Positioning method, apparatus, and storage medium

Abstract

The application relates to a positioning method, a device and a storage medium. The method comprises the following steps: when a satellite signal quality score is greater than or equal to a first set quality score threshold, an initial positioning position of a user taking a car is acquired by a mobile terminal positioning module; a search space is acquired according to a confidence interval of the positioning module and the initial positioning position; candidate roads of the search space are acquired according to map data of the search space, the candidate roads comprising passable vehicle roads in the search space which can be reached on foot; a plurality of candidate positions of the candidate roads are acquired by linear sampling of the candidate roads according to a set sampling rule; residual scores of each candidate position of the plurality of candidate positions are acquired according to the initial positioning position and the plurality of candidate positions, and a candidate position corresponding to a minimum residual score is determined as a positioning position of the user taking the car. The scheme provided by the application can improve the positioning accuracy of the car positioning, and meet the requirement of the car positioning on the positioning accuracy.

Description

Technical Field

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

[0002] Urban canyons are man-made urban environments composed of dense high-rise buildings and streets. Their shape is similar to that of natural canyons. Streets serve as the ground level, and the vertical interfaces of buildings form spatial structures. They are commonly found in urban core areas.

[0003] Satellite positioning is a radio navigation technology based on satellite signals. It determines the precise location, speed, and time information of a user terminal by receiving ranging signals from multiple satellites.

[0004] The relevant ride-hailing positioning technology, based on satellite positioning of smartphones, can achieve a positioning accuracy of about ten meters. However, in complex urban canyon environments, satellite signals are easily blocked or reflected by tall buildings. Due to NLOS (Non-Line-of-Sight) errors, satellite signals experience multipath problems, causing instability and malfunctions, which in turn affect the accuracy of lateral positioning, resulting in less accurate ride-hailing positioning results.

[0005] In summary, the positioning accuracy of related technologies for ride-hailing is low in urban canyon environments, and cannot meet the positioning accuracy requirements of ride-hailing. Summary of the Invention

[0006] To address or partially address the problems existing in related technologies, this application provides a positioning method, device, and storage medium that can improve the positioning accuracy of ride-hailing positioning, accurately locate the user's ride-hailing location, and meet the positioning accuracy requirements of ride-hailing positioning.

[0007] The first aspect of this application provides a positioning method, including: If the satellite signal quality score is greater than or equal to a first set quality score threshold, the initial location of the user's ride-hailing location located by the mobile terminal positioning module is obtained, wherein the satellite signal quality score is a score that evaluates the quality of the satellite signal used by the positioning module to locate the initial location. The search space is obtained based on the confidence interval of the positioning module and the initial positioning position; Based on the map data of the search space, candidate roads of the search space are obtained, including walkable and vehicular roads of the search space. According to the set sampling rules, the candidate roads are linearly sampled to obtain multiple candidate positions of the candidate roads; Based on the initial location and the plurality of candidate locations, the residual score of each candidate location is obtained, and the candidate location corresponding to the smallest residual score is determined as the location of the user's ride-hailing.

[0008] In one embodiment, the confidence interval includes the 95% error ellipse of the positioning module; The step of obtaining the search space based on the confidence interval of the positioning module and the initial positioning position includes: The search space is obtained with the initial positioning position as the center and k times the length of the major axis of the 95% error ellipse as the radius, where 1≤k≤5.

[0009] In one embodiment, obtaining candidate roads in the search space based on map data of the search space includes: Based on the map data of the search space, obtain the pedestrian network and accessible vehicular roads of the search space; The passable vehicle roads that have nodes of the pedestrian network in the designated buffer zone are selected as candidate roads.

[0010] In one embodiment, the step of linearly sampling the candidate roads according to a set sampling rule to obtain multiple candidate positions of the candidate roads includes: If the road network side is identified based on the satellite signal, the traffic attributes of the candidate road are obtained; wherein, the road network side is a binary label representing the user on one side of the candidate road; If the candidate road is determined to be a one-way road based on the traffic attributes, then the lane centerline of the candidate road that is a one-way road is linearly sampled according to a set step size to obtain multiple candidate positions of the candidate road. If the candidate road is determined to be a two-way road based on the traffic attributes, an offset distance is set for the lane centerline of the candidate road to be a two-way road, and a first-side virtual road segment and a second-side virtual road segment of the candidate road are obtained. If the user is determined to be on the first-side virtual road segment of the candidate road based on the road network side, the first-side virtual road segment is linearly sampled according to the set step size to obtain multiple candidate positions of the candidate road. If the user is determined to be on the second-side virtual road segment of the candidate road based on the road network side, the second-side virtual road segment is linearly sampled according to the set step size to obtain multiple candidate positions of the candidate road.

[0011] In one embodiment, obtaining the residual score of each candidate position based on the initial positioning position and the plurality of candidate positions includes: Based on the initial location and the multiple candidate locations, obtain the walking direction from the initial location to each of the multiple candidate locations; Based on the multiple candidate locations, obtain the road direction of the road where each candidate location is located; Based on the walking direction and the road direction, obtain the angle between the walking direction and the road direction; Based on the included angle, obtain the map matching degree of each candidate location from the initial positioning location to the multiple candidate locations; Based on the initial positioning location, the multiple candidate locations, the included angle, and the map matching degree, the residual score of each candidate location is obtained.

[0012] In one embodiment, obtaining the residual score of each candidate location based on the initial positioning location, the plurality of candidate locations, the included angle, and the map matching degree includes: Based on the initial positioning location and the plurality of candidate locations, the distance between the initial positioning location and each of the plurality of candidate locations is obtained; Based on the included angle, obtain the probability of the walking direction from the initial positioning position to each of the multiple candidate positions; Based on the walking direction probability, obtain the map matching degree of each candidate location from the initial location to the plurality of candidate locations; Based on the distance, the included angle, and the map matching degree, as well as the first weight of the distance, the second weight of the included angle, and the third weight of the map matching degree, the residual score of each of the plurality of candidate locations is obtained.

[0013] In one embodiment, the method includes: The location of the user's ride-hailing is verified and corrected based on the location determined by the PDR system of the mobile terminal, and the verified and corrected location is determined as the target location of the user's ride-hailing.

[0014] In one embodiment, the method further includes: If the satellite signal quality score is less than the first set quality score threshold, the user's location when hailing a taxi is obtained through the PDR system of the mobile terminal.

