Communication method and apparatus

Abstract

The communication method and device provided by the embodiments of the present application relate to the technical field of communication. The intelligent model (such as an AI / ML model) for predicting the positioning error of the first node using the navigation system is trained by using the historical positioning data of the first node and the positioning error data at the moment corresponding to the historical positioning data, the positioning information of the navigation system can be combined with the positioning error predicted by the intelligent model, and the positioning information output by the navigation system can be compensated based on the positioning error, thereby improving the accuracy and flexibility of the positioning of the first node, and reducing the model complexity. Especially suitable for positioning scenarios of high-speed mobile carriers, effectively solving the accuracy and mutation problems of model positioning or navigation system positioning in high-speed scenarios.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, and particularly relates to a communication method and device. BACKGROUND

[0002] In order to provide positioning-related services for a UE (User Equipment), the UE needs to be positioned. Due to the wide deployment of mobile communication networks, there is a demand for high-precision wireless positioning of the UE.

[0003] Since a positioning method based on geometric relationships (such as triangulation) is greatly affected by environmental factors, especially in current scenarios such as ultra-dense networking, it is difficult to meet the requirements of high precision, low latency, real-time performance, and dynamic adaptability. In the 5th generation mobile communication technology (5G), Artificial Intelligence (AI) / Machine Learning (ML) is introduced, which can apply different AI / ML functions to mobile communication networks.

[0004] Therefore, how to use an AI / ML model to more accurately position the UE is a problem that needs to be solved at present. SUMMARY

[0005] Embodiments of the present application provide a communication method and device, which can effectively improve the positioning accuracy of the UE.

[0006] In a first aspect, embodiments of the present application provide a communication method, applied to a first node, which can be a user equipment (UE). The method comprises receiving first information from a second node, which can be a Location Management Function (LMF) network element. The first information includes input data and expected output data for training an intelligent model. The input data and the expected output data are determined according to a preset positioning scenario. The input data includes historical positioning data of the first node, and the expected output data includes positioning error data at a time corresponding to the historical positioning data. The method further comprises determining the intelligent model according to the first information. The intelligent model is used to train positioning error according to current positioning data.

[0007] The embodiments of the present application train an intelligent model (such as an AI / ML model) for predicting the positioning error of the first node using the navigation system by using the historical positioning data of the first node and the positioning error data at the corresponding time of the historical positioning data, which can combine the positioning information of the navigation system with the positioning error predicted by the intelligent model, and compensate the positioning information output by the navigation system based on the positioning error, thereby improving the accuracy and flexibility of the positioning of the first node. It is especially suitable for the positioning scene of high-speed mobile carriers, and effectively solves the accuracy and mutation problems of model positioning or navigation system positioning in high-speed scenarios.

[0008] In an optional implementation, the intelligent model can be a Gated Recurrent Unit (GRU) model. As a variant of recurrent neural network, the GRU model has only two memory unit gates, so the training parameters of the GRU model are reduced compared with other variants of recurrent neural network, such as Long Short-Term Memory (LSTM) model, and the computational complexity is lower, which can greatly improve the training efficiency.

[0009] In an optional implementation, the positioning scene includes a first positioning scene of combined positioning by multiple navigation systems, the multiple navigation systems include a main navigation system and an auxiliary navigation system, the historical positioning data includes first historical positioning data of the main navigation system, and the positioning error data includes positioning difference data between the multiple navigation systems at the corresponding time of the first historical positioning data. The above determining the intelligent model according to the first information can be implemented in the following manner: taking the first historical positioning data as input and the positioning difference data as output, training the first mapping relationship between the input data and the output data in the intelligent model. The intelligent model is determined according to the first mapping relationship.

[0010] Optionally, the main navigation system can include an Inertial Navigation System (INS), and the auxiliary navigation system can include a Global Navigation Satellite System (GNSS).

[0011] In the positioning scenario of positioning by a plurality of navigation systems in combination, the GNSS / INS historical navigation data of the UE is obtained from the LMF, the INS positioning data in the GNSS / INS historical navigation data (i.e., the first historical positioning data) is taken as input, and the positioning difference data between the GNSS / INS positioning data and the INS positioning data (i.e., the difference between the position navigation results hereinafter) is taken as expected output, to train the intelligent model. The AI model can be used to assist in error compensation for UE positioning, and the INS positioning information in the GNSS signal loss state (in which the satellite signal cannot be locked due to signal shielding, etc.) can be corrected.

[0012] In an optional implementation, the positioning scenario includes a second positioning scenario of positioning by one navigation system, the historical positioning data includes second historical positioning data of the navigation system, the positioning error data includes an error sequence corresponding to the second historical positioning data, and the error sequence is a sequence of positioning errors corresponding to the positioning position elements at each time in the second historical positioning data. The determination of the intelligent model according to the first information can be performed in the following manner: the second historical positioning data is taken as input, and the error sequence is taken as output, to train a second mapping relationship between the input data and the output data in the intelligent model. The intelligent model is determined according to the second mapping relationship.

[0013] Optionally, the first information can further include historical positioning true values at each time, and the error sequence can be determined according to the historical positioning true values.

[0014] Exemplarily, the UE can perform positioning by using only the INS or another navigation system. Considering that the UE can not have the capability of combined navigation in some scenarios, in order to effectively improve the positioning accuracy of the UE in such scenarios, the historical positioning data of the UE in positioning by using the navigation system is taken as input, and the error sequence corresponding to the historical positioning data is taken as expected output, to train the intelligent model. The trained model can be used to predict the positioning error of the single navigation system, to realize error compensation of the single navigation system and improve the positioning accuracy.

[0015] In an optional implementation, the determination of the intelligent model according to the first information can be performed in the following manner: the intelligent model is determined according to a preset model training period and the first information; and the model training period is determined based on the time interval step of the historical positioning data and the number of the historical positioning data.

[0016] The embodiment of the present application considers the model training period, and specifies the time range of the data (i.e., the historical positioning data and the error data at the corresponding time in the first information) used for model training. In combination with various historical data information related to positioning contained in the first information, the model learns these data within this specific training period, adjusts the weight parameters, so that the model can make full use of the positioning data with time correlation, better learn the relationship between the error and various input information, to improve the prediction accuracy and robustness of the model, and provide reliable support for subsequent positioning error correction.

[0017] In an optional implementation, the intelligent model can also be updated according to a preset model update period and the first information. The model update period is determined according to the motion state of the first node.

[0018] The embodiment of the present application considers that in the high-speed moving state of the UE, the model may not be applicable to the current rapidly changing motion state characteristics, and as the motion state changes and time elapses, the prediction accuracy of the model may also be affected. By dynamically adjusting the model update period according to the error accumulation rate in different motion states, and updating the intelligent model in combination with the model update period, the model accuracy can be effectively improved.

[0019] In an optional implementation, before receiving the first information from the second node, a request message can also be sent to the second node, and the request message is used to request the first information from the second node. In this way, the UE can obtain the first information used for training the intelligent model in time when needed, thereby improving the positioning accuracy, especially in complex or high-speed moving scenarios.

[0020] In an optional implementation, before receiving the first information from the second node, the second information can also be reported to the second node, and the second information is used to indicate the positioning capability information of the first node. The second information includes at least one of the following: a model structure supporting model positioning, a data type of input and expected output required for training the model, a model training period, and a model update period.

[0021] In this way, the UE reports the second information, and the LMF can better understand the specific positioning function and supported technology of the UE, thereby providing more optimized positioning service for the UE. For example, if the UE supports a specific model positioning technology, the LMF can provide corresponding assistance data (such as the first information) for model training of the UE, thereby enhancing the positioning accuracy of the UE.

[0022] In a second aspect, an embodiment of the present application provides a communication method applied to a first node, comprising: obtaining a positioning error by processing current positioning data according to a preset intelligent model, wherein the intelligent model is determined according to first information sent by a second node; and sending third information to the second node, wherein the third information comprises the positioning error, or the third information comprises positioning information determined according to the positioning error.

[0023] In an optional implementation, the process of processing the current positioning data according to the preset intelligent model can be performed in the following manner: when the moving speed of the first node reaches a preset threshold, the current positioning data is processed according to the preset intelligent model.

[0024] In an optional implementation, the process of processing the current positioning data according to the preset intelligent model can be performed in the following manner: the current positioning data is input into the intelligent model, and the current positioning data is processed based on the intelligent model to obtain a positioning error at a moment corresponding to the current positioning data. The current positioning data comprises at least one of the following: an angular velocity measurement value, a specific force measurement value, a solved velocity navigation solution, and a heading angle navigation solution.

[0025] In an optional implementation, positioning compensation information for the current positioning data can also be determined according to the positioning error, and the positioning information can be determined according to the positioning compensation information and the current positioning data.

[0026] In an optional implementation, the current positioning data is first current positioning data obtained by a primary navigation system in a first positioning scenario, and the positioning compensation information is compensation positioning data for positioning of a secondary navigation system in the first positioning scenario. The positioning information can be determined by fusing the positioning compensation information and the current positioning data through a Kalman filter.

[0027] In an optional implementation, the current positioning data is second current positioning data obtained by a navigation system in a second positioning scenario, and the positioning compensation information is correction positioning data for correcting the second current positioning data. The positioning information can be determined by correcting the current positioning data according to the positioning compensation information.

[0028] In a third aspect, an embodiment of the present application provides a communication method, applied to a second node, comprising: sending first information to a first node, the first information comprising input data and expected output data used for training an intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data comprising historical positioning data of the first node, and the expected output data comprising positioning error data at a time corresponding to the historical positioning data.

[0029] In an optional implementation, before the first information is sent to the first node, the method further comprises: receiving a request message sent by the first node, the request message being used to request the first information from the second node.

[0030] In an optional implementation, before the first information is sent to the first node, the method further comprises: receiving second information reported by the first node, the second information being used to indicate positioning capability information of the first node, and the second information comprising at least one of the following: a model structure supporting model positioning, a data type of input and expected output required for training the model, a model training period, and a model updating period.

[0031] In a fourth aspect, an embodiment of the present application provides a communication apparatus, which can be an electronic device, or a chip or chip system in the electronic device. The communication apparatus can comprise a first transceiver unit and a first processing unit. When the communication apparatus is an electronic device, the first transceiver unit can be a Wi-Fi module or a cellular network module, etc. The first transceiver unit is configured to perform the steps of transceiving, so that the electronic device implements the communication method described in the first aspect or any possible implementation manner of the first aspect. When the communication apparatus is an electronic device, the first processing unit can be a processor. The communication apparatus can further comprise a storage unit, which can be a memory. The storage unit is configured to store instructions, and the first processing unit executes the instructions stored in the storage unit, so that the electronic device implements the communication method described in the first aspect or any possible implementation manner of the first aspect. When the communication apparatus is a chip or chip system in the electronic device, the first processing unit can be a processor. The first processing unit executes the instructions stored in the storage unit, so that the electronic device implements the communication method described in the first aspect or any possible implementation manner of the first aspect. The storage unit can be a storage unit (for example, a register, a cache, etc.) in the chip, or a storage unit (for example, a read-only memory, a random access memory, etc.) in the electronic device and located outside the chip.

[0032] An example first transceiving unit is configured to receive first information from a second node, the first information including input data and expected output data for training an intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data including historical positioning data, and the expected output data including positioning error data corresponding to the historical positioning data at a time point.

[0033] In an optional implementation, the intelligent model can be a gated recurrent unit model.

