Positioning method and apparatus, electronic device, and computer storage medium

Abstract

Embodiments of the present application provide a positioning method, device, electronic equipment and computer storage medium. The positioning method comprises: receiving a positioning request, wherein the positioning request carries at least positioning fingerprint information scanned by a to-be-positioned object; determining whether the positioning request is a tunnel positioning request according to the positioning fingerprint information and historical positioning position information of the to-be-positioned object; and if so, determining a position of the to-be-positioned object in the tunnel according to the positioning fingerprint information, the historical positioning position information of the to-be-positioned object and corresponding fingerprint positioning features. The positioning method can realize fast positioning in a tunnel.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a positioning method, apparatus, electronic device, and computer storage medium. Background Technology

[0002] Navigation technology is a technology that uses real-time location tracking to plan and guide routes. Taking navigation guidance as an example, real-time location tracking is necessary during navigation. Outdoors, existing positioning methods primarily rely on satellite positioning systems (such as GPS or BeiDou) to pinpoint the user's location. However, satellite signals can be blocked in tunnels or underground environments, making it impossible to locate the user's position using satellite positioning systems in these situations.

[0003] To address the challenge of positioning in tunnels and other environments lacking satellite signals, current technologies typically employ dead reckoning for assisted positioning. However, dead reckoning relies on satellite positioning information prior to the user's entry into the tunnel. Furthermore, as the vehicle's travel time within tunnels and similar environments increases, significant cumulative reckoning errors can accumulate, resulting in substantial inaccuracies in the position obtained through dead reckoning.

[0004] Therefore, existing technologies lack technical solutions that can accurately locate a user's position in scenarios such as tunnels. Summary of the Invention

[0005] In view of this, embodiments of this application provide a positioning scheme to at least partially solve the above-mentioned problems.

[0006] According to a first aspect of the embodiments of this application, a positioning method is provided, comprising: receiving a positioning request, the positioning request carrying at least positioning fingerprint information of an object to be positioned scanned; determining whether the positioning request is a tunnel positioning request based on the positioning fingerprint information and historical positioning information of the object to be positioned; if so, determining the position of the object to be positioned in the tunnel based on the positioning fingerprint information, the historical positioning information of the object to be positioned, and the corresponding fingerprint positioning features.

[0007] According to a second aspect of the embodiments of this application, a positioning device is provided, comprising: a receiving module for receiving a positioning request, the positioning request carrying at least positioning fingerprint information of an object to be positioned; a first determining module for determining whether the positioning request is a tunnel positioning request based on the positioning fingerprint information and historical positioning information of the object to be positioned; and a second determining module for determining the position of the object to be positioned within the tunnel based on the positioning fingerprint information, the historical positioning information of the object to be positioned, and the corresponding fingerprint positioning features.

[0008] According to a third aspect of the present application, an electronic device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; the memory is used to store at least one executable instruction, wherein the executable instruction causes the processor to perform an operation corresponding to the positioning method described in the first aspect.

[0009] According to a fourth aspect of the embodiments of this application, a computer storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the positioning method as described in the first aspect.

[0010] According to the positioning scheme provided in this application, the positioning fingerprint information and historical positioning location information of the object to be located are used to determine whether the positioning request is a tunnel positioning request. If it is a tunnel positioning request, the location of the object to be located in the tunnel is determined based on the positioning fingerprint information, historical positioning location information, and corresponding fingerprint positioning features. This enables accurate positioning in the tunnel. Since each positioning is based on the scanned positioning fingerprint information, no cumulative error is generated, solving the problem of inaccurate positioning in tunnels without satellite signals. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0012] Figure 1a This is a flowchart illustrating the steps of a positioning method according to Embodiment 1 of this application;

[0013] Figure 1b for Figure 1a A schematic diagram of a scenario example in the illustrated embodiment;

[0014] Figure 2a This is a flowchart illustrating the steps of a positioning method according to Embodiment 2 of this application;

[0015] Figure 2b for Figure 2a A schematic diagram of different trajectory points outside and inside the tunnel in the illustrated embodiment;

[0016] Figure 2c for Figure 2a A schematic diagram illustrating the training of a tunnel determination model and a tunnel positioning model in the embodiment shown;

[0017] Figure 3This is a structural block diagram of a positioning device according to Embodiment 3 of this application;

[0018] Figure 4 This is a schematic diagram of the structure of an electronic device according to Embodiment 4 of this application. Detailed Implementation

[0019] To enable those skilled in the art to better understand the technical solutions in the embodiments of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art should fall within the protection scope of the embodiments of this application.

[0020] The specific implementation of the embodiments of this application will be further described below with reference to the accompanying drawings.

[0021] Example 1

[0022] Reference Figure 1a The diagram shows a step flow chart of the positioning method according to Embodiment 1 of this application.

[0023] In this embodiment, the implementation process of the positioning method is explained by taking the configuration of the positioning method on the server side as an example. Of course, in other embodiments, the positioning method can also be configured on a terminal device (such as a user's mobile phone or a vehicle terminal) to achieve the positioning of the target object.

[0024] The positioning method includes the following steps:

[0025] Step S102: Receive a location request.

[0026] The location request carries at least the location fingerprint information of the object to be located. The object to be located can be any suitable device, such as a user-carried terminal device (e.g., mobile phone, smartwatch, smart glasses, etc.) or a terminal device installed in a vehicle (e.g., in-vehicle computer, etc.).

[0027] The location fingerprint information scanned from the object to be located includes, but is not limited to: scanned base station information and / or scanned wireless network information (such as a Wi-Fi network). The devices that create base stations and Wi-Fi hotspots can both be referred to as fingerprint devices.

[0028] Location fingerprint information is used to indicate the network environment of the current location of the object to be located. Since the network environment is different in different locations, the object to be located can be located through the network environment in order to meet the user's location and navigation needs.

[0029] Base stations can provide internet access services to terminal devices, and the approximate geographical location of the terminal device can be determined through base station information.