[0015] A second aspect of this application provides a positioning device, comprising: Processor; and A memory that stores executable code, which, when executed by the processor, causes the processor to perform the method described above.

[0016] A third aspect of this application provides a computer-readable storage medium having executable code stored thereon, which, when executed by a processor, causes the processor to perform the method described above.

[0017] A fourth aspect of this application provides a computer program product comprising computer instructions that, when executed by a processor, implement the method described above.

[0018] The technical solution provided in this application may include the following beneficial results: The technical solution of this application involves obtaining the initial location of the user's ride-hailing service, determined by the mobile terminal positioning module, when the satellite signal quality score is greater than or equal to a first preset quality score threshold. The satellite signal quality score is a score that evaluates the quality of the satellite signal used by the positioning module to determine the initial location. A search space is obtained based on the confidence interval of the positioning module and the initial location. Candidate roads in the search space are obtained based on map data of the search space, including walkable and vehicular roads. Linear sampling is performed on the candidate roads according to a set sampling rule to obtain multiple candidate locations for each candidate road. Based on the initial location and the multiple candidate locations, a residual score is obtained for each candidate location, and the candidate location corresponding to the smallest residual score is determined as the user's ride-hailing location. Even in urban canyon environments where satellite signals are blocked or reflected by tall buildings, reducing the positioning accuracy of the mobile terminal positioning module, the system can still correct the initial location of the user's ride-hailing location based on the positioning accuracy of the mobile terminal positioning module, provided the satellite signal quality score is greater than or equal to a first set quality score threshold. This improves the positioning accuracy of ride-hailing positioning and accurately locates the user's boarding position, solving the problem that the positioning accuracy of the mobile terminal positioning module cannot meet the positioning accuracy requirements of ride-hailing positioning in urban canyon environments, thus satisfying the positioning accuracy requirements of ride-hailing positioning.

[0019] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0020] The above and other objects, features and advantages of this application will become more apparent from the more detailed description of exemplary embodiments thereof in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments thereof.

[0021] Figure 1 This is a flowchart illustrating the positioning method in an embodiment of this application; Figure 2 This is another schematic flowchart illustrating the positioning method in an embodiment of this application; Figure 3 This is a schematic diagram of the positioning device shown in the embodiments of this application. Detailed Implementation

[0022] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to make this application more thorough and complete, and to fully convey the scope of this application to those skilled in the art.

[0023] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0024] It should be understood that although the terms "first," "second," "third," etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0025] This application provides a positioning method that can improve the positioning accuracy of ride-hailing positioning, accurately locate the user's ride-hailing location, and meet the positioning accuracy requirements of ride-hailing positioning.

[0026] The technical solutions of the embodiments of this application are described in detail below with reference to the accompanying drawings.

[0027] Figure 1 This is a flowchart illustrating the positioning method in an embodiment of this application.

[0028] See Figure 1 A positioning method, comprising: Step 101: If the satellite signal quality score is greater than or equal to the first set quality score threshold, then obtain the initial location of the user's ride-hailing location located by the mobile terminal positioning module. The satellite signal quality score is a score that evaluates the quality of the satellite signal used by the positioning module to locate the initial location.

[0029] In one embodiment, when a user places a ride-hailing order through a ride-hailing app (application) on a mobile terminal, the user's mobile terminal can be located by a positioning module to obtain the satellite signal of the initial location of the user's ride-hailing order. Based on the satellite signal, the satellite signal quality score is obtained. If the satellite signal quality score is greater than or equal to a first set quality score threshold, the initial location of the user's ride-hailing order located by the user's mobile terminal positioning module is obtained.

[0030] Step 102: Obtain the search space based on the confidence interval of the mobile terminal positioning module and the initial positioning location.

[0031] In one embodiment, the confidence interval of the mobile terminal positioning module represents the positioning accuracy range of the mobile terminal positioning module. Based on the positioning accuracy range of the mobile terminal positioning module, the maximum or minimum radius of the positioning accuracy range centered on the initial positioning position can be obtained to acquire the search space for determining the user's taxi-hailing and boarding location.

[0032] Step 103: Based on the map data of the search space, obtain candidate roads in the search space, including walkable and vehicular roads in the search space.

[0033] In one embodiment, city map data can be obtained based on the initial location, and map data of the search space range can be obtained from the city map data; based on the map data of the search space range, the pedestrian network and accessible vehicular roads of the search space range can be obtained; based on the pedestrian network and accessible vehicular roads of the search space range, the accessible vehicular roads that the user in the search space range can reach on foot through the pedestrian network can be obtained.

[0034] In one embodiment, the pedestrian network within the search space is the pedestrian paths within the search space. The drivable vehicular roads within the search space are the roads used by vehicles within the search space.

[0035] Step 104: According to the set sampling rules, perform linear sampling on the candidate roads to obtain multiple candidate positions of the candidate roads.

[0036] In one embodiment, candidate roads can be linearly sampled according to a set sampling rule (e.g., a set sampling step size) to obtain multiple candidate positions of the candidate roads.

[0037] Step 105: Based on the initial location and multiple candidate locations, obtain the residual score of each candidate location, and determine the candidate location corresponding to the smallest residual score as the user's location when hailing a ride.

[0038] In one embodiment, the following steps can be taken: First, the distance from the initial location to each of the multiple candidate locations can be calculated based on the initial location and multiple candidate locations. Second, the angle between the walking direction and the road direction of each candidate location can be calculated based on the walking direction and the road direction of the road where each candidate location is located. Third, the probability of the walking direction from the initial location to each candidate location can be calculated based on the angle between the walking direction and the road direction. Fourth, the map matching degree from the initial location to each candidate location can be obtained based on the walking direction probability. Fifth, the residual score of each candidate location can be calculated based on the distance, the angle between the walking direction and the road direction, and the map matching degree. Finally, the candidate location corresponding to the minimum residual score is determined as the user's ride-hailing location, and the user's ride-hailing location is uploaded to the ride-hailing app so that the ride-hailing app can use the user's ride-hailing location as the user's location when issuing ride-hailing orders.

