Indoor parking lot positioning method, computer device, storage medium and program product

Abstract

The application provides an indoor parking lot positioning method, computer equipment, a storage medium and a program product. The application can obtain a plurality of real-time received signal strengths (RSS) measured in a target area at a current time; receive a lane pattern database and a fingerprint database of the target area; determine a historical lane in which historical position data is located from a plurality of lanes in the lane pattern database according to the historical position data obtained by positioning in the target area at a historical time, the historical lane including a plurality of candidate position data; and perform positioning based on the plurality of real-time RSS, the plurality of candidate position data, and a plurality of RSS corresponding to each position data in the fingerprint database to obtain target position data at the current time. The application can perform positioning in combination with the historical position data at the historical time to obtain the target position data at the current time, thereby effectively improving positioning accuracy.

Description

Technical Field

[0001] This application relates to the field of terminal technology, and in particular to an indoor parking lot positioning method, computer equipment, storage medium, and program product. Background Technology

[0002] Currently, terminals can achieve location tracking using positioning systems, such as Wireless Fidelity (Wi-Fi) positioning systems. The process of a terminal using a Wi-Fi positioning system to locate itself in an indoor parking lot can involve measuring the Received Signal Strength (RSS) of the Wi-Fi signal from the access point (AP) and estimating the terminal's location based on the RSS. However, due to the significant fluctuations in Wi-Fi signals, the measured RSS is inaccurate, leading to a large discrepancy between the estimated location and the actual location in an indoor parking lot. Summary of the Invention

[0003] In view of this, it is necessary to provide an indoor parking lot positioning method, computer equipment, storage medium, and program product that can effectively improve the positioning accuracy of indoor parking lots.

[0004] The first aspect of this application provides a positioning method applied to a terminal, comprising: acquiring multiple real-time received signal strengths measured in a target area at the current time; receiving a lane pattern database and a fingerprint database of the target area, wherein the lane pattern database includes multiple lanes in the target area and multiple location data included in each lane, and the fingerprint database includes multiple RSSs corresponding to each location data; determining the historical lane where the historical location data is located from the multiple lanes in the lane pattern database based on historical location data obtained from positioning in the target area at a historical time, wherein the historical lane includes multiple candidate location data; and performing positioning based on multiple real-time RSSs, multiple candidate location data, and multiple RSSs corresponding to each location data to obtain the target location data at the current time.

[0005] The target area can include enclosed indoor spaces, such as indoor parking lots. The historical time can include times prior to the current time, and the historical location data for a historical time can be one or more, such as multiple historical location data for a single historical time, or multiple historical location data corresponding to multiple historical times. The historical lanes can include part or all of one or more lanes.

[0006] By adopting this technical solution, the historical lane where the historical location data is located can be obtained by combining historical location data at historical time. The target location data at the current time can be obtained by using multiple candidate location data included in the historical lane, multiple RSS corresponding to each location data, and multiple real-time RSS at the current time. This application introduces historical location data at historical time and combines it with multiple real-time RSS measured at the current time for positioning. Compared with positioning by using multiple real-time RSS at the current time, which may not be accurate, this application can effectively improve positioning accuracy.

[0007] In one possible implementation, based on historical location data obtained from locating the target area at a historical time, the historical lane where the historical location data is located is determined from multiple lanes in the lane pattern database. This includes: searching for matching location data that matches the historical location data from multiple location data in the lane pattern database; and determining the lane to which the matching location data belongs as the historical lane where the historical location data is located.

[0008] By adopting this technical solution, the historical location data at historical moments can be matched with the lane pattern database to determine the historical lane where the historical location data is located.

[0009] In one possible implementation, positioning is performed based on multiple real-time RSSs, multiple candidate location data, and multiple RSSs corresponding to each location data to obtain the target location data at the current moment, including:

[0010] Based on multiple location data in the fingerprint database and multiple RSSs corresponding to each location data, the initial location data corresponding to multiple matching RSSs that match multiple real-time RSSs are determined; based on multiple candidate location data of historical lanes, the initial location data is corrected to obtain the target location data at the current time.

[0011] By adopting this technical solution, the initial position data at the current moment can be determined first, and then the target position data at the current moment can be determined by correcting the initial position data.

[0012] In one possible implementation, the initial location data is corrected based on multiple candidate location data from historical locations to obtain the target location data at the current moment, including:

[0013] When the initial position data is any one of the multiple candidate position data, the initial position data is determined as the target position data at the current time; when the initial position data is not any one of the multiple candidate position data, the target position data at the current time is determined from the multiple candidate position data based on the initial position data.

[0014] By adopting this technical solution, the initial position data can be corrected to obtain the target position data at the current moment, which belongs to multiple candidate position data.

[0015] In one possible implementation, when the initial position data is not any of the multiple candidate position data, the target position data at the current moment is determined from the multiple candidate position data based on the initial position data, including:

[0016] When the initial position data is not any of the multiple candidate position data, the candidate position data that satisfies the target position data relationship with the initial position data is determined from the multiple candidate position data as the target position data at the current time.

[0017] By adopting this technical solution, the target location data at the current moment can be determined from multiple candidate location data based on the initial location data.

[0018] In one possible implementation, based on multiple location data in the fingerprint database and multiple RSSs corresponding to each location data, initial location data corresponding to multiple matching RSSs that match multiple real-time RSSs are determined, including:

[0019] A first positioning model is generated based on a fingerprint database. The first positioning model includes multiple location data and multiple RSSs for each location data. The initial location data corresponding to multiple matching RSSs that match multiple real-time RSSs are determined from the multiple RSSs of each location data using the first positioning model.

[0020] By adopting this technical solution, a first positioning model can be generated and used to determine the initial position data corresponding to multiple real-time RSSs at the current moment.

[0021] In one possible implementation, positioning is performed based on multiple real-time RSSs, multiple candidate location data, and multiple RSSs corresponding to each location data to obtain the target location data at the current moment, including:

[0022] In the fingerprint database, multiple RSSs corresponding to each candidate location data are determined; from the multiple RSSs corresponding to each candidate location data, multiple matching RSSs that match the multiple real-time RSSs are determined, and the candidate location data corresponding to the multiple matching RSSs are determined as the target location data.

[0023] By adopting this technical solution, the target location data at the current moment can be determined from multiple candidate location data and multiple RSS corresponding to each candidate location data, based on multiple real-time RSS at the current moment.

