Positioning method and device

Abstract

The embodiment of the invention provides a positioning method and equipment, and is applied to the field of communication. The method comprises the following steps: receiving communication data from terminal equipment, wherein the communication data comprises a plurality of PCIs (Peripheral Component Interconnect) and signal quality parameters of a plurality of corresponding signals; determining the position of the terminal device according to the communication data by using a plurality of positioning models, the plurality of positioning models including a first positioning model and at least one second positioning model; or a third positioning model is utilized to determine the position of the terminal device according to the communication data, the third positioning model is a model formed by combining a plurality of positioning models, and the plurality of positioning models comprise the first positioning model and at least one second positioning model; and then sending the position of the terminal equipment. Based on the scheme, the communication data does not need to be transmitted to the core network equipment for position calculation after being acquired, the position calculation can be performed at the access network equipment side, the transmission link of the communication data is shortened, and the calculation pressure of the core network equipment is reduced.

Description

Technical Field

[0001] The present application relates to the field of communications, and in particular to a positioning method and device. Background Art

[0002] In the current cellular mobile communication system, when determining the location of a terminal device, the terminal device is required to measure the signal quality data of multiple cell signals it obtains, and then report these measurement data to the location management function (LMF) of the core network through the base station. The LMF of the core network determines the location of the terminal based on these measurement data.

[0003] This terminal positioning solution requires the terminal to transmit the measurement data to the core network through the base station. The transmission link of the measurement data is long, more network resources are required, and the possibility of data packet loss increases. At the same time, since a large amount of terminal device measurement data will be transmitted to the LMF of the core network, the LMF of the core network needs to process a large amount of measurement data to locate multiple terminals, which puts a lot of calculation pressure on the LMF. Summary of the invention

[0004] An embodiment of the present application provides a positioning method and device. The method can receive the communication data of a terminal device through an access network device, and then use multiple positioning models or a combined positioning model to determine the position of the terminal device without transmitting it to a core network device for position calculation, thereby shortening the transmission link of the communication data and reducing the computing pressure of the core network device.

[0005] In the first aspect, an embodiment of the present application provides a positioning method, which is applied to a first access network device, and the method includes: the first access network device first receives communication data from a terminal device, and the communication data includes multiple physical cell identifiers (PCIs) and corresponding signal quality parameters of multiple signals. Then the first access network device can use multiple positioning models to determine the location of the terminal device according to the communication data, and the multiple positioning models include a first positioning model corresponding to the first access network device and at least one second positioning model corresponding to at least one adjacent access network device; or the first access network device can also use a third positioning model to determine the location of the terminal device according to the communication data, and the third positioning model is a model merged by multiple positioning models, and the multiple positioning models include a first positioning model corresponding to the first access network device and at least one second positioning model corresponding to at least one adjacent access network device, and the model type of the first access network model and the at least one second positioning model is the same; then the first access network device sends the location of the terminal device to the terminal or access network device.

[0006] Based on the above solution, after obtaining the communication data, the access network device no longer needs to transmit it to the core network device for location calculation. The location calculation can be performed on the access network device side, which shortens the transmission link of the communication data, requires fewer network resources, reduces the possibility of data packet loss, and reduces the calculation pressure of the core network device. At the same time, the access network device can use multiple positioning models or merged models to calculate the terminal location, with stronger location calculation capabilities, especially for the terminal device at the edge of the access network device coverage area. The location calculation is more accurate, and the access network device has a more comprehensive coverage of the terminal device location positioning.

[0007] In one possible implementation, when a first access network device uses multiple positioning models to determine the location of a terminal device based on communication data, the above-mentioned use of multiple positioning models to determine the location of a terminal device based on communication data includes: using multiple positioning models to determine multiple predicted locations based on the communication data, the multiple predicted locations corresponding one-to-one to the multiple positioning models; and determining the location of the terminal device based on the multiple predicted positions.

[0008] Based on the above scheme, a method for positioning using multiple positioning models is specifically provided, multiple predicted positions are obtained using multiple positioning models, and then the position of the terminal device is determined according to the multiple predicted positions. The positioning model of the adjacent access network device is used for positioning, thereby enhancing the positioning capability of the first access network device and obtaining a larger coverage range, especially for the edge position of the coverage area of ​​the first access network device.

[0009] In one possible implementation, the above-mentioned determining the location of the terminal device based on multiple predicted locations includes: determining a weighted average location of multiple predicted locations as the location of the terminal device; or, determining multiple predicted locations in a location set among the multiple predicted locations; and determining the location of the terminal device based on the multiple predicted locations in the location set. In this possible implementation, the location of the terminal device can be determined based on the weighted average position of each predicted position, and the influence of key models with high location correlation can be enhanced by increasing the weight; or the results of remote predicted positions can be removed, and the location of the terminal device can be determined based on the predicted positions in the concentrated positions, which has higher positioning accuracy.

[0010] In one possible implementation, when the access network device uses a third positioning model to determine the location of a terminal device based on communication data, the above-mentioned multiple positioning models are grid-based fingerprint models. Before using the third positioning model to determine the location of the terminal device based on the communication data, the above-mentioned method also includes: obtaining a first fingerprint data set corresponding to the first positioning model and at least one second fingerprint data set corresponding to at least one second positioning model, the fingerprint data including grid coordinates, PCI and corresponding signal quality parameters; generating a third positioning model based on the first fingerprint data set and at least one second fingerprint data set.

[0011] In this possible implementation, a model merging method is specifically provided, which improves the feasibility of the embodiment of the present application. At the same time, the access network device uses the merged model to calculate the terminal position, which has a stronger position calculation capability, especially for the terminal device position calculation at the edge of the access network device coverage area is more accurate, and the access network device has a more comprehensive coverage of the terminal device position positioning.

[0012] In a possible implementation, the method further includes: detecting the positioning accuracy of the first positioning model; when the accuracy of the terminal device position located by the first positioning model is less than a positioning accuracy threshold, retraining the first positioning model to obtain a retrained first positioning model.