[0039] The positioning method of this application embodiment obtains the initial positioning location of the user's ride-hailing service when the satellite signal quality score is greater than or equal to a first preset quality score threshold. The satellite signal quality score is a score that evaluates the quality of the satellite signal used by the positioning module to locate the initial positioning location. Based on the confidence interval of the positioning module and the initial positioning location, a search space is obtained. Based on the map data of the search space, candidate roads in the search space are obtained, including walkable and vehicular roads in the search space. According to a preset sampling rule, linear sampling is performed on the candidate roads to obtain multiple candidate locations. Based on the initial positioning location and the multiple candidate locations, a residual score is obtained for each candidate location, and the candidate location corresponding to the smallest residual score is determined as the user's ride-hailing positioning location. Even in urban canyon environments where satellite signals are blocked or reflected by tall buildings, reducing the positioning accuracy of the mobile terminal positioning module, the system can still correct the initial location of the user's ride-hailing location based on the positioning accuracy of the mobile terminal positioning module, provided the satellite signal quality score is greater than or equal to a first set quality score threshold. This improves the positioning accuracy of ride-hailing positioning and accurately locates the user's boarding position, solving the problem that the positioning accuracy of the mobile terminal positioning module cannot meet the positioning accuracy requirements of ride-hailing positioning in urban canyon environments, thus satisfying the positioning accuracy requirements of ride-hailing positioning.

[0040] Figure 2 This is another schematic flowchart illustrating the positioning method in an embodiment of this application. Figure 2 Compared to Figure 1 The scheme of this application is described in more detail.

[0041] See Figure 2 A positioning method, comprising: Step 201: Obtain the satellite signal quality score based on the satellite signal of the user's initial location when hailing a ride, determined by the mobile terminal positioning module.

[0042] In one embodiment, the mobile terminal includes, but is not limited to, smartphones, tablets, and smartwatches. The positioning module of the mobile terminal can be a multi-technology fusion satellite positioning module, for example, it can be a satellite positioning module including GPS (Global Positioning System), BeiDou, GLONASS (GLOBAL NAVIGATION SATELLITE SYSTEM), and Galileo (Galileo satellite navigation system) multi-mode chips.

[0043] In one embodiment, when a user places a ride-hailing order through a ride-hailing app on a mobile terminal, the user can use the mobile terminal's positioning module to locate themselves and obtain all satellite signals for the initial location. Based on all satellite signals, the satellite signal quality score Q is calculated.

[0044] Where N represents the number of satellites from which the mobile terminal positioning module locates the initial positioning location; i represents the i-th satellite from which the mobile terminal positioning module locates the initial positioning location; This represents the carrier-to-noise ratio of the signal from the i-th satellite. This represents the maximum carrier-to-noise ratio of the signals from N satellites. This represents the elevation angle of the i-th satellite; The normalized elevation angle constant represents the elevation angle of N satellites; Let represent the azimuth weighting function for the i-th satellite based on building occlusion prediction.

[0045] In one embodiment, the elevation angle of the i-th satellite can be used as the elevation angle of the N satellites. Obtain elevation angle normalized value The normalized value ranges from [0,1]. The average of the normalized elevation angles of each of the N satellites is taken as the normalized elevation angle constant of the N satellites. .

[0046] Step 202: Determine whether the satellite signal quality score is greater than or equal to the first set quality score threshold; if yes, proceed to step 203; if no, proceed to step 210.

[0047] In one embodiment, it can be determined whether the satellite signal quality score of the satellite signal used by the positioning module to locate the initial positioning position is greater than or equal to a first set quality score threshold; if the satellite signal quality score is greater than or equal to the first set quality score threshold, step 203 is executed; if the satellite signal quality score is less than the first set quality score threshold, step 210 is executed.

[0048] Step 203: Obtain the initial location of the user's ride-hailing trip as determined by the mobile terminal's positioning module.

[0049] In one embodiment, if the satellite signal quality score is greater than or equal to a first set quality score threshold, the initial location of the user's ride-hailing service, located by the mobile terminal positioning module, can be obtained.

[0050] Step 204: Determine the search space based on the confidence interval of the positioning module and the initial positioning position.

[0051] In one embodiment, the confidence interval of the positioning module can be the 95% error ellipse of the positioning module when calculating the positioning. The length of the major axis of the 95% error ellipse (2σ in the horizontal direction) can be twice the standard deviation σ of the direction of maximum variation.

[0052] In one embodiment, a circular search space can be obtained with the initial positioning position as the center and the length of the major axis 2σ of the 95% error ellipse as the radius R.

[0053] In one embodiment, the 95% error ellipse can be rotated to the Northeast-Eastern-Upper (ENU) coordinate system to obtain an elliptical search space. The origin of the ENU can be the initial positioning position.

[0054] In one embodiment, if the satellite signal quality score is less than a second set quality score threshold, a circular search space can be obtained with the initial positioning position as the center and a radius R of k times (i.e., 2kσ) the major axis length of the 95% error ellipse 2σ. Here, 1 < k ≤ 5, so as to expand the size of the search space.

[0055] Step 205: Based on the map data of the search space, obtain candidate roads in the search space, including walkable and vehicular roads in the search space.

[0056] In one embodiment, candidate roads in the search space refer to the set of walkable vehicular road segments extracted from map data of the search space via nodes and ways in a pedestrian network. The pedestrian network is a walkable topology formed by the geometric connections of nodes and ways. Paths in the pedestrian network include pedestrian paths (e.g., sidewalks, pedestrian streets, overpasses, etc.). Nodes in the pedestrian network include key points and vertices (e.g., intersections, crosswalks, stairwell entrances, inflection points, or segmental connection points) within the pedestrian paths.

[0057] In one embodiment, OSM (Open Street Map) map data of the city where the initial location is located can be downloaded; based on the highway label of the OSM map data, the pedestrian network and accessible vehicular roads in the search space can be obtained respectively; based on the pedestrian network and accessible vehicular roads in the search space, the accessible vehicular roads of nodes with pedestrian networks in a set buffer are selected as candidate roads, and the candidate roads are accessible vehicular roads that the user can reach on foot through the pedestrian network.

