Region category estimation method, device, equipment, medium and program product

Abstract

The invention discloses a region category estimation method, device and equipment, a medium and a program product, which can be applied to the map field and the traffic field. The region category estimation method comprises the steps of obtaining a region area of a target region, and detecting whether the region area is located in a preset area range; when the area of the region is in a preset area range, acquiring historical positioning information of the target region in a historical time period; dividing the historical time period into a first time period and a second time period according to the historical positioning information; based on the historical positioning information, the first time period and the second time period, the category of the target area in the target time period is estimated, and the universality of the area classification scheme can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a region category estimation method and device, electronic equipment, computer storage medium and computer program product. BACKGROUND

[0002] Region category estimation has great value. Based on the region category estimation result, resource allocation can be more effectively optimized, development trends can be predicted, and even references or suggestions can be provided in terms of traffic. Region category estimation refers to estimating the flow data such as the passenger flow or vehicle flow of a region at a specified time. For example, predicting the passenger flow of a certain business district at a specified time, predicting the passenger flow of a certain station at a specified time, and the like.

[0003] Current region category estimation schemes mainly rely on video devices to estimate the flow data in a specific range by using videos and / or pictures captured by the video devices. However, in the current region category estimation scheme, for regions not covered by the video devices, direct region category estimation of these regions is not possible, and auxiliary estimation needs to be performed by using the region categories of the surrounding regions of these regions. It can be seen that the current region category estimation scheme has strong limitations. SUMMARY

[0004] Embodiments of the present application provide a region category estimation method and device, electronic equipment, computer readable storage medium and computer program product, which do not need to rely on video devices for region category estimation. For regions not covered by the video devices, direct region category estimation can be performed, thereby improving the universality of the region category estimation scheme.

[0005] In a first aspect, the present application provides a region category estimation method, including:

[0006] obtaining a region area of a target region, and detecting whether the region area is located in a preset area range;

[0007] when the region area is located in the preset area range, obtaining historical positioning information of the target region in a historical period;

[0008] dividing the historical period into a first time period and a second time period according to the historical positioning information;

[0009] estimating a category of the target region in a target period based on the historical positioning information, the first time period and the second time period.

[0010] In a second aspect, the present application further provides a region category estimation device, including:

[0011] The detection module is configured to acquire a region area of the target region, and detect whether the region area is located in a preset area range.

[0012] The acquisition module is configured to acquire historical positioning information of the target region in a historical period when the region area is located in the preset area range.

[0013] The division module is configured to divide the historical period into a first time period and a second time period according to the historical positioning information.

[0014] The estimation module is configured to estimate a category of the target region in a target period based on the historical positioning information, the first time period and the second time period.

[0015] Optionally, in some embodiments of the present application, the division module comprises:

[0016] The acquisition sub-module is configured to acquire historical positioning points of the target region in the historical period from the historical positioning information.

[0017] The division sub-module is configured to divide the historical period into the first time period and the second time period based on the historical positioning points.

[0018] Optionally, in some embodiments of the present application, the division sub-module comprises:

[0019] The acquisition unit is configured to acquire historical positioning points of the target region in the historical period from the historical positioning information.

[0020] The division unit is configured to divide the historical period into the first time period and the second time period based on the historical positioning points.

[0021] Optionally, in some embodiments of the present application, the division unit comprises:

[0022] The calculation sub-unit is configured to calculate a median corresponding to the historical positioning points in the historical period.

[0023] The determination sub-unit is configured to determine a point number corresponding to the historical positioning points in a preset time interval of the historical period.

[0024] The division sub-unit is configured to divide the historical period into the first time period and the second time period based on the median and the point number.

[0025] Optionally, in some embodiments of the present application, the division sub-unit is specifically configured to:

[0026] calculate a median square difference of the historical positioning points in a corresponding preset time interval according to the median and the point number.

[0027] divide the historical time period into a first time period and a second time period based on the median squared difference and a preset clustering algorithm.

[0028] Optionally, in some embodiments of the present application, the dividing subunit is specifically configured to:

[0029] determine an initial clustering center corresponding to the preset clustering algorithm;

[0030] calculate a mean of the median squared difference corresponding to the median value squared difference;

[0031] update the initial clustering center according to the mean of the median squared difference, to obtain a first clustering center and a second clustering center;

[0032] divide the historical time period into a first time period and a second time period according to a first distance between the historical positioning point and the first clustering center, and a second distance between the historical positioning point and the second clustering center.

