Method, device and equipment for judging regional type based on urban road and POI data

Abstract

The present application relates to the region type recognition technology, disclose a kind of based on urban road and POI data's region type discrimination method, comprising: obtaining the road network data set and POI data set of first target area, the road network data set is divided, and the block data set is obtained, the block data set is merged with POI data set, and the merged data set is obtained;Extract block POI data, and the category screening is carried out to block POI data, and the interest POI category is obtained;The weighted score value of interest POI category is calculated, when there is commercial sign, the category proportion of commercial type in interest POI category is calculated;The region type label of first target area is determined according to the category proportion, and the random forest model is constructed using region type label, and the region type discrimination is carried out to second target area according to random forest model.The present application also proposes a kind of based on urban road and POI data's region type discrimination device and electronic equipment.The present application can improve the accuracy of region type discrimination.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of region type recognition, and particularly relates to a region type discrimination method and device based on urban road and POI data and electronic equipment. BACKGROUND

[0002] With the acceleration of urbanization, traffic congestion, housing shortage and commuting difficulties and other problems not only trouble the life of urban residents, but also restrict the development of the city, and the development of the city gradually produces different functional areas, such as residential areas, education areas and commercial areas. In order to better distinguish the functional areas of the region and bring convenience to people, it is necessary to analyze the road data and POI data of the region to discriminate the region type.

[0003] The existing region type discrimination technology is mainly based on the road conditions in the map software to divide the region, and then discriminate the region type. In actual application, the roads and the distribution of actual facilities in different regions are different, and only considering the distribution of the road conditions may lead to a single discrimination method of the region type, thereby reducing the accuracy of discriminating the region type. SUMMARY

[0004] The present application provides a region type discrimination method and device based on urban road and POI data and electronic equipment, which mainly aims to solve the problem of low accuracy in discriminating the region type.

[0005] To achieve the above purpose, the present application provides a region type discrimination method based on urban road and POI data, which comprises:

[0006] S1, acquiring the road network data set and the POI data set of the first target region, dividing the road network data set by using a preset road network division algorithm to obtain a block data set, and merging the block data set with the POI data set to obtain a merged data set;

[0007] S2, extracting the block POI data in the merged data set by using a preset electronic fence, and screening the block POI data according to a preset block type interest demand to obtain an interest POI type, wherein the screening of the block POI data according to the preset block type interest demand to obtain the interest POI type comprises:

[0008] S21, calculating the public awareness of each POI data in the block POI data according to the following awareness formula:

[0009]

[0010] wherein R is the public awareness, K is the number of POI data in the block POI data, and P is the number of POI data in the interest POI type.i is the number of cognitive emotions for the i-th cognitive emotion, K A is the number of cognitive emotions A, K B is the number of cognitive emotions B, K C is the number of cognitive emotions C, K D is the number of cognitive emotions D, K E is the number of cognitive emotions E;

[0011] S22, when the public cognitive degree is less than a preset cognitive degree threshold, eliminating the POI data corresponding to the public cognitive degree in the block POI data to obtain updated block POI data;

[0012] S23, when the public cognitive degree is greater than or equal to a preset cognitive degree threshold, performing category screening on the POI data in the updated block POI data according to the block category interest demand to obtain the interest POI category;

[0013] S3, calculating a weighted score value of the interest POI category by using a preset weighting algorithm, judging whether a commercial sign exists in the merged data set according to the weighted score value, and when the commercial sign exists, calculating a category proportion of a commercial type in the interest POI category;

[0014] S4, determining a regional type label of the first target area according to the category proportion and a preset category proportion threshold, constructing a random forest model by using the regional type label, and performing regional type discrimination on a preset second target area according to the random forest model.

[0015] Optionally, the road network data set is divided by using a preset road network division algorithm to obtain a block data set, including:

[0016] performing road screening on the roads in the road network data set to obtain screened roads;

[0017] performing level division on the screened roads according to a preset road level to obtain level roads;

[0018] performing spatial division on the level roads by using a preset buffer zone to obtain road spaces;

[0019] eliminating the road spaces from the road network data set to obtain the block data set.

[0020] Optionally, the block POI data in the merged data set is extracted by using a preset electronic fence, including:

[0021] selecting any interest point in the merged data set as a target point;

[0022] determining fence coordinates of the electronic fence according to the target point;

[0023] generating a polygon region according to the fence coordinates;

[0024] extracting POI data in the merged data set by using the polygon region, and collecting the POI data as block POI data.

[0025] Optionally, the calculating the weighted score value of the interested POI category by using a preset weighting algorithm comprises:

[0026] obtaining a category score value of each of the interested POI categories;

[0027] determining a category weight of each of the interested POI categories by using a preset analytic hierarchy process;

[0028] calculating the weighted score value of the interested POI category according to the category score value and the category weight by using the weighting algorithm:

[0029]

[0030] wherein F is the weighted score value, p j is a category score value of the jth interested POI category, w j is a category weight of the jth interested POI category, and n is a number of the interested POI categories.

