CN116383326A

CN116383326A - Method and device for updating position information of interest point data and computer equipment

Info

Publication number: CN116383326A
Application number: CN202310402764.2A
Authority: CN
Inventors: 李星宇; 岳大威
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2023-04-06
Filing date: 2023-04-06
Publication date: 2023-07-04

Abstract

The embodiment of the invention relates to a method, a device, computer equipment, a storage medium and a computer program product for updating position information of interest point data, which can be applied to scenes such as maps, internet of vehicles, automatic driving or traffic. The method comprises the following steps: acquiring a target image comprising a target interest point, wherein target interest point data of the target interest point has corresponding first position information; determining adjacent interest points adjacent to the target interest point from the target image through the first position information, wherein the adjacent interest points of the adjacent interest points have corresponding second position information; acquiring first position information confidence coefficient of target interest point data and second position information confidence coefficient of adjacent interest point data; and updating any one of the first position information and the second position information by the first position information confidence and the second position information confidence. The method can improve the accuracy of updating the position information of the interest point data.

Description

Method and device for updating position information of interest point data and computer equipment

Technical Field

The present invention relates to the field of data processing, and in particular, to a method, an apparatus, and a computer device for updating location information of point of interest data.

Background

Along with the development of communication technology and the wide application of internet electronic maps, POI (Point of Interest, interest point) data exist in the internet electronic maps, and the POI data generally refer to point data in the internet electronic maps. However, the data error correction of POI data needs to take the position information and the name information into consideration, that is, the difficulty of data error correction is high.

Currently, because POI data generally originates from a plurality of data sources, updating the position information of POI data by different data sources is a common data error correction method, however, in practical applications, different data sources may exist to provide different position information for the same POI data, thereby reducing the accuracy of updating the position information of the point of interest data. Therefore, how to improve the accuracy of the location information update of the point of interest data is a problem to be solved.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, and a storage medium for updating location information of point of interest data, which can improve accuracy of location information update of the point of interest data.

In a first aspect, the present application provides a method for updating location information of point of interest data. The method comprises the following steps:

acquiring a target image comprising a target interest point, wherein target interest point data of the target interest point has corresponding first position information;

determining adjacent interest points adjacent to the target interest point from the target image through the first position information, wherein the adjacent interest points of the adjacent interest points have corresponding second position information;

acquiring first position information confidence coefficient of target interest point data and second position information confidence coefficient of adjacent interest point data, wherein the first position information confidence coefficient is a parameter for evaluating that the first position information is correct position information, and the second position information confidence coefficient is a parameter for evaluating that the second position information is correct position information;

and updating any one of the first position information and the second position information by the first position information confidence and the second position information confidence.

In a second aspect, the present application further provides a location information updating device for point of interest data. The device comprises:

the image acquisition module is used for acquiring a target image comprising a target interest point, and target interest point data of the target interest point has corresponding first position information;

The adjacent interest point determining module is used for determining adjacent interest points adjacent to the target interest point from the target image through the first position information, and the adjacent interest points of the adjacent interest points have corresponding second position information;

the confidence coefficient acquisition module is used for acquiring first position information confidence coefficient of target interest point data and second position information confidence coefficient of adjacent interest point data, wherein the first position information confidence coefficient is a parameter for evaluating that the first position information is correct position information, and the second position information confidence coefficient is a parameter for evaluating that the second position information is correct position information;

and the position information updating module is used for updating any one of the first position information and the second position information through the first position information confidence coefficient and the second position information confidence coefficient.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:

The method, the device, the computer equipment, the storage medium and the computer program product for updating the position information of the interest point data comprise firstly acquiring a target image comprising a target interest point, wherein the target interest point data of the target interest point have corresponding first position information, then determining an adjacent interest point adjacent to the target interest point from the target image through the first position information, the adjacent interest point data of the adjacent interest point have corresponding second position information, and acquiring the first position information confidence coefficient of the target interest point data and the second position information confidence coefficient of the adjacent interest point data, wherein the first position information confidence coefficient is a parameter for evaluating that the first position information is correct position information, the second position information confidence coefficient is a parameter for evaluating that the second position information is correct position information, and finally updating any one of the first position information and the second position information through the first position information confidence coefficient and the second position information confidence coefficient. By the method, the adjacent interest points adjacent to the target interest point are found through the first position information of the target interest point, so that whether the position information in the interest point data corresponding to the target interest point and the adjacent interest point is correct or not is estimated through the first position information confidence coefficient and the second position information confidence coefficient, namely, the position information corresponding to each interest point is adjusted and updated through the accuracy of the position information of the interest point and the accuracy of the position information of the interest point adjacent to the interest point, and the possibility error of independently determining the position information is avoided, so that the accuracy of updating the position information of the interest point data is improved.

Drawings

FIG. 1 is an application environment diagram of a method for updating location information of point of interest data in one embodiment;

FIG. 2 is a flow diagram of an application structure of a method for updating location information of point of interest data in one embodiment;

FIG. 3 is a flow chart illustrating a method for updating location information of interest point data according to an embodiment;

FIG. 4 is a schematic diagram of an embodiment of a target image in one embodiment;

FIG. 5 is a diagram of an embodiment of a target point of interest and neighboring points of interest in one embodiment;

FIG. 6 is a flow diagram of determining contiguous points of interest from contiguous sub-points of interest in a target sub-image, in one embodiment;

FIG. 7 is a flow diagram of determining contiguous points of interest from contiguous sub-points of interest in one embodiment;

FIG. 8 is a partial flow diagram of determining contiguous points of interest in one embodiment;

FIG. 9 is a partial flow chart illustrating determining neighboring points of interest according to the first location information and the third location information in one embodiment;

FIG. 10 is a schematic view of an embodiment of a first region in one embodiment;

FIG. 11 is a schematic diagram of an embodiment of a first coordinate in one embodiment;

FIG. 12 is a schematic view of an embodiment of a second region in one embodiment;

FIG. 13 is a schematic flow chart of a portion of determining neighboring points of interest from points of interest to be determined according to first coordinates and second coordinates in one embodiment;

FIG. 14 is a schematic flow chart of a portion of determining neighboring points of interest from the points of interest to be determined according to the first calculated coordinates and the second calculated coordinates in one embodiment;

FIG. 15 is a schematic flow chart of a portion of determining neighboring points of interest from the points of interest to be determined according to the first calculated coordinates and the second calculated coordinates;

FIG. 16 is a schematic view of an embodiment of a first left edge and a first right edge in one embodiment;

FIG. 17 is a schematic view of an embodiment of a first vertical distance in one embodiment;

FIG. 18 is a partial flow diagram of determining neighboring points of interest from among points of interest to be determined in one embodiment;

FIG. 19 is a schematic flow chart of a portion of determining neighboring points of interest from among points of interest to be determined according to another embodiment;

FIG. 20 is a diagram of an embodiment of left and right contiguous points of interest in one embodiment;

FIG. 21 is a flowchart of a method for updating location information of interest point data according to another embodiment;

FIG. 22 is a flow diagram of updating location information with confidence in the location information, in one embodiment;

FIG. 23 is a flow chart illustrating a method for updating location information of point of interest data according to an embodiment;

FIG. 24 is a block diagram showing a position information updating apparatus of interest point data in one embodiment;

FIG. 25 is a block diagram showing a position information updating apparatus for point of interest data according to another embodiment;

fig. 26 is an internal structural diagram of the computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

Along with the development of communication technology and the wide application of internet electronic maps, POI (Point of Interest, interest point) data exist in the internet electronic maps, and the POI data generally refer to point data in the internet electronic maps. However, the data error correction of POI data needs to take the position information and the name information into consideration, that is, the difficulty of data error correction is high. Currently, because POI data generally originates from a plurality of data sources, updating the position information of POI data by different data sources is a common data error correction method, however, in practical applications, different data sources may exist to provide different position information for the same POI data, thereby reducing the accuracy of updating the position information of the point of interest data. Therefore, how to improve the accuracy of the location information update of the point of interest data is a problem to be solved.

Based on the above, through the interest point data with wrong position information in the multivariate ecological data mining library, such as position information and address conflict, main and sub point position information conflict, position information conflict of different sources and the like, the aforementioned strategies ignore the most intuitive images, and in the existing image library, hundreds of millions of images are used for each real street, real road condition and real map, the images not only can provide the name information and the interest point position information of the interest points, but also can provide other interest points with adjacent relations for each interest point in space position. Therefore, the embodiment of the application provides a method for updating the position information of the interest point data in consideration of the fact that other interest points with adjacent relations are provided by all the interest points, so that the accuracy of updating the position information of the interest point data is improved.

The method for updating the position information of the interest point data, provided by the embodiment of the application, can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on the cloud or other servers.

Specifically, taking the application to the server 104 as an example, the server 104 first obtains a target image including a target point of interest, where the target point of interest includes corresponding first location information, and the target image may be an image obtained by performing image acquisition on a map road, or may be a plurality of images obtained by performing image acquisition on the map road. And the target image may be obtained by the server 104 from a data storage system, or may be obtained by the server 104 through communication interaction with the terminal 102, which is not limited herein.

Based on this, the server 104 determines, from the target image, an adjacent interest point adjacent to the target interest point through the first position information corresponding to the target interest point, the adjacent interest point data of the adjacent interest point has the corresponding second position information, and further obtains a first position information confidence level of the target interest point data and a second position information confidence level of the adjacent interest point data, where the first position information confidence level is a parameter for evaluating that the first position information is correct position information, the second position information confidence level is a parameter for evaluating that the second position information is correct position information, and updates any one of the first position information and the second position information through the first position information confidence level and the second position information confidence level. Therefore, the server 104 can adjust and update the position information corresponding to each interest point through two dimensions of the accuracy of the position information of the interest point and the accuracy of the position information of the interest point adjacent to the interest point, thereby avoiding the possibility error of independently determining the position information and improving the accuracy of the position information update of the interest point data.

The terminal 102 may be, but not limited to, various desktop computers, notebook computers, smart phones, tablet computers, internet of things devices, portable wearable devices, intelligent voice interaction devices, intelligent home appliances, vehicle terminals, aircrafts, etc., and the internet of things devices may be intelligent speakers, intelligent televisions, intelligent air conditioners, intelligent vehicle devices, etc. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers. The method for updating the position information of the interest point data provided by the embodiment of the application can be applied to various scenes, including but not limited to maps, internet of vehicles, automatic driving or traffic related scenes and the like.

The following describes a specific method architecture of the location information updating method of the point of interest data according to the embodiment of the present application, as shown in fig. 2, specifically including object detection 202, neighboring point of interest calculation 204, and location information updating 206. The target detection 202 specifically includes target image searching and target interest point detection, that is, an initial image set is acquired first, each initial image in the initial image set includes at least one interest point data, and then the target detection 202 is completed by extracting a target object type from each initial image and determining a target image including a target interest point.

Next, the calculation 204 of adjacent points of interest specifically includes calculating candidate adjacent points of interest and screening the adjacent points of interest, identifying a first region of a target point of interest in a target image, determining a first coordinate by using a vertex of the first region and first position information, identifying a target image, determining a point of interest to be determined in the target image, which is consistent with the object type of the target point of interest, having corresponding third position information, identifying second regions of each point of interest to be determined, which correspond to each other in the target image, determining second coordinates by using vertices of each second region and each third position information, determining a first calculation coordinate by using the first coordinate, and determining second calculation coordinates by using each second coordinate, thereby determining a first candidate left adjacent point of interest and a first candidate right adjacent point of interest from each point of interest to be determined by using the first calculation coordinate and each second calculation coordinate, and completing the calculation step of the candidate adjacent points of interest. Based on this, a first vertical distance from the first center point coordinate to the first edge and a second vertical distance from each second center point coordinate to each second edge are calculated, and the first candidate left neighboring interest point and the first candidate right neighboring interest point are screened to determine a left neighboring interest point and a right neighboring interest point, that is, the screening of the neighboring interest points is completed, thereby completing the neighboring interest point calculation 204.

Finally, the location information update 206 specifically includes location information distance calculation and location information update, that is, a location information difference between the first location information and the second location information is calculated first, then whether the location information difference is greater than a location threshold is determined, and if so, the location information update is performed through the first location information confidence level and the second location information confidence level, and if the location information difference is less than or equal to the location threshold, the location information update is ended. It is to be understood that the example of fig. 2 is only for a specific implementation architecture of the location information updating method of the access point data, and should not be construed as a specific limitation of the present application.

