CN117112587A

CN117112587A - Map data processing method, device, medium and equipment

Info

Publication number: CN117112587A
Application number: CN202311352914.XA
Authority: CN
Inventors: 李东旗; 卢俊之; 陈叶
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2023-10-19
Filing date: 2023-10-19
Publication date: 2023-11-24
Anticipated expiration: 2043-10-19
Also published as: CN117112587B

Abstract

The application discloses a map data processing method, a device, a medium and equipment, relating to the field of maps, wherein the method comprises the following steps: obtaining map data to be detected of a map, wherein the map data to be detected comprises interest point data, road data and background data; dividing the map according to the road data to obtain at least one closed area; determining feature information corresponding to each closed region in at least one closed region according to the interest point data, the road data and the background data; according to the characteristic information corresponding to each closed region, predicting the distribution accuracy of interest points to obtain a prediction index value corresponding to each closed region; and updating the interest point data in the map data to be detected according to the prediction index value corresponding to each closed region to obtain target map data of the map. The method and the device can efficiently and accurately detect the interest points with unreasonable distribution, and improve the accuracy of map data.

Description

Map data processing method, device, medium and equipment

Technical Field

The present application relates to the field of maps, and in particular, to a map data processing method, apparatus, medium, and device.

Background

With the development of internet technology, services (Location Based Services, LBS) based on geographical locations are increasingly abundant and diverse, such as navigation services, local living services, etc. Accordingly, higher demands are also put on the accuracy of the map data. In the process of collecting, processing, drawing, updating and the like, data errors are possibly generated in map data, so that the conditions of unreasonable distribution of interest points (Point of Interest, POIs) and inaccurate interest point data are caused, and the accuracy degree of the interest point data directly influences the quality of the map data and the effect of service based on geographic positions.

Disclosure of Invention

In order to improve the accuracy of map data, the application provides a map data processing method, a map data processing device, a map data processing medium and map data processing equipment. The technical scheme is as follows:

in a first aspect, the present application provides a map data processing method, the method comprising:

obtaining map data to be detected of a map, wherein the map data to be detected comprises interest point data, road data and background data;

dividing the map according to the road data to obtain at least one closed area;

determining feature information corresponding to each closed region in the at least one closed region according to the interest point data, the road data and the background data, wherein the feature information indicates interest point distribution feature information, road line distribution feature information and background surface distribution feature information of the corresponding closed region;

According to the characteristic information corresponding to each closed region, predicting the distribution accuracy of interest points to obtain a prediction index value corresponding to each closed region, wherein the prediction index value represents the distribution accuracy of the interest points in the corresponding closed region;

and updating the interest point data in the map data to be detected according to the prediction index value corresponding to each closed area to obtain target map data of the map.

Optionally, the dividing the map according to the road data to obtain at least one closed area includes:

acquiring regional management hierarchy data;

dividing the map according to the region management level data to obtain at least one management region;

and dividing each management area in the at least one management area according to the road data to obtain at least one closed area.

Optionally, the dividing each management area in the at least one management area according to the road data to obtain at least one closed area includes:

determining a road network diagram corresponding to each management area according to the road data, wherein the road network diagram is a diagram taking intersections as nodes and roads between the intersections as edges;

Performing depth-first search processing on the road network graph corresponding to each management area, and determining at least one loop in the road network graph corresponding to each management area, wherein each loop in the at least one loop is a path of which the starting point and the end point are the same target node in the road network graph, and the target node is any node in the road network graph;

dividing each management area according to at least one loop in the road network diagram corresponding to each management area to obtain at least one closed area; the at least one enclosed region does not overlap each other.

Optionally, the determining, according to the point of interest data, the road data and the background data, feature information corresponding to each of the at least one closed area includes:

generating map element index information according to the interest point data, the road data and the background data;

determining the region interest point data corresponding to each closed region, the region road data corresponding to each closed region and the region background data corresponding to each closed region according to the map element index information;

And calculating to obtain the characteristic information corresponding to each closed region according to the region interest point data corresponding to each closed region, the region road data corresponding to each closed region and the region background data corresponding to each closed region.

Optionally, the calculating to obtain the feature information corresponding to each closed area according to the area interest point data corresponding to each closed area, the area road data corresponding to each closed area, and the area background data corresponding to each closed area includes:

calculating and obtaining interest point distribution characteristic information corresponding to each closed region according to region interest point data corresponding to each closed region, wherein the interest point distribution characteristic information comprises the number and types of interest points in the corresponding closed region;

according to the regional road data corresponding to each closed region, road line distribution characteristic information corresponding to each closed region is calculated, wherein the road line distribution characteristic information comprises the names, the grades and the number of lanes of roads in the corresponding closed region;

according to the regional background data corresponding to each closed region, calculating and obtaining background surface distribution characteristic information corresponding to each closed region, wherein the background surface distribution characteristic information comprises the area and area occupation ratio of the background in the corresponding closed period region;

And determining the feature information corresponding to each closed region according to the interest point distribution feature information corresponding to each closed region, the road line distribution feature information corresponding to each closed region and the background surface distribution feature information corresponding to each closed region.

Optionally, the updating the interest point data in the map data to be detected according to the prediction index value corresponding to each closed area to obtain target map data of the map includes:

acquiring a preset index threshold;

determining at least one target closed region according to the prediction index value corresponding to each closed region and the preset index threshold value; the predictive index value corresponding to each target closed region in the at least one target closed region is lower than the preset index threshold value;

determining regional interest point data corresponding to the at least one target closed region according to the interest point data;

and deleting the region interest point data corresponding to the at least one target closed region from the map data to be detected to obtain the target map data.

