set containing PRS1 and PRS2 resources will be 1 and 2.

[0120] In one possible implementation, an association table can be pre-built based on the identification information of the PRS resource and related information of the PRS resource (including but not limited to carrier frequency information, bandwidth information, Comb structure information, OFDM parameter information, PRS transmission period information, and beamwidth of the PRS resource). In this way, the network-side device can send only the identification information of the PRS resource to the terminal. The terminal can obtain the related information associated with the identification information of the PRS resource by querying the aforementioned association table based on the identification information of the PRS resource sent by the network-side device, thereby simplifying the information interaction between the network-side device and the terminal.

[0121] PRS supports beamforming, thus introducing the concept of a PRS resource. A PRS resource ID corresponds to one beam within a TRP. One or more PRS resources can form a PRS resource set, or a PRS resource set can contain one or more PRS resources. A TRP can contain one or more PRS resources.

[0122] In addition, to increase the audibility of the UE (terminal), the NR system supports PRS beam scanning and PRS beam repetition, and also supports PRS reference neighboring cell RS (cell-specific reference signal) as a spatial QCL (quasi-co-location) reference signal.

[0123] The carrier frequency information and bandwidth information (such as antenna bandwidth) associated with the PRS resource set can be determined by the index of the starting resource block (RB) configured in the PRS resource set and the number of RBs.

[0124] The NR system operates in two frequency bands: FR1 and FR2. FR1 ranges from 450MHz to 6000MHz, while FR2 ranges from 24250MHz to 52600MHz. PRS supports transmission with a maximum bandwidth of 100MHz in FR1 and a maximum bandwidth of 400MHz in FR2. The PRS bandwidth configuration is independent of the BWP configuration. When the PRS bandwidth exceeds the BWP bandwidth, the UE can use the measurement gap to measure the PRS.

[0125] The Comb structure information associated with the PRS resource set is used to represent the frequency domain density associated with the PRS resource set, that is, the frequency domain density of the PRS associated with the PRS resource set on each Physical Resource Block (PRB). The Comb structure information may include the comb structure corresponding to each PRS resource, such as Comb N, where Comb N indicates that the PRS are equally spaced in the frequency domain with an interval of N subcarriers.

[0126] PRS supports interleaved patterns and flexible pattern configuration. The PRS resource combo structure can support {2, 4, 6, 12}; the number of symbols (adjacent symbols) can support {2, 4, 6, 12}. The combinations of symbol count and combo size supported by this application embodiment are shown in Table 1 below:

[0127] Comb-2 {0，1} {0，1，0，1} {0，1，0，1，0，1} {0，1，0，1，0，1，0，1，0，1，0，1} Comb-4 NA {0，2，1，3} NA {0，2，1，3，0，2，1，3，0，2，1，3}} Comb-6 NA NA {0，3，1，4，2，5} {0，3，1，4，2，5，0，3，1，4，2，5} Comb-12 NA NA NA {0，6，3，9，1，7，4，10，2，8，5，11}

[0128] Table 1

[0129] Typical PRS patterns under different comb structures are as follows: Figures 6-9 As shown in the figure, the horizontal squares represent the OFDM symbol positions in the time domain, the vertical squares represent the subcarrier positions in the frequency domain, and the gray squares represent the resource element (RE) positions mapped by the PRS resources in the time and frequency domains. Figure 6 The PRS pattern is a combination of 2 symbols and Comb 2, with a corresponding frequency domain offset of {0, 1}. It is used to indicate the offset of the positioning reference signal at the RE level in adjacent symbols (e.g., frequency domain offset). The RE position of the positioning reference signal in the next symbol can be calculated from the RE position in the previous adjacent symbol and the configured RE offset. Figure 7 The PRS pattern is a combination of 4 symbols and Comb 4, with corresponding frequency domain offsets of {0, 2, 1, 3}. Figure 8The PRS pattern is a combination of 6 symbols and Comb 6, with corresponding frequency domain offsets of {0, 3, 1, 4, 2, 5}. Figure 9 The PRS pattern is a combination of 12 symbols and Comb 12, with corresponding frequency domain offsets of {0, 6, 3, 9, 1, 7, 4, 10, 2, 8, 5, 11}.

[0130] The OFDM (Orthogonal Frequency Division Multiplexing) parameter information associated with the PRS resource set may include the index of the starting orthogonal frequency division multiplexing symbol in a time slot and the number of OFDM symbols occupied by the PRS resource.

[0131] The PRS transmission period information associated with the PRS resource set may include transmission periods expressed in timeslots to define the timeslot locations used for transmitting PRS resources.

[0132] For the beamwidth associated with the PRS resource set, different PRS resources in the PRS resource set are associated with different beams. The beamwidth associated with the PRS resource set refers to the beamwidth associated with each PRS resource in the PRS resource set.

[0133] The identification information of the TRP to which each PRS resource belongs and the identification information of the PRS port within the PRS resource set can be used to determine the PRS port associated with the AI ​​model. A single TRP can be associated with multiple PRS resources, and each PRS resource can be associated with each PRS port on that TRP. Therefore, by setting the identification information of the TRP to which each PRS resource belongs and the identification information of the PRS port, each PRS resource within the PRS resource set can be associated with a specific PRS port and TRP, thereby determining the PRS port associated with the AI ​​model.

[0134] Optionally, the configuration information of the N AI models includes at least one of the following:

[0135] Item D-1: Identification information of the N AI models;

[0136] D-2: Structural information of the N AI models;

[0137] Item D-3: Computational capability requirements for the N AI models;

[0138] Item D-4: Storage capacity requirements for the N AI models;

[0139] Item D-5: Parameter information of the N AI models;

[0140] Item D-6: Functional information of the N AI models;

[0141] Item D-7: The type of input data for the N AI models;

[0142] Item D-8: The format of the input data for the N AI models;

[0143] Item D-9: Preprocessing method for the input data of the N AI models;

[0144] Item D-10: The type of output data for the N AI models;

[0145] Item D-11: The format of the output data of the N AI models;

[0146] Item D-12: Post-processing method for the output data of the N AI models.

