WO2023071405A1

WO2023071405A1 - Indoor parking lot positioning method, computer device, storage medium, and program product

Info

Publication number: WO2023071405A1
Application number: PCT/CN2022/112107
Authority: WO
Inventors: 洪伟评
Original assignee: 华为技术有限公司
Priority date: 2021-10-26
Filing date: 2022-08-12
Publication date: 2023-05-04
Also published as: CN116033544A

Abstract

Provided in the present application are an indoor parking lot positioning method, a computer device, a storage medium, and a program product. According to the present application, the method comprises: acquiring a plurality of real-time received signal strengths (RSSs) measured in a target area at the current moment; receiving a lane pattern database and a fingerprint database of the target area; according to historical position data obtained by performing positioning in the target area at historical moments, determining historical lanes, where the historical position data is located, from among a plurality of lanes of the lane pattern database, wherein the historical lanes comprise a plurality of pieces of candidate position data; and performing positioning on the basis of the plurality of real-time RSSs, the plurality of pieces of candidate position data and the plurality of RSSs corresponding to each piece of position data in the fingerprint database, so as to obtain target position data at the current moment. According to the present application, historical position data at historical moments can be combined for positioning to obtain target position data at the current moment, so that the positioning accuracy is effectively improved.

Description

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

Cross References to Related Applications

This application claims the priority of the Chinese patent application with the application number 202111263441.7 and the application name "indoor parking lot positioning method, computer equipment, storage medium and program product" submitted to the China Patent Office on October 26, 2021, the entire content of which Incorporated in this application by reference.

technical field

The present application relates to the field of terminal technology, and in particular to an indoor parking lot positioning method, computer equipment, storage media and program products.

Background technique

Nowadays, a terminal can be positioned by means of a positioning system, such as a common positioning system such as a Wireless Fidelity (Wi-Fi) positioning system. Among them, the process of positioning the terminal in the indoor parking lot by means of the Wi-Fi positioning system may include: measuring the received signal strength (Received Signal Strength, RSS) of the Wi-Fi signal from the access point (Access Point, AP), according to the RSS Estimating the location of the terminal. However, due to large fluctuations in the Wi-Fi signal, the RSS measured by the terminal is inaccurate, which in turn leads to a large gap between the estimated location of the indoor parking lot and the real location.

Contents of the invention

In view of this, it is necessary to provide an indoor parking lot positioning method, computer equipment, storage media and program products, which can effectively improve the positioning accuracy of the indoor parking lot.

The first aspect of the present application provides a positioning method, which is applied to a terminal, including: obtaining a plurality of real-time received signal strengths measured in a target area at the current moment; receiving a lane pattern database and a fingerprint database of the target area, the lane pattern database including the target area Multiple lanes in the lane, and multiple location data included in each lane, the fingerprint database includes multiple RSS corresponding to each location data; according to the historical location data obtained by positioning the target area at historical moments, from the multiple lane pattern database Determine the historical lane where the historical position data is located in each lane, and the historical lane includes multiple candidate position data; perform positioning based on multiple real-time RSS, multiple candidate position data, and multiple RSS corresponding to each position data, and obtain the current moment. Target location data.

Wherein, the target area may include a closed indoor space, such as an indoor parking lot. The historical moment can include the moment before the current moment, and the historical location data of the historical moment can be one or more, such as multiple historical location data of one historical moment, or multiple historical location data corresponding to multiple historical moments, historical lane Can include part or all of one or more lanes.

By adopting this technical solution, the historical lane where the historical position data is located can be obtained by combining the historical position data at historical moments, and through multiple candidate position data included in the historical lane, multiple RSSs corresponding to each position data, and multiple real-time RSS for positioning to obtain target location data at the current moment, this application introduces historical location data at historical moments, and combines multiple real-time RSS measured at the current moment for positioning, which may not be accurate compared to only using the current moment. Multiple real-time RSS for positioning, this application can effectively improve the positioning accuracy.

In a possible implementation, according to the historical location data obtained by positioning the target area at historical moments, the historical lane where the historical location data is located is determined from multiple lanes in the lane pattern database, including: from multiple locations in the lane pattern database In the data, the matching position data matching with the historical position data is searched; the lane to which the matching position data belongs is determined as the historical lane where the historical position data is located.

By adopting this technical solution, the historical position data at historical moments can be matched through the lane pattern database, and the historical lane where the historical position data is located can be determined.

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

According to a plurality of location data in the fingerprint database and a plurality of RSSs corresponding to each location data, determine the initial location data corresponding to a plurality of matching RSSs matched with a plurality of real-time RSSs; based on a plurality of candidate location data of historical lanes, for The initial position data is corrected to obtain the target position data at the current moment.

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.

In a possible implementation, based on multiple candidate location data of historical locations, the initial location data is corrected to obtain target location data at the current moment, including:

When the initial position data is any one of a plurality of candidate position data, it is determined that the initial position data is the target position data at the current moment; when the initial position data is not any one of the plurality of candidate position data, according to the initial position data, Target position data at the current moment is determined from a plurality of candidate position data.

By adopting this technical solution, the initial position data can be corrected to obtain target position data at the current moment belonging to multiple candidate position data.

In a possible implementation manner, when the initial position data is not any one of multiple candidate position data, according to the initial position data, the target position data at the current moment is determined from multiple candidate position data, including:

When the initial position data is not any one of the plurality of candidate position data, from the plurality of candidate position data, it is determined that the candidate position data that satisfies the target position data relationship with the initial position data is the current target position data.

By adopting this technical solution, the target position data at the current moment can be determined from a plurality of candidate position data according to the initial position data.

In a possible implementation manner, according to multiple location data in the fingerprint database and multiple RSS corresponding to each location data, determine initial location data corresponding to multiple matching RSSs that match multiple real-time RSSs, including:

A first location model is generated based on the fingerprint database, the first location model includes a plurality of location data, and a plurality of RSS of each location data; through the first location model, from the plurality of RSS of each location data, determine and multiple real-time The initial location data corresponding to the multiple matching RSS of the RSS.

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

In the fingerprint database, determine a plurality of RSSs corresponding to each candidate position data in the plurality of candidate position data; from the plurality of RSSs corresponding to each candidate position data, determine a plurality of matching RSSs that match the plurality of real-time RSSs , and determine the candidate location data corresponding to multiple matching RSSs as the target location data.

By adopting this technical solution, the target location data at the current moment can be determined according to the multiple real-time RSSs at the current moment from the plurality of candidate positioning data and the plurality of RSSs corresponding to each candidate positioning data.