Optionally, the predicting processing for the accuracy of the distribution of the points of interest according to the feature information corresponding to each closed area, to obtain a predicted index value corresponding to each closed area, includes:

Inputting the feature information corresponding to each closed region into an interest point distribution prediction model, and performing feature characterization processing to obtain feature characterization data corresponding to each closed region;

performing regression prediction processing aiming at the distribution accuracy of the interest points according to the characteristic characterization data corresponding to each closed region to obtain a prediction index value corresponding to each closed region; the interest point distribution prediction model is a regression model trained based on a gradient lifting decision tree algorithm.

Optionally, the method further comprises:

acquiring sample map data of a sample map, wherein the sample map data comprises sample interest point data, sample road data and sample background data;

dividing the sample map according to the sample road data to obtain at least one sample closed area;

determining sample feature information corresponding to each sample sealing area in the at least one sample sealing area according to the sample interest point data, the sample road data and the sample background data, wherein the sample feature information indicates sample interest point distribution feature information, sample road route distribution feature information and sample background surface distribution feature information of the corresponding sample sealing area;

Acquiring label data corresponding to each sample sealing area, wherein the label data represents the accuracy of interest point distribution in the corresponding sample sealing area;

training a preset machine learning model based on sample characteristic information corresponding to each sample sealing area, label data corresponding to each sample sealing area and the gradient lifting decision tree algorithm to obtain the interest point distribution prediction model.

In a second aspect, the present application provides a map data processing apparatus, the apparatus comprising:

the data acquisition module is used for acquiring map data to be detected of a map, wherein the map data to be detected comprises interest point data, road data and background data;

the area dividing module is used for dividing the map according to the road data to obtain at least one closed area;

the feature determining module is used for determining feature information corresponding to each closed region in the at least one closed region according to the interest point data, the road data and the background data, wherein the feature information indicates interest point distribution feature information, road line distribution feature information and background surface distribution feature information of the corresponding closed region;

The prediction module is used for performing prediction processing on the interest point distribution accuracy according to the characteristic information corresponding to each closed region to obtain a prediction index value corresponding to each closed region, wherein the prediction index value represents the accuracy of the interest point distribution in the corresponding closed region;

and the data updating module is used for updating the interest point data in the map data to be detected according to the prediction index value corresponding to each closed area to obtain target map data of the map.

In a third aspect, the present application provides a computer readable storage medium having stored therein at least one instruction or at least one program loaded and executed by a processor to implement a map data processing method as described in the first aspect.

In a fourth aspect, the present application provides a computer device comprising a processor and a memory having stored therein at least one instruction or at least one program loaded and executed by the processor to implement a map data processing method as described in the first aspect.

In a fifth aspect, the present application provides a computer program product comprising computer instructions which, when executed by a processor, implement a map data processing method as described in the first aspect.

The map data processing method, the map data processing device, the map data processing medium and the map data processing equipment provided by the application have the following technical effects:

the scheme provided by the application utilizes the road data in the map data to be detected of the map, divides the map into at least one closed area, and determines the characteristic information corresponding to each closed area according to the interest point data, the road data and the background data in the map data to be detected, wherein the characteristic information can indicate the interest point distribution characteristic information, the road line distribution characteristic information and the background surface distribution characteristic information corresponding to the corresponding closed areas, namely, the distribution characteristics in the closed areas are described from three dimensions of points, lines and surfaces; finally, according to the technical scheme provided by the application, prediction processing aiming at the distribution accuracy of the interest points is carried out according to the characteristic information corresponding to each closed region, so that a prediction index value corresponding to each closed region is obtained, the prediction index value can indicate the distribution accuracy of the interest points in the corresponding closed region, further, according to the prediction index value corresponding to each closed region, the interest point data can be updated, and erroneous interest point data is deleted or adjusted, so that target map data of a map is obtained, the distribution of the interest points in the map is more reasonable, the interest point data in the target map data is more accurate, and finally, the accuracy of the target map data is improved, so that the application requirements of services based on geographic positions can be better met.

Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.

Drawings

In order to more clearly illustrate the embodiments of the application or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic view of an implementation environment of a map data processing method according to an embodiment of the present application;

fig. 2 is a flow chart of a map data processing method according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a management area according to an embodiment of the present application;

FIG. 4 is a schematic flow chart of dividing a map to obtain a closed area according to an embodiment of the present application;

FIG. 5 is a schematic illustration of an enclosed area provided by an embodiment of the present application;

FIG. 6 is a schematic flow chart of determining feature information according to an embodiment of the present application;

FIG. 7 is a schematic flow chart of model training according to an embodiment of the present application;

FIG. 8 is a flowchart of updating map data according to an embodiment of the present application;

fig. 9 is a schematic diagram of a map data processing apparatus according to an embodiment of the present application;

fig. 10 is a schematic diagram of a hardware structure of an apparatus for implementing a map data processing method according to an embodiment of the present application.

Detailed Description

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 scheme provided by the embodiment of the application relates to technologies such as Machine Learning (ML) of artificial intelligence.

Machine Learning (ML) is a multi-domain interdisciplinary, involving multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, etc. 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. The pre-training model is the latest development result of deep learning, and integrates the technology.

The scheme provided by the embodiment of the application can be deployed at the cloud, and the cloud technology and the like are also involved.