[0147] For item D-1, the identification information of the AI ​​model can be a pre-set digital ID or name for the AI ​​model. This identification information can be associated with the relevant information used to configure the AI ​​model (such as items D-2 to D-12), so that the terminal can obtain the relevant information associated with the identification information of the AI ​​model by looking up a table or other means based solely on the identification information of the AI ​​model sent by the network side, thereby simplifying the information interaction between the network side device and the terminal.

[0148] For item D-2, the structural information of the AI ​​model may include at least one of the following: model type (e.g., fully connected neural network, convolutional neural network, hands-on deep learning (Transformer) or others), number of layers in the network, number of neurons in each layer, activation function type of each layer, and normalization method of each layer (e.g., batch normalization, layer normalization).

[0149] For item D-3, the information on the computational power requirements of the AI ​​model is used to indicate the computing power required for the AI ​​model's inference, that is, its corresponding computational complexity.

[0150] For item D-4, the storage capacity requirement information of the AI ​​model is used to indicate the storage capacity required by the AI ​​model, that is, the parameter scale required for AI model inference. For example, it may include at least one of the following: the number of bits for floating-point storage (e.g., floating-point (float) 32 / float 64 / ...), the storage space required to store the first model, and the memory space required for AI model inference.

[0151] For item D-5, the parameter information of the AI ​​model may include at least one of the model's weights and biases.

[0152] For item D-6, the functional information of the AI ​​model is used to indicate the functions implemented by the AI ​​model, such as channel compression and positioning. In this embodiment of the application, the configuration method is mainly introduced using the AI ​​model with positioning based on the functional information as an example, but it can also be applied to the configuration of AI models with other functions associated with PRS.

[0153] For item D-7, the type of input data for the AI ​​model is used to indicate the input content of the model, such as indicating that the input data of the model is the channel impulse response.

[0154] For item D-8, the format of the AI ​​model's input data indicates information such as the structure and dimensions of the model's input data, including the arrangement of the channel impulse responses of each PRS port associated with the AI ​​model. Network-side devices can pre-set the arrangement of the channel impulse responses of the PRS ports based on the global ID of the PRS port, or a combination of the local ID of the PRS port and its corresponding TRP ID. For example, they can arrange the channel impulse responses of each PRS port associated with the AI ​​model in descending order of the global ID or combined ID, thereby obtaining the input data for the AI ​​model.

[0155] For item D-9, the preprocessing method for the input data of the AI ​​model can include data processing methods such as truncation (removing the high-order bytes of the data and keeping only the low-order bytes). For example, if the preprocessing method for the input data of the AI ​​model is truncation, and the terminal measures the PRS to obtain a channel impulse response containing 4096 data points, then the channel impulse response is truncated, and only the first 256 data points are input into the AI ​​model.

[0156] For item D-10, the type of output data of the AI ​​model is used to indicate the content of the model's output, such as indicating that the model's output data is location.

[0157] For item D-11: The format of the AI ​​model's output data, used to indicate information such as the structure and dimensions of the model's output data.

[0158] For item D-12, post-processing of the AI ​​model's output data can include data processing methods such as filtering and transformation to improve the accuracy of the AI ​​model's output results.

[0159] Secondly, such as Figure 5 As shown in the embodiment of this application, another positioning method is provided, which includes at least the following steps:

[0160] Step 501: The network-side device sends AI model information to the terminal, so that the terminal can execute the positioning process based on the AI ​​model information;

[0161] The AI ​​model information includes: configuration information of N AI models, and the association between the N AI models and the positioning reference signal (PRS) port, where N is a positive integer greater than or equal to 1.

[0162] In this embodiment of the application, the network-side device may be Figure 1 Access network equipment, such as base stations or newly defined AI processing nodes on the access network side, can also be Figure 1 The core network equipment, such as the Network Data Analytics Function (NWDAF), Location Management Function (LMF), or newly defined processing nodes on the core network side, can also be a combination of the above-mentioned nodes.

[0163] As one possible implementation, after the network-side device sends the AI ​​model information to the terminal, it also includes:

[0164] The network-side device receives N location information returned by the terminal after the terminal executes the location process. The N location information are location information output by the N AI models configured by the terminal for the terminal respectively.

[0165] The network-side device obtains the final location result of the terminal based on the N location information.

[0166] In this embodiment of the application, the location information may be the suspected location of the terminal. The network-side device obtains the actual location of the terminal (i.e., the final location result) based on the N suspected locations by means of clustering or calculating the mean. The location information may also be intermediate parameters used to calculate the terminal location, such as signal arrival time parameters. The network-side device further determines the actual location of the terminal based on the N intermediate parameters.

[0167] As one possible implementation, the configuration information of the N AI models is determined based on the N AI models trained by the network-side device, and the association between the N AI models and the Positioning Reference Signal (PRS) port is determined based on the training samples corresponding to the N AI models, where N is a positive integer greater than or equal to 1.

[0168] Considering the different channel characteristics of PRS transmission through different PRS ports, the network-side equipment uses training samples associated with different PRS ports to train N AI models for processing measurements transmitted through different PRS ports. Based on the training samples used to train each AI model, the PRS port associated with each trained AI model is determined. Then, configuration information for configuring the N AI models locally, as well as the association between the N AI models and the positioning reference signal (PRS) ports, is sent to the terminal device, enabling the terminal to clearly understand which PRS port each of the locally configured N AI models is associated with.