[0058] In one embodiment, based on the storage method of the pedestrian network and accessible vehicular roads in the search space, and using a set distance as a condition, accessible vehicular roads with nodes in the search space that have pedestrian networks within a set distance can be selected as candidate roads. For example, it can be checked whether there are nodes in the pedestrian network within a 15-meter buffer zone for accessible vehicular roads in the search space; if there are nodes in the pedestrian network within the 15-meter buffer zone (meaning the user can reach the accessible vehicular road on foot), then the accessible vehicular road is retained and selected as a candidate road; if there are no nodes in the pedestrian network within the 15-meter buffer zone (meaning the user cannot reach the accessible vehicular road on foot), then the accessible vehicular road is discarded. Candidate roads are accessible vehicular roads that are passable by vehicles (vehicles can drive to them) and accessible by pedestrians (users can get into vehicles).

[0059] In one specific embodiment, roads with highway labels of highway=footway, highway=path, highway=pedestrian, and footway=sidewalk can be obtained by spatial indexing based on the highway labels in the OSM map data. The roads with highway labels of highway=footway, highway=path, highway=pedestrian, and footway=sidewalk in the search space are then used as the pedestrian network of the search space.

[0060] In one specific embodiment, based on the highway labels in the OSM map data, spatial indexing can be used to obtain roads with highway labels of highway=primary, highway=secondary, highway=tertiary, highway=residential, highway=service, and highway=unclassified. Roads with highway labels of highway=primary, highway=secondary, highway=tertiary, highway=residential, highway=service, and highway=unclassified in the search space can be used as traversable vehicle roads in the search space.

[0061] In one embodiment, for each candidate road in the search space, road information for each candidate road can be obtained through city map data. This road information includes lane centerlines and traffic attributes. Traffic attributes indicate whether the passable road is a one-way or two-way road.

[0062] Step 206: Determine whether the road network side is identified based on the satellite signal of the initial positioning position determined by the positioning module. The road network side is a binary label indicating that the user is on one side of the candidate road. If the road network side is identified, proceed to step 207. If the road network side is not identified, proceed to step 201.

[0063] In one embodiment, the road network side is a binary label indicating which side of the candidate road the user is currently on (left or right side of the candidate road).

[0064] In one embodiment, the signal characteristics of the satellite signal used by the positioning module to locate the initial positioning position can be input into the SVM (Support Vector Machine) model. The signal characteristics of the satellite signal include the signal characteristics of the satellite signal in the left half of the sky and the signal characteristics of the satellite signal in the right half of the sky. The SVM model identifies the road network side based on the signal characteristics of the satellite signal. If the road network side is identified, step 207 is executed; if the road network side is not identified, step 201 is executed.

[0065] In one embodiment, the satellite signal can be obtained based on the satellite signal used by the positioning module to determine the initial positioning position. The azimuth angle (a) and elevation angle (e) are determined using Otsu's method (Otsu binarization method) combined with Bayesian risk minimization to dynamically determine the optimal soft threshold. Based on the optimal soft threshold, the signal characteristics of satellite signals in the left and right halves of the sky are calculated separately. The signal characteristics of the left half-sky satellite signals include the number of satellites with strong signals, the azimuth angle score, and the elevation angle score. The signal characteristics of the right half-sky satellite signals also include the number of satellites with strong signals, the azimuth angle score, and the elevation angle score. Based on the signal characteristics of the left and right half-sky satellite signals, the road network side is identified using an SVM model to determine whether the road network side has been identified.

[0066] In one embodiment, based on the C / N0 of the satellite signals in the left and right halves of the sky at the initial positioning position determined by the positioning module, the Otsu algorithm is used. Based on the statistical characteristics of the grayscale histogram, an initial hard threshold is determined by maximizing the inter-class variance, dividing the satellite signals into noise and valid satellite signals. Building upon the Otsu algorithm segmentation, a Bayesian risk minimization criterion is introduced. By defining a misclassification cost function (e.g., the cost of misclassifying noise as a satellite signal), distribution parameters are fitted based on the Otsu segmentation results, and the initial hard threshold is iteratively adjusted to minimize the Bayesian risk. The threshold that minimizes the Bayesian risk is obtained as the optimal soft threshold. Based on the optimal soft threshold, the number of satellites in the left and right halves of the sky that belong to strong signals is obtained respectively.

[0067] In one embodiment, the road direction θ of the user's current road (the road where the initial location is located) in the northeast-northeast coordinate system can be obtained. road Road direction θ road The angle between the road centerline and the X / Y axes of the northeast-northeast coordinate system is taken as the reference direction, and θ is determined according to the road direction. road Determine the left and right halves of the sky in the northeast-northeast coordinate system; define the azimuth range as (θ). road +90°-90°)-(θ) road The sky corresponding to +90° (+90°) is defined as the left half of the sky, and the azimuth range is (θ). road -90°-90°)-(θ) road The sky corresponding to -90° and +90° is determined to be the right half of the sky.

[0068] In one embodiment, if information about urban buildings can be obtained, the obstructed angle can be further modified by combining the 3D model with the cropped angle, and the corresponding azimuth ranges of the left and right halves of the sky can be corrected respectively.

[0069] In one embodiment, adaptive azimuth segmentation (0-180° and 180-360°) can be achieved in the northeast-northeast coordinate system, and the segmentation boundary between the left and right halves of the sky can be dynamically adjusted in conjunction with the three-dimensional model of urban buildings.

[0070] In one embodiment, the positioning module can locate the satellite at its initial position, obtain the satellites in the left half of the sky in the northeast celestial coordinate system, and obtain the satellite signals of the satellites in the left half of the sky in the northeast celestial coordinate system. Based on the C / N0 of the satellite signals in the left half of the sky and the optimal soft threshold, the satellites in the left half of the sky whose C / N0 is greater than or equal to the optimal soft threshold are considered as satellites with strong signals in the left half of the sky, and the number N of satellites with strong signals in the left half of the sky is obtained. left .

[0071] In one embodiment, the positioning module can locate the satellite at its initial position, obtain the satellites in the right half of the sky in the northeast celestial coordinate system, and obtain the satellite signals of the satellites in the right half of the sky in the northeast celestial coordinate system. Based on the C / N0 of the satellite signals in the right half of the sky and the optimal soft threshold, satellites in the right half of the sky whose C / N0 is greater than or equal to the optimal soft threshold are considered as satellites with strong signals in the right half of the sky, and the number N of satellites with strong signals in the right half of the sky is obtained. right .

[0072] In one embodiment, the azimuth rating criterion could be: satellites closer to the road direction and with a high elevation angle are more reliable.