[0031] Optionally, the calculating the category proportion of the business type in the interested POI category comprises:

[0032] counting a first POI data quantity in each of the interested POI categories, and counting a second POI data quantity in each of the business types in the interested POI categories;

[0033] calculating the category proportion of the business type according to the first POI data quantity and the second POI data quantity by using a category proportion formula as follows:

[0034]

[0035] wherein T v is the category proportion of the vth business type, s u is a first POI data quantity of the uth interested POI category, γ v is a second POI data quantity of the vth business type, and m is a number of the business types.

[0036] Optionally, the constructing a random forest model by using the region type label comprises:

[0037] The region type labels are divided by using a preset estimation algorithm to obtain a divided region type label data set;

[0038] In each of the divided region type label data sets, a label feature is selected as a root node, and a left node and a right node are split in the root node;

[0039] Each of the divided region type label data sets is distributed to the left node and the right node to obtain a classification regression tree, and the classification regression trees are collected to form the random forest model.

[0040] Optionally, the region type discrimination of the preset second target region according to the random forest model comprises:

[0041] Obtaining to-be-discriminated region data of the second target region;

[0042] The to-be-discriminated region data is classified by using each classification regression tree in the random forest model to obtain a classification prediction value;

[0043] The region with the maximum classification prediction value is selected as the region type of the second target region.

[0044] To solve the above problems, the application further provides a region type discrimination device based on urban road and POI data, which comprises:

[0045] A data merging module is configured to obtain a road network data set and a POI data set of a first target region, divide the road network data set by using a preset road network division algorithm to obtain a block data set, and merge the block data set and the POI data set to obtain a merged data set;

[0046] A POI category screening module is configured to extract block POI data in the merged data set by using a preset electronic fence, and screen the block POI data according to a preset block category interest demand to obtain an interest POI category;

[0047] A category proportion calculation module is configured to calculate a weighted score value of the interest POI category by using a preset weighting algorithm, and determine whether a commercial sign exists in the merged data set according to the weighted score value, and calculate a category proportion of a commercial type in the interest POI category when the commercial sign exists;

[0048] A region type discrimination module is configured to determine a region type label of the first target region according to the category proportion and a preset category proportion threshold value, construct a random forest model by using the region type label, and discriminate the region type of a preset second target region according to the random forest model.

[0049] To solve the above problems, the present application also provides an electronic device, which comprises:

[0050] at least one processor; and,

[0051] a memory connected in communication with the at least one processor; wherein,

[0052] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the above-mentioned region type discrimination method based on urban road and POI data.

[0053] The embodiment of the present application can improve the accuracy of region type discrimination by dividing the road network data set of the target region to obtain a block data set, merging the block data set with a POI data set to obtain a merged data set, and then extracting block POI data according to the merged data set. By screening the POI categories of interest, scoring and weighting the POI categories in the block, and then judging whether there is a commercial sign in the region according to the weighted score value, the commercial area and the non-commercial area can be accurately determined. When there is a commercial sign, the category proportion of each commercial type is calculated, and the region type label is determined according to the category proportion, and then a random forest model is constructed using the region type label, and the random forest model is used to discriminate the region type of other regions, so as to realize the region type discrimination of the target region, and improve the accuracy of region type discrimination, which is convenient for other regions to easily realize region type discrimination. Therefore, the region type discrimination method, device and electronic device based on urban road and POI data provided by the present application can solve the problem of low accuracy in region type discrimination. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 The flowchart of the region type discrimination method based on urban road and POI data provided by an embodiment of the present application;

[0055] Figure 2 The schematic diagram of city division provided by an embodiment of the present application;

[0056] Figure 3 The road division schematic diagram of the region provided by an embodiment of the present application;

[0057] Figure 4 The commercial circle division schematic diagram provided by an embodiment of the present application;

[0058] Figure 5 The region type prediction result schematic diagram provided by an embodiment of the present application;

[0059] Figure 6A region type of Guangzhou region provided by an embodiment of the present application is divided;

[0060] Figure 7 A region type of Shenzhen region provided by an embodiment of the present application is divided;

[0061] Figure 8 A region type division-block judgment flowchart provided by an embodiment of the present application is shown in the figure;

[0062] Figure 9 A function module diagram of a region type discrimination device based on urban road and POI data provided by an embodiment of the present application is shown in the figure;

[0063] Figure 10 A structure schematic diagram of an electronic device for implementing a region type discrimination method based on urban road and POI data provided by an embodiment of the present application is shown in the figure.

[0064] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0065] It should be understood that the specific embodiments described herein are merely intended to explain the present application and are not intended to limit the present application.

[0066] An embodiment of the present application provides a region type discrimination method based on urban road and POI data. An execution subject of the region type discrimination method based on urban road and POI data includes but is not limited to at least one of electronic devices such as a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the present application. In other words, the region type discrimination method based on urban road and POI data can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster and the like. The server can be a stand-alone server, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN), and big data and artificial intelligence platforms and the like basic cloud computing services.