[0034] In an optional implementation, the positioning scenario includes a first positioning scenario of positioning by a plurality of navigation systems, the plurality of navigation systems including a main navigation system and an auxiliary navigation system, the historical positioning data includes first historical positioning data of the main navigation system, and the positioning error data includes positioning difference data between the plurality of navigation systems at a time point corresponding to the first historical positioning data; the first processing unit is specifically configured to train a first mapping relationship between the input data and the output data in the intelligent model by taking the first historical positioning data as the input and taking the positioning difference data as the output, and determine the intelligent model according to the first mapping relationship.

[0035] In an optional implementation, the main navigation system can include an inertial navigation system, and the auxiliary navigation system can include a global navigation satellite system.

[0036] In an optional implementation, the positioning scenario includes a second positioning scenario of positioning by one navigation system, the historical positioning data includes second historical positioning data of the navigation system, and the positioning error data includes an error sequence corresponding to the second historical positioning data, the error sequence being a sequence of positioning errors corresponding to positioning position elements at each time point in the second historical positioning data; the first processing unit is specifically configured to train a second mapping relationship between the input data and the output data in the intelligent model by taking the second historical positioning data as the input and taking the error sequence as the output, and determine the intelligent model according to the second mapping relationship.

[0037] In an optional implementation, the first information can further include historical positioning true values at each time point, and the error sequence is determined according to the historical positioning true values.

[0038] In an optional implementation, the first processing unit is specifically configured to determine the intelligent model according to a preset model training period and the first information; the model training period is determined based on a time interval step of the historical positioning data and a quantity of the historical positioning data.

[0039] In an optional implementation, the first processing unit is further configured to update the intelligent model according to a preset model update period and the first information, wherein the model update period is determined according to the motion state of the first node.

[0040] In an optional implementation, the first transceiving unit is further configured to send a request message to the second node after receiving the first signal from the second node, wherein the request message is used to request the first information from the second node.

[0041] In an optional implementation, the first transceiving unit is further configured to report second information to the second node before receiving the first information from the second node, wherein the second information is used to indicate the positioning capability information of the first node, and the second information comprises at least one of the following: a model structure supporting model positioning, a data type of input and expected output required for training the model, a model training period, and a model update period.

[0042] In a fifth aspect, an embodiment of the present application provides another communication apparatus, which can be an electronic device, or a chip or chip system in the electronic device. The communication apparatus can comprise a second transceiving unit and a second processing unit. When the communication apparatus is an electronic device, the second transceiving unit can be a Wi-Fi module or a cellular network module, etc. The second transceiving unit is configured to perform the steps of transceiving, so that the electronic device implements a communication method described in the second aspect or any possible implementation manner of the second aspect. When the communication apparatus is an electronic device, the second processing unit can be a processor. The communication apparatus can further comprise a storage unit, which can be a memory. The storage unit is configured to store instructions, and the second processing unit executes the instructions stored in the storage unit, so that the electronic device implements a communication method described in the second aspect or any possible implementation manner of the second aspect. When the communication apparatus is a chip or chip system in the electronic device, the second processing unit can be a processor. The second processing unit executes the instructions stored in the storage unit, so that the electronic device implements a communication method described in the second aspect or any possible implementation manner of the second aspect. The storage unit can be a storage unit (for example, a register, a cache, etc.) in the chip, or a storage unit (for example, a read-only memory, a random access memory, etc.) in the electronic device and located outside the chip.

[0043] For example, the second processing unit is configured to process the current positioning data according to a preset intelligent model to obtain a positioning error, wherein the intelligent model is determined according to the first information sent by the second node; and the second transceiving unit is configured to send third information to the second node, wherein the third information comprises the positioning error, or the third information comprises positioning information determined according to the positioning error.

[0044] In an optional implementation, the second processing unit is specifically configured to process the current positioning data according to a preset intelligent model when the moving speed of the first node reaches a preset threshold.

[0045] In an optional implementation, the second processing unit is specifically configured to input the current positioning data into the intelligent model, process the current positioning data based on the intelligent model, and obtain the positioning error at the moment corresponding to the current positioning data. The current positioning data includes at least one of the following: an angular velocity measurement value, a specific force measurement value, a solved speed navigation solution, and a heading angle navigation solution.

[0046] In an optional implementation, the second processing unit is further configured to determine positioning compensation information for the current positioning data according to the positioning error, and determine the positioning information according to the positioning compensation information and the current positioning data.

[0047] In an optional implementation, the current positioning data is first current positioning data obtained by the primary navigation system in a first positioning scenario, and the positioning compensation information is compensation positioning data for positioning of the secondary navigation system in the first positioning scenario. The second processing unit is specifically configured to fuse the positioning compensation information and the current positioning data by a Kalman filter to obtain the positioning information.

[0048] In an optional implementation, the current positioning data is second current positioning data obtained by the navigation system in a second positioning scenario, and the positioning compensation information is correction positioning data for correcting the second current positioning data. The second processing unit is specifically configured to correct the current positioning data according to the positioning compensation information to obtain the positioning information.

[0049] In a sixth aspect, an embodiment of the present application provides another communication apparatus. The communication apparatus can be an electronic device, or a chip or chip system in the electronic device. The communication apparatus can include a third transceiver unit. When the communication apparatus is an electronic device, the third transceiver unit can be a Wi-Fi module or a cellular network module, etc. The third transceiver unit is configured to perform the steps of transceiving, so that the electronic device implements a communication method described in the third aspect or any possible implementation manner of the third aspect.

[0050] For example, the third transceiver unit is configured to send first information to the first node, the first information including input data and expected output data for training the intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data including historical positioning data of the first node, and the expected output data including positioning error data at a moment corresponding to the historical positioning data.

[0051] In an optional implementation, the third transceiver is further configured to receive a request message sent by the first node before sending the first information to the first node, the request message being used to request the first information from the second node.

[0052] In an optional implementation, the third transceiver is further configured to receive second information reported by the first node before sending the first information to the first node, the second information being used to indicate the positioning capability information of the first node, and the second information including at least one of the following: a model structure of a model positioning, a data type of an input and an expected output required for training the model, a model training period, and a model updating period.

[0053] In a seventh aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, the memory is used to store computer execution instructions, and the processor is used to run the computer execution instructions stored in the memory to execute the method described in the first aspect or any possible implementation manner of the first aspect; or, to execute the method described in the second aspect or any possible implementation manner of the second aspect; or, to execute the method described in the third aspect or any possible implementation manner of the third aspect.

[0054] In an eighth aspect, an embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores computer programs or instructions, when the computer programs or instructions are run on a computer, the computer is caused to execute the method described in the first aspect or any possible implementation manner of the first aspect; or, to execute the method described in the second aspect or any possible implementation manner of the second aspect; or, to execute the method described in the third aspect or any possible implementation manner of the third aspect.

[0055] In a ninth aspect, an embodiment of the present application provides a computer program product including a computer program, when the computer program is run, the computer is caused to execute the method described in the first aspect or any possible implementation manner of the first aspect; or, to execute the method described in the second aspect or any possible implementation manner of the second aspect; or, to execute the method described in the third aspect or any possible implementation manner of the third aspect.

[0056] In a tenth aspect, the present application provides a chip system, the chip or the chip system comprising at least one processor and a communication interface, the communication interface and the at least one processor being interconnected by a line, the at least one processor being configured to execute computer programs or instructions to perform the method described in the first aspect or any possible implementation manner of the first aspect, or perform the method described in the second aspect or any possible implementation manner of the second aspect; perform the method described in the third aspect or any possible implementation manner of the third aspect. The communication interface in the chip can be an input / output interface, a pin or a circuit, etc.

[0057] In a possible implementation, the chip or the chip system described above in the present application further comprises at least one memory, and the at least one memory stores instructions. The memory can be a storage unit inside the chip, for example, a register, a cache, etc., or a storage unit of the chip (for example, a read-only memory, a random access memory, etc.).

[0058] It should be understood that the second aspect to the tenth aspect of the present application correspond to the technical solution of the first aspect of the present application, and the beneficial effects obtained by each aspect and the corresponding possible implementation manner are similar, and the related description will not be repeated. BRIEF DESCRIPTION OF DRAWINGS

[0059] Figure 1 A possible architecture of a communication system provided by an embodiment of the present application is shown in a schematic diagram;

[0060] Figure 2a A possible application scenario provided by an embodiment of the present application is shown in a schematic diagram;

[0061] Figure 2b Another possible application scenario provided by an embodiment of the present application is shown in a schematic diagram;

[0062] Figure 3 A flowchart of a communication method provided by an embodiment of the present application is shown in a schematic diagram;

[0063] Figure 4 An example diagram of GNSS / INS combined navigation in an embodiment of the present application is shown;

[0064] Figure 5 A structure diagram of a GRU model in an embodiment of the present application is shown;

[0065] Figure 6 A flowchart of a training process of a GRU model in an embodiment of the present application is shown in a schematic diagram;

[0066] Figure 7 A flowchart of a prediction process of a GRU model in an embodiment of the present application is shown in a schematic diagram;

[0067] Figure 8FIG. 1 is a schematic diagram of a training process of a GRU model according to an embodiment of the present application;

[0068] Figure 9 FIG. 2 is a schematic diagram of a prediction process of a GRU model according to an embodiment of the present application;

[0069] Figure 10 FIG. 3 is an example diagram of a training period and an update period according to an embodiment of the present application;

[0070] Figure 11 FIG. 4 is a schematic diagram of a communication method according to an embodiment of the present application;

[0071] Figure 12 FIG. 5 is a schematic diagram of a communication method according to an embodiment of the present application;

[0072] Figure 13 FIG. 6 is a schematic diagram of a communication method according to an embodiment of the present application;

[0073] Figure 14 FIG. 7 is a schematic diagram of a communication apparatus according to an embodiment of the present application;

[0074] Figure 15 FIG. 8 is a schematic diagram of a communication apparatus according to an embodiment of the present application;

[0075] Figure 16 FIG. 9 is a schematic diagram of a communication apparatus according to an embodiment of the present application;

[0076] Figure 17 FIG. 10 is a schematic diagram of an electronic device according to an embodiment of the present application;

[0077] Figure 18 FIG. 11 is a schematic diagram of a chip system according to an embodiment of the present application. DETAILED DESCRIPTION

[0078] In order to clearly describe the technical solutions of the embodiments of the present application, first, the related technical background and related technologies of the embodiments of the present application are briefly introduced as follows:

[0079] First, a brief introduction to the navigation system. Navigation is to guide the moving carrier (hereinafter referred to as carrier, such as UE, vehicle, unmanned aerial vehicle, etc.) from the current position to the predetermined target position according to the reasonable route, and the real-time position of the carrier needs to be accurately obtained during the period. In the traditional fields of navigation, aviation, surveying and mapping, as well as emerging fields such as automatic driving, unmanned aerial vehicles, etc., navigation and positioning technology plays a very important role. Navigation and positioning technology mainly determines the actual position of the carrier based on "direct positioning" and "dead reckoning". Direct positioning is to use identifiable external information to directly determine the position of the carrier, among which the Global Navigation Satellite System (GNSS) is a typical direct positioning system. In addition to satellite positioning using radio signals, there are laser ranging positioning based on infrared signals and sonar positioning based on sound waves. Dead reckoning is to use the motion amount of the carrier such as speed, attitude, acceleration, etc., and combine it with the motion model to calculate the motion state information of the carrier. The Inertial Navigation System (INS) is a typical dead reckoning positioning system.