In a possible implementation manner, the positioning method further includes:

Based on the fingerprint database and the lane pattern database, a second positioning model is generated, and the second positioning model includes multiple lanes in the target area, multiple position data in each lane, and multiple RSS of each position data;

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

Through the second positioning model, determine a plurality of RSS corresponding to each candidate position data in a plurality of candidate position data, and determine a plurality of matches matching a plurality of real-time RSS from the plurality of RSS corresponding to each candidate position data RSS, and determine multiple candidate location data corresponding to the matching RSS as the target location data.

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

The second aspect of the present application provides a method for generating lane pattern data, including:

Obtain multiple location data collected in the target area and corresponding multiple sets of lane data, as well as the collection time stamp of each location data; map each location data in the multiple location data to a location grid, to Determining a plurality of location grids corresponding to a plurality of location data; connecting the plurality of location grids in sequence according to the acquisition time stamps of their corresponding location data to obtain at least one first trajectory data of the target area; A track data is expanded to obtain a lane pattern database of the target area. The lane pattern database includes multiple lanes, each lane includes multiple track data, and each track data includes multiple position data.

By adopting this technical scheme, the acquired lane data can be extended to obtain the lane pattern database of the target space. Compared with the process of re-measurement and construction of the lane pattern database, this technical scheme uses the collected lane data to effectively improve the Acquisition efficiency of lane pattern database.

In a possible implementation, the lane data includes width data and margin data, and the margin data is the distance between the position data corresponding to the lane data and the sideline of the lane, and the first trajectory data is expanded according to multiple sets of lane data to obtain the target area The lane pattern database includes: determining multiple sets of first lane data corresponding to position data in the first track data; determining the position of the lane where the first track data is located according to at least one width data and margin data in multiple sets of first track data Width, and the distance from the first trajectory data to the sideline of the lane where it is located; based on the width and distance, the first trajectory data is expanded to obtain the lane pattern database of the target area.

In a possible implementation, the lane data includes lane type data, and 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, including: combining multiple The location grids are sequentially connected according to the timestamps of their corresponding location data to obtain at least one initial trajectory data of the target area; multiple sets of initial lane data corresponding to the initial trajectory data are determined; according to at least one lane type data in the initial lane data, the The initial trajectory data is corrected to obtain at least one first trajectory data of the target area.

The third aspect of the present application provides a data collection method, including:

Display the acquisition interface of the data acquisition client, the acquisition interface includes the real-time image of the target area and the detection control, the real-time image includes the lane image area corresponding to the lane to be collected in the target area; in response to the trigger operation for the detection control, the real-time image Carry out identification, and determine the suggested route for the data collection device on the lane to be collected according to the recognition result, and the collection suggestion information corresponding to the suggested route, and the collection suggestion information is used to instruct the data collection device to perform data collection along the suggested route on the lane to be collected; The collection suggestion information for the lane to be collected is displayed in the lane image area.

Wherein, the data collection client can run on a computer device, and the data collection client can display collection suggestion information, and can also generate a partial lane pattern map of the target area according to the collected lane data and fingerprint data.

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

In a possible implementation, the collection suggestion information includes a collection suggestion line drawn in the lane image area, the collection suggestion line includes at least one of a suggested direction line, a suggested margin line, and a suggested middle distance line, and the suggested direction line indicates data For the direction of collection, it is recommended that the margin line indicates the distance from the data collection device to the sideline of the lane where it is located, and the middle distance line indicates the distance from the data collection device to the center line of the lane where it is located.

By adopting the technical solution, simple and clear collection suggestion information can be provided to the user, which helps the user to accurately collect data according to the collection suggestion information.

In a possible implementation, in response to a trigger operation on the detection control, the real-time picture image is recognized, and according to the recognition result, the acquisition suggestion information for the lane to be collected is determined, including: in response to the trigger operation on the detection control, the Real-time screen image recognition to obtain the width data and sideline data of the lane to be collected; according to the width data, determine the number of suggested lines for the lane to be collected and the number of suggested lines for the lane image area; according to the sideline data, the suggested line and the number of suggested lines to be collected, determine the distance between each suggested line and the sideline of the lane to be collected, and the position of each collected suggested line in the lane image area.

By adopting this technical solution, the width data and sideline data of the lane to be collected can be identified and obtained, and then the collection suggestion information for the lane to be collected can be determined.

In a fourth aspect, the present application provides a computer device, and the computer device includes at least one processor and a memory. The memory is used to store instructions, and the processor is used to execute instructions to implement the positioning method of the first aspect, the lane pattern data generation method of the second aspect, and the data collection method of the third aspect.

In the fifth aspect, the present application provides a computer-readable storage medium, the computer-readable storage medium stores a program, and the program enables the computer device to execute the positioning method of the first aspect, the lane pattern data generation method of the second aspect, and the second aspect. Three methods of data collection.

In a sixth aspect, the present application provides a computer program product. The computer program product includes computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the positioning method of the first aspect and the positioning method of the second aspect are implemented. A method for generating lane pattern data, and a data collection method in the third aspect.

It can be understood that the computer device provided by the fourth aspect above, the computer-readable storage medium provided by the fifth aspect, and the computer program product provided by the sixth aspect correspond to the method provided by the first aspect, the second aspect, or the third aspect above , therefore, reference may be made to the above for the beneficial effects or various implementation manners it can achieve, and details will not be repeated here.

Description of drawings

FIG. 1 is a schematic diagram of an implementation scene of the positioning method for an indoor parking lot provided by the present application;

Fig. 2 is a schematic flow chart of the indoor parking lot positioning method provided by the present application;

Fig. 3 is the implementation schematic diagram of the positioning method of the indoor parking lot provided by the present application;

FIG. 4 is a schematic diagram of the user interface of the indoor parking lot positioning method provided by the present application;

FIG. 5 is a schematic diagram of another user interface of the indoor parking lot positioning method provided by the present application;

FIG. 6 is a schematic diagram of another user interface of the indoor parking lot positioning method provided by the present application;

FIG. 7 is a schematic diagram of the acquisition route of the indoor parking lot positioning method provided by the present application;

Fig. 8 is another schematic flow chart of the indoor parking lot positioning method provided by the present application;

FIG. 9 is a schematic diagram of another user interface of the indoor parking lot positioning method provided by the present application;

FIG. 10 is a schematic diagram of another collection route of the indoor parking lot positioning method provided by the present application;

FIG. 11 is a schematic diagram of another acquisition route of the indoor parking lot positioning method provided by the present application;

FIG. 12 is a schematic diagram of another acquisition route of the indoor parking lot positioning method provided by the present application;

