Positioning method, apparatus, device, storage medium, and product

Abstract

The application discloses a positioning method, device, equipment, storage medium and product, and belongs to the computer technical field.The method comprises the following steps: acquiring station fingerprint information corresponding to at least one traffic station; acquiring target base station information corresponding to a target positioning point; matching the target base station information with the station fingerprint information, generating matching data corresponding to the target base station information and the at least one traffic station; and determining a target traffic station matched by the target positioning point based on the matching data.The technical scheme provided by the embodiment of the application can be applied to the field of maps, the base station information corresponding to the positioning point is matched with the station fingerprint capable of representing the characteristics of the base station, the station positioning is realized, the problem of inaccurate station positioning caused by factors such as weak satellite navigation positioning signals or few station wireless local area network distributions can be avoided, and the accuracy, timeliness and flexibility of the station positioning are improved.

Description

Technical Field

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

[0002] Subways are a very common mode of transportation in people's daily lives. Since subways usually operate underground or indoors, GPS (Global Positioning System) positioning cannot accurately locate users in the subway.

[0003] In related technologies, the location of a subway station is determined by comparing the Wi-Fi signals scanned by the terminal in the subway with manually collected Wi-Fi signals from the subway station. However, in reality, there are few available Wi-Fi networks in subway stations, and the terminal scans Wi-Fi networks at a low frequency. Therefore, the accuracy, timeliness, and flexibility of the above-mentioned technologies for station location are poor. Summary of the Invention

[0004] This application provides a positioning method, apparatus, device, storage medium, and product that can improve the accuracy, timeliness, and flexibility of site positioning.

[0005] According to one aspect of the embodiments of this application, a positioning method is provided, the method comprising:

[0006] Obtain site fingerprint information corresponding to at least one transportation station, wherein the site fingerprint information is used to characterize the base station features associated with the at least one transportation station;

[0007] Obtain the target base station information corresponding to the target location point;

[0008] The target base station information is matched with the site fingerprint information to generate matching data between the target base station information and the at least one transportation station. The matching data is used to characterize the degree of matching between the target base station information and the at least one transportation station.

[0009] Based on the matching data, the target transportation station matching the target location point is determined.

[0010] According to one aspect of the embodiments of this application, a positioning device is provided, the device comprising:

[0011] A site fingerprint acquisition module is used to acquire site fingerprint information corresponding to at least one transportation station, wherein the site fingerprint information is used to characterize the base station features associated with the at least one transportation station.

[0012] The base station information acquisition module is used to acquire the target base station information corresponding to the target positioning point;

[0013] A site matching module is used to match the target base station information with the site fingerprint information to generate matching data between the target base station information and the at least one transportation station. The matching data is used to characterize the degree of matching between the target base station information and the at least one transportation station.

[0014] The station determination module is used to determine the target transportation station that matches the target location point based on the matching data.

[0015] According to one aspect of the embodiments of this application, a computer device is provided, the computer device including a processor and a memory, the memory storing at least one instruction, at least one program, code set or instruction set, the at least one instruction, the at least one program, the code set or instruction set being loaded and executed by the processor to implement the above-described positioning method.

[0016] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, wherein at least one instruction, at least one program, code set, or instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the above-described positioning method.

[0017] According to one aspect of the embodiments of this application, a computer program product is provided, the computer program product including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform to implement the above-described positioning method.

[0018] The technical solution provided in this application can bring the following beneficial effects:

[0019] By acquiring site fingerprint information that characterizes the base station features associated with transportation stations, and target base station information corresponding to the target location point, and matching the target base station information with the site fingerprint information of at least one transportation station, matching data reflecting the degree of matching between the target base station information and at least one transportation station can be determined. Based on this matching data, the target transportation station matching the target location point can be identified. By matching the base station information corresponding to the location point with the site fingerprint that characterizes the base station features, site positioning can be achieved. This avoids the problem of inaccurate site positioning caused by weak satellite navigation signals or limited wireless local area network distribution, improving the accuracy, timeliness, and flexibility of site positioning. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of an application runtime environment provided in one embodiment of this application;

[0022] Figure 2 This is a flowchart of a positioning method provided in one embodiment of this application. Figure 1 ;

[0023] Figure 3 This is a flowchart of a positioning method provided in one embodiment of this application. Figure 2 ;

[0024] Figure 4 An example diagram illustrating a user trajectory is shown;

[0025] Figure 5 An exemplary diagram illustrates a method for constructing site fingerprint information based on base station information sequences;

[0026] Figure 6 This is a flowchart of a positioning method provided in one embodiment of this application. Figure 3 ;

[0027] Figure 7 This is a flowchart of a positioning method provided in one embodiment of this application. Figure 4 ;

[0028] Figure 8 An exemplary schematic diagram for determining sequence matching scores is shown;

[0029] Figure 9 This is a flowchart of a positioning method provided in one embodiment of this application. Figure 5 ;

[0030] Figure 10 An exemplary schematic diagram of a transportation station route is shown;

[0031] Figure 11 An exemplary diagram of a page with optimized positioning is shown;

[0032] Figure 12 This is a block diagram of a positioning device provided in one embodiment of this application;

[0033] Figure 13 This is a structural block diagram of a computer device provided in one embodiment of this application. Detailed Implementation

[0034] The technical solutions provided in this application can be applied to the fields of mapping and transportation. A brief description is given below to facilitate understanding by those skilled in the art.

[0035] Intelligent Traffic Systems (ITS), also known as Intelligent Transportation Systems, effectively integrate advanced technologies (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operations research, artificial intelligence, etc.) into transportation, service control, and vehicle manufacturing. This strengthens the connection between vehicles, roads, and users, thereby forming a comprehensive transportation system that ensures safety, improves efficiency, enhances the environment, and conserves energy.

[0036] Intelligent Vehicle Infrastructure Cooperative Systems (IVICS) are a development direction of Intelligent Transportation Systems (ITS). IVICS utilizes advanced wireless communication and next-generation Internet technologies to implement comprehensive, real-time dynamic information exchange between vehicles and infrastructure. Based on the collection and fusion of dynamic traffic information across all times and spaces, it conducts active vehicle safety control and cooperative road management, fully realizing effective collaboration between people, vehicles, and roads. This ensures traffic safety, improves traffic efficiency, and ultimately forms a safe, efficient, and environmentally friendly road traffic system.

[0037] The positioning method provided in this application embodiment can be applied to the above-mentioned intelligent transportation system or intelligent vehicle-road cooperative system to achieve accurate positioning of transportation stations.

[0038] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0039] Please refer to Figure 1 This diagram illustrates an application runtime environment provided in one embodiment of this application. The application runtime environment may include: terminal 10 and server 20.

[0040] Terminal 10 includes, but is not limited to, electronic devices such as mobile phones, computers, smart voice interaction devices, smart home appliances, in-vehicle terminals, game consoles, e-book readers, multimedia playback devices, and wearable devices. Application clients can be installed on terminal 10.

[0041] In this embodiment, the application described above can be any application capable of providing location services. Typically, the application is a map application. Of course, other types of applications besides map applications can also provide location services. For example, social applications, interactive entertainment applications, browser applications, shopping applications, content sharing applications, virtual reality (VR) applications, augmented reality (AR) applications, etc., are not limited in this embodiment. Optionally, the terminal 10 runs a client of the above-mentioned application.

[0042] Server 20 provides background services to clients of applications in terminal 10. For example, server 20 can be a background server for the aforementioned applications. Server 20 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Optionally, server 20 can simultaneously provide background services to applications in multiple terminals 10.

[0043] Optionally, terminal 10 and server 20 can communicate with each other via network 30. Terminal 10 and server 20 can be directly or indirectly connected via wired or wireless communication, which is not limited herein. In this embodiment, terminal 10 can be connected to network 30 via a base station.

[0044] Before introducing the method embodiments provided in this application, a brief introduction will be given on the application scenarios, related terms or nouns that may be involved in the method embodiments of this application, so as to facilitate the understanding of those skilled in the art.

[0045] WiFi (Wireless Networking Technology): Enables network-connectable devices to connect to each other wirelessly. WiFi access points deployed in shopping malls, office buildings, and residential buildings provide internet access.

[0046] MAC (Media Access Control Address): A unique identifier for WiFi.

[0047] WiFi positioning: A method of spatial positioning that uses the WiFi signal field searched by the terminal. During positioning, the mobile phone scans to obtain the MAC list of surrounding WiFi devices and signal strength information, and uploads the information to the positioning server for positioning. The positioning accuracy is about 10 to 200 meters.