[0024] In one possible implementation, the location method also includes:

[0025] Based on the fingerprint database and lane pattern database, a second positioning model is generated. The second positioning model includes multiple lanes within the target area, multiple location data within each lane, and multiple RSSs for each location data.

[0026] Based on multiple real-time RSSs, multiple candidate location data of historical lanes, and multiple RSSs corresponding to each location data, the target location data at the current moment is obtained, including:

[0027] The second positioning model determines multiple RSSs corresponding to each candidate location data in multiple candidate location data. From the multiple RSSs corresponding to each candidate location data, multiple matching RSSs that match the multiple real-time RSSs are determined, and the candidate location data corresponding to the multiple matching RSSs are determined as the target location data.

[0028] By adopting this technical solution, a second positioning model can be generated and used to directly determine the target location data corresponding to multiple real-time RSSs at the current moment.

[0029] A second aspect of this application provides a method for generating lane pattern data, including:

[0030] Acquire multiple location data and their corresponding multiple sets of lane data collected within the target area, as well as the collection timestamp of each location data; map each location data in the multiple location data to a location grid to determine the multiple location grids corresponding to the multiple location data; connect the multiple location grids sequentially according to the collection timestamps of their corresponding location data to obtain at least one first trajectory data of the target area; expand the first trajectory data based on the multiple sets of lane data to obtain a lane pattern database of the target area, the lane pattern database including multiple lanes, each lane including multiple trajectory data, and each trajectory data including multiple location data.

[0031] By adopting this technical solution, the collected lane data can be extended to obtain a lane pattern database of the target space. Compared with the process of re-measuring and reconstructing the lane pattern database, this technical solution effectively improves the efficiency of obtaining the lane pattern database by utilizing the collected lane data.

[0032] In one possible implementation, the lane data includes width data and margin data, where the margin data is the distance between the position data corresponding to the lane data and the lane edge. The first trajectory data is expanded based on multiple sets of lane data to obtain a lane pattern database for the target area, including: determining multiple sets of first lane data corresponding to the position data in the first trajectory data; determining the width of the lane where the first trajectory data is located and the distance between the first trajectory data and the lane edge based on at least one width data and margin data in the multiple sets of first lane data; and expanding the first trajectory data based on the width and distance to obtain a lane pattern database for the target area.

[0033] In one possible implementation, the lane data includes lane type data. Multiple location grids are sequentially connected according to the timestamps of their corresponding location data to obtain at least one first trajectory data of the target area. This includes: sequentially connecting multiple location grids according to the timestamps of their corresponding location data to obtain at least one initial trajectory data of the target area; determining multiple sets of initial lane data corresponding to the initial trajectory data; and correcting the initial trajectory data according to at least one lane type data in the initial lane data to obtain at least one first trajectory data of the target area.

[0034] A third aspect of this application provides a data acquisition method, including:

[0035] The data acquisition client displays the acquisition interface, which includes a real-time image of the target area and a detection control. The real-time image includes the lane image area corresponding to the lane to be acquired in the target area. In response to a trigger operation on the detection control, the real-time image is recognized, and based on the recognition result, a suggested route for the data acquisition device in the lane to be acquired and the corresponding acquisition suggestion information are determined. The acquisition suggestion information is used to instruct the data acquisition device to acquire data along the suggested route in the lane to be acquired. The acquisition suggestion information for the lane to be acquired is displayed in the lane image area.

[0036] The data acquisition client can run on a computer device. It can display data acquisition suggestion information and generate a partial lane pattern map of the target area based on the acquired lane data and fingerprint data.

[0037] By adopting this technical solution, data collection suggestion information can be generated on the data collection client for the current lane to be collected, so that users can collect data according to the collection suggestion information, thereby obtaining the required data, improving the user collection experience and increasing data collection efficiency.

[0038] In one possible implementation, the acquisition suggestion information includes acquisition suggestion lines drawn in the lane image area. The acquisition suggestion lines include at least one of a suggestion direction line, a suggestion edge distance line, and a suggestion center distance line. The suggestion direction line indicates the direction of data acquisition, the suggestion edge distance line indicates the distance of the data acquisition device from the edge line of the lane, and the suggestion center distance line indicates the distance of the data acquisition device from the center line of the lane.

[0039] By adopting this technical solution, users can be provided with simple and clear data collection suggestions, which helps them to accurately collect data based on these suggestions.

[0040] In one possible implementation, in response to a trigger operation on the detection control, the real-time image is identified, and based on the identification result, acquisition suggestion information for the lane to be acquired is determined, including: in response to a trigger operation on the detection control, the real-time image is identified to obtain the width data and edge line data of the lane to be acquired; based on the width data, the number of suggested lines for the lane to be acquired and the number of suggested lines for the lane image area are determined; based on the edge line data, the number of suggested lines, and the number of suggested lines, the distance of each suggested line from the edge line of the lane to be acquired and the position of each suggested line in the lane image area are determined.

[0041] By adopting this technical solution, the width and edge data of the lane to be collected can be identified, and then the collection suggestions for the lane to be collected can be determined.

[0042] Fourthly, this application provides a computer device including at least one processor and a memory. The memory is used to store instructions, and the processor is used to execute the instructions to implement the positioning method of the first aspect, the lane pattern data generation method of the second aspect, and the data acquisition method of the third aspect.

[0043] Fifthly, this application provides a computer-readable storage medium storing a program that causes a computer device to perform the positioning method of the first aspect, the lane pattern data generation method of the second aspect, and the data acquisition method of the third aspect.

[0044] Sixthly, this application provides a computer program product including computer-readable instructions that, when executed by one or more processors, implement the positioning method of the first aspect, the lane pattern data generation method of the second aspect, and the data acquisition method of the third aspect.