Further, the method for updating the location information of the interest point data provided in the embodiment of the present application specifically needs to be performed by a model obtained by machine learning, thereby introducing an artificial intelligence related technology:

artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use the knowledge to obtain optimal results. In other words, artificial intelligence is an integrated technology of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence, i.e. research on design principles and implementation methods of various intelligent machines, enables the machines to have functions of sensing, reasoning and decision.

The artificial intelligence technology is a comprehensive subject, and relates to the technology with wide fields, namely the technology with a hardware level and the technology with a software level. Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

In the embodiment of the application, a Machine Learning (ML) related technology is specifically needed, and the ML is a multi-domain cross subject, and relates to multiple subjects such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, and the like. It is specially studied how a computer simulates or implements learning behavior of a human to acquire new knowledge or skills, and reorganizes existing knowledge structures to continuously improve own performance. Machine learning is the core of artificial intelligence, a fundamental approach to letting computers have intelligence, which is applied throughout various areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, confidence networks, reinforcement learning, transfer learning, induction learning, teaching learning, and the like. With research and advancement of artificial intelligence technology, research and application of artificial intelligence technology is being developed in various fields, such as common smart home, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned, automatic driving, unmanned aerial vehicles, robots, smart medical treatment, smart customer service, etc., and it is believed that with the development of technology, artificial intelligence technology will be applied in more fields and with increasing importance value.

In one embodiment, as shown in fig. 3, a method for updating location information of point of interest data is provided, and the method is described by taking the application of the method to the server in fig. 1 as an example, it can be understood that the method can also be applied to a terminal, and can also be applied to a system including the terminal and the server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the steps of:

step 302, obtaining a target image including a target interest point, where target interest point data of the target interest point has corresponding first location information.

The target interest points are POIs of the position information to be updated, and the target interest points are POIs of target object types, wherein the target object types can be shop signboards, buildings, public transportation sites and the like, and the target object types are determined according to actual application requirements. Because each point of interest (POI) has corresponding point of interest data (i.e., POI data), the POI data generally refers to point class data in the internet electronic map, and the POI data at least includes attribute information such as name information and location information, the target point of interest data of the target point of interest specifically includes first location information corresponding to the target point of interest, the location information may be latitude and longitude information or other coordinate system information that may uniquely indicate the location of the point of interest, and the attribute information may also include object type, address information, time information, and the like.

Specifically, the server acquires a target image including a target interest point, and the server may acquire the target image from the data storage system, that is, in practical application, acquire images of each region on the map based on a preset time period, and then store the acquired images in the data storage system, so that the server performs target object type extraction on each acquired image in the data storage system, and determines a target image including the target interest point from each acquired image. Or, the server may acquire the acquired images through communication interaction with the terminal, and then perform object type extraction on the acquired images to determine the target image including the target interest point from each acquired image, so that a specific mode of specifically acquiring the target image is not limited.

Further, taking the specific application to the map field as an example, the server obtaining the target image including the target interest point specifically includes: acquiring a plurality of acquired images obtained by image acquisition of each area on the map, determining the target object type of the target interest point, extracting the target object type of each acquired image based on the target object type, and determining the target image from each acquired image. The terminal can send the acquired multiple acquired images to the server in real time in the image acquisition process, so that the server acquires the multiple acquired images. Or after the terminal completes image acquisition, transmitting the acquired plurality of acquired images to a server, and acquiring the plurality of acquired images by the server.

Based on the above, when the server needs to update the position information of the target interest point, for example, when the server needs to update the position information of a shop sign, update the position information of a building or update the position information of a public transportation station, the server determines the target object type of the target interest point of the position information to be updated, and then extracts the target object type of each acquired image based on the target object type. That is, the server detects object types of all the points of interest in the acquired image to extract a candidate acquired image including the target object type, then determines a candidate acquired image including the target point of interest from among the candidate acquired images, and determines the candidate acquired image including the target point of interest as the target image.

It can be known that the target image may be one image obtained by image acquisition on the map road, or may be a plurality of images obtained by image acquisition on the map road, that is, the target image may be one image or a plurality of images, which is not limited herein.

For easy understanding of the target image and the target interest point, taking the specific example of the target interest point as a shop sign, as shown in fig. 4, the target image 402 specifically includes the target interest point 404, the target interest point data of the target interest point 404 has corresponding first position information 406, the first position information 406 is used to describe the specific position of the target interest point 404 on the map, and the first position information 406 is specifically (XX 1, YY 2). It will be appreciated that the foregoing examples are all used to understand the present solution, and in practical applications, the target interest point may also be other related objects that may appear on a map, such as a building, a public transportation site, etc., based on different application scenarios, and the specific application is not limited herein.

Step 304, determining adjacent interest points adjacent to the target interest point from the target image through the first position information, wherein the adjacent interest point data of the adjacent interest points has corresponding second position information.

Wherein, the adjacent interest points at least comprise: the left adjacent interest point and the right adjacent interest point, and the second position information at least includes: left adjacent position information corresponding to the left adjacent point of interest data, and right adjacent position information corresponding to the right adjacent point of interest data. And the adjacent interest point is an interest point adjacent to the target interest point in the target image, namely, the adjacent interest point and the target interest point have an adjacent relation in the same image, and the adjacent relation is specifically a left-right adjacent relation. As can be seen from the description of the foregoing embodiment, each point of interest has corresponding point of interest data, and the POI data at least includes attribute information such as name information and location information, so that the neighboring point of interest data of the neighboring point of interest specifically includes second location information corresponding to the neighboring point of interest, and similarly, the location information may be longitude and latitude information or other coordinate system information that can uniquely indicate the location of the data, which is not limited herein, and the attribute information may also include object type, address information, time information, and the like.

Second, since there may be at least one point of interest having an adjacency relationship with the target point of interest in the target image, the adjacency point of interest includes at least: a left adjacent interest point and a right adjacent interest point, wherein the left adjacent interest point is positioned at the left side of the target interest point in the target image, and the right adjacent interest point is positioned at the right side of the target interest point in the target image. Therefore, the second location information corresponding to the neighboring point of interest includes at least: left adjacent position information corresponding to the left adjacent interest point, and right adjacent position information corresponding to the right adjacent interest point data.

Specifically, the server determines candidate adjacent interest points with adjacent relation to the target interest point from the target image through the first position information, and then screens the candidate adjacent interest points by further considering the distance relation and the position relation between the interest points. In practical application, the target interest point has corresponding target interest point data, so that the adjacent relation between the target interest point and the adjacent interest point can correspond to the adjacent relation of the interest point data corresponding to the interest point, namely, the space coordinate relation between the target interest point data and the adjacent interest point data can be mapped through the position information in the target interest point data and the adjacent interest point data, and therefore, the distance between the target interest point data and the position information in the adjacent interest point data is smaller than a distance threshold value.

Further, taking the map field as an example, it can be seen from the foregoing embodiment that the server specifically acquires a plurality of acquired images obtained by performing image acquisition on each region on the map, determines a target object type of the target interest point, performs target object type extraction on each acquired image based on the target object type, and determines a target image from each acquired image. Therefore, in the process of determining the adjacent interest points, the server should also consider the target object type of the target interest point, that is, the server specifically needs to determine, from the target image, the adjacent interest points adjacent to the target interest point and having the same object type through the first location information and the target object type, that is, the determined object type of the adjacent interest point is the target object type. For example, if the target point of interest is a store sign, then the adjacent point of interest is also a store sign, or if the target point of interest is a public transportation site, then the adjacent point of interest is also a public transportation site.

For ease of understanding, as shown in FIG. 5, the target point of interest 504 is included in the target image 502, and the target point of interest 502 has a left adjacent point of interest 506 and a right adjacent point of interest 508, with the right adjacent point of interest 508 to the right of the target point of interest 504 in the target image 502, and the left adjacent point of interest 506 to the left of the target point of interest 504 in the target image 502. It will be appreciated that the example of fig. 5 is only for understanding the present solution and should not be construed as limiting the present solution.

It will be appreciated that, since the neighboring points of interest have corresponding second location information, the abscissa (e.g., longitude coordinate) in the second location information corresponding to the left neighboring point of interest should be smaller than the abscissa (e.g., longitude coordinate) in the first location information corresponding to the target point of interest to ensure that the left neighboring point of interest is to the left of the target point of interest in the target image. Similarly, the abscissa (e.g., longitude coordinate) in the second position information corresponding to the right and left adjacent interest points is larger than the abscissa (e.g., longitude coordinate) in the first position information corresponding to the target interest point, so as to ensure that the right adjacent interest point is located on the right side of the target interest point in the target image. Specific limitations are specifically set forth herein.

Step 306, obtaining a first location information confidence coefficient of the target interest point data and a second location information confidence coefficient of the adjacent interest point data, wherein the first location information confidence coefficient is a parameter for evaluating that the first location information is correct location information, and the second location information confidence coefficient is a parameter for evaluating that the second location information is correct location information.

The position information confidence is a parameter for evaluating that the position information is correct position information, and the position information confidence can be trusted or untrusted. The first positional information confidence is thus a parameter for evaluating the first positional information as correct positional information, and the second positional information confidence is a parameter for evaluating the second positional information as correct positional information. For example, a position information confidence of "0" indicates that the position information is not trusted, i.e., the position information is erroneous, and similarly, a position information confidence of "1" indicates that the position information is trusted, i.e., the position information is correct, it will be appreciated that the position information confidence may also have been described in terms of probability, i.e., the position information confidence may be used to describe the probability that the position information is correct, and is not limited herein.

Specifically, the server acquires a first position information confidence coefficient of first position information corresponding to the target interest point data and acquires a second position information confidence coefficient of second position information corresponding to the adjacent interest point data. The server may specifically obtain the first location information confidence level and the second location information confidence level from the data storage system. Alternatively, the server may also acquire the first location information confidence coefficient and the second location information confidence coefficient through communication interaction with the terminal, so a specific manner of acquiring the location information confidence coefficient is not limited.

Step 308, updating any one of the first location information and the second location information by the first location information confidence and the second location information confidence.

Specifically, the server updates any one of the first location information and the second location information by the first location information confidence and the second location information confidence. That is, the server can determine whether the first position information is correct or not according to the first position information confidence coefficient, and can determine whether the second position information is correct or not according to the second position information confidence coefficient, so that when any position information confidence coefficient exists in the first position information confidence coefficient and the second position information confidence coefficient, the server updates and adjusts the error position information when the corresponding position information is described as the error position information. And the confidence of the position information corresponding to the updated position information before updating is not trusted.

In the method for updating the position information of the interest point data, the adjacent interest point adjacent to the target interest point is found through the first position information of the target interest point, so that whether the position information in the interest point data corresponding to the target interest point and the adjacent interest point is correct or not is estimated through the first position information confidence coefficient and the second position information confidence coefficient, namely, the position information corresponding to each interest point is adjusted and updated through the accuracy of the position information of the interest point and the accuracy of the position information of the interest point adjacent to the interest point, so that the possibility error of independently determining the position information is avoided, and the accuracy of updating the position information of the interest point data is improved.

In one embodiment, the target image includes a plurality of target sub-images, each of which includes a target point of interest; the first location information includes a plurality of first sub-location information.

The target image comprises a plurality of target sub-images, and each target sub-image comprises a target interest point. The first position information is coordinate system information which uniquely indicates the position of the target interest point, and certain deviation and difference exist in the coordinate system information of the target interest point in different target sub-images, so that the first position information comprises a plurality of first sub-position information, and the first sub-position information specifically corresponds to one target sub-image. Exemplary, for example: the target image comprises a target sub-image A1, a target sub-image A2 and a target sub-image A3, and the first sub-position information B1 of the target interest point corresponding to the target sub-image A1, the first sub-position information B2 of the target interest point corresponding to the target sub-image A2 and the first sub-position information B3 of the target interest point corresponding to the target sub-image A3.

Based on this, as shown in fig. 6, determining the contiguous interest adjacent to the target interest point from the target image by the first position information includes:

step 602, determining adjacent sub-interest points adjacent to the target interest point from the corresponding target sub-images according to the first sub-position information.

The adjacent sub-interest points are interest points adjacent to the target interest points in the corresponding target sub-images, namely, the adjacent sub-interest points and the target interest points have an adjacent relation in the same target sub-image, and the object types of the adjacent sub-interest points are consistent with the object types of the target interest points. Second, since there may be at least one point of interest having an adjacent relationship with the target point of interest in each target sub-image, the adjacent sub-points of interest include at least: a left adjacent sub-interest point and a right adjacent sub-interest point, wherein the left adjacent sub-interest point is positioned at the left side of the target interest point in the corresponding target sub-image, and the right adjacent sub-interest point is positioned at the right side of the target interest point in the corresponding target sub-image. Therefore, the location information corresponding to the adjacent sub-interest point includes at least: the location information corresponding to the left adjacent sub-interest point and the location information corresponding to the right adjacent sub-interest point are similar to the adjacent sub-interest points, and detailed description thereof is omitted herein.