[0048] WiFi fingerprint: A unique WiFi network for each physical location, containing a list of scanned WiFi networks and their signal strength distribution information.

[0049] GPS positioning system: A satellite navigation and positioning system developed by the United States in the 1970s. Its basic principle is to measure the distance between satellites at known locations and the user's receiver, and then combine the data from multiple satellites to locate the receiver.

[0050] Location request: The data used to send to the server for location verification consists of information such as WiFi, Bluetooth, base station and GPS scanned by mobile devices and other terminal devices.

[0051] Base station: A public mobile communication base station is an interface device for mobile devices to access the Internet. It is also a type of radio station, which refers to a radio transceiver station that transmits information between a mobile communication switching center and a mobile phone terminal within a certain radio coverage area.

[0052] Base station positioning: a method of spatial positioning using base station signals searched by mobile phones. During positioning, the mobile phone scans to obtain information about surrounding base stations and uploads the information to the positioning server for positioning. The positioning accuracy is approximately 100 to 500 meters.

[0053] Please refer to Figure 2 It illustrates the flow of a positioning method provided in one embodiment of this application. Figure 1 This method can be applied to computer devices, which refer to electronic devices with data computing and processing capabilities. For example, the entity executing each step can be... Figure 1 The application runtime environment shown is server 20. The method may include the following steps (210-240).

[0054] Step 210: Obtain the station fingerprint information corresponding to at least one transportation station.

[0055] The aforementioned transportation stations include, but are not limited to, subway stations, transportation stations inside tunnels, and transportation stations inside mines. In some application scenarios, these transportation stations are typically located in underground or enclosed environments with weak GPS signals.

[0056] Site fingerprint information is used to characterize the base station features associated with at least one transportation station. Using the site fingerprint information based on base station features, a base station-based transportation station location method can be achieved. In some network positioning scenarios, a WiFi-based positioning scheme can be used. However, WiFi-based positioning schemes typically rely heavily on the WiFi signals scanned by the terminal and the frequency of those scans. For scenarios where the transportation station is a subway station, the aforementioned WiFi-based positioning scheme can only cover a limited number of subway stations. For stations that cannot be covered by the WiFi-based positioning scheme, the aforementioned site fingerprint information based on base station features can be used to locate these stations.

[0057] Optionally, the aforementioned site fingerprint information may further include at least one Wi-Fi feature associated with a transportation station. Site location can also be achieved through these Wi-Fi features; however, in situations where available Wi-Fi signals at transportation stations are scarce, or where the update time of the scanned Wi-Fi list is limited, site location can be achieved using the aforementioned base station features. This is because, under conditions of limited available Wi-Fi signals at transportation stations, the terminal scans limited Wi-Fi signal information, making Wi-Fi location impossible. Furthermore, with updates to mobile phone operating systems, the frequency of Wi-Fi scan list updates decreases. It is highly likely that the terminal will not have Wi-Fi updates at the user's stopover point, leading to location errors. Optionally, site fingerprints based on the aforementioned Wi-Fi features can be constructed through manual collection or based on historical data.

[0058] The base station features or WiFi features in the above-mentioned site fingerprint information can be selected according to different site conditions to achieve site positioning from multiple aspects.

[0059] This application's embodiments primarily use base station information as sample data for constructing fingerprints. However, site fingerprint information is not limited to base station information; it can also include other application information from the terminal, such as QR code scanning information as the initial site information. It can also include operational information within the site, such as transportation time and user movement status. Furthermore, site fingerprint information can also include multimodal environmental information such as sound information within the transportation station. Based on this environmental information, a unique correspondence between the user's location and the transportation station can be established, thereby achieving site-level positioning.

[0060] In an exemplary embodiment, the site fingerprint information includes pairing information between the transportation station corresponding to the site fingerprint information and at least one base station. Accordingly, as... Figure 3 As shown, the implementation process of step 210 above includes the following steps (211-213). Figure 3 The flowchart of a positioning method provided in one embodiment of this application is shown. Figure 2 .

[0061] Step 211: Obtain historical trajectory data corresponding to at least one user account.

[0062] Historical trajectory data includes base station information and traffic stop identification information corresponding to at least one historical trajectory point. The base station information corresponding to a historical trajectory point refers to the base station information scanned or connected to by the terminal at that historical trajectory point. Optionally, the base station information includes base station identification information and base station signal strength information.

[0063] Map navigation is a typical application scenario in the embodiments of this application. In map navigation scenarios, many users use subway route planning and travel according to the plan, generating a large amount of historical trajectory data, which provides a good data foundation for base station mining based on subway trajectory.

[0064] In an exemplary embodiment, trajectory matching is performed based on the planned subway trajectory within the target time period and the actual trajectory corresponding to the planned subway trajectory. Some abnormal trajectory points in the actual trajectory are eliminated, and the user's real trajectory is mined to obtain the historical trajectory data corresponding to at least one user account.

[0065] In one example, such as Figure 4 As shown, it exemplifies a schematic diagram of a user trajectory. Figure 4 The map navigation page 40 shows the planned route 43 (thick solid line) from "Zhenru" subway station 41 to "Jiangning Road" subway station 42 and the actual positioning trajectory route 44 (thick dashed line). Among them, the multiple positioning points 45 on the positioning trajectory route 44 are positioning points reported during the journey. The positioning request reported by the terminal at each positioning point includes the base station information corresponding to the terminal at the positioning point.

[0066] The following lists the trajectory data corresponding to several historical trajectories to facilitate understanding by those skilled in the art. T1, T2, T3, and T4 are four trajectories, and the corresponding trajectory data and scanned base station information for each are as follows:

[0067] T1={S1: (Wi, Ri), S2: (Wi, Ri), S3: (Wj, Rj)};

[0068] T2={S2: (Wj, Rj), S3: (Wk, Rk), S4: (Wl, Rl)};

[0069] T3={S3: (Wk, Rk), S2: (Wj, Rj), S1: (Wi, Ri)};

[0070] T4={S4: (Wl, Rl), S3: (Wl, Rl), S2: (Wk, Rk)}.

[0071] Where T represents the user's trajectory, S represents a transportation station, W represents a base station, and R represents the base station signal strength. S1, S2, S3, and S4 are four different transportation stations, corresponding to four trajectory location points. Wi is the base station identifier corresponding to base station i, Ri is the base station signal strength of base station i at the corresponding location point, Wj is the base station identifier corresponding to base station j, Rj is the base station signal strength of base station j at the corresponding location point, Wk is the base station identifier corresponding to base station k, Rk is the base station signal strength of base station k at the corresponding location point, and Wl is the base station identifier corresponding to base station l, Rl is the base station signal strength of base station l at the corresponding location point. Note that if the user's terminal scans the same base station Wi, the user's location may be at subway station S1 or S2.

[0072] Step 212: Based on the base station information and traffic station identification information corresponding to at least one historical trajectory point, determine the pairing information between at least one traffic station and its corresponding historical paired base station.

[0073] Pairing information is used to characterize the pairing status between traffic stops and base stations. This information includes the base station information and the number of pairings for historically paired base stations. The base station information includes base station identification information and base station signal strength information.

[0074] The aforementioned historical trajectory points correspond to two types of information: one is the base station information scanned by the terminal at the historical trajectory point, and the other is the location result corresponding to the historical trajectory point, i.e., the traffic station identification information corresponding to the historical trajectory point. The aforementioned historical paired base station refers to the base station that has been paired with a traffic station. For example, S1:(Wi, Ri) in T1 above refers to the base station information (Wi, Ri) scanned by the first trajectory point in the terminal's T1 trajectory, and the traffic station S1 corresponding to the first trajectory point, respectively.

[0075] In the example of the four trajectories T1, T2, T3, and T4 mentioned above, the pairing information between traffic stations S1, S2, S3, and S4 and their respective historical paired base stations can be determined by using the trajectory data of T1, T2, T3, and T4. The pairing information for transportation station S1 includes historical base station information (Wi, Ri) that has been paired with transportation station S1, and the number of times they have been paired (1 time in T1 and 1 time in T3). The pairing information for transportation station S2 includes historical base station information (Wi, Ri), (Wj, Rj), and (Wk, Rk) that has been paired with transportation station S2, and the number of times they have been paired (1 time, 2 times, and 1 time), respectively. The pairing information for transportation station S3 includes historical base station information (Wj, Rj), (Wk, Rk), and (Wl, Rl) that has been paired with transportation station S3, and the number of times they have been paired (1 time, 2 times, and 1 time), respectively. The pairing information for transportation station S3 includes historical base station information (Wl, Rl) that has been paired with transportation station S4, and the number of times they have been paired (2 times). Step 213: Based on the base station information and pairing counts of the historically paired base stations, generate site fingerprint information corresponding to at least one transportation station.