[0045] Understandably, the computer equipment provided in the fourth aspect, the computer-readable storage medium provided in the fifth aspect, and the computer program product provided in the sixth aspect correspond to the methods provided in the first, second, or third aspects. Therefore, the beneficial effects or various implementation methods that they can achieve can be referred to above, and will not be repeated here. Attached Figure Description

[0046] Figure 1 A schematic diagram illustrating an implementation scenario of the indoor parking lot positioning method provided in this application;

[0047] Figure 2 A flowchart illustrating the indoor parking lot positioning method provided in this application;

[0048] Figure 3 A schematic diagram illustrating the implementation of the indoor parking lot positioning method provided in this application;

[0049] Figure 4 A user interface diagram illustrating the indoor parking lot positioning method provided in this application;

[0050] Figure 5 Another user interface diagram for the indoor parking lot positioning method provided in this application;

[0051] Figure 6 Another user interface diagram for the indoor parking lot positioning method provided in this application;

[0052] Figure 7 A schematic diagram of the data collection route for the indoor parking lot positioning method provided in this application;

[0053] Figure 8 Another flowchart illustrating the indoor parking lot positioning method provided in this application;

[0054] Figure 9 Another user interface diagram for the indoor parking lot positioning method provided in this application;

[0055] Figure 10 Another data collection route diagram for the indoor parking lot positioning method provided in this application;

[0056] Figure 11 Another data collection route diagram for the indoor parking lot positioning method provided in this application;

[0057] Figure 12 Another data collection route diagram for the indoor parking lot positioning method provided in this application;

[0058] Figure 13 Another flowchart illustrating the indoor parking lot positioning method provided in this application;

[0059] Figure 14 A schematic diagram of the lane layout stage for the indoor parking lot positioning method provided in this application;

[0060] Figure 15 Another lane layout diagram stage of the indoor parking lot positioning method provided in this application;

[0061] Figure 16 Another lane layout diagram stage of the indoor parking lot positioning method provided in this application;

[0062] Figure 17 Another lane layout diagram stage of the indoor parking lot positioning method provided in this application;

[0063] Figure 18 Another flowchart illustrating the indoor parking lot positioning method provided in this application;

[0064] Figure 19 Another user interface diagram for the indoor parking lot positioning method provided in this application;

[0065] Figure 20 A schematic diagram of the architecture of the indoor parking lot positioning method provided in this application;

[0066] Figure 21 Another flowchart illustrating the indoor parking lot positioning method provided in this application;

[0067] Figure 22 Example diagram showing the corrected results of the indoor parking lot positioning method provided in this application;

[0068] Figure 23 Another schematic diagram of the indoor parking lot positioning method provided in this application;

[0069] Figure 24 Another flowchart illustrating the indoor parking lot positioning method provided in this application;

[0070] Figure 25 Example diagram illustrating the scope determination of the indoor parking lot positioning method provided in this application;

[0071] Figure 26 A schematic diagram of the structure of the computer device provided in this application. Detailed Implementation

[0072] It should be noted that in this application, "at least one" means one or more, and "more than one" means 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, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or sequence.

[0073] When computer equipment performs real-time positioning in an indoor parking lot, it can estimate the positioning result based on the RSS (Responsibility Scale) of multiple measured Wi-Fi signals. This estimation can be achieved through a positioning model, which can be built from a fingerprint database. The fingerprint database can include multiple location data points within the indoor parking lot, along with the corresponding RSS values ​​for each location. Therefore, during real-time positioning, the positioning model can query the fingerprint database for the location data corresponding to the measured RSS values; this location data is the positioning result. However, because Wi-Fi signals fluctuate within an indoor parking lot, the RSS values ​​measured by the computer equipment may have significant errors, leading to a lower accuracy rate for the positioning result obtained by the positioning model.

[0074] This application provides an indoor parking lot positioning method. The indoor parking lot positioning method can be integrated into one or more computer devices. The computer devices may include at least one of a terminal, a server, etc. The terminal may include a smartphone, laptop, tablet, smart wearable device, in-vehicle smart terminal, etc. The server may include a local server, cloud server, etc., and the terminal and server can be connected via wired or wireless means, etc.

[0075] For example, see Figure 1 The indoor parking lot positioning method of this application can be implemented jointly by terminal 10 and server 20. Terminal 10 and server 20 are connected via wired or wireless means. Terminal 10 is used to collect fingerprint data and lane data on the lanes of the indoor parking lot and send the fingerprint data and lane data to server 20. Server 20 is used to store the received fingerprint data and lane data into a fingerprint database and a lane database, respectively. Server 20 is also used to establish a lane pattern database of the indoor parking lot based on the data in the fingerprint database and the lane database.

[0076] Terminal 10 is also configured to respond to a location request initiated by the user interface and send multiple RSS feeds collected in real time during its movement to server 20 according to the location request. Server 20 is also configured to determine the target location of terminal 10 at the current moment based on the multiple RSS feeds at each moment and on a fingerprint database and a lane pattern database. In another embodiment, server 20 is also configured to send target location information to terminal 10, so that terminal 10 can display its current location to the user on the user interface.

[0077] Specifically, please refer to the following: Figure 2 and Figure 3 , Figure 2 A flowchart illustrating the indoor parking lot location method. Figure 3 This is a schematic diagram illustrating the implementation of an indoor parking method, such as... Figure 2 and Figure 3 As shown, the indoor parking lot positioning method of this application may include the following steps.

[0078] 101. Data Acquisition.

[0079] For example, data can be collected in the driveways of an indoor parking lot using data acquisition devices. For instance, such as... Figure 3 As shown in p1, the following data is collected when a user drives a vehicle in an indoor parking lot: 1) location data at different locations; 2) RSS of the Wi-Fi signal emitted by different access points (APs) at each location; 3) lane type data (e.g., one-way, two-way), width data, and distance data from the edge of the lane at each location. Figure 3 As shown in p2, fingerprint database and lane database can be obtained from the collected data.

[0080] 102. Establish a lane pattern database.

[0081] Specifically, a lane pattern database can be established based on fingerprint and lane databases. For example... Figure 3 As shown on page 3, the data in the lane pattern database can characterize the lane pattern map of an indoor parking lot.

[0082] 103. Establish a positioning model.

[0083] The positioning model can be built based on the fingerprint database, or it can be built based on both the fingerprint database and the lane pattern database.

[0084] 104. Online positioning.

[0085] Online positioning can be performed based on a lane pattern database, a positioning model, and multiple RSS feeds received at the current moment, as shown in p5 of the figure, to determine the user's current location.

[0086] The indoor parking lot positioning method of this application can perform positioning based on a positioning model generated from a lane pattern database and a fingerprint database. Compared with the prior art, which only uses a positioning model generated from a fingerprint database for positioning, this application can effectively improve the accuracy of positioning results.