Cloud technology (Cloud technology): the system is a hosting technology for integrating hardware, software, network and other series resources in a wide area network or a local area network to realize calculation, storage, processing and sharing of data, and can be understood as a general term of network technology, information technology, integration technology, management platform technology, application technology and the like applied based on a cloud computing business model, and a resource pool can be formed, so that the system is used as required, and is flexible and convenient. Background service of the technical network system needs a large amount of computing and storage resources, such as video websites, picture websites and more portal websites, along with the high development and application of the internet industry, each object possibly has an own identification mark and needs to be transmitted to the background system for logic processing, data of different levels are processed separately, and various industry data needs powerful system rear shield support, so cloud technology needs to be supported by cloud computing. Cloud computing is a computing model that distributes computing tasks over a large number of computer-made resource pools, enabling various application systems to acquire computing power, storage space, and information services as needed. The network that provides the resources is referred to as the "cloud". Resources in the cloud are infinitely expandable in the sense of users, and can be acquired at any time, used as needed, expanded at any time and paid for use as needed. As a basic capability provider of cloud computing, a cloud computing resource pool platform, referred to as a cloud platform for short, is generally called an infrastructure as a service (Infrastructure as a Service, iaaS), and multiple types of virtual resources are deployed in the resource pool for external clients to select for use. The cloud computing resource pool mainly comprises: computing devices (which may be virtualized machines, including operating systems), storage devices, and network devices.

In order to improve the accuracy of map data, the embodiment of the application provides a map data processing method, a device, a medium and equipment. The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application. Examples of the embodiments are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements throughout or elements having like or similar functionality.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

In order to facilitate understanding of the technical solution and the technical effects thereof described in the embodiments of the present application, the embodiments of the present application explain related terms:

points of interest: point of Interest, which may be referred to simply as POI, refers to points of landmark construction and geographic entities closely related to people's life, such as schools, hospitals, malls, parks.

Depth-first search: depth First Search, abbreviated DFS, a depth-first search belongs to one of the graph algorithms for traversing all nodes in a graph or tree data structure. The procedure is briefly described as going deep enough for each possible branch path to no longer go deep, and each node can only be accessed once.

Gradient lifting decision tree: gradient Boosting Decision Tree, abbreviated as GBDT, is an algorithm that classifies or regresses data by employing an additive model (i.e., a linear combination of basis functions) and continuously reducing the residuals generated by the training process.

It will be appreciated that in the specific embodiments of the present application, related data such as user location information is involved, and when the above embodiments of the present application are applied to specific products or technologies, user permissions or consents need to be obtained, and the collection, use and processing of related data need to comply with related laws and regulations and standards of related countries and regions.

Referring to fig. 1, an implementation environment of a map data processing method according to an embodiment of the present application is shown in fig. 1, where the implementation environment may include at least a client 01 and a server 02.

Specifically, the client 01 may include smart phones, desktop computers, tablet computers, notebook computers, vehicle terminals, digital assistants, smart wearable devices, voice interaction devices, and other devices, or may include software running in the devices, for example, web pages provided by some service providers to users, or may provide applications provided by the service providers to users. Specifically, the client 01 may be configured to display the target map data, and the client 01 may further request a service based on a geographic location from the server 02 based on its own positioning information.

Specifically, the server 02 may be an independent physical server, or may be a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs (Content Delivery Network, content delivery networks), and basic cloud computing services such as big data and artificial intelligence platforms. The server 02 may include a network communication unit, a processor, a memory, and the like. The terminal and the server may be directly or indirectly connected through wired or wireless communication, and the present application is not limited herein. Specifically, the server 02 may be configured to perform map data processing on map data to be detected of a map in advance, including dividing the map according to road data in the map data to be detected to obtain at least one closed area; according to the interest point data, the road data and the background data in the map data to be detected, determining feature information corresponding to each closed area in at least one closed area, wherein the feature information can indicate interest point distribution feature information, road line distribution feature information and background surface distribution feature information of the corresponding closed area; inputting the characteristic information corresponding to each closed region into an interest point distribution prediction model, and performing prediction processing on the interest point distribution to obtain a prediction index value corresponding to each closed region, wherein the prediction index value can represent the accuracy of the interest point distribution in the corresponding closed region; and updating the interest point data in the map data to be detected according to the prediction index value corresponding to each closed region to obtain target map data of the map. Specifically, the server 02 may be further configured to send target map data to the client 01, receive a service request based on a geographic location sent by the client 01, and perform corresponding request response processing.

The embodiment of the application can also be realized by combining Cloud technology, wherein Cloud technology (Cloud technology) refers to a hosting technology for integrating hardware, software, network and other series resources in a wide area network or a local area network to realize calculation, storage, processing and sharing of data, and can also be understood as the general term of network technology, information technology, integration technology, management platform technology, application technology and the like applied based on a Cloud computing business model. Cloud technology requires cloud computing as a support. Cloud computing is a computing model that distributes computing tasks over a large number of computer-made resource pools, enabling various application systems to acquire computing power, storage space, and information services as needed. The network that provides the resources is referred to as the "cloud". Specifically, the server 02 and the database are located in the cloud, and the server 02 may be a physical machine or a virtualized machine.

Referring to fig. 2, which is a flowchart of a map data processing method according to an embodiment of the present application, the present application provides the method operation steps described in the examples or the flowcharts, but may include more or less operation steps based on conventional or non-creative labor. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When implemented in a real system or server product, the methods illustrated in the embodiments or figures may be performed sequentially or in parallel (e.g., in a parallel processor or multithreaded environment). Referring to fig. 2, a map data processing method provided by an embodiment of the present application may include the following steps:

S210: and acquiring map data to be detected of the map, wherein the map data to be detected comprises interest point data, road data and background data.

In the process of collecting, processing, drawing, updating and the like, data errors are possibly generated in map data, so that the conditions of unreasonable distribution of interest points (Point of Interest, POIs) and inaccurate interest point data are caused, and the accuracy degree of the interest point data directly influences the quality of the map data and the effect of service based on geographic positions. It is necessary to detect and update the map data.