[0076] The site fingerprint information corresponding to each transportation station mainly includes the base station identifier W that has been paired with that transportation station, the signal strength R, and the number of pairings N, in the format (W, R, N). Here, the signal strength R can be represented by the average signal strength, or it can be represented by other relevant information; this embodiment of the application does not limit this. Optionally, the number of pairings N can be converted into the matching observation probability, which will be explained in the following content.

[0077] In one example, such as Figure 5 As shown, it exemplifies a schematic diagram of constructing site fingerprint information based on base station information sequences. Figure 5 The data reflects the positional relationship between the trajectory points of each of the four trajectories T1, T2, T3, and T4 and the transportation stations S1, S2, S3, and S4.

[0078] In the example of the four trajectories T1, T2, T3, and T4 above, the site fingerprint information for each of the transportation stations S1, S2, S3, and S4 can be constructed using their respective pairing information, namely, their respective historical paired base station information and the corresponding number of pairings. Based on the trajectory data of the four trajectories T1, T2, T3, and T4, the constructed site fingerprints for each of the transportation stations S1, S2, S3, and S4 are as follows:

[0079] S1 = {(Wi, Ri, 2)};

[0080] S2={(Wi, Ri, 1), (Wj, Rj, 2), (Wk, Rk, 1)};

[0081] S3={(Wj, Rj, 1), (Wk, Rk, 2), (Wl, Rl, 1)};

[0082] S4 = {(Wl, Rl, 2)}.

[0083] In an exemplary embodiment, the site fingerprint information includes the matching observation probability corresponding to historically paired base stations, where the matching observation probability characterizes the degree of location matching between the base station and the traffic station. Optionally, normalizing the number of pairings in the site fingerprint information can yield the matching observation probability corresponding to each historically paired base station. Accordingly, as... Figure 6 As shown, the implementation process of step 213 above includes the following steps (213a~213c), Figure 6 The flowchart of a positioning method provided in one embodiment of this application is shown. Figure 3 .

[0084] Step 213a: Determine the total number of pairings for each of the at least one transportation station based on the number of pairings between each transportation station and its corresponding historical pairing base station.

[0085] For any transportation station, the number of pairings between that transportation station and its corresponding historical matching base station can be obtained from its station fingerprint information. By summing these pairing counts from the station fingerprint information, the total number of pairings for that transportation station can be obtained. Performing the above operation for each transportation station will yield the total number of pairings for at least one transportation station.

[0086] From the site fingerprints corresponding to each of the aforementioned transportation stations S1, S2, S3, and S4, the number of pairings between each station and its corresponding historical base station information can be determined. For example, the pairing count between transportation station S1 and its corresponding historical base station information is 2; the pairing counts between transportation station S2 and its corresponding historical base station information are 1, 2, and 1 respectively; the pairing counts between transportation station S3 and its corresponding historical base station information are 1, 2, and 1 respectively; and the pairing count between transportation station S4 and its corresponding historical base station information is 2. Summing up the pairing counts between transportation stations S1, S2, S3, and S4 and their corresponding historical base station information yields the total pairing counts for each station. For example, the total pairing count for S1 is 2, for S2 it is 4, for S3 it is 4, and for S4 it is 4.

[0087] Step 213b: Divide the number of pairings corresponding to the historical pairing base stations by the total number of pairings to obtain the matching observation probability corresponding to the historical pairing base stations.

[0088] The matching observation probability here is the probability obtained by counting and normalizing the number of pairings between each transportation station and base station information when all users scan base station information at any subway station Sα within the target time period. Here, α represents the index of any transportation station. In this practical application, the spatial relationship between base stations and transportation stations is fixed, so we can assume that the matching observation probability is time-independent; that is, the probability that a user observes a certain base station at a certain transportation station is constant. Therefore, the matching observation probability characterizes the degree of location matching between base stations and transportation stations. The higher the number of pairings between a transportation station and a base station, the greater the matching observation probability, indicating that the spatial distance between the transportation station and the base station is closer, and the more reliable the positioning accuracy.

[0089] In the site fingerprints corresponding to the above-mentioned transportation stations S1, S2, S3, and S4, the number of pairings corresponding to each historical paired base station in the site fingerprint can be divided by the total number of pairings corresponding to the site fingerprint, thereby normalizing the number of pairings and obtaining the matching observation probability corresponding to each historical paired base station.

[0090] In an exemplary embodiment, historical trajectory data within the target time period can be used to determine mapping data between at least one transportation station and at least one base station. For example, the pairing information between each transportation station and its corresponding historically paired base station can be used. Based on the number of pairings between each transportation station and each base station, the matching observation probability of each base station at each transportation station can be determined, and an observation probability matrix can be constructed. The formula for determining the matching observation probability is as follows:

[0091]

[0092] in, This indicates that at time t, the user is at transportation station S. α Scanned to base station W i The probability, P(W) i |S α ) indicates transportation station S α With base station W i The probability of matching observations between them. Optionally, P(W) i |S α It can be obtained from the observation probability matrix.

[0093] Step 213c: Based on the base station information and matching observation probability corresponding to the historical paired base stations, generate site fingerprint information corresponding to at least one traffic station.

[0094] Optionally, the base station information and the corresponding matching observation probability corresponding to each historical paired base station can be combined on a base station basis to obtain the station fingerprint information corresponding to each traffic station.

[0095] Taking transportation station S2 as an example, the specific process of optimizing the site fingerprint information corresponding to S2 is as follows: the number of matches in the site fingerprint information {(Wi, Ri, 1), (Wj, Rj, 2), (Wk, Rk, 1)} of transportation station S2 is normalized to obtain the matching observation probability corresponding to each historical paired base station of transportation station S2, and the number of matches is updated to the matching observation probability to obtain the optimized site fingerprint information {(Wi, Ri, 0.25), (Wj, Rj, 0.5), (Wk, Rk, 0.25)} of S2.

[0096] The above normalization operation can be applied to each transportation station to obtain the optimized station fingerprint information. In the example above, by normalizing the number of pairings of the station fingerprints corresponding to each of the above transportation stations S1, S2, S3, and S4, the optimized station fingerprint information corresponding to each of the transportation stations S1, S2, S3, and S4 is as follows:

[0097] S1 = {(Wi, Ri, 1)};

[0098] S2={(Wi, Ri, 0.25), (Wj, Rj, 0.5), (Wk, Rk, 0.25)};

[0099] S3={(Wj, Rj, 0.25), (Wk, Rk, 0.5), (Wl, Rl, 0.25)};

[0100] S4 = {(Wl, Rl, 1)}.

[0101] The site fingerprint information for each transportation station includes the base station information of the historical paired base stations corresponding to that transportation station and the corresponding matching observation probability.

[0102] In this embodiment, base station fingerprints of transportation stations are mined based on the historical location log trajectories of a large number of users. Base stations are associated with transportation stations, supporting an indefinite association between a base station and a transportation station. A base station may be associated with multiple transportation stations, and a transportation station may be associated with multiple base stations. By calculating the posterior probability of a base station appearing at a given station in the trajectory and the prior transition probability between transportation stations, base station and subway station mapping data is generated, and station fingerprints based on base station features are determined, thereby improving the accuracy of station positioning.

[0103] In some applications, base stations are classified as site base stations and non-site base stations. If a terminal is connected to a site base station, the terminal's location can be updated to the transportation station bound to that site base station. However, in real-world scenarios, base station positioning itself has a large coverage area, and a user's route can scan the same base station at multiple stations. This means a base station may be associated with multiple stations, and a station may be associated with multiple base stations. Simply classifying base stations as site base stations or non-site base stations for site positioning results in low accuracy of the mined base station locations, easily leading to misjudgments, delayed site location updates, and positioning errors. For example, if a base station is located between two subway stations, directly returning the result of a single-point request will not reflect the route information, causing positioning errors for adjacent stations.