[0030] Wireless network information refers to networks that, excluding base stations, communicate wirelessly with terminal devices according to wireless communication protocols. Examples include Wi-Fi networks.

[0031] Taking the location scenario during a user's driving journey as an example, while the vehicle is in motion, the user's terminal device scans the base station information and / or wireless network information of its location every once in a while (this information can be collectively referred to as location fingerprint information), and sends this information to the server in the location request so that the server can locate the user based on the location fingerprint information carried in the location request.

[0032] Of course, in other embodiments, if the positioning method is configured locally on the user's terminal device, the terminal device can achieve positioning locally based on the positioning fingerprint information. This embodiment does not limit this.

[0033] Step S104: Determine whether the positioning request is a tunnel positioning request based on the positioning fingerprint information and the historical positioning information of the object to be located.

[0034] Because the positioning methods differ inside and outside the tunnel, it's necessary to determine whether a received positioning request is a tunnel positioning request to ensure accuracy. Furthermore, since the positioning fingerprint information differs depending on the location of the object, analyzing the positioning fingerprint information and historical location information can quickly determine whether a positioning request is a tunnel positioning request. This improves the speed of the determination, ensures accuracy, helps reduce positioning latency, and enhances the user experience.

[0035] Those skilled in the art can determine whether a location request is a tunnel location request using any appropriate method, and this embodiment does not impose any limitations on this. For example, the base station to be scanned can be determined based on the base station information included in the location fingerprint information, and then the location fingerprint device corresponding to the pre-collected tunnel (e.g., a base station or a device that creates a Wi-Fi hotspot) can be determined based on whether the scanned base station includes such a device. If it does, it indicates that the probability of the object to be located being in the tunnel is relatively high. It should be noted that if the object to be located has video or image capture capabilities, the determination of whether it is in a tunnel location scenario can also be made by combining or based on the video or image captured by the object to be located.

[0036] If the location request is determined to be a tunnel location request, then step S106 is executed, and the location is performed using the location method corresponding to that inside the tunnel to ensure location accuracy. Alternatively, if the location request is determined not to be a tunnel location request, then the location is performed using the location method corresponding to that outside the tunnel.

[0037] Step S106: If yes, then determine the location of the object to be located in the tunnel based on the positioning fingerprint information, the historical positioning location information of the object to be located, and the corresponding fingerprint positioning features.

[0038] When inside a tunnel, it is difficult to obtain satellite signals, so positioning fingerprint information is required for location.

[0039] The historical location information of the object to be located includes at least one of the following: location time, location type, and location, but is not limited to these:

[0040] Fingerprint location features can be characteristics of the corresponding fingerprint device, including, but not limited to, the location information of the grid within the signal coverage area of ​​the fingerprint device and / or the signal strength of the fingerprint device within the grid. The grid can be a region obtained by dividing the signal coverage area of ​​the fingerprint device in an appropriate manner.

[0041] In one specific implementation, the trained tunnel positioning model can be used to determine the location of the object to be located. For example, positioning feature data can be constructed using positioning fingerprint information, historical positioning information, and fingerprint positioning features. This positioning feature data can then be input into the tunnel positioning model to obtain the location information output by the tunnel positioning model.

[0042] Of course, in other embodiments, other appropriate methods can be used to determine the position of the object to be located in the tunnel, and this embodiment does not limit this.

[0043] Through the above steps, it is possible to determine whether a positioning request is a tunnel positioning request by using the positioning fingerprint information (including at least one of base station information and wireless network information) and historical positioning information of the object to be located. If it is a tunnel positioning request, the location of the object to be located within the tunnel is determined based on the positioning fingerprint information, historical positioning information, and fingerprint positioning features. Since positioning depends on positioning fingerprint information, historical positioning information, and fingerprint positioning features, the accuracy of positioning within the tunnel is guaranteed. Moreover, each positioning relies on the currently scanned positioning fingerprint information, so there is no cumulative error, resulting in higher positioning accuracy.

[0044] The implementation process of the positioning method will be explained below using a specific use case.

[0045] like Figure 1b As shown, the example is a user driving a vehicle into tunnel A and locating the user within tunnel A.

[0046] At time t1, the user, carrying a terminal device, drives a vehicle into tunnel A. Because the tunnel makes it difficult to obtain satellite signals, at time t2, the user's terminal device scans the location's fingerprint information (such as base station information and Wi-Fi network information). Since the signals from base stations and Wi-Fi hotspots have corresponding coverage areas, at time t2, the location fingerprint information collected by the terminal device includes information from base station 1 and Wi-Fi-1 and Wi-Fi-2. The terminal device carries this location fingerprint information in a location request and sends the request to the server.

[0047] The server receives the location request. Since there is no satellite signal in the location request, it determines whether the location request is a tunnel location request based on the location fingerprint information and the historical location information of the object to be located. For example, during pre-collection, big data analysis determines that base station 1 is a location fingerprinting device for the tunnel, meaning that it is highly likely to scan base station 1 when the object is in tunnel A. When the base station information included in the location fingerprint information contains base station 1, the probability of determining that the location request is a tunnel location request is relatively high.

[0048] If the location request is determined to be a tunnel location request, the corresponding tunnel location method is used for location. That is, based on the location fingerprint information, historical location information and fingerprint location features, the specific location of the object to be located in the tunnel is determined and the determined location information is sent to the terminal device.

[0049] This embodiment utilizes the location fingerprint information and historical location information of the object to be located scanned to determine whether the location request is a tunnel location request. If it is a tunnel location request, the location of the object to be located within the tunnel is determined based on the location fingerprint information, historical location information, and corresponding fingerprint location features. This enables accurate positioning within the tunnel. Since each positioning is based on the scanned location fingerprint information, no cumulative error occurs, solving the problem of inaccurate positioning in tunnels without satellite signals.

[0050] Example 2

[0051] Reference Figure 2a The flowchart of the positioning method according to Embodiment 2 of this application is shown.