[0013] In this possible implementation, the first access network device also detects the positioning accuracy of the first positioning model, ensuring that the positioning accuracy of the first positioning model meets the requirements and ensuring the accuracy of positioning performed by the first access network device.

[0014] In a possible implementation manner, the method further includes: sending the retrained first positioning model to an adjacent access network device.

[0015] In this possible implementation, the first access network device will also send the retrained first positioning model to the adjacent access network device, which can improve the positioning capability of the adjacent access network device.

[0016] In one possible implementation, the third positioning model is obtained after re-merging models, and the method further includes: receiving a retrained target second positioning model from a second access network device, where the second access network device is any one of the adjacent access network devices; and re-merging models according to the retrained target second positioning model to obtain a third positioning model.

[0017] In a possible implementation manner, the signal quality parameter includes at least one of a cell signal strength and a cell positioning reference signal PRS strength.

[0018] In a possible implementation, the multiple positioning models are grid-based fingerprint models and / or neural network models.

[0019] In the second aspect, an embodiment of the present application provides a positioning model training method, the method comprising: inputting a training sample set into an initial positioning model, the training samples of the training sample set comprising communication data acquired by a terminal device and corresponding position truth labels, multiple physical cell identifiers PCI of the communication data and corresponding signal quality parameters of multiple signals; using the initial positioning model, determining a predicted position of the terminal device according to the communication data and the corresponding position truth labels; determining a feedback value according to a loss function, the predicted position and the training samples; adjusting model parameters of the initial positioning model according to the feedback values ​​to obtain a positioning model.

[0020] In one possible implementation, the above-mentioned positioning model is a grid-based fingerprint model, and the method also includes: obtaining multiple fingerprint data sets corresponding to multiple positioning models, the fingerprint data including grid coordinates, PCI and corresponding signal quality parameters; generating a third positioning model based on multiple fingerprint data sets, the third positioning model is a positioning model merged from multiple positioning models.

[0021] In a third aspect, an embodiment of the present application provides a first access network device, comprising: a processor and a memory. The processor is coupled to the memory; the memory is used to store computer instructions, and the computer instructions are loaded and executed by the processor to enable the first access network device to implement any one of the methods provided in the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a first access network device, comprising: a processor and a memory. The processor is coupled to the memory; the memory is used to store computer instructions, and the computer instructions are loaded and executed by the processor to enable the first access network device to implement any one of the methods provided in the first aspect.

[0023] In a fifth aspect, an embodiment of the present application provides a chip, comprising: a processor and an interface circuit; the interface circuit is used to receive code instructions and transmit them to the processor; the processor is used to run the code instructions to execute any one of the methods provided in the first aspect.

[0024] In a sixth aspect, an embodiment of the present application provides a chip, comprising: a processor and an interface circuit; the interface circuit is used to receive code instructions and transmit them to the processor; the processor is used to run the code instructions to execute any one of the methods provided in the first aspect.

[0025] In a seventh aspect, an embodiment of the present application provides a computer-readable storage medium, in which at least one computer program instruction is stored. The computer program instruction is loaded and executed by a processor to implement any one of the methods provided in the first aspect above.

[0026] In an eighth aspect, an embodiment of the present application provides a computer-readable storage medium, in which at least one computer program instruction is stored. The computer program instruction is loaded and executed by a processor to implement any one of the methods provided in the first aspect above.

[0027] In a ninth aspect, an embodiment of the present application provides a computer program product, comprising computer execution instructions, which, when executed on a computer, enable the computer to execute any one of the methods provided in the first aspect.

[0028] In a tenth aspect, an embodiment of the present application provides a computer program product, comprising computer execution instructions, which, when executed on a computer, enable the computer to execute any one of the methods provided in the first aspect.

[0029] The possible implementation methods of the second to tenth aspects have effects similar to those of the first aspect and the possible designs of the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A schematic diagram of a scene of a positioning method; Figure 2 A schematic diagram of a scenario of a positioning method provided in an embodiment of the present application; Figure 3 A flowchart of a positioning model training method provided in an embodiment of the present application; Figure 4 A schematic diagram of a scenario of a positioning method provided in an embodiment of the present application; Figure 5 A schematic diagram of a scenario of a positioning method provided in an embodiment of the present application; Figure 6 A flowchart of a positioning method provided in an embodiment of the present application; Figure 7 A schematic diagram of a scenario of a positioning method provided in an embodiment of the present application; Figure 8 A schematic diagram of a flow chart of another positioning method provided in an embodiment of the present application; Fig. 9 A schematic diagram of the structure of a first access network device provided in an embodiment of the present application; Fig.10 A schematic diagram of the structure of another first access network device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present application are described below in conjunction with the accompanying drawings.

[0032] In the description of this application, unless otherwise specified, " / " indicates that the objects associated with each other are in an "or" relationship, for example, A / B can represent A or B; "and / or" in this application is merely a description of the association relationship between associated objects, indicating that three relationships may exist, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural.

[0033] In the description of this application, unless otherwise specified, "plurality" means two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0034] In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference.

[0035] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0036] It is understood that the "embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the various embodiments in the entire specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It is understood that in various embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0037] It can be understood that some optional features in the embodiments of the present application may be implemented independently in certain scenarios without relying on other features, such as the solution on which they are currently based, to solve corresponding technical problems and achieve corresponding effects, or may be combined with other features according to needs in certain scenarios. Accordingly, the devices provided in the embodiments of the present application may also realize these features or functions accordingly, which will not be elaborated here.

[0038] In this application, unless otherwise specified, the same or similar parts between the various embodiments can refer to each other. In this application, if there is no special description or logical conflict between the various embodiments, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and different embodiments can be combined to form new embodiments according to their inherent logical relationships. The following implementation methods of this application do not constitute a limitation on the scope of protection of this application.

[0039] like Figure 1 As shown, in the current cellular mobile communication system, when determining the location of a terminal device, the terminal device needs to measure the signal quality data of multiple cell signals it obtains and other measurement data, and then report these measurement data to the location management network element LMF of the core network through the base station. The LMF of the core network calculates the location of the terminal device based on these measurement data to obtain the positioning result. Then the LMF of the core network sends the location of the terminal device to the terminal device through the base station.