[0104] The present application embodiment uses the probability of occurrence in the trajectory to characterize the relationship between the base station and the traffic station, which is more reasonable. The station fingerprint information can more comprehensively measure the characteristics of the base station corresponding to the traffic station.

[0105] Step 220: Obtain the target base station information corresponding to the target positioning point.

[0106] In one possible implementation, the receiving terminal sends a location request, which includes target base station information corresponding to the aforementioned target location point.

[0107] In an exemplary embodiment, the target base station information includes a base station information sequence, which includes base station information corresponding to the terminal at at least one location point, and the at least one location point includes the target location point. The at least one location point including the target location point may further include a preset number of preceding location points corresponding to the target location point. Optionally, the target location point is the last location point among the at least one location points, and the base station information corresponding to the target location point in the base station information sequence is the last item of base station information.

[0108] Base station information includes base station identification information and base station signal strength information.

[0109] The following is a specific sequence of base station information to facilitate understanding by those skilled in the art.

[0110] In one possible application scenario, the terminal sends a location request to the server. The location request includes a sequence of base station information T5 scanned by the terminal at at least one location point along the user's current trajectory, where T5 = {Wi, Wj, Wk, Wl}. Here, Wi, Wj, Wk, and Wl are the base station identifiers corresponding to base station i, base station j, base station k, and base station l, respectively.

[0111] Step 230: Match the target base station information with the site fingerprint information to generate matching data between the target base station information and at least one transportation station.

[0112] Matching data is used to characterize the degree of matching between target base station information and at least one transportation station.

[0113] Optionally, the target base station information can also be the base station information corresponding to the target location point. The base station information corresponding to the target location point is matched with the site fingerprint information to obtain the number of matches or the probability of matching between the target base station information and each traffic station, i.e., the matching data mentioned above. Then, the traffic station with the highest number of matches or the highest probability of matching can be used as the location result.

[0114] In an exemplary embodiment, the target base station information includes a base station information sequence, which includes base station information corresponding to the terminal at at least one location point, where at least one location point includes the target location point. The site fingerprint information includes pairing information between the traffic station corresponding to the site fingerprint information and at least one base station. Accordingly, as... Figure 3 As shown, the implementation process of step 230 above includes the following steps (231-232).

[0115] Step 231: Based on the pairing information between the base station information and at least one traffic station, determine at least one candidate station sequence corresponding to the base station information sequence.

[0116] At least one candidate site sequence includes candidate traffic sites that have been paired with base station information corresponding to at least one location point.

[0117] In an exemplary embodiment, the aforementioned base station information sequence can be used as the base station observation sequence corresponding to the historical base station and the current base station. The Viterbi algorithm, which is inferred by the Hidden Markov Model (HMM), can find the candidate site sequence most likely to correspond to the observation result (base station information sequence).

[0118] In an exemplary embodiment, such as Figure 6 As shown, the implementation process of step 231 above includes the following steps (2311 to 2312).

[0119] Step 2311: Based on the pairing information corresponding to at least one transportation station, determine the transportation stations that have been paired with the base station information among the at least one transportation station as candidate transportation stations corresponding to at least one positioning point.

[0120] In one possible implementation, the base station information sequence can be constructed based on the base station information scanned by the terminal at at least one location point. Then, the traffic stations that have been paired with each base station information in the base station information sequence are used as candidate traffic stations for each location point corresponding to each base station information. In this way, at least one candidate traffic station can be determined for each location point.

[0121] In another possible implementation, the at least one location point includes a target location point and a preceding location point that has been located before the target location point. Since the preceding location point has already been located, the preceding traffic station corresponding to the preceding location point can be determined. For the target location point, the base station information scanned by the terminal at the target location point can be matched with the pairing information corresponding to at least one traffic station, and the traffic station that has been paired with the base station information of the target location point can be used as the candidate traffic station corresponding to the target location point.

[0122] Step 2312: Arrange and combine the candidate transportation stations to obtain at least one candidate station sequence.

[0123] In one possible implementation, after obtaining at least one candidate traffic station corresponding to each of the above positioning points, the candidate traffic stations corresponding to each positioning point are arranged and combined according to the position order of the positioning points to obtain at least one candidate station sequence corresponding to the base station information sequence.

[0124] In another possible implementation, after obtaining the candidate traffic stations and preceding traffic stations corresponding to the target location point, the preceding traffic stations and the candidate traffic stations corresponding to the target location point can be combined to obtain at least one candidate station sequence.

[0125] Based on the examples of T1, T2, T3, T4, and T5 above, for the base station information sequence T5 included in the current location request, the candidate site sequence corresponding to the base station information sequence T5 can be determined according to the site fingerprint information of the traffic stations S1, S2, S3, and S4 determined by the four trajectories T1, T2, T3, and T4. For example, candidate site sequences such as S1->S2->S3->S4; S2->S3->S3->S4; and S1->S2->S3->S3 can be determined.

[0126] Step 232: Match the base station information with the site fingerprint information corresponding to the candidate traffic stations to obtain sequence matching data between the base station information sequence and at least one candidate site sequence.

[0127] The aforementioned matching data includes sequence matching data, which includes a sequence matching score between a base station information sequence and at least one candidate site sequence. The sequence matching score is used to characterize the degree of matching between the base station information sequence and the candidate site sequence.

[0128] This application embodiment can not only match the base station information of a single location point scanned by the user with the site fingerprint information, but also match the scanned base station information sequence with the site fingerprint information. At the same time, it performs subway positioning based on single base station and continuous base station algorithms to ensure the accuracy of site positioning.

[0129] After determining the above candidate site sequence, matching can be performed based on the constructed site fingerprint information. In this embodiment, the matching process has the following specific implementation methods.

[0130] In one possible implementation, such as Figure 7 As shown, one implementation of step 232 above includes the following steps (2321-2322). Figure 7 The flowchart of a positioning method provided in one embodiment of this application is shown. Figure 4 .

[0131] Step 2321: Obtain the number of pairings between base station information and candidate traffic stations from the site fingerprint information corresponding to the candidate traffic stations.

[0132] The number of times the above base station information is paired with candidate traffic stations can be obtained by statistically analyzing historical trajectory data within the target time period.

[0133] The site fingerprint information corresponding to the candidate traffic station includes historical base station information that has been paired with the candidate traffic station and the number of pairings corresponding to the historical base station information. Since the candidate traffic station is determined based on historical pairing relationships, the candidate traffic station corresponding to each location point in the candidate site sequence is a traffic station that has been paired with the base station information corresponding to that location point. Therefore, the number of pairings between the current base station information and the candidate traffic station can be obtained from the number of pairings corresponding to each historical base station information in the site fingerprint information corresponding to the candidate traffic station.

[0134] Traverse each base station information in the base station information sequence and the candidate traffic stations corresponding to each base station information to obtain the number of pairings between each candidate traffic station in each candidate station sequence and the base station information at the corresponding position in the base station information sequence.

[0135] Step 2322: Based on the number of pairings, determine the sequence matching score between the base station information sequence and at least one candidate site sequence.

[0136] The sequence matching data includes a sequence matching score, which is used to characterize the degree of matching between the base station information sequence and the candidate site sequence.

[0137] The number of pairings between each candidate traffic station in each candidate station sequence and the corresponding base station information in the base station information sequence is summed to obtain the sequence matching score between each candidate station sequence and the base station information sequence.

[0138] Alternatively, the formula for determining the sequence matching score based on the number of pairings is as follows:

[0139] F=∑N(S α Wi (2)

[0140] Where F is the sequence matching score, N(S) α W i W is the base station identifier of base station i. i At transportation station S α The number of pairings corresponding to the site fingerprint information.

[0141] In one example, such as Figure 8 As shown, this example illustrates a schematic diagram for determining sequence matching scores. In the above example, the site fingerprint information corresponding to traffic stations S1, S2, S3, and S4 can be determined from four trajectories T1, T2, T3, and T4. For the base station information sequence T5, the device constructs a corresponding candidate site sequence based on the historical paired sites of the base station information in T5. Following Formula 2, it dynamically traverses from the first observation point base station identifier Wi in T5 to the last base station identifier Wl, determining the number of pairings between each base station identifier and the candidate traffic station at the corresponding position in each candidate site sequence, thereby obtaining the sequence matching score for each candidate site. After comparison, the candidate site sequence with the highest sequence matching score under the observation sequence T5 is selected as S1->S2->S3->S4, with a corresponding highest sequence matching score of 8. Specifically, the number of pairings between base station identifier Wi and S1 is 2, the number of pairings between base station identifier Wj and S2 is 2, the number of pairings between base station identifier Wk and S3 is 2, and the number of pairings between base station identifier Wl and S4 is 2, totaling 8. In the base station information sequence T5, the target location point is the location point corresponding to the last base station identifier Wl. The traffic station corresponding to Wl in the station sequence is S4. Therefore, the user's target location point can be located at traffic station S4.