[0169] As one possible implementation, before the network-side device sends the AI ​​model information to the terminal, it also includes:

[0170] The network-side device receives channel impulse responses sent by multiple sampling points. The impulse responses are obtained by the sampling points performing channel estimation on the reference positioning signal (PRS).

[0171] The network-side device generates training samples based on multiple channel impulse responses, the locations of the multiple sampling points, and the PRS port used to transmit the PRS.

[0172] The network-side device uses the training samples to train multiple initial AI models, thereby obtaining multiple trained AI models.

[0173] The network-side device determines the AI ​​model information based on the configuration information of N AI models out of the plurality of trained AI models and the PRS ports associated with the training samples of the N AI models.

[0174] In this embodiment, the network-side device can set up sampling points in the cell corresponding to each TRP. Based on the location of each sampling point, the PRS measured by each sampling point and its associated PRS resources, TRP and PRS port, training samples are generated. Each training sample is randomly grouped according to its corresponding PRS port to obtain training sample sets corresponding to different PRS port groups. The initial AI model is trained using each training sample set. After training, the top N AI models with the best performance can be selected according to the model performance evaluation parameters. AI model information is generated based on the N AI models and the PRS resources, TRP and PRS ports associated with their corresponding training sample sets, and the AI ​​model information is sent to the terminal.

[0175] As can be seen from the above steps, in this embodiment, the network-side device sends configuration information of N AI models and the association relationship between the N AI models and PRS ports to the terminal. This enables the terminal to configure the N AI models according to the configuration information. Based on the association relationship between each AI model and the PRS port, the terminal selectively measures the PRS of the PRS port associated with each AI model, allowing the N AI models to process the measurements of their associated PRS separately, thereby improving the terminal's positioning accuracy. Optionally, in the case of duplicate PRS port numbers, the association relationship between the N AI models and the positioning reference signal PRS port includes: a first association relationship between the N AI models and the TRP group, and a second association relationship between the N AI models and the PRS port group.

[0176] When the PRS ports are not numbered repeatedly, the association between the N AI models and the positioning reference signal PRS ports includes: the second association between the N AI models and the PRS port group;

[0177] Each AI model is associated with a TRP group that includes one or more TRPs, and each AI model is associated with a PRS port group that includes one or more PRS ports.

[0178] Please refer to the preceding text for an explanation of the first and second association relationships, which will not be repeated here. Optionally, the first association relationship between the N AI models and the TRP group includes at least one of the following:

[0179] Item A-1: ​​The association between each AI model and the identification information of the TRP group;

[0180] Item A-2: The relationship between each AI model and the configuration information of the TRP group.

[0181] Optionally, the first association between the N AI models and the TRP group includes at least one of the following:

[0182] Item A-1: ​​The association between each AI model and the identification information of the TRP group;

[0183] Item A-2: The relationship between each AI model and the configuration information of the TRP group.

[0184] For explanations of items A-1 and A-2, please refer to the previous text; they will not be repeated here.

[0185] Optionally, the configuration information of the TRP group includes at least one of the following:

[0186] The quantity information of TRPs within the TRP group;

[0187] The identification information of each TRP within the TRP group;

[0188] The location information of each TRP within the TRP group.

[0189] For details on the configuration information of TRP groups, please refer to the previous text, which will not be repeated here.

[0190] Optionally, the second association between the N AI models and the PRS port group includes at least one of the following:

[0191] Item B-1: The association between each AI model and the identification information of the PRS port group;

[0192] Item B-2: The relationship between the configuration information of each AI model and the PRS port group.

[0193] For explanations of items B-1 and B-2, please refer to the previous text; they will not be repeated here.

[0194] Optionally, the configuration information of the PRS port group includes at least one of the following:

[0195] Information on the number of PRS ports within the PRS port group;

[0196] Identification information of each PRS port within the PRS port group;

[0197] The first quasi-co-address information of the PRS ports within the PRS port group;

[0198] The second quasi-co-address information between the PRS port groups;

[0199] Location information of each PRS port within the PRS port group;

[0200] The identification information of the TRP to which each PRS port in the PRS port group belongs.

[0201] For details on the configuration information of the PRS port group, please refer to the previous text, and it will not be repeated here.

[0202] Optionally, the AI ​​model information further includes: a third association relationship between the N AI models and the PRS resource set, wherein the third association relationship includes at least one of the following:

[0203] Item C-1: The association between each AI model and the identification information of the PRS resource set;

[0204] Item C-2: The relationship between each AI model and the configuration information of the PRS resource set;

[0205] Each AI model is associated with a PRS resource set, which includes one or more PRS resources. The configuration information of the PRS resource contains the information required by the terminal to complete the measurement of the PRS (such as subcarrier spacing, frequency band, comb structure, etc.). Each PRS resource corresponds to a beam of the TRP corresponding to its PRS resource set.

[0206] For explanations of items C-1 and C-2, please refer to the previous text; they will not be repeated here.

[0207] Optionally, the configuration information of the PRS resource set includes at least one of the following:

[0208] Identification information of the PRS resources associated with the PRS resource set;

[0209] Carrier frequency information associated with the PRS resource set;

[0210] Bandwidth information associated with the PRS resource set;

[0211] Comb structure information associated with the PRS resource set;

[0212] OFDM parameter information associated with the PRS resource set;

[0213] PRS transmission cycle information associated with the PRS resource set;

[0214] The beamwidth associated with the PRS resource set;

[0215] The identification information of the TRP to which each PRS resource belongs within the PRS resource set;

[0216] The identification information of the PRS port to which each PRS resource belongs within the PRS resource set.

[0217] For details on the configuration information of PRS resource sets, please refer to the previous text, which will not be repeated here.