[0080] Each navigation system has its own unique advantages, such as INS, which has strong autonomy and can provide more navigation parameter data and higher output frequency. The defects of INS are also more obvious, and its error will gradually accumulate over time, so the long-term reliability is low. The advantage of GNSS is accurate positioning accuracy, and the error does not accumulate with time, but the disadvantage is that the navigation parameter information is not comprehensive, and the signal is easy to be interrupted by interference. In many complex environments, due to the strict requirements of the carrier on positioning accuracy and accuracy, relying on a single navigation technology alone is difficult to achieve the expected effect, so in some scenarios, the advantages of combined navigation technology by fusing the data of multiple navigation systems are increasingly prominent. GNSS / INS combined navigation technology is the most widely used combined navigation scheme for vehicles and unmanned aerial vehicles.

[0081] The Next Generation Radio Access Network (NG-RAN) can use multiple positioning methods to determine the position of the UE, mainly including: (1) signal measurement. (2) Measurement-based position estimation and optional speed calculation. These processes can be performed by the UE or the serving base station, and then the positioning information is reported to the Location Management Function (LMF) through different data transmission methods. The positioning methods supported by NG-RAN include GNSS navigation, inertial navigation positioning, WLAN positioning, and Bluetooth positioning, etc. Different positioning methods are suitable for mobile terminals in different scenarios.

[0082] With the wide deployment of mobile communication networks, there is an increasing demand for high-precision wireless positioning of carriers such as user equipment (UE). With the possibility of AI / ML models being applied in UE positioning, the UE can choose the following positioning service modes when sending a function message to the LMF: (1) traditional geometric relationship-based positioning methods (such as triangulation); (2) AI / ML direct positioning; (3) AI / ML assisted positioning.

[0083] However, traditional geometric relationship-based positioning methods (such as triangulation) are significantly affected by environmental factors in non-line-of-sight environments, complex urban areas, and ultra-dense networking environments, and are difficult to meet the requirements of high precision, low latency, real-time, and dynamic adaptability. Current AI / ML positioning algorithms mainly rely on historical positioning data to train the model to predict the UE's location information to complete positioning. The positioning accuracy of these models is highly dependent on past data, and the computational complexity is high, with poor flexibility. Moreover, when the UE moves slowly, the training and prediction errors of the AI model are small; in high-speed moving scenarios, the UE position change will cause the AI prediction performance to drop sharply.

[0084] Therefore, the current UE positioning technology faces the following problems:

[0085] (1) The accuracy of traditional geometric relationship-based positioning methods is limited in non-line-of-sight environments, complex urban areas, and ultra-dense networking environments.

[0086] (2) Current AI / ML models require a large amount of positioning data for training, and the cost of obtaining high-quality data is high. Moreover, the model has high computational complexity, which is limited in resource-constrained terminals, and has poor flexibility.

[0087] (3) Current AI / ML models are difficult to adapt to high-speed moving scenarios such as UEs.

[0088] Therefore, there is an urgent need to study AI / ML-based assisted positioning or direct positioning algorithms to improve the accuracy and robustness of UE positioning technology.

[0089] Therefore, the communication method and device provided in the embodiments of the present application are proposed. A first node (a moving carrier such as a UE) receives first information of a second node (a node carrying historical positioning data of the moving carrier such as an LMF network element), the first information including input data and expected output data for training an intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data including historical positioning data of the first node, and the expected output data including positioning error data at a time corresponding to the historical positioning data, and the intelligent model is determined according to the first information, the intelligent model being used to train positioning error according to current positioning data. In this process, the historical positioning data of the first node and the positioning error data at the time corresponding to the historical positioning data are used to train an intelligent model (such as an AI / ML model) for predicting positioning error of the first node using a navigation system for positioning. The positioning information of the navigation system can be combined with the positioning error predicted by the intelligent model, and the positioning information output by the navigation system can be compensated based on the positioning error, thereby improving the accuracy and flexibility of positioning of the first node. It is especially suitable for positioning scenarios of high-speed moving carriers, and effectively solves the accuracy and mutation problems of model positioning or navigation system positioning in high-speed scenarios. In addition, compared with training a model to predict position information in the related art, the embodiments of the present application focus more on error characteristics, have lower model complexity, and the data used to train the model is also more concise, reducing the excessive dependence on a large amount of historical positioning data.

[0090] In the following, the embodiments of the present application will take various currently commonly used navigation positioning technologies as scheme embodiments to explain the specific implementation details of the AI / ML assisted positioning mode in detail.

[0091] First of all, it should be noted that in the embodiments of the present application, the same items or similar items with basically the same functions and effects are distinguished by using "first", "second", etc. For example, the first chip and the second chip are only used to distinguish different chips, and do not limit the sequence. Those skilled in the art can understand that "first", "second", etc. do not limit the quantity and execution order, and "first", "second", etc. also do not necessarily mean different.

[0092] It should be noted that in the embodiments of the present application, "exemplary" or "for example" is used to represent an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" is intended to present the relevant concept in a specific manner.

[0093] In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more. The "and / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single item or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0094] In the present application, "sending information / data" only indicates the direction of information / data transmission, including direct sending by the communication interface (such as air interface, etc.) of the device, "sending" can also be understood as the "output" of the module interface, and "sending" can include indirect sending by the processing unit through the communication interface, that is, the processing unit outputs information / data through the module interface, and then transmits to the communication interface of the device for sending. "Receiving information / data" only indicates the direction of information / data transmission, including direct receiving by the communication interface, "receiving" can also be understood as the "input" of the module interface, and "receiving information / data" can include indirect receiving by the processing unit through the communication interface, that is, the communication interface receives information / data, and then transmits to the module interface of the processing unit, and then the module interface inputs the information / data to the processing unit. "Sending information / data to (such as terminal)" can be understood as that the destination of the information is the terminal. It can include direct or indirect sending of information / data to the terminal. "Receiving information / data from (such as terminal)" can be understood as that the source of the information is the terminal. It can include direct or indirect receiving of information / data from the terminal. The information / data can be processed as necessary between the source and the destination of the information / data, such as format change, etc., but the destination can understand the valid information / data from the source. Similar expressions in the present application can be understood similarly, and will not be repeated here.

[0095] The technical solutions of the embodiments of the present application can be applied to various communication systems, for example: long term evolution (long term evolution, LTE) system, 5th generation (5th generation, 5G) communication system, satellite communication system, wireless fidelity (wireless fidelity, WiFi) system, and the scheme provided by the present application can also be applied to future communication systems or other communication systems, etc. The present application does not make any limitation.

[0096] Figure 1is a schematic diagram of an architecture of a communication system applicable to the communication method provided in the present application. Figure 1 A schematic diagram of a possible, non-limiting system architecture is shown. As Figure 1 illustrated, the communication system includes a radio access network (RAN) 10 and a core network (CN) 20. Optionally, the communication system further includes the Internet 30. The RAN 10 includes at least one RAN node (e.g., 110a and 110b in Figure 1 , collectively referred to as 110) and at least one terminal (e.g., 120a-120j in Figure 1 , collectively referred to as 120). Other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1 ), etc., can also be included in the RAN 10. The terminals 120 are wirelessly connected to the RAN nodes 110. The RAN nodes 110 are connected to the core network 20 through wireless or wired means. The core network devices in the core network 20 and the RAN nodes 110 in the RAN 10 can be different physical devices, respectively, or can be the same physical device that integrates the core network logical functions and the radio access network logical functions.

[0097] The RAN 10 can be a 3rd generation partnership project (3GPP) related cellular system, e.g., a 4G, 5G mobile communication system, or a future-oriented evolved system. The RAN 10 can also be an open RAN (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (Wi-Fi) system. The RAN 10 can also be a communication system that integrates two or more of the above systems.

[0098] The RAN nodes 110, which can also be referred to as access network devices, RAN entities, or access nodes, etc., are part of the communication system and help terminals to access the wireless access. The RAN nodes 110 in the communication system can be of the same type or of different types. In some scenarios, the roles of the RAN nodes 110 and the terminals 120 are relative, e.g., Figure 1 in which the network element 120i can be a helicopter or a drone, which can be configured as a mobile base station. For those terminals 120j that access the RAN 10 through the network element 120i, the network element 120i is a base station; but for the base station 110a, the network element 120i is a terminal. The RAN nodes 110 and the terminals 120 are sometimes collectively referred to as communication apparatuses, e.g., Figure 1Network elements 110a and 110b can be understood as communication devices with base station functions, while network elements 120a-120j can be understood as communication devices with terminal functions.

[0099] In one possible scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a next-generation base station in a 6G mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system, etc. Figure 1 110a), micro base stations or indoor stations (such as Figure 1 The RAN node can be a 110b unit, a relay node or donor node, or a radio controller in a CRAN scenario. Optionally, the RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU).

[0100] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with different RAN nodes each implementing a portion of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be set up separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0101] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, the CU can also be referred to as O-CU (Open Central Unit, responsible for processing the control plane (Control Plane) protocol, including being responsible for managing the packet data aggregation protocol (PDCP), service data adaptation protocol (SDAP) and radio resource control (RRC) protocol entity), DU can also be referred to as (Open Distributed Unit, O-DU, with baseband processing function, with complete protocol layer function, mainly responsible for data encryption and integrity protection and other high-layer protocol functions. At the same time, it has physical layer high-layer processing function), CU-CP can also be referred to as O-CU-CP, CU-UP can also be referred to as O-CU-UP, and RU can also be referred to as (Open Radio Unit, O-RU, with physical layer bottom layer signal processing function, mainly responsible for transmitting and receiving radio frequency signals). For the convenience of description, the CU, CU-CP, CU-UP, DU and RU are taken as examples for description in this application. Any one of the CU (or CU-CP, CU-UP), DU and RU in this application can be realized by a software module, a hardware module, or a combination of a software module and a hardware module.

[0102] The terminal can also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. The terminal can be widely applied to various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), internet of things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, remote medical treatment, smart power grid, smart furniture, smart office, smart wear, smart transportation, smart city, etc. The terminal can be a mobile phone, tablet computer, computer with wireless transceiver function, wearable device, vehicle, unmanned aerial vehicle, helicopter, airplane, ship, robot, mechanical arm, smart home device, etc.

[0103] In the embodiments of the present application, the terminal and the network device can be hardware devices, or software functions running on special hardware, software functions running on general hardware, such as virtualized functions instantiated on a platform (e.g., a cloud platform), or entities including special or general hardware devices and software functions. The specific form of the terminal and the network device is not limited in the present application.