Fig. 13 is another schematic flowchart of the indoor parking lot positioning method provided by the present application;

Figure 14 is a schematic diagram of the stage of the lane pattern diagram of the indoor parking lot positioning method provided by the present application;

FIG. 15 is a schematic diagram of another lane pattern diagram stage of the indoor parking lot positioning method provided by the present application;

FIG. 16 is a schematic diagram of another lane pattern diagram stage of the indoor parking lot positioning method provided by the present application;

Figure 17 is a schematic diagram of another lane pattern diagram stage of the indoor parking lot positioning method provided by the present application;

Fig. 18 is another schematic flowchart of the indoor parking lot positioning method provided by the present application;

FIG. 19 is a schematic diagram of another user interface of the indoor parking lot positioning method provided by the present application;

FIG. 20 is a schematic diagram of the structure of the indoor parking lot positioning method provided by the present application;

FIG. 21 is another schematic flowchart of the indoor parking lot positioning method provided by the present application;

Figure 22 is an example diagram of the result correction of the indoor parking lot positioning method provided by the present application;

FIG. 23 is another structural schematic diagram of the indoor parking lot positioning method provided by the present application;

Fig. 24 is another schematic flowchart of the indoor parking lot positioning method provided by the present application;

Figure 25 is an example diagram of determining the range of the indoor parking lot positioning method provided by the present application;

FIG. 26 is a schematic structural diagram of a computer device provided by the present application.

Detailed ways

It should be noted that in this application, "at least one" means one or more, and "multiple" means two or more than two. "And/or" describes the association relationship of associated objects, indicating that there can be three types of relationships, for example, A and/or B can mean: A exists alone, A and B exist simultaneously, and B exists alone, where A, B Can be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of this application and the drawings are used to distinguish similar objects, not to Describe a specific order or sequence.

When the computer equipment locates the indoor parking lot in real time, it can estimate the positioning result according to the RSS of multiple Wi-Fi signals measured. The estimation can be realized through the positioning model. The positioning model can be established by the fingerprint database, which can include indoor Multiple location data of the parking lot and multiple RSS corresponding to each location data. Therefore, when the positioning model performs real-time positioning, it can query the location data corresponding to multiple RSS measurements from the fingerprint database. The location data is the positioning result. However, because the Wi-Fi signal fluctuates in the indoor parking lot, there may be large errors in the RSS measured by the computer equipment, which in turn leads to a low accuracy rate of the positioning results obtained by the positioning model.

The present application provides a positioning method for an indoor parking lot. The indoor parking lot location method can be integrated on one or more computer devices. The computer device may include at least one of a terminal, a server, and the like. Terminals can include smartphones, laptops, tablets, smart wearable devices, vehicle-mounted smart terminals, etc. The server may include a local server, a cloud server, etc., and the terminal and the server may be connected in a wired or wireless manner, and so on.

For example, referring to FIG. 1 , the positioning method for an indoor parking lot of the present application may be jointly implemented by a terminal 10 and a server 20 . The terminal 10 is connected to the server 20 in a wired or wireless manner. The terminal 10 is used to collect fingerprint data and lane data on the lane of the indoor parking lot, and send the fingerprint data and lane data to the server 20 . The server 20 is used to store the received fingerprint data and lane data into the fingerprint database and the lane database respectively. The server 20 is also used for establishing the lane pattern database of the indoor parking lot according to the data in the fingerprint database and the lane database.

The terminal 10 is also used for responding to the positioning request initiated by the user on the user interface, and sending to the server 20 multiple RSSs collected in real time during the moving process to the server 20 according to the positioning request. The server 20 is also used to determine the target location of the terminal 10 at the current moment based on multiple RSSs at each moment and based on the fingerprint database and the lane pattern database. In another embodiment, the server 20 is further configured to send the target location information to the terminal 10, so that the terminal 10 can display the current location to the user on the user interface.

Specifically, please refer to Fig. 2 and Fig. 3 together. Fig. 2 is a schematic flow diagram of the indoor parking lot positioning method, and Fig. 3 is a schematic diagram of the implementation of the indoor parking lot method. As shown in Fig. 2 and Fig. 3, the indoor parking lot of the present application The parking lot positioning method may include the following steps.

101. Data collection.

For example, data collection can be carried out on the driveway of an indoor parking lot through a data collection device. For example, as shown in p1 in Figure 3, the user drives a vehicle in an indoor parking lot to collect: 1) location data at different locations, 2) RSS of Wi-Fi signals sent by different APs at each location, 3) each The type data of the lane where the position is located (such as one-way type, two-way type), width data, and the margin data of each position from the edge line of its lane, as shown in p2 in Figure 3, the fingerprint can be obtained from the collected data database and lane database.

102. Establish a lane pattern database.

Specifically, the lane pattern database can be established according to the fingerprint database and the lane database. As shown in p3 in Figure 3, the data in the lane pattern database can represent the lane pattern map of the indoor parking lot.

103. Establish a positioning model.

The positioning model can be established based on the fingerprint database, or jointly established based on the fingerprint database and the lane pattern database.

104. Online positioning.

Online positioning can be performed based on the lane pattern database, the positioning model, and multiple RSSs received at the current moment, as shown in p5 in the figure, to determine the current location of the user.

The indoor parking lot positioning method of the present application can be positioned based on the positioning model generated by the lane pattern database and the fingerprint database. Compared with the prior art that only uses the positioning model generated by the fingerprint database for positioning, this application can effectively improve the accuracy of the positioning results. Rate.

In the process of implementing the positioning method for the indoor parking lot, the present application also provides multiple user interfaces displayed on the computer equipment in order to facilitate information interaction with users. The user interface can display collection suggestion information when the user collects data through the computer equipment, display the pattern map of the indoor parking lot, and/or display the current location obtained by real-time positioning. The computer device may include at least one display screen, and the display screen may display different user interfaces at different stages of data collection, for example, multiple user interfaces may be displayed sequentially on one display screen, or may be displayed separately on different display screens, specifically It can be handled flexibly in the actual application process, and there is no limitation here.

For example, as shown in FIG. 4 , the terminal 10 may display a user interface a1, and the user interface a1 includes a suggestion information control a01, a lane pattern control a02, and a current location control a03. When the user triggers the suggestion information control a01, the terminal 10 can display the collection suggestion information for the current lane on the user interface a2 (such as the suggested travel route a001 in the figure); a3 shows the pattern diagram of the indoor parking lot generated according to the collected data; when the user triggers the current location control a03, the terminal 10 can display the user's current location in the indoor parking lot on the user interface a4 (the current location icon a003 in the figure) .