[0040] This terminal positioning solution requires the terminal to transmit the measurement data to the core network through the base station, and the transmission link of the measurement data is long. At the same time, since a large amount of terminal device measurement data will be transmitted to the LMF of the core network, the LMF of the core network needs to process a large amount of measurement data to locate multiple terminals, and the calculation pressure of the LMF is relatively large.

[0041] An embodiment of the present application provides a positioning method, which is applied to a first access network device, and the method includes: receiving communication data from a terminal device, the communication data including multiple physical cell identifiers PCIs and corresponding signal quality parameters of multiple signals; using multiple positioning models to determine the position of the terminal device according to the communication data, the multiple positioning models including a first positioning model corresponding to the first access network device and at least one second positioning model corresponding to at least one adjacent access network device; or, using a third positioning model to determine the position of the terminal device according to the communication data, the third positioning model is a model merged from multiple positioning models, the multiple positioning models including a first positioning model corresponding to the first access network device and at least one second positioning model corresponding to at least one adjacent access network device; and sending the position of the terminal device.

[0042] like Figure 2As shown, based on the above scheme, after obtaining the communication data, the access network device does not need to transmit it to the core network device for position calculation. The position calculation can be performed on the access network device side, which shortens the transmission link of the communication data and reduces the calculation pressure of the core network device. At the same time, the access network device can use multiple positioning models or merged models to calculate the terminal position, with stronger position calculation capabilities, especially for the terminal device position calculation at the edge of the cell corresponding to the access network device. It is more accurate, and the access network device has a more comprehensive coverage of the terminal device position positioning.

[0043] In the embodiment of the present application, the access network device may be referred to as a radio access network (RAN) device, which is a device that provides wireless communication functions for terminal devices. Access network devices include, for example, but are not limited to: next generation base stations (generation nodeB, gNB) in 5G, evolved node B (evolved node B, eNB), baseband units (baseband units, BBU), transmitting and receiving points (transmitting and receiving points, TRP), transmitting points (transmitting points, TP), base stations in future mobile communication systems or access points in WiFi systems, etc. The access network device may also be a wireless controller, a centralized unit (centralized unit, CU), and / or a distributed unit (distributed unit, DU) in a cloud radio access network (cloud radio access network, CRAN) scenario, or the network device may be a relay station, a vehicle-mounted device, and a network device in a future evolved PLMN network, etc.

[0044] The terminal device can communicate with multiple access network devices of different technologies. For example, the terminal device can communicate with an access network device supporting long term evolution (LTE), can communicate with an access network device supporting 5G, and can also communicate with an access network device supporting LTE and an access network device supporting 5G at the same time. The embodiments of the present application are not limited.

[0045] In the embodiment of the present application, the device for realizing the function of the network device may be a network device; or it may be a device capable of supporting the network device to realize the function, such as a chip system, which may be installed in the network device. In the technical solution provided in the embodiment of the present application, the technical solution provided in the embodiment of the present application is described by taking the device for realizing the function of the network device as an example that the network device is used as the network device.

[0046] The technical solution provided in the embodiments of the present application can be applied to various communication systems, such as: long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), universal mobile telecommunication system (UMTS), worldwide interoperability for microwave access (WiMAX) communication system, fifth generation (5G) mobile communication system, new radio (NR), etc. The 5G mobile communication system in the embodiments of the present application includes a non-standalone (NSA) 5G mobile communication system or a standalone (SA) 5G mobile communication system.

[0047] The technical solution provided in the embodiments of the present application can also be applied to future communication systems, such as the sixth-generation mobile communication system, etc., and the embodiments of the present application are not limited to this.

[0048] It is understandable that in the embodiments of the present application, the execution subject may execute some or all of the steps in the embodiments of the present application, and these steps or operations are only examples. The embodiments of the present application may also execute other operations or variations of various operations. In addition, the various steps may be executed in different orders presented in the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application need to be executed.

[0049] It should be noted that the message names between the devices or the names of the parameters in the messages in the following embodiments of the present application are only examples, and other names may be used in the specific implementation, and the embodiments of the present application do not specifically limit this.

[0050] Combine the following Figures 3 to 6 The technical solution of the present application is described in detail with specific method embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0051] For example, Figure 3 A flowchart of a positioning model training method provided in an embodiment of the present application. Figure 3 As shown, the positioning model training method may specifically include the following steps: 301. The first access network device performs positioning model training according to training samples.

[0052] In an embodiment of the present application, the access network device can input a training sample set into an initial positioning model, the training samples of the training sample set including communication data acquired by the terminal device and corresponding position truth labels, the communication data including multiple physical cell identifier PCI labels and signal quality parameters corresponding to the PCI labels.

[0053] Then the access network device uses the initial positioning model to determine the predicted position of the terminal device according to the communication data and the corresponding position truth label; then determines the feedback value according to the loss function, the position truth label and the training sample; finally, adjusts the model parameters of the initial positioning model according to the feedback value to obtain the first positioning model. The first positioning model is used to input the above communication data and output the position of the terminal device corresponding to the communication data.

[0054] In an embodiment of the present application, the signal quality parameters may include cell signal strength and cell positioning reference signal (positioning reference signal, PRS) strength, reference signal received power (reference singnal received power, RSRP), reference signal received quality (Reference Singnal Received Quality, RSRQ), received signal strength indication (Received Singnal Strengthen Indicator, RSSI), signal to interference and noise ratio (Signal to Interference & Noise Ratio, SINR), channel quality (Channel Quality Indicator, CQI) and throughput, etc. In addition, it may also be other parameters that can reflect the signal quality between the terminal device and the access network device, which are not limited here.

[0055] In the embodiment of the present application, the positioning model can be a grid-based fingerprint model, a neural network model, a machine learning model, etc. In addition, it can also be other models used for positioning, which are not specifically limited here.

[0056] In the embodiment of the present application, after each access network device has trained its corresponding positioning model, it can locate the terminal device according to the positioning model. At the same time, positioning according to the positioning model can obtain more accurate positioning and higher positioning efficiency.