[0052] In this embodiment, the location method is configured on the server side as an example for explanation. Of course, in other embodiments, the location method can also be configured in any suitable terminal device, and this embodiment does not impose any restrictions on this.

[0053] The positioning method includes the aforementioned steps S102 to S106. In order to accurately determine whether the target object is in the tunnel based on the network fingerprint information and to accurately locate it, the positioning method also includes steps S100a to S100d.

[0054] Step S100a: Based on the information of trajectory points included in the historical trajectory data of the positioning object that has passed through the sample tunnel, determine the trajectory points located within the sample tunnel.

[0055] Historical trajectory data can be obtained through any appropriate means. For example, it can be obtained from location log data. Historical trajectory data includes information on multiple trajectory points, such as the location information and location fingerprint information of the trajectory points. By analyzing historical trajectory data (this analysis can be done manually or using existing data analysis tools), historical trajectory data that traversed the sample tunnel can be extracted from the acquired historical trajectory data. Of course, historical trajectory data that did not traverse the tunnel but passed through the outer roads of the tunnel can also be obtained as needed (for ease of description, this is referred to as outer trajectory data).

[0056] The location information of trajectory points in historical trajectory data of passing through sample tunnels can be obtained in the following way:

[0057] Based on the tunnel entry and exit times in the multiple historical trajectory data, the average tunnel travel speed corresponding to the multiple historical trajectory data is determined.

[0058] For each historical trajectory data, since satellite signals are lost after entering the tunnel, the last trajectory point containing satellite signals before the tunnel entrance can be identified as the trajectory point for entering the tunnel, and the positioning time of this trajectory point for entering the tunnel can be used as the tunnel entry time.

[0059] Similarly, satellite signals can be reacquired after exiting the tunnel. Therefore, the first trajectory point containing satellite signals after the tunnel exit can be used as the trajectory point for exiting the tunnel, and the positioning time of this trajectory point can be used as the time of exiting the tunnel.

[0060] Based on the time of entering the tunnel, the time of exiting the tunnel, and the length of the corresponding sample tunnel, the average speed of traversing the sample tunnel corresponding to the historical trajectory data can be calculated.

[0061] For multiple trajectory points within multiple tunnels in the multiple historical trajectory data, the location information of the multiple trajectory points within the multiple tunnels is determined based on the positioning time of the multiple trajectory points within the multiple tunnels and the average travel speed within the tunnels.

[0062] To ensure detection accuracy and eliminate the adverse effects of traffic congestion within the tunnel, an overall average passage speed is calculated based on the average passage speed from multiple historical trajectory data sets and the number of historical trajectory data sets. Based on this overall average passage speed, historical trajectory data sets with average passage speeds greater than the overall average passage speed are selected from the multiple historical trajectory data sets; these historical trajectory data sets represent those from non-congested conditions.

[0063] For these historical trajectory data in non-congested conditions, for each trajectory point inside the tunnel in the historical trajectory data in non-congested conditions, the travel distance of the current trajectory point inside the tunnel relative to the tunnel entrance is determined based on the current positioning time of the trajectory point inside the tunnel and the average travel speed inside the tunnel, thereby determining the location information of the current trajectory point inside the tunnel.

[0064] For example, such as Figure 2b As shown, at time t1, the object to be located is at point A when a satellite signal is acquired. Based on this satellite signal, the position information of the object to be located at point A is determined. At time t2, the object to be located travels to point B, and positioning fingerprint information is acquired. Based on the average travel speed of historical trajectory data and the time difference between time t1 and time t2, the distance traveled by the object to be located is determined, and thus the position information of point B is determined. Step S100b: Based on the position information of the trajectory points within the sample tunnel and the positioning fingerprint information indicating the positioning fingerprint device, the positioning fingerprint device corresponding to the sample tunnel is determined, and the fingerprint positioning features of the positioning fingerprint device are determined.

[0065] The fingerprint positioning device can be a base station or a WIFI hotspot creation device that can be scanned inside the tunnel.

[0066] The fingerprint positioning features of a fingerprint positioning device include, but are not limited to, the location information and / or signal strength information of the grid contained in the signal coverage area of ​​the fingerprint positioning device. The grid can be obtained by dividing the signal coverage area of ​​the fingerprint positioning device.

[0067] In one specific implementation, step S100b is achieved through the following process:

[0068] Process A: Determine the positioning fingerprint device corresponding to the sample tunnel based on the positioning fingerprint information indicated by the positioning fingerprint information corresponding to the trajectory points in the sample tunnel.

[0069] These trajectory points can be the trajectory points of a single object to be located (such as a terminal device), or they can be the trajectory points of multiple objects to be located.

[0070] If the location fingerprint information corresponding to trajectory points 1 to 3 all indicate that the object to be located has scanned base stations A and B, and the location fingerprint information corresponding to trajectory points 4 to 10 all indicate that the object to be located has scanned base stations B and C, the location fingerprint device indicated by the location fingerprint information that these trajectory points can scan can be used to determine the location fingerprint device corresponding to the tunnel.

[0071] Process B: Based on the location information of the trajectory points in the sample tunnel of the same positioning fingerprint device, determine the signal coverage area of ​​the positioning fingerprint device.

[0072] Based on the location information of each trajectory point and the positioning fingerprint information of that trajectory point, the location distribution of the object to be located that can be scanned by the positioning fingerprint device can be determined, that is, the signal coverage area of ​​each positioning fingerprint device.

[0073] For example, if trajectory points 1-3 and 17-22 all detect base station A, the signal coverage area of ​​base station A can be determined based on the location information of these trajectory points. This coverage area indicates the geographical area that the signal of base station A can cover. Taking a circular coverage area as an example, it can be represented using the latitude and longitude coordinates of the center point and the radius. Of course, other appropriate methods can also be used.

[0074] Process C: Divide the signal coverage area of ​​the positioning fingerprint device into a grid.