[0073] In one embodiment, the azimuth score of each satellite in the left half of the sky and the azimuth score of each satellite in the right half of the sky can be calculated based on the azimuth angles of the satellites in the left half of the sky and the azimuth angles of the satellites in the right half of the sky, respectively. The azimuth score takes the value of [0, 1].

[0074] In one embodiment, the azimuth angle of the i-th satellite in the left half of the sky is α. left_i azimuth angle a left_i The azimuth score is w(a) left_i ), w(a left_i )=exp[-(Δa left_i ÷σ a )²], Where, Δa left_i =min(|a left_i -θ road |, 360°-|a left_i -θ road |);σ a =40°; In one embodiment, the azimuth angle score w(a) of each satellite in the left half of the sky can be used as a basis. left_i Obtain the normalized azimuth score of satellites in the left half of the sky. left-a ,

[0075] Among them, M left Indicates the number of satellites in the left half of the sky; e left_i This represents the elevation angle of the i-th satellite in the left half of the sky.

[0076] In one embodiment, the azimuth angle of the i-th satellite in the right half of the sky is α. right_i azimuth angle a right_i The azimuth score is w(a) right_i ), w(a right_i )=exp[-(Δa right_i ÷σ a )²], Where, Δa right_i =min(|a right_i -θ road |, 360°-|a right_i -θ road |);σ a =40°; In one embodiment, the azimuth angle score w(a) of each satellite in the right half of the sky can be used as a basis. right_i Obtain the normalized azimuth score of satellites in the right half of the sky. right-a ,

[0077] Among them, M right Indicates the number of satellites in the right half of the sky; e right_i This represents the elevation angle of the i-th satellite in the right half of the sky.

[0078] In one embodiment, the elevation angle score of each satellite in the left half of the sky and the elevation angle of each satellite in the right half of the sky can be calculated based on the elevation angle of the satellite in the left half of the sky and the elevation angle of the satellite in the right half of the sky, respectively, with the elevation angle score taking the value of [0,1].

[0079] In one embodiment, the elevation angle of the i-th satellite in the left half of the sky is e. left_i Angle of elevation e left_i The elevation angle score is s(e) left_i ), s(e left_i )=sin(e left_i The elevation angle e of the i-th satellite in the left half of the sky. left_i It is directly mapped to 0-1.

[0080] In one embodiment, the elevation angle score s(e) of each satellite in the left half of the sky can be used as a basis. left_i Obtain the normalized elevation angle score of satellites in the left half of the sky. left-e ,

[0081] Among them, M left This represents the number of satellites in the left half of the sky; I represents the indicator function, which is 1 when the carrier-to-noise ratio (CNR) of the i-th satellite signal in the left half of the sky is greater than or equal to the optimal soft threshold t_final, and 0 when the CNR is less than the optimal soft threshold t_final; C / N o-left_i This represents the carrier-to-noise ratio of the i-th satellite in the left half of the sky.

[0082] In one embodiment, the elevation angle of the i-th satellite in the right half of the sky is e. right_i Angle of elevation e right_i The elevation angle score is s(e) right_i ), s(e right_i )=sin(e right_i The elevation angle e of the i-th satellite in the right half of the sky. right_i It is directly mapped to 0-1.

[0083] In one embodiment, the elevation angle score s(e) of each satellite in the right half of the sky can be used as a basis. right_i Obtain the normalized elevation angle score of satellites in the right half of the sky. right-e ,

[0084] Among them, M right This represents the number of satellites in the right half of the sky; I represents the indicator function, which is 1 when the carrier-to-noise ratio (CNR) of the i-th satellite signal in the right half of the sky is greater than or equal to the optimal soft threshold t_final, and 0 when the CNR is less than the optimal soft threshold t_final; C / N o-right_i This represents the carrier-to-noise ratio of the i-th satellite in the right half of the sky.

[0085] In one embodiment, the number N of satellites whose signals in the left half of the sky are strong signals is determined. left The number N of satellites with strong signals in the right half of the sky. right Normalized azimuth score of satellites in the left half of the sky left-a Normalized Elevation Angle Score left-eand the normalized azimuth score of satellites in the right half of the sky. right-a Normalized Elevation Angle Score right-e Input the SVM model, identify the road network side through the SVM model, and determine whether the road network side is identified; if the road network side is identified, proceed to step 207; if the road network side is not identified, proceed to step 201.

[0086] Step 207: Obtain the traffic attributes of the candidate roads, and perform linear sampling on the candidate roads according to the set sampling rules and the traffic attributes of the candidate roads to obtain multiple candidate locations of the candidate roads.

[0087] In one embodiment, if the road network side is identified based on the satellite signal of the initial positioning position located by the positioning module, the traffic attributes of the candidate road are obtained; the candidate road is determined to be a one-way road or a two-way road based on the traffic attributes; if the candidate road is determined to be a one-way road based on the traffic attributes, the lane centerline of the candidate road that is a one-way road is linearly sampled according to a set step size to obtain multiple candidate positions of the candidate road.

[0088] In one embodiment, if the candidate road is determined to be a two-way road based on traffic attributes, an offset distance is set for the lane centerline of the candidate road to be a two-way road, and a first-side virtual road segment and a second-side virtual road segment are obtained. If the user is determined to be on the first-side virtual road segment of the candidate road based on the road network, the first-side virtual road segment is linearly sampled at a set step size to obtain multiple candidate positions of the candidate road to be a two-way road. If the user is determined to be on the second-side virtual road segment of the candidate road based on the road network, the second-side virtual road segment is linearly sampled at a set step size to obtain multiple candidate positions of the candidate road to be a two-way road.

[0089] In one specific embodiment, for candidate roads with one-way traffic, the lane centerlines of the candidate roads with one-way traffic can be linearly sampled in 1-meter increments to obtain multiple candidate positions for the candidate roads with one-way traffic. For candidate roads with two-way traffic, the lane centerlines of the candidate roads with two-way traffic can be shifted 3 meters to the left and right to obtain left and right virtual road segments. Based on the identified road network side, it is determined whether the user is located on the left virtual road segment or the right virtual road segment. If the user is located on the left virtual road segment, the left virtual road segment is linearly sampled in 1-meter increments to obtain multiple candidate positions for the candidate roads with two-way traffic. If the user is located on the right virtual road segment, the right virtual road segment is linearly sampled in 1-meter increments to obtain multiple candidate positions for the candidate roads with two-way traffic.