It should be noted that the users in this application may include objects using computer equipment that integrates some or all steps of the indoor parking lot positioning method, such as developers, users, intelligent robots, testing machines, etc.

This embodiment will introduce the process in which the user collects data on the driveway of the indoor parking lot with the help of the data collection device in this application, and obtains the fingerprint database and the driveway database.

Wherein, the fingerprint database may include multiple sets of fingerprint data, and each set of fingerprint data may include a piece of location data and a plurality of RSSs corresponding to the location data, wherein the location data may be a certain location data collected by the data collection device in the indoor parking lot. The latitude and longitude of the location, and the RSS may be the signal strength of Wi-Fi signals received by the data collection device from different APs at the latitude and longitude. The lane database can include multiple sets of lane data, and each set of lane data can include the type data (such as one-way type, two-way type) and width data of the lane where a certain position of the indoor parking lot is located, and the distance between the position and the edge of the lane where it is located. Margin data for the line.

The data acquisition equipment can include one or more of computer equipment, professional acquisition equipment, etc. When there are multiple data acquisition equipment, the data acquisition equipment can be connected together in a wired or wireless manner, and the computer equipment can include a terminal, a terminal Such as smartphones, smart vehicle terminals, smart wearable devices, smart cameras, drones, etc., users can control the data collection equipment to move along the lane in the indoor parking lot, and the data collection equipment collects fingerprints on the lane during the movement process Data and lane data, the way to control the movement of data acquisition equipment can be such as fixing the data acquisition equipment on the vehicle, the user drives the vehicle to move on the lane, or controlling the movement of the drone with the fixed data acquisition equipment, and so on.

For example, the terminal and the high-precision positioning instrument can be fixed on the vehicle, and the high-precision positioning instrument can be an inertial measurement unit and an inertial detector based on the high navigation level of iNAV-RQH (inertial gyro navigation system). The user can drive the vehicle on the lane of the indoor parking lot, and collect data through the terminal and high-precision positioning equipment. The terminal can collect multiple RSS in each set of fingerprint data, as well as all lane data, and the high-precision positioning equipment can collect fingerprints. Location data in the data. The terminal and the high-precision positioning instrument can upload the collected data to the cloud server in real time, store the fingerprint data in the fingerprint database, and store the lane data in the lane database.

The lane data can be collected in various ways, for example, the lane image can be collected by an image acquisition device or an image acquisition module on a computer device, and the computer device can recognize the lane image to obtain the lane data.

The fingerprint data and lane data collected by this application can be stored in the fingerprint database and the lane database respectively, and the fingerprint database and the lane database can be set in the data acquisition device or in other computer equipment (such as a server), and the details can be flexible processing without limitation.

In the embodiment of this application, in order to collect fingerprint data and lane data that can fully describe the lanes of the indoor parking lot, during the manual collection process, the collection suggestion information for the current lane can be displayed to the user through the data collection device, so as to prompt the user to follow the Collect suggested information for data collection.

In this embodiment of the application, a manual data collection application can be installed on the data collection device, and the user interface of the manual data collection application can display collection suggestion information, and the collection suggestion information can include one or more of voice, video, text, image, etc. Various. Several controls can be used in the process of displaying collection suggestion information. It should be noted that the controls can be one or more combinations of buttons, edit boxes, selection boxes, text boxes, etc., and the user's trigger operations on the controls can include A combination of one or more operations such as clicking, sliding, and long pressing can be flexibly set and processed during actual application, and there is no limitation here.

For example, after the user starts the manual data collection application, as shown in Figure 5, the manual data collection application can display the collection interface a01, and the collection interface c01 includes the real-time picture 001 and the detection control 002 of the indoor parking lot captured by the data collection equipment, and the real-time picture 001 includes the image of the lane to be collected. The data acquisition device can respond to the user's trigger operation on the detection control 002, identify the image in the real-time screen 001, and display the acquisition suggestion information for the lane on the acquisition interface a01 according to the identification result.

There are many ways to display the collection suggestion information. As shown in Figure 5, after the data collection device recognizes the image in the real-time screen 001, the collection suggestion box 003 can be displayed on the collection page c02, and the collection suggestion box 003 can include collection Suggested text, the collected suggested text can be read by the user, and the user can refer to the information provided by the collected suggested text for data collection; and as shown in Figure 5, after the data collection device recognizes the image in the real-time screen 001, it can be displayed on the collection page c03 Display the collection suggestion line, display the suggested direction line 0041, the suggested margin line 0042, and the suggested middle distance line 0043 in the real-time screen, the user can move in the direction pointed by the suggested direction line 0041, and can use the suggested margin The line 0042 and the recommended mid-distance line 0043 are boundary lines, and the data collection equipment is controlled to collect data within the area defined by the suggested editing line 0042 and the suggested mid-distance line 0043.

The collection suggestion information in the embodiment of the present application may be determined by the recognition result of the image in the real-time picture, and specifically, there may be multiple ways.

In some embodiments, the data acquisition device can identify the position of the edge line of the lane in the image (ie, the edge data), and determine the suggested route for the user to collect according to the position of the edge line of the lane. The suggested information for collection can be: The suggested route of the preset distance from the edge line is shown in Figure 6. The collection page shows that d01 can display the graphic line d001 of the suggested route 1. The user can refer to the graphic line d001 in Figure 6 to drive the vehicle. The user is on the road as shown in Figure 7. Drive the vehicle along the proposed route 1 for data collection.

In some embodiments, one or more data collections can be performed on a lane. Specifically, the data collection device can identify the type and width of the lane in the image, as shown in Figure 8. If the lane is a bidirectional type, the centerline of the lane can be determined and the position of the edge line, and then judge whether the width of the lane is greater than the preset first value, if not, then the distance from the suggested line to the center line and the edge line can be determined respectively, and the suggested information can be collected as follows: along the distance from the center line Set the suggested route with the first distance and the preset second distance from the edge line, as shown in Figure 9, the collection page display d02 can display the first graphic line d021 and the second graphic line d022 of the suggested route, the user can As shown, the vehicle is driven to collect data along a suggested route with a preset first distance from the center line and a preset second distance from the edge line.

If the lane is a one-way type, you can determine the position of the edge line, and then determine whether the width of the lane is greater than the preset first value. If not, you can determine the distance from the suggested line to the edge line. The suggested information collection includes: along the distance Please refer to Figure 6 and Figure 7 for the recommended route of the preset distance from the edge of the lane, the collection page diagram and the user collection diagram.