[0075] To improve positioning accuracy, the signal coverage area of ​​the fingerprint positioning device is divided into multiple smaller grids. The grid division method can be determined as needed, and this embodiment does not impose any restrictions on it.

[0076] One feasible approach is to determine the area of ​​the geographical region covered by each grid, dividing the signal coverage area of ​​the fingerprint device into multiple grids of similar or identical size. The grids can be rectangular, hexagonal, circular, etc.

[0077] Process D: Determine the position information of the corresponding grid based on the position information of the trajectory points falling into the corresponding grid, and / or determine the signal strength information of the grid based on the signal strength information of the positioning fingerprint device in the positioning fingerprint information corresponding to the trajectory points falling into the corresponding grid.

[0078] In one specific implementation, when determining the position information of the grid, for each grid, the two farthest trajectory points from the trajectory points falling into the grid are selected, and the boundary of the grid is defined by the position information of these two trajectory points.

[0079] When determining the signal strength information of a grid, assume that the positioning fingerprinting devices covering grid A include base stations A and C. Trajectory points 1-10 falling within grid A are sampled by base station A, and each trajectory point has a corresponding sampled signal strength. The signal strength information of base station A within grid A is determined based on the signal strengths sampled by trajectory points 1-10. Similarly, trajectory points 11-22 falling within grid A are sampled by base station C, and each trajectory point has a corresponding sampled signal strength. The signal strength information of base station C within grid A is determined based on the signal strengths sampled by trajectory points 11-22.

[0080] This method enables the pre-collection of fingerprint positioning features of the positioning fingerprint device inside the tunnel, which can then be used in the subsequent tunnel positioning process.

[0081] In order to accurately locate, in addition to pre-collecting the fingerprint device and the corresponding fingerprint positioning features, a tunnel determination model for tunnel determination and a tunnel positioning model for tunnel positioning can also be pre-trained.

[0082] For example, a first neural network model is trained as a tunnel determination model through step S100c.

[0083] Step S100c: Train a tunnel determination model to determine whether a location request is a tunnel location request.

[0084] The tunneling detection model can be a neural network model, such as a neural network model combining a convolutional neural network (CNN) and an attention mechanism, or other models with appropriate structures.

[0085] The tunnel identification model can be trained using historical trajectory data (such as historical trajectory data obtained from location log data) so that the trained tunnel identification model can accurately determine whether a location request is a tunnel location request.

[0086] like Figure 2c As shown, the training process can be implemented through the following procedures E to G:

[0087] Process E: Based on the obtained location log data, determine the historical trajectory data inside multiple tunnels when passing through tunnels and / or the historical trajectory data outside multiple tunnels when passing through roads surrounding the tunnels.

[0088] As mentioned earlier, location log data includes historical trajectory data for multiple location objects. Historical trajectory data includes multiple trajectory points (i.e., historical location points), each containing the location time and location. By analyzing the historical trajectory data, it is possible to determine historical trajectory data inside tunnels where passage is made, and / or, historical trajectory data outside tunnels where passage is made via roads surrounding the tunnels.

[0089] For example, given the known range of tunnel coordinates, if the location information of one or more historical positioning points in the historical trajectory data falls within the tunnel's coordinate range, then it is identified as historical trajectory data within the tunnel. Alternatively, if no historical positioning point in the historical trajectory data falls within the tunnel's coordinate range, but the difference between the location information of one or more historical positioning points in the historical trajectory data and the tunnel's coordinate range is less than a set value (the set value can be determined as needed), then the historical trajectory data is identified as historical trajectory data outside the tunnel.

[0090] Process F: Select multiple tunnel positioning points from multiple tunnel historical trajectory data and determine positive samples based on the network fingerprint information of the tunnel positioning points; and / or, select multiple tunnel external positioning points from multiple tunnel external historical trajectory data and determine negative samples based on the network fingerprint information of the tunnel external positioning points.

[0091] In addition to historical trajectory data, the location log data also includes data from multiple network points. These network point data are divided into two types: one is based on satellite signals, which includes the acquisition time, satellite signal data, and the corresponding historical trajectory; the other is based on location fingerprint data, which includes the acquisition time, location fingerprint data, and the corresponding historical trajectory.

[0092] By matching network points with historical location points in historical trajectory data according to time, the location fingerprint information or satellite signal corresponding to the historical location point can be determined.

[0093] The location point inside the tunnel can be a historical location point in the tunnel where the location information is located within the tunnel's historical trajectory data.

[0094] External positioning points can be historical positioning points in the historical trajectory data outside the tunnel whose coordinate range from the tunnel's coordinates is less than a set value. For example, if the tunnel's coordinate range is a rectangular area defined by (x1, y1) and (x2, y2), then when determining external positioning points, historical positioning points can be found in the historical trajectory data outside the tunnel whose coordinates in the X direction are between x1 and x2, whose coordinates in the Y direction are outside y1 and y2, and whose distance from y1 or y2 is less than a set value (the set value can be determined as needed).

[0095] Of course, in other embodiments, other methods can be used to determine the positioning points inside and outside the tunnel, and this embodiment does not limit this.

[0096] After determining the location fingerprint information of historical location points, the location points within the tunnel can be identified from the historical trajectory data within the tunnel, and positive samples can be determined based on the location fingerprint information corresponding to the location points within the tunnel. For example, for location point 1 within the tunnel, its location fingerprint information and the information on whether the N adjacent location points (N can be determined as needed, N is greater than or equal to 1) before location point 1 within the tunnel are within the tunnel are used to form the first input data. The first input data and the positive marker data are then used to form the positive sample.

[0097] And / or,

[0098] The system selects locations outside the tunnel from historical trajectory data outside the tunnel and determines negative samples based on the location fingerprint information corresponding to these locations. For example, for location point 3 outside the tunnel, its location fingerprint information and information on whether the N adjacent locations preceding location point 3 are inside the tunnel are used to form the second input data. The second input data and the negative label data are then used to form the negative sample.