[0104] The following further introduces possible application scenarios of the embodiments of the present application, taking UE positioning as an example, as shown in Figure 2a and Figure 2b . Figure 2a It is shown that the UE has a combined navigation capability, for example, the UE has a GNSS navigation system and an INS navigation system, and can adopt CNSS / INS combined navigation positioning. The UE can receive input data and expected output data for training an intelligent model sent by the LMF, and the input data and expected output data can be historical positioning data (such as INS historical positioning data obtained by differential GNSS / INS) and corresponding positioning error data (such as positioning difference data between GNSS / INS positioning results and INS positioning results) of the UE using CNSS / INS combined navigation positioning, so as to train an intelligent model that can be used to predict positioning error. Especially when the UE is in a high-speed motion state, due to Doppler effect, signals are blocked by buildings, bridges, etc. in urban environments, or multi-path effect (signal reflection) occurs, etc., so that the GNSS positioning accuracy is no longer accurate. The UE can use the trained intelligent model to predict the positioning error data corresponding to the GNSS in combination with the INS navigation data, and determine the positioning compensation information by using the positioning error data, so as to realize the positioning compensation of the INS navigation data, and solve the problem of poor positioning accuracy of the UE in high-speed motion. Figure 2b It is shown that the UE adopts a navigation system, such as an INS navigation system, for navigation positioning, which is different from the scenario shown in Figure 2a The input data and expected output data used by the UE to train the intelligent model can be historical positioning data of the INS and a positioning error sequence corresponding to the historical positioning data, so as to effectively improve the positioning accuracy of the UE in the scenario of a navigation system, and improve the positioning accuracy in a high-speed motion scenario. It should be understood that in some application scenarios, the UE can also obtain or store an intelligent model that has been trained from other devices or apparatuses, without training the intelligent model, and directly apply the intelligent model to predict the positioning error.

[0105] In combination with the above possible application scenarios, Figure 3 is one of the flow diagrams of the communication method proposed in the embodiments of the present application. The first node can be any terminal or apparatus (such as a chip or a module, etc.) configured in the terminal, for example, the first node can be Figure 2a or Figure 2b It is shown that the UE or the apparatus (such as a chip or a module, etc.) configured in the UE in the application scenario, which can also be Figure 1 It is shown that any mobile device in the terminal 120 or the apparatus (such as a chip or a module, etc.) configured in the mobile device. The second node can be Figure 2a or Figure 2b It is shown that the LMF, which can also beFigure 1 Any core network device or apparatus (such as a chip or module, etc.) configured in the core network device is shown. The following takes the first node as the UE and the second node as the LMF as an example to describe the embodiments of the present application. As shown in the figure, the method can include steps S301 and S302. Figure 3

[0106] Step S301, the UE receives first information from the LMF, the first information including input data and expected output data for training the intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data including historical positioning data of the first node, and the expected output data including positioning error data at a time corresponding to the historical positioning data.

[0107] The location management function (LMF) is a key component in the communication network architecture, responsible for managing and providing services related to the location of user equipment (UE). As a centralized location management entity in the network, the LMF can collect and integrate positioning data from multiple sources, including base station signal measurement and time synchronization information, etc. This centralized data management ensures the integrity and reliability of the data, providing comprehensive and accurate historical positioning data for the UE. These data are verified by the network and have high credibility, which helps to improve the effect of model training. In addition, by obtaining data from the LMF, the UE can make its positioning model consistent with the overall positioning strategy of the network, improving the quality and consistency of the positioning service.

[0108] Optionally, the LMF can send the first information to the UE through the positioning protocol (LTE Positioning Protocol, LPP) assistance message (LPP Provide Assistance Information). The first information can be requested by the UE, provided by the LMF to the UE, or actively provided by the LMF to the UE, which is not particularly limited in this embodiment.

[0109] In this embodiment, the positioning scenario can include scenarios corresponding to multiple navigation systems, or scenarios corresponding to one navigation system. The following are two example ways provided by this embodiment.

[0110] Example one: the positioning scenario can include a first positioning scenario for combined positioning by multiple navigation systems, the multiple navigation systems including a main navigation system and an auxiliary navigation system, the historical positioning data including first historical positioning data of the main navigation system, and the positioning error data including positioning difference data between the multiple navigation systems at a time corresponding to the first historical positioning data.

[0111] ​In this example, the primary navigation system can be an inertial navigation system (INS) system, and the secondary navigation system can be a global navigation satellite system (GNSS) system. In some examples, the primary navigation system can also be a GNSS system, and the secondary navigation system can be an INS system. Alternatively, the primary navigation system and the secondary navigation system are other navigation systems, which are not particularly limited in the present embodiment.

[0112] In combination with the foregoing, the INS can obtain the position, velocity and attitude information of the carrier (UE in the present embodiment) by integrating the accelerometer and gyroscope measurement data, but at the same time, it is accompanied by data drift, measurement error and error time accumulation problems, which can cause the position and velocity information obtained by the INS in navigation to rapidly diverge. Therefore, the secondary positioning information of the GNSS can be used to compensate for the positioning error of the INS, and the compensation principle is as shown in Figure 4 The inertial measurement unit (IMU), accelerometer and gyroscope can measure the acceleration and angular velocity of the carrier and other measurement information. Then, the INS calculates the measurement information input by the IMU, that is, integrates and calculates the accelerometer and gyroscope measurement data, and the position, velocity and attitude information of the carrier can be obtained. The GNSS determines the position and other information by receiving satellite signals, which can provide high-precision secondary positioning information. The Kalman (KF) filter receives the position, velocity and attitude information obtained by the INS data calculation and the secondary positioning information provided by the GNSS, and fuses the two sets of information to correct the error of the INS, thereby outputting the corrected positioning information. After correction, the positioning information provided by the INS is significantly improved in accuracy, effectively solving the problem of positioning divergence caused by INS error accumulation. It can be understood that the KF filter is an optimal estimation algorithm based on a state space model, which can accurately estimate and correct the system state in the presence of noise and uncertainty.

[0113] However, the GNSS improves the accuracy of the INS positioning to some extent. However, the GNSS system is easily affected by the observation environment, and the satellite signal is easily affected by the sheltering objects such as high-rise buildings and tree shadows, so that the satellite signal received by the GNSS is disturbed, and even in places such as tunnels with serious sheltering, the GNSS signal is completely interrupted. At this time, the integrated navigation system degenerates into a single INS for positioning, and the positioning accuracy and precision will also decrease. Therefore, in this positioning scenario, the present application obtains the GNSS / INS historical navigation data of the UE from the LMF, uses the INS positioning data in the GNSS / INS historical navigation data (i.e., the first historical positioning data) as input, and the positioning difference data between the GNSS / INS positioning data and the INS positioning data (i.e., the difference between the position navigation results in the following ) as the expected output to train the subsequent intelligent model (such as an AI / ML model). The AI model can be used to assist in error compensation for UE positioning, and can correct the INS positioning information in a GNSS signal loss state (in which the satellite signal cannot be locked due to signal blocking, etc.).

[0114] It should be noted that in other navigation system scenarios, the overall positioning accuracy will decrease as the accuracy of one of the navigation systems decreases. The present embodiment only uses GNSS / INS as an example to illustrate the technical solutions of the present application, and is not a limitation of the technical solutions of the present application.

[0115] Example two, the positioning scenario includes a second positioning scenario positioned by one of the navigation systems, the historical positioning data includes second historical positioning data of the navigation system, and the positioning error data includes an error sequence corresponding to the second historical positioning data, the error sequence being a sequence composed of positioning errors corresponding to positioning position elements at each time in the second historical positioning data.

[0116] In this example, the UE can only use one navigation system (such as INS or other navigation systems) for positioning. Compared with the combined positioning of multiple navigation systems, the positioning accuracy of a single navigation system is relatively low. Considering that the UE may not have the ability to combine navigation in some scenarios, in order to effectively improve the positioning accuracy of the UE in such scenarios, the present embodiment can also improve the positioning accuracy of the UE for the positioning scenario of one navigation system. Similar to the combined navigation scenario, the data used to train the intelligent model is the historical positioning data of the UE using the navigation system for positioning as input, and the error sequence corresponding to the historical positioning data is used as the expected output to train the intelligent model, to predict the positioning error of the single navigation system, thereby achieving error compensation and improving the positioning accuracy.

[0117] In step S302, the UE determines an intelligent model according to the first information, the intelligent model being used to train a positioning error according to current positioning data.

[0118] Optionally, the intelligent model can use a Gated Recurrent Unit (GRU) model.

[0119] Considering that the error of the navigation system usually has a correlation with time, especially for INS navigation, since the error of the IMU has a correlation with time, the neural network model can be used to train and predict the error change of the INS, to provide error compensation for the positioning calculation of the INS.

[0120] Recurrent Neural Network (RNN) is a kind of neural network model that performs well on sequence data. Unlike traditional feedforward neural networks, RNN has feedback loop connection, which enables them to capture time dependence in sequence data. However, RNN is prone to gradient vanishing problem when processing long time sequence data, which affects the prediction accuracy of the model. Therefore, two variants of RNN model are derived to solve this problem. Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) both introduce gating mechanism to solve the gradient vanishing problem of RNN model. The difference between them is that LSTM introduces three gating mechanisms, namely input gate, forget gate and output gate, which control the input, forget and output of information respectively, and introduces a memory unit to store key information. However, since the three gates of LSTM have different contributions to improving prediction accuracy, under the condition of limited computing power and storage resources, omitting the gate with smaller contribution and the corresponding weight is beneficial to improve the operation speed and reduce the calculation space. Therefore, the GRU model optimizes the three gates of LSTM model into two gates, namely reset gate and update gate. The update gate realizes the input gate in the LSTM model, which receives data input from the outside and processes the data, and the update gate realizes the forget gate and output gate in the LSTM model. The internal structure of the GRU model is shown in Figure 5 , and described as follows in combination with mathematical formula:

[0121] (1)

[0122] (2)

[0123] (3)

[0124] (4)

[0125] In the formula, Z t , r t are update gate and reset gate respectively, X t represents the input vector at the current time t, h t-1 is the memory variable (hidden state) at the previous time t-1; W, U are corresponding weight parameters, and the different subscripts represent the weights used in different calculation processes, for example, W z , U z are used for update gate calculation, W r , U r are used for reset gate calculation, and so on h t is the candidate set, and h tis the hidden state for the current time t, which is the final output state that fuses the information of the previous state and the candidate hidden state; σ represents the sigmoid activation function; and represents the element-wise multiplication (Hadamard product), that is, the multiplication of corresponding elements of two vectors of the same dimension. The principle of the above formula is as follows: first, according to the formula, the input data and the previous time memory variable are arranged and combined, and the input data is converted to (0, 1) through the sigmoid function and input to the update gate and the reset gate. Then, the reset gate, the input data, and the past state variable are linearly transformed and combined. Finally, the information of the two is superimposed as the output of the current time.

[0126] Since the GRU model has only two memory unit gates, the training parameters of the GRU model are reduced compared to the LSTM model, the computational complexity is lower, and the training efficiency can be greatly improved.

[0127] Next, the training process of the intelligent model is further introduced for different positioning scenarios.

[0128] In the first positioning scenario corresponding to the combination positioning of various navigation systems, the above determination of the intelligent model according to the first information can be performed in the following manner: the first historical positioning data is taken as the input, the positioning difference value data is taken as the output, and the first mapping relationship between the input data and the output data in the intelligent model is trained; and the intelligent model is determined according to the first mapping relationship.