In the embodiment of the application, the map data to be detected comprises interest point data, road data and background data. The interest point data characterizes the attribute of each interest point in the map, and can include, but is not limited to, the type of the interest point, the name of the interest point, the geographic address of the interest point, the longitude and latitude coordinates of the interest point and the like; the road data characterizes the attributes of each road in the map, which can include, but is not limited to, the type of the road, the level of the road, the coordinates of the starting and ending points of the road, the number of lanes of the road, etc.; the background data characterizes attributes of background areas in the map, such as greenbelts, buildings, lakes, etc., which may include, but are not limited to, the type of background area, the projected shape of the background area, the projected area of the background area, etc. It will be appreciated that the map data to be detected may include all data describing map information from which a complete map may be drawn. The embodiment of the application mainly utilizes the interest point data, the road data and the background data in the map data to be detected to detect the distribution condition of the interest points in the map data.

S220: and dividing the map according to the road data to obtain at least one closed area.

In the embodiment of the application, the geographical area related to the map is firstly divided to obtain at least one closed area, and the at least one closed area can be processed in parallel, so that the data processing efficiency is improved.

In an embodiment of the present application, at least one of the enclosed areas does not overlap each other.

In one embodiment of the present application, step S220 may be implemented as:

s310: region management hierarchy data is acquired.

By way of example, the management levels may include province, city, county, town, village, community, street, etc., and the regional management level data may indicate geographic regions corresponding to the management levels in the map.

S320: and dividing the map according to the regional management hierarchy data to obtain at least one management region.

Illustratively, the minimum management area level of the division is a street, the map is divided according to the area management level data, and the obtained at least one management area is a street area. For example, as shown in fig. 3, the divided management areas may be street areas, which are an a street area corresponding to a left dotted circle and a B street area corresponding to a right dot-dotted circle.

S330: and dividing each management area in the at least one management area according to the road data to obtain at least one closed area.

The road map structure is used for dividing each management area into at least one closed area, and the closed area can be an area surrounded by a closed loop path in the management area.

Considering that the distribution condition of interest points in the closed area has higher association degree with the closed area and has low association degree with other closed areas, the embodiment of the application uses the closed area as a detection object and utilizes map data in the closed area to detect the accuracy of the distribution of the interest points in the closed area.

In the above embodiment, the current region management level data is utilized to perform preliminary division to obtain at least one management region, and each management region is divided again according to the road data, so that at least one closed region which is not overlapped with each other can be rapidly and accurately obtained, and the closed region is taken as a detection object, so that the accuracy of the distribution of the interest points is detected.

In one embodiment of the present application, as shown in fig. 4, step S330 may be implemented as:

s331: and determining a road network diagram corresponding to each management area according to the road data, wherein the road network diagram takes intersections as nodes and roads between the intersections as edges.

Firstly, road data corresponding to each management area in the road data can be acquired; secondly, converting roads in the road network in each management area into edges according to road data corresponding to each management area, wherein the numbers of the edges can use the numbers of the roads, intersections in the road network can be converted into nodes, the numbers of the nodes can use the numbers of the intersections, and in addition, two end points of the edges respectively correspond to the starting point and the end point of the roads, and also can convert the two end points of the edges into nodes; and finally, establishing a connection relation between the nodes, and establishing bidirectional connection between each node and adjacent nodes through edges, thereby forming a road network diagram of the graph structure.

S332: and carrying out depth-first search processing on the road network map corresponding to each management area, determining at least one loop in the road network map corresponding to each management area, wherein each loop in the at least one loop is a path with the starting point and the end point of the same target node in the road network map, and the target node is any node in the road network map.

It is feasible to traverse each neighbor node which is not accessed from any node in the road network graph, recursively call the depth-first search function, and if the node which is accessed in the search process is encountered, it is indicated that the node accessed in the search process and the edge between the nodes form a loop, that is, the loop is a path of which the starting point and the end point are the same target node in the road network graph, and the edge in the loop does not appear repeatedly.

S333: dividing each management area according to at least one loop in the road network diagram corresponding to each management area to obtain at least one closed area; at least one of the enclosed areas does not overlap each other.

It is possible to divide each management area based on the area covered by the loop, resulting in at least one closed area, which may be indicated by the area enclosed by the dashed line in fig. 5.

In the embodiment, each management area in the map is abstracted into the road network map, and the map algorithm is used for further area division, so that the closed area with smaller area can be obtained efficiently and accurately, and the efficiency and the accuracy of detection by taking the closed area as a detection object are higher.

In another embodiment of the present application, the map may be further divided directly by using a graph algorithm to obtain at least one closed area, which is not described herein.

S230: and determining feature information corresponding to each closed region in at least one closed region according to the interest point data, the road data and the background data, wherein the feature information indicates interest point distribution feature information, road line distribution feature information and background surface distribution feature information of the corresponding closed region.

In the embodiment of the application, the feature information corresponding to each closed region characterizes the attribute information with higher association degree with the distribution of the interest points in the corresponding closed region, and can be extracted from three dimensions of points, lines and planes when the feature information is determined, so the feature information can comprise three aspects of feature interest point distribution feature information, road line distribution feature information and background plane distribution feature information.

In one embodiment of the present application, as shown in fig. 6, step S230 may be implemented as:

s410: and generating map element index information according to the interest point data, the road data and the background data.

Possibly, the map element index information can be generated by encoding the interest point data, the road data and the background data by using a multidimensional space point index algorithm, such as Geohash or Google S2.