[0067] Referring to Figure 1 The flowchart of the region type discrimination method based on urban road and POI data provided by an embodiment of the present application is shown in the figure. In the embodiment, the region type discrimination method based on urban road and POI data includes:

[0068] S1, acquire a road network dataset and a POI dataset of a first target region, divide the road network dataset by using a preset road network division algorithm to obtain a block dataset, and perform data merging on the block dataset and the POI dataset to obtain a merged dataset;

[0069] In the embodiment of the application, the road network dataset contains various road basic attributes of the target region, the POI dataset is interest point data, includes basic attribute information such as area name, area category, area geology, province, city, area, and latitude and longitude, and the POI data is a kind of marked point-like abstract geographical spatial data representing geographical entities, including many urban facilities closely related to people, such as supermarkets, shopping malls, schools, banks, etc. However, due to the complexity of the original POI data and the existence of data redundancy, data cleaning and data reclassification are required to obtain the POI dataset after preprocessing.

[0070] In detail, the road network dataset of the first target region can be acquired through an open source map (Open Street Map, OSM). OSM aims to provide users with free and easy-to-access digital map resources, and has very high positioning accuracy and topological relationship, great openness, and the POI dataset of the first target region can be acquired through Gaode map.

[0071] Further, as shown in Figure 2 The schematic diagram of the city division can be used to distinguish the types of regions in different cities by dividing different cities and marking city road lines in the city information of the map.

[0072] In the embodiment of the application, the road network dataset is divided to generate road region units of the target region, so as to facilitate the discrimination of the types of regions of the target region. The block dataset is the region road formed by dividing the roads in the road network dataset.

[0073] In the embodiment of the application, the road network dataset is divided by using a preset road network division algorithm to obtain a block dataset, including:

[0074] The roads in the road network dataset are subjected to road screening to obtain screened roads;

[0075] The screened roads are subjected to grade division according to a preset road grade to obtain grade roads;

[0076] The grade roads are subjected to spatial division by using a preset buffer zone to obtain road spaces;

[0077] The road spaces are removed from the road network dataset to obtain the block dataset.

[0078] In detail, based on the road network dataset of the first target area, the roads in the road network dataset are filtered to select primary roads, secondary roads, tertiary roads, and arterial roads. The filtered roads include primary roads, secondary roads, tertiary roads, and arterial roads. Based on the actual road conditions in the first target area, the filtered roads can be divided into three levels, with arterial roads being the first level, primary and secondary roads being the second level, and tertiary roads being the third level.

[0079] Specifically, to create road spaces, buffer zones of 40 meters, 20 meters, and 10 meters are set to spatially divide roads of different levels, thus forming road spaces. These road spaces are then removed from the road network dataset, and smaller road spaces are deleted, ultimately yielding the block dataset.

[0080] Furthermore, such as Figure 3 The diagram shows a road division in a certain area of ​​Shenzhen. Roads are drawn as polygons using polygons to mark the road divisions. Marking is done along the shortest path to form multiple different regional roads. Based on the regional roads, the target area can be divided into multiple areas, which facilitates the identification of the regional type of the target area.

[0081] In this embodiment of the invention, merging the block dataset and the POI dataset involves labeling POI points of interest in different block roads. Therefore, the block dataset and the POI dataset can be merged to obtain a merged dataset. This merged dataset serves as the data foundation for region classification of different areas.

[0082] Furthermore, the POI datasets of different blocks are extracted and analyzed according to the constraints to determine the types of POI data in the POI datasets.

[0083] S2. Extract block POI data from the merged dataset using a preset electronic fence, and filter the block POI data according to preset block type interest requirements to obtain interest POI types.

[0084] In this embodiment of the invention, the electronic fence refers to using a virtual fence to enclose a virtual geographical boundary. When a mobile phone or electronic product enters or leaves a specific geographical area, or moves within that area, the mobile phone or electronic product can receive automatic notifications and warnings.

[0085] In this embodiment of the invention, the step of extracting block POI data from the merged dataset using a preset electronic fence includes:

[0086] Select any point of interest in the merged dataset as the target point;

[0087] determining the fence coordinates of the electronic fence according to the target point;

[0088] generating a polygon region according to the fence coordinates;

[0089] extracting POI data in the merged data set by using the polygon region, and collecting the POI data as block POI data.

[0090] In detail, the POI data of different regions is included in the merged data set, and the POI data is a point of interest, that is, a point concept. When the region type is determined, the region is determined from a larger range, that is, the region around the POI is enclosed by a polygon, like a fence.