[0057] In the embodiment of the present application, it can be understood that the training sample of the first access network device is the communication data obtained by the terminal device. Since the terminal device that establishes communication with the first access network device is usually located within the coverage range of the first access network device, the positioning model trained by the first access network device according to the sample is most applicable within the coverage range of the first access network device, that is, the positioning of the terminal device within this range is more accurate, and the accuracy outside this range is lower than the accuracy within this range.

[0058] In one possible implementation, the first access network device may receive training samples from adjacent access network devices in addition to its own training samples. The first access network device may also be trained based on the training samples to obtain stronger positioning capabilities and a wider range of applicability.

[0059] In a possible implementation manner, the access network device also shares its corresponding positioning model with an adjacent access network device. The method further includes: 302. A first access network device receives a second positioning model from an adjacent access network device.

[0060] The first access network device receives at least one second positioning model corresponding to at least one adjacent access network device.

[0061] In the embodiment of the present application, the first access network device can train the corresponding first positioning model, and it can be understood that the access network device adjacent to the first access network device can also train its corresponding second positioning model. After the adjacent access network device has trained the second positioning model, the second positioning model can be sent to the first access network device, so the first access network device can receive at least one second positioning model corresponding to at least one adjacent access network device.

[0062] In the embodiment of the present application, after training the positioning model, the access network device will send the positioning model to the adjacent access network devices.

[0063] 303. The first access network device combines multiple positioning models to obtain a third positioning model.

[0064] After receiving the at least one second positioning model, the first access network device may combine the first positioning model and the at least one second positioning model into one positioning model to obtain a third positioning model.

[0065] For example, when the positioning model is a grid-based fingerprint model, the first access network device can first obtain multiple fingerprint data sets corresponding to the first positioning model and at least one second positioning model, and the fingerprint data include grid coordinates, PCI and corresponding signal quality parameters. Then, the first access network device can generate a third positioning model based on the multiple fingerprint data sets. The third positioning model is a positioning model merged from multiple positioning models, and the fingerprint data set corresponding to the third positioning model includes the fingerprint data of the above-mentioned first positioning model and the fingerprint data set of the above-mentioned at least one second positioning model.

[0066] Specifically, for example, if the multiple positioning models are grid-based fingerprint models, the first access network device can first disassemble the multiple models to obtain a fingerprint data set for each positioning model, and the fingerprint data may include grid coordinates, PCI, and corresponding signal quality parameters. Specifically, a first fingerprint data set corresponding to the first positioning model and at least one second fingerprint data set corresponding to at least one second positioning model can be obtained, and then these fingerprint data sets can be merged. A third positioning model is determined based on the first fingerprint data set and at least one second fingerprint data set, and the third fingerprint data set of the third positioning model includes the fingerprint data of the above-mentioned first fingerprint data set and at least one second fingerprint data set.

[0067] For example Figure 4 As shown, the multiple positioning models are grid-based fingerprint models. For the position coordinate (x1, y1), the fingerprint data in the fingerprint database of model 1 includes (pci1: -80; pci5: -100; pci6: -90), the fingerprint data in the fingerprint database of model 2 includes (pci1: -80; pci2: -85; pci6: -85), and the fingerprint data in the fingerprint database of model 6 includes (pci1: -85; pci2: -80; pci5: -100; pci6: -90). After the model is merged, for the position coordinate (x1, y1), the fingerprint data in the fingerprint database of the third positioning model includes (pci1: -80, -80, -85; pci2: -85, -80; pci5: -100, -100; pci6: -90, -85, -90).

[0068] For the position coordinate (x2, y2), the fingerprint data in the fingerprint database of model 3 includes (pci1: -95; pci3: -95; pci4: -70; pci5: -95), and the fingerprint data in the fingerprint database of model 4 includes (pci1: -90; pci3: -95; pci4: -75; pci5: -90). After the model is merged, for the position coordinate (x2, y2), the fingerprint data in the fingerprint database of the third positioning model includes (pci1: -95, -90; pci3: -95, -95; pci4: -70, -75; pci5: -95, -90). It can be understood that the fingerprint database of the third positioning model includes fingerprint data of more positioning models, which is not limited here.

[0069] like Figure 5 As shown, in the embodiment of the present application, the model corresponding to each access network device is based on the location samples of the terminal devices within the coverage of the access network device. Therefore, the model corresponding to each access network device is more accurate for the location positioning of the terminal devices within the coverage of the access network device, but the location positioning accuracy of the terminal devices outside the coverage of the access network device is insufficient. Therefore, after the positioning model is merged, the third positioning model merged by the access network device has a larger coverage range and stronger positioning capability than the first positioning model of the access network device, especially for the edge position of the access network device coverage area, the third positioning model is more accurate in calculating the location of the terminal device at this position.

[0070] like Figure 4 As shown, when positioning the terminal at the position coordinates (x1, y1), the position is at the edge of the coverage of model 1, so a more accurate result can be obtained by combining model 2 and model 6 for positioning. Similarly, when positioning the terminal at the position coordinates (x2, y2), the position is outside the coverage of model 1 and within the coverage of model 3 and model 4, and the third positioning model is merged based on model 1 to model 6, so the terminal device at this position can be positioned using the third positioning model.

[0071] After obtaining the third positioning model, the first access device can perform terminal positioning according to the third positioning model.

[0072] In an embodiment of the present application, the first access device merges multiple positioning models into a third positioning model. Since the multiple positioning models include the second positioning model of an adjacent access network device of the first access network device, the second positioning model is more accurate in calculating the position of the terminal device within the coverage range of the adjacent access network device. Therefore, the merged third positioning model has a stronger position calculation capability, especially for the terminal device at the edge of the coverage range of the first access network device, the first access device can calculate its position more accurately, and the access network device has a more comprehensive coverage of the terminal device position positioning.

[0073] For example, Figure 6 A schematic diagram of a positioning method provided in an embodiment of the present application. Figure 4 As shown, the positioning method may specifically include the following steps: 601. The first access network device trains a positioning model.