[0033] Optionally, in some embodiments of the present application, the device further comprises a verification subunit, which is configured to:

[0034] determine a second silhouette score of the historical positioning point belonging to the second clustering center according to the second distance between the historical positioning point and the second clustering center;

[0035] verify the first clustering center and the second clustering center based on the first silhouette score and the second silhouette score;

[0036] The dividing subunit is specifically further configured to: when the verification passes, divide the historical time period into a first time period and a second time period according to a first distance between the historical positioning point and the first clustering center, and a second distance between the historical positioning point and the second clustering center.

[0037] Optionally, in some embodiments of the present application, the first acquisition module is specifically configured to:

[0038] determine newly added regional data, and generate a target region based on the newly added regional data;

[0039] acquire a regional area of the target region according to boundary information of the target region.

[0040] Optionally, in some embodiments of the present application, the first acquisition module is specifically further configured to:

[0041] acquire boundary information of at least one candidate region;

[0042] According to a preset mode, the boundary information of the candidate region is used to store data of the candidate region to a region database.

[0043] Optionally, in some embodiments of the present application, the second obtaining module is specifically configured to:

[0044] When the area is within a preset area range, a historical positioning database is obtained;

[0045] A historical positioning point corresponding to the target region in the historical positioning database is determined as a historical positioning point, and an object identifier corresponding to the historical positioning point is obtained.

[0046] Optionally, in some embodiments of the present application, the estimation module is specifically configured to:

[0047] From the historical positioning information, a historical positioning point and a positioning identifier corresponding to the target region in a historical time period are obtained;

[0048] The falling information of the historical positioning point in a preset time interval of the first time period is determined;

[0049] An average value of the positioning identifier in the first time period is calculated;

[0050] A first point average value corresponding to the historical positioning point in the first time period is calculated, and

[0051] A second point average value corresponding to the historical positioning point in the second time period is calculated;

[0052] According to the falling information, the first point average value and the second point average value, a category of the target region in a target time period is estimated.

[0053] In a third aspect, the embodiments of the present application further provide an electronic device, including a processor and a memory, the memory stores an application program, and the processor is configured to run the application program in the memory to implement the steps in the region category estimation method provided by the embodiments of the present application.

[0054] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium, which stores a plurality of instructions, and the instructions are adapted to be loaded by a processor to execute the steps in the region category estimation method provided by the embodiments of the present application.

[0055] In a fifth aspect, the embodiments of the present application further provide a computer program product, including a computer program or instructions, which are executed by a processor to implement the steps in the region category estimation method provided by the embodiments of the present application.

[0056] The embodiments of the present application provide a method, device, electronic device, computer storage medium and computer program product for estimating area categories. When the area of ​​a target area is obtained and the area of ​​the target area is detected to be within a preset area range, when the area of ​​the target area is within the preset area range, the historical positioning information of the target area in the historical period is obtained. Then, based on the historical positioning information, the historical period is divided into a first time period and a second time period. Finally, based on the historical positioning information, the first time period and the second time period, the category of the target area in the target period is estimated. The area category estimation scheme provided by the present application, when it is detected that the area of ​​the target area is within the preset area range, the historical period is divided into a first time period and a second time period according to the historical positioning information of the target area in the historical period. Finally, based on the historical positioning information, the first time period and the second time period, the category of the target area in the target period is estimated. The entire area category estimation process does not rely on the video or picture taken by the video device, and the estimation of the area classification can be completed. It can be seen that the area category estimation scheme of the present application can adapt to various area category estimation scenarios of different ranges, thereby improving the versatility of the area classification scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0058] Figure 1 This is a schematic diagram of the distributed database system architecture in related technologies;

[0059] Figure 2 Schematic diagram of a scenario of a method for estimating area categories provided in an embodiment of the present application;

[0060] Figure 3 Schematic diagram of the process of estimating the regional category provided in the embodiment of the present application;

[0061] Figure 4 This is another flowchart of the method for estimating area categories provided in an embodiment of the present application;

[0062] Figure 5 Schematic diagram of the structure of the area category estimation device provided in an embodiment of the present application;

[0063] Figure 6 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0064] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments of the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative work fall within the scope of the present application.