[0091] Specifically, any selected POI point of interest data in the merged data set is taken as a target point, and the range is expanded based on the target point to obtain the fence coordinates of the electronic fence based on the target point, that is, the coordinate range when the target is expanded. The fence coordinates of the electronic fence can be obtained by using the latitude and longitude in the Gaode map, and the electronic fence coordinates are connected to generate a polygon region. The POI data in the merged data set is extracted in the polygon region, and each POI point of interest is collected as the block POI data. That is, only the POI point of interest within the polygon region can be extracted, and the extraction of the POI data beyond the polygon region will be warned.

[0092] Further, after the POI data is filtered within the preset electronic fence, a plurality of POI data points of interest are obtained within the region, and the types of the POI data points of interest are analyzed.

[0093] In the embodiment of the application, the block type interest demand refers to the type screening of the POI data in the region according to the type demand of the own judgment and the actual facility distribution of the target area. As shown in the figure, Figure 4 which is a commercial circle division schematic diagram, the block type includes a commercial circle and a non-commercial circle, and the commercial circle includes a commercial district commercial circle, a community type commercial circle, an office district commercial circle, a transportation hub commercial circle, a school and education commercial circle, a scenic spot type commercial circle and other commercial circles.

[0094] In the embodiment of the application, the block POI data is screened according to the preset block type interest demand to obtain the POI type of interest, which includes:

[0095] The public awareness of each POI data in the block POI data is calculated according to the following cognitive degree formula:

[0096]

[0097] Wherein, R is the public cognition degree, K i is the number of the ith cognition emotion, K A is the number of cognition emotion A, K B is the number of cognition emotion B, K C is the number of cognition emotion C, K D is the number of cognition emotion D, K E is the number of cognition emotion E;

[0098] When the public cognition degree is less than a preset cognition degree threshold, the POI data corresponding to the public cognition degree in the block POI data is eliminated to obtain updated block POI data;

[0099] When the public cognition degree is greater than or equal to the preset cognition degree threshold, the POI data in the updated block POI data is classified according to the block category interest demand to obtain the interest POI category.

[0100] In detail, the public space emotion information of urban residents is obtained by means of on-site questionnaire, wherein cognition emotion A is very positive (happy, excited, etc.), cognition emotion B is generally positive (comfortable, calm, etc.), cognition emotion C is neutral (calm, indifferent, etc.), cognition emotion D is generally negative (uncomfortable, irritable, etc.), cognition emotion E is very negative (disappointed, disgusting, etc.), cognition emotion F is going, but not many times, cognition emotion G is not going, but hearing, and cognition emotion H is going frequently. The number of cognition emotions is counted by means of questionnaire survey, and the public cognition degree of each POI data is calculated according to the number of cognition emotions.

[0101] Specifically, although each POI in the block POI data has a certain influence range and representative information, the public cognition degree of some types of POI is low, such as road intersection, entrance and exit, bus station, newspaper stand, etc. This type of POI does not have obviousness in the identification of urban functional area, and therefore, the POI with low public cognition degree is eliminated from the original block POI data. When the public cognition degree is greater than or equal to the preset cognition degree threshold, the POI data that can obviously represent the characteristics of the urban functional area is selected. For example, according to the block category interest demand, the updated block POI data is divided into commercial circle and non-commercial circle, and the commercial circle can be further divided into commercial district commercial circle, community type commercial circle, office district commercial circle, traffic hub commercial circle, school and education commercial circle, scenic spot type commercial circle and other commercial circle.

[0102] Further, the type proportion analysis is performed according to the divided POI category, so as to perform division and discrimination analysis on the regional type of the target area, and thus the accuracy of the regional category discrimination can be improved.

[0103] S3, calculating a weighted score value of the interest POI category by using a preset weighting algorithm, judging whether a commercial sign exists in the merged data set according to the weighted score value, and calculating a category proportion of a commercial type in the interest POI category when the commercial sign exists;

[0104] In the embodiment of the application, each interest POI category in a block is scored and the scores are weighted and summarized to determine commercial and non-commercial areas in a target area according to the score summary.

[0105] In the embodiment of the application, the calculation of the weighted score value of the interest POI category by using the preset weighting algorithm comprises:

[0106] obtaining a category score of each interest POI category;

[0107] determining a category weight of each interest POI category by using a preset analytic hierarchy process;

[0108] calculating the weighted score value of the interest POI category according to the category score and the category weight by using the weighting algorithm:

[0109]

[0110] wherein F is the weighted score value, p j is a category score of the jth interest POI category, w j is a category weight of the jth interest POI category, and n is the number of the interest POI categories.

[0111] In detail, each interest POI category is scored by questionnaire survey, and the overall score of each interest POI category in the questionnaire is counted. The category weight of each interest POI category is determined according to the floor area and public awareness of each interest POI category by using the analytic hierarchy process. The analytic hierarchy process is a decision-making method of qualitative and quantitative analysis by decomposing a problem to be decided and its related factors into target, criterion, scheme and other levels. A hierarchical structure model needs to be established, a judgment matrix needs to be constructed, and the weight of a factor needs to be determined according to the judgment matrix.