[0074] The first access network device trains a first positioning model, and the first positioning model is used to determine the position of the terminal device according to the communication data provided by the terminal device.

[0075] Specifically, the method for the first access network device to train the positioning model can refer to the above Figure 3 The positioning model training method shown will not be repeated here.

[0076] 602. The first access network device receives communication data from the terminal device.

[0077] The terminal device can obtain the physical cell identifier PCI and the signal quality parameters of the corresponding multiple signals of the multiple signals broadcast by all the cells, and each PCI can correspond to at least one signal quality parameter.

[0078] For example, terminal device 1 is located within the coverage of base station 1, but the terminal device 1 can receive signals from base station 1, base station 2 and base station 3. The signal quality parameter used by the terminal is the cell positioning reference signal (PRS). The communication data that the terminal device 1 can obtain may be: (pci1, PRS=100; pci2, PRS=80; pci3, PRS=60). The communication data indicates that the signal PRS of base station 1 corresponding to pci1 measured by the terminal device is 100; the signal PRS of base station 2 corresponding to pci2 measured is 80; the signal PRS of base station 3 corresponding to pci3 measured is 60.

[0079] It can be understood that for the signal of a base station, the terminal device can measure multiple quality parameters of the signal. For example, for the signal of base station 1, the terminal device can measure the PRS of the signal and the cell reference signal strength of the signal. The obtained communication data can be (pci1, PRS=100, cell reference signal strength=90), which is not limited here.

[0080] Correspondingly, the first access network device receives the communication data sent by the terminal device.

[0081] 603. The first access network device determines the location of the terminal device according to the communication data.

[0082] After receiving the communication data, the first access network device uses the positioning model to determine the location of the terminal device according to the communication data.

[0083] Specifically, in the embodiment of the present application, the first access network device may use multiple positioning models to locate the terminal device, which may include a first positioning module of the first access network device and at least one second positioning model corresponding to at least one adjacent access network device; the terminal device may also be located using a third positioning model, which is a model merged from multiple positioning models, which include a first positioning model corresponding to the first access network device and at least one second positioning model corresponding to at least one adjacent access network device. The following are described separately: The first access network device uses multiple positioning models to locate the terminal device: After receiving the communication data, the first access network device determines the location of the terminal device based on the communication data using multiple positioning models, including a first positioning model corresponding to the first access network device and at least one second positioning model corresponding to at least one adjacent access network device.

[0084] Specifically, the first access network device can calculate the corresponding predicted position based on the communication data using each of the multiple positioning models, each positioning model determines the corresponding predicted position, and then determine the position of the terminal device based on the multiple predicted positions determined by the multiple positioning models.

[0085] In a possible implementation, the first access network device may determine a weighted average position of multiple predicted positions as the position of the terminal device, for example, the predicted position coordinates determined by positioning model 1 are (80, 90, 70), the predicted position coordinates determined by positioning model 2 are (80, 95, 75), the predicted position coordinates determined by positioning model 3 are (75, 90, 75), and the predicted position coordinates determined by positioning model 4 are (80, 85, 70), wherein positioning model 1 is the base station model of the cell in which the terminal device establishes communication, The weight of this model is 0.7, and the weight of the other models is 0.1. After weighted averaging of the four prediction models, the terminal position coordinates (x, y, z) are obtained: x=80*0.7+80*0.1+75*0.1+80*0.1=79.5, y=90*0.7+95*0.1+90*0.1+85*0.1=90, z=70*0.7+75*0.1+75*0.1+70*0.1=71, terminal position coordinates (x, y, z) = (79.5, 90, 71). It can be understood that the weights corresponding to each model can be different or the same, and the specific weights are not limited here.

[0086] In another possible implementation, the first access network device may first determine multiple predicted positions in a position set among the multiple predicted positions, and then determine the position of the terminal device according to the multiple predicted positions in the position set. Figure 7 As shown, the first access network device determines the corresponding four predicted positions through four positioning models, among which the predicted positions 1, 2, and 3 determined by positioning models 1, 2, and 3 are relatively concentrated, and the predicted position 4 determined by positioning model 4 is relatively remote relative to other positions. The first access network device can remove the influence of predicted position 4 on the final result and determine the position of the terminal device only according to predicted positions 1, 2, and 3. When determining the position of the terminal device according to predicted positions 1, 2, and 3, a weighted average method, an average method, or other methods can be used, which are not limited here.

[0087] In the embodiment of the present application, multiple models are used for positioning respectively, and the model type does not affect the position determination of the terminal device. The model types of multiple positioning models can be the same or different, and are not specifically limited here.

[0088] In the embodiment of the present application, the model corresponding to each access network device is based on the location samples of the terminal devices within the coverage of the access network device. Therefore, the model corresponding to each access network device is more accurate for the location positioning of the terminal devices within the coverage of the access network device, but the accuracy of the location positioning of the terminal devices outside the coverage of the access network device is insufficient. Therefore, when positioning the terminal device, the access network device can call the first positioning model and at least one second positioning model for positioning. Compared with calling only the first positioning model, the coverage is larger and the positioning capability is stronger. In particular, for the edge position of the coverage area of ​​the first access network device, calling the first positioning model and at least one second positioning model is more accurate for the location calculation of the terminal device at this position.

[0089] The first access network device uses a third positioning model to locate the terminal device: The first access network device uses a third positioning model to determine the location of the terminal device according to the communication data. The third positioning model is a model merged from multiple positioning models. The multiple positioning models include a first positioning model corresponding to the first access network device and at least one second positioning model corresponding to at least one adjacent access network device. The first positioning model and the at least one second positioning model are of the same model type and therefore can be merged.

[0090] Specifically, for example, if the multiple positioning models are grid-based fingerprint models, the first access network device can first disassemble the multiple models to obtain a fingerprint data set for each positioning model, and the fingerprint data may include grid coordinates, PCI, and corresponding signal quality parameters. Specifically, a first fingerprint data set corresponding to the first positioning model and at least one second fingerprint data set corresponding to at least one second positioning model can be obtained, and then these fingerprint data sets can be merged. A third positioning model is determined based on the first fingerprint data set and at least one second fingerprint data set, and the third fingerprint data set of the third positioning model includes the fingerprint data of the above-mentioned first fingerprint data set and at least one second fingerprint data set.