S420: and determining the region interest point data corresponding to each closed region, the region road data corresponding to each closed region and the region background data corresponding to each closed region according to the map element index information.

That is, according to the index information of map elements, the data corresponding to the map elements in each enclosed area is recalled. It should be noted that, the region interest point data corresponding to each closed region, the region road data corresponding to each closed region, and the region background data corresponding to each closed region are all data encoded by using the multidimensional spatial point index algorithm.

S430: and calculating to obtain the characteristic information corresponding to each closed region according to the region interest point data corresponding to each closed region, the region road data corresponding to each closed region and the region background data corresponding to each closed region.

In the above embodiment, the map element index information is generated according to the point of interest data, the road data and the background data, so that the data corresponding to each closed region can be recalled quickly, and the feature information corresponding to each closed region can be determined quickly.

In one embodiment of the present application, step S430 may be implemented as:

S431: according to the regional interest point data corresponding to each closed region, the interest point distribution characteristic information corresponding to each closed region is obtained through calculation, wherein the interest point distribution characteristic information comprises the number and types of the interest points in the corresponding closed region.

S432: and calculating road line distribution characteristic information corresponding to each closed region according to the regional road data corresponding to each closed region, wherein the road line distribution characteristic information comprises names, grades and the number of lanes of roads in the corresponding closed region.

S433: according to the regional background data corresponding to each closed region, calculating to obtain the background surface distribution characteristic information corresponding to each closed region, wherein the background surface distribution characteristic information comprises the area and the area ratio of the background in the corresponding closed period region.

S434: and determining the characteristic information corresponding to each closed region according to the interest point distribution characteristic information corresponding to each closed region, the road line distribution characteristic information corresponding to each closed region and the background surface distribution characteristic information corresponding to each closed region.

In the above embodiment, the information types specifically included in the point of interest distribution feature information, the road line distribution feature information, and the background surface distribution feature information may be specifically set according to service requirements, practical experience, and the like, and the embodiment of the present application is merely an example. By determining the characteristic information with higher association degree with the distribution condition of the interest points, the accuracy of subsequent detection can be improved.

S240: and according to the characteristic information corresponding to each closed region, carrying out prediction processing aiming at the distribution accuracy of the interest points, and obtaining a prediction index value corresponding to each closed region, wherein the prediction index value represents the distribution accuracy of the interest points in the corresponding closed region.

In the embodiment of the application, based on the feature information corresponding to each closed region, prediction processing is performed for the distribution accuracy of the interest points, if the obtained prediction index value indicates that the distribution of the interest points in the closed region is unreasonable and inaccurate, the interest point data in the closed region can be considered as error data, and if the prediction index value indicates that the distribution of the interest points in the closed region is reasonable and accurate, the interest point data in the closed region can be considered as accurate data.

In the related art, the distance between the coordinates of the interest points and each map element such as a road line, a water system surface, a green ground surface, a building surface and the like needs to be calculated, then whether the distribution of the interest points is reasonable and accurate is judged by comparing the distance with a preset distance threshold value, the mode is mainly based on rules, the distance threshold value needs to be set by relying on the experience of experts in the field, the setting rule of the distance threshold value needs to be continuously optimized for ensuring the accuracy of final judgment, but the accuracy of the mode for detecting whether the distribution of the interest points is reasonable is limited due to geographic differences, and a large amount of manpower and time are consumed.

In one embodiment of the present application, the prediction process for the accuracy of the point of interest distribution using a model based on machine learning may specifically include:

s241: and inputting the feature information corresponding to each closed region into an interest point distribution prediction model, and carrying out feature characterization processing to obtain feature characterization data corresponding to each closed region.

The interest point distribution prediction model can be a regression model trained based on a gradient lifting decision tree algorithm, and the interest point distribution detection model is trained to be used for detecting whether the interest point distribution in each closed area is reasonable and accurate.

In the processing process of the interest point distribution prediction model, the feature information corresponding to each closed region is preferably mapped to the feature space where the model is located, that is, feature characterization processing is required to be performed on the feature information corresponding to each closed region, including but not limited to feature preprocessing, feature extraction or feature embedding representation, and the like, so that feature characterization data corresponding to each closed region is obtained.

S242: and carrying out regression prediction processing aiming at the distribution accuracy of the interest points according to the characteristic characterization data corresponding to each closed region to obtain a prediction index value corresponding to each closed region.

The regression prediction process for the accuracy of the distribution of the interest point, which is executed by the distribution prediction model of the interest point, is to analyze and predict the causal relationship between the feature characterization data (independent variable) corresponding to each closed region and the accuracy of the distribution of the interest point (dependent variable), and the obtained prediction index value can be a probability value between 0 and 1.

If the interest point distribution prediction model is a regression model trained based on a gradient lifting decision tree algorithm, the interest point distribution prediction model comprises a plurality of decision trees, each decision tree corresponds to a causal relationship between feature characterization data and interest point distribution accuracy, and the causal relationship can indicate probability values of the accurate type of the distribution of the interest points under the condition of the feature characterization data; the interest point distribution prediction model performs feature fitting according to the feature characterization data corresponding to each closed region, and determines the fitting degree or similarity between the feature characterization data corresponding to each closed region and the feature characterization data corresponding to each decision tree; and then, according to the fitting degree between the characteristic representation data corresponding to each closed region and the characteristic representation data corresponding to each decision tree and the weight corresponding to each decision tree, carrying out weighted summation calculation to finally obtain a prediction index value corresponding to each closed region, wherein the prediction index value can indicate the accuracy of the distribution of the interest points in the corresponding closed region.