[0112] Specifically, the weighted score value of the interest POI category is calculated according to the category score and the category weight. The category weight represents the importance of the interest POI category, so that the region type can be accurately identified. The commercial and non-commercial areas in the region are determined by using the weighted score value.

[0113] Further, the commercial sign includes shopping centers, supermarkets, department stores, catering, when the weighted score value is greater than the preset score threshold, it indicates that there is a shopping center, supermarket, department store, catering in the block POI category in the merged data set, and it is determined that this block POI category is a commercial area; when the weighted score value is less than the preset score threshold, it is determined that this block POI category is a non-commercial area.

[0114] In the embodiment of the application, when the commercial area and the non-commercial area are determined according to the weighted score value, when the commercial sign exists, the commercial area is further divided, and the category proportion of the commercial area commercial circle, community type commercial circle, office area commercial circle, traffic hub commercial circle, school and education commercial circle, scenic type commercial circle and other commercial circles in the commercial area is determined, and the city area type is predicted according to the category proportion.

[0115] In the embodiment of the application, the calculation of the category proportion of the commercial type in the interest POI category includes:

[0116] The first POI data quantity in each interest POI category is counted, and the second POI data quantity in each commercial type in the interest POI category is counted;

[0117] The category proportion of the commercial type is calculated according to the first POI data quantity and the second POI data quantity by using the following category proportion formula:

[0118]

[0119] Wherein, T v is the category proportion of the vthcommercial type, s u is the first POI data quantity of the uthinterest POI category, γ v is the second POI data quantity of the vthcommercial type, and m is the category number of the commercial type.

[0120] In detail, for the commercial area containing multiple commercial circles, the POI data of each commercial type is judged by proportion, first the POI data quantity in the commercial area in the interest POI category is counted, and then the POI data quantity in each commercial type in the commercial area is counted, such as the POI data quantity in the community type circle in the commercial area, the POI data quantity in the office area circle, etc.

[0121] Specifically, the category proportion of each commercial type can be calculated according to the POI data quantity, so as to further judge the specific commercial type label according to the category proportion, and then predict and distinguish the area type of the target area according to the commercial type label.

[0122] S4, determining a region type label of the first target region according to the category proportion and a preset category proportion threshold, constructing a random forest model by using the region type label, and determining a region type of a preset second target region according to the random forest model.

[0123] In the embodiment of the present application, the category proportion threshold is determined as 50% according to the proportion of each business type, which is used as a standard for judging the nature of each business type. When the category proportion of a business type is 50% or more, the region is determined as a single function area, and the single function area includes a business district, a community type business circle, an office district business circle, a transportation hub business circle, a school and education business circle, a scenic type business circle and other business circles. When the category proportion of all types of POIs does not reach 50%, it is determined that the region is a mixed function area, and the mixed type depends on the three main POI types in the region. When the region does not contain POI, the type proportion is null, and the type region is a null region.

[0124] In detail, the region type of the target region is determined by constructing a random forest model to predict the region type of the target region, and the predetermined region type label is used as a sample type label, wherein the sample type label includes a business district, a community type business circle, an office district business circle, a transportation hub business circle, a school and education business circle, a scenic type business circle and other business circles. The random forest model is constructed according to the sample type label to determine the region type of the target region.

[0125] In the embodiment of the present application, the random forest model is a classical Bagging model (bagging model), and the weak learner is a decision tree model, which is a model for classifying data.

[0126] In the embodiment of the present application, the random forest model is constructed by using the region type label, including:

[0127] The region type label is divided by using a preset estimation algorithm to obtain a divided region type label data set;

[0128] Any selected label feature in each of the divided region type label data sets is taken as a root node, and left and right nodes are split in the root node;

[0129] Each of the divided region type label data sets is distributed to the left node and the right node to obtain a classification regression tree, and the classification regression trees are collected to form the random forest model.

[0130] In detail, the estimation algorithm uses the bootstrap algorithm to randomly draw K training samples of size nt with replacement from the region type label dataset. Each training sample typically contains only 2 / 3 of the original training set, with the remaining 1 / 3 being referred to as out-of-bag data. For each training sample, i.e., each region type label dataset, any feature from the region type label is selected as the root node, and a left and right node are split from this root node to complete the construction of a classification and regression tree. The generated classification and regression trees are combined into a random forest, and the region type of the target region is predicted and determined based on the random forest.

[0131] In this embodiment of the invention, the second target region is predicted by using a random forest model to obtain the region types of the second target region, such as scenic spots, commercial areas, and schools.

[0132] In this embodiment of the invention, the step of determining the region type of the preset second target region based on the random forest model includes:

[0133] Obtain the data of the region to be judged in the second target region;

[0134] The random forest model is used to classify the data in the region to be judged, and the classification prediction value is obtained.

[0135] The region with the largest classification prediction value is selected as the region type of the second target region.