Specifically, the server determines candidate adjacent sub-interest points with adjacent relation to the target interest points from all target sub-images of the target image through the first position information, and then screens the candidate adjacent sub-interest points by further considering the distance relation and the position relation between the interest points. The manner of determining the adjacent sub-interest points is similar to that of determining the adjacent interest points in the full-text embodiment, and will not be repeated here.

Illustratively, the target image includes a target sub-image A1, a target sub-image A2, and a target sub-image A3, and the server determines, in the target sub-image A1, an adjacent sub-interest point C1 adjacent to the target interest point by the first sub-position information B1 of the target interest point in the target sub-image A1, where the adjacent sub-interest point C1 specifically includes a left adjacent sub-interest point D1 and a right adjacent sub-interest point E1. Similarly, the server determines an adjacent sub-interest point C2 adjacent to the target interest point in the target sub-image A2 through the first sub-position information B2 of the target interest point in the target sub-image A2, wherein the adjacent sub-interest point C2 specifically comprises a left adjacent sub-interest point D2 and a right adjacent sub-interest point E2. And the server further determines an adjacent sub-interest point C3 adjacent to the target interest point in the target sub-image A3 through the first sub-position information B3 of the target interest point in the target sub-image A3, wherein the adjacent sub-interest point C3 specifically comprises a left adjacent sub-interest point D3 and a right adjacent sub-interest point E3.

In step 604, from the adjacent sub-interest points of each target sub-image, an adjacent interest point is determined.

Specifically, the server determines an adjacent interest point from adjacent sub-interest points of each target sub-image. Namely, the server specifically calculates the adjacent sub-interest points of each target sub-image and the distance difference value between the adjacent sub-interest points and the target interest points, and determines the adjacent sub-interest point with the smallest distance difference value as the adjacent interest point.

It may be appreciated that, since each neighboring sub-interest point also includes a left neighboring sub-interest point and a right neighboring sub-interest point, the server may divide the left neighboring sub-interest point in the neighboring sub-interest points of each target sub-image into a left neighboring sub-interest point set, and then determine the left neighboring sub-interest point in the left neighboring sub-interest point set, where the distance difference between the left neighboring sub-interest point set and the target interest point is the smallest, as the left neighboring interest point in the neighboring interest points. Similarly, the server may divide the right adjacent sub-interest point in the adjacent sub-interest points of each target sub-image into a right adjacent sub-interest point set, and then determine the right adjacent sub-interest point in the right adjacent sub-interest point set, where the distance difference between the right adjacent sub-interest point set and the target interest point is the smallest, as the right adjacent interest point in the adjacent interest points. It is known that the left adjacent point of interest and the right adjacent point of interest included in the adjacent points of interest may originate from different target sub-images.

Illustratively, further description is made based on the example of step 602, since the adjacent sub-interest point C1 includes the left adjacent sub-interest point D1 and the right adjacent sub-interest point E1, the adjacent sub-interest point C2 includes the left adjacent sub-interest point D2 and the right adjacent sub-interest point E2, and the adjacent sub-interest point C3 includes the left adjacent sub-interest point D3 and the right adjacent sub-interest point E3. The server may obtain a left contiguous set of sub-interests including left contiguous sub-interests D1, left contiguous sub-interests D2, and left contiguous sub-interests D3, and a right contiguous set of sub-interests including right contiguous sub-interests E1, right contiguous sub-interests E2, and right contiguous sub-interests E3. If the server determines that the distance difference between the left adjacent sub-interest point D2 and the target interest point is the smallest in the left adjacent sub-interest point set, and determines that the distance difference between the right adjacent sub-interest point E1 and the target interest point is the smallest in the right adjacent sub-interest point set, then determining the adjacent interest point of the target interest point specifically includes: a left contiguous sub-point of interest D2 from the target sub-image A2, and a right contiguous sub-point of interest E1 from the target sub-image A1.

For ease of understanding, as shown in fig. 7, a target sub-image 701, a target sub-image 702, and a target sub-image 703 are included, and target points of interest 704 exist in all of the target sub-images 701 to 704. A left neighboring sub-interest point 705 and a right neighboring sub-interest point 706 that are adjacent to the target interest point 704 are determined in the target sub-image 701, a left neighboring sub-interest point 707 and a right neighboring sub-interest point 708 that are adjacent to the target interest point 704 are determined in the target sub-image 702, and a left neighboring sub-interest point 709 and a right neighboring sub-interest point 710 that are adjacent to the target interest point 704 are determined in the target sub-image 703. Then, a distance difference between each left adjacent sub-interest point and the target interest point 704 is calculated, that is, a distance difference between the left adjacent sub-interest point 705 and the target interest point 704 is calculated, a distance difference between the left adjacent sub-interest point 707 and the target interest point 704 is calculated, and if the distance difference between the left adjacent sub-interest point 709 and the target interest point 704 is minimum, the left adjacent sub-interest point 709 can be determined as one adjacent interest point of the target interest point 704.

Similarly, the distance difference between each right adjacent sub-interest point and the target interest point 704 is calculated, that is, the distance difference between the right adjacent sub-interest point 706 and the target interest point 704 is calculated, the distance difference between the right adjacent sub-interest point 708 and the target interest point 704 is calculated, and the distance difference between the right adjacent sub-interest point 710 and the target interest point 704 is calculated, if the distance difference between the right adjacent sub-interest point 706 and the target interest point 704 is the smallest, the right adjacent sub-interest point 706 may be determined as one adjacent interest point of the target interest point 704, so the adjacent interest point 711 of the target interest point 704 specifically includes: left neighbor sub-point of interest 709 and right neighbor sub-point of interest 706.

It is to be understood that both the foregoing examples and the illustrations are for the understanding of the present invention, and are not to be construed as limiting the invention in any way.

In this embodiment, by performing screening and confirming on all target sub-images including the target interest point, an error in determining the adjacent interest point due to an error of a single image is avoided, so that an adjacent relationship with the target interest point is determined, and the adjacent sub-interest point closest to the target interest point is determined, so that reliability and accuracy of determining the adjacent interest point finally can be ensured, and accuracy of updating position information of subsequent interest point data is improved.

In one embodiment, as shown in fig. 8, determining, from the target image, an adjacent interest point adjacent to the target interest point by the first position information includes:

step 802, performing object recognition on the target image, and determining an interest point to be determined, which is consistent with the object type of the target interest point in the target image, wherein the interest point to be determined has corresponding third position information.

Specifically, the server performs object recognition on the target image, determines an interest point to be determined, which is consistent with the object type of the target interest point, in the target image, where the interest point to be determined may be one interest point or a plurality of interest points to be determined, and is not limited herein. The server specifically detects the target image based on the object type of the target interest point, detects the interest point to be determined, which is consistent with the object type of the target interest point, from the target image, and divides the interest point to be determined from the target image. The foregoing object detection may also be referred to herein as object extraction, and is a method for image segmentation based on geometric and statistical features of an object, specifically for segmenting and identifying the object, which is not described in detail herein.

For example, if the object type of the target point of interest is a store sign, the server may determine all store signs from the target image by target detection, and determine a store sign that does not include the target point of interest from all store signs as the point of interest to be determined. For example, the object type of the target point of interest is a shop sign, while 3 shop signs are determined by target detection in the target image, and the target point of interest is specifically included in the three shop signs, so that another 2 shop signs can be determined as points of interest to be determined, that is, the point of interest to be determined F1 and the point of interest to be determined F2 are obtained. Or if the object type of the target interest point is a public transportation site, the server may determine all public transportation sites from the target image through target detection, and determine public transportation sites that do not include the target interest point in all public transportation sites as the interest point to be determined. It is to be understood that the foregoing examples have been provided merely for the purpose of explanation and are in no way to be construed as limiting.

In step 804, the adjacent points of interest are determined from the points of interest to be determined by the first location information and the third location information.

Specifically, the server determines the adjacent interest point from the interest points to be determined through the first position information and the third position information. The server considers the position relation and the distance relation between each interest point to be determined and the target interest point through the first position information and the third position information, so that adjacent interest points are determined in the interest points to be determined. The positional relationship includes at least: the interest point to be determined is positioned on the left side of the target interest point, the interest point to be determined is positioned on the right side of the target interest point, the interest point to be determined is positioned above the target interest point, the interest point to be determined is positioned below the target interest point, and the like.

In this embodiment, the object recognition is used to ensure that the determined interest point to be determined is consistent with the object type of the target interest point, so as to ensure that the determined adjacent interest point from the interest points to be determined is consistent with the object type of the target interest point, and then the position information of the interest points can consider the position relationship and the distance relationship between each interest point, so as to ensure that the determined adjacent interest points meet the adjacent requirement, thereby improving the reliability and the accuracy of the adjacent interest points and further improving the accuracy of the position information updating of the subsequent interest point data.

As will be described in detail below, if the first location information and the third location information are used, the method of determining the neighboring points of interest in consideration of the location relationship and the distance relationship is as follows: in one embodiment, as shown in fig. 9, determining, from the points of interest to be determined, an adjacent point of interest by the first location information and the third location information, includes:

in step 902, a first region of the target interest point in the target image is identified, and a first coordinate is determined according to a vertex of the first region and the first position information, wherein the first region is a quadrilateral region.

The first area is a quadrilateral area, and the first area is specifically a minimum circumscribed quadrilateral of the target interest point, where the circumscribed quadrilateral may be a rectangle or a square, and the specific location is not limited. Based on this, the aforementioned first coordinates specifically include coordinates of four vertices of the first region in the target image. For example, the first coordinates specifically include: (x 11, y 11), (x 21, y 21), (x 31, y 31), (x 41, y 41).

Specifically, the server identifies a first region of the target point of interest in the target image, that is, the server determines a minimum circumscribed quadrangle of the region in which the target point of interest is located, and determines the minimum circumscribed quadrangle as the first region. For ease of understanding, as shown in fig. 10, a target point of interest 1004 exists in the target image 1002, and then, from the target image 1002, a minimum circumscribed quadrangle of an area where the target point of interest 1004 is located is determined, so that the first area 1006 can be obtained.

Further, the server determines coordinates of four vertexes of the first area in the target image according to the positions of the vertexes of the first area and first position information of the target interest point, so as to obtain first coordinates. For ease of understanding, as shown in fig. 11, there is a target point of interest 1102 in the target image 1101, and then, a minimum circumscribed quadrangle of the area where the target point of interest 1102 is located is determined as a first area 1103, and the first area 1103 has

vertices

1104, 1105, 1106 and 1107, then, coordinates of the vertices 1104 to 1107 in the target image 1101 can be determined by the first position information of the target point of interest 1102 and the specific position distribution of the

vertices

1104, 1105, 1106 and 1107, respectively, so as to obtain the first coordinates.

Step 904, identifying second areas corresponding to the points of interest to be determined in the target image, and determining second coordinates according to the vertices of the second areas and the third position information, wherein the second areas are quadrilateral areas.

The second area is a quadrilateral area, and the second area is specifically a minimum circumscribed quadrilateral of the interest point to be determined, where the circumscribed quadrilateral may be a rectangle or a square, and the specific point is not limited herein. Based on this, the aforementioned second coordinates are coordinates of four vertices of the second region in the target image.

Specifically, the server identifies second areas corresponding to the points of interest to be determined in the target image respectively, that is, the server determines the minimum circumscribed quadrangle of the area where the points of interest to be determined are located, and determines the minimum circumscribed quadrangle as the second area corresponding to the points of interest to be determined. For example, if the to-be-determined interest point F1 and the to-be-determined interest point F2 exist, the smallest circumscribed quadrangle of the area where the to-be-determined interest point F1 is located may be determined as the second area G1 corresponding to the to-be-determined interest point F1, and the smallest circumscribed quadrangle of the area where the to-be-determined interest point F2 is located may be determined as the second area G2 corresponding to the to-be-determined interest point F2.

For easy understanding, as shown in fig. 12, the target image 1201 has the target interest point 1202, and the object type of the target interest point 1202 is a shop sign, so the server may determine the interest point 1203 to be determined and the interest point 1204 to be determined, which are also shop signs, in the target image 1201, and then determine the minimum circumscribed quadrangle of the area where the interest point 1203 to be determined is located from the target image 1201, so that the second area 1205 corresponding to the interest point 1203 to be determined can be obtained. Similarly, from the target image 1201, the minimum circumscribed quadrangle of the region where the point of interest 1204 is located is determined, so as to obtain the second region 1206 corresponding to the point of interest 1204.