If the width of the lane is greater than the preset first value and not greater than the preset second value, it can be determined that the lane requires two data collections (such as data collection near the left side and the right side of the lane), and the user can be determined according to the position of the lane edge. When collecting the first suggested route and the second suggested route, collecting 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, wherein the distance between the first suggested route and the lane The third distance is preset from the edge line of the lane, and the fourth distance is preset from the second suggested line to the edge line of the lane. As shown in Figure 11, the user can drive the vehicle along the first suggested line and the second suggested line in one-way mode. lanes for data collection.

If the width of a single lane is greater than the preset second value, it can be determined that the lane needs three data collections (such as data collection near the left side of the lane, the middle and the right side respectively), and the third suggestion for user collection is determined according to the position of the edge line of the lane route, the fourth suggested route and the fifth suggested route, the collection of suggested information may include: traveling along the third suggested route for the first time, then traveling along the fourth suggested route for the second time, and finally following the fifth suggested route for the third time The second travel, wherein, the third suggested route is a preset fifth distance from the edge line of the lane, the fourth suggested route is preset a sixth distance from the lane edge line, and the fifth suggested route is preset a seventh distance from the lane edge line, As shown in FIG. 12 , the user can drive the vehicle along the third suggested route, the fourth suggested route and the fifth suggested route to collect data in one-way lanes.

It should be noted that the suggested route described in the embodiment of this application is only an example. When data collection is performed in an actual application scenario, the form of the suggested route and the way the user performs data collection with reference to the suggested route may include Flexible handling of needs.

This embodiment can output collection suggestion information to the user in real time according to the condition of the lane, which is convenient for the user to collect data according to the collection suggestion information, and improves the efficiency of user data collection and user experience.

The embodiment of this application will introduce the establishment process of the lane pattern database. The lane pattern database can include information data and direction data of multiple lanes, the direction data of the lane can represent the direction of the lane, the information data of the lane can include multiple position data in the lane, and the data in the lane pattern database can represent Lane pattern diagram of indoor parking lot.

Specifically, referring to FIG. 13, the flow of the lane pattern data establishment process may include:

201. The computer device maps each location data in the fingerprint database to different location grids.

For example, referring to Figure 14, six location data are sequentially mapped to six location grids.

202. The computer device establishes directional trajectory data according to the lane type data in the lane database and each position grid.

For example, referring to Fig. 15, according to the time stamps of the lane data, the position grids are sequentially connected according to the time stamps to obtain two track data, and the direction of the track data is the direction in which the position grids are connected.

According to the time stamp of the lane type data in the lane database, the lane type data corresponding to each position grid is determined. As shown in Figure 15, the lanes corresponding to all position grids are two-way types, and the track data can be corrected according to the lane type. For example, In Figure 16, the trajectory data formed by the connection of position grid 1, position grid 2 and position grid 3 is corrected. Since position grid 2 is in another one-way lane of a two-way lane, the user is advised to follow the According to the usual line collection with the edge line of the lane, multiple position data on the straight line should be obtained, then position grid 2 needs to be eliminated here, and position grid 1 and position grid 3 need to be directly connected to obtain the corrected trajectory data .

203. The computer device expands the trajectory data according to the width data and margin data in the lane database to obtain a directional lane pattern diagram, and saves the lane pattern diagram in the lane pattern database.

Each position grid refers to an area in the indoor parking lot. According to the width data of the lane where the position grid is located in the lane database and the margin data of the position data corresponding to the position grid in the lane from the edge line of the lane, the track The data is expanded to determine the trajectory data of some areas in the lane that have not been collected. As shown in Figure 17, insert new trajectory data into the grid area adjacent to the trajectory data according to the width data, and insert new trajectory data into the lane edge grid area according to the margin data. Insert new trajectory data into the grid area to get the lane pattern. The direction of the lane is the direction of the trajectory data initially established. Perform the above operations on all lanes to get the lane pattern of the indoor parking lot and save it in in the lane pattern database.

In the embodiment of the present application, as shown in Figure 18, the location data in the fingerprint database can be mapped to the location grid, and the trajectory data can be established according to the lane type data in the lane database, and the established trajectory data can be corrected and confirmed. , and then according to the lane width data and margin data in the lane database, the trajectory data on the lane can be expanded to obtain more abundant position data on the lane, and then the lane pattern database can be obtained.

The application can quickly calculate the lane pattern diagram of the indoor parking lot according to the existing fingerprint database and the lane database.

In the embodiment of the present application, the data collection device can collect data during the movement process, and the manual data collection application can display the lane pattern generated by the collected position data and lane data.

For example, users can collect lane data and multiple RSS data in real time through a smartphone, and collect location data in real time through a high-precision positioning instrument. The location data and multiple RSS in the database, as well as the lane data stored in the lane database, generate the lane pattern map of the indoor parking lot in real time, and the server transmits the lane pattern map to the smartphone, and the smartphone displays the lane pattern on the user interface of the smartphone picture.

Specifically, the user can trigger the lane pattern diagram control on the user interface, and the computer device can respond to the trigger operation and display the generated lane pattern diagram. For example, referring to FIG. 4, the data collection device can display a user interface a1, which includes a suggestion information control a01, a lane pattern control a02, and a current position control a03. When the user triggers the lane pattern control a02, the terminal 10 can display the user interface a3 shows the pattern diagram of the indoor parking lot generated according to the collected data.

In some embodiments, the computer device can also perform quality inspection on the collected position data and lane data, and the way of quality inspection can include: the group number of the position data and/or lane data collected in a specific area/lane is greater than If the threshold is preset, it is determined that the quality inspection is qualified; otherwise, the quality inspection is not qualified. If the quality inspection is not qualified, data collection for a specific area/lane needs to be re-collected. For example, when the number of sets of position data and lane data in lane 1 is greater than the preset If the threshold value is 1, it is determined that the quality inspection of lane 1 is qualified. When the number of sets of position data in lane 2 is less than the preset threshold value 1, it is determined that the quality inspection of lane 1 fails.

The manual data collection application can also display the quality inspection results on the layout map interface, prompting the user to re-collect the data in the area where the data failed the quality inspection. The user triggers the lane pattern map control a02, as shown in Figure 19, the manual data collection application displays the lane pattern map on the pattern map interface a3, and distinguishes the lane 1 where the successfully collected data is located on the lane pattern map (that is, the lane where the quality inspection data is located, That is, the area containing several dots in Figure 19), the lane 2 where the failed data collection is located (i.e. the lane where the quality inspection failed data is located, that is, the area containing several oblique lines in Figure 19), and the uncollected data area 3 (i.e. gray area in 19).