[0142] Optionally, the base station information includes base station signal strength information; correspondingly, such as Figure 9 As shown, step 2322 above can be replaced by step 2322a. Figure 9 The flowchart of a positioning method provided in one embodiment of this application is shown. Figure 5 .

[0143] Step 2322a: Based on the number of pairings and the base station signal strength information, determine the sequence matching score between the base station information sequence and at least one candidate site sequence.

[0144] Optionally, the weight value corresponding to the number of pairings is determined based on the base station signal strength information, and the sequence matching score between the base station information sequence and at least one candidate site sequence is determined based on the number of pairings and the weight value corresponding to the number of pairings.

[0145] Optionally, the formula for determining the sequence matching score based on the number of pairings and the base station signal strength is as follows:

[0146]

[0147] Where F is the sequence matching score, N(S) α W i W is the base station identifier of base station i. i At transportation station S α The number of pairings corresponding to the site fingerprint information, R i For base station signal strength, These are weight values ​​calculated based on signal strength; the stronger the signal, the larger the weight value.

[0148] In another possible implementation, the site fingerprint information also includes the matching observation probability between the traffic station corresponding to the site fingerprint information and at least one base station, where the matching observation probability is used to characterize the degree of location matching between the base station and the traffic station; correspondingly, such as Figure 6 As shown, another implementation of step 232 above includes the following steps (232a to 232c).

[0149] Step 232a: Obtain the station transfer probability between adjacent candidate traffic stations in at least one candidate station sequence.

[0150] The station transfer probability is determined based on the connection path between transportation stations.

[0151] In one possible implementation, the station transition probability between adjacent candidate transportation stations in each candidate station sequence is obtained from the station transition probability matrix. This station transition probability matrix can be determined by the connection path corresponding to at least one transportation station.

[0152] For any given transportation station, identify the adjacent transportation stations with accessible connecting paths. Based on the connection relationships between the current transportation station and its adjacent stations, determine the weight information from the current transportation station to its adjacent stations. Optionally, the weight information from the current transportation station to itself can also be determined.

[0153] Determine the total weight information between this transportation station and its neighboring transportation stations. Optionally, obtain the total weight information between this transportation station and its neighboring transportation stations, as well as its own station.

[0154] Based on the total weight information mentioned above, as well as the weight information corresponding to adjacent transportation stations and the station itself, normalization processing is performed to obtain the station transfer probability between the transportation station and its adjacent transportation stations; based on the station transfer probability between each transportation station and its adjacent transportation stations, the above-mentioned station transfer probability matrix can be constructed.

[0155] In one example, such as Figure 10 As shown, it exemplifies a schematic diagram of a transportation station route. Figure 10 In this model, adjacent transportation stations are connected by paths; for example, subway station 101 is adjacent to subway stations 102, 103, and 104. In the transition weight matrix, the weights from subway station 101 to subway stations 102, 103, and 104 are all 1, while the weight between subway station 101 and other non-adjacent stations is 0. Furthermore, this embodiment adds edges connecting transportation stations to themselves, physically representing whether a user is at their current station or moving to the next station over a given period. Finally, the transition weight matrix for each transportation station is normalized. For example, the initial weights from subway station 101 to subway stations 102, 103, and 104 are 1, and after normalization, they are all 1 / 4. The probability of going to other subway stations is 0.

[0156] Step 232b: Obtain the matching observation probability corresponding to the base station information from the site fingerprint information corresponding to the candidate traffic station.

[0157] The process for determining the matching observation probability has been explained above and will not be repeated here.

[0158] Step 232c: Based on the site transfer probability and the matching observation probability corresponding to the base station information, determine the sequence matching score between the base station information sequence and at least one candidate site sequence.

[0159] Optionally, the formula for determining the sequence matching score based on the site transition probability and the matching observation probability is as follows:

[0160]

[0161] Where P represents probability, the superscript represents time, and the subscript represents the corresponding subway station and base station. This indicates that at time t=0, which is the starting time corresponding to the first location point scan of the base station information sequence, the user is at traffic station S. α Scanned to base station W i The probability of the transportation station S α With base station W i The corresponding matching observation probabilities. This indicates that the user travels from transportation station S within the time interval from t to t+1. α To transportation station S β The transition probability. This indicates that at time t+1, the user is at transportation station S. β Scanned to base station W j The probability of the transportation station Sβ With base station W j The corresponding matching observation probabilities.

[0162] This application embodiment considers historical trajectory information and supports the positioning of continuous base stations. Specifically, it can match the best station sequence for the above base station information sequence, and then achieve accurate positioning of the target positioning point through the target traffic station in the best station sequence, thereby improving the accuracy of station positioning.

[0163] Step 240: Based on the matching data, determine the target transportation station that matches the target location point.

[0164] Optionally, after obtaining the number of matches or the probability of matching between the target base station information and each traffic station, the traffic station with the highest number of matches or the highest probability of matching is determined as the target traffic station.

[0165] In an exemplary embodiment, the matching data mentioned above includes sequence matching data, which includes the sequence matching score. Accordingly, as... Figure 3 As shown, the implementation process of step 240 above includes the following steps (241-242).

[0166] Step 241: Based on the sequence matching score, determine the target site sequence corresponding to the base station information sequence from at least one candidate site sequence.

[0167] Optionally, the candidate site sequence with the highest sequence matching score is determined as the target site sequence.

[0168] In the exemplary embodiment, the sequence matching score determined by equation (4) above considers the probability of the base station observed at each transportation station, and also considers the spatial transfer relationship of the subway station. Based on the scoring function corresponding to equation (4) above, HMM (Hidden Markov Model) can be directly used for optimization. The basic idea of ​​the Viterbi algorithm is to find Si->Sj in each step, thereby finding the target station sequence that maximizes the sequence matching score.

[0169] Step 242: Determine the transportation station corresponding to the target location point in the target station sequence as the target transportation station.

[0170] In one example, such as Figure 11As shown, this example illustrates a page diagram for locating a subway station on a map. When a user uses a mobile map for location or navigation within the subway, inaccurate map application positioning can lead to incorrect location; especially when a user initiates walking navigation around the subway, failing to accurately confirm whether the current location has reached the subway station will result in a poor user experience. Map page 110 shows the location result based on conventional network positioning. In map page 110, the user's actual location is at subway station 118, and the user's location points determined by three different map applications are user location point 111 for map application 1, user location point 112 for map application 2, and user location point 113 for map application 3. The distances between user location points 111, 112, and 113 and subway station 118 are all relatively far, locating the user around the subway station rather than inside, resulting in a poor user experience. By applying the positioning method provided in this application embodiment, the positioning effect shown in map page 114 can be achieved, thereby improving the positioning accuracy of mobile maps and enhancing the user experience. On map page 114, the user location points determined by the positioning method provided in this application embodiment for the three different map applications mentioned above have all been optimized. As shown on map page 114, the distances between the optimized positioning point 115 (map application 1), optimized positioning point 116 (map application 2), and optimized positioning point 117 (map application 3) and the user's actual subway station 118 are significantly reduced, which can significantly improve the user experience. Related experimental tests show that without considering historical base station information, the station positioning success rate is 90%, and with historical base station information, the station positioning success rate can be increased to 94%. For subway positioning scenarios with little or no WiFi, this solution can significantly improve positioning accuracy, thereby improving the positioning experience.

[0171] The application of this embodiment in the subway positioning scenario can optimize and improve various situations encountered in the subway positioning scenario, avoid the impact of weak WiFi signal or mobile phone refresh delay, and significantly improve the station positioning recall rate and station positioning accuracy in the subway scenario.

[0172] In an exemplary embodiment, such as Figure 6 As shown, after obtaining the above sequence matching score, the above method further includes the following steps (250-260).

[0173] Step 250: If the sequence matching score corresponding to the target station sequence is greater than or equal to the target threshold, determine that the target location point is within the station area corresponding to the target traffic station.

[0174] Step 260: If the sequence matching score corresponding to the target site sequence is less than the target threshold, determine that the target location point is outside the site area.