[0099] Process G: The first neural network model is trained using the positive samples and / or the negative samples to obtain a first neural network model that determines whether the target object is inside the tunnel based on the target object's location fingerprint information.

[0100] Positive samples are input into the first neural network model to train it, enabling the first neural network model to learn the features of the location fingerprint information of the location points in the tunnel. This allows the trained first neural network model to accurately determine whether the target object is in the tunnel based on the location fingerprint information.

[0101] And / or, negative samples are input into the first neural network model to train the first neural network model, so that the first neural network can learn the features of the positioning fingerprint information of the positioning point outside the tunnel, so that the trained first neural network model can determine whether the target object is outside the tunnel based on the positioning fingerprint information of the target object.

[0102] When training the first neural network model using positive and negative samples, the first neural network model can better determine whether the target object is inside the tunnel based on the location fingerprint information, thereby improving the accuracy of the judgment and avoiding the problem of inaccurate positioning when the target object is driving on the road outside the tunnel and is mistakenly judged to be inside the tunnel.

[0103] Of course, in other embodiments, other methods can be used to train the first neural network model, and this embodiment does not impose any limitations.

[0104] In addition to training the tunnel determination model to improve the accuracy of judging whether a positioning request is a tunnel positioning request, step S100d can be executed to train the tunnel positioning model, so that the trained tunnel positioning model can accurately locate the position of the object to be located in the tunnel based on the positioning fingerprint information, thereby improving the positioning accuracy.

[0105] Specifically, step S100d: train a tunnel positioning model to determine the location of the object to be located within the tunnel.

[0106] The tunnel localization model can be a neural network model that combines convolutional neural networks with attention mechanisms.

[0107] In this embodiment, for each tunnel, the tunnel is divided into multiple grids. Based on historical positioning log data, the network points contained in each grid are determined. Then, training samples are formed based on the positioning fingerprint information of the network points in each grid and the position of the grid. The training samples are used to train the tunnel positioning model, so that the tunnel positioning model can learn the network feature information of each grid, so that the location of the object to be located can be located in the future.

[0108] It should be noted that during a location request process for the object to be located, the aforementioned steps S100a to S100d may or may not be executed, and this embodiment does not impose any restrictions on this. In this embodiment, as the object to be located moves with a vehicle or other vehicle, it sends a location request to a server configured with a location method at regular intervals. This location request carries at least the location fingerprint information collected from the object to be located. In this embodiment, the location fingerprint information includes base station information and wireless network information as an example for explanation.

[0109] In order to locate the object to be located, the server configured with the location method executes the aforementioned steps S102 to S106.

[0110] In this embodiment, in order to ensure the accuracy of the judgment on whether the positioning request is a tunnel positioning request, and to avoid the judgment taking too long and affecting the positioning response speed of the object to be located outside the tunnel, step S104 includes the following sub-steps S1041 to S1042.

[0111] Sub-step S1041: Based on the fingerprint device information included in the positioning fingerprint information, determine whether the corresponding fingerprint device includes the positioning fingerprint device of the pre-collected tunnel.

[0112] The location fingerprint device for the tunnel can be the one collected in the aforementioned steps. If the base station information carried in the location fingerprint information includes the location fingerprint device for the tunnel, it indicates that the object to be located is likely inside the tunnel, meaning the probability of the location request being a tunnel location request is relatively high. However, because the location fingerprint device for the tunnel has a certain coverage area, the object to be located may also have its signal collected when it is on the road outside the tunnel, which may lead to misjudgment. To improve the accuracy of the judgment, when determining that the location fingerprint device includes the tunnel, sub-step S1042 can be executed for further and more accurate judgment.

[0113] Sub-step S1042: If included, determine whether the request is a tunnel positioning request based on the positioning fingerprint information and the historical positioning information of the object to be located.

[0114] In a specific implementation, sub-step S1042 is implemented through processes H to I:

[0115] Process H: Construct judgment feature data based on the positioning fingerprint information and the historical positioning information of the object, including the positioning time and positioning type.

[0116] For example, as needed, the location time and location type in the base station information, wireless network information (including but not limited to WIFI network information) and the historical location information of the object to be located (e.g., the M closest historical location information before the current time) in the location fingerprint information can be converted into vectors of a set length. The set length can be determined as needed. The first vector corresponding to the base station information, the second vector corresponding to the wireless network information, and the third vector corresponding to the historical location information are concatenated to construct the judgment feature data.

[0117] Process G: Input the determination feature data into a pre-trained tunnel determination model, and determine the probability that the request is a tunnel positioning request by the tunnel determination model. If the probability is greater than a preset threshold, then the request is determined to be a tunnel positioning request.

[0118] The preset threshold can be determined as needed, and this embodiment does not impose any restrictions on it. For example, the preset threshold can be 90%, 95%, etc.

[0119] The tunnel identification model can determine the probability that a location request is a tunnel location request based on identification feature data. Because the tunnel identification model integrates multiple data, the judgment is more accurate, effectively preventing false positives and thus improving the accuracy of subsequent positioning.

[0120] If the location request is determined to be a tunnel location request, then step S106 is executed; otherwise, any appropriate method corresponding to the outside of the tunnel can be used for location, and this embodiment does not limit this.

[0121] Step S106: If yes, then determine the location of the object to be located in the tunnel based on the positioning fingerprint information, the historical positioning location information of the object to be located, and the corresponding fingerprint positioning features.

[0122] In a specific implementation, step S106 can be achieved through the following sub-steps:

[0123] Sub-step S1061: Obtain the fingerprint positioning features matched by the fingerprint device indicated by the positioning fingerprint information.

[0124] In one specific implementation, the fingerprint location features matched by the fingerprint device are retrieved from a database of collected fingerprint location features. This database is constructed from the fingerprint location features of the pre-collected fingerprint devices mentioned in the preceding steps.