[0091] For example Figure 4As shown, the multiple positioning models are grid-based fingerprint models. For the position coordinate (x1, y1), the fingerprint data in the fingerprint database of model 1 includes (pci1: -80; pci5: -100; pci6: -90), the fingerprint data in the fingerprint database of model 2 includes (pci1: -80; pci2: -85; pci6: -85), and the fingerprint data in the fingerprint database of model 6 includes (pci1: -85; pci2: -80; pci5: -100; pci6: -90). After the model is merged, for the position coordinate (x1, y1), the fingerprint data in the fingerprint database of the third positioning model includes (pci1: -80, -80, -85; pci2: -85, -80; pci5: -100, -100; pci6: -90, -85, -90).

[0092] For the position coordinate (x2, y2), the fingerprint data in the fingerprint database of model 3 includes (pci1: -95; pci3: -95; pci4: -70; pci5: -95), and the fingerprint data in the fingerprint database of model 4 includes (pci1: -90; pci3: -95; pci4: -75; pci5: -90). After the model is merged, for the position coordinate (x2, y2), the fingerprint data in the fingerprint database of the third positioning model includes (pci1: -95, -90; pci3: -95, -95; pci4: -70, -75; pci5: -95, -90). It can be understood that the fingerprint database of the third positioning model includes fingerprint data of more positioning models, which is not limited here.

[0093] like Figure 5 As shown, in the embodiment of the present application, the model corresponding to each access network device is based on the location samples of the terminal devices within the coverage of the access network device. Therefore, the model corresponding to each access network device is more accurate for the location positioning of the terminal devices within the coverage of the access network device, but the location positioning accuracy of the terminal devices outside the coverage of the access network device is insufficient. Therefore, after the positioning model is merged, the third positioning model merged by the access network device has a larger coverage range and stronger positioning capability than the first positioning model of the access network device, especially for the edge position of the access network device coverage area, the third positioning model is more accurate in calculating the location of the terminal device at this position.

[0094] like Figure 4As shown, when positioning the terminal at the position coordinates (x1, y1), the position is at the edge of the coverage of model 1, so a more accurate result can be obtained by combining model 2 and model 6 for positioning. Similarly, when positioning the terminal at the position coordinates (x2, y2), the position is outside the coverage of model 1 and within the coverage of model 3 and model 4, and the third positioning model is based on the merger of model 1 to model 6, so the terminal device at this position can be positioned using the third positioning model.

[0095] 604. The first access network device sends the location of the terminal device.

[0096] After determining the location of the terminal device, the first access network device may send the location of the terminal device to a device that needs to obtain the location of the terminal device. For example, the first access network device may send the location of the terminal device to the terminal device or to a core network device.

[0097] In one possible implementation, Figure 8 As shown, the method also includes: 605. The first access network device retrains the first positioning model.

[0098] The first access network device can detect the positioning accuracy of the first positioning model. When the positioning accuracy of the first positioning model is less than the positioning accuracy threshold, the first access network device can retrain the first positioning model. The positioning accuracy of the retrained first positioning model is greater than or equal to the positioning accuracy threshold.

[0099] Specifically, in order to ensure accurate positioning, the first access network device can detect the positioning accuracy of the first positioning model at any time. During the detection, the first access network device can use the communication data including the true value of the position to detect the first positioning model. The communication data includes multiple PCIs, corresponding multiple signal quality parameters and corresponding true value of the position. The multiple PCIs and the corresponding signal quality parameters are input into the first positioning model, and then the first positioning model outputs the predicted position. If the error of the predicted position compared with the true value of the position is greater than the error threshold, it can be determined that the first positioning model needs to be retrained.

[0100] Specifically, when retraining is performed, the samples used in the training may include the communication data and the corresponding true position values ​​acquired by the first access network device during the period from the last training to the current training.

[0101] 607. The first access network device sends the retrained first positioning model.

[0102] After the first access network device retrains the first positioning model, the retrained first positioning model can be sent to adjacent access network devices, so that the adjacent access network devices can use the retrained first positioning model to locate the terminal device.

[0103] In a possible implementation, the method further includes: 608. The first access network device receives the retrained target second positioning model.

[0104] The first access network device receives a retrained target second positioning model from a second access network device, where the second access network device is any one of the adjacent access network devices of the first access network device.

[0105] It is understandable that other access network devices will also perform positioning accuracy detection on their corresponding positioning models, and retrain if the positioning accuracy fails. Therefore, the first access network device can also receive the retrained positioning models of other access network devices.

[0106] It can be understood that after receiving the retrained target second positioning model, the first access network device will replace the previous target second positioning model with the retrained target second positioning model.

[0107] When the first access network device uses multiple positioning models to locate the terminal device, the first access network device directly uses the retrained positioning model to locate the terminal device; when the first access network device uses the third positioning model to locate the terminal device, the first access network device needs to merge the models again to obtain the re-merged third positioning model.

[0108] 609. The first access network device merges the models again to obtain a re-merged third positioning model.

[0109] When the first access network device uses the third positioning model to locate the terminal device, the first access network device re-merges the model according to the re-trained target second positioning model to obtain a re-merged third positioning model. The specific re-model merging method is the same as the above-mentioned model merging method, and is not specifically limited here.

[0110] After obtaining the re-integrated third positioning model, the first access network device can use the re-integrated third positioning model to determine the terminal location.

[0111] Combined with the above Figures 3 to 8 , the positioning method provided in an embodiment of the present application is explained, and the first access network device for executing the above positioning method provided in an embodiment of the present application is described below.