[0218] Optionally, the configuration information of the N AI models includes at least one of the following:

[0219] Item D-1: Identification information of the N AI models;

[0220] D-2: Structural information of the N AI models;

[0221] Item D-3: Computational capability requirements for the N AI models;

[0222] Item D-4: Storage capacity requirements for the N AI models;

[0223] Item D-5: Parameter information of the N AI models;

[0224] Item D-6: Functional information of the N AI models;

[0225] Item D-7: The type of input data for the N AI models;

[0226] Item D-8: The format of the input data for the N AI models;

[0227] Item D-9: Preprocessing method for the input data of the N AI models;

[0228] Item D-10: The type of output data for the N AI models;

[0229] Item D-11: The format of the output data of the N AI models;

[0230] Item D-12: Post-processing method for the output data of the N AI models.

[0231] For explanations of items D-1 to D-12, please refer to the previous text; they will not be repeated here.

[0232] The positioning method provided in this application can be executed by a positioning device. This application uses the example of a positioning device executing the positioning method to illustrate the positioning device provided in this application.

[0233] Thirdly, embodiments of this application provide a positioning device that can be applied to a terminal, such as... Figure 10 As shown, the positioning device 100 includes:

[0234] The receiving module 101 is used to receive AI model information from the network-side device;

[0235] The positioning module 102 is used to execute a positioning process based on the AI ​​model information. The AI ​​model information includes: configuration information of N AI models and the association relationship between the N AI models and the positioning reference signal PRS port. N is a positive integer greater than or equal to 1.

[0236] Optionally, the configuration information of the N AI models is determined by the network-side device based on the N trained AI models, and the association between the N AI models and the Positioning Reference Signal (PRS) port is determined based on the training samples corresponding to the N AI models.

[0237] Optionally, in the case of repeated PRS port numbering, the association between the N AI models and the positioning reference signal PRS port includes: a first association between the N AI models and the TRP group, and a second association between the N AI models and the PRS port group;

[0238] When the PRS ports are not numbered repeatedly, the association between the N AI models and the positioning reference signal PRS ports includes: the second association between the N AI models and the PRS port group;

[0239] Each AI model is associated with a TRP group that includes one or more TRPs, and each AI model is associated with a PRS port group that includes one or more PRS ports.

[0240] Optionally, the first association between the N AI models and the TRP group includes at least one of the following:

[0241] The association between each AI model and the identification information of the TRP group;

[0242] The association between each AI model and the configuration information of the TRP group.

[0243] Optionally, the configuration information of the TRP group includes at least one of the following:

[0244] The quantity information of TRPs within the TRP group;

[0245] The identification information of each TRP within the TRP group;

[0246] The location information of each TRP within the TRP group.

[0247] Optionally, the second association between the N AI models and the PRS port group includes at least one of the following:

[0248] The association between each AI model and the identification information of the PRS port group;

[0249] The association between each AI model and the configuration information of the PRS port group.

[0250] Optionally, the configuration information of the PRS port group includes at least one of the following:

[0251] Information on the number of PRS ports within the PRS port group;

[0252] Identification information of each PRS port within the PRS port group;

[0253] The first quasi-co-address information of the PRS ports within the PRS port group;

[0254] The second quasi-co-address information between the PRS port groups;

[0255] Location information of each PRS port within the PRS port group;

[0256] The identification information of the TRP to which each PRS port in the PRS port group belongs.

[0257] Optionally, the AI ​​model information further includes: a third association relationship between the N AI models and the PRS resource set, wherein the third association relationship includes at least one of the following:

[0258] The association between each AI model and the identification information of the PRS resource set;

[0259] The association between each AI model and the configuration information of the PRS resource set;

[0260] Each AI model is associated with a PRS resource set that includes one or more PRS resources.

[0261] Optionally, the configuration information of the PRS resource set includes at least one of the following:

[0262] Identification information of the PRS resources associated with the PRS resource set;

[0263] Carrier frequency information associated with the PRS resource set;

[0264] Bandwidth information associated with the PRS resource set;

[0265] Comb structure information associated with the PRS resource set;

[0266] OFDM parameter information associated with the PRS resource set;

[0267] PRS transmission cycle information associated with the PRS resource set;

[0268] The beamwidth associated with the PRS resource set;

[0269] The identification information of the TRP to which each PRS resource belongs within the PRS resource set;

[0270] The identification information of the PRS port to which each PRS resource belongs within the PRS resource set.

[0271] Optionally, the configuration information of the N AI models includes at least one of the following:

[0272] The identification information of the N AI models;

[0273] The structural information of the N AI models;

[0274] Information on the computational capability requirements of the N AI models;

[0275] Storage capacity requirements for the N AI models;

[0276] Parameter information of the N AI models;

[0277] Functional information of the N AI models;

[0278] The types of input data for the N AI models;

[0279] The format of the input data for the N AI models;

[0280] The preprocessing method for the input data of the N AI models;

[0281] The types of output data from the N AI models;

[0282] The format of the output data of the N AI models;

[0283] The post-processing method for the output data of the N AI models.

[0284] Optionally, the device further includes a configuration module;

[0285] The configuration module is used to configure N AI models according to the configuration information of the AI ​​models;

[0286] The positioning module is specifically configured to measure the positioning reference signal associated with each of the N AI models according to the correlation between the N AI models and the positioning reference signal PRS port, to obtain N measurement quantities, the N measurement quantities including the channel impulse response corresponding to the PRS port associated with each of the N AI models; input the N measurement quantities into their respective associated AI models to obtain positioning information output by the N AI models for the terminal, and the terminal returns the N positioning information of the terminal to the network-side device.

[0287] The positioning device in this application 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 device. For example, the terminal device can include, but is not limited to, the types of terminal devices 11 listed above.