[0087] In implementing the indoor parking lot positioning method, this application also provides multiple user interfaces displayed on a computer device to facilitate information interaction with the user. These user interfaces can display data collection suggestions, a layout map of the indoor parking lot, and / or the current location obtained through real-time positioning when the user is collecting data via the computer device. The computer device may include at least one display screen, which can display different user interfaces at different stages of data collection. For example, multiple user interfaces can be displayed sequentially on one display screen or separately on different display screens; the specific handling can be flexible in practical applications and is not limited here.

[0088] For example, such as Figure 4 Terminal 10 can display a user interface a1, which includes a suggestion information control a01, a lane layout map control a02, and a current location control a03. When the user triggers the suggestion information control a01, terminal 10 can display collected suggestion information for the current lane on user interface a2 (as shown in the suggested travel route a001 in the figure); when the user triggers the lane layout map control a02, terminal 10 can display the layout map of the indoor parking lot generated based on the collected data on user interface a3; when the user triggers the current location control a03, terminal 10 can display the user's current location in the indoor parking lot on user interface a4 (as shown in the current location icon a003 in the figure).

[0089] It should be noted that the users in this application may include objects that use computer devices that integrate some or all of the steps of the indoor parking lot positioning method. These objects may include developers, users, intelligent robots, testing machines, etc.

[0090] This embodiment will describe the process by which a user uses a data acquisition device to collect data on the lanes of an indoor parking lot to obtain a fingerprint database and a lane database.

[0091] The fingerprint database can include multiple sets of fingerprint data. Each set of fingerprint data can include a location data point and multiple RSS values ​​corresponding to that location data. The location data can be the latitude and longitude of a specific location collected by the data acquisition device in the indoor parking lot, and the RSS values ​​can be the signal strength of Wi-Fi signals received by the data acquisition device from different access points at that latitude and longitude. The lane database can include multiple sets of lane data. Each set of lane data can include the type data (e.g., one-way or two-way) and width data of the lane where a specific location is located in the indoor parking lot, as well as the distance data from that location to the edge line of its lane.

[0092] Data acquisition devices can include one or more computer devices, professional acquisition instruments, etc. When there are multiple data acquisition devices, they can be connected together via wired or wireless means. Computer devices can include terminals, such as smartphones, smart vehicle terminals, smart wearable devices, smart cameras, drones, etc. Users can control the data acquisition devices to move along the lane in an indoor parking lot. During the movement, the data acquisition devices collect fingerprint data and lane data on the lane. The methods of controlling the movement of the data acquisition devices can be such as fixing the data acquisition devices to a vehicle and having the user drive the vehicle to move along the lane, or controlling a drone with the data acquisition devices fixed to it to move, etc.

[0093] For example, the terminal and high-precision positioning instrument can be fixed to a vehicle. The high-precision positioning instrument can be an inertial measurement unit and inertial detector based on iNAV-RQH (Inertial Gyro Navigation System) with a high navigation level. Users can drive the vehicle in the lanes of an indoor parking lot and collect data through the terminal and high-precision positioning instrument. The terminal can collect multiple RSSs from each set of fingerprint data, as well as all lane data, while the high-precision positioning instrument can collect the position data from the fingerprint data. The terminal and high-precision positioning instrument can upload the collected data to a cloud server in real time, storing the fingerprint data in a fingerprint database and the lane data in a lane database.

[0094] Lane data can be collected in various ways. For example, lane images can be collected by image acquisition devices or image acquisition modules on computer devices, and the computer devices can then identify the lane images to obtain lane data.

[0095] The fingerprint data and lane data collected in this application can be stored in a fingerprint database and a lane database, respectively. The fingerprint database and lane database can be set in the data collection device or in other computer devices (such as servers). The specific handling is flexible and no restrictions are imposed here.

[0096] In this embodiment of the application, in order to collect fingerprint data and lane data that can fully describe the indoor parking lot lanes, during the manual collection process, the data collection device can display collection suggestion information for the current lane to prompt the user to collect data according to the collection suggestion information.

[0097] In this embodiment, a manual data collection application can be installed on the data collection device. The user interface of the manual data collection application can display collection suggestion information, which may include one or more forms such as voice, video, text, and images. Several controls can be used to display the collection suggestion information. It should be noted that the controls can be a combination of one or more forms such as buttons, edit boxes, selection boxes, and text boxes. User actions on the controls can include one or more combinations of actions such as clicking, swiping, and long-pressing. These can be flexibly set and processed in actual applications and are not limited here.

[0098] For example, after a user enables a manual data collection application, such as Figure 5 As shown, the manual data collection application can display a collection interface a01. The collection interface c01 includes a real-time image 001 of the indoor parking lot captured by the data collection device and a detection control 002. The real-time image 001 includes an image of the lane to be collected. The data collection device can respond to the user's trigger operation on the detection control 002, recognize the image in the real-time image 001, and display collection suggestion information for that lane on the collection interface a01 based on the recognition result.

[0099] There are several ways to display collected suggestion information, such as Figure 5 As shown, after the data acquisition device recognizes the image in the real-time screen 001, it can display a data acquisition suggestion box 003 on the acquisition page c02. The data acquisition suggestion box 003 can include data acquisition suggestion text, which can be read by the user. The user can refer to the information provided in the data acquisition suggestion text to perform data acquisition; for example, Figure 5 As shown, after the data acquisition device recognizes the image in the real-time screen 001, it can display acquisition suggestion lines on the acquisition page c03. The real-time screen displays suggestion direction lines 0041, suggestion margin lines 0042, and suggestion center distance lines 0043. The user can move in the direction pointed to by suggestion direction line 0041. During the movement, the user can use suggestion margin lines 0042 and suggestion center distance lines 0043 as boundary lines to control the data acquisition device to perform data acquisition within the area defined by suggestion editing lines 0042 and suggestion center distance lines 0043.

[0100] The collection suggestion information in this embodiment can be determined by the recognition results of the image in the real-time screen, and there can be a variety of specific methods.

[0101] In some embodiments, the data acquisition device can identify the position of lane edge lines in an image (i.e., edge line data) and determine a suggested route for user data acquisition based on the position of the lane edge lines. The suggested route can be: traveling along a suggested route at a preset distance from the edge line of a single lane, such as... Figure 6 The data collection page displays the suggested line d001, which can be used as a reference. Figure 6 The diagram shows the line d001 indicating the driver is driving a vehicle, and the user is on the road as follows: Figure 7 As shown, the vehicle is driven along the suggested route 1 to collect data.