[0136] In detail, the random forest model uses a classification regression tree for each of the following types of business districts: commercial districts, community-type business districts, office districts, transportation hubs, school and educational districts, tourist attractions, and other business districts. When performing region classification on the data of the region to be classified, the random forest model is used to classify the data and obtain the predicted value of the region to be classified belonging to each classification regression tree. The business label corresponding to the largest classification prediction value is selected as the region type of the second target region.

[0137] Specifically, such as Figure 5 The image shows a schematic diagram of the region type prediction results. Based on the original map information, regions are divided into different types, such as... Figure 5 The area with POI data is Zhujiang Park. After using a random forest model to predict whether the area is a scenic spot, it can be further divided into commercial areas and residential communities based on different POI data.

[0138] Furthermore, such as Figure 6As shown in the figure, the regional types divided in Guangzhou region, according to the terrain and urban planning of Guangzhou region, the regional types of Guangzhou region are divided, and the specific position of each region is determined, that is, the commercial district, the community type commercial circle, the office district commercial circle, the traffic hub commercial circle, the school and education commercial circle, the scenic spot type commercial circle, the other commercial circle, the office community mixed commercial circle, the commercial office mixed commercial circle, the commercial community mixed commercial circle and the non-commercial circle are divided in Guangzhou region. Similarly, as shown in the figure, Figure 7 As shown in the figure, the regional types divided in Shenzhen region, the specific regional types divided in Shenzhen are the same as the specific regional types divided in Guangzhou region.

[0139] In the embodiment of the application, in order to further explain the regional type discrimination method, as shown in the figure, Figure 8 As shown in the figure, the regional type division-block judgment flow chart, that is, the POI data set and the block data set based on the road network division are merged, the POI data in the block is extracted based on the electronic fence, and the POI categories of interest are screened, the POI in the block is scored and weighted, and the weighted value is used to judge whether there is a supermarket, shopping center, department store, catering, when there is a supermarket, shopping center, catering, etc., the commercial district is determined, and the proportion of each POI category is judged, the random forest model is established according to the sample type label, and the random forest model is used to discriminate other city regions.

[0140] The embodiment of the application can improve the accuracy of regional type discrimination by dividing the road network data set of the target region to obtain the block data set, merging the block data set with the POI data set to obtain the merged data set, and then extracting the block POI data according to the merged data set. Screen the POI categories of interest, score and weight the POI categories in the block, and then judge whether there is a commercial sign in the region according to the weighted score value. The commercial district and the non-commercial district can be accurately judged. When there is a commercial sign, the proportion of each commercial type is calculated, and the regional type label is determined according to the proportion of the type, and then the random forest model is constructed using the regional type label, and the random forest model is used to discriminate the regional type of other regions. The regional type discrimination of the target region can be realized, and the accuracy of regional type discrimination can be improved, which is convenient for other regions to easily realize regional type discrimination. Therefore, the regional type discrimination method, device and electronic equipment based on city road and POI data provided by the application can solve the problem of low accuracy in regional type discrimination.

[0141] As shown in the figure, Figure 9 As shown in the figure, the functional module diagram of the regional type discrimination device based on city road and POI data provided by an embodiment of the application.

[0142] The area type discrimination device 100 based on urban road and POI data according to the present application can be installed in an electronic device. According to the functions implemented, the area type discrimination device 100 based on urban road and POI data can include a data merging module 101, a POI category screening module 102, a category proportion calculation module 103, and an area type discrimination module 104. The modules according to the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, and are stored in the memory of the electronic device.

[0143] In the present embodiment, the functions of each module / unit are as follows:

[0144] The data merging module 101 is configured to obtain a road network data set and a POI data set of a first target area, divide the road network data set using a preset road network division algorithm to obtain a block data set, and merge the block data set with the POI data set to obtain a merged data set.

[0145] The POI category screening module 102 is configured to extract block POI data in the merged data set using a preset electronic fence, and screen the block POI data according to a preset block category interest demand to obtain an interest POI category.

[0146] The category proportion calculation module 103 is configured to calculate a weighted score value of the interest POI category using a preset weighting algorithm, determine whether a commercial sign exists in the merged data set according to the weighted score value, and calculate a category proportion of a commercial type in the interest POI category when the commercial sign exists.

[0147] The area type discrimination module 104 is configured to determine an area type label of the first target area according to the category proportion and a preset category proportion threshold, construct a random forest model using the area type label, and discriminate the area type of a preset second target area according to the random forest model.

[0148] In detail, each module in the area type discrimination device 100 based on urban road and POI data in the present embodiment uses the same technical means as the area type discrimination method based on urban road and POI data in the above Figures 1 to 7 , and can produce the same technical effects, which will not be described here again.

[0149] As shown in Figure 10 , it is a structural schematic diagram of an electronic device for implementing an area type discrimination method based on urban road and POI data according to an embodiment of the present application.

[0150] The electronic device 1 can include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and can further include a computer program stored in the memory 11 and executable on the processor 10, such as a region type determination program based on urban road and POI data.