[0288] The positioning device provided in this application embodiment can implement the various processes implemented in the positioning method embodiment described in the first aspect and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0289] Fourthly, embodiments of this application provide another positioning device, which can be applied to network-side devices, such as... Figure 11 As shown, the positioning device 200 includes:

[0290] The model information sending module 201 is used to send AI model information to the terminal so that the terminal can execute the positioning process according to the AI ​​model information;

[0291] The AI ​​model information includes: configuration information of N AI models, and the association between the N AI models and the positioning reference signal (PRS) port, where N is a positive integer greater than or equal to 1.

[0292] Optionally, in the case of repeated PRS port numbering, the association between the N AI models and the positioning reference signal PRS port includes: a first association between the N AI models and the TRP group, and a second association between the N AI models and the PRS port group;

[0293] When the PRS ports are not numbered repeatedly, the association between the N AI models and the positioning reference signal PRS ports includes: the second association between the N AI models and the PRS port group;

[0294] Each AI model is associated with a TRP group that includes one or more TRPs, and each AI model is associated with a PRS port group that includes one or more PRS ports.

[0295] Optionally, the first association between the N AI models and the TRP group includes at least one of the following:

[0296] The association between each AI model and the identification information of the TRP group;

[0297] The association between each AI model and the configuration information of the TRP group.

[0298] Optionally, the configuration information of the TRP group includes at least one of the following:

[0299] The quantity information of TRPs within the TRP group;

[0300] The identification information of each TRP within the TRP group;

[0301] The location information of each TRP within the TRP group.

[0302] Optionally, the second association between the N AI models and the PRS port group includes at least one of the following:

[0303] The association between each AI model and the identification information of the PRS port group;

[0304] The association between each AI model and the configuration information of the PRS port group.

[0305] Optionally, the configuration information of the PRS port group includes at least one of the following:

[0306] Information on the number of PRS ports within the PRS port group;

[0307] Identification information of each PRS port within the PRS port group;

[0308] The first quasi-co-address information of the PRS ports within the PRS port group;

[0309] The second quasi-co-address information between the PRS port groups;

[0310] Location information of each PRS port within the PRS port group;

[0311] The identification information of the TRP to which each PRS port in the PRS port group belongs.

[0312] Optionally, the AI ​​model information further includes: a third association relationship between the N AI models and the PRS resource set, wherein the third association relationship includes at least one of the following:

[0313] The association between each AI model and the identification information of the PRS resource set;

[0314] The association between each AI model and the configuration information of the PRS resource set;

[0315] Each AI model is associated with a PRS resource set that includes one or more PRS resources.

[0316] Optionally, the configuration information of the PRS resource set includes at least one of the following:

[0317] Identification information of the PRS resources associated with the PRS resource set;

[0318] Carrier frequency information associated with the PRS resource set;

[0319] Bandwidth information associated with the PRS resource set;

[0320] Comb structure information associated with the PRS resource set;

[0321] OFDM parameter information associated with the PRS resource set;

[0322] PRS transmission cycle information associated with the PRS resource set;

[0323] The beamwidth associated with the PRS resource set;

[0324] The identification information of the TRP to which each PRS resource belongs within the PRS resource set;

[0325] The identification information of the PRS port to which each PRS resource belongs within the PRS resource set.

[0326] Optionally, the configuration information of the N AI models includes at least one of the following:

[0327] The identification information of the N AI models;

[0328] The structural information of the N AI models;

[0329] Information on the computational capability requirements of the N AI models;

[0330] Storage capacity requirements for the N AI models;

[0331] Parameter information of the N AI models;

[0332] Functional information of the N AI models;

[0333] The types of input data for the N AI models;

[0334] The format of the input data for the N AI models;

[0335] The preprocessing method for the input data of the N AI models;

[0336] The types of output data from the N AI models;

[0337] The format of the output data of the N AI models;

[0338] The post-processing method for the output data of the N AI models.

[0339] Optionally, the device further includes:

[0340] The information receiving module is used to receive N positioning information returned by the terminal after the terminal executes the positioning process. The N positioning information are positioning information output by the N AI models configured by the terminal for the terminal respectively.

[0341] The processing module is used to obtain the final positioning result of the terminal based on the N positioning information.

[0342] Optionally, the configuration information of the N AI models is determined by the network-side device based on the N trained AI models, and the association between the N AI models and the Positioning Reference Signal (PRS) port is determined based on the training samples corresponding to the N AI models.

[0343] Optionally, the device further includes:

[0344] The data receiving module is used to receive channel impulse responses sent by multiple sampling points, wherein the impulse responses are obtained by the sampling points performing channel estimation on the reference positioning signal PRS;

[0345] The sample generation module is used to generate training samples based on multiple channel impulse responses, the positions of the multiple sampling points, and the PRS port used to transmit the PRS.

[0346] The model training module is used to train multiple initial AI models using the training samples to obtain multiple trained AI models.

[0347] The information processing module is used to determine AI model information based on the configuration information of N AI models among the multiple trained AI models and the PRS ports associated with the training samples of the N AI models.

[0348] The positioning device provided in this application embodiment can implement the various processes implemented in the positioning method embodiment described in the second aspect and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0349] Optional, such as Figure 12 As shown, this application embodiment also provides a communication device 900, including a processor 901 and a memory 902. The memory 902 stores programs or instructions that can run on the processor 901. For example, when the communication device 900 is a network-side device, when the program or instructions are executed by the processor 901, they implement the various steps of the positioning method embodiment described in the first aspect above, and achieve the same technical effect. When the communication device 900 is a terminal device, when the program or instructions are executed by the processor 901, they implement the various steps of the positioning method embodiment described in the second aspect above, and achieve the same technical effect. To avoid repetition, further details are omitted here.

[0350] like Figure 13 The diagram shown is a hardware structure schematic of a terminal device that implements an embodiment of this application.

[0351] The terminal device 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.