[0090] Step 208: Based on the initial location and multiple candidate locations, obtain the residual score of each candidate location, and determine the candidate location corresponding to the smallest residual score as the user's location when hailing a ride.

[0091] In one embodiment, based on the initial location and multiple candidate locations, the walking direction from the initial location to each of the multiple candidate locations can be obtained; based on the multiple candidate locations, the road direction of the road where each of the multiple candidate locations is located can be obtained; based on the walking direction and the road direction, the angle between the walking direction and the road direction can be obtained; based on the angle, the map matching degree of walking from the initial location to each of the multiple candidate locations can be obtained; based on the initial location, multiple candidate locations, the angle, and the map matching degree, the residual score of each of the multiple candidate locations can be obtained, and the candidate location corresponding to the minimum residual score can be determined as the user's location for hailing a taxi.

[0092] In one embodiment, the distance between the initial location and each of the multiple candidate locations can be obtained based on the initial location and multiple candidate locations; the walking direction from the initial location to each of the multiple candidate locations can be obtained based on the initial location and multiple candidate locations; the road direction of the road where each of the multiple candidate locations is located can be obtained based on the multiple candidate locations; the angle between the walking direction and the road direction can be obtained based on the walking direction; the probability of walking from the initial location to each of the multiple candidate locations can be obtained based on the angle; the map matching degree of walking from the initial location to each of the multiple candidate locations can be obtained based on the walking direction probability; and the residual score of each of the multiple candidate locations can be obtained based on the distance, the angle, and the map matching degree, as well as a first weight for the distance, a second weight for the angle, and a third weight for the map matching degree, and the candidate location corresponding to the smallest residual score can be determined as the user's location for hailing a taxi.

[0093] In one embodiment, the distance between the initial positioning position and each of the multiple candidate positions can be the Euclidean distance between the initial positioning position and each of the multiple candidate positions in the northeast-central coordinate system.

[0094] In one embodiment, the walking direction from the initial location to each of the multiple candidate locations can be obtained through the PDR (Pedestrian Dead Reckoning) system of the mobile terminal.

[0095] In one embodiment, the road direction of the road where each candidate location is located can be obtained based on city map data.

[0096] In one embodiment, the included angle θ corresponding to each of the multiple candidate locations can be obtained based on the walking direction from the initial positioning location to each candidate location and the road direction of the road where each of the multiple candidate locations is located.

[0097] In one embodiment, the PDR system of the mobile terminal can be used to obtain the displacement vector d_pdr for a set time (e.g., 5 s) from the initial positioning position to each of the multiple candidate positions; obtain the position vector d_cand of each of the multiple candidate positions relative to the current position (initial positioning position); calculate the angle between the displacement vector d_pdr and the position vector d_cand based on the displacement vector d_pdr and the position vector d_cand, and use the angle between the displacement vector d_pdr and the position vector d_cand as the angle θ between the walking direction and the road direction.

[0098] In one embodiment, the walking direction probability represents the probability that the walking direction of a user from the current location (initial location) to a candidate location is consistent with the direction of the road (the road where the current location is located). The walking direction probability P_walk for each of the multiple candidate locations can be calculated based on the angle θ between the walking direction and the road direction for each candidate location from the initial location; where, P_walk = 0.5 + 0.5 × cosθ.

[0099] In one embodiment, the probability of walking direction P_walk from the initial location to each of the multiple candidate locations can be used to calculate the map matching degree from the initial location to each of the multiple candidate locations.

[0100] In one embodiment, if the candidate road where the candidate location is located is a one-way road, the map matching degree of each candidate location is D_map, which is the distance from the initial location to the multiple candidate locations; where, D_map = (1-P_walk) + 2×I(oneway∧θ>90°); I is the penalty function. When the condition is oneway∧θ>90°, the penalty function value is 1. oneway∧θ>90° means that the candidate road where the candidate location is located is a one-way road and the angle θ between the walking direction and the road direction of the candidate road is greater than 90 degrees. When the condition is other (except oneway∧θ>90°), the penalty function value is 0.

[0101] In one embodiment, if the candidate road where the candidate location is located is a two-way road, the map matching degree of each candidate location is D_map, which is the distance from the initial location to the multiple candidate locations; where, D_map = (1- P_walk) + 0.5×I(θ>90°); When the condition is θ>90°, the penalty function value is 1. θ>90° means that the candidate road where the candidate location is located is a two-way road and the angle θ between the walking direction and the road direction of the candidate road is greater than 90 degrees. When the condition is other (θ≤90°), the penalty function value is 0.

[0102] In one embodiment, the initial positioning position P can be used as a reference. GNSS With the o-th candidate position P among multiple candidate positions o distance Walk from the initial location to the o-th candidate location P among multiple candidate locations. o The angle θ between the walking direction and the road direction o The map matching degree D_map between the initial location and the o-th candidate location among multiple candidate locations. o and distance First weight α, included angle θ o The second weight β and the map matching degree D_map o The third weight γ is used to calculate the residual score R of the o-th candidate position among multiple candidate positions. o ;in, R o =α× +β×θ o +γ×D_map o .

[0103] In one embodiment, the weights α, β, and γ are adaptive weights.

[0104] In one embodiment, the residual score R of the o-th candidate position among a plurality of candidate positions can be used as a basis. o The minimum residual score is obtained, and the candidate location corresponding to the minimum residual score is determined as the user's location when hailing a ride.

[0105] Step 209: Verify and correct the user's ride-hailing location based on the location determined by the PDR system of the mobile terminal, and determine the verified and corrected user ride-hailing location as the target location for the user's ride-hailing.

[0106] In one embodiment, the location of the user who hailed a taxi in step 207 (hereinafter collectively referred to as GNSS location P) can be used as the basis for the location. GNSS, calibThe GNSS location is determined using the PDR system of the mobile terminal, and the first PDR position of the GNSS location is obtained; the first PDR position is compared with the GNSS position P. GNSS, calib The heading angle of the PDR system is calibrated using a filter; then the GNSS position P is repositioned using the PDR system after the heading angle is calibrated. GNSS, calib Obtain GNSS position P GNSS, calib The second PDR position; using the second PDR position to determine the GNSS position P GNSS, calib The system performs verification and correction to obtain the verified and corrected location of the user's ride-hailing service, and then determines the verified and corrected location as the target location for the user's ride-hailing service.