The embodiment of the present application can quickly calculate the lane pattern diagram of the indoor parking lot according to the existing fingerprint database and the lane database, and display the lane pattern diagram on the user interface, which is convenient for the user to check in real time. The lane pattern map displayed on the interface shows whether the collected data is qualified, and then prompts the user to re-collect data on the lane where the unqualified data is located.

The process of establishing a positioning model and online positioning in this application will be introduced below.

In the embodiment of the present application, the process of establishing a positioning model and online positioning can be realized by computer equipment. Referring to FIG. Establish a positioning model. During the online positioning process, multiple RSSs measured online in real time can be input into the positioning model. The positioning model can output the initial position data at the current moment (that is, the original positioning result in the figure). The computer equipment can be combined with the lane pattern database. Correct the initial position data to obtain the target position data at the current moment (that is, the final positioning result in the figure).

Specifically, the fingerprint database includes multiple sets of fingerprint data, and each set of fingerprint data includes location data and multiple RSSs. When the vehicle is moving and needs to be positioned, the positioning model can query the fingerprint database and multiple RSSs at the current moment. The same location data, the location indicated by the location data is the initial location at the current moment. The computer device can determine the historical lane where the historical position data at the historical moment is located according to the lane pattern database, determine part or all of the position data contained in the historical lane as candidate position data, and correct the initial position data according to the candidate position data in the historical lane, The target location data where the terminal is located at the current moment is obtained.

It should be noted that, during the execution of the step of determining the initial position at the current moment and the step of determining the historical lane, the execution order of the two can be flexibly adjusted according to factors such as the application scenario and the performance of the computer equipment, for example, it can also be the first Execute the step of determining the historical lane, and then execute the step of determining the initial position at the current moment, or perform the step of determining the historical lane and the step of determining the initial position at the current moment at the same time.

Among them, the historical moment can be the moment before the current moment, and the lane pattern database includes multiple lanes and multiple position data in each lane, and the matching position matching the historical position data of the historical moment can be found in the lane pattern database data, match the position data such as the same position data as the historical position data, the position data adjacent to the historical position data, etc., and determine the lane to which the matching position data belongs in the lane pattern database as the historical lane.

Among them, multiple candidate position data can be determined from all the position data included in the historical lanes. Specifically, for example, according to the directionality of the historical lanes, a part of the lanes in front of the matching lane data can be determined from the historical lanes. The location data of is the candidate location data.

Among them, if the initial position is not any one of the candidate position data, the initial position at the current moment is corrected, and the target position data is determined from multiple candidate position data; if the initial position is any one of the multiple candidate position data , it is determined that the initial position at this time is the target position data at this time.

For example, referring to Figure 21, you can query the lane where the historical position of t-1 seconds is located from the lane pattern database, query the type of lane where the initial position is located at the current moment, and correct the initial position to the lane where the initial position is located in t-1 second according to the lane type , to get the final positioning result at the current moment.

For example, refer to Figure 22, which shows multiple examples of corrected positioning results. It should be noted that the historical position data can be the final positioning point of t-1 seconds below, and the initial position data can be the final positioning point of t seconds below. Positioning point, the target position data can be as the final positioning point in t-1 seconds below, the target position data relationship between the initial position data and the target position data can be as follows, the two are on the same horizontal line, the connecting line between the two and the horizontal line clip The angle is 45 degrees and so on. In Example 1, the final positioning point of t-1 seconds is on the one-way lane, and the original positioning point of t seconds is in the non-lane area next to the one-way lane. The final positioning point of t seconds can be Corrected to: the front side of the final positioning point at t-1 second in the one-way lane, at this time the target position data relationship is on the same horizontal line; as in Example 2, the final positioning point at t-1 second is on the right lane of the two-way lane , the original positioning point of t seconds is on the left lane of the two-way lane, the final positioning point of t second can be corrected to: the front side of the final positioning point of t-1 second in the right lane of the two-way lane, at this time the target position data relationship to be on the same horizontal line.

As in Example 3, the final positioning point of t-1 seconds is on the right one-way lane, and the original positioning point of t seconds is on the left one-way lane separated from the right one-way lane by a non-lane area, so the final positioning point of t seconds can be The positioning point is corrected to: the front side of the final positioning point at t-1 second in the right one-way lane, at this time the target position data relationship is on the same horizontal line; as in Example 4, the final positioning point at t-1 second is in the vertical straight line On a one-way lane, the original positioning point for t seconds is on the horizontal straight one-way lane intersecting with the longitudinal straight one-way lane, and the final positioning point for t seconds can be corrected to: t-1 seconds in the longitudinal straight one-way lane The front side of the final positioning point, the intersection of two lanes, at this time the target position data relationship is on the same horizontal line.

As in Example 5, the final positioning point for t-1 seconds is on the longitudinal straight one-way lane, and the original positioning point for t seconds is in the non-lane area adjacent to the longitudinal straight one-way lane, the final positioning point for t seconds can be Corrected to: the front side of the final positioning point of t-1 second in the longitudinal straight one-way lane, at this time the target position data relationship is on the same horizontal line; as in example 6, the final positioning point of t-1 second is in the vertical straight single-way lane At the boundary between the lane and the intersection area where you can go straight or turn left/right, the original positioning point for t seconds is in the non-lane area adjacent to the intersection area, and the final positioning point for t seconds can be corrected to: intersection The center position of the area, the data relationship of the target position this time is that the angle between the connecting line and the horizontal line is 45.

In the embodiment of the present application, the initial position data obtained by multiple RSSs that may not be accurate can be corrected in combination with the lane pattern data map, so as to effectively improve the positioning accuracy of the indoor parking lot.

In the embodiment of the present application, the process of establishing the positioning model and online positioning can be realized by computer equipment. Referring to FIG. 23, the fingerprint database and the lane database are obtained through data collection, and the lane pattern database is established from the fingerprint database and the lane database, and then the fingerprint database can be used. Establish a positioning model with the lane pattern database. During the online positioning process, multiple RSSs measured online in real time can be input into the positioning model, and the positioning model can output the target position data at the current moment (that is, the final positioning result in the figure).

Specifically, when the positioning model determines the target position at the current moment, it can first determine the historical lane to which the historical position data belongs in the lane pattern database according to the historical position data at the historical moment. The historical lane includes multiple candidate position data, and the candidate position data It can be part or all of the position data contained in the historical lane, and then according to the multiple RSS at the current time, determine the target position data at the current time from multiple candidate position data, and output the target position data.