[0352] Those skilled in the art will understand that the terminal device 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 13 The terminal device structure shown in the figure does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0353] 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 two parts: 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, and joysticks, which will not be described in detail here.

[0354] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 1001 can transmit it to the processor 1010 for processing; in addition, 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, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[0355] 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 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. 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 link 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.

[0356] The processor 1010 may include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, 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 the processor 1010.

[0357] The radio frequency unit 1001 is used to receive AI model information from network-side devices;

[0358] The processor 1010 is used to execute a positioning process based on the AI ​​model information, wherein the AI ​​model information includes: configuration information of N AI models and the association relationship between the N AI models and the positioning reference signal PRS port, where N is a positive integer greater than or equal to 1.

[0359] Optionally, the configuration information of the N AI models is determined by the network-side device based on the N trained AI models, and the association between the N AI models and the Positioning Reference Signal (PRS) port is determined based on the training samples corresponding to the N AI models.

[0360] Optionally, before executing the positioning process, the processor 1010 is also configured to configure N AI models according to the configuration information of the AI ​​models;

[0361] The positioning process executed by processor 1010 is as follows:

[0362] Based on the correlation between the N AI models and the positioning reference signal (PRS) port, the positioning reference signal associated with each of the N AI models is measured to obtain N measurement quantities, which include the channel impulse response corresponding to the PRS port associated with each of the N AI models.

[0363] The N measurements are input into their respective associated AI models to obtain the positioning information output by the N AI models for the terminal, and the N positioning information of the terminal are returned to the network-side device.

[0364] Optionally, in the case of repeated PRS port numbering, the association between the N AI models and the positioning reference signal PRS port includes: a first association between the N AI models and the TRP group, and a second association between the N AI models and the PRS port group;

[0365] When the PRS ports are not numbered repeatedly, the association between the N AI models and the positioning reference signal PRS ports includes: the second association between the N AI models and the PRS port group;

[0366] Each AI model is associated with a TRP group that includes one or more TRPs, and each AI model is associated with a PRS port group that includes one or more PRS ports.

[0367] Optional,

[0368] The first association between the N AI models and the TRP group includes at least one of the following:

[0369] The association between each AI model and the identification information of the TRP group;

[0370] The association between each AI model and the configuration information of the TRP group.

[0371] Optionally, the configuration information of the TRP group includes at least one of the following:

[0372] The quantity information of TRPs within the TRP group;

[0373] The identification information of each TRP within the TRP group;

[0374] The location information of each TRP within the TRP group.

[0375] Optionally, the second association between the N AI models and the PRS port group includes at least one of the following:

[0376] The association between each AI model and the identification information of the PRS port group;

[0377] The association between each AI model and the configuration information of the PRS port group.

[0378] Optionally, the configuration information of the PRS port group includes at least one of the following:

[0379] Information on the number of PRS ports within the PRS port group;

[0380] Identification information of each PRS port within the PRS port group;

[0381] The first quasi-co-address information of the PRS ports within the PRS port group;

[0382] The second quasi-co-address information between the PRS port groups;

[0383] Location information of each PRS port within the PRS port group;

[0384] The identification information of the TRP to which each PRS port in the PRS port group belongs.

[0385] Optionally, the AI ​​model information further includes: a third association relationship between the N AI models and the PRS resource set, wherein the third association relationship includes at least one of the following:

[0386] The association between each AI model and the identification information of the PRS resource set;

[0387] The association between each AI model and the configuration information of the PRS resource set;

[0388] Each AI model is associated with a PRS resource set that includes one or more PRS resources.

[0389] Optionally, the configuration information of the PRS resource set includes at least one of the following:

[0390] Identification information of the PRS resources associated with the PRS resource set;

[0391] Carrier frequency information associated with the PRS resource set;

[0392] Bandwidth information associated with the PRS resource set;

[0393] Comb structure information associated with the PRS resource set;

[0394] OFDM parameter information associated with the PRS resource set;

[0395] PRS transmission cycle information associated with the PRS resource set;

[0396] The beamwidth associated with the PRS resource set;

[0397] The identification information of the TRP to which each PRS resource belongs within the PRS resource set;

[0398] The identification information of the PRS port to which each PRS resource belongs within the PRS resource set.

[0399] Optionally, the configuration information of the N AI models includes at least one of the following:

[0400] The identification information of the N AI models;

[0401] The structural information of the N AI models;

[0402] Information on the computational capability requirements of the N AI models;

[0403] Storage capacity requirements for the N AI models;

[0404] Parameter information of the N AI models;

[0405] Functional information of the N AI models;

[0406] The types of input data for the N AI models;

[0407] The format of the input data for the N AI models;

[0408] The preprocessing method for the input data of the N AI models;

[0409] The types of output data from the N AI models;

[0410] The format of the output data of the N AI models;

[0411] The post-processing method for the output data of the N AI models.

[0412] This application also provides a terminal, such as... Figure 14As shown, the terminal 1100 includes: an antenna 111, a radio frequency (RF) device 112, a baseband device 113, a processor 114, and a memory 115. The antenna 111 is connected to the RF device 112. In the uplink direction, the RF device 112 receives information through the antenna 111 and transmits the received information to the baseband device 113 for processing. In the downlink direction, the baseband device 113 processes the information to be transmitted and transmits it to the RF device 112. The RF device 112 processes the received information and transmits it through the antenna 111.

[0413] The method executed by the terminal in the above embodiments can be implemented in the baseband device 113, which includes a baseband processor.

[0414] Baseband device 113 may include, for example, at least one baseband board on which multiple chips are disposed, such as Figure 14 As shown, one of the chips is, for example, a baseband processor, which is connected to the memory 115 via a bus interface to call the program in the memory 115 and execute the network device operation shown in the above method embodiment.

[0415] The terminal may also include a network interface 116, such as a common public radio interface (CPRI).