[0175] In real-world scenarios, devices can determine whether a user's location is inside or outside a transportation hub by judging whether the current base station information belongs to that hub. However, many base stations within transportation hubs can be scanned by user terminals from outside the hub, or due to slow mobile phone scanning updates, users may be misjudged as being inside the transportation hub even when they are outside. This application's embodiments use the aforementioned sequence matching score to distinguish whether the user's current actual location scenario originated inside the transportation hub.

[0176] In this application embodiment, the site location scenarios are enriched, and the determination of whether a site is inside or outside the site can be optimized and improved through two approaches.

[0177] (1) On-site determination is made using the score calculated by HMM, or by using the probability threshold of the occurrence of the base station sequence. For example, if the base station information sequence is {Wi, Wj, Wk}, the sequence matching score F = P(Wi|Si)*P(Si->Sj)*P(Wj|Sj)*P(Sj->Sk)*P(Wk|Sk) can be calculated based on the probability of the base station appearing in the site fingerprint and the site transfer probability. This score represents the probability of the base station information sequence appearing in the traffic station. Here, {Si, Sj, Sk} is the target site sequence obtained by the HMM model matching. When F>=0.5, it can be determined that the target location point is within the site area corresponding to the target traffic station; otherwise, it is outside the site area.

[0178] (2) By integrating WiFi information and base station information, if the user is required to scan the base station information of the current base station and the WiFi information of the corresponding transportation station, then it is determined that the target location point is within the station area corresponding to the target transportation station.

[0179] Furthermore, this embodiment considers the scenario of location tracking at transportation stations, such as subway stations. Due to the user's relatively fast movement speed and the potential delay in updating information via mobile phone scanning, the user's location may lag behind the actual location. This embodiment utilizes historical base station information to deduce the user's location, eliminating the problem of signal delays. Specifically, the user's location can be deduced using timestamp information. For example, although the device locates the user at station S1 based on base station information sequence, if the timestamp of the current base station is 60 seconds greater than the timestamp of the location station, the user can be located at station S2, the next station after S1. Two assumptions are made here: First, the subway travel time between S1 and S2 is approximately one minute. This information can be obtained from the normal travel time of transportation routes. Second, S1 is not connected to any other stations besides S2; that is, the location is not a transfer station. This information can also be obtained from known transportation routes.

[0180] In summary, the technical solution provided in this application, by acquiring site fingerprint information that characterizes the base station features associated with a transportation station and target base station information corresponding to the target positioning point, and matching the target base station information with the site fingerprint information of at least one transportation station, can determine matching data that reflects the degree of matching between the target base station information and at least one transportation station. Furthermore, based on the aforementioned matching data, the target transportation station matching the target positioning point can be determined. By matching the base station information corresponding to the positioning point with the site fingerprint that characterizes the base station features, site positioning is achieved. This avoids the problem of inaccurate site positioning caused by factors such as weak satellite navigation positioning signals or limited distribution of wireless local area networks at the site, thus improving the accuracy, timeliness, and flexibility of site positioning.

[0181] The following are embodiments of the apparatus of this application, which can be used to execute embodiments of the method of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method of this application.

[0182] Please refer to Figure 12 This diagram illustrates a block diagram of a positioning device according to an embodiment of this application. The device has the function of implementing the above-described positioning method; this function can be implemented in hardware or by hardware executing corresponding software. The device can be a computer device or can be installed within a computer device. The device 1200 may include: a site fingerprint acquisition module 1210, a base station information acquisition module 1220, a site matching module 1230, and a site determination module 1240.

[0183] The site fingerprint acquisition module 1210 is used to acquire site fingerprint information corresponding to at least one transportation station, wherein the site fingerprint information is used to characterize the base station features associated with the at least one transportation station.

[0184] The base station information acquisition module 1220 is used to acquire the target base station information corresponding to the target positioning point;

[0185] The site matching module 1230 is used to match the target base station information with the site fingerprint information to generate matching data between the target base station information and the at least one transportation station. The matching data is used to characterize the degree of matching between the target base station information and the at least one transportation station.

[0186] The station determination module 1240 is used to determine the target transportation station matching the target location point based on the matching data.

[0187] In an exemplary embodiment, the target base station information includes a base station information sequence, the base station information sequence includes base station information corresponding to the terminal at at least one location point, the at least one location point includes the target location point, and the site fingerprint information includes pairing information between the traffic station corresponding to the site fingerprint information and at least one base station; the site matching module 1230 includes: a candidate sequence determination unit and a candidate sequence matching unit.

[0188] A candidate sequence determination unit is used to determine at least one candidate site sequence corresponding to the base station information sequence based on the pairing information between the base station information and the at least one traffic station, wherein the at least one candidate site sequence includes candidate traffic stations that have been paired with the base station information corresponding to the at least one location point.

[0189] A candidate sequence matching unit is used to match the base station information with the site fingerprint information corresponding to the candidate traffic station to obtain sequence matching data between the base station information sequence and the at least one candidate site sequence, wherein the matching data includes the sequence matching data.

[0190] In an exemplary embodiment, the candidate sequence matching unit includes: a pairing count acquisition subunit and a matching score determination subunit.

[0191] The pairing count acquisition subunit is used to acquire the pairing count between the base station information and the candidate traffic station from the station fingerprint information corresponding to the candidate traffic station.

[0192] The matching score determination subunit is used to determine the sequence matching score between the base station information sequence and the at least one candidate site sequence based on the number of pairings.

[0193] The sequence matching data includes the sequence matching score, which is used to characterize the degree of matching between the base station information sequence and the candidate site sequence.

[0194] In an exemplary embodiment, the base station information includes base station signal strength information, and the matching score determination subunit is further configured to determine the sequence matching score between the base station information sequence and the at least one candidate site sequence based on the number of pairings and the base station signal strength information.

[0195] In an exemplary embodiment, the site fingerprint information further includes the matching observation probability between the traffic station corresponding to the site fingerprint information and the at least one base station, the matching observation probability being used to characterize the degree of location matching between the base station and the traffic station; the candidate sequence matching unit further includes: a transition probability acquisition subunit and an observation probability acquisition subunit.

[0196] The transfer probability acquisition subunit is used to acquire the station transfer probability between adjacent candidate transportation stations in the at least one candidate station sequence, wherein the station transfer probability is determined based on the connection path between the transportation stations.

[0197] The observation probability acquisition subunit is used to obtain the matching observation probability corresponding to the base station information from the site fingerprint information corresponding to the candidate traffic station.

[0198] The matching score determination subunit is further configured to determine the sequence matching score between the base station information sequence and the at least one candidate site sequence based on the site transfer probability and the matching observation probability corresponding to the base station information.

[0199] In an exemplary embodiment, the site determination module 1240 includes: a target sequence determination unit and a target site determination unit.

[0200] A target sequence determination unit is used to determine the target site sequence corresponding to the base station information sequence from the at least one candidate site sequence based on the sequence matching score.

[0201] The target station determination unit is used to determine the traffic station corresponding to the target location point in the target station sequence as the target traffic station.

[0202] In an exemplary embodiment, the device 1200 further includes a site-inside / outside positioning module.

[0203] The station internal and external positioning module is used to determine the target positioning point within the station area corresponding to the target transportation station when the sequence matching score corresponding to the target station sequence is greater than or equal to the target threshold.

[0204] The site-inside-outside positioning module is also used to determine that the target positioning point is outside the site area if the sequence matching score corresponding to the target site sequence is less than the target threshold.

[0205] In an exemplary embodiment, the candidate sequence determination unit includes: a candidate site determination subunit and a candidate site arrangement subunit.

[0206] The candidate site determination subunit is used to determine, based on the pairing information corresponding to the at least one traffic station, the traffic stations that have been paired with the base station information among the at least one traffic stations as candidate traffic stations corresponding to the at least one positioning point.

[0207] The candidate station arrangement subunit is used to arrange and combine the candidate transportation stations to obtain the at least one candidate station sequence.

[0208] In an exemplary embodiment, the site fingerprint acquisition module 1210 includes: a historical trajectory acquisition unit, a pairing information determination unit, and a site fingerprint generation unit.

[0209] The historical trajectory acquisition unit is used to acquire historical trajectory data corresponding to at least one user account. The historical trajectory data includes base station information and traffic station identification information corresponding to at least one historical trajectory point.