[0125] For example, the location fingerprinting devices corresponding to tunnel A are base stations A and B. When a user passes through tunnel A, the location fingerprint information indicates that base stations A and B have been scanned. Then, the fingerprint location features that match base stations A and B can be retrieved from the fingerprint location features of the aforementioned pre-collected location fingerprinting devices.

[0126] The fingerprint positioning features include the location information and / or signal strength information of the grids contained in the signal coverage areas of base stations A and B. This grid can be all the grids contained in the signal coverage areas of base stations A and B, or it can be a selection of grids from all the grids.

[0127] When selecting a subset of grid cells, for each grid cell, the weights of base station A and base station B within that grid are calculated, and these two weights are added together to obtain the total weight. Then, the total weights of all grid cells covered by base stations A and B are sorted, and the top N weights are selected. This method reduces the amount of fingerprint location feature data and allows for the rapid selection of grid cells in the overlapping areas of base stations A and B.

[0128] Of course, fingerprint positioning features can be obtained in other embodiments, and this embodiment does not limit this.

[0129] Sub-step S1062: Construct location feature data based on the location fingerprint information, the historical location information of the object including location time, location type and location, and the fingerprint location features.

[0130] For example, similar to constructing judgment feature data, the positioning fingerprint information, positioning time, positioning type and positioning location in historical positioning information, and fingerprint positioning features are vectorized and then concatenated to form positioning feature data.

[0131] Sub-step S1063: Input the positioning feature data into a pre-trained tunnel positioning model, and use the tunnel positioning model to determine the position of the object to be located in the tunnel.

[0132] Because the tunnel positioning model learns the network environment characteristics of different locations, it can determine the location of the object within the tunnel by inputting positioning feature data. The tunnel positioning model can directly output the latitude and longitude of the location, or it can represent the location in other ways.

[0133] The implementation process of the positioning method will be explained below with reference to a specific use case:

[0134] While the vehicle is traveling outside the tunnel, the object to be located collects satellite signals periodically to determine its position. Once the vehicle enters the tunnel, the object can no longer obtain satellite signals, so it sends the scanned location fingerprint information to the server in the location request.

[0135] If the location fingerprint information server determines that the fingerprint device indicated by the location fingerprint information includes a location fingerprint device in the tunnel, then the probability that the location request is a tunnel location request is high. In order to more accurately determine whether it is in the tunnel, a judgment feature data is constructed based on the location fingerprint information and the historical location information of the object, including the location time and location type. The judgment feature data is then input into the tunnel judgment model. If the probability that the tunnel judgment model determines that the location request is a tunnel location request is greater than a preset threshold, then the tunnel positioning method is used for positioning.

[0136] Specifically, based on the scanned positioning fingerprint information, the positioning time, positioning type (such as network positioning or satellite positioning) and positioning location in the historical positioning location information of the object to be located, and the fingerprint positioning features corresponding to the fingerprint device indicated by the positioning fingerprint information, positioning feature data is constructed, and the positioning feature data is input into the tunnel positioning model to obtain the position output by the tunnel positioning model.

[0137] This positioning method requires users to carry only an internet-connected terminal device (such as a mobile phone). It does not require users to carry any other specific hardware devices. It only needs to use positioning fingerprint information such as base station information and wireless network information to determine whether the object to be located is in the tunnel and can achieve positioning. The positioning is mainly based on the base station information and wireless network information at the current time, so there will be no cumulative error.

[0138] Before positioning, the tunnel truth can be determined in advance using historical positioning log data. This allows for a more accurate identification of the positioning fingerprint device in the tunnel, as well as the fingerprint positioning characteristics of the device. Based on this fingerprint, it is possible to make a preliminary judgment on whether the object to be located is inside the tunnel, which helps improve the accuracy and speed of the judgment.

[0139] Example 3

[0140] Reference Figure 3 The diagram shows a structural block diagram of the positioning device according to Embodiment 3 of this application.

[0141] In this embodiment, the positioning device includes:

[0142] The receiving module 302 is used to receive a positioning request, wherein the positioning request carries at least the positioning fingerprint information of the object to be located.

[0143] The first determining module 304 is used to determine whether the positioning request is a tunnel positioning request based on the positioning fingerprint information and the historical positioning location information of the object to be located.

[0144] The second determining module 306 is used to determine the position of the object to be located in the tunnel based on the positioning fingerprint information, the historical positioning location information of the object to be located, and the corresponding fingerprint positioning features.

[0145] Optionally, the first determining module 304 includes:

[0146] The third determining module 3041 is used to determine whether the corresponding fingerprint device includes the pre-collected positioning fingerprint device of the tunnel based on the fingerprint device information included in the positioning fingerprint information.

[0147] The fourth determining module 3042 is used to determine whether the request is a tunnel positioning request based on the positioning fingerprint information and the historical positioning location information of the object to be located, if the request is included.

[0148] Optionally, the fourth determining module 3042 is used to construct determination feature data based on the positioning fingerprint information and the historical positioning location information of the object, including the positioning time and positioning type; input the determination feature data into a pre-trained tunnel determination model, and determine the probability that the request is a tunnel positioning request by the tunnel determination model. If the probability is greater than a preset threshold, the request is determined to be a tunnel positioning request.

[0149] Optionally, the second determining module 306 is used to obtain the fingerprint positioning features matched by the fingerprint device indicated by the positioning fingerprint information; construct positioning feature data based on the positioning fingerprint information, the historical positioning location information of the object including positioning time, positioning type and positioning location, and the fingerprint positioning features; input the positioning feature data into a pre-trained tunnel positioning model, and determine the position of the object to be located in the tunnel by the tunnel positioning model.

[0150] Optionally, the device further includes:

[0151] The fifth determining module 308 is used to determine the trajectory point in the sample tunnel based on the information of the trajectory points included in the historical trajectory data of the positioning object that has passed through the sample tunnel before the receiving module 302 receives the positioning request.

[0152] The sixth determining module 310 is used to determine the positioning fingerprint device corresponding to the sample tunnel and the fingerprint positioning features of the positioning fingerprint device based on the position information of the trajectory point in the sample tunnel and the positioning fingerprint information collected.