[0102] In some embodiments, a lane can be data collected once or multiple times. Specifically, the data acquisition device can identify the type and width of the lane in the image, such as... Figure 8 As shown, if the lane is bidirectional, the positions of the lane centerline and edge line can be determined. Then, it is determined whether the lane width is greater than a preset first value. If it is not greater, the distances from the suggested route to the centerline and edge line can be determined respectively. The suggested information can be collected as follows: travel along the suggested route that is a preset first distance from the centerline and a preset second distance from the edge line. Figure 9 The data collection page displays d02, which can show the first schematic line d021 and the second schematic line d022 of the suggested route. Users can then... Figure 10 As shown, the driving vehicle collects data along a suggested route that is a preset first distance from the center line and a preset second distance from the edge line.

[0103] If the lane is one-way, the position of the edge line can be determined, and then it can be checked whether the lane width is greater than a preset first value. If it is not greater, the distance from the suggested route to the edge line can be determined. The suggested information collected includes: traveling along the suggested route at a preset distance from the lane edge line. The data collection page illustration and user data collection illustration can be referenced respectively. Figure 6 and Figure 7 .

[0104] If the lane width is greater than a preset first value but not greater than a preset second value, it can be determined that the lane needs to undergo two data collections (e.g., data collection near the left and right sides of the lane). Based on the position of the lane edge line, the user's first and second suggested routes are determined. The collected suggested information may include: traveling along the first suggested route for the first time, and then traveling along the second suggested route for the second time. The first suggested route is at a preset third distance from the lane edge line, and the second suggested route is at a preset fourth distance from the lane edge line. The user can then... Figure 11 As shown, the driving vehicle collects data along the first suggested route and the second suggested route in a one-way lane.

[0105] If the width of a single lane is greater than a preset second value, it can be determined that the lane needs to undergo three data collections (e.g., data collection near the left, middle, and right sides of the lane). Based on the position of the lane edge line, the user's third, fourth, and fifth suggested routes are determined. The collected suggested information may include: traveling along the third suggested route for the first time, then along the fourth suggested route for the second time, and finally along the fifth suggested route for the third time. The third suggested route is at a preset fifth distance from the lane edge line, the fourth suggested route is at a preset sixth distance, and the fifth suggested route is at a preset seventh distance. Users can then... Figure 12 As shown, the driving vehicle collected data along the third, fourth, and fifth suggested routes in one-way lanes.

[0106] It should be noted that the suggested route described in this application embodiment is only an example. In actual application scenarios, when collecting data, the form of the suggested route and the way users refer to the suggested route for data collection can be flexibly handled according to actual needs.

[0107] This embodiment can output data collection suggestions to the user in real time based on the lane conditions, making it easier for the user to collect data according to the suggestions, thus improving the efficiency of data collection and the user experience.

[0108] This application embodiment will describe the process of establishing a lane pattern database. The lane pattern database may include information data and direction data of multiple lanes. The direction data of a lane can represent the direction of the lane, and the information data of a lane can include multiple location data within the lane. The data in the lane pattern database can represent the lane pattern diagram of an indoor parking lot.

[0109] Specifically, see Figure 13 The process of establishing lane pattern data can include:

[0110] 201. The computer device maps the location data in the fingerprint database to different location grids.

[0111] For example, participate Figure 14 The six location data points are mapped sequentially into six location grids.

[0112] 202. The computer equipment establishes directional trajectory data based on the lane type data in the lane database and the grid at each location.

[0113] For example, see Figure 15 Based on the timestamps of the lane data, the position grids are connected sequentially according to the timestamps to obtain two trajectory data. The direction of the trajectory data is the direction in which the position grids are connected.

[0114] Based on the timestamps of lane type data in the lane database, determine the lane type data corresponding to each location grid, such as... Figure 15 All grid locations in the data correspond to lanes of a two-way type, allowing for correction of the trajectory data based on lane type, such as... Figure 16 The trajectory data formed by connecting position grid 1, position grid 2 and position grid 3 is corrected. Since position grid 2 is on the other one-way lane of the two-way lane, and the data collection process recommends that the user collect data along the line parallel to the edge of the lane, multiple position data on a straight line should be obtained. Therefore, position grid 2 needs to be removed here, and position grid 1 and position grid 3 are directly connected to obtain the corrected trajectory data.

[0115] 203. The computer equipment expands the trajectory data based on the width and margin data in the lane database to obtain a directional lane pattern map, and saves the lane pattern map in the lane pattern database.

[0116] Each location grid represents a region within the indoor parking lot. The trajectory data can be expanded based on the lane width data of the location grid in the lane database, as well as the distance from the lane edge to the corresponding location data within the lane. This allows for the identification of trajectory data for areas within the lane that were not previously collected. Figure 17 Based on the width data, new trajectory data is inserted into the grid area of ​​the adjacent lane data. Based on the edge distance data, new trajectory data is inserted into the grid area of ​​the lane edge to obtain the lane layout map. The direction of the lane is the direction of the initially established trajectory data. By performing the above operations on all lanes, the lane layout map of the indoor parking lot can be obtained and saved in the lane layout database.

[0117] In the embodiments of this application, such as Figure 18 It can map location data from the fingerprint database to the location grid, establish trajectory data based on lane type data from the lane database, and correct and confirm the established trajectory data. Then, based on the lane width and margin data from the lane database, it can expand the trajectory data on the lane to obtain richer location data on the lane, thereby obtaining the lane pattern database.

[0118] This application can quickly deduce the lane layout diagram of an indoor parking lot based on existing fingerprint and lane databases.

[0119] In this embodiment of the application, the data acquisition device can collect data during movement, and the manual data acquisition application can display a lane pattern map generated from the collected location data and lane data.

[0120] For example, users can collect lane data and multiple RSS feeds in real time using their smartphones, and collect location data in real time using high-precision positioning instruments. The smartphones and high-precision positioning instruments can upload the collected data to the server in real time. The server can generate a lane layout map of the indoor parking lot in real time based on the location data and multiple RSS feeds stored in the fingerprint database, as well as the lane data stored in the lane database. The server transmits the lane layout map to the smartphone, and the smartphone displays the lane layout map on its user interface.