[0210] The pairing information determination unit is used to determine the pairing information between the at least one traffic station and its corresponding historical pairing base station based on the base station information corresponding to the at least one historical trajectory point and the traffic station identification information. The pairing information is used to characterize the pairing status between the traffic station and the base station, and the pairing information includes the base station information and the number of pairings corresponding to the historical pairing base station.

[0211] The site fingerprint generation unit is used to generate site fingerprint information corresponding to each of the at least one transportation station based on the base station information corresponding to the historical paired base stations and the number of pairings.

[0212] In an exemplary embodiment, the site fingerprint information includes the matching observation probability corresponding to the historical paired base station, and the matching observation probability is used to characterize the degree of location matching between the base station and the traffic station; the site fingerprint generation unit includes: a pairing number determination subunit, an observation probability determination subunit, and a site fingerprint generation subunit.

[0213] The pairing count determination subunit is used to determine the total pairing count for each of the at least one transportation station based on the pairing count between the at least one transportation station and its corresponding historical pairing base station.

[0214] The observation probability determination subunit is used to divide the number of pairings corresponding to the historical pairing base station by the total number of pairings to obtain the matching observation probability corresponding to the historical pairing base station.

[0215] The site fingerprint generation subunit is used to generate site fingerprint information corresponding to each of the at least one transportation station based on the base station information corresponding to the historical paired base stations and the matching observation probability.

[0216] In summary, the technical solution provided in this application, by acquiring site fingerprint information that characterizes the base station features associated with a transportation station and target base station information corresponding to the target positioning point, and matching the target base station information with the site fingerprint information of at least one transportation station, can determine matching data that reflects the degree of matching between the target base station information and at least one transportation station. Furthermore, based on the aforementioned matching data, the target transportation station matching the target positioning point can be determined. By matching the base station information corresponding to the positioning point with the site fingerprint that characterizes the base station features, site positioning is achieved. This avoids the problem of inaccurate site positioning caused by factors such as weak satellite navigation positioning signals or limited distribution of wireless local area networks at the site, thus improving the accuracy, timeliness, and flexibility of site positioning.

[0217] It should be noted that the apparatus provided in the above embodiments is only illustrated by the division of the above functional modules when implementing its functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0218] Please refer to Figure 13 This diagram illustrates a structural block diagram of a computer device according to an embodiment of this application. The computer device can be a server or a terminal for performing the aforementioned positioning method. Specifically:

[0219] Computer device 1300 includes a central processing unit (CPU) 1301, a system memory 1304 including random access memory (RAM) 1302 and read-only memory (ROM) 1303, and a system bus 1305 connecting the system memory 1304 and the CPU 1301. Computer device 1300 also includes a basic input / output system (I / O system) 1306 that facilitates information transfer between various devices within the computer, and a mass storage device 1307 for storing the operating system 1313, application programs 1314, and other program modules 1315.

[0220] The basic input / output system 1306 includes a display 1308 for displaying information and an input device 1309 for user input, such as a mouse or keyboard. Both the display 1308 and the input device 1309 are connected to the central processing unit 1301 via an input / output controller 1310 connected to the system bus 1305. The basic input / output system 1306 may also include the input / output controller 1310 for receiving and processing input from multiple other devices such as a keyboard, mouse, or electronic stylus. Similarly, the input / output controller 1310 also provides output to a display screen, printer, or other types of output devices.

[0221] Mass storage device 1307 is connected to central processing unit 1301 via a mass storage controller (not shown) connected to system bus 1305. Mass storage device 1307 and its associated computer-readable media provide non-volatile storage for computer device 1300. That is, mass storage device 1307 may include computer-readable media (not shown) such as hard disk or CD-ROM (Compact Disc Read-Only Memory) drive.

[0222] Without loss of generality, computer-readable media can include computer storage media and communication media. Computer storage media includes volatile and non-volatile, removable and non-removable media implemented using any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes RAM, ROM, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), flash memory or other solid-state storage technologies, CD-ROM, DVD (Digital Video Disc) or other optical storage, magnetic tape cassettes, magnetic tape, disk storage, or other magnetic storage devices. Of course, those skilled in the art will recognize that computer storage media are not limited to the above-mentioned types. The system memory 1304 and mass storage device 1307 described above can be collectively referred to as memory.

[0223] According to various embodiments of this application, the computer device 1300 can also be connected to a remote computer on a network, such as the Internet. That is, the computer device 1300 can be connected to the network 1312 via the network interface unit 1311 connected to the system bus 1305, or the network interface unit 1311 can be used to connect to other types of networks or remote computer systems (not shown).

[0224] The memory also includes a computer program stored in the memory and configured to be executed by one or more processors to implement the above-described positioning method.

[0225] In an exemplary embodiment, a computer-readable storage medium is also provided, the storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set, when executed by a processor, implements the above-described positioning method.

[0226] Optionally, the computer-readable storage medium may include: ROM (Read Only Memory), RAM (Random Access Memory), SSD (Solid State Drives), or optical disc, etc. The random access memory may include ReRAM (Resistance Random Access Memory) and DRAM (Dynamic Random Access Memory).

[0227] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the aforementioned positioning method.

[0228] It should be understood that "multiple" as used herein refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. Furthermore, the step numbers described herein are merely illustrative of one possible execution order. In some other embodiments, the steps may not be executed in numerical order, such as two steps with different numbers being executed simultaneously, or two steps with different numbers being executed in the reverse order of the illustration. This application does not limit this.

[0229] In addition, in the specific embodiments of this application, data such as user information are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0230] The above description is merely an exemplary embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A positioning method, characterized by, The method comprises: acquiring historical trajectory data, the historical trajectory data comprising base station information and traffic site identification information corresponding to at least one historical trajectory point; determining pairing information between at least one traffic site and respective corresponding historical pairing base stations based on the base station information and the traffic site identification information corresponding to the at least one historical trajectory point, the pairing information comprising base station information corresponding to the historical pairing base stations and pairing times; generating site fingerprint information corresponding to the at least one traffic site based on the base station information corresponding to the historical pairing base stations and the pairing times, the site fingerprint information being used to represent characteristics of base stations associated with the at least one traffic site; acquiring target base station information corresponding to a target positioning point; matching the target base station information with the site fingerprint information to generate matching data corresponding between the target base station information and the at least one traffic site, the matching data being used to represent a matching degree between the target base station information and the at least one traffic site; determining a target traffic site matched by the target positioning point based on the matching data.

2. The method of claim 1, wherein, The target base station information comprises a base station information sequence, the base station information sequence comprising base station information corresponding to at least one positioning point, the at least one positioning point comprising the target positioning point, and the site fingerprint information comprising pairing information between at least one base station and a traffic site corresponding to the site fingerprint information; The matching of the target base station information with the site fingerprint information to generate matching data corresponding between the target base station information and the at least one traffic site comprises: determining at least one candidate site sequence corresponding to the base station information sequence based on the pairing information corresponding to the base station information and the at least one traffic site, the at least one candidate site sequence comprising candidate traffic sites paired with the base station information corresponding to the at least one positioning point; matching the base station information with site fingerprint information corresponding to the candidate traffic sites to obtain sequence matching data between the base station information sequence and the at least one candidate site sequence, the matching data comprising the sequence matching data.

3. The method of claim 2, wherein, The matching of the base station information with site fingerprint information corresponding to the candidate traffic sites to obtain sequence matching data between the base station information sequence and the at least one candidate site sequence comprises: acquiring pairing times between the base station information and the candidate traffic sites from the site fingerprint information corresponding to the candidate traffic sites; determining a sequence matching score corresponding to the base station information sequence and the at least one candidate site sequence based on the pairing times; The sequence matching data comprises the sequence matching score, and the sequence matching score is used to represent a matching degree between the base station information sequence and the candidate site sequence.

4. The method of claim 3, wherein, The base station information comprises base station signal strength information, and the determination of the sequence matching score corresponding to the base station information sequence and the at least one candidate site sequence based on the pairing times comprises: Determine a sequence matching score corresponding to the base station information sequence and the at least one candidate station sequence based on the pairing times and the base station signal strength information.