Further, the server determines coordinates of four vertexes of the second area in the target image according to the positions of the vertexes of the second area and second position information of the interest point to be determined, so as to obtain second coordinates. For example, the second coordinates of the second area G1 corresponding to the point of interest F1 to be determined specifically include: the second coordinates of the second region G1 corresponding to (x 12, y 12), (x 22, y 22), (x 32, y 32), (x 42, y 42) and the point of interest F1 to be determined specifically include: (x 13, y 13), (x 23, y 23), (x 33, y 33), (x 43, y 43). The second coordinates are specifically similar to the first coordinates described above, and will not be described again here. It is to be understood that the examples in this embodiment are for understanding the present solution and should not be construed as being particularly limiting.

And step 906, determining adjacent interest points from the interest points to be determined through the first coordinates and the second coordinates.

Specifically, the server considers the location relationship and the distance relationship between the region where the target interest point is located and the region where each interest point to be determined is located through the first coordinates and each second coordinate, and determines the adjacent interest point in the interest points to be determined.

In this embodiment, the position relationship and the distance relationship between each interest point can be more comprehensively considered through the specific area of the interest point in the image, so that the reliability and the accuracy of the determined adjacent interest points are further ensured, and the accuracy of the position information updating of the subsequent interest point data is improved.

In one embodiment, as shown in fig. 13, determining the neighboring points of interest from the points of interest to be determined by the first coordinates and the second coordinates includes:

step 1302, determining a first calculated coordinate by a first coordinate, where the first calculated coordinate includes at least: the system comprises a first maximum coordinate, a first minimum coordinate and a first center point coordinate, wherein the first maximum coordinate comprises a maximum abscissa and a maximum ordinate in the first coordinate, and the first minimum coordinate comprises a minimum abscissa and a minimum ordinate in the first coordinate.

Wherein the first calculated coordinates include at least: the system comprises a first maximum coordinate, a first minimum coordinate and a first center point coordinate, wherein the first maximum coordinate comprises a maximum abscissa and a maximum ordinate in the first coordinate, and the first minimum coordinate comprises a minimum abscissa and a minimum ordinate in the first coordinate. The first center point coordinate is a coordinate corresponding to the center point of the first area, that is, an average value of abscissas of four vertices in the first coordinate is an abscissa of the first center point coordinate, and an average value of ordinates of four vertices in the first coordinate is an ordinate of the first center point coordinate. For example, the first coordinates specifically include: (x 11, y 11), (x 21, y 21), (x 31, y 31), (x 41, y 41), then the first center point coordinate is

Based on this, the first maximum coordinates specifically include: the maximum abscissa of four vertices in the first coordinate, and the maximum ordinate of four vertices in the first coordinate, for example, specifically includes: (x 11, y 11), (x 21, y 21), (x 31, y 31), (x 41, y 41), and x11 is the largest abscissa of x11, x21, x31, and x41, and y31 is the largest ordinate of y11, y21, y31, and y41, then the first largest coordinate is (x 11, y 31).

Next, the first minimum coordinates specifically include: the minimum abscissa among the four vertices in the first coordinate, and the minimum ordinate among the four vertices in the first coordinate, for example, specifically include: (x 11, y 11), (x 21, y 21), (x 31, y 31), (x 41, y 41), and x21 is the smallest abscissa among x11, x21, x31, and x41, and y41 is the smallest ordinate among y11, y21, y31, and y41, then the first smallest coordinate is (x 21, y 41). It is to be understood that the first maximum coordinate and the first minimum coordinate may be coordinates corresponding to four vertices in the first area, or may not be coordinates corresponding to any vertex.

Specifically, the server determines, by using the first coordinates of the first area, a first calculation coordinate corresponding to the first area, that is, the server determines an average value of the abscissas of the four vertices of the first area as the abscissas of the first center point coordinate, and determines an average value of the ordinates of the four vertices of the first area as the ordinates of the first center point coordinate, so as to obtain the first center point coordinate. Then, the server specifically constructs a first maximum coordinate through coordinates corresponding to the four vertexes in the first coordinate, a maximum abscissa among the four vertexes, and a maximum ordinate among the four vertexes in the first coordinate. Similarly, the server may also construct the first minimum coordinate from the minimum abscissa of the four vertices and the minimum ordinate of the four vertices in the first coordinate.

In step 1304, second calculation coordinates corresponding to each second coordinate are determined, where the second calculation coordinates at least include: the second maximum coordinates comprise a maximum abscissa and a maximum ordinate in the second coordinates, and the second minimum coordinates comprise a minimum abscissa and a minimum ordinate in the second coordinates.

Wherein the second calculated coordinates include at least: the second maximum coordinates comprise a maximum abscissa and a maximum ordinate in the second coordinates, and the second minimum coordinates comprise a minimum abscissa and a minimum ordinate in the second coordinates. The second center point coordinate is a coordinate corresponding to the center point of the second area, that is, an average value of abscissas of four vertices in the second coordinate is an abscissa of the second center point coordinate, and an average value of ordinates of four vertices in the second coordinate is an ordinate of the second center point coordinate. For example, the second coordinates specifically include: (x 12, y 12), (x 22, y 22), (x 32, y 32), (x 42, y 42), then the second center point coordinate is

Based on this, the second maximum coordinates specifically include: the maximum abscissa of four vertices in the second coordinate, and the maximum ordinate of four vertices in the second coordinate, for example, the second coordinate specifically includes: (x 12, y 12), (x 22, y 22), (x 32, y 32), (x 42, y 42), and x22 is the largest abscissa of x12, x22, x32, and x42, and y32 is the largest ordinate of y12, y22, y32, and y42, then the second largest coordinate is (x 22, y 32).

Next, the second minimum coordinates specifically include: the minimum abscissa among the four vertices in the second coordinate, and the minimum ordinate among the four vertices in the second coordinate, for example, the second coordinate specifically includes: (x 12, y 12), (x 22, y 22), (x 32, y 32), (x 42, y 42), and x42 is the smallest abscissa among x12, x22, x32, and x42, and y12 is the smallest ordinate among y12, y22, y32, and y42, then the second smallest coordinate is (x 42, y 12). It is to be understood that the second maximum coordinate and the second minimum coordinate may be coordinates corresponding to four vertices in the second area, or may not be coordinates corresponding to any vertex.

Specifically, the server determines second calculation coordinates corresponding to each second region through the second coordinates of each second region. That is, for each second region, the server determines an average of the abscissas of the four vertices of the second region as the abscissas of the second center point coordinates, and determines an average of the ordinates of the four vertices of the second region as the ordinates of the second center point coordinates to obtain the second center point coordinates. And then, the server specifically constructs a second maximum coordinate through coordinates corresponding to the four vertexes in the second coordinate, the maximum abscissa among the four vertexes, and the maximum ordinate among the four vertexes in the second coordinate. Similarly, the server may also construct the second minimum coordinate from the minimum abscissa of the four vertices and the minimum ordinate of the four vertices in the second coordinate. The specific calculation manner of the second calculation coordinates is similar to the determination manner of the first calculation coordinates, and will not be described herein.

In step 1306, adjacent points of interest are determined from the points of interest to be determined by the first calculated coordinates and the second calculated coordinates.

Specifically, the server further considers the vertex position and the center point position of the region where the target interest point is located, and the position relationship and the distance relationship between the vertex position and the center point position of the region where the interest point to be determined is located through the first calculation coordinates and the second calculation coordinates, and determines the adjacent interest point from the interest points to be determined.

In this embodiment, further, by using the vertex position and the center point position of the specific area of the interest point in the image, since the specific area range of the interest point can be described by the fixed point position, the center point position can more accurately determine the distance between two interest points, so that the position relationship and the distance relationship between each interest point are more comprehensively and finely considered, the reliability and the accuracy of the determined adjacent interest points are further ensured, and the accuracy of the position information update of the subsequent interest point data is improved.

In one embodiment, as shown in fig. 14, determining the neighboring points of interest from the points of interest to be determined by the first calculated coordinates and the second calculated coordinates includes:

Step 1402, determining a vertical coordinate range corresponding to each second calculation coordinate, where the vertical coordinate range is composed of a minimum ordinate of the second calculation coordinates and a maximum ordinate of the second calculation coordinates.

The vertical coordinate range is composed of the minimum ordinate in the second calculation coordinates and the maximum ordinate in the second calculation coordinates.

Specifically, since the second calculated coordinates include at least: the second maximum coordinates, the second minimum coordinates and the second center point coordinates, and the second maximum coordinates include the maximum abscissa and the maximum ordinate among the second coordinates, and the second minimum coordinates include the minimum abscissa and the minimum ordinate among the second coordinates. Therefore, the server determines the vertical coordinate ranges corresponding to the second calculation coordinates respectively, that is, for the second calculation coordinates corresponding to each second area, the server determines the minimum range value of the vertical coordinate ranges through the minimum ordinate included in the second minimum ordinate in the second calculation coordinates. Similarly, the server determines a minimum range value of the vertical coordinate range by the maximum ordinate included in the second maximum ordinate among the second calculation coordinates.

For ease of understanding, further description will be made based on the foregoing examples, and for example, the second coordinates specifically include: (x 12, y 12), (x 22, y 22), (x 32, y 32), (x 42, y 42), if x22 is the largest abscissa of x12, x22, x32, and x42, and y32 is the largest ordinate of y12, y22, y32, and y42, then the second largest coordinate is (x 22, y 32). Second, x42 is the smallest abscissa among x12, x22, x32, and x42, and y12 is the smallest ordinate among y12, y22, y32, and y42, then the second smallest coordinate is (x 42, y 12), that is, the second largest coordinate (x 22, y 32), and the second smallest coordinate (x 42, y 12) are included in the second calculated coordinates. Thus, it is known from the second maximum coordinates (x 22, y 32), that y32 is the maximum ordinate among the second calculated coordinates. Similarly, the second minimum coordinate (x 42, y12 means that y12 is the minimum ordinate among the second calculated coordinates).

In step 1404, adjacent points of interest are determined from the points of interest to be determined by the first calculated coordinates, the second calculated coordinates, and the vertical coordinate range.

Wherein the vertical coordinate range of the adjacent interest point includes the ordinate of the first center point coordinate.

Specifically, the adjacent points of interest are determined from the points of interest to be determined by the first calculated coordinates, the respective second calculated coordinates, and the vertical coordinate range. That is, the server considers the position and the distance relationship between the vertex position and the center point position of the region where the target interest point is located and the vertex position and the center point position of the region where the interest point to be determined is located through the first calculation coordinates and the second calculation coordinates. Further, considering that in practical application, the target point of interest and the determined adjacent point of interest cannot be displaced excessively from top to bottom, so that the relationship between the target point of interest and the adjacent point of interest that are adjacent from top to bottom is avoided, instead of the left and right adjacent required in the scheme, when determining the adjacent point of interest, the ordinate of the first center point coordinate in the first calculated coordinates corresponding to the first region should be considered, and should be within the vertical coordinate range of the adjacent point of interest obtained in the foregoing manner.

For example, further description will be made based on the foregoing examples, if the vertical coordinate range is specifically [ y12, y32]And the first center point coordinates are

When there is->

The point of interest to be determined for the aforementioned second coordinate may be determined as a contiguous point of interest.

In this embodiment, on the basis of considering the position relationship and the distance relationship between each interest point more comprehensively and in a refined manner, the vertical coordinate range can also limit that the target interest point and the determined adjacent interest point cannot be dislocated excessively up and down, so as to avoid the occurrence of the relationship that the target interest point and the determined adjacent interest point are adjacent up and down, ensure that the target interest point and the determined adjacent interest point are interest points in a true left-right adjacent relationship, further ensure the reliability and accuracy of the determined adjacent interest point, and improve the accuracy of updating the position information of the subsequent interest point data.

Since the points of interest having the left-right adjacency relationship with the target point of interest can be determined in the present embodiment, and the left-right adjacency relationship specifically includes the left adjacency relationship and the right adjacency relationship, in determining the adjacency points of interest, it is further necessary to consider the specific adjacency relationship between each point of interest to be determined and the target point of interest, and a method of considering the specific adjacency relationship between the points of interest by the first calculation coordinates and the second calculation coordinates will be described in detail below. It will be appreciated that, in practical applications, the adjacent points of interest may be determined together with the limitation requirements of the vertical coordinate ranges described in the foregoing embodiments, which is not limited herein.