[0121] Specifically, users can trigger a lane layout map control on the user interface, and the computer device can respond to this trigger and display the generated lane layout map. For example, when participating in... Figure 4 The data acquisition device can display a user interface a1, which includes a suggestion information control a01, a lane layout control a02, and a current location control a03. When the user triggers the lane layout control a02, the terminal 10 can display the layout of the indoor parking lot generated based on the collected data on the user interface a3.

[0122] In some embodiments, the computer device can also perform quality inspection on the collected location data and lane data. The quality inspection method may include: if the number of sets of location data and / or lane data collected in a specific area / lane is greater than a preset threshold, then the quality inspection is determined to be qualified; otherwise, the quality inspection is unqualified. If the quality inspection is unqualified, the specific area / lane needs to be re-collected. For example, if the number of sets of location data and lane data in lane 1 is greater than a preset threshold 1, then lane 1 is determined to be qualified. If the number of sets of location data in lane 2 is less than a preset threshold 1, then lane 2 is determined to be unqualified.

[0123] The manual data collection application can also display the quality inspection results on the layout map interface, prompting the user to re-collect data for the areas where the quality inspection data failed. The user triggers the lane layout map control a02, such as... Figure 19 The manual data collection application displays the lane layout map on screen A3, and clearly marks lane 1 (i.e., the lane containing the qualified data) on the lane layout map. Figure 19 The area containing several dots), lane 2 where the data collection failed (i.e., the lane where the quality inspection failed data), i.e. Figure 19 The area containing several diagonal lines), and the uncollected data area 3 (i.e. Figure 19 (the gray area in the image).

[0124] This application embodiment can quickly deduce the lane layout map of an indoor parking lot based on existing fingerprint database and lane database, and display the lane layout map on the user interface for users to view in real time. This application embodiment can also display whether the collected data is qualified on the lane layout map displayed on the user interface, and then prompt the user to re-collect data for the lanes with unqualified data.

[0125] The following section will describe the process of establishing the positioning model and online positioning in this application.

[0126] In this embodiment of the application, the process of establishing a positioning model and online positioning can be implemented by a computer device, see [link to relevant documentation]. Figure 20 Data collection yields fingerprint and lane databases, which are then used to build a lane pattern database. A positioning model can be built from the fingerprint database. During online positioning, multiple real-time online measurements of RSS can be input into the positioning model, which can output the initial position data at the current moment (i.e., the original positioning result in the figure). The computer equipment can combine the lane pattern database to correct the initial position data and obtain the target position data at the current moment (i.e., the final positioning result in the figure).

[0127] Specifically, the fingerprint database includes multiple sets of fingerprint data. Each set of fingerprint data includes location data and multiple RSSs. When a vehicle is in motion and needs to be located, the positioning model can query the fingerprint database for location data that matches the multiple RSSs at the current moment. The location indicated by this location data is the initial location at the current moment. The computer equipment can determine the historical lane where the historical location data is located based on the lane pattern database, identify some or all of the location data contained in the historical lane as candidate location data, and correct the initial location data based on the candidate location data in the historical lane to obtain the target location data of the terminal at the current moment.

[0128] It should be noted that the execution order of the steps to determine the initial position at the current moment and the steps to determine the historical lane can be flexibly adjusted according to factors such as the application scenario and the performance of the computer equipment. For example, the steps to determine the historical lane can be executed first, followed by the steps to determine the initial position at the current moment, or the steps to determine the historical lane and the steps to determine the initial position at the current moment can be executed simultaneously.

[0129] Here, the historical moment can be a moment before the current moment. The lane pattern database includes multiple lanes and multiple location data within each lane. You can search for matching location data that matches the historical location data of the historical moment in the lane pattern database. Matching location data includes location data that is the same as the historical location data, location data that is adjacent to the historical location data, etc., and the lane to which the matching location data in the lane pattern database belongs is determined as the historical lane.

[0130] In this process, multiple candidate location data can be determined from all location data included in the historical lanes. Specifically, based on the directionality of the historical lanes, a portion of the lanes ahead of the matching lane data can be determined from the historical lanes, and the location data within this portion of the lanes is the candidate location data.

[0131] If the initial position is not any of the candidate position data, the initial position at the current moment is corrected, and the target position data is determined from the multiple candidate position data; if the initial position is any of the multiple candidate position data, then the initial position at that moment is determined as the target position data at that moment.

[0132] For example, see Figure 21 It can query the lane where the historical position was at t-1 seconds from the lane pattern database, query the type of the lane where the initial position is at the current moment, and correct the initial position to the lane where it was at t-1 seconds based on the lane type to obtain the final positioning result at the current moment.

[0133] For example, see Figure 22 The diagram shows several examples of corrected positioning results. It should be noted that historical position data can be the final positioning point at time t-1 (as described below), initial position data can be the final positioning point at time t (as described below), and target position data can be the final positioning point at time t-1 (as described below). The target position data relationship between the initial position data and the target position data can be described as both being on the same horizontal line, or the angle between the line connecting them and the horizontal line being 45 degrees, etc. In example 1, the final positioning point at time t-1 is on a one-way lane, and the original positioning point at time t is in a non-lane area next to the one-way lane. The final positioning point at time t can be corrected to be in front of the final positioning point at time t-1 in the one-way lane. At this point, the target position data relationship is on the same horizontal line. Similarly, in example 2, the final positioning point at time t-1 is on the right lane of a two-way road, and the original positioning point at time t is on the left lane of a two-way road. The final positioning point at time t can be corrected to be in front of the final positioning point at time t-1 in the right lane of a two-way road. At this point, the target position data relationship is on the same horizontal line.

[0134] In Example 3, the final location point at t-1 seconds is on the right-hand lane, and the original location point at t seconds is on the left-hand lane, separated from the right-hand lane by a non-lane area. The final location point at t seconds can be corrected to be in front of the final location point at t-1 seconds in the right-hand lane. At this time, the target position data relationship is on the same horizontal line. In Example 4, the final location point at t-1 seconds is on the longitudinal straight-ahead lane, and the original location point at t seconds is on the transverse straight-ahead lane that intersects with the longitudinal straight-ahead lane. The final location point at t seconds can be corrected to be in front of the final location point at t-1 seconds in the longitudinal straight-ahead lane, at the intersection of the two lanes. At this time, the target position data relationship is on the same horizontal line.