5. The method of claim 2, wherein, The station fingerprint information further comprises a matching observation probability corresponding to the traffic station corresponding to the station fingerprint information and the at least one base station, and the matching observation probability is used to represent a location matching degree between the base station and the traffic station. The matching of the base station information and the station fingerprint information corresponding to the candidate traffic station to obtain sequence matching data between the base station information sequence and the at least one candidate station sequence comprises: Obtain a station transition probability between adjacent candidate traffic stations in the at least one candidate station sequence, and the station transition probability is a transition probability determined based on a connection path between traffic stations. Obtain a matching observation probability corresponding to the base station information from the station fingerprint information corresponding to the candidate traffic station. Determine a sequence matching score corresponding to the base station information sequence and the at least one candidate station sequence based on the station transition probability and the matching observation probability corresponding to the base station information.

6. The method according to any one of claims 3 to 5, characterized in that, The determination of the target traffic station matched with the target positioning point based on the matching data comprises: Determine a target station sequence corresponding to the base station information sequence from the at least one candidate station sequence based on the sequence matching score; Determine the traffic station corresponding to the target positioning point in the target station sequence as the target traffic station.

7. The method of claim 6, wherein, The method further comprises: In a case where the sequence matching score corresponding to the target station sequence is greater than or equal to a target threshold, determine that the target positioning point is in a station area corresponding to the target traffic station; In a case where the sequence matching score corresponding to the target station sequence is less than the target threshold, determine that the target positioning point is outside the station area.

8. The method of claim 2, wherein, The determination of the at least one candidate station sequence corresponding to the base station information sequence based on the pairing information corresponding to the at least one traffic station comprises: Determine, based on the pairing information corresponding to the at least one traffic station, a traffic station paired with the base station information in the at least one traffic station as a candidate traffic station corresponding to the at least one positioning point; Arrange and combine the candidate traffic stations to obtain the at least one candidate station sequence.

9. The method of claim 1, wherein, The obtaining of the historical trajectory data comprises: Obtain historical trajectory data corresponding to at least one object account.

10. The method of claim 1, wherein, The station fingerprint information comprises a matching observation probability corresponding to the historical paired base station, and the matching observation probability is used to represent a location matching degree between the base station and the traffic station. The generation of the station fingerprint information corresponding to each of the at least one traffic station based on the base station information corresponding to the historical paired base station and the pairing times comprises: Determine a total pairing time corresponding to each of the at least one traffic station based on the pairing times between the at least one traffic station and the historical paired base station corresponding thereto; and Determine a station fingerprint corresponding to each of the at least one traffic station based on the total pairing time corresponding to each of the at least one traffic station and the base station information corresponding to the historical paired base station. divide the pairing times corresponding to the historical pairing base station by the total pairing times to obtain a matching observation probability corresponding to the historical pairing base station; generate the site fingerprint information corresponding to each of the at least one traffic site based on the base station information corresponding to the historical pairing base station and the matching observation probability.

11. A positioning device, characterized by The apparatus comprises: a site fingerprint acquisition module configured to acquire site fingerprint information corresponding to at least one traffic site, the site fingerprint information being configured to represent base station features associated with the at least one traffic site; a base station information acquisition module configured to acquire target base station information corresponding to a target positioning site; a site matching module configured to match the target base station information with the site fingerprint information to generate matching data corresponding to the target base station information and the at least one traffic site, the matching data being configured to represent a matching degree between the target base station information and the at least one traffic site; a site determination module configured to determine a target traffic site matched by the target positioning site based on the matching data. The site fingerprint acquisition module comprises: a historical trajectory acquisition unit configured to acquire historical trajectory data, the historical trajectory data comprising base station information and traffic site identification information corresponding to at least one historical trajectory point; a pairing information determination unit configured to determine pairing information between the at least one traffic site and a respective historical pairing base station based on the base station information and the traffic site identification information corresponding to the at least one historical trajectory point, the pairing information comprising base station information and pairing times corresponding to the historical pairing base station; a site fingerprint generation unit configured to generate site fingerprint information corresponding to each of the at least one traffic site according to the base station information and the pairing times corresponding to the historical pairing base station.

12. The apparatus of claim 11, wherein, The target base station information comprises a base station information sequence, the base station information sequence comprising base station information corresponding to at least one positioning site, the at least one positioning site comprising the target positioning site, and the site fingerprint information comprises pairing information between a traffic site corresponding to the site fingerprint information and at least one base station; The site matching module comprises: a candidate sequence determination unit configured to determine at least one candidate site sequence corresponding to the base station information sequence based on the base station information and pairing information corresponding to the at least one traffic site, the at least one candidate site sequence comprising candidate traffic sites paired with the base station information corresponding to the at least one positioning site; a candidate sequence matching unit configured to match the base station information with site fingerprint information corresponding to the candidate traffic sites to obtain sequence matching data between the base station information sequence and the at least one candidate site sequence, the matching data comprising the sequence matching data.

13. The apparatus of claim 12, wherein, The candidate sequence matching unit comprises: a pairing times acquisition subunit configured to acquire pairing times between the base station information and the candidate traffic sites from the site fingerprint information corresponding to the candidate traffic sites. The matching score determination subunit is configured to determine a sequence matching score corresponding to the base station information sequence and the at least one candidate station sequence based on the pairing times. The sequence matching data includes the sequence matching score, and the sequence matching score is used to represent a matching degree between the base station information sequence and the candidate station sequence.

14. The apparatus of claim 13, wherein, The base station information includes base station signal strength information, and the matching score determination subunit is further configured to: determine the sequence matching score corresponding to the base station information sequence and the at least one candidate station sequence based on the pairing times and the base station signal strength information.

15. The apparatus of claim 12, wherein, The station fingerprint information further includes a matching observation probability corresponding to the at least one base station and a traffic station corresponding to the station fingerprint information, and the matching observation probability is used to represent a location matching degree between the base station and the traffic station. The candidate sequence determination unit further includes: The transition probability acquisition subunit is configured to acquire a station transition probability between adjacent candidate traffic stations in the at least one candidate station sequence, and the station transition probability is a transition probability determined based on a connection path between traffic stations. The observation probability acquisition subunit is configured to acquire the matching observation probability corresponding to the base station information from the station fingerprint information corresponding to the candidate traffic station. The matching score determination subunit is further configured to determine the sequence matching score corresponding to the base station information sequence and the at least one candidate station sequence based on the station transition probability and the matching observation probability corresponding to the base station information.

16. The apparatus of any one of claims 13 to 15, wherein, The station determination module includes: The target sequence determination unit is configured to determine a target station sequence corresponding to the base station information sequence from the at least one candidate station sequence based on the sequence matching score. The target station determination unit is configured to determine a traffic station corresponding to the target positioning point in the target station sequence as the target traffic station.

17. The apparatus of claim 16, wherein, The device further includes: The station in-out positioning module is configured to determine that the target positioning point is in a station area corresponding to the target traffic station in a case where the sequence matching score corresponding to the target station sequence is greater than or equal to a target threshold, and determine that the target positioning point is out of the station area in a case where the sequence matching score corresponding to the target station sequence is less than the target threshold.

18. The apparatus of claim 12, wherein, The candidate sequence determination unit includes: The candidate station determination subunit is configured to determine a candidate traffic station corresponding to the at least one positioning point from the at least one traffic station based on pairing information corresponding to the at least one traffic station and the base station information. The candidate station arrangement subunit is configured to arrange and combine the candidate traffic stations to obtain the at least one candidate station sequence.

19. The apparatus of claim 11, wherein, The history trajectory acquisition unit is further configured to: acquire history trajectory data corresponding to at least one object account.

20. The apparatus of claim 11, wherein, The station fingerprint information includes a matching observation probability corresponding to the history pairing base station, and the matching observation probability is used to represent a location matching degree between the base station and the traffic station. The station fingerprint generation unit includes: The pairing frequency determination sub-unit is configured to determine the total pairing frequency of each of the at least one traffic station according to the pairing frequency between the at least one traffic station and the respective corresponding historical pairing base station; The observation probability determination sub-unit is configured to divide the pairing frequency corresponding to the historical pairing base station by the total pairing frequency to obtain the matching observation probability corresponding to the historical pairing base station; The station fingerprint generation sub-unit is configured to generate the station fingerprint information corresponding to each of the at least one traffic station based on the base station information corresponding to the historical pairing base station and the matching observation probability.

21. A computer device, comprising: The computer device comprises a processor and a memory, and the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to realize the positioning method of any one of claims 1 to 10.

22. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to realize the positioning method of any one of claims 1 to 10.

23. A computer program product, characterised in that, The computer program product comprises computer instructions stored in a computer readable storage medium, and the processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes to realize the positioning method of any one of claims 1 to 10.

Images