For example, referring to Figure 24, the positioning model can search the lane range where the historical position of t-1 is located in the lane pattern database, and then determine the lane where the historical position of t-1 is located, and set this lane as the location of the positioning result at the current moment In the region, the positioning model determines the position data corresponding to the multiple RSSs from all the position data in the lane according to the received multiple RSSs at the current moment, and the position data is the final positioning result at the current moment.

For example, referring to Figure 25, it should be noted that the historical location data can be the final positioning point at t-1 seconds below, and the range defined by multiple candidate location data can be the positioning result range at the current moment below, as shown in the figure According to the positioning result of t-1, an example of determining the range of the positioning result at the current moment. In example 1, the one-way lane where the t-1 positioning point is located is the range of the positioning result of t seconds. In example 2, t-1 positioning The right lane of the two-way lane where the point is located is the range of the positioning result for t seconds. In example 3, the one-way straight road at the intersection where the t-1 positioning point is located is the range of the positioning result for t seconds. In example 4, t- 1 The multi-directional road at the intersection where the positioning point is located is the range of the positioning result for t seconds.

In this embodiment of the present application, the range of positioning results of multiple RSSs that may be inaccurate may be limited in combination with the lane pattern diagram, so as to output more accurate positioning results and effectively improve the positioning accuracy of the indoor parking lot.

For example, in the underground parking lot of a shopping mall, see the table below, the indoor parking lot positioning method of this application (Wi-Fi positioning algorithm uses lane pattern data correction) and the existing positioning method (Wi-Fi positioning algorithm does not have lane pattern data) , at different positions on different floors, the circular error probability (Circular Error Probable, CEP) of the positioning result is different, CEP68 and CEP95 refer to the circular error probability of 68% and the circular error probability of 95%, for example, the verification floor is Shopping mall A B2 floor, when the mobile phone is at A, the value of CEP68 is 5.3 meters, and the value of CEP95 is 15.6 meters, which respectively refer to the error of the positioning result obtained by the positioning algorithm relative to the circle with the mobile phone position A as the center. % chance is less than 5.3 meters, 95% chance is less than 15.6 meters.

Table 1

From the data in Table 1, it can be seen that the CEP of the Wi-Fi positioning algorithm of this application using lane pattern data correction is significantly lower than the CEP of the Wi-Fi positioning algorithm without lane pattern data on the same floor and at the same location, which shows that the CEP of this application The method can obviously reduce the positioning error and improve the positioning accuracy.

Referring to FIG. 26 , it is a schematic diagram of the hardware structure of the computer device 100 provided by the embodiment of the present application. As shown in FIG. 26 , 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 . One or more computer programs 1005 are configured to be executed by the processor 1002 . The one or more computer programs 1005 include instructions, which can be used to implement all or part of the steps of the method for locating an indoor parking lot in the computer device 100 .

It can be understood that the structure shown in this embodiment does not constitute a specific limitation on the computer device 100 . In other embodiments, computer device 100 may include more or fewer components than shown, or combine certain components, or separate certain components, or arrange different components. For example, computer device 100 may also include a camera.

The processor 1002 may include one or more processing units, for example: the processor 1002 may include an application processor (application processor, AP), a modem, a graphics processing unit (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), controller, video codec, digital signal processor (digital signal processor, DSP), baseband processor, and/or neural network processor (neural-network processing unit, NPU), etc. Wherein, different processing units may be independent devices, or may be integrated in one or more processors.

The processor 1002 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in processor 1002 is a cache memory. The memory may hold instructions or data that the processor 1002 has just used or recycled. If the processor 1002 needs to use the instruction or data again, it can be directly recalled from the memory. Repeated access is avoided, and the waiting time of the processor 1002 is reduced, thereby improving the efficiency of the system.

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

In some embodiments, the memory 1003 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, internal memory, plug-in hard disk, smart memory card (Smart Media Card, SMC), secure digital (Secure Digital (SD) card, flash card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.

This embodiment also provides a computer storage medium, in which computer instructions are stored, and when the computer instructions are run on the electronic equipment, the electronic equipment executes the steps of the above-mentioned related methods to realize the positioning of the indoor parking lot in the above-mentioned embodiments. method.

This embodiment also provides a computer program product, which, when running on a computer, causes the computer to execute the above related steps, so as to realize the indoor parking lot positioning method in the above embodiment.

In addition, an embodiment of the present application also provides a device, which may specifically be a chip, a component or a module, and the device may include a connected processor and a memory; wherein the memory is used to store computer-executable instructions, and when the device is running, The processor can execute the computer-executable instructions stored in the memory, so that the chip executes the indoor parking lot positioning method in the above method embodiments.

Wherein, the computer equipment, computer storage medium, computer program product or chip provided in this embodiment are all used to execute the corresponding method provided above, therefore, the beneficial effects it can achieve can refer to the corresponding method provided above The beneficial effects in the method will not be repeated here.

Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and brevity of the description, only the division of the above-mentioned functional modules is used as an example for illustration. In practical applications, the above-mentioned functions can be allocated according to needs It is completed by different functional modules, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

In the several embodiments provided in this application, it should be understood that the disclosed devices and methods may be implemented in other ways. For example, the device embodiments described above are schematic. For example, the division of the modules or units is a logical function division. In actual implementation, there may be other division methods, for example, multiple units or components may be combined or may be integrated into another device, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

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

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

If the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the software product is stored in a storage medium Among them, several instructions are included to make a device (which may be a single-chip microcomputer, a chip, etc.) or a processor (processor) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disc and other media that can store program codes. .

The above is only a specific implementation of the application, but the protection scope of the application is not limited thereto, and any changes or replacements within the technical scope disclosed in the application should be covered within the protection scope of the application .