In the above embodiment, the regression model based on machine learning is used to perform prediction processing for the accuracy of the distribution of the interest points, so that the setting of the judgment rule and the distance threshold is avoided, the processing efficiency is improved, and the detection accuracy can be effectively improved.

In one embodiment of the application, the interest point distribution prediction model can be a regression model obtained by training based on a gradient lifting decision tree algorithm, and the interest point distribution prediction model can also be a regression model obtained by training based on algorithms such as random forests, neural networks and the like in machine learning.

In an embodiment of the present application, prediction processing for the accuracy of the distribution of the points of interest may be performed on the feature information corresponding to each closed region based on the clustering idea, so as to obtain a prediction index value corresponding to each closed region. Specifically, a plurality of historical characteristic information clusters with accurate interest point distribution and a plurality of historical characteristic information clusters with inaccurate interest point distribution are obtained, the similarity degree of the characteristic information corresponding to each closed area and the class center of each historical characteristic information cluster is used as the probability that the characteristic information corresponding to each closed area is classified into each historical characteristic information cluster, and then the probability that the interest points in each closed area are distributed accurately or the probability that the interest points in each closed area are distributed inaccurately is determined according to the probability that the characteristic information corresponding to each closed area is classified into each historical characteristic information cluster.

In one embodiment of the present application, there is further provided a training process of the point of interest distribution prediction model, as shown in fig. 7, which may include the steps of:

s510: sample map data of a sample map is acquired, the sample map data including sample point of interest data, sample road data, and sample background data.

S520: and dividing the sample map according to the sample road data to obtain at least one sample sealing area.

S530: and determining sample characteristic information corresponding to each sample sealing area in at least one sample sealing area according to the sample interest point data, the sample road data and the sample background data, wherein the sample characteristic information indicates sample interest point distribution characteristic information, sample road route distribution characteristic information and sample background surface distribution characteristic information of the corresponding sample sealing area.

The steps S510 to S530 may refer to the steps S210 to S230 in the foregoing embodiments, and are not described herein.

S540: and acquiring label data corresponding to each sample sealing area, wherein the label data characterizes the accuracy of the distribution of the interest points in the corresponding sample sealing area.

The label data can be obtained by manual labeling, and the label data can represent whether the whole corresponding sample sealing area is distributed reasonably and accurately. Under the condition that the integral distribution of the corresponding sample sealing area is reasonable and accurate, the distribution of interest points in the corresponding sample sealing area can be considered to be reasonable and accurate; under the condition that the integral distribution of the corresponding sample sealing area is unreasonable and inaccurate, the distribution of the interest points in the corresponding sample sealing area can be considered to be unreasonable and inaccurate.

S550: training a preset machine learning model based on sample characteristic information corresponding to each sample sealing area, label data corresponding to each sample sealing area and a gradient lifting decision tree algorithm to obtain an interest point distribution prediction model.

Specifically, inputting sample characteristic information corresponding to each sample sealing area into a preset machine learning model, and performing prediction processing aiming at the distribution accuracy of interest points to obtain sample prediction index values corresponding to each sample sealing area; and calculating a loss value according to the sample prediction index value corresponding to each sample sealing area and the label data corresponding to each sample sealing area, and further performing iterative training on the machine learning model by using the loss value based on a gradient lifting decision tree algorithm until the machine learning model meets a preset convergence condition. In addition, the machine learning model can be optimized by combining indexes such as learning rate, tree number and the like.

In the embodiment, the model is subjected to supervised training by using the label data, so that the prediction accuracy of the model can be improved.

S250: and updating the interest point data in the map data to be detected according to the prediction index value corresponding to each closed region to obtain target map data of the map.

In the embodiment of the application, if the prediction index value indicates that the distribution of the interest points in the closed area is unreasonable and inaccurate, the interest point data in the closed area can be considered as error data and needs to be deleted or modified, and if the prediction index value indicates that the distribution of the interest points in the closed area is reasonable and accurate, the interest point data in the closed area can be considered as accurate data and does not need to be updated.

The embodiment of the application can perform offline mining on the stock map data, find out and clean the error data in the stock map data, and also can perform online detection on the incremental map data, identify the error data and reject the storage of the error data, thereby ensuring the accuracy of the map data.

In one embodiment of the present application, as shown in fig. 8, step S250 may be implemented as:

s610: and acquiring a preset index threshold.

The preset index threshold is a preset critical index value for judging whether the distribution is reasonably accurate, and can be set to be 0.5 or 0.75.

S620: and determining at least one target closed region according to the predictive index value corresponding to each closed region and a preset index threshold value, wherein the predictive index value corresponding to each target closed region in the at least one target closed region is lower than the preset index threshold value.

The higher the corresponding predictive index value of each closed region is, the higher the rationality accuracy of the interest point distribution in the corresponding closed region is, and vice versa. And comparing the prediction index value corresponding to each closed region with a preset index threshold value, screening out at least one target closed region, wherein the prediction index value corresponding to each target closed region can be not higher or lower than the preset index threshold value, and the distribution of interest points in the target region is unreasonable and inaccurate.

S630: and determining regional interest point data corresponding to at least one target closed region according to the interest point data.

S640: and deleting the region interest point data corresponding to the at least one target closed region from the map data to be detected to obtain target map data.

In the above embodiment, the prediction index value is compared with the preset index threshold value, and the target area with the prediction index value lower than the preset index threshold value, that is, the target area with unreasonable distribution of the interest points, is screened, so that the accuracy of the obtained target map can be improved by deleting the area interest point data corresponding to the target area.