[0107] In one embodiment, the PDR system can be initialized based on data from the mobile terminal's accelerometer and gyroscope, and the initial position P can be recorded. PDR,0 and initial heading angle θ PDR,0 The PDR system's PDR position and heading angle are updated based on accelerometer and gyroscope data for each sampling period (e.g., 100 milliseconds); based on GNSS position P... GNSS, calib The heading angle of the PDR system is calibrated using a Kalman filter or an extended Kalman filter (EKF) based on the PDR position.

[0108] In one embodiment, the GNSS position P can be repositioned by calibrating the PDR system after adjusting the heading angle. GNSS, calib Obtain GNSS position P GNSS, calib Second PDR position P PDR,calib According to the second PDR position P PDR,calib and GNSS position P GNSS, calib Obtain the second PDR position P PDR,calib With GNSS position P GNSS, calib distance Based on the prediction of the GNSS position P by the mobile terminal navigation system GNSS, calib Walk to the second PDR location P PDR,calib Navigation direction θnav and GNSS position P GNSS, calib Pointing to the second PDR position P PDR,calib The vector direction θcand is calculated; based on the navigation direction θnav and the vector direction θcand, the angle Δθ between the navigation direction θnav and the vector direction θcand is calculated; based on the angle Δθ, the position P from the GNSS is obtained. GNSS, calib Walk to the second PDR location P PDR,calib The probability of the walking direction; based on the probability of the walking direction, obtain the probability from the GNSS position P. GNSS, calibWalk to the second PDR location P PDR,calib Map matching degree D_map,calib; based on distance The GNSS position P is calculated using the included angle Δθ, map matching degree D_map,calib, and the first weight of distance, the second weight of included angle, and the third weight of map matching degree. GNSS, calib residual fraction R GNSS, calib ;in, R GNSS, calib =α× +β×Δθ+γ×D_map,calib.

[0109] In one embodiment, if GNSS position P GNSS, calib residual fraction R GNSS, calib If the residual score is less than the set residual score threshold, then the user's location in step 207 is determined as the user's final target location for the ride; if the GNSS location P GNSS, calib residual fraction R GNSS, calib If the residual score is greater than or equal to the set residual score threshold, the location of the user's ride-hailing in step 207 is corrected by the location located by the PDR system of the mobile terminal. The corrected location of the user's ride-hailing is determined as the final target location of the user's ride-hailing. The final target location of the user's ride-hailing is uploaded to the ride-hailing APP so that the ride-hailing APP can use the target location as the user's location to issue a ride-hailing order.

[0110] Step 210: Obtain the user's location when hailing a taxi through the PDR system of the mobile terminal.

[0111] In one embodiment, if the satellite signal quality score is less than a first set quality score threshold, the user's ride-hailing location can be obtained through the PDR system of the mobile terminal, and uploaded to the ride-hailing APP so that the ride-hailing APP can use the user's ride-hailing location as the user's location to issue a ride-hailing order.

[0112] The positioning method of this application embodiment obtains the initial positioning location of the user's ride-hailing service when the satellite signal quality score is greater than or equal to a first preset quality score threshold. The satellite signal quality score is a score that evaluates the quality of the satellite signal used by the positioning module to locate the initial positioning location. Based on the confidence interval of the positioning module and the initial positioning location, a search space is obtained. Based on the map data of the search space, candidate roads in the search space are obtained, including walkable and vehicular roads in the search space. According to a preset sampling rule, linear sampling is performed on the candidate roads to obtain multiple candidate locations. Based on the initial positioning location and the multiple candidate locations, a residual score is obtained for each candidate location, and the candidate location corresponding to the smallest residual score is determined as the user's ride-hailing positioning location. Even in urban canyon environments where satellite signals are blocked or reflected by tall buildings, reducing the positioning accuracy of the mobile terminal positioning module, the system can still correct the initial location of the user's ride-hailing location based on the positioning accuracy of the mobile terminal positioning module, provided the satellite signal quality score is greater than or equal to a first set quality score threshold. This improves the positioning accuracy of ride-hailing positioning and accurately locates the user's boarding position, solving the problem that the positioning accuracy of the mobile terminal positioning module cannot meet the positioning accuracy requirements of ride-hailing positioning in urban canyon environments, thus satisfying the positioning accuracy requirements of ride-hailing positioning.

[0113] Furthermore, in the positioning method of this application embodiment, if the road network side is identified based on the satellite signal from the initial positioning position determined by the positioning module, then the candidate roads are linearly sampled according to the set sampling rules to obtain multiple candidate positions of the candidate roads. This eliminates the need for pre-establishing a complex model to identify NLOS signals (Non-Line-of-Sight, satellite signals that propagate to the receiver via reflection or diffraction). When the road network side is identified based on the satellite signal from the initial positioning position determined by the positioning module, linear sampling of the candidate roads according to the set sampling rules to obtain multiple candidate positions of the candidate roads can exclude NLOS signals from the satellite signal, avoid the multipath effect caused by the superposition of NLOS and LOS signals, suppress the interference of NLOS signals on the positioning module's initial positioning position determination, and improve the positioning accuracy of the positioning module.

[0114] Furthermore, the positioning method in this application embodiment selects passable vehicle roads with nodes in a set buffer zone that have a pedestrian network as candidate roads; obtains the distance between the initial positioning position and each of the multiple candidate positions based on the initial positioning position and multiple candidate positions; obtains the walking direction probability from the initial positioning position to each of the multiple candidate positions based on the included angle; obtains the map matching degree from the initial positioning position to each of the multiple candidate positions based on the walking direction probability; obtains the residual score of each of the multiple candidate positions based on the distance, included angle, and map matching degree, and determines the candidate position corresponding to the minimum residual score as the user's positioning position for hailing a taxi. By combining pedestrian networks to select candidate roads, the system searches for the location closest to the actual location among multiple candidate locations on these roads to determine the user's ride-hailing location. These candidate locations satisfy road topology constraints and are accessible by vehicles on foot, thus improving the positioning accuracy of the user's ride-hailing location to the road network information level (less than 5 meters). The determined user ride-hailing location is not only a precisely located pick-up point but also a conveniently accessible pick-up point on foot, enhancing the user experience of the ride-hailing application.