[0112] like Fig. 9 As shown, Fig. 9 A schematic diagram of the structure of a first access network device provided in an embodiment of the present application. Fig. 9 As shown, the first access network device 900 may include: In a possible implementation, when the access network device uses the third positioning model to determine the location of the terminal device according to the communication data, the multiple positioning models are grid-based fingerprint models, and before using the third positioning model to determine the location of the terminal device according to the communication data, the first access network device includes: An acquisition module 901 is configured to acquire a first fingerprint data set corresponding to a first positioning model and at least one second fingerprint data set corresponding to at least one second positioning model, wherein the fingerprint data includes grid coordinates, PCI, and corresponding signal quality parameters; The generating module 902 generates a third positioning model according to the first fingerprint data set and at least one second fingerprint data set.

[0113] A first receiving module 903 is used to receive communication data from a terminal device, where the communication data includes a plurality of physical cell identifiers PCIs and corresponding signal quality parameters of a plurality of signals; Determination module 904 is used to determine the location of the terminal device according to communication data using multiple positioning models, the multiple positioning models include a first positioning model corresponding to the first access network device and at least one second positioning model corresponding to at least one adjacent access network device; or, to determine the location of the terminal device according to communication data using a third positioning model, the third positioning model is a model merged from multiple positioning models, the multiple positioning models include a first positioning model corresponding to the first access network device and at least one second positioning model corresponding to at least one adjacent access network device, and the model type of the first positioning model and the at least one second positioning model are the same.

[0114] In one possible implementation, when the first access network device uses multiple positioning models to determine the location of the terminal device based on communication data, the determination module 904 is specifically used to: use multiple positioning models to determine multiple predicted locations based on the communication data, and the multiple predicted locations correspond one-to-one to the multiple positioning models; determine the location of the terminal device based on the multiple predicted positions.

[0115] In a possible implementation, the determination module 904 is specifically used to: determine a weighted average position of multiple predicted positions as the position of the terminal device; or, determine multiple predicted positions in a position set among the multiple predicted positions; and determine the position of the terminal device based on the multiple predicted positions in the position set. The sending module 905 is used to send the location of the terminal device.

[0116] In a possible implementation, the first access network device 900 further includes: A detection module 906, configured to detect the positioning accuracy of the first positioning model; The retraining module 907 is used to retrain the first positioning model to obtain a retrained first positioning model when the accuracy of the terminal device position positioned by the first positioning model is less than a positioning accuracy threshold.

[0117] In a possible implementation, the sending module 905 is further configured to send the retrained first positioning model to an adjacent access network device.

[0118] In a possible implementation, the first access network device 900 further includes: A second receiving module 907 is configured to receive a retrained target second positioning model from a second access network device, where the second access network device is any one of the adjacent access network devices; The merging module 908 is used to re-merge the models according to the re-trained target second positioning model to obtain a third positioning model.

[0119] In a possible implementation manner, the signal quality parameter includes at least one of a cell signal strength and a cell positioning reference signal PRS strength.

[0120] In a possible implementation, the multiple positioning models are grid-based fingerprint models and / or neural network models.

[0121] The first access network device 900 can be used to implement the above Figures 3 to 8 Any of the methods shown is not specifically limited here.

[0122] Fig.10 A schematic diagram of the structure of a first access network device provided in an embodiment of the present application. Fig.10 As shown, the first access network device 1000 includes one or more (including two) processors 1001 , a communication line 1002 and a communication interface 1003 . Optionally, the first access network device 1000 also includes a memory 1004 .

[0123] In some implementations, the memory 1004 stores the following elements: executable modules or data structures, or a subset thereof, or an extended set thereof.

[0124] The method described in the above embodiment of the present application can be applied to the processor 1001, or implemented by the processor 1001. The processor 1001 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 1001 or an instruction in the form of software. The above processor 1001 can be a general-purpose processor (for example, a microprocessor or a conventional processor), a digital signal processor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates, transistor logic devices or discrete hardware components. The processor 1001 can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application.

[0125] The steps of the method disclosed in the embodiment of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. Among them, the software module can be located in a mature storage medium in the field such as a random access memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable read only memory (EEPROM). The storage medium is located in the memory 1004, and the processor 1001 reads the information in the memory 1004 and completes the steps of the above method in combination with its hardware.

[0126] The processor 1001 , the memory 1004 , and the communication interface 1003 may communicate with each other via the communication line 1002 .

[0127] In the above embodiments, the instructions stored in the memory for execution by the processor may be implemented in the form of a computer program product, wherein the computer program product may be pre-written in the memory, or may be downloaded and installed in the memory in the form of software.

[0128] The embodiment of the present application also provides a computer program product, which includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function executed by the first access network device in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may 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 may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated. For example, the available medium may include a magnetic medium (e.g., a floppy disk, a hard disk or a tape), an optical medium (e.g., a digital versatile disc (DVD)), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0129] An embodiment of the present application provides a first access network device, which includes a processor and a memory, the memory is used to store a computer program, and the processor is used to execute the computer program to perform the above-mentioned positioning method.

[0130] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program or instruction. When the computer program or instruction is executed by the processor, the method executed by the first access network device is implemented. The method described in the above embodiment can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. If implemented in software, the function can be stored as one or more instructions or codes on a computer-readable medium or transmitted on a computer-readable medium. Computer-readable media can include computer storage media and communication media, and can also include any medium that can transfer a computer program from one place to another. The storage medium can be any target medium that can be accessed by a computer.

[0131] As a possible design, the computer-readable medium may include a compact disc read-only memory (CD-ROM), RAM, ROM, EEPROM or other optical disk storage; the computer-readable medium may include a magnetic disk storage or other magnetic disk storage device. Moreover, any connection line may also be appropriately referred to as 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, DSL or wireless technology such as infrared, radio and microwave, the coaxial cable, fiber optic cable, twisted pair, DSL or wireless technology such as infrared, radio and microwave are included in the definition of the medium. Disks and optical disks as used herein include compact disks (CDs), laser disks, optical disks, DVDs, floppy disks and Blu-ray disks, where disks usually reproduce data magnetically, while optical disks reproduce data optically using lasers. Combinations of the above should also be included in the scope of computer-readable media.