In one embodiment, as shown in fig. 15, determining the neighboring points of interest from the points of interest to be determined by the first calculated coordinates and the second calculated coordinates includes:

in step 1502, a center point distance between the first center point coordinates and each of the second center point coordinates is calculated.

The center point distance is the distance between the center point coordinates (first center point coordinates) of the first area and the center point coordinates (second center point coordinates) of the second area. Specifically, the server calculates through the abscissa and the ordinate in the first center point coordinates and the abscissa and the ordinate in each second center point coordinate, so as to obtain the center point distances respectively corresponding to the first center point coordinates and each second center point coordinate. That is, calculating the abscissa difference value between the abscissa in the first center point coordinate and the abscissa in the second center point coordinate, performing square operation on the abscissa difference value, calculating the ordinate difference value between the ordinate in the first center point coordinate and the ordinate in the second center point coordinate, performing square operation on the ordinate difference value, summing the abscissa difference value after square operation and the ordinate difference value after square operation, and finally performing open root operation on the summed value to obtain the center point distance.

For ease of understanding, the foregoing calculation process is specifically exemplified by equation (1):

wherein d_i_j is the center point distance between the first center point coordinate and the second center point coordinate, i_x_c is the abscissa in the first center point coordinate, j_x_c is the abscissa in the second center point coordinate, i_y_c is the ordinate in the first center point coordinate, and j_y_c is the ordinate in the second center point coordinate.

Step 1504, determining a first edge according to the first calculated coordinates, and determining respective corresponding second edges according to the second calculated coordinates, where the first edge is a first left edge or a first right edge, and the second edge is a second left edge or a second right edge.

The first edge is a first left edge or a first right edge, and the first edge is specifically a leftmost edge line of a region occupied by the first region or a rightmost edge line of a region occupied by the first region, so that the first left edge is specifically a line extending vertically to the abscissa with a first minimum coordinate in the first calculated coordinates as a starting point, and the first right edge is specifically a line extending vertically to the abscissa with a first maximum coordinate in the first calculated coordinates as a starting point. Similarly, the second edge is a second left edge or a second right edge, and the second edge is specifically a leftmost edge line of the area occupied by the second area or a rightmost edge line of the area occupied by the second area, so that the second left edge is specifically a line extending vertically to the abscissa with a second minimum coordinate in the second calculated coordinates as a starting point, and the second right edge is specifically a line extending vertically to the abscissa with a second maximum coordinate in the second calculated coordinates as a starting point.

Specifically, since the first minimum coordinates include the minimum abscissa and the minimum ordinate in the first coordinates, in order to determine the leftmost edge line of the area occupied by the first area, the server may vertically extend to the abscissa by taking the first minimum coordinate in the first calculation coordinates as the starting point to obtain the first left edge, and similarly, since the first maximum coordinates include the maximum abscissa and the maximum ordinate in the first coordinates, in order to determine or the rightmost edge line of the area occupied by the first area, the server may vertically extend to the abscissa by taking the first maximum coordinate in the first calculation coordinates as the starting point to obtain the first right edge.

For ease of understanding, as shown in fig. 16, there is a target point of interest 1602 in the target image 1601, then, it is determined that the smallest circumscribed quadrangle of the region in which the target point of interest 1602 is located is the first region 1603, and the first region 1603 has

vertices

1604, 1605, 1606 and 1607, then, coordinates of the vertices 1604 to 1607 in the target image 1601 can be determined from the first coordinates by the first position information of the target point of interest 1602 and the specific position distributions of the

vertices

1604, 1605, 1606 and 1607, respectively. If the coordinate corresponding to the vertex 1606 is the first minimum coordinate of the first coordinates, and the coordinate corresponding to the vertex 1605 is the first maximum coordinate of the first coordinates, then the coordinate corresponding to the vertex 1606 extends vertically to the abscissa to obtain the first left edge 1608, and the coordinate corresponding to the vertex 1605 extends vertically to the abscissa to obtain the first right edge 1609.

Similarly, for each second coordinate, since the second minimum coordinate includes the minimum abscissa and the minimum ordinate in the second coordinates, in order to determine the leftmost edge line of the area occupied by the second area, the server may obtain the second left edge by vertically extending to the abscissa with the second minimum coordinate in the second calculated coordinates as the starting point, and similarly, since the second maximum coordinate includes the maximum abscissa and the maximum ordinate in the second coordinates, in order to determine or the rightmost edge line of the area occupied by the second area, the server may obtain the second right edge by vertically extending to the abscissa with the second maximum coordinate in the second calculated coordinates as the starting point. The specific vertical extension is similar to that of fig. 16, and is not illustrated and described in detail herein.

In step 1506, a first vertical distance from the first center point coordinates to the first edge and a second vertical distance from each second center point coordinate to each second edge are calculated.

Specifically, the server calculates a first vertical distance from the first center point coordinates to the first edges, and a second vertical distance from each of the second center point coordinates to each of the second edges. Since the first edge is the first left edge or the first right edge, the server specifically calculates the vertical distance between the first center point coordinate and the first left edge as the first vertical distance when the first edge is the first left edge, whereas the server specifically calculates the vertical distance between the first center point coordinate and the first right edge as the first vertical distance when the first edge is the first right edge.

To facilitate understanding, further description is made based on the example of fig. 16, as shown in fig. 17, a target interest point 1702 exists in the target image 1701, and then the smallest circumscribed quadrangle of the region in which the target interest point 1702 is located is determined as a first region 1703, and the first region 1703 exists a center point 1704, and the coordinates of the center point 1704 can be determined. If the first left edge 1705 and the first right edge 1706 are determined as described in the previous embodiment, the distance 1707 from the coordinates of the center point 1704 to the first left edge 1705 may be the first vertical distance, and the distance 1708 from the coordinates of the center point 1704 to the first right edge 1706 may be the first vertical distance.

Similarly, since the second edge is the second left edge or the second right edge, the server specifically calculates the vertical distance between the second center point coordinate and the second left edge as the second vertical distance when the second edge is the second left edge, and otherwise, the server specifically calculates the vertical distance between the second center point coordinate and the second right edge as the second vertical distance when the second edge is the second right edge. The specific calculation of the second vertical distance is similar to that of fig. 17, and is not described in detail. And it is to be understood that the examples in the present embodiment are all for understanding the present scheme, but should not be construed as specific limitations of the present scheme.

In step 1508, an adjacent interest point is determined from the interest points to be determined by the first calculated coordinates, the second calculated coordinates, the center point distance, the first vertical distance, and the second vertical distance.

Specifically, the server determines the adjacent interest point from the interest points to be determined by the first calculated coordinates, the second calculated coordinates, the center point distance, the first vertical distance, and the second vertical distance. The server determines a left-right adjacent relation between each interest point to be determined and the target interest point through the first calculated coordinates, the second calculated coordinates, the first vertical distance and the second vertical distance, namely, whether the interest point to be determined and the target interest point are in a left adjacent relation or a right adjacent relation.

Further, the greater the distance between the center points indicates that the points of interest are farther apart, and the smaller the distance between the center points indicates that the points of interest are closer apart, so that the server selects the point of interest to be determined with the minimum distance between the center point of interest to be determined and the target point of interest as the adjacent point of interest. That is, the server may select, from among the points of interest to be determined having a left adjacency relationship with the target point of interest, the point of interest to be determined having the smallest center point distance as the left adjacency point of interest, and select, from among the points of interest to be determined having a right adjacency relationship with the target point of interest, the point of interest to be determined having the smallest center point distance as the right adjacency point of interest.

In this embodiment, the left-right adjacency relationship between the to-be-determined interest point and the target interest point can be determined through the calculated coordinates and the vertical distance of each interest point, and then, among the to-be-determined interest points respectively having the left adjacency relationship and the right adjacency relationship, the nearest to-be-determined interest point is further selected by considering the center point distance and is respectively used as the left adjacency interest point and the right adjacency interest point, so that not only the correctness of the left adjacency relationship and the right adjacency relationship can be ensured, but also the adjacency interest point can be truly close to the target interest point, and further, the reliability and the accuracy of the determined adjacency interest point can be ensured, and the accuracy of the position information updating of the subsequent interest point data can be improved.

The following will describe in detail how to determine the left neighboring point of interest and the right neighboring point of interest, respectively, and first how to determine the left neighboring point of interest:

in one embodiment, as shown in fig. 18, the first vertical distance is the vertical distance from the first left edge to the first center point coordinate, and the second vertical distance is the vertical distance from the second right edge to the first center point coordinate. Based on this, determining an adjacent interest point from among the interest points to be determined by the first calculated coordinates, the second calculated coordinates, the center point distance, the first vertical distance, and the second vertical distance, includes:

In step 1802, a first candidate left adjacent interest point is determined from the interest points to be determined by the first calculation coordinates and the second calculation coordinates, and the abscissa in the second center point coordinates of the first candidate left adjacent interest point is smaller than the abscissa in the first center point coordinates.

Wherein the abscissa in the second center point coordinate of the first candidate left-neighboring point of interest is smaller than the abscissa in the first center point coordinate. Specifically, the server selects, based on the first calculated coordinates and each second calculated coordinate, an abscissa in the second center point coordinates, and a point of interest to be determined that is smaller than the abscissa in the first center point coordinates as a first candidate left-neighboring point of interest. That is, the first candidate left-neighboring point of interest needs to satisfy: j_x_c < i_x_c, where j_x_c is the abscissa in the second center point coordinate and i_x_c is the abscissa in the first center point coordinate.

In step 1804, a corresponding first overlapping distance is calculated from the first vertical distance and each second vertical distance.

The first overlapping distance is specifically: the values obtained by summing the first vertical distance and the second vertical distance and multiplying the sum with a preset value can be 1.5, 1.2, 1.8 and the like, and the specific preset value needs to be determined according to actual conditions.

Specifically, for each second vertical distance, the server performs summation processing on the first vertical distance and the second vertical distance, and performs product operation on a value obtained by summation and a preset value to obtain a first overlapping distance. For ease of understanding, the foregoing calculation process is specifically exemplified by the formula (2), with the so-called example in which the preset value is 1.5:

1.5×(i_dis_c_l+j_dis_c_r)；(2)

where i_dis_c_l is a first vertical distance and j_dis_c_r is a second vertical distance. The first vertical distance is a vertical distance from the first left edge to the first center point coordinate, and the second vertical distance is a vertical distance from the second right edge to the first center point coordinate.

In step 1806, a second candidate left neighboring interest point is determined from the first candidate left neighboring interest points by the first overlapping distance, the first vertical distances, and the center point distances between the second center point coordinates of the second candidate left neighboring interest point and the first center point coordinates are greater than the first vertical distances and less than the first overlapping distances.

The center point distance between the second center point coordinate of the second candidate left adjacent interest point and the first center point coordinate is larger than the first vertical distance and smaller than the first overlapping distance. Specifically, the server determines a first candidate left-neighboring interest point, of which the center point distance between the second center point coordinate and the first center point coordinate is greater than the first vertical distance and less than the first overlapping distance, as a second candidate left-neighboring interest point.

The so-called example, i.e. the second candidate left-neighboring point of interest needs to satisfy with a preset value of 1.5: i_dis_c_l < dis_i_j <1.5 (i_dis_c_l+j_dis_c_r), wherein d_i_j is the center point distance between the first center point coordinate and the second center point coordinate, i_dis_c_l is the first vertical distance, and 1.5 (i_dis_c_l+j_dis_c_r) is the first overlap distance.

In step 1808, determining a left neighboring interest point from the second candidate left neighboring interest points by using the respective center point distances, where the center point distance between the second center point coordinates of the left neighboring interest point and the first center point coordinates is smaller than the center point distances between the second center point coordinates of the other second candidate left neighboring interest points and the first center point coordinates.

The center point distance between the second center point coordinate of the left adjacent interest point and the first center point coordinate is smaller than the center point distance between the second center point coordinate of the other second candidate left adjacent interest points and the first center point coordinate. Specifically, the server selects, as the left neighboring points of interest, the second candidate left neighboring points of interest having the smallest center point distance (i.e., closest to the point of interest) by the center point distance between each second candidate left neighboring point of interest and the target point of interest.

In this embodiment, the size comparison between the abscissa of the center point coordinates ensures that the selected first candidate left adjacent interest point is located on the right side of the target interest point, that is, the reliability of the right adjacent relationship is ensured. And secondly, limiting the selected second candidate left adjacent interest points by the first overlapping distance, the first vertical distances and the center point distances, wherein the second candidate left adjacent interest points possibly adjacent to but not overlapping with the target interest point can be selected as the left adjacent interest point by the center point distances, so that the correctness of the left adjacent relation can be ensured, the adjacent interest points possibly adjacent to but not overlapping with the target interest point can be ensured, the reliability and the accuracy of the obtained left adjacent interest points are higher, and the accuracy of the position information updating of the follow-up interest point data is improved.