[0115] Furthermore, the positioning method in this application verifies and corrects the user's ride-hailing location based on the location determined by the mobile terminal's PDR system, and then determines the verified and corrected user ride-hailing location as the user's target location. Utilizing the mobile terminal's PDR system to verify and correct the user's ride-hailing location further improves the positioning accuracy to the road network information level, enhancing the reliability and accuracy of the user's ride-hailing location and solving the problem of insufficient satellite positioning accuracy.

[0116] Corresponding to the aforementioned application function implementation method embodiments, this application also provides a positioning device and corresponding embodiments.

[0117] Figure 3 This is a schematic diagram of the positioning device shown in the embodiments of this application.

[0118] See Figure 3 The positioning device 1000 includes a memory 1010 and a processor 1020.

[0119] The processor 1020 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. Memory 1010 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM may store static data or instructions required by processor 1020 or other modules of the computer. Permanent storage devices may be read-write storage devices. Permanent storage devices may be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices use mass storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices may be removable storage devices (e.g., floppy disks, optical drives). System memory may be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. System memory may store some or all of the instructions and data required by the processor during operation. Furthermore, memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (e.g., DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, memory 1010 may include a removable storage device that is readable and / or writable, such as a laser disc (CD), a read-only digital multifunction optical disc (e.g., DVD-ROM, dual-layer DVD-ROM), a read-only Blu-ray disc, an ultra-high density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.

[0120] The memory 1010 stores executable code, which, when processed by the processor 1020, can cause the processor 1020 to execute part or all of the methods described above.

[0121] Furthermore, the method according to this application can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing some or all of the steps in the method described above.

[0122] Alternatively, this application may also be implemented as a computer-readable storage medium (or a non-transitory machine-readable storage medium or a machine-readable storage medium) storing executable code (or computer program or computer instruction code) which, when executed by a processor of a positioning device (or electronic device, or server, etc.), causes the processor to perform some or all of the steps of the methods described above according to this application.

[0123] This application also provides a computer program product, which includes computer instructions that, when executed by a processor, implement the method described above.

[0124] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A positioning method, characterized in that, include: If the satellite signal quality score is greater than or equal to a first set quality score threshold, the initial location of the user's ride-hailing location located by the mobile terminal positioning module is obtained, wherein the satellite signal quality score is a score that evaluates the quality of the satellite signal used by the positioning module to locate the initial location. The search space is obtained based on the confidence interval of the positioning module and the initial positioning position; Based on the map data of the search space, candidate roads of the search space are obtained, including walkable and vehicular roads of the search space. According to the set sampling rules, the candidate roads are linearly sampled to obtain multiple candidate positions of the candidate roads; Based on the initial location and the plurality of candidate locations, a residual score is obtained for each of the plurality of candidate locations, including: obtaining the walking direction from the initial location to each of the plurality of candidate locations based on the initial location and the plurality of candidate locations; obtaining the road direction of the road where each of the plurality of candidate locations is located based on the plurality of candidate locations; obtaining the angle between the walking direction and the road direction based on the walking direction and the road direction; obtaining the map matching degree from the initial location to each of the plurality of candidate locations based on the angle; and obtaining the residual score for each of the plurality of candidate locations based on the initial location, the plurality of candidate locations, the angle, and the map matching degree. The candidate location corresponding to the minimum residual score is determined as the user's ride-hailing location.

2. The method according to claim 1, characterized in that, The confidence interval includes the 95% error ellipse of the positioning module; The step of obtaining the search space based on the confidence interval of the positioning module and the initial positioning position includes: The search space is obtained with the initial positioning position as the center and k times the length of the major axis of the 95% error ellipse as the radius, where 1≤k≤5.

3. The method according to claim 1, characterized in that, The step of obtaining candidate roads in the search space based on the map data of the search space includes: Based on the map data of the search space, obtain the pedestrian network and accessible vehicular roads of the search space; The passable vehicle roads that have nodes of the pedestrian network in the designated buffer zone are selected as candidate roads.

4. The method according to claim 1, characterized in that, The step of linearly sampling the candidate roads according to a set sampling rule to obtain multiple candidate positions of the candidate roads includes: If the road network side is identified based on the satellite signal, the traffic attributes of the candidate road are obtained; wherein, the road network side is a binary label representing the user on one side of the candidate road; If the candidate road is determined to be a one-way road based on the traffic attributes, then the lane centerline of the candidate road that is a one-way road is linearly sampled according to a set step size to obtain multiple candidate positions of the candidate road. If the candidate road is determined to be a two-way road based on the traffic attributes, an offset distance is set for the lane centerline of the candidate road to be a two-way road, and a first-side virtual road segment and a second-side virtual road segment of the candidate road are obtained. If the user is determined to be on the first-side virtual road segment of the candidate road based on the road network side, the first-side virtual road segment is linearly sampled according to the set step size to obtain multiple candidate positions of the candidate road. If the user is determined to be on the second-side virtual road segment of the candidate road based on the road network side, the second-side virtual road segment is linearly sampled according to the set step size to obtain multiple candidate positions of the candidate road.

5. The method according to claim 1, characterized in that, The step of obtaining the residual score for each of the multiple candidate locations based on the initial positioning location, the multiple candidate locations, the included angle, and the map matching degree includes: Based on the initial positioning location and the plurality of candidate locations, the distance between the initial positioning location and each of the plurality of candidate locations is obtained; Based on the included angle, obtain the probability of the walking direction from the initial positioning position to each of the multiple candidate positions; Based on the walking direction probability, obtain the map matching degree of each candidate location from the initial location to the plurality of candidate locations; Based on the distance, the included angle, and the map matching degree, as well as the first weight of the distance, the second weight of the included angle, and the third weight of the map matching degree, the residual score of each of the plurality of candidate locations is obtained.

6. The method according to claim 1, characterized in that, The method includes: The location of the user's ride-hailing is verified and corrected based on the location determined by the pedestrian trajectory estimation system of the mobile terminal, and the verified and corrected location of the user's ride-hailing is determined as the target location of the user's ride-hailing.

7. The method according to claim 1, characterized in that, The method further includes: If the satellite signal quality score is less than the first set quality score threshold, the user's location when hailing a taxi is obtained through the pedestrian trajectory estimation system of the mobile terminal.

8. A positioning device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, It stores executable code that, when executed by a processor, causes the processor to perform the method as described in any one of claims 1-7.

Images