Claims

A positioning method, applied to a terminal, comprising:

Obtain multiple real-time received signal strengths (Received Signal Strength, RSS) measured in the target area at the current moment;

receiving a lane pattern database and a fingerprint database of the target area, the lane pattern database including a plurality of lanes in the target area and a plurality of position data included in each of the lanes, the fingerprint database including each Multiple RSSs corresponding to the location data;

According to the historical location data obtained by positioning in the target area at historical moments, determine the historical lane where the historical location data is located from the multiple lanes in the lane pattern database, the historical lane includes a plurality of candidate location data;

Positioning is performed based on the multiple real-time RSSs, the multiple candidate location data, and multiple RSSs corresponding to each of the location data, to obtain target location data at the current moment.
The method according to claim 1, characterized in that, according to the historical position data obtained by positioning in the target area at historical moments, the historical lane where the historical position data is located is determined from a plurality of lanes in the lane pattern database, include:

Finding matching position data that matches the historical position data from the plurality of position data in the lane pattern database;

The lane to which the matching position data belongs is determined as the historical lane where the historical position data is located.
The method according to claim 1, wherein the positioning is performed based on the plurality of real-time RSS, the plurality of candidate location data, and the plurality of RSS corresponding to each location data, to obtain the current Time target location data, including:

determining initial location data corresponding to a plurality of matching RSSs matching the plurality of real-time RSSs according to a plurality of location data in the fingerprint database and a plurality of RSSs corresponding to each location data;

Based on the multiple candidate position data of the historical lane, the initial position data is corrected to obtain the target position data at the current moment.
The method according to claim 3, wherein the multiple candidate position data based on the historical position is used to correct the initial position data to obtain the target position data at the current moment, comprising:

When the initial position data is any one of the plurality of candidate position data, determining that the initial position data is the target position data at the current moment;

When the initial position data is not any one of the plurality of candidate position data, according to the initial position data, the target position data at the current moment is determined from the plurality of candidate position data.
The method according to claim 4, wherein when the initial position data is not any one of the plurality of candidate position data, according to the initial position data, from the plurality of candidate positions The target position data at the current moment is determined in the data, including:

When the initial position data is not any one of the plurality of candidate position data, from the plurality of candidate position data, determine that the candidate position data that satisfies the target position data relationship with the initial position data is the The target position data at the current moment.
The method according to claim 3, characterized in that, according to the plurality of location data in the fingerprint database and the plurality of RSS corresponding to each location data, determine a plurality of real-time RSS matching Match the initial location data corresponding to RSS, including:

generating a first location model based on the fingerprint database, the first location model including a plurality of location data, and a plurality of RSS for each location data;

Determining initial location data corresponding to multiple matching RSSs matching the multiple real-time RSSs from the multiple RSSs of each location data by using the first positioning model.
The method according to claim 1, wherein the positioning is performed based on the plurality of real-time RSS, the plurality of candidate location data, and the plurality of RSS corresponding to each location data, to obtain the current location Target location data, including:

In the fingerprint database, determining a plurality of RSSs corresponding to each candidate position data in the plurality of candidate position data;

From the plurality of RSSs corresponding to each candidate location data, determine a plurality of matching RSSs that match the plurality of real-time RSSs, and determine the candidate location data corresponding to the plurality of matching RSSs as target location data.
The method according to claim 7, further comprising:

Based on the fingerprint database and the lane pattern database, generate a second positioning model, the second positioning model includes a plurality of lanes in the target area, a plurality of position data in each lane, and each position data Multiple RSS of;

The positioning based on the plurality of real-time RSSs, the plurality of candidate position data of the historical lanes, and the plurality of RSS corresponding to each position data to obtain the target position data at the current moment includes:

Using the second positioning model, determine a plurality of RSSs corresponding to each candidate position data in the plurality of candidate position data, and determine the plurality of real-time RSSs from the plurality of RSSs corresponding to each candidate position data matching multiple matching RSSs, and determining the candidate location data corresponding to the multiple matching RSSs as target location data.
A method for generating lane pattern data, comprising:

Obtain multiple location data collected in the target area and corresponding multiple sets of lane data, as well as the collection time stamp of each location data;

Mapping each position data of the plurality of position data to a position grid respectively, so as to determine a plurality of position grids corresponding to the plurality of position data;

Connecting the plurality of location grids sequentially according to the collection time stamps of their corresponding location data, to obtain at least one first trajectory data of the target area;

Expand the first trajectory data according to 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 a plurality of trajectory data, and each trajectory data Include multiple location data.
The method according to claim 9, wherein the lane data includes width data and margin data, and the margin data is the distance between the position data corresponding to the lane data and the lane edge,

The said first trajectory data is expanded according to the multiple sets of lane data to obtain the lane pattern database of the target area, including:

determining multiple sets of first lane data corresponding to the position data in the first trajectory data;

Determine the width of the lane where the first trajectory data is located and the distance from the first trajectory data to the sideline of the lane where the first trajectory data is located according to at least one width data and margin data in the plurality of sets of first lane data;

Expanding the first trajectory data based on the width and the distance to obtain a lane pattern database of the target area.
The method according to claim 9, wherein the lane data comprises lane type data,

The step of connecting the plurality of location grids sequentially according to the time stamps of their corresponding location data to obtain at least one first trajectory data of the target area includes:

Connecting the plurality of location grids sequentially according to the time stamps 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;

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.
A data collection method, comprising:

Displaying the collection interface of the data collection client, the collection interface includes a real-time picture image of the target area and detection controls, the real-time picture image includes a lane image area corresponding to the lane to be collected in the target area;

Responding to the trigger operation for the detection control, the real-time picture image is recognized, and the suggested route for the data collection device in the lane to be collected is determined according to the recognition result, and the collection suggestion information corresponding to the suggested route is determined. The collection suggestion information is used to instruct the data collection device to collect data along the suggested route on the lane to be collected;

Displaying collection suggestion information for the to-be-collected lane in the lane image area.
The method according to claim 12, wherein the collection suggestion information includes a collection suggestion line drawn in the lane image area, and the collection suggestion line includes a suggested direction line, a suggested margin line and a suggested middle distance line At least one of them, the suggested direction line indicates the direction of data collection, the suggested margin line indicates the distance between the data collection equipment and the lane edge, and the suggested middle distance line indicates the distance between the data collection equipment and the lane centerline. distance.
The method according to claim 13, characterized in that, in response to the trigger operation on the detection control, the real-time picture image is recognized, and the collection suggestion information for the lane to be collected is determined according to the recognition result, include:

In response to a trigger operation on the detection control, identify the real-time picture image, and obtain the width data and sideline data of the lane to be collected;

According to the width data, determine the number of suggested lines for the lane to be collected and the number of suggested lines for collection in the lane image area;

According to the sideline data, the number of suggested lines and the number of suggested lines to be collected, determine the distance between each suggested line and the sideline of the lane to be collected, and determine the distance between each suggested line to be collected in the The position in the image area of the lane.
A computer device, characterized in that the computer device includes at least one processor, a memory and a communication module;

said at least one processor is coupled to said memory and said communications 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;

The instructions, when executed by the at least one processor, cause the at least one processor to perform the method of any one of claims 1-14.
A computer-readable storage medium, characterized in that the computer-readable storage medium stores a program, and the program causes a computer device to execute the method according to any one of claims 1 to 14.
A computer program product, characterized in that the computer program product includes computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the implementation of any one of claims 1 to 14 Methods.