[0153] Optionally, the fingerprint positioning features of the positioning fingerprint device include the location information and / or signal strength information of the grid contained in the signal coverage area of ​​the positioning fingerprint device.

[0154] Optionally, the sixth determining module 310 includes:

[0155] The seventh determining module 3101 is used to determine the positioning fingerprint device corresponding to the sample tunnel based on the positioning fingerprint information indicated by the positioning fingerprint device corresponding to the trajectory point in the sample tunnel.

[0156] The eighth determining module 3102 is used to determine the signal coverage area of ​​the positioning fingerprint device based on the location information of the trajectory points in the sample tunnel of the same positioning fingerprint device.

[0157] The partitioning module 3103 is used to divide the signal coverage area of ​​the positioning fingerprint device into a grid.

[0158] The ninth determining module 3104 is used to determine the position information of the corresponding grid based on the position information of the trajectory points falling into the corresponding grid, and / or to determine the signal strength information of the grid based on the signal strength information of the positioning fingerprint device in the positioning fingerprint information corresponding to the trajectory points falling into the corresponding grid.

[0159] The positioning device of this embodiment is used to implement the corresponding positioning methods in the foregoing method embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here. Furthermore, the functional implementation of each module in the positioning device of this embodiment can be referred to the description of the corresponding part in the foregoing method embodiments, which will also not be repeated here.

[0160] Example 4

[0161] Reference Figure 4 The diagram shows a structural schematic of an electronic device according to Embodiment 4 of this application. The specific embodiments of this application do not limit the specific implementation of the electronic device.

[0162] like Figure 4 As shown, the electronic device may include: a processor 402, a communications interface 404, a memory 406, and a communications bus 408.

[0163] in:

[0164] The processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408.

[0165] Communication interface 404 is used to communicate with other electronic devices or servers.

[0166] The processor 402 is used to execute program 410, which can specifically execute the relevant steps in the above-described positioning method embodiment.

[0167] Specifically, program 410 may include program code that includes computer operation instructions.

[0168] Processor 42 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or they may be processors of different types, such as one or more CPUs and one or more ASICs.

[0169] Memory 406 is used to store program 410. Memory 406 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0170] Specifically, program 410 can be used to cause processor 402 to perform the following operations: receive a positioning request, the positioning request carrying at least the positioning fingerprint information of the object to be located scanned; determine whether the positioning request is a tunnel positioning request based on the positioning fingerprint information and the historical positioning information of the object to be located; if so, determine the position of the object to be located in the tunnel based on the positioning fingerprint information, the historical positioning information of the object to be located, and the corresponding fingerprint positioning features.

[0171] In an optional implementation, program 410 is further configured to cause processor 402, when determining whether the positioning request is a tunnel positioning request based on the positioning fingerprint information and the historical positioning location information of the object to be located, to determine whether the corresponding fingerprint device includes the pre-collected positioning fingerprint device of the tunnel based on the fingerprint device information included in the positioning fingerprint information; if it does, then to determine whether the request is a tunnel positioning request based on the positioning fingerprint information and the historical positioning location information of the object to be located.

[0172] In an optional implementation, program 410 is further configured to cause processor 402, when determining whether the request is a tunnel positioning request based on the positioning fingerprint information and the historical positioning information of the object, to construct determination feature data based on the positioning time and positioning type included in the positioning fingerprint information and the historical positioning information of the object; input the determination feature data into a pre-trained tunnel determination model, and have the tunnel determination model determine the probability that the request is a tunnel positioning request; if the probability is greater than a preset threshold, then the request is determined to be a tunnel positioning request.

[0173] In an optional implementation, program 410 is further configured to cause processor 402, when determining the location of the object to be located in the tunnel based on the positioning fingerprint information, the historical positioning location information of the object to be located, and the corresponding fingerprint positioning features, to acquire the fingerprint positioning features matched by the fingerprint device indicated by the positioning fingerprint information; construct positioning feature data based on the positioning fingerprint information, the historical positioning location information of the object including the positioning time, positioning type and positioning location, and the fingerprint positioning features; and input the positioning feature data into a pre-trained tunnel positioning model, so that the tunnel positioning model determines the location of the object to be located in the tunnel.

[0174] In an optional implementation, program 410 is further configured to cause processor 402, before receiving a positioning request, to determine the trajectory point in the sample tunnel based on the information of the trajectory point included in the historical trajectory data of the positioning object passing through the sample tunnel; and to determine the positioning fingerprint device corresponding to the sample tunnel and the fingerprint positioning feature of the positioning fingerprint device based on the location information of the trajectory point in the sample tunnel and the positioning fingerprint device indicated by the collected positioning fingerprint information.

[0175] In one optional implementation, the fingerprint positioning features of the positioning fingerprint device include the location information and / or signal strength information of the grid contained in the signal coverage area of ​​the positioning fingerprint device.

[0176] In an optional implementation, program 410 is further configured to cause processor 402 to determine the positioning fingerprint device corresponding to the sample tunnel based on the location information of the trajectory points in the sample tunnel and the positioning fingerprint device indicated by the collected positioning fingerprint information, and to determine the fingerprint positioning features of the positioning fingerprint device, thereby determining the positioning fingerprint device corresponding to the sample tunnel based on the positioning fingerprint information indicated by the positioning fingerprint information corresponding to the trajectory points in the sample tunnel; determining the signal coverage area of ​​the positioning fingerprint device based on the location information of the trajectory points in the sample tunnel with the same positioning fingerprint device; dividing the signal coverage area of ​​the positioning fingerprint device into a grid; determining the location information of the corresponding grid based on the location information of the trajectory points falling into the corresponding grid; and / or determining the signal strength information of the grid based on the signal strength information of the positioning fingerprint device in the positioning fingerprint information corresponding to the trajectory points falling into the corresponding grid.