[0416] Specifically, the terminal 1100 in this embodiment of the invention further includes: instructions or programs stored in memory 115 and executable on processor 114, wherein processor 114 calls the instructions or programs in memory 115 to execute. Figure 10 The methods executed by each module shown achieve the same technical effect, and to avoid repetition, they will not be described in detail here.

[0417] This application also provides a network-side device. For example... Figure 15 As shown, the network-side device 1200 includes a processor 1201, a network interface 1202, and a memory 1203. The network interface 1202 is, for example, a common public radio interface (CPRI).

[0418] Specifically, the network-side device 1200 of this embodiment further includes: instructions or programs stored in memory 1203 and executable on processor 1201, wherein processor 1201 calls the instructions or programs in memory 1203 to execute. Figure 11 The methods executed by each module shown achieve the same technical effect, and to avoid repetition, they will not be described in detail here.

[0419] 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 positioning method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0420] The processor is the processor in the terminal device 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.

[0421] 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 positioning method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0422] 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.

[0423] 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 positioning method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0424] This application also provides a positioning system, including: a terminal device and a network-side device, wherein the terminal can be used to perform the steps of the positioning method as described in the first aspect above, and the network-side device can be used to perform the steps of the positioning method as described in the second aspect above.

[0425] 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.

[0426] 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.

[0427] 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 positioning method, characterized in that, include: The terminal receives AI model information from network-side devices; The terminal executes a positioning process based on the AI ​​model information, which includes: configuration information of N AI models and the association between the N AI models and the positioning reference signal PRS port, where N is a positive integer greater than or equal to 1; In the case of repeated PRS port numbering, the association between the N AI models and the positioning reference signal PRS port includes: a first association between the N AI models and the TRP group, and a second association between the N AI models and the PRS port group; When the PRS ports are not numbered repeatedly, the association between the N AI models and the positioning reference signal PRS ports includes: the second association between the N AI models and the PRS port group; Each AI model is associated with a TRP group that includes one or more TRPs, and each AI model is associated with a PRS port group that includes one or more PRS ports.

2. The method according to claim 1, characterized in that, The configuration information of the N AI models is determined based on the N AI models trained by the network-side device, and the association between the N AI models and the Positioning Reference Signal (PRS) port is determined based on the training samples corresponding to the N AI models.

3. The method according to claim 1, characterized in that, The first association between the N AI models and the TRP group includes at least one of the following: The association between each AI model and the identification information of the TRP group; The association between each AI model and the configuration information of the TRP group.

4. The method according to claim 3, characterized in that, The configuration information of the TRP group includes at least one of the following: The quantity information of TRPs within the TRP group; The identification information of each TRP within the TRP group; The location information of each TRP within the TRP group.

5. The method according to claim 1, characterized in that, The second association between the N AI models and the PRS port group includes at least one of the following: The association between each AI model and the identification information of the PRS port group; The association between each AI model and the configuration information of the PRS port group.

6. The method according to claim 5, characterized in that, The configuration information of the PRS port group includes at least one of the following: Information on the number of PRS ports within the PRS port group; Identification information of each PRS port within the PRS port group; The first quasi-co-address information of the PRS ports within the PRS port group; The second quasi-co-address information between the PRS port groups; Location information of each PRS port within the PRS port group; The identification information of the TRP to which each PRS port in the PRS port group belongs.

7. The method according to claim 1, characterized in that, The AI ​​model information also includes: a third association relationship between the N AI models and the PRS resource set, wherein the third association relationship includes at least one of the following: The association between each AI model and the identification information of the PRS resource set; The association between each AI model and the configuration information of the PRS resource set; Each AI model is associated with a PRS resource set that includes one or more PRS resources.

8. The method according to claim 7, characterized in that, The configuration information of the PRS resource set includes at least one of the following: Identification information of the PRS resources associated with the PRS resource set; Carrier frequency information associated with the PRS resource set; Bandwidth information associated with the PRS resource set; Comb structure information associated with the PRS resource set; OFDM parameter information associated with the PRS resource set; PRS transmission cycle information associated with the PRS resource set; The beamwidth associated with the PRS resource set; The identification information of the TRP to which each PRS resource belongs within the PRS resource set; The identification information of the PRS port to which each PRS resource belongs within the PRS resource set.

9. The method according to claim 1, characterized in that, The configuration information of the N AI models includes at least one of the following: The identification information of the N AI models; The structural information of the N AI models; Information on the computational capability requirements of the N AI models; Storage capacity requirements for the N AI models; Parameter information of the N AI models; Functional information of the N AI models; The types of input data for the N AI models; The format of the input data for the N AI models; The preprocessing method for the input data of the N AI models; The types of output data from the N AI models; The format of the output data of the N AI models; The post-processing method for the output data of the N AI models.

10. The method according to any one of claims 1-9, characterized in that, Before the terminal executes the positioning process, it also includes: The terminal configures N AI models according to the configuration information of the AI ​​models; The terminal executes a positioning process, including: The terminal measures the positioning reference signal associated with each of the N AI models according to the correlation between the N AI models and the positioning reference signal PRS port, and obtains N measurement quantities, the N measurement quantities including the channel impulse response corresponding to the PRS port associated with each of the N AI models; The terminal inputs the N measurements into their respective associated AI models to obtain positioning information output by the N AI models for the terminal, and then returns the N positioning information to the network-side device.

11. A positioning method, characterized in that, include: The network-side device sends AI model information to the terminal, so that the terminal can perform a positioning process based on the AI ​​model information; The AI ​​model information includes: configuration information of N AI models and the association between the N AI models and the Positioning Reference Signal (PRS) port, where N is a positive integer greater than or equal to 1; In the case of repeated PRS port numbering, the association between the N AI models and the positioning reference signal PRS port includes: a first association between the N AI models and the TRP group, and a second association between the N AI models and the PRS port group; When the PRS ports are not numbered repeatedly, the association between the N AI models and the positioning reference signal PRS ports includes: the second association between the N AI models and the PRS port group; Each AI model is associated with a TRP group that includes one or more TRPs, and each AI model is associated with a PRS port group that includes one or more PRS ports.