In one embodiment, as shown in fig. 19, the first vertical distance is the vertical distance from the first right edge to the first center point coordinate, and the second vertical distance is the vertical distance from the second left edge to the first center point coordinate. Based on this, determining an adjacent interest point from among the interest points to be determined by the first calculated coordinates, the second calculated coordinates, the center point distance, the first vertical distance, and the second vertical distance, includes:

In step 1902, a first candidate right-adjacent interest point is determined from the interest points to be determined by the first calculated coordinates and the second calculated coordinates, and the abscissa in the second center point coordinates of the first candidate right-adjacent interest point is greater than the abscissa in the first center point coordinates.

Wherein the abscissa in the second center point coordinate of the first candidate right-adjacent interest point is greater than the abscissa in the first center point coordinate. Specifically, the server selects, based on the first calculated coordinates and each second calculated coordinate, an abscissa in the second center point coordinates, and a point of interest to be determined that is larger than the abscissa in the first center point coordinates as a first candidate right-adjacent point of interest. That is, the first candidate right-contiguous point of interest needs to satisfy: j_x_c > i_x_c, wherein j_x_c is the abscissa in the second center point coordinate and i_x_c is the abscissa in the first center point coordinate.

In step 1904, a corresponding second overlapping distance is calculated by the first vertical distance and each second vertical distance.

Wherein, the second overlapping distance specifically is: the values obtained by summing the first vertical distance and the second vertical distance and multiplying the sum with a preset value can be 1.5, 1.2, 1.8 and the like, and the specific preset value needs to be determined according to actual conditions.

Specifically, for each second vertical distance, the server performs summation processing on the first vertical distance and the second vertical distance, and performs product operation on a value obtained by summation and a preset value to obtain a second overlapping distance. For ease of understanding, the foregoing calculation process is specifically exemplified by the formula (3), with a preset value of 1.5 being exemplified:

1.5×(i_dis_c_r+j_dis_c_l)；(3)

where i_dis_c_r is a first vertical distance and j_dis_c_l is a second vertical distance. The first vertical distance is a vertical distance from the first right edge to the first center point coordinate, and the second vertical distance is a vertical distance from the second left edge to the first center point coordinate.

In step 1906, a second candidate right-neighboring interest point is determined from the first candidate right-neighboring interest points by the second overlapping distance, the first vertical distances, and the center point distance between the second center point coordinates of the second candidate right-neighboring interest point and the first center point coordinates is greater than the first vertical distance and less than the second overlapping distance.

The center point distance between the second center point coordinate of the second candidate right adjacent interest point and the first center point coordinate is greater than the first vertical distance and less than the second overlapping distance. Specifically, the server determines a first candidate right-neighboring-interest point, in which a center point distance between the second center point coordinate and the first center point coordinate is greater than the first vertical distance and less than the second overlapping distance, as a second candidate right-neighboring-interest point.

The so-called example, i.e. the second candidate right-adjacent point of interest needs to satisfy with a preset value of 1.5: i_dis_c_r < dis_i_j <1.5× (i_dis_c_r+j_dis_c_l), wherein d_i_j is the center point distance between the first center point coordinate and the second center point coordinate, i_dis_c_r is the first vertical distance, and 1.5× (i_dis_c_r+j_dis_c_l) is the second overlapping distance.

In step 1908, a right neighboring interest point is determined from the second candidate right neighboring interest points by the respective center point distances, and the center point distance between the second center point coordinates and the first center point coordinates of the right neighboring interest point is smaller than the center point distances between the second center point coordinates and the first center point coordinates of the other second candidate right neighboring interest points.

The center point distance between the second center point coordinate of the right adjacent interest point and the first center point coordinate is smaller than the center point distance between the second center point coordinate of the other second candidate right adjacent interest points and the first center point coordinate. Specifically, the server selects the second candidate right adjacent interest point with the smallest center point distance (i.e. the closest center point distance) as the right adjacent interest point through the center point distance between each second candidate right adjacent interest point and the target interest point.

Thus, by way of introduction to the foregoing embodiment, as shown in fig. 20, a left adjacent point of interest 2006 having a left adjacent relationship with the target point of interest 2004, and a right adjacent point of interest 2008 having a right adjacent relationship with the target point of interest 2004 can be determined in the target image 2002.

In this embodiment, the size comparison between the abscissa of the center point coordinates ensures that the selected first candidate right adjacent interest point is located on the right side of the target interest point, that is, the reliability of the right adjacent relationship is ensured. And secondly, limiting the selected second candidate right adjacent interest point by the first overlapping distance, the first vertical distances and the center point distances, wherein the second candidate right adjacent interest point possibly adjacent to but not overlapping with the target interest point, and selecting the nearest second candidate right adjacent interest point as the right adjacent interest point by the center point distance, so that not only can the accuracy of the right adjacent relation be ensured, but also the adjacent interest point possibly adjacent to but not overlapping with the target interest point can be ensured, and the reliability and the accuracy of the obtained right adjacent interest point are higher, thereby improving the accuracy of updating the position information of the follow-up interest point data.

In one embodiment, as shown in fig. 21, after determining the neighboring point of interest adjacent to the target point of interest, the method for updating the location information of the point of interest data further includes:

Step 2102, calculating a position information difference between the first position information and the second position information.

The position information difference value is used for describing the distance between the first position information and the second position information. I.e. the server specifically calculates the distance between the first location information and the second location information and determines the resulting result as the location information difference. The specific calculation manner is similar to that of calculating the center point distance illustrated in the foregoing formula (1), and will not be repeated here.

And the server calculates a position information difference between the first position information and the second position information after determining the adjacent interest point adjacent to the target interest point from the target image through the first position information and before acquiring the first position information confidence coefficient of the target interest point data and the second position information confidence coefficient of the adjacent interest point data.

Based on this, the first position information and the second position information are updated by the first position information confidence and the second position information confidence, including:

in step 2106, if the difference between the position information is greater than the position threshold, updating any one of the first position information and the second position information by the first position information confidence and the second position information confidence.

The present invention has been made in view of the above problems, and an object of the present invention is to update incorrect position information by correct position information with high confidence, so that it is not necessary to update the position information when both the position information are correct. Based on this, the server will determine whether the difference between the location information is greater than the location threshold, i.e. determine whether the distance between the first location information and the second location information exceeds the location threshold, if not, it indicates that the first location information and the second location information are relatively adjacent, it indicates that the determined adjacent interest point has a low probability of location information error, and no subsequent step of location information update is performed.

Otherwise, if the difference between the position information is greater than the position threshold, that is, the distance between the first position information and the second position information exceeds the position threshold, it is indicated that there is an error in the position information between the two adjacent interest points (that is, the target interest point and the adjacent interest point), and at this time, the error correction update needs to be performed on the position information, so that the server updates any one of the first position information and the second position information through the first position information confidence and the second position information confidence in the manner described in the foregoing embodiment.

In this embodiment, by using the difference value between the first location information and the second location information, it is determined whether the first location information and the second location information are wrong, and error correction update is performed on the location information with the error, and error correction update is not performed on the location information with the possibility of not having the error, so that resource consumption for updating the location information is reduced on the basis of ensuring the reliability of updating the location information.

In one embodiment, as shown in fig. 22, updating any one of the first location information and the second location information by the first location information confidence and the second location information confidence includes:

step 2202, if the confidence level of the first position information is trusted and the confidence level of the second position information is not trusted, performing random dithering on the first position information, and replacing the second position information with the first position information after the random dithering.

Specifically, if the first location information confidence level is trusted and the second location information confidence level is untrusted, the server may replace the first location information with the second location information. That is, when the confidence level of the first location information is trusted and the confidence level of the second location information is untrusted, the first location information confidence level describes that the first location information is correct location information, and the second location information describes that the second location information is incorrect location information, so that adjustment of the second location information is required, and because the adjacent interest point is adjacent to the target interest point, the second location information can be replaced by the first location information, that is, the second location information corresponding to the adjacent interest point is replaced by the first location information of the target interest point.

Optionally, since the direct replacement may cause the superposition of the first location information and the second location information, but in actual application, the two interest points may not completely coincide, so as to increase randomness to ensure that the location information of the two different interest points are not completely coincident, in actual application, the two different interest points may be staggered during map display, and in addition, it is considered that the two different interest points are adjacent in actual location. Therefore, if the confidence level of the first position information is trusted and the confidence level of the second position information is untrusted, the first position information is subjected to random dithering, and the second position information is replaced by the first position information subjected to the random dithering. The server performs random dithering on the first position information, and then replaces the second position information with the first position information after the random dithering, namely replaces the second position information corresponding to the adjacent interest point with the first position information after the random dithering.

The random dithering process may be dithering for performing a preset distance on at least one of the abscissa and the ordinate in the first position information, and the preset distance may be 1 meter (m), 2m, 5m, and the like. And as can be seen from the foregoing embodiments, since the neighboring points of interest include at least: the left adjacent interest point and the right adjacent interest point, namely the second position information at least comprises: left adjacent position information corresponding to the left adjacent point of interest data, and right adjacent position information corresponding to the right adjacent point of interest data. Therefore, if the left adjacent position information is not trusted, the random dithering of the abscissa in the first position information may be performed to the left, that is, the abscissa in the first position information is reduced, and if the first position information is (X1, Y1) and the preset distance is 2m, and the left adjacent position information in the second position information is not trusted, the first position information after the random dithering may be (X1-2 m, Y1), and (X1-2 m, y1+2), for easy understanding.

Similarly, if the right adjacent position information is not trusted, then the random dithering of the abscissa in the first position information may be performed to the right, that is, the abscissa in the first position information is increased, and for ease of understanding, if the first position information is (X1, Y1) and the preset distance is 1m, and particularly the right adjacent position information in the second position information is not trusted, then the first position information after the random dithering may be (x1+1, Y1), and (x1+1, Y1-m), etc. It will be appreciated that the foregoing examples are only for understanding the present solution, and that the specific setting of the preset distance and the manner of random jitter need to be flexibly determined based on actual situations, and are not limited herein.

Step 2204, if the first position information confidence is unreliable and the second position information confidence is reliable, performing random dithering on the second position information, and replacing the first position information with the second position information after the random dithering.

Specifically, if the first location information confidence is not trusted and the second location information confidence is trusted, the server may replace the first location information with the second location information. That is, when the second position information confidence is trusted and the first position information confidence is not trusted, the second position information confidence is described as the correct position information, and the first position information confidence is described as the wrong position information, so that the first position information needs to be adjusted, and the adjacent interest point is adjacent to the target interest point, so that the first position information can be replaced by the second position information, that is, the first position information corresponding to the adjacent interest point is replaced by the second position information of the target interest point.

Optionally, since the direct replacement may cause the second location information to coincide with the first location information, but in actual application, the two interest points may not coincide completely, so as to increase randomness to ensure that the location information of the two different interest points are not coincident completely, in actual application, the two different interest points may be staggered during map display, and in addition, it is considered that the two different interest points are adjacent in actual location. Therefore, if the second position information confidence is trusted and the first position information confidence is untrusted, the second position information is subjected to random dithering, and the first position information is replaced by the second position information subjected to random dithering. The server performs random dithering on the second position information, and then replaces the first position information with the second position information after the random dithering, namely replaces the first position information corresponding to the adjacent interest point with the second position information after the random dithering. The specific random dithering process is similar to the previous embodiment, and will not be repeated here.

It can be understood that in practical application, there may be a case that the confidence level of the first location information is not trusted and the confidence level of the second location information is also not trusted, which indicates that there is no trusted location information, and the server does not process the location information at this time, and at this time, the verification and update of the location information may be performed by triggering a manual audit. Similarly, if the first position information confidence coefficient is reliable and the second position information confidence coefficient is also reliable, the method does not accord with the actual situation, and therefore the position information is not processed, and at the moment, the position information can be checked and updated in a mode of triggering manual verification. The manner in which the manual audit and associated location information are updated is not limited herein.

In this embodiment, the reliability of the updated position information is ensured by replacing the unreliable position information with the position information confidence level being the reliable position information, and further, the fact that the target interest point and the adjacent interest point are adjacent but not overlapped in the actual position is considered, so that the randomness and the flexibility can be improved by performing the replacement operation after the position information is randomly dithered, and the reliability of the position information update is further ensured.