[0135] In Example 5, the final positioning point at t-1 seconds is on the longitudinal straight-ahead one-way lane, and the original positioning point at t seconds is in the non-lane area adjacent to the longitudinal straight-ahead one-way lane. The final positioning point at t seconds can be corrected to: the front side of the final positioning point at t-1 seconds in the longitudinal straight-ahead one-way lane. At this time, the target position data relationship is on the same horizontal line. In Example 6, the final positioning point at t-1 seconds is at the boundary between the longitudinal straight-ahead one-way lane and the intersection area where straight-ahead or left / right turns are allowed. The original positioning point at t seconds is in the non-lane area adjacent to the intersection area. The final positioning point at t seconds can be corrected to: the center position of the intersection area. At this time, the target position data relationship is that the angle between the connecting line and the horizontal line is 45 degrees.

[0136] The embodiments of this application can combine lane pattern data maps to correct the initial position data obtained from multiple RSSs, which may not be accurate, thereby effectively improving the positioning accuracy of indoor parking lots.

[0137] In this embodiment of the application, the process of establishing a positioning model and online positioning can be implemented by a computer device, see [link to relevant documentation]. Figure 23 Data collection yields fingerprint and lane databases, which are then used to build a lane pattern database. A positioning model can then be built from these databases. During online positioning, multiple real-time online measurements of RSS data can be input into the positioning model, which can then output the target location data at the current moment (i.e., the final positioning result in the figure).

[0138] Specifically, when determining the target location at the current moment, the positioning model can first determine the historical lane to which the historical location data belongs in the lane pattern database based on the historical location data at historical moments. The historical lane includes multiple candidate location data, which can be part or all of the location data contained in the historical lane. Then, based on the multiple RSSs at the current moment, the target location data at the current moment is determined from the multiple candidate location data, and the target location data is output.

[0139] For example, seeFigure 24 The positioning model can search the lane range of the historical location of t-1 in the lane pattern database, and then determine the lane where the historical location of t-1 is located. The lane is set as the area where the positioning result is located at the current time. Based on the multiple RSS received at the current time, the positioning model determines the location data corresponding to these multiple RSS from all the location data in the lane. This location data is the final positioning result at the current time.

[0140] For example, see Figure 25 It should be noted that historical location data can be the final location point at t-1 seconds as described below, and the range defined by multiple candidate location data can be the location result range at the current moment as described below. The figure shows an example of determining the location result range at the current moment based on the location result at t-1 seconds. In example 1, the one-way lane where the t-1 location point is located is the location result range at t seconds. In example 2, the right lane of the two-way lane where the t-1 location point is located is the location result range at t seconds. In example 3, the one-way straight lane of the intersection where the t-1 location point is located is the location result range at t seconds. In example 4, the multi-way lane of the intersection where the t-1 location point is located is the location result range at t seconds.

[0141] This application embodiment can combine lane pattern maps to limit the range of positioning results of multiple RSSs that may not be accurate, thereby outputting more accurate positioning results and effectively improving the positioning accuracy of indoor parking lots.

[0142] For example, in the underground parking lot of a shopping mall, as shown in the table below, the circular error probability (CEP) of the positioning results varies at different locations on different floors for the indoor parking lot positioning method of this application (Wi-Fi positioning algorithm using lane pattern data correction) and the existing positioning method (Wi-Fi positioning algorithm without lane pattern data). CEP68 and CEP95 refer to a 68% and 95% circular error probability, respectively. For example, if the verification floor is AB2 of the shopping mall and the mobile phone location is A, the value of CEP68 is 5.3 meters and the value of CEP95 is 15.6 meters. Here, it means that the positioning result obtained by the positioning algorithm has a 68% probability of being less than 5.3 meters and a 95% probability of being less than 15.6 meters relative to the circular error centered on the mobile phone location A.

[0143] Table 1

[0144]

[0145] As shown in Table 1, the CEP of the Wi-Fi positioning algorithm in this application when using lane pattern data for correction is significantly lower than that of the Wi-Fi positioning algorithm without lane pattern data at the same floor and location. This indicates that the method in this application can significantly reduce positioning error and improve positioning accuracy.

[0146] refer to Figure 26 This is a schematic diagram of the hardware structure of the computer device 100 provided in an embodiment of this application. Figure 26 As shown, the computer device 100 may include a screen 1001, a processor 1002, a memory 1003, and a communication bus 1004. The memory 1003 is used to store one or more computer programs 1005. The one or more computer programs 1005 are configured to be executed by the processor 1002. The one or more computer programs 1005 include instructions that can be used to implement all or part of the steps of the indoor parking lot positioning method in the computer device 100.

[0147] It is understood that the structure illustrated in this embodiment does not constitute a specific limitation on the computer device 100. In other embodiments, the computer device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. For example, the computer device 100 may also include a camera.

[0148] Processor 1002 may include one or more processing units, such as application processors (APs), modems, graphics processing units (GPUs), image signal processors (ISPs), controllers, video codecs, digital signal processors (DSPs), baseband processors, and / or neural network processing units (NPUs). These different processing units may be independent devices or integrated into one or more processors.

[0149] The processor 1002 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 1002 is a cache memory. This memory can store instructions or data that the processor 1002 has just used or that are used repeatedly. If the processor 1002 needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces the waiting time of the processor 1002, and thus improves the efficiency of the system.

[0150] In some embodiments, the processor 1002 may include one or more interfaces. Interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a SIM interface, and / or a USB interface, etc.

[0151] In some embodiments, memory 1003 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0152] This embodiment also provides a computer storage medium storing computer instructions. When the computer instructions are executed on an electronic device, the electronic device performs the aforementioned method steps to implement the indoor parking lot positioning method in the above embodiment.

[0153] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to implement the indoor parking lot positioning method in the above embodiment.

[0154] In addition, embodiments of this application also provide an apparatus, which may specifically be a chip, component or module. The apparatus may include a connected processor and a memory; wherein the memory is used to store computer execution instructions, and when the apparatus is running, the processor may execute the computer execution instructions stored in the memory to cause the chip to execute the indoor parking lot positioning method in the above method embodiments.

[0155] In this embodiment, the computer device, computer storage medium, computer program product or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0156] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. 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.

[0157] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are illustrative. For instance, the division of modules or units is a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0158] The unit described as a separate component may or may not be physically separate. The component shown as a unit can be one physical unit or multiple physical units, that is, it can be located in one place or distributed in multiple different places. Some or all of the units can be selected to achieve the purpose of the solution in this embodiment according to actual needs.