[0129] Exemplarily, taking the GRU model as an example, in combination with Figure 6 As shown in FIG. 1, when the GNSS signal is not interrupted, the differential GNSS navigation information (denoted as P GNSS ) and the information obtained from the INS mechanical arrangement (that is, the output of the inertial measurement unit IMU, denoted as P INS ) can be input into a Kalman filter to solve the positioning information, and then the INS data is corrected (to obtain the corrected positioning information, including the position P GNSS / INS , which can also include the velocity V GNSS / INS and the acceleration A GNSS / INS ). In addition, the specific force f b output by the IMU, the angular velocity ω b , and optionally, the velocity information V INS solved by the INS and the heading angle information (that is, the attitude information) A INS) as the input matrix of the GRU model. Specifically, since the GNSS signal is lost, the integrated navigation system degenerates into a single INS positioning system, and therefore the model input is the INS output result. The INS is a navigation system that uses an inertial measurement unit (such as an accelerometer and a gyroscope) to measure the motion state, so the input of the GRU network can be the fusion result of the IMU measurement output and the INS navigation positioning result output (in some embodiments, only the position data calculated by the INS can be used as the input, which is not particularly limited in the present embodiment). The INS position calculation generally includes carrier attitude calculation, velocity specific force calculation and position calculation. Alternatively, the input feature vector X t may be:

[0130] (5)

[0131] where ω bT represents the three-axis angular velocity measurement (i.e. angular velocity) from the gyroscope, f bT represents the three-axis specific force measurement (i.e. specific force) from the accelerometer, v nT represents the three-dimensional velocity navigation solution (i.e. velocity information) from the INS mechanical arrangement, and sinφ and cosφ represent the heading angle navigation solution (i.e. heading angle information), respectively. It should be understood that T represents transpose.

[0132] Correspondingly, the difference δP between the GNSS and INS position navigation results at the corresponding time (optionally, the difference δv in velocity information and the difference δA in heading angle information can also be included) can be used as the expected output of the GRU model training, and the mapping relationship between the input and the target output can be established. It can be understood that the above data used for training the model can be historical positioning data when the GNSS signal is not interrupted from the LMF.

[0133] As shown in Figure 7 , when the GNSS signal is interrupted, the GNSS will not be able to provide the corresponding navigation information, at which time the UE can enable the pre-trained GRU model to predict the error difference value at the corresponding time, and use the error difference value to calculate the pseudo-GNSS position information (i.e. positioning compensation information). Then the pseudo-GNSS position information and the INS calculation information are sent into the Kalman filter to suppress the error divergence problem of the INS, and thus improve the positioning accuracy of the UE.

[0134] As mentioned above, the INS or other similar navigation system has the characteristic that the error diverges over time, and the intelligent model such as the GRU model is good at processing data with time series characteristics as a variant of the recurrent neural network. Accordingly, the GRU model can also be used to predict and estimate the error of a single navigation system such as the INS navigation system to correct the defects of the INS itself.

[0135] Correspondingly, in the positioning of the corresponding second positioning scenario using a navigation system, the determination of the intelligent model according to the first information can be performed in the following manner: the second historical positioning data is taken as input, and the error sequence is taken as output, and a second mapping relationship between the input data and the output data in the intelligent model is trained. And the intelligent model is determined according to the second mapping relationship.

[0136] Optionally, the first information can further include historical positioning true values at each time, and the error sequence is determined according to the historical positioning true values. For example, the positioning position element information at each time is compared with the corresponding historical positioning true value, and the error sequence corresponding to the time sequence at the pre-defined time length (the pre-defined time length can be adaptively set by a person skilled in the art in combination with actual application or experience value, for example, it can be the time length corresponding to the training period or the update period mentioned below) is obtained.

[0137] The INS output result can be the IMU measurement result and the INS calculation result (it can also include only the INS calculation result), and the input feature matrix of the GRU model can be similar to the above-mentioned various navigation combination, which can be the fusion result of the IMU measurement output and the INS navigation positioning result output, as shown in formula (5).

[0138] Compared with the above-mentioned positioning scenarios of various navigation system combinations, the goal of the intelligent model in this example is to correct the error for a single navigation system positioning method such as INS. Therefore, the GRU model in this embodiment expects the output to be the error sequence of INS. The error sequence can be the difference value of the corresponding position elements between the INS output result and the actual positioning result, and the compensation value in the INS calculation process is corrected. The expected output matrix of the GRU can be simply defined as shown in the following formula.

[0139] (6)

[0140] In the formula, Y t represents the expected output matrix, corresponding to ω bT , f bT , v nT , sinφ and cosφ at the corresponding time Position element error value, that is, compensation value in the INS calculation process. Optionally, for the positioning scenario of the UE using a navigation system, the GRU model training and prediction process can be shown in the following formula. Figure 8 and Figure 9 . Wherein, ΔP(t), ΔV(t), ΔA(t) are the position error, velocity error and heading angle error at t time. P GRU / INS , V GRU / INS , AGRU / INS These are the positioning information after model compensation for positioning errors. In some embodiments, they may only include ΔP(t) and P. GRU / INS This application does not impose any specific limitations on this.

[0141] It should be understood that, in the model, the mapping relationship refers to the relationship between the input data and the target output learned by the GRU model through training. This relationship can be represented in the model as a set of optimized parameters and weights, which define how the input data is transformed into an output prediction. During training, the model can continuously adjust its internal parameters and weights through the backpropagation algorithm to learn the mapping relationship between the input data and the output error.

[0142] The above technical solutions can effectively improve the positioning accuracy compensation when using a single navigation system for positioning, and can also reduce model complexity.

[0143] Optionally, considering that the model needs to be trained to obtain optimal weight parameter information to achieve higher prediction accuracy, and that the error of the navigation system is correlated with time, especially for the INS navigation system, where the error gradually accumulates over time, this embodiment improves the robustness of the model by setting a training period during the training process. Specifically, step S302 above, which determines the intelligent model based on the first information, can be done in the following way:

[0144] Based on the preset model training period and the first information, the intelligent model is determined; wherein, the model training period is determined based on the time interval step of historical positioning data and the amount of historical positioning data.

[0145] For example, the training period T train The time interval step τ is determined based on the historical location data and the number of historical location data points N. The calculation formula is as follows: Here, the time interval step τ represents the time interval between two adjacent historical location data points; the number of historical location data points N refers to the number of historical data points used for model training. That is, the training cycle can be determined by both the number of historical data points used for training and the time intervals between these data points. For example, if there are 100 historical location data points and the time interval step between adjacent data points is 0.1 seconds, then the training cycle can be T. train =100 × 0.1 = 10 seconds.

[0146] In the process of intelligent model training to determine the intelligent model, the above model training period is considered, and the time range of the data (i.e., the historical positioning data and the error data at the corresponding time in the first information) used for model training is specified. In combination with various historical data information related to positioning contained in the first information, the model learns these data within this specific training period, adjusts the weight parameters, so that the model can make full use of the positioning data with time correlation, better learn the relationship between the error and various input information, and improve the prediction accuracy and robustness of the model to provide reliable support for subsequent positioning error correction.

[0147] Further, considering that the model is not applicable to the current motion state characteristics in the high-speed moving state of the UE, and the prediction accuracy of the model may also be affected as the motion state changes and time elapses, to further improve the model accuracy, the embodiment sets a model update period. Specifically, the scheme can also include the following steps: updating the intelligent model according to the preset model update period and the first information. The model update period is determined according to the motion state of the UE.

[0148] Exemplarily, the motion state of the UE can be identified and classified, such as different categories (such as by analyzing sensor data such as accelerometers, gyroscopes, GPS speed information, etc. to identify different motion states) such as stationary, low-speed moving, medium-speed moving, and high-speed moving. By analyzing the error accumulation characteristics under each motion state, generally, the error accumulates faster in the high-speed moving state, while the error accumulates slower in the stationary or low-speed state. According to the error accumulation rate under different motion states, the model update period is dynamically adjusted. For example, in the high-speed moving state, a shorter update period is set to update the model more timely, so as to adapt to the rapidly changing motion state. While in the stationary or low-speed moving state, since the error accumulates slowly, the prediction accuracy of the model is less affected, and the update period can be extended. It can be understood that the first information in the embodiment can be real-time, for example, in the corresponding update period or training period, the first information is obtained from the LMF in real time for model updating or training.

[0149] Taking the GNSS / INS combined positioning scenario as an example, the training period and the update period of the intelligent model can be as shown in Figure 10 on the T time axis, containing the training period T train and the update period T update , wherein the training period Ttrain is a continuous time interval on the time axis T, representing the time range covered by the data used for GRU model training, and the update period T update represents the time interval for retraining the already trained GRU model, for example, every certain time (such as T updateThe retraining of the model is triggered once every time the UE is in the GNSS lock state for 1 hour. At the moment when the GNSS is lost, that is, at the moment t, the trained or updated intelligent model can be used for positioning error prediction, thereby improving the positioning accuracy of the UE.

[0150] In the related art, in the GNSS / INS integrated navigation scheme using neural network model online learning and compensation, during the GNSS / INS integrated navigation process, when the GNSS is normal, the first neural network and the second neural network are alternately trained within a set period. Through the cycle of each period, one of the first neural network and the second neural network is always in the training state of the training process, and the other is in the standby state of the trained neural network. The trained neural network is used to realize the function of predicting pseudo-GNSS signals according to the input INS data. When the GNSS is lost during navigation, the neural network in standby state is connected to the integrated structure of the integrated navigation, the INS data is input into the connected neural network, and the pseudo-GNSS signals predicted by the neural network are used to compensate the original INS data through the Kalman filter to output the positioning result. The technical scheme needs to alternately train two neural networks, the model is complex and has poor flexibility, and the model is to predict the actual positioning position. In addition, due to the limited computing and storage resources of the UE itself, training two neural networks will cause insufficient computing resources of the UE. The embodiment adopts the training of positioning error, which can use the traditional positioning method and intelligent model assisted positioning to jointly optimize the positioning accuracy and precision when the GNSS is lost, can make predictions that meet the current environment of the user, has stronger real-time and flexibility. Moreover, the embodiment considers the problem of limited UE resources, only needs to train or update one intelligent model, saves the resource consumption of the UE, and focuses on the training of positioning error, the model is simpler and has lower data dependence. In addition, by setting the training period and the update period of the model, the effective update and dynamic adaptability of the AI / ML model enable the continuous and efficient operation of the positioning service, and can quickly respond to environmental changes, improve the positioning error prediction effectiveness of the model, and further improve the positioning accuracy of the UE.

[0151] Figure 11 is a flowchart of a communication method provided by the embodiment of the present application, which includes steps S1100-S1104, compared with Figure 3 Corresponding to the embodiment, the embodiment further includes steps S1100-S1101 before receiving the first information from the second node.

[0152] In step S1102, the UE sends a request message to the LMF, and the request message is used to request the first information from the second node.

[0153] Exemplarily, the UE can send a request message to the LMF to request the LMF to send the first information when the UE has a positioning requirement, for example, when the UE needs to enter a high-speed mobile scene requiring a higher-precision positioning service.

[0154] In this way, the UE can obtain the first information for training the intelligent model in time when needed, thereby improving the positioning accuracy, especially in complex or high-speed mobile scenarios.

[0155] In some examples, the LMF can also actively send the first information to the UE, which is not particularly limited in this embodiment.

[0156] Step S1103, the UE receives the first information from the LMF, the first information including input data and expected output data for training the intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data including historical positioning data of the first node, and the expected output data including positioning error data at a time corresponding to the historical positioning data.

[0157] Step S1104, the UE determines the intelligent model according to the first information, the intelligent model being used to train the positioning error according to current positioning data.

[0158] It should be noted that step S1103 and step S1104 correspond to steps S301 and S302 in Figure 3 respectively, and the principles are similar. For relevant description, reference can be made to the foregoing, which will not be repeated here.

[0159] Further, before receiving the first information from the second node, the method can further include the following step S1101:

[0160] Step S1101, the UE reports second information to the LMF, the second information being used to indicate positioning capability information of the UE, the second information including at least one of the following: a model structure supporting model positioning, a data type of input and expected output required for training the model, a model training period, and a model update period.