[0151] The processor 10 can be composed of integrated circuits in some embodiments, for example, can be composed of a single packaged integrated circuit, or can be composed of multiple packaged integrated circuits with the same function or different functions, including one or more combinations of central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control core of the electronic device, connects various components of the entire electronic device through various interfaces and lines, executes programs or modules stored in the memory 11 (such as executing a region type determination program based on urban road and POI data), and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0152] The memory 11 includes at least one type of readable storage medium, including flash memories, mobile hard disks, multimedia cards, card-type memories (such as SD or DX memories, etc.), magnetic memories, magnetic disks, optical disks, etc. The memory 11 can be an internal storage unit of the electronic device in some embodiments, such as a mobile hard disk of the electronic device. The memory 11 can also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Further, the memory 11 can include both the internal storage unit and the external storage device of the electronic device. The memory 11 can be used not only to store application software and various data installed on the electronic device, such as the code of the region type determination program based on urban road and POI data, but also to temporarily store data that has been output or will be output.

[0153] The communication bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize the connection and communication between the memory 11 and the at least one processor 10, etc.

[0154] The communication interface 13 is configured to realize the communication between the electronic device and other devices, and includes a network interface and a user interface. Optionally, the network interface can include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), and is usually configured to establish a communication connection between the electronic device and other electronic devices. The user interface can be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface can also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch screen, etc. The display can also be appropriately referred to as a display screen or a display unit, and is configured to display information processed in the electronic device and to display a visualized user interface.

[0155] Only the electronic device with components is shown in the figure, and those skilled in the art can understand that the structure shown in the figure does not constitute a limitation on the electronic device, and the electronic device can include fewer or more components than those shown in the figure, or some components can be combined, or different components can be arranged.

[0156] For example, although not shown, the electronic device can further include a power supply (such as a battery) for supplying power to each component. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, so as to realize functions such as charge management, discharge management and power consumption management through the power management device. The power supply can also include one or more direct current or alternating current power supplies, a recharging device, a power supply fault detection circuit, a power supply converter or inverter, a power supply state indicator, etc. The electronic device can also include various sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be described here.

[0157] It should be understood that the embodiments are only for illustration, and the scope of the patent application is not limited by the structure.

[0158] The region type distinguishing program stored in the memory 11 in the electronic device 1 is a combination of a plurality of instructions, which, when running in the processor 10, can realize:

[0159] Obtain a road network data set and a POI data set of a first target region, divide the road network data set by using a preset road network division algorithm to obtain a block data set, and perform data merging on the block data set and the POI data set to obtain a merged data set;

[0160] Extract block POI data in the merged data set by using a preset electronic fence, and perform category screening on the block POI data according to a preset block category interest demand to obtain an interest POI category;

[0161] Calculate a weighted score value of the interest POI category by using a preset weighting algorithm, and determine whether a commercial sign exists in the merged data set according to the weighted score value, when the commercial sign exists, calculate a category proportion of a commercial type in the interest POI category;

[0162] Determine a region type label of the first target region according to the category proportion and a preset category proportion threshold, construct a random forest model by using the region type label, and distinguish a region type of a preset second target region according to the random forest model.

[0163] Specifically, the specific implementation method of the processor 10 on the above instructions can refer to the description of the related steps in the corresponding embodiment of the accompanying drawings, which will not be described here.

[0164] Further, the modules / units integrated in the electronic device 1 are implemented in the form of software function units and sold or used as independent products, which can be stored in a computer readable storage medium. The computer readable storage medium can be volatile or non-volatile. For example, the computer readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM).

[0165] In several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the modules is only a logical function division, and there can be another division manner in actual implementation.

[0166] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, i.e., may be located in one place, or may be distributed to multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment of the present application according to actual needs.

[0167] In addition, each functional module in various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0168] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0169] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and therefore all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any additional reference signs in the claims should not be considered as limiting the claims involved.

[0170] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence (AI) is to use digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0171] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The plurality of units or devices stated in the system claims can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names and not to indicate any particular order.

[0172] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A regional type discrimination method based on urban road and POI data, characterized in that, The method comprises: S1, acquiring a road network data set and a POI data set of a first target area, dividing the road network data set by using a preset road network division algorithm to obtain a block data set, and merging the block data set with the POI data set to obtain a merged data set; S2, extracting block POI data in the merged data set by using a preset electronic fence, and screening the block POI data according to a preset block category interest demand to obtain an interest POI category, wherein the screening of the block POI data according to the preset block category interest demand to obtain the interest POI category comprises: S21, calculating a public awareness of each POI data in the block POI data according to the following awareness formula: in, For the aforementioned public awareness, For the first The number of cognitive emotions, For cognitive emotions Quantity, For cognitive emotions Quantity, For cognitive emotions Quantity For cognitive emotions Quantity For cognitive emotions Quantity; S22, when the public awareness is less than a preset awareness threshold, removing the POI data corresponding to the public awareness from the block POI data to obtain updated block POI data; S23, when the public awareness is greater than or equal to the preset awareness threshold, screening the POI data in the updated block POI data according to the block category interest demand to obtain the interest POI category; S3, calculating a weighted score value of the interest POI category by using a preset weighting algorithm, judging whether a commercial sign exists in the merged data set according to the weighted score value, and when the commercial sign exists, calculating a category proportion of a commercial type in the interest POI category; S4, determining a regional type label of the first target area according to the category proportion and a preset category proportion threshold, constructing a random forest model by using the regional type label, and judging a regional type of a preset second target area according to the random forest model.