12. The method according to claim 11, characterized in that, The first association between the N AI models and the TRP group includes at least one of the following: The association between each AI model and the identification information of the TRP group; The association between each AI model and the configuration information of the TRP group.

13. The method according to claim 12, characterized in that, The configuration information of the TRP group includes at least one of the following: The quantity information of TRPs within the TRP group; The identification information of each TRP within the TRP group; The location information of each TRP within the TRP group.

14. The method according to claim 11, characterized in that, The second association between the N AI models and the PRS port group includes at least one of the following: The association between each AI model and the identification information of the PRS port group; The association between each AI model and the configuration information of the PRS port group.

15. The method according to claim 14, characterized in that, The configuration information of the PRS port group includes at least one of the following: Information on the number of PRS ports within the PRS port group; Identification information of each PRS port within the PRS port group; The first quasi-co-address information of the PRS ports within the PRS port group; The second quasi-co-address information between the PRS port groups; Location information of each PRS port within the PRS port group; The identification information of the TRP to which each PRS port in the PRS port group belongs.

16. The method according to claim 11, characterized in that, The AI ​​model information also includes: a third association relationship between the N AI models and the PRS resource set, wherein the third association relationship includes at least one of the following: The association between each AI model and the identification information of the PRS resource set; The association between each AI model and the configuration information of the PRS resource set; Each AI model is associated with a PRS resource set that includes one or more PRS resources.

17. The method according to claim 16, characterized in that, The configuration information of the PRS resource set includes at least one of the following: Identification information of the PRS resources associated with the PRS resource set; Carrier frequency information associated with the PRS resource set; Bandwidth information associated with the PRS resource set; Comb structure information associated with the PRS resource set; OFDM parameter information associated with the PRS resource set; PRS transmission cycle information associated with the PRS resource set; The beamwidth associated with the PRS resource set; The identification information of the TRP to which each PRS resource belongs within the PRS resource set; The identification information of the PRS port to which each PRS resource belongs within the PRS resource set.

18. The method according to claim 11, characterized in that, The configuration information of the N AI models includes at least one of the following: The identification information of the N AI models; The structural information of the N AI models; Information on the computational capability requirements of the N AI models; Storage capacity requirements for the N AI models; Parameter information of the N AI models; Functional information of the N AI models; The types of input data for the N AI models; The format of the input data for the N AI models; The preprocessing method for the input data of the N AI models; The types of output data from the N AI models; The format of the output data of the N AI models; The post-processing method for the output data of the N AI models.

19. The method according to any one of claims 11-18, characterized in that, After the network-side device sends the AI ​​model information to the terminal, it also includes: The network-side device receives N location information returned by the terminal after the terminal executes the location process. The N location information are location information output by the N AI models configured by the terminal for the terminal respectively. The network-side device obtains the final location result of the terminal based on the N location information.

20. The method according to any one of claims 11-18, characterized in that, The configuration information of the N AI models is determined by the network-side device based on the N trained AI models, and the association between the N AI models and the Positioning Reference Signal (PRS) port is determined based on the training samples corresponding to the N AI models.

21. The method according to claim 20, characterized in that, Before the network-side device sends the AI ​​model information to the terminal, it also includes: The network-side device receives channel impulse responses sent by multiple sampling points. The impulse responses are obtained by the sampling points performing channel estimation on the reference positioning signal (PRS). The network-side device generates training samples based on multiple channel impulse responses, the locations of the multiple sampling points, and the PRS port used to transmit the PRS. The network-side device uses the training samples to train multiple initial AI models, thereby obtaining multiple trained AI models. The network-side device determines the AI ​​model information based on the configuration information of N AI models out of the plurality of trained AI models and the PRS ports associated with the training samples of the N AI models.

22. A positioning device, characterized in that, include: The receiving module is used to receive AI model information from network-side devices; The positioning module is used to execute a positioning process based on the AI ​​model information, wherein the AI ​​model information includes: configuration information of N AI models and the association relationship between the N AI models and the positioning reference signal PRS port, where N is a positive integer greater than or equal to 1; In the case of repeated PRS port numbering, the association between the N AI models and the positioning reference signal PRS port includes: a first association between the N AI models and the TRP group, and a second association between the N AI models and the PRS port group; When the PRS ports are not numbered repeatedly, the association between the N AI models and the positioning reference signal PRS ports includes: the second association between the N AI models and the PRS port group; Each AI model is associated with a TRP group that includes one or more TRPs, and each AI model is associated with a PRS port group that includes one or more PRS ports.

23. A positioning device, characterized in that, include: The model information sending module is used to send AI model information to the terminal so that the terminal can execute the positioning process based on the AI ​​model information; The AI ​​model information includes: configuration information of N AI models and the association between the N AI models and the Positioning Reference Signal (PRS) port, where N is a positive integer greater than or equal to 1; In the case of repeated PRS port numbering, the association between the N AI models and the positioning reference signal PRS port includes: a first association between the N AI models and the TRP group, and a second association between the N AI models and the PRS port group; When the PRS ports are not numbered repeatedly, the association between the N AI models and the positioning reference signal PRS ports includes: the second association between the N AI models and the PRS port group; Each AI model is associated with a TRP group that includes one or more TRPs, and each AI model is associated with a PRS port group that includes one or more PRS ports.

24. A terminal, 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 positioning method as described in any one of claims 1 to 10.

25. A network-side 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 positioning method as described in any one of claims 11 to 21.

Images