[0161] Exemplarily, the second information can be LPP Provide Capabilities information.

[0162] In this embodiment, the UE reports the second information, so that the LMF can better understand the specific positioning function and supported technology of the UE, thereby providing more optimized positioning service for the UE. For example, if the UE supports a specific model positioning technology, the LMF can provide corresponding assistance data (such as the first information) for model training of the UE, thereby enhancing the positioning accuracy of the UE.

[0163] Optionally, before the UE reports the second information to the LMF, the LMF can request the second information from the UE. That is, step S1100 can also be included, i.e., the LMF requests the second information from the UE, and the request can be sent through LPP RequestCapabilities information.

[0164] Exemplarily, in the intelligent model (AI / ML model) assisted positioning mode provided in the embodiment, when the LMF requests the UE to report the positioning capability information currently supported by the UE, the UE can report the AI / ML model used, the model input and output content (i.e., the data types of the input and expected output required for training the model), the model training period, the model update period, and the model structure, etc. in the message if the UE currently supports the AI / ML direct positioning or assisted positioning mode. The LMF provides the UE with positioning assistance information according to the positioning capability information reported by the UE. The positioning assistance information can be requested by the UE or sent by the LMF actively without request. If the UE supports AI / ML positioning and initiates the assistance information request, the assistance information provided by the LMF can include but is not limited to AI / ML model training input and expected output data, historical positioning accuracy value (i.e., historical positioning true value), etc. After sending the assistance information, the LMF sends the UE with positioning request information. After the UE is positioned in the AI / ML assisted positioning mode, the UE reports the positioning result to the LMF.

[0165] Through the above technical solution, the AI / ML assisted positioning mode can be applied to the scene where the UE such as a UAV or a vehicle has a high motion speed, can make up for the positioning error of the traditional positioning method (such as INS positioning), effectively improve the positioning accuracy, and has lower model complexity and higher flexibility.

[0166] Figure 12 FIG. 3 is a third flowchart of a communication method provided in the embodiment of the application, which continues to take the first node as the UE and the second node as the LMF as an example for illustration.

[0167] In step S1201, the UE processes the current positioning data according to the preset intelligent model to obtain a positioning error. The intelligent model is determined according to the first information sent by the second node.

[0168] Optionally, the intelligent model can be trained by the UE, and the training process is described above. In some embodiments, the intelligent model can also be obtained by real-time interaction with other devices or servers, or pre-stored in the UE, and does not necessarily have to be trained by the UE. Accordingly, the model training process in the above embodiments can also be trained for other UEs or devices, and transmitted to other UEs or devices through interaction to perform model positioning. The present embodiment does not particularly limit whether the model training subject and the application subject are the same subject.

[0169] It should be understood that when the model training subject and the model application subject are not the same subject, the relevant data used to train the model, such as historical positioning data, is the relevant data for the model application subject.

[0170] In step S1202, the UE sends third information to the LMF, and the third information includes the positioning error, or the third information includes the positioning information determined according to the positioning error.

[0171] Optionally, the UE can report the third information to the LMF after the LMF sends the positioning request.

[0172] In the present embodiment, the UE performs assisted positioning in combination with an intelligent (AI / ML) model, that is, in the AI / ML assisted positioning mode, the UE can include two types of protocol messages in the positioning message reported to the LMF. One is that the UE reports the output result of the AI / ML model and the traditional positioning result (such as the INS positioning result) respectively to the LMF for processing, that is, the third information can include the positioning error and the INS positioning result. When the UE selects this type for reporting, the content of the output result of the AI / ML model (such as error compensation information or pseudo-observation information, etc.) can be stated in the report to facilitate the LMF to process the data. The other is that the UE autonomously fuses the output result of the AI / ML assisted positioning and the traditional positioning result to report the final positioning result to the LMF, that is, the third information includes the positioning information determined according to the positioning error.

[0173] In this way, the positioning error prediction in combination with the AI / ML model enables the UE to more accurately process the positioning data, thereby improving the overall positioning accuracy. Secondly, the UE has flexibility, which can choose to report the output result of the AI / ML model and the traditional positioning result respectively, or report the final positioning result after fusion. Through flexible configuration of the application scenario of the intelligent model and the reporting format of the position information, the advantages of the intelligent model in different positioning scenarios are fully utilized.

[0174] Optionally, considering that the accuracy of the traditional positioning method has a greater impact on the UE in a high-speed moving scenario, and has a smaller impact on a non-high-speed moving scenario, the AI / ML model can be used for auxiliary positioning in the high-speed moving scenario to save the UE computing resources. Specifically, the process of processing the current positioning data according to the preset intelligent model can be as follows: when the moving speed of the first node reaches a preset threshold, the current positioning data is processed according to the preset intelligent model.

[0175] It should be noted that the preset threshold can be adaptively set by the person skilled in the art according to actual application or experience, and the present embodiment does not particularly limit this.

[0176] In this way, by using the AI / ML model for auxiliary positioning in the high-speed moving scenario, the positioning accuracy can be effectively improved, and the use of computing resources is optimized.

[0177] Optionally, the process of processing the current positioning data according to the preset intelligent model can be as follows: the current positioning data is input into the intelligent model, and the current positioning data is processed based on the intelligent model to obtain the positioning error at the moment corresponding to the current positioning data. The current positioning data includes at least one of the following: an angular velocity measurement value, a specific force measurement value, a solved speed navigation solution, and a heading angle navigation solution.

[0178] It should be noted that the model processing process is similar to the model training process, and the above-mentioned model training process can be combined with the model processing process. Figure 8 The corresponding content can be understood, and the related description will not be repeated here.

[0179] Optionally, in the scenario where the UE reports the fused positioning information, the UE can also determine the positioning compensation information for the current positioning data according to the positioning error. And the positioning information is determined according to the positioning compensation information and the current positioning data.

[0180] For example, taking GNSS / INS combined positioning as an example, the positioning error output by the model corresponds to the error caused by the interruption of the GNSS signal. The error difference value at the corresponding moment is predicted by the AI / ML model, and the pseudo-GNSS position information can be calculated by using the error difference value (for example, the current position calculated by the INS is corrected by using the predicted error difference value. Specifically, the error difference value is added to the current position calculation result of the INS to generate the pseudo-GNSS position information. This process is equivalent to simulating the position information provided by the GNSS system in the case where the GNSS signal is not interrupted, that is, the positioning compensation information). Then, the pseudo-GNSS position information and the INS calculation information are sent into the Kalman filter to suppress the error divergence problem of the INS.

[0181] In an optional implementation of the example, the current positioning data is first current positioning data obtained by the primary navigation system in a first positioning scenario, and the positioning compensation information is compensation positioning data obtained by replacing positioning of the secondary navigation system in the first positioning scenario. The positioning information is determined according to the positioning compensation information and the current positioning data, specifically: the positioning compensation information and the current positioning data are fused by a Kalman filter to obtain the positioning information.

[0182] It should be noted that the model processing process is similar to the model training process, and can be understood in combination with the corresponding content in the above embodiments, and relevant descriptions will not be repeated here.

[0183] In another optional implementation of the example, the current positioning data is second current positioning data obtained by the navigation system in a second positioning scenario, and the positioning compensation information is modified positioning data obtained by modifying the second current positioning data. The process of determining the positioning information according to the positioning compensation information and the current positioning data can be as follows: the current positioning data is modified according to the positioning compensation information to obtain the positioning information.

[0184] For example, the positioning compensation information can be superimposed on the current positioning data to obtain the positioning information.

[0185] It should be noted that the model processing process is similar to the model training process, and can be understood in combination with the corresponding content in the above embodiments, and relevant descriptions will not be repeated here.

[0186] Correspondingly, the embodiment of the application also provides a communication method, which is combined with Figure 3 For example, the LMF sends first information to the UE, the first information including input data and expected output data used for training the intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data including historical positioning data of the first node, and the expected output data including positioning error data at a time corresponding to the historical positioning data.

[0187] In an optional implementation, before sending the first information to the first node, the LMF can also receive a request message sent by the first node, the request message being used for requesting the first information from the second node.

[0188] In an optional implementation, before sending the first information to the first node, the LMF can also receive second information reported by the first node, the second information being used for indicating positioning capability information of the first node, the second information including at least one of the following: a model structure supporting model positioning, a data type of input and expected output required for training the model, a model training period, and a model updating period.

[0189] It should be noted that the above embodiment is a peer-to-peer embodiment of the UE, and the related description and benefits can refer to the UE side embodiment content, which will not be repeated here.

[0190] Figure 13 is a fourth flowchart of a communication method provided by the embodiment of the application. In the embodiment, the UE can be the subject of model training and model application, and the UE positioning and the uploading of positioning information are realized through interaction between the UE and the LMF. As shown in Figure 13 , the method can include the following steps:

[0191] In step S1301, the LMF sends an LPP request to the UE to request second information, i.e., positioning capability related information.

[0192] In step S1302, after receiving the request of the LMF, the UE provides the second information, i.e., the positioning capability information of the UE itself, such as the model structure of the UE supporting model positioning, the data types of the input and expected output required for training the model, the model training period and the model update period, etc., to the LMF.

[0193] In step S1303, the LMF can send the first information, i.e., the positioning assistance information, to the UE actively or based on the request of the UE, which can be sent without the request message sent by the UE, to assist the UE in model training and positioning.

[0194] In step S1304, the LMF sends a positioning request to the UE to obtain the position information of the UE.

[0195] In step S1305, the UE trains the intelligent model using the first information fed back by the LMF, and uses the intelligent model, such as the time series model of GRU, to train the error change of the navigation system (such as INS), to predict the positioning error for compensating the navigation system.

[0196] In step S1306, the UE reports the third information to the LMF, and the reporting content corresponding to the third information can include the positioning measurement information of the navigation system and the positioning error predicted by the intelligent model (here, the GRU model), or the reporting content can be the fusion of the intelligent model assisted positioning output result and the traditional positioning result, and the final positioning result reported to the LMF by the UE, so as to more accurately determine the position of the UE by the LMF.

[0197] Figure 14 is a structural schematic diagram of a communication device provided by the embodiment of the application. The communication device can be an electronic device, or a chip or chip system in the electronic device. As shown in Figure 14As shown, the communication apparatus 1400 can include a first transceiving unit 1401 and a first processing unit 1402. When the communication apparatus is an electronic device, the first transceiving unit 1401 can be a Wi-Fi module or a cellular network module, etc. The first transceiving unit 1401 is configured to perform the steps of transceiving, so that the electronic device implements the communication method described in the above method embodiments. When the communication apparatus is an electronic device, the first processing unit 1402 can be a processor. The communication apparatus can further include a storage unit, which can be a memory. The storage unit is configured to store instructions, and the first processing unit 1402 executes the instructions stored in the storage unit, so that the electronic device implements the communication method described in the above method embodiments. When the communication apparatus is a chip or a chip system in an electronic device, the first processing unit 1402 can be a processor. The first processing unit 1402 executes the instructions stored in the storage unit, so that the electronic device implements a communication method described in the first aspect or any possible implementation manner of the first aspect. The storage unit can be a storage unit (e.g., a register, a cache, etc.) in the chip, or a storage unit (e.g., a read-only memory, a random access memory, etc.) in the electronic device and located outside the chip.