2. The method of claim 1, wherein the method is characterized by, The division of the road network data set by using the preset road network division algorithm to obtain the block data set comprises: performing road screening on roads in the road network data set to obtain screened roads; performing hierarchical division on the screened roads according to a preset road level to obtain hierarchical roads; performing spatial division on the hierarchical roads by using a preset buffer zone to obtain road spaces; removing the road spaces from the road network data set to obtain the block data set. 3.The method of claim 1, wherein, The extraction of the block POI data in the merged data set by using the preset electronic fence comprises: selecting any interest point in the merged data set as a target point; determining fence coordinates of the electronic fence according to the target point; generating a polygon region according to the fence coordinates; extracting POI data in the merged data set by using the polygon region, and collecting the POI data as block POI data. 4.The method of claim 1, wherein, The calculation of the weighted score value of the interest POI category by using the preset weighting algorithm comprises: acquiring a category score value of each interest POI category; determining a category weight of each interest POI category by using a preset analytic hierarchy process; calculating the weighted score value of the interest POI category according to the category score value and the category weight by using the weighting algorithm: wherein, is the weighted score value, is a category score value for a th interest POI category, is a category weight for a th interest POI category, is a number of the interest POI categories. 5.The method of claim 1, wherein, The calculating the category proportion of the business type in the interest POI category comprises: counting a first POI data quantity in each of the interest POI categories, and counting a second POI data quantity in each of the business types in the interest POI category; calculating the category proportion of the business type according to the first POI data quantity and the second POI data quantity by using a category proportion formula as follows: wherein, is the category proportion of the first commercial type, is the category proportion of the first commercial type, is the first POI data quantity of the interest POI category, is the first POI data quantity of the interest POI category, is the second POI data quantity of the commercial type, is the second POI data quantity of the commercial type, is the category quantity of the commercial type.

6. The method of claim 1 to 5, wherein The constructing the random forest model by using the area type label comprises: dividing the area type label by using a preset estimation algorithm to obtain a divided area type label data set; selecting any label feature in each of the divided area type label data sets as a root node, and splitting a left node and a right node in the root node; allocating each of the divided area type label data sets to the left node and the right node to obtain a classification regression tree, and collecting the classification regression tree as the random forest model.

7. The regional type discrimination method based on urban road and POI data according to claim 1, wherein, The area type discrimination of a preset second target area according to the random forest model comprises: obtaining to-be-discriminated area data of the second target area; classifying the to-be-discriminated area data by using each classification regression tree in the random forest model to obtain a classification prediction value; selecting a region with the maximum classification prediction value as the area type of the second target area.

8. An area type discrimination device based on urban road and POI data, characterized by, The device comprises: a data merging module configured to obtain a road network data set and a POI data set of a first target area, divide the road network data set by using a preset road network division algorithm to obtain a block data set, and merge the block data set and the POI data set to obtain a merged data set; a POI category screening module configured to extract block POI data in the merged data set by using a preset electronic fence, and screen categories of the block POI data according to a preset block category interest demand to obtain an interest POI category, wherein the screening of the categories of the block POI data according to the preset block category interest demand to obtain the interest POI category comprises: calculating a public awareness degree of each POI data in the block POI data according to a cognitive degree formula as follows: wherein, is the number of public recognitions, is the number of first is the number of second is the number of third is the number of fourth is the number of fifth is the number of sixth is the number of seventh is the number of eighth is the number of ninth is the number of tenth is the number of eleventh is the number of twelfth when the public awareness degree is less than a preset awareness degree threshold, removing the POI data corresponding to the public awareness degree in the block POI data to obtain updated block POI data; when the public awareness degree is greater than or equal to the preset awareness degree threshold, screening the categories of the POI data in the updated block POI data according to the block category interest demand to obtain the interest POI category; a category proportion calculation module configured to calculate a weighted score value of the interest POI category by using a preset weighting algorithm, determine whether a business sign exists in the merged data set according to the weighted score value, and calculate a category proportion of a business type in the interest POI category when the business sign exists. The region type determination module is configured to determine a region type label of the first target region according to the category proportion and a preset category proportion threshold, construct a random forest model by using the region type label, and determine a region type of a preset second target region according to the random forest model.

9. An electronic device, comprising: The electronic device includes: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the region type determination method based on urban road and POI data according to any one of claims 1 to 7.

Images