As can be seen from the foregoing embodiments, the map data processing method provided by the present application divides a map into at least one closed area by using road data in map data to be detected, and determines feature information corresponding to each closed area according to interest point data, road data and background data in the map data to be detected, where the feature information may indicate interest point distribution feature information, road line distribution feature information and background surface distribution feature information corresponding to the corresponding closed area, that is, distribution features in the closed area are described from three dimensions of points, lines and surfaces; finally, according to the technical scheme provided by the application, prediction processing aiming at the distribution accuracy of the interest points is carried out according to the characteristic information corresponding to each closed region, so that a prediction index value corresponding to each closed region is obtained, the prediction index value can indicate the distribution accuracy of the interest points in the corresponding closed region, further, according to the prediction index value corresponding to each closed region, the interest point data can be updated, and erroneous interest point data is deleted or adjusted, so that target map data of a map is obtained, the distribution of the interest points in the map is more reasonable, the interest point data in the target map data is more accurate, and finally, the accuracy of the target map data is improved, so that the application requirements of services based on geographic positions can be better met.

The embodiment of the application also provides a map data processing device 900, as shown in fig. 9, the device 900 may include:

the data acquisition module 910 is configured to acquire map data to be detected of a map, where the map data to be detected includes interest point data, road data, and background data;

the area dividing module 920 is configured to divide the map according to the road data to obtain at least one closed area;

a feature determining module 930, configured to determine feature information corresponding to each of the at least one closed area according to the point of interest data, the road data, and the background data, where the feature information indicates point of interest distribution feature information, road line distribution feature information, and background surface distribution feature information of the corresponding closed area;

the prediction module 940 is configured to perform prediction processing for accuracy of the distribution of the points of interest according to the feature information corresponding to each closed region, and obtain a prediction index value corresponding to each closed region, where the prediction index value characterizes the accuracy of the distribution of the points of interest in the corresponding closed region;

and a data updating module 950, configured to update the interest point data in the map data to be detected according to the prediction index value corresponding to each closed area, so as to obtain target map data of the map.

In one embodiment of the present application, the area dividing module 920 may include:

a first data acquisition unit configured to acquire area management hierarchy data;

the first dividing unit is used for dividing the map according to the region management level data to obtain at least one management region;

and the second dividing unit is used for dividing each management area in the at least one management area according to the road data to obtain at least one closed area.

In one embodiment of the present application, the second dividing unit may include:

the road network diagram determining subunit is used for determining a road network diagram corresponding to each management area according to the road data, wherein the road network diagram is a diagram taking intersections as nodes and roads between the intersections as edges;

the depth-first searching subunit is configured to perform depth-first searching processing on the road network graph corresponding to each management area, determine at least one loop in the road network graph corresponding to each management area, where each loop in the at least one loop is a path in which a start point and an end point in the road network graph are both the same target node, and the target node is any node in the road network graph;

The dividing subunit is used for dividing each management area according to at least one loop in the road network diagram corresponding to each management area to obtain at least one closed area; the at least one enclosed region does not overlap each other.

In one embodiment of the present application, the feature determination module 930 may include:

an index information generating unit for generating map element index information according to the interest point data, the road data and the background data;

the regional data determining unit is used for determining regional interest point data corresponding to each closed region, regional road data corresponding to each closed region and regional background data corresponding to each closed region according to the map element index information;

the characteristic information determining unit is used for calculating and obtaining characteristic information corresponding to each closed area according to the area interest point data corresponding to each closed area, the area road data corresponding to each closed area and the area background data corresponding to each closed area.

In one embodiment of the present application, the characteristic information determining unit may include:

The first characteristic information determining subunit is used for calculating and obtaining the interest point distribution characteristic information corresponding to each closed area according to the area interest point data corresponding to each closed area, wherein the interest point distribution characteristic information comprises the number and the type of the interest points in the corresponding closed area;

the second characteristic information determining subunit is used for calculating and obtaining road line distribution characteristic information corresponding to each closed area according to the area road data corresponding to each closed area, wherein the road line distribution characteristic information comprises the names, the grades and the number of lanes of the roads in the corresponding closed area;

a third characteristic information determining subunit, configured to calculate, according to the area background data corresponding to each closed area, background surface distribution characteristic information corresponding to each closed area, where the background surface distribution characteristic information includes a corresponding area and area occupation ratio of a background in the closed period area;

the characteristic information determining subunit is configured to determine characteristic information corresponding to each closed area according to the interest point distribution characteristic information corresponding to each closed area, the road line distribution characteristic information corresponding to each closed area, and the background surface distribution characteristic information corresponding to each closed area.

In one embodiment of the present application, the data update module 950 may include:

the second data acquisition unit is used for acquiring a preset index threshold value;

the region screening unit is used for determining at least one target closed region according to the prediction index value corresponding to each closed region and the preset index threshold value; the predictive index value corresponding to each target closed region in the at least one target closed region is lower than the preset index threshold value;

the target closed region data determining unit is used for determining region interest point data corresponding to the at least one target closed region according to the interest point data;

and the data updating unit is used for deleting the region interest point data corresponding to the at least one target closed region from the map data to be detected to obtain the target map data.

In one embodiment of the present application, the prediction module 940 may include:

the feature characterization unit is used for inputting the feature information corresponding to each closed region into the interest point distribution prediction model, and performing feature characterization processing to obtain feature characterization data corresponding to each closed region;

the regression prediction unit is used for carrying out regression prediction processing aiming at the distribution accuracy of the interest points according to the characteristic characterization data corresponding to each closed region to obtain a prediction index value corresponding to each closed region; the interest point distribution prediction model is a regression model trained based on a gradient lifting decision tree algorithm.