[0159] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0160] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially or in other words, the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0161] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. A positioning method, applied to a terminal, comprising: Obtain multiple real-time received signal strengths (RSS) measured in the target area at the current moment. The system receives a lane pattern database and a fingerprint database for the target area. The lane pattern database includes multiple lanes within the target area and multiple location data within each lane. The fingerprint database includes multiple RSSs corresponding to each location data. Based on historical location data obtained from locating the target area at a historical time, the historical lane where the historical location data is located is determined from the multiple lanes in the lane pattern database, and the historical lane includes multiple candidate location data; The target location data at the current moment is obtained by performing positioning based on the multiple real-time RSSs, the multiple candidate location data, and the multiple RSSs corresponding to each location data.

2. The method according to claim 1, characterized in that, The step of determining the historical lane containing the historical location data from multiple lanes in the lane pattern database based on historical location data obtained from locating the target area at a historical time includes: From multiple location data in the lane pattern database, find matching location data that matches the historical location data; The lane to which the matched location data belongs is determined as the historical lane to which the historical location data is located.

3. The method according to claim 1, characterized in that, The step of locating the target location data at the current moment based on the multiple real-time RSSs, the multiple candidate location data, and the multiple RSSs corresponding to each location data includes: Based on multiple location data in the fingerprint database and multiple RSSs corresponding to each location data, determine the initial location data corresponding to multiple matching RSSs that match the multiple real-time RSSs; Based on multiple candidate location data of the historical lanes, the initial location data is corrected to obtain the target location data at the current moment.

4. The method according to claim 3, characterized in that, The initial location data is corrected based on multiple candidate location data from the historical location to obtain the target location data at the current moment, including: When the initial position data is any one of the plurality of candidate position data, the initial position data is determined to be the target position data at the current time; When the initial position data is not any of the multiple candidate position data, the target position data at the current time is determined from the multiple candidate position data based on the initial position data.

5. The method according to claim 4, characterized in that, When the initial position data is not any one of the plurality of candidate position data, determining the target position data at the current time from the plurality of candidate position data based on the initial position data includes: When the initial position data is not any of the plurality of candidate position data, the candidate position data that satisfies the target position data relationship with the initial position data is determined from the plurality of candidate position data as the target position data at the current time.

6. The method according to claim 3, characterized in that, The step of determining initial location data corresponding to multiple matching RSSs that match the multiple real-time RSSs based on multiple location data in the fingerprint database and multiple RSSs corresponding to each location data includes: A first positioning model is generated based on the fingerprint database. The first positioning model includes multiple location data and multiple RSSs for each location data. The first positioning model determines the initial location data corresponding to multiple matching RSSs that match the multiple real-time RSSs from multiple RSSs of each location data.

7. The method according to claim 1, characterized in that, The step of positioning based on the multiple real-time RSSs, the multiple candidate location data, and the multiple RSSs corresponding to each location data to obtain the target location data at the current time includes: In the fingerprint database, multiple RSSs corresponding to each candidate location data in the plurality of candidate location data are determined; From the multiple RSSs corresponding to each candidate location data, determine multiple matching RSSs that match the multiple real-time RSSs, and determine the candidate location data corresponding to the multiple matching RSSs as the target location data.

8. The method according to claim 7, characterized in that, The method further includes: Based on the fingerprint database and the lane pattern database, a second positioning model is generated. The second positioning model includes multiple lanes within the target area, multiple location data within each lane, and multiple RSSs for each location data. The process of locating the target location data at the current moment based on the multiple real-time RSSs, the multiple candidate location data of the historical lanes, and the multiple RSSs corresponding to each location data includes: Using the second positioning model, multiple RSSs corresponding to each candidate location data are determined. From the multiple RSSs corresponding to each candidate location data, multiple matching RSSs that match the multiple real-time RSSs are determined, and the candidate location data corresponding to the multiple matching RSSs is determined as the target location data.

9. A method for generating lane pattern data, used to establish a lane pattern database as described in any one of claims 1 to 8, comprising: Acquire multiple location data collected within the target area and their corresponding multiple sets of lane data, as well as the collection timestamp of each location data; Each of the multiple location data is mapped to a location grid to determine the multiple location grids corresponding to the multiple location data. The multiple location grids are connected sequentially according to the acquisition timestamps of their corresponding location data to obtain at least one first trajectory data of the target area; The first trajectory data is expanded based on the multiple sets of lane data to obtain the lane pattern database of the target area. The lane pattern database includes multiple lanes, each lane includes multiple trajectory data, and each trajectory data includes multiple location data.

10. The method according to claim 9, characterized in that, The lane data includes width data and edge distance data, whereby the edge distance data is the distance from the lane edge line to the corresponding position data of the lane data. The step of expanding the first trajectory data based on the multiple sets of lane data to obtain the lane pattern database of the target area includes: Determine multiple sets of first lane data corresponding to the location data in the first trajectory data; Based on at least one width data and edge distance data from the multiple sets of first lane data, determine the width of the lane where the first trajectory data is located, and the distance of the first trajectory data from the edge line of the lane where it is located; The first trajectory data is expanded based on the width and the distance to obtain a lane pattern database for the target area.

11. The method according to claim 9, characterized in that, The lane data includes lane type data. The step of sequentially connecting the multiple location grids according to the timestamps of their corresponding location data to obtain at least one first trajectory data of the target area includes: The multiple location grids are connected sequentially according to the timestamps of their corresponding location data to obtain at least one initial trajectory data of the target area; Determine multiple sets of initial lane data corresponding to the initial trajectory data; Based on at least one lane type data in the initial lane data, the initial trajectory data is corrected to obtain at least one first trajectory data for the target area.

12. A computer device, characterized in that, The computer device includes at least one processor, memory, and communication module; The at least one processor is connected to the memory and the communication module; The memory is used to store instructions, the processor is used to execute the instructions, and the communication module is used to communicate with the device under the control of the at least one processor; When the instruction is executed by the at least one processor, it causes the at least one processor to perform the method as described in any one of claims 1 to 11.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that causes a computer device to perform the method as described in any one of claims 1 to 11.

14. A computer program product, characterized in that, The computer program product includes computer-readable instructions that, when executed by one or more processors, implement the method as described in any one of claims 1 to 11.

Images