Based on the foregoing detailed description of the embodiments, a complete flow of the method for updating the location information of the point of interest data in the embodiments of the present application will be described, and in one embodiment, as shown in fig. 23, a method for updating the location information of the point of interest data is provided, and the method is described by taking the server in fig. 1 as an example, where it is understood that the method may also be applied to a terminal, and may also be applied to a system including a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the steps of:

step 2301, acquiring a plurality of acquired images obtained by acquiring images of each region on the map, and determining a target object type of the target interest point.

The target interest points are POIs of the position information to be updated, and the target interest points are POIs of target object types, wherein the target object types can be shop signboards, buildings, public transportation sites and the like, and the target object types are determined according to actual application requirements. The target interest point data of the target interest point specifically includes first position information corresponding to the target interest point, where the position information may be longitude and latitude information or other coordinate system information capable of uniquely indicating the position of the interest point, and the attribute information may also include an object type, address information, time information, and the like.

Specifically, the terminal performs image acquisition on each area on the map through the image acquisition device to obtain a plurality of acquired images, and the terminal can send the acquired plurality of acquired images to the server in real time in the image acquisition process, so that the server acquires the plurality of acquired images. Or after the terminal completes image acquisition, transmitting the acquired plurality of acquired images to a server, and acquiring the plurality of acquired images by the server.

In step 2302, a target object type is extracted for each of the acquired images based on the target object type, and a target image is determined from each of the acquired images.

The target image may be one image obtained by performing image acquisition on a map road, or may be a plurality of images obtained by performing image acquisition on a map road, that is, the target image may be one image or a plurality of images, which is not limited herein.

Specifically, when the server needs to update the position information of the target interest point, for example, when the server needs to update the position information of a certain shop sign, update the position information of a certain building or update the position information of a certain public transportation site, the server determines the target object type of the target interest point of the position information to be updated, and then extracts the target object type of each acquired image based on the target object type. That is, the server detects object types of all the points of interest in the acquired image to extract a candidate acquired image including the target object type, then determines a candidate acquired image including the target point of interest from among the candidate acquired images, and determines the candidate acquired image including the target point of interest as the target image.

And 2303, performing object recognition on the target image, and determining the to-be-determined interest point in the target image, wherein the type of the to-be-determined interest point is consistent with that of the target interest point.

Specifically, the server performs object recognition on the target image, determines an interest point to be determined, which is consistent with the object type of the target interest point, in the target image, where the interest point to be determined may be one interest point or a plurality of interest points to be determined, and is not limited herein.

In step 2304, a first region of the target point of interest in the target image is identified, and a first coordinate is determined from vertices of the first region and the first location information.

The first area is a quadrilateral area, and the first area is specifically a minimum circumscribed quadrilateral of the target interest point, where the circumscribed quadrilateral may be a rectangle or a square, and the specific location is not limited.

Specifically, the server identifies a first region of the target point of interest in the target image, that is, the server determines a minimum circumscribed quadrangle of the region in which the target point of interest is located, and determines the minimum circumscribed quadrangle as the first region. Further, the server determines coordinates of four vertexes of the first area in the target image according to the positions of the vertexes of the first area and first position information of the target interest point, so as to obtain first coordinates.

In step 2305, second regions corresponding to the points of interest to be determined in the target image are identified, and second coordinates are determined by the vertices of the second regions and the third position information.

Specifically, the server identifies second areas corresponding to the points of interest to be determined in the target image respectively, that is, the server determines the minimum circumscribed quadrangle of the area where the points of interest to be determined are located, and determines the minimum circumscribed quadrangle as the second area corresponding to the points of interest to be determined. Further, the server determines coordinates of four vertexes of the second area in the target image according to the positions of the vertexes of the second area and second position information of the interest point to be determined, so as to obtain second coordinates.

In step 2306, first calculated coordinates are determined from the first coordinates, and second calculated coordinates, respectively, are determined from the second coordinates.

Wherein the first calculated coordinates include at least: the system comprises a first maximum coordinate, a first minimum coordinate and a first center point coordinate, wherein the first maximum coordinate comprises a maximum abscissa and a maximum ordinate in the first coordinate, and the first minimum coordinate comprises a minimum abscissa and a minimum ordinate in the first coordinate. Second, the second calculated coordinates include at least: the second maximum coordinates comprise a maximum abscissa and a maximum ordinate in the second coordinates, and the second minimum coordinates comprise a minimum abscissa and a minimum ordinate in the second coordinates.

Further, the server determines second calculation coordinates corresponding to the second areas through the second coordinates of the second areas. That is, for each second region, the server determines an average of the abscissas of the four vertices of the second region as the abscissas of the second center point coordinates, and determines an average of the ordinates of the four vertices of the second region as the ordinates of the second center point coordinates to obtain the second center point coordinates. And then, the server specifically constructs a second maximum coordinate through coordinates corresponding to the four vertexes in the second coordinate, the maximum abscissa among the four vertexes, and the maximum ordinate among the four vertexes in the second coordinate. Similarly, the server may also construct the second minimum coordinate from the minimum abscissa of the four vertices and the minimum ordinate of the four vertices in the second coordinate. The specific calculation manner of the second calculation coordinates is similar to the determination manner of the first calculation coordinates, and will not be described herein.

In step 2307, a respective corresponding vertical coordinate range is determined by each second calculated coordinate.

In step 2308, a center point distance between the first center point coordinates and each of the second center point coordinates is calculated.

The center point distance is the distance between the center point coordinates (first center point coordinates) of the first area and the center point coordinates (second center point coordinates) of the second area. Specifically, the server calculates through the abscissa and the ordinate in the first center point coordinates and the abscissa and the ordinate in each second center point coordinate, so as to obtain the center point distances respectively corresponding to the first center point coordinates and each second center point coordinate.

In step 2309, a first edge is determined according to the first calculated coordinates, and a respective second edge is determined according to each second calculated coordinate.

The first edge is a first left edge or a first right edge, and the first edge is specifically a leftmost edge line of a region occupied by the first region or a rightmost edge line of a region occupied by the first region. Specifically, since the first minimum coordinates include the minimum abscissa and the minimum ordinate in the first coordinates, in order to determine the leftmost edge line of the area occupied by the first area, the server may vertically extend to the abscissa by taking the first minimum coordinate in the first calculation coordinates as the starting point to obtain the first left edge, and similarly, since the first maximum coordinates include the maximum abscissa and the maximum ordinate in the first coordinates, in order to determine or the rightmost edge line of the area occupied by the first area, the server may vertically extend to the abscissa by taking the first maximum coordinate in the first calculation coordinates as the starting point to obtain the first right edge.

At step 2310, a first vertical distance from the first center point coordinates to the first edge and a second vertical distance from each of the second center point coordinates to each of the second edges are calculated.

In step 2311, the neighboring points of interest are determined from the points of interest to be determined by the first calculated coordinates, the second calculated coordinates, the vertical coordinate ranges, the center point distance, the first vertical distance, and the second vertical distances.

Specifically, the server determines the neighboring interest points from the interest points to be determined by the first calculated coordinates, the second calculated coordinates, the vertical coordinate range, the center point distance, the first vertical distance, and the second vertical distance in a similar manner as described in the foregoing embodiment, and details thereof will not be repeated here.

At step 2312, a position information difference between the first position information and the second position information is calculated.

Step 2313, obtain the first location information confidence of the target point of interest data and the second location information confidence of the neighboring point of interest data.

In step 2314, if the position information difference is greater than the position threshold, the first position information confidence level is trusted and the second position information confidence level is untrusted, performing random dithering on the first position information, and replacing the second position information with the first position information after the random dithering.

The present invention has been made in view of the above problems, and an object of the present invention is to update incorrect position information by correct position information with high confidence, so that it is not necessary to update the position information when both the position information are correct. Based on the above, the server determines whether the position information difference is greater than the position threshold, if the position information difference is greater than the position threshold, the first position information confidence is trusted and the second position information confidence is untrusted, performs random dithering on the first position information, and replaces the second position information with the first position information after the random dithering.

In step 2315, if the position information difference is greater than the position threshold, the first position information confidence is unreliable, and the second position information confidence is trusted, performing random dithering on the second position information, and replacing the first position information with the second position information after the random dithering.

Similarly, if the position information difference is greater than the position threshold, the first position information confidence is trusted and the second position information confidence is untrusted, performing random dithering on the first position information, and replacing the second position information with the first position information after the random dithering.

It should be understood that the specific implementation of steps 2301 to 2315 is similar to the previous embodiments, and will not be repeated here.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a position information updating device of the interest point data for realizing the position information updating method of the interest point data. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the location information updating device for one or more point of interest data provided below may refer to the limitation of the location information updating method for point of interest data hereinabove, and will not be repeated herein.

In one embodiment, as shown in fig. 24, there is provided a location information updating apparatus of point of interest data, including: an image acquisition module 2402, an adjacent point of interest determination module 2404, a confidence acquisition module 2406, and a location information update module 2408, wherein:

an image acquisition module 2402, configured to acquire a target image including a target point of interest, where target point of interest data of the target point of interest has corresponding first location information;

an adjacent interest point determining module 2404, configured to determine, from the target image, an adjacent interest point adjacent to the target interest point through the first location information, where the adjacent interest point of the adjacent interest point has corresponding second location information;

The confidence coefficient obtaining module 2406 is configured to obtain a first location information confidence coefficient of the target point of interest data, which is a parameter for evaluating that the first location information is correct location information, and a second location information confidence coefficient of the neighboring point of interest data, which is a parameter for evaluating that the second location information is correct location information;

the location information updating module 2408 is configured to update any one of the first location information and the second location information according to the first location information confidence and the second location information confidence.

In one embodiment, the image acquisition module 2402 is specifically configured to acquire a plurality of acquired images obtained by performing image acquisition on each region on the map, and determine a target object type of the target interest point; extracting the target object type of each acquired image based on the target object type, and determining a target image from each acquired image;

the adjacent interest point determining module 2404 is specifically configured to determine, from the target image, an adjacent interest point adjacent to the target interest point and having a consistent object type through the first location information and the target object type.

In one embodiment, the target image includes a plurality of target sub-images, each of which includes a target point of interest; the first location information includes a plurality of first sub-location information;

The adjacent interest point determining module 2404 is specifically configured to determine, from each corresponding target sub-image, an adjacent sub-interest point adjacent to the target interest point through each first sub-position information; from the contiguous sub-points of interest of each target sub-image, contiguous points of interest are determined.

In one embodiment, the adjacent interest point determining module 2404 is specifically configured to perform object recognition on the target image, determine a to-be-determined interest point in the target image, where the to-be-determined interest point is consistent with an object type of the target interest point, and the to-be-determined interest point has corresponding third location information; and determining adjacent interest points from the interest points to be determined through the first position information and the third position information.

In one embodiment, the adjacent interest point determining module 2404 is specifically configured to identify a first region of the target interest point in the target image, and determine a first coordinate according to a vertex of the first region and the first position information, where the first region is a quadrilateral region; identifying second areas corresponding to the interest points to be judged in the target image respectively, and determining second coordinates through vertexes of the second areas and third position information respectively, wherein the second areas are quadrilateral areas; and determining adjacent interest points from the interest points to be determined through the first coordinates and the second coordinates.

In one embodiment, the adjacent interest point determining module 2404 is specifically configured to determine a first calculated coordinate by using a first coordinate, where the first calculated coordinate includes at least: the system comprises a first maximum coordinate, a first minimum coordinate and a first center point coordinate, wherein the first maximum coordinate comprises a maximum abscissa and a maximum ordinate in the first coordinate, and the first minimum coordinate comprises a minimum abscissa and a minimum ordinate in the first coordinate; determining second calculation coordinates corresponding to the second coordinates respectively, wherein the second calculation coordinates at least comprise: the system comprises a first maximum coordinate, a first minimum coordinate and a first central point coordinate, wherein the first maximum coordinate comprises a first horizontal coordinate and a first vertical coordinate in the first coordinate, and the first minimum coordinate comprises a second horizontal coordinate and a second vertical coordinate in the second coordinate; and determining adjacent interest points from the interest points to be determined through the first calculated coordinates and the second calculated coordinates.

In one embodiment, the adjacent interest point determining module 2404 is specifically configured to determine, by using each second calculation coordinate, a vertical coordinate range corresponding to each second calculation coordinate, where the vertical coordinate range is formed by a minimum ordinate in the second calculation coordinate and a maximum ordinate in the second calculation coordinate; determining adjacent interest points from the interest points to be determined through the first calculated coordinates, the second calculated coordinates and the vertical coordinate range; wherein the vertical coordinate range of the adjacent interest point includes the ordinate of the first center point coordinate.