[0198] For example, the first transceiving unit 1401 is configured to receive first information from a second node, the first information including input data and expected output data used for training an intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data including historical positioning data, and the expected output data including positioning error data at a time corresponding to the historical positioning data; and the first processing unit 1402 is configured to determine the intelligent model according to the first information, the intelligent model being used for training positioning error according to current positioning data.

[0199] In an optional implementation manner, the intelligent model can be a gated recurrent unit model.

[0200] In an optional implementation manner, the positioning scenario includes a first positioning scenario of positioning by a combination of multiple navigation systems, the multiple navigation systems including a main navigation system and an auxiliary navigation system, the historical positioning data includes first historical positioning data of the main navigation system, and the positioning error data includes positioning difference data between the multiple navigation systems at a time corresponding to the first historical positioning data; and the first processing unit 1402 is specifically configured to train a first mapping relationship between the input data and the output data in the intelligent model by taking the first historical positioning data as the input and taking the positioning difference data as the output; and determine the intelligent model according to the first mapping relationship.

[0201] In an optional implementation manner, the main navigation system can include an inertial navigation system, and the auxiliary navigation system can include a global navigation satellite system.

[0202] In an optional implementation, the positioning scenario includes a second positioning scenario positioned by a navigation system, the historical positioning data includes second historical positioning data of the navigation system, the positioning error data includes an error sequence corresponding to the second historical positioning data, and the error sequence is a sequence composed of positioning errors corresponding to positioning position elements at each time in the second historical positioning data; the first processing unit 1402 is specifically configured to train a second mapping relationship between input data and output data in the intelligent model by taking the second historical positioning data as the input and the error sequence as the output. And determine the intelligent model according to the second mapping relationship.

[0203] In an optional implementation, the first information can further include historical positioning true values at each time, and the error sequence is determined according to the historical positioning true values.

[0204] In an optional implementation, the first processing unit 1402 is specifically configured to determine the intelligent model according to a preset model training period and the first information; wherein the model training period is determined based on a time interval step of the historical positioning data and a quantity of the historical positioning data.

[0205] In an optional implementation, the first processing unit 1402 is further configured to update the intelligent model according to a preset model update period and the first information; wherein the model update period is determined according to a motion state of the first node.

[0206] In an optional implementation, the first transceiver unit 1401 is further configured to send a request message to the second node after receiving the first information from the second node, and the request message is used to request the first information from the second node.

[0207] In an optional implementation, the first transceiver unit 1401 is further configured to report second information to the second node before receiving the first information from the second node, and the second information is used to indicate positioning capability information of the first node, and the second information includes at least one of the following: a model structure supporting model positioning, a data type of input and expected output required for training the model, a model training period, and a model update period.

[0208] It should be noted that the above-mentioned embodiment device can execute the steps corresponding to the UE side (model training) method embodiment, and the related description and beneficial effects can be referred to the above-mentioned method embodiment content, which will not be repeated here.

[0209] Figure 15 FIG. 8 is a structural schematic diagram of another communication device provided by the embodiment of the present application. The communication device can be an electronic device, or a chip or chip system in the electronic device. As shown in FIG. 8, the communication device includes a first transceiver unit 8001, a first processing unit 8002, and a first storage unit 8003. Figure 15As shown, the communication apparatus 1500 can include a second transceiving unit 1501 and a second processing unit 1502. When the communication apparatus is an electronic device, the second transceiving unit 1501 can be a Wi-Fi module or a cellular network module, etc. The second transceiving unit 1501 is configured to perform the steps of transceiving, so that the electronic device implements a communication method described in the second aspect or any possible implementation manner of the second aspect. When the communication apparatus is an electronic device, the second processing unit 1502 can be a processor. The communication apparatus can further include a storage unit, which can be a memory. The storage unit is configured to store instructions, and the second processing unit 1502 executes the instructions stored in the storage unit, so that the electronic device implements the communication method described in the method embodiment. When the communication apparatus is a chip or a chip system in an electronic device, the second processing unit 1502 can be a processor. The second processing unit 1502 executes the instructions stored in the storage unit, so that the electronic device implements a communication method described in the second aspect or any possible implementation manner of the second aspect. The storage unit can be a storage unit (e.g., a register, a cache, etc.) in the chip, or a storage unit (e.g., a read-only memory, a random access memory, etc.) in the electronic device and located outside the chip.

[0210] For example, the second processing unit 1502 is configured to process the current positioning data according to a preset intelligent model to obtain a positioning error, wherein the intelligent model is determined according to the first information sent by the second node; and the second transceiving unit 1501 is configured to send third information to the second node, wherein the third information includes the positioning error, or the third information includes positioning information determined according to the positioning error.

[0211] In an optional implementation manner, the second processing unit 1502 is specifically configured to process the current positioning data according to a preset intelligent model when the moving speed of the first node reaches a preset threshold.

[0212] In an optional implementation manner, the second processing unit 1502 is specifically configured to input the current positioning data into the intelligent model, and process the current positioning data based on the intelligent model to obtain a positioning error at a moment corresponding to the current positioning data. The current positioning data includes at least one of the following: an angular velocity measurement value, a specific force measurement value, a solved speed navigation solution, and a heading angle navigation solution.

[0213] In an optional implementation manner, the second processing unit 1502 is further configured to determine positioning compensation information for the current positioning data according to the positioning error, and determine positioning information according to the positioning compensation information and the current positioning data.

[0214] In an optional implementation, the current positioning data is first current positioning data obtained by the primary navigation system in a first positioning scenario, and the positioning compensation information is compensation positioning data obtained by positioning of the secondary navigation system in the first positioning scenario. The second processing unit 1502 is specifically configured to obtain the positioning information by fusing the positioning compensation information and the current positioning data through a Kalman filter.

[0215] In an optional implementation, the current positioning data is second current positioning data obtained by the navigation system in a second positioning scenario, and the positioning compensation information is modified positioning data obtained by modifying the second current positioning data. The second processing unit 1502 is specifically configured to modify the current positioning data according to the positioning compensation information to obtain the positioning information.

[0216] It should be noted that the above-mentioned embodiment device can execute the steps corresponding to the UE side (model application) method embodiment, and the related description and beneficial effects can be referred to the above-mentioned method embodiment content, which will not be repeated here.

[0217] Figure 16 Another structure schematic diagram of a communication device provided by an embodiment of the present application is provided. The communication device can be an electronic device, or a chip or chip system in the electronic device. As shown in Figure 16 The communication device 1600 can include a third transceiver unit 1601. When the communication device is an electronic device, the third transceiver unit 1601 can be a Wi-Fi module or a cellular network module, etc. The third transceiver unit 1601 is configured to execute the steps of transceiving, so that the electronic device implements the communication method provided by the method embodiment.

[0218] For example, the third transceiver unit 1601 is configured to send first information to a first node, the first information including input data and expected output data for training an intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data including historical positioning data of the first node, and the expected output data including positioning error data at a time corresponding to the historical positioning data.

[0219] In an optional implementation, the third transceiver unit 1601 is further configured to receive a request message sent by the first node before sending the first information to the first node, the request message being used to request the first information from the second node.

[0220] In an optional implementation, the third transceiver 1601 is further configured to receive second information reported by the first node before sending the first information to the first node, the second information being used to indicate the positioning capability information of the first node, and the second information comprising at least one of the following: a model structure supporting model positioning, a data type of input and expected output required for training the model, a model training period, and a model updating period.

[0221] It should be noted that the above-mentioned embodiment device can perform the steps corresponding to the LMF-side method embodiment, and the related description and beneficial effects can be referred to the above-mentioned method embodiment content, which will not be repeated here.

[0222] Figure 17 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. The above-mentioned method embodiments can be applied in an electronic device with communication function. As shown in Figure 17 , the electronic device 1700 can be applied in a system as shown in Figure 1 , and perform the functions of the terminal or network device in the above-mentioned method embodiments. As shown in Figure 17 , the electronic device 1700 comprises a processor 1701 and a transceiver 1702. Optionally, the electronic device 1700 further comprises a memory 1703. The processor 1701, the transceiver 1702 and the memory 1703 can communicate with each other through internal connection paths, and transfer control and / or data signals. The memory 1703 is used to store computer programs, and the processor 1701 is used to call and run the computer programs in the memory 1703 to control the transceiver 1702 to transceive signals. Optionally, the electronic device 1700 can further comprise an antenna 1704, which is used to send the uplink data or uplink control signaling output by the transceiver 1702 through wireless signals.

[0223] The above-mentioned processor 1701 and the memory 1703 can be combined into one processing device, and the processor 1701 is used to execute the program codes stored in the memory 1703 to realize the above-mentioned functions. Specifically, the memory 1703 can be integrated in the processor 1701 or independent of the processor 1701. The processor 1701 can correspond to the processing unit or the processor in the above-mentioned embodiments.

[0224] The above-mentioned transceiver 1702 can correspond to the transceiver unit in the above-mentioned embodiments. The transceiver 1702 can comprise a receiver (or receiver, receiving circuit) and a transmitter (or transmitter, transmitting circuit). The receiver is used to receive signals, and the transmitter is used to transmit signals.

[0225] It should be understood that Figure 17The electronic device 1700 shown can implement each process involving the terminal or the network device in the above method embodiments. The operations and / or functions of each module in the electronic device 1700 are respectively for implementing the corresponding processes in the above method embodiments. For details, refer to the description in the above method embodiments, and the detailed description is appropriately omitted here.

[0226] The processor 1701 described above can be used to perform the actions implemented internally by the terminal or the network device described in the above method embodiments, and the transceiver 1702 can be used to perform the actions of sending or receiving by the network device to the terminal or by the terminal from the network device described in the above method embodiments. For details, refer to the description in the above method embodiments, and the description is not repeated here.

[0227] Optionally, the electronic device 1700 described above can further include a power supply 1705 for providing power supply to various devices or circuits in the terminal.

[0228] In addition, in order to make the function of the terminal more perfect, when the electronic device 1700 is the terminal, it can further include one or more of an input unit 1706, a display unit 1707, an audio circuit 1708, a camera 1709 and a sensor 1710, and the audio circuit can further include a speaker 1708a, a microphone 1708b, etc.

[0229] The above method embodiments can be applied to a processor or implemented by a processor. The processor can be an integrated circuit chip with a signal processing capability. In the implementation process, each step of the above method embodiments can be completed by integrated logic circuits or instruction of software form in the processor.

[0230] The processor described above can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a ready programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or any combination thereof. The general processor can be a microprocessor, or any conventional processor, etc.

[0231] The steps of the method disclosed in the embodiments of the present application can be directly embodied as hardware code processing executed by a processor, or a combination of hardware and software modules in the code processing. The software module can be located in a storage medium such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically programmable read-only memory, register, or the like. The storage medium is located in the storage, and the processor reads information in the storage and combines hardware to complete the steps of the above method.

[0232] The memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (read-only memory, ROM), a programmable read-only memory (programmable ROM, PROM), an erasable programmable read-only memory (erasable PROM, EPROM), an electrically erasable programmable read-only memory (electrically EPROM, EEPROM) or a flash memory. The volatile memory can be a random access memory (random access memory, RAM) used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchlink dynamic random access memory (synchlink DRAM, SLDRAM) and direct memory bus random access memory (direct rambus RAM, DR RAM). It should be noted that the memory of the system and method described herein is intended to include but not limited to these and any other suitable types of memory.