In one embodiment of the present application, the apparatus 900 may further include:

a sample data acquisition unit configured to acquire sample map data of a sample map, the sample map data including sample point-of-interest data, sample road data, and sample background data;

the sample closed area dividing unit is used for dividing the sample map according to the sample road data to obtain at least one sample closed area;

the sample feature determining unit is used for determining sample feature information corresponding to each sample sealing area in the at least one sample sealing area according to the sample interest point data, the sample road data and the sample background data, wherein the sample feature information indicates sample interest point distribution feature information, sample road route distribution feature information and sample background surface distribution feature information of the corresponding sample sealing area;

the tag data acquisition unit is used for acquiring tag data corresponding to each sample sealing area, and the tag data represents the accuracy of the distribution of the interest points in the corresponding sample sealing area;

the model training unit is used for training a preset machine learning model based on the sample characteristic information corresponding to each sample sealing area, the label data corresponding to each sample sealing area and the gradient lifting decision tree algorithm to obtain the interest point distribution prediction model.

It should be noted that, in the apparatus provided in the foregoing embodiment, when implementing the functions thereof, only the division of the foregoing functional modules is used as an example, in practical application, the foregoing functional allocation may be implemented by different functional modules, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the apparatus and the method embodiments provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the apparatus and the method embodiments are detailed in the method embodiments and are not repeated herein.

The embodiment of the application provides a computer device, which comprises a processor and a memory, wherein at least one instruction or at least one section of program is stored in the memory, and the at least one instruction or the at least one section of program is loaded and executed by the processor to realize a map data processing method as provided by the embodiment of the method.

Fig. 10 is a schematic diagram of a hardware structure of an apparatus for implementing a map data processing method provided by an embodiment of the present application, where the apparatus may participate in forming or including an apparatus or a system provided by an embodiment of the present application. As shown in fig. 10, the apparatus 10 may include one or more processors 1002 (shown in the figures as 1002a, 1002b, … …,1002 n) (the processor 1002 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1004 for storing data, and a transmission device 1006 for communication functions. In addition, the method may further include: a display, an input/output interface (I/O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of the I/O interface), a network interface, a power supply, and/or a camera. It will be appreciated by those of ordinary skill in the art that the configuration shown in fig. 10 is merely illustrative and is not intended to limit the configuration of the electronic device described above. For example, the device 10 may also include more or fewer components than shown in fig. 10, or have a different configuration than shown in fig. 10.

It should be noted that the one or more processors 1002 and/or other data processing circuits described above may be referred to herein generally as "data processing circuits. The data processing circuit may be embodied in whole or in part in software, hardware, firmware, or any other combination. Further, the data processing circuitry may be a single stand-alone processing module, or incorporated in whole or in part into any of the other elements in the device 10 (or mobile device). As referred to in embodiments of the application, the data processing circuit acts as a processor control (e.g., selection of the path of the variable resistor termination connected to the interface).

The memory 1004 may be used to store software programs and modules of application software, and the processor 1002 executes the software programs and modules stored in the memory 1004 to perform various functions and data processing, i.e., implement a map data processing method according to the embodiments of the present application. Memory 1004 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 1004 may further include memory located remotely from the processor 1002, which may be connected to the device 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission means 1006 is for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communications provider of device 10. In one example, the transmission means 1006 includes a network adapter (Network Interface Controller, NIC) that can be connected to other network devices via a base station to communicate with the internet. In one example, the transmission device 1006 may be a Radio Frequency (RF) module for communicating with the internet wirelessly.

The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the device 10 (or mobile device).

The present application also provides a computer readable storage medium, which may be disposed in a server to store at least one instruction or at least one program related to a map data processing method in a method embodiment, where the at least one instruction or the at least one program is loaded and executed by the processor to implement a map data processing method provided in the method embodiment.

Alternatively, in this embodiment, the storage medium may be located in at least one network server among a plurality of network servers of the computer network. Alternatively, in the present embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Embodiments of the present application also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs a map data processing method provided in the above-described various alternative embodiments.

It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

The embodiments of the present application are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for apparatus, devices and storage medium embodiments, the description is relatively simple as it is substantially similar to method embodiments, with reference to the description of method embodiments in part.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.

Claims

1. A map data processing method, characterized in that the method comprises:

Dividing the map according to the road data to obtain at least one closed area;

2. The method of claim 1, wherein the dividing the map according to the road data to obtain at least one closed area comprises:

acquiring regional management hierarchy data;

3. The method of claim 2, wherein dividing each of the at least one management area according to the road data to obtain at least one closed area comprises:

4. The method of claim 1, wherein determining feature information corresponding to each of the at least one closed region based on the point of interest data, the road data, and the background data comprises:

5. The method of claim 4, wherein the calculating the feature information corresponding to each closed region according to the region interest point data corresponding to each closed region, the region road data corresponding to each closed region, and the region background data corresponding to each closed region includes:

6. The method according to claim 1, wherein updating the interest point data in the map data to be detected according to the prediction index value corresponding to each closed region to obtain target map data of the map includes:

Acquiring a preset index threshold;

7. The method of claim 1, wherein the performing prediction processing for the accuracy of the distribution of the points of interest according to the feature information corresponding to each closed region to obtain the prediction index value corresponding to each closed region includes:

8. The method of claim 7, wherein the method further comprises:

9. A map data processing apparatus, characterized in that the apparatus comprises:

10. A computer-readable storage medium, characterized in that at least one instruction or at least one program is stored in the computer-readable storage medium, which is loaded and executed by a processor to implement a map data processing method according to any one of claims 1 to 8.

11. A computer device comprising a processor and a memory, wherein the memory has stored therein at least one instruction or at least one program that is loaded and executed by the processor to implement a map data processing method as claimed in any one of claims 1 to 8.