[0177] The specific implementation of each step in procedure 410 can be found in the corresponding steps and units described in the above-described positioning method embodiments, and will not be repeated here. Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the devices and modules described above can be referred to the corresponding process descriptions in the aforementioned method embodiments, and will not be repeated here.

[0178] It should be noted that, depending on the implementation needs, the various components / steps described in the embodiments of this application can be broken down into more components / steps, or two or more components / steps or parts of the operation of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of this application.

[0179] The methods described in the embodiments of this application can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CD-ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or as computer code downloaded over a network that is originally stored in a remote recording medium or a non-transitory machine-readable medium and will be stored in a local recording medium. Thus, the methods described herein can be processed by software stored on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It is understood that the computer, processor, microprocessor controller, or programmable hardware includes storage components (e.g., RAM, ROM, flash memory, etc.) capable of storing or receiving software or computer code that, when accessed and executed by the computer, processor, or hardware, implements the positioning methods described herein. Furthermore, when a general-purpose computer accesses code used to implement the positioning methods shown herein, the execution of the code transforms the general-purpose computer into a dedicated computer for performing the positioning methods shown herein.

[0180] Those skilled in the art will recognize that the units and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented 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 embodiments of this application.

[0181] The above embodiments are only used to illustrate the embodiments of this application, and are not intended to limit the embodiments of this application. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the embodiments of this application. Therefore, all equivalent technical solutions also fall within the scope of the embodiments of this application, and the patent protection scope of the embodiments of this application should be defined by the claims.

Claims

1. A positioning method, comprising: receiving a positioning request carrying at least positioning fingerprint information scanned by a to-be-positioned object; determining whether the positioning request is a tunnel positioning request according to the positioning fingerprint information and historical positioning location information of the to-be-positioned object; if yes, obtaining fingerprint positioning features matched by a fingerprint device indicated by the positioning fingerprint information; constructing positioning feature data according to the positioning fingerprint information, the positioning time, the positioning type and the positioning location included in the historical positioning location information of the object, and the fingerprint positioning features; inputting the positioning feature data into a pre-trained tunnel positioning model to determine a location of the to-be-positioned object in the tunnel by the tunnel positioning model. The determination of whether the positioning request is a tunnel positioning request according to the positioning fingerprint information and the historical positioning location information of the to-be-positioned object comprises: determining whether the corresponding fingerprint device contains pre-acquired positioning fingerprint devices of the tunnel according to fingerprint device information included in the positioning fingerprint information; if yes, determining whether the request is a tunnel positioning request according to the positioning fingerprint information and the historical positioning location information of the to-be-positioned object. The determination of whether the request is a tunnel positioning request according to the positioning fingerprint information and the historical positioning location information of the to-be-positioned object comprises: constructing judgment feature data according to the positioning time and the positioning type included in the positioning fingerprint information and the historical positioning location information of the object; inputting the judgment feature data into a pre-trained tunnel judgment model to determine a probability that the request is a tunnel positioning request by the tunnel judgment model, and determining that the request is a tunnel positioning request if the probability is greater than a preset threshold. Before receiving the positioning request, the method further comprises: determining a trajectory point in a sample tunnel according to information of the trajectory point included in historical trajectory data of a positioning object passing through the sample tunnel; determining the positioning fingerprint device corresponding to the sample tunnel and determining fingerprint positioning features of the positioning fingerprint device according to location information of the trajectory point in the sample tunnel and positioning fingerprint devices indicated by acquired positioning fingerprint information. The fingerprint positioning features of the positioning fingerprint device comprise location information and / or signal strength information of a grid included in a signal coverage area of the positioning fingerprint device. The determination of the positioning fingerprint device corresponding to the sample tunnel and the determination of the fingerprint positioning features of the positioning fingerprint device according to the location information of the trajectory point in the sample tunnel and the positioning fingerprint devices indicated by acquired positioning fingerprint information comprises: determining the positioning fingerprint device corresponding to the sample tunnel according to the positioning fingerprint device indicated by the positioning fingerprint information corresponding to the trajectory point in the sample tunnel; determining the signal coverage area of the positioning fingerprint device according to location information of the trajectory point in the sample tunnel acquiring the same positioning fingerprint device; dividing the signal coverage area of the positioning fingerprint device into a grid. ​ ​ ​ ​ ​ 2. The method of claim 1, wherein, ​ ​ ​ 3. The method of claim 2, wherein, ​ ​ ​ 4. The method of claim 2 or 3, wherein, ​ ​ ​ 5. The method of claim 4, wherein, ​ 6. The method of claim 5, wherein, ​ ​ ​ ​ According to position information of the trajectory points falling into the corresponding grid, position information of the corresponding grid is determined, and / or according to signal strength information of the positioning fingerprint device in the positioning fingerprint information corresponding to the trajectory points falling into the corresponding grid, signal strength information of the grid is determined.

7. A positioning apparatus, comprising: a receiving module configured to receive a positioning request carrying at least positioning fingerprint information scanned by a to-be-positioned object; a first determining module configured to determine whether the positioning request is a tunnel positioning request according to the positioning fingerprint information and historical positioning position information of the to-be-positioned object; a second determining module configured to, if yes, acquire a fingerprint positioning feature matched by a fingerprint device indicated by the positioning fingerprint information; construct positioning feature data according to the positioning fingerprint information, the positioning time, the positioning type and the positioning position included in the historical positioning position information of the object, and the fingerprint positioning feature; input the positioning feature data into a pre-trained tunnel positioning model, and determine a position of the to-be-positioned object in the tunnel according to the tunnel positioning model.

8. An electronic device comprising: a processor, a memory, a communication interface and a communication bus, the processor, the memory and the communication interface performing communication with each other through the communication bus; the memory is configured to store at least one executable instruction, and the executable instruction causes the processor to perform operations corresponding to the positioning method in any one of claims 1-6.

9. A computer storage medium having a computer program stored thereon, the program being executed by a processor to implement the positioning method in any one of claims 1-6.

Images