[0132] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processing unit of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] The above specific implementation methods further illustrate the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above are only specific implementation methods of the present application and are not used to limit the protection scope of the present application. Any modifications, equivalent substitutions, improvements, 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 positioning method, characterized in that: Applied to a first access network device, the method includes: Receiving communication data from a terminal device, the communication data comprising a plurality of physical cell identifiers PCIs and corresponding signal quality parameters of a plurality of signals; Determine the position of the terminal device according to the communication data using a plurality of positioning models, wherein the plurality of positioning models include a first positioning model corresponding to the first access network device and at least one second positioning model corresponding to at least one adjacent access network device; or, using a third positioning model to determine the position of the terminal device according to the communication data, the third positioning model being a model merged from multiple positioning models, the multiple positioning models including a first positioning model corresponding to the first access network device and at least one second positioning model corresponding to the at least one adjacent access network device, the first positioning model and the at least one second positioning model being of the same model type; The location of the terminal device is sent.

2. The method according to claim 1, characterized in that In a case where the first access network device uses multiple positioning models to determine the location of the terminal device according to the communication data, the using multiple positioning models to determine the location of the terminal device according to the communication data includes: Determine a plurality of predicted positions according to the communication data using the plurality of positioning models, the plurality of predicted positions corresponding one-to-one to the plurality of positioning models; The position of the terminal device is determined based on the multiple predicted positions.

3. The method according to claim 2, characterized in that The determining the position of the terminal device according to the multiple predicted positions includes: Determining a weighted average position of the multiple predicted positions as the position of the terminal device; or, determining a plurality of predicted positions in a position set among the plurality of predicted positions; The location of the terminal device is determined according to the multiple predicted locations in the location set.

4. The method according to claim 1, characterized in that: In a case where the access network device uses a third positioning model to determine the position of the terminal device according to the communication data, the multiple positioning models are grid-based fingerprint models, and before using the third positioning model to determine the position of the terminal device according to the communication data, the method further includes: Acquire a first fingerprint data set corresponding to the first positioning model and at least one second fingerprint data set corresponding to the at least one second positioning model, wherein the fingerprint data includes grid coordinates, PCI, and corresponding signal quality parameters; The third positioning model is generated based on the first fingerprint data set and the at least one second fingerprint data set.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Detecting the positioning accuracy of the first positioning model; When the accuracy of the terminal device position located by the first positioning model is less than a positioning accuracy threshold, the first positioning model is retrained to obtain a retrained first positioning model.

6. The method according to claim 5, characterized in that The method further comprises: The retrained first positioning model is sent to an adjacent access network device.

7. The method according to claim 6, characterized in that The third positioning model is obtained after re-merging the models, and the method further includes: receiving a retrained target second positioning model from a second access network device, where the second access network device is any one of the adjacent access network devices; Based on the retrained target second positioning model, models are merged again to obtain the third positioning model.

8. The method according to any one of claims 1 to 7, wherein the signal quality parameter comprises at least one of a cell signal strength and a cell positioning reference signal (PRS) strength.

9. The method according to claim 8, characterized in that The multiple positioning models are grid-based fingerprint models and / or neural network models.

10. A positioning model training method, characterized in that: The method comprises: Inputting a training sample set into an initial positioning model, wherein the training samples of the training sample set include communication data acquired by the terminal device and corresponding position truth labels, and the communication data includes multiple physical cell identifiers PCI and corresponding signal quality parameters of multiple signals; Determine the predicted position of the terminal device according to the communication data and the corresponding position truth label using the initial positioning model; Determine the feedback value based on the loss function, predicted position and training samples; The model parameters of the initial positioning model are adjusted according to the feedback values ​​to obtain the positioning model.

11. The method according to claim 10, characterized in that The positioning model is a grid-based fingerprint model, and the method further includes: Acquire multiple fingerprint data sets corresponding to the multiple positioning models, the fingerprint data including grid coordinates, PCI and corresponding signal quality parameters; The third positioning model is generated according to the multiple fingerprint data sets, and the third positioning model is a positioning model merged from multiple positioning models.

12. A first access network device, characterized in that: The first access network device includes: A receiving module, configured to receive communication data from a terminal device, wherein the communication data includes a plurality of physical cell identifiers PCIs and corresponding signal quality parameters of a plurality of signals; a determination module, configured to determine the position of the terminal device according to the communication data using a plurality of positioning models, wherein the plurality of positioning models include a first positioning model corresponding to the first access network device and at least one second positioning model corresponding to at least one adjacent access network device; or used to determine the position of the terminal device according to the communication data using a third positioning model, the third positioning model being a model merged from multiple positioning models, the multiple positioning models including a first positioning model corresponding to the first access network device and at least one second positioning model corresponding to the at least one adjacent access network device, the first positioning model and the at least one second positioning model being of the same model type; A sending module is used to send the location of the terminal device.

13. A positioning model training device, characterized in that: The positioning model training device comprises: An input module is used to input a training sample set into an initial positioning model, wherein the training samples of the training sample set include communication data acquired by the terminal device and corresponding position truth labels, and the communication data includes multiple physical cell identifiers PCI and corresponding signal quality parameters of multiple signals; A first determination module, configured to determine the predicted position of the terminal device according to the communication data and the corresponding position truth label using an initial positioning model; The second determination module is used to determine the feedback value according to the loss function, the predicted position and the training sample; The adjustment module is used to adjust the model parameters of the initial positioning model according to the feedback value to obtain the positioning model.

14. A first access network device, characterized in that: The device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call the computer program to execute the positioning method according to any one of claims 1 to 9.

15. A positioning model training device, characterized in that: The device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call the computer program to execute the positioning method according to any one of claims 10 to 11.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program or instruction, and when the computer program or instruction is executed, the positioning method according to any one of claims 1 to 9 is implemented.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program or instruction, and when the computer program or instruction is executed, the positioning method according to any one of claims 10 to 11 is implemented.

18. A computer program product, characterized in that The invention comprises a computer program, which, when being executed, enables a computer to execute the positioning method according to any one of claims 1 to 9.

19. A computer program product, characterized in that The invention comprises a computer program, which, when being executed, enables a computer to execute the positioning method according to any one of claims 10 to 11.

Images