In one embodiment, the neighboring interest point determining module 2404 is specifically configured to calculate a center point distance between the first center point coordinate and each of the second center point coordinates; determining a first edge according to the first calculation coordinates, and determining respective corresponding second edges according to the second calculation coordinates, wherein the first edge is a first left edge or a first right edge, and the second edge is a second left edge or a second right edge; calculating a first vertical distance from the first center point coordinates to the first edges and a second vertical distance from each second center point coordinate to each second edge; and determining adjacent interest points from the interest points to be determined through the first calculated coordinates, the second calculated coordinates, the center point distance, the first vertical distance and the second vertical distance.

In one embodiment, the adjacent interest point determining module 2404 is specifically configured to determine, from the interest points to be determined, a first candidate left adjacent interest point by using the first calculated coordinates and the second calculated coordinates, where an abscissa in a second center point coordinate of the first candidate left adjacent interest point is smaller than an abscissa in the first center point coordinate; respectively calculating a corresponding first overlapping distance through a first vertical distance and each second vertical distance, wherein the first vertical distance is the vertical distance from the first left edge to the first center point coordinate, and the second vertical distance is the vertical distance from the second right edge to the first center point coordinate; determining a second candidate left adjacent interest point from the first candidate left adjacent interest points through the first overlapping distance, the first vertical distances and the center point distances, wherein the center point distance between the second center point coordinates of the second candidate left adjacent interest point and the first center point coordinates is larger than the first vertical distance and smaller than the first overlapping distance; and determining a left adjacent interest point from the second candidate left adjacent interest points through the center point distances, wherein the center point distance between the second center point coordinates and the first center point coordinates of the left adjacent interest points is smaller than the center point distance between the second center point coordinates and the first center point coordinates of other second candidate left adjacent interest points.

In one embodiment, the adjacent interest point determining module 2404 is specifically configured to determine, from the interest points to be determined, a first candidate right adjacent interest point by using the first calculated coordinates and the second calculated coordinates, where an abscissa in a second center point coordinate of the first candidate right adjacent interest point is greater than an abscissa in the first center point coordinate; respectively calculating a corresponding second overlapping distance through a first vertical distance and each second vertical distance, wherein the first vertical distance is the vertical distance from the first right edge to the first center point coordinate, and the second vertical distance is the vertical distance from the second left edge to the first center point coordinate; determining a second candidate right adjacent interest point from the first candidate right adjacent interest points through the second overlapping distance, the first vertical distances and the center point distances, wherein the center point distance between the second center point coordinates of the second candidate right adjacent interest point and the first center point coordinates is larger than the first vertical distance and smaller than the second overlapping distance; and determining a right adjacent interest point from the second candidate right adjacent interest points through the center point distances, wherein the center point distance between the second center point coordinates and the first center point coordinates of the right adjacent interest points is smaller than the center point distance between the second center point coordinates and the first center point coordinates of other second candidate right adjacent interest points.

In one embodiment, as shown in fig. 26, the location information updating device of the point of interest data further includes a location information difference calculating module 2502;

a positional information difference calculation module 2502 for calculating a positional information difference between the first positional information and the second positional information;

the location information updating module 2408 is specifically configured to update any one of the first location information and the second location information by the first location information confidence and the second location information confidence if the location information difference is greater than the location threshold.

In one embodiment, the location information updating module 2408 is specifically configured to, if the first location information confidence is trusted and the second location information confidence is untrusted, perform a random dithering process on the first location information, and replace the second location information with the first location information after the random dithering process.

In one embodiment, the location information updating module 2408 is specifically configured to, if the confidence level of the first location information is unreliable and the confidence level of the second location information is trusted, perform random dithering on the second location information, and replace the first location information with the second location information after the random dithering.

The modules in the location information updating device of the point of interest data may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a server or a terminal, and in this embodiment, the computer device is taken as a server for illustration, and the internal structure thereof may be shown in fig. 26. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing related data such as images, point of interest data and the like. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a method for updating location information of point of interest data.

It will be appreciated by those skilled in the art that the structure shown in fig. 26 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application is applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.

In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical feature information of the above embodiments may be arbitrarily combined, and for brevity of description, all possible combinations of the technical feature information in the above embodiments are not described, however, as long as there is no contradiction between the combinations of the technical feature information, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. A method for updating location information of point of interest data, comprising:

Acquiring first position information confidence coefficient of the target interest point data and second position information confidence coefficient of the adjacent interest point data, wherein the first position information confidence coefficient is a parameter for evaluating that the first position information is correct position information, and the second position information confidence coefficient is a parameter for evaluating that the second position information is correct position information;

updating any one of the first location information and the second location information by the first location information confidence and the second location information confidence.

2. The method of claim 1, wherein the acquiring the target image including the target point of interest comprises:

acquiring a plurality of acquired images obtained by image acquisition of each region on a map, and determining the type of a target object of the target interest point;

performing target object type extraction on each acquired image based on the target object type, and determining the target image from each acquired image;

the determining, from the target image, an adjacent interest point adjacent to the target interest point through the first position information includes:

and determining the adjacent interest points adjacent to the target interest point and consistent in object type from the target image through the first position information and the target object type.

3. The method of claim 1, wherein the target image comprises a plurality of target sub-images, each of the target sub-images comprising the target point of interest; the first location information includes a plurality of first sub-location information;

the determining, from the target image, the contiguous interest adjacent to the target interest point through the first location information includes:

determining adjacent sub-interest points adjacent to the target interest point from the corresponding target sub-images through the first sub-position information;

and determining the adjacent interest points from the adjacent sub interest points of each target sub image.

4. The method of claim 1, wherein the determining, from the target image, the neighboring point of interest adjacent to the target point of interest by the first location information comprises:

performing object recognition on the target image, and determining an interest point to be judged, which is consistent with the object type of the target interest point, in the target image, wherein the interest point to be judged has corresponding third position information;

and determining the adjacent interest points from the interest points to be determined through the first position information and the third position information.

5. The method of claim 4, wherein the determining the neighboring points of interest from the points of interest to be determined by the first location information and the third location information comprises:

identifying a first area of the target interest point in the target image, and determining a first coordinate through the vertex of the first area and the first position information, wherein the first area is a quadrilateral area;

identifying second areas corresponding to the interest points to be determined in the target image respectively, and determining second coordinates through vertexes of the second areas and the third position information respectively, wherein the second areas are quadrilateral areas;

and determining the adjacent interest points from the interest points to be determined through the first coordinates and the second coordinates.

6. The method of claim 5, wherein the determining the contiguous interest point from the interest points to be determined by the first coordinates and the second coordinates comprises:

determining a first calculated coordinate by the first coordinate, wherein the first calculated coordinate at least comprises: a first maximum coordinate, a first minimum coordinate and a first center point coordinate, wherein the first maximum coordinate comprises a maximum abscissa and a maximum ordinate in the first coordinate, and the first minimum coordinate comprises a minimum abscissa and a minimum ordinate in the first coordinate;

Determining second calculation coordinates corresponding to the second coordinates respectively, wherein the second calculation coordinates at least comprise: a second maximum coordinate, a second minimum coordinate and a second center point coordinate, wherein the second maximum coordinate comprises a maximum abscissa and a maximum ordinate in the second coordinate, and the second minimum coordinate comprises a minimum abscissa and a minimum ordinate in the second coordinate;

and determining the adjacent interest points from the interest points to be determined through the first calculated coordinates and the second calculated coordinates.

7. The method of claim 6, wherein the determining the contiguous points of interest from each of the points of interest to be determined by the first calculated coordinates and each of the second calculated coordinates comprises:

determining a vertical coordinate range corresponding to each second calculation coordinate, wherein the vertical coordinate range is composed of a minimum ordinate of the second calculation coordinates and a maximum ordinate of the second calculation coordinates;

determining the adjacent interest points from the interest points to be determined through the first calculated coordinates, the second calculated coordinates and the vertical coordinate range;

8. The method of claim 6, wherein the determining the contiguous points of interest from each of the points of interest to be determined by the first calculated coordinates and each of the second calculated coordinates comprises:

calculating a center point distance between the first center point coordinates and each of the second center point coordinates;

determining a first edge according to the first calculation coordinates, and determining a second edge corresponding to each second calculation coordinate, wherein the first edge is a first left edge or a first right edge, and the second edge is a second left edge or a second right edge;

calculating a first vertical distance from the first center point coordinates to the first edge and a second vertical distance from each second center point coordinate to each second edge;

and determining the adjacent interest points from the interest points to be determined through the first calculated coordinates, the second calculated coordinates, the center point distance, the first vertical distance and the second vertical distance.

9. The method of claim 8, wherein the determining the contiguous interest point from the interest points to be determined by the first calculated coordinates, the second calculated coordinates, the center point distance, the first vertical distance, and the second vertical distance comprises:

Determining a first candidate left adjacent interest point from the interest points to be determined through the first calculation coordinates and the second calculation coordinates, wherein the abscissa of the second center point coordinates of the first candidate left adjacent interest point is smaller than the abscissa of the first center point coordinates;

respectively calculating a corresponding first overlapping distance through the first vertical distance and each second vertical distance, wherein the first vertical distance is the vertical distance from the first left edge to the first center point coordinate, and the second vertical distance is the vertical distance from the second right edge to the first center point coordinate;

determining a second candidate left-adjacent interest point from the first candidate left-adjacent interest points through the first overlapping distance, the first vertical distances and the center point distances, wherein the center point distance between the second center point coordinates of the second candidate left-adjacent interest point and the first center point coordinates is larger than the first vertical distance and smaller than the first overlapping distance;

and determining the left adjacent interest point from the second candidate left adjacent interest points through the center point distances, wherein the center point distance between the second center point coordinates of the left adjacent interest points and the first center point coordinates is smaller than the center point distance between the second center point coordinates of other second candidate left adjacent interest points and the first center point coordinates.

10. The method of claim 8, wherein the determining the contiguous interest point from the interest points to be determined by the first calculated coordinates, the second calculated coordinates, the center point distance, the first vertical distance, and the second vertical distance comprises:

determining a first candidate right adjacent interest point from the interest points to be determined through the first calculation coordinates and the second calculation coordinates, wherein the abscissa of the second center point coordinates of the first candidate right adjacent interest point is larger than the abscissa of the first center point coordinates;

respectively calculating corresponding second overlapping distances through the first vertical distances and the second vertical distances, wherein the first vertical distances are the vertical distances from the first right edge to the first center point coordinates, and the second vertical distances are the vertical distances from the second left edge to the first center point coordinates;

determining a second candidate right-adjacent interest point from the first candidate right-adjacent interest points through the second overlapping distance, the first vertical distances and the center point distances, wherein the center point distance between the second center point coordinates of the second candidate right-adjacent interest point and the first center point coordinates is larger than the first vertical distance and smaller than the second overlapping distance;

And determining the right adjacent interest point from the second candidate right adjacent interest points through the center point distances, wherein the center point distance between the second center point coordinates of the right adjacent interest points and the first center point coordinates is smaller than the center point distance between the second center point coordinates of other second candidate right adjacent interest points and the first center point coordinates.

11. The method according to claim 1, wherein the method further comprises:

calculating a position information difference between the first position information and the second position information;

the updating the first location information and the second location information by the first location information confidence and the second location information confidence includes:

and if the position information difference value is larger than a position threshold value, updating any one of the first position information and the second position information through the first position information confidence coefficient and the second position information confidence coefficient.

12. The method of claim 1 or 11, wherein updating any of the first location information and the second location information with the first location information confidence and the second location information confidence comprises:

If the first position information confidence coefficient is credible and the second position information confidence coefficient is not credible, carrying out random dithering on the first position information, and replacing the second position information with the first position information subjected to the random dithering;

and if the first position information confidence coefficient is unreliable and the second position information confidence coefficient is reliable, carrying out random dithering on the second position information, and replacing the first position information with the second position information subjected to the random dithering.

13. A location information updating apparatus of point of interest data, the apparatus comprising:

the image acquisition module is used for acquiring a target image comprising a target interest point, wherein target interest point data of the target interest point have corresponding first position information;

an adjacent interest point determining module, configured to determine, from the target image through the first location information, an adjacent interest point adjacent to the target interest point, where adjacent interest point data of the adjacent interest point has corresponding second location information;

the confidence coefficient acquisition module is used for acquiring first position information confidence coefficient of the target interest point data and second position information confidence coefficient of the adjacent interest point data, wherein the first position information confidence coefficient is a parameter for evaluating that the first position information is correct position information, and the second position information confidence coefficient is a parameter for evaluating that the second position information is correct position information;

14. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 12 when the computer program is executed.

15. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 12.