[0233] Figure 18 A chip system provided by the embodiments of the present application, as shown in Figure 18 The chip system 1800 includes at least one processor 1801 and a communication interface 1802, the communication interface 1802 and the at least one processor 1801 are interconnected by a line, the at least one processor 1801 is used to run computer programs or instructions, and is used to support the functions of the terminal or network equipment involved in any of the above method embodiments, for example, receiving or processing the information involved in the above method. Among them, the communication interface in the chip system can be an input / output interface, a pin or a circuit, etc.

[0234] In a possible design, the chip system further includes a memory 1803 configured to store computer program instructions and data, where the memory 1803 can be a storage unit inside the chip, for example, a register, a cache, or the like, or a storage unit of the chip (for example, a read-only memory, a random access memory, or the like). In some embodiments, the memory 1803 can also be an external memory.

[0235] The chip system can be composed of a chip, or can include a chip and other discrete devices.

[0236] In a possible implementation, the chip or the chip system described above in the present application further includes at least one memory in which instructions are stored.

[0237] Correspondingly, the embodiments of the present application further provide a computer program product, which includes a computer program (also referred to as code or instructions). When the computer program is run, the method performed by the terminal or the method performed by the network device in the method embodiments described above is executed.

[0238] Correspondingly, the embodiments of the present application further provide a computer readable storage medium, which stores a computer program (also referred to as code or instructions). When the computer program is run, the method performed by the terminal or the method performed by the network device in the method embodiments described above is executed.

[0239] The present application further provides a communication system, which includes the terminal and the network device described above.

[0240] The method provided by the above embodiments can be implemented by software, hardware, firmware, or any combination thereof, in whole or in part. When implemented by software, the computer program product can be implemented in whole or in part in the form of a computer program. The computer program product can include one or more computer instructions. When loaded and executed on a computer, the computer program instructions can generate the processes or functions according to the embodiments of the present application in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center through a wired (for example, coaxial cable, optical fiber, digital subscriber (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic disk), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0241] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0242] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device, and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0243] In several embodiments provided in the present application, it should be understood that the disclosed system, device, and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the unit is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed mutual units can be indirect coupling or communication connection through some interfaces, devices, or units, which can be electrical, mechanical, or other forms.

[0244] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, can be located in one place, or can be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0245] In addition, the functional units in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically, or two or more units can be integrated into one unit.

[0246] If the function is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical scheme of the present application or part of the technical scheme can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method of each embodiment of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, and various program code storage media.

[0247] In various embodiments of the present application, the terms and / or descriptions of different embodiments are consistent and can be mutually referred to if there is no special description and no logical conflict. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0248] In a possible implementation, the computer readable medium can include a RAM, a ROM, a compact disc read-only memory (CD-ROM) or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that is suitable for storing desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. Disk and disc, as used herein, include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray® disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer readable media.

[0249] The embodiments of the present application are described with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as a combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that instructions executed by the computer or other programmable data processing apparatus produce the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 The functions of a flow or a plurality of flows and / or blocks Figure 1 The functions of a flow or a plurality of flows and / or blocks

[0250] The above detailed description of the specific implementation is further detailed for the purpose of the present application, technical solutions and beneficial effects, and it should be understood that the above is only a specific implementation of the present application, and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made on the basis of the technical solutions of the present application should be included in the protection scope of the present application.

Claims

1. A communication method characterized by comprising: Applied to a first node, comprising: receiving first information from a second node, the first information comprising input data and expected output data for training an intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data comprising historical positioning data of the first node, and the expected output data comprising positioning error data corresponding to the historical positioning data at a time; training the intelligent model according to the first information, the intelligent model being used to train positioning error according to current positioning data obtained by at least one navigation system positioning; wherein the positioning scenario comprises at least one positioning scenario of the navigation system positioning, and the positioning error is used to compensate for the current positioning data.

2. The method of claim 1, wherein, The positioning scenario comprises a first positioning scenario of combined positioning by a plurality of navigation systems, the plurality of navigation systems comprising a main navigation system and an auxiliary navigation system, the historical positioning data comprising first historical positioning data of the main navigation system, and the positioning error data comprising positioning difference data between the plurality of navigation systems at a time corresponding to the first historical positioning data; training the intelligent model according to the first information, comprising: training a first mapping relationship between input data and output data in the intelligent model by taking the first historical positioning data as input and the positioning difference data as output; training the intelligent model according to the first mapping relationship.

3. The method of claim 2, wherein, The main navigation system comprises an inertial navigation system, and the auxiliary navigation system comprises a global navigation satellite system.

4. The method of claim 1, wherein, The positioning scenario comprises a second positioning scenario of positioning by a navigation system, the historical positioning data comprising second historical positioning data of the navigation system, and the positioning error data comprising an error sequence corresponding to the second historical positioning data, the error sequence being a sequence composed of positioning errors corresponding to positioning position elements at each time in the second historical positioning data; training the intelligent model according to the first information, comprising: training a second mapping relationship between input data and output data in the intelligent model by taking the second historical positioning data as input and the error sequence as output; training the intelligent model according to the second mapping relationship.

5. The method of claim 4, wherein, The first information further comprises historical positioning true values at each time, and the error sequence is determined according to the historical positioning true values.

6. The method according to any one of claims 1 to 5, characterized in that, training the intelligent model according to the first information, comprising: training the intelligent model according to a preset model training period and the first information, wherein the model training period is determined based on a time interval step of the historical positioning data and a quantity of the historical positioning data.

7. The method according to any one of claims 1 to 5, characterized in that, Further comprising: updating the intelligent model according to a preset model update period and the first information, wherein the model update period is determined according to a motion state of the first node.

8. The method according to any one of claims 1 to 5, characterized in that, Before receiving the first information from the second node, further comprising: sending a request message to the second node, the request message being used to request the first information from the second node.

9. The method according to any one of claims 1 to 5, characterized in that, The method further comprises, before receiving the first information from the second node: reporting second information to the second node, the second information being used to indicate positioning capability information of the first node, the second information comprising at least one of the following: a model structure supporting model positioning, data types of input and expected output required for training a model, a model training period, and a model updating period.

10. The method according to any one of claims 1 to 5, characterized in that, The intelligent model comprises a gated recurrent unit model.

11. A communication method, comprising: The method is applied to the first node, and the method comprises: processing, according to a preset intelligent model, current positioning data obtained by at least one navigation system, to obtain positioning error, wherein the intelligent model is trained according to first information sent by a second node, the first information comprising input data and expected output data used for training the intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data comprising historical positioning data of the first node, the expected output data comprising positioning error data at a time corresponding to the historical positioning data, and the positioning scenario comprising at least one positioning scenario of combined positioning of navigation systems; sending, to the second node, third information comprising the positioning error, the positioning error being used to compensate for the current positioning data, or the third information comprising positioning information determined according to the positioning error.

12. The method of claim 11, wherein, The processing, according to the preset intelligent model, of the current positioning data comprises: when a moving speed of the first node reaches a preset threshold, processing, according to the preset intelligent model, the current positioning data.

13. The method according to claim 11 or 12, characterized in that, The processing, according to the preset intelligent model, of the current positioning data comprises: inputting the current positioning data into the intelligent model, processing the current positioning data based on the intelligent model to obtain positioning error at a time corresponding to the current positioning data; wherein the current positioning data comprises at least one of the following: an angular velocity measurement value, a specific force measurement value, a solved velocity navigation solution, and a heading angle navigation solution.

14. The method of claim 11 or 12, wherein, The method further comprises: determining, according to the positioning error, positioning compensation information for the current positioning data; determining, according to the positioning compensation information and the current positioning data, the positioning information.

15. The method of claim 14, wherein, The current positioning data is first current positioning data obtained by a primary navigation system in a first positioning scenario, and the positioning compensation information is compensation positioning data for positioning of a secondary navigation system in the first positioning scenario. The determination, according to the positioning compensation information and the current positioning data, of the positioning information comprises: fusing, by a Kalman filter, the positioning compensation information and the current positioning data to obtain the positioning information.

16. The method of claim 14, wherein, The current positioning data is second current positioning data obtained by a navigation system in a second positioning scenario, and the positioning compensation information is correction positioning data for correcting the second current positioning data. The determination, according to the positioning compensation information and the current positioning data, of the positioning information comprises: correcting the current positioning data according to the positioning compensation information to obtain the positioning information.

17. A method of communication, comprising: The method is applied to the second node, and the method comprises: sending first information to a first node, the first information comprising input data and expected output data for training an intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data comprising historical positioning data of the first node, the expected output data comprising positioning error data at a time corresponding to the historical positioning data, the positioning scenario comprising at least one positioning scenario of a navigation system positioning; wherein the first information is used to train the intelligent model, and the intelligent model is used to train a positioning error according to current positioning data obtained by at least one navigation system positioning, the positioning error being used to compensate the current positioning data.

18. The method of claim 17, wherein, Before sending the first information to the first node, further comprising: receiving a request message sent by the first node, the request message being used to request the first information from the second node.

19. The method of claim 17 or 18, wherein, Before sending the first information to the first node, further comprising: receiving second information reported by the first node, the second information being used to indicate positioning capability information of the first node, the second information comprising at least one of the following: a model structure supporting model positioning, a data type of input and expected output required for training a model, a model training period, and a model updating period.

20. A communications device, characterized by comprising: a first transceiving unit, configured to receive first information from a second node, the first information comprising input data and expected output data for training an intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data comprising historical positioning data, and the expected output data comprising positioning error data at a time corresponding to the historical positioning data; a first processing unit, configured to train the intelligent model according to the first information, the intelligent model being used to train a positioning error according to current positioning data obtained by at least one navigation system positioning; wherein the positioning scenario comprises at least one positioning scenario of a navigation system positioning, and the positioning error is used to compensate the current positioning data.

21. A communications device, characterized by comprising: a second processing unit, configured to process current positioning data obtained by at least one navigation system positioning according to a preset intelligent model to obtain a positioning error, wherein the intelligent model is trained according to first information sent by a second node, the first information comprising input data and expected output data for training an intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data comprising historical positioning data of a first node, and the expected output data comprising positioning error data at a time corresponding to the historical positioning data, the positioning scenario comprising at least one positioning scenario of a navigation system combined positioning; a second transceiving unit, configured to send third information to the second node, the third information comprising the positioning error, the positioning error being used to compensate the current positioning data, or the third information comprising positioning information determined according to the positioning error.

22. A communications device, characterized by comprising: The third transceiver unit is configured to send first information to the first node, the first information comprising input data and expected output data for training the intelligent model, the input data and the expected output data being determined according to a preset positioning scenario, the input data comprising historical positioning data of the first node, the expected output data comprising positioning error data at a time corresponding to the historical positioning data, and the positioning scenario comprising at least one positioning scenario of a navigation system positioning. The first information is used to train the intelligent model, and the intelligent model is used to train a positioning error according to current positioning data obtained by at least one navigation system positioning, and the positioning error is used to compensate for the current positioning data.

23. An electronic device, comprising: The method comprises: a processor and a memory; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, so that the electronic device executes the communication method according to any one of claims 1-19. 24.A computer readable storage medium, storing a computer program, characterized in that, The computer program is executed by the processor to implement the communication method according to any one of claims 1-19.

25. A chip system, characterized by The communication method according to any one of claims 1-19 is executed by the at least one processor running a computer program or instructions.

26. A computer program product, characterised in that, The computer program is executed by the processor to implement the communication method according to any one of claims 1-19. The communication method according to any one of claims 1-19 is executed by the at least one processor running a computer program or instructions.

Images