[0065] The present application provides a region category estimation method and device, electronic equipment, computer storage medium and computer program product.

[0066] The region category estimation can be integrated in a server or a terminal. The server can be a physical server, a server cluster composed of multiple physical servers, or a distributed system. The server can also be 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, network acceleration services, and basic cloud computing services such as big data and artificial intelligence platforms. The server can be directly or indirectly connected to the terminal through wired or wireless communication. The terminal can be a smartphone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, or the like, but is not limited thereto. The terminal and the server can be directly or indirectly connected through wired or wireless communication, which is not limited in the present application.

[0067] The region category estimation scheme provided by the present application can be applied to an intelligent transportation system. The intelligent transportation system (ITS) is also called an intelligent transportation system (ITS). Advanced scientific and technological methods (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operations research, artificial intelligence, etc.) are effectively integrated into transportation, service control, and vehicle manufacturing to strengthen the connection between vehicles, roads, and users, thereby forming a comprehensive transportation system that ensures safety, improves efficiency, improves the environment, and saves energy.

[0068] For example, refer to Figure 1The present application provides an intelligent transportation system, including an area category estimation device 10 and a traffic planning device 20. The area category estimation device 10 obtains the area of ​​the target area and detects whether the area is within a preset area range. When the area is within the preset area range, the area category estimation device 10 obtains the historical positioning information of the target area in the historical period. Then, the area category estimation device 10 divides the historical period into a first time period and a second time period based on the historical positioning information. Then, the area category estimation device 10 estimates the category of the target area in the target period based on the historical positioning information, the first time period and the second time period. Finally, the area category estimation device 10 sends the category of the target area in the target period to the traffic planning device 20. The traffic planning device 20 generates a traffic plan for the target area in the target period based on the category of the target area in the target period, such as a traffic light switching time, etc., which can specifically indicate the red light duration and the green light duration.

[0069] The area category estimation scheme provided by the present application, when it is detected that the area of ​​the target area is within a preset area range, divides the historical period into a first time period and a second time period according to the historical positioning information of the target area in the historical period. Finally, based on the historical positioning information, the first time period and the second time period, the category of the target area in the target period is estimated. The entire area category estimation process does not rely on the video or picture taken by the video equipment, and the estimation of the area classification can be completed. Therefore, for areas without video equipment coverage, the area category estimation scheme of the present application can also be used to estimate area classification events in real time, thereby improving the estimation efficiency of area classification events. At the same time, the area category estimation scheme of the present application can adapt to area category estimation scenarios of various different ranges.

[0070] For example, see Figure 2 Taking the area category estimation device integrated into the server as an example, when the server detects that the area of ​​the target area is within a preset area range, it divides the historical period into a first time period and a second time period according to the historical positioning information of the target area in the historical period. Finally, based on the historical positioning information, the first time period and the second time period, the category of the target area in the target period is estimated.

[0071] It can be understood that in the specific implementation of this application, related data such as attribute data, attribute sets and attribute subsets are involved. When the following embodiments of this application are applied to specific products or technologies, permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0072] It should be noted that the order of description of the following embodiments is not intended to limit the preferred order of the embodiments.

[0073] The embodiment will be described from the perspective of a region category estimation device, which can be integrated in an electronic device, which can be a server.

[0074] The embodiment of the present application provides a region category estimation method, comprising: obtaining a region area of a target region, and detecting whether the region area is located in a preset area range; when the region area is located in the preset area range, obtaining historical positioning information of the target region in a historical period; dividing the historical period into a first time period and a second time period according to the historical positioning information; and estimating a category of the target region in a target period based on the historical positioning information, the first time period and the second time period.

[0075] Please refer to Figure 3 , Figure 3 The flowchart of the road network processing method provided by the present application is shown. The specific process of the road network processing method can be as follows:

[0076] 101、obtaining a region area of a target region, and detecting whether the region area is located in a preset area range.

[0077] For example, specifically, the target region can be a region corresponding to a cell, a region corresponding to a street or a region corresponding to a city, which can be determined according to actual conditions. Further, the target region is generated by newly added data of a region database. For example, the region database contains a large amount of region data, when the newly added region data is obtained, the target region is generated according to the newly added region data, and then the region area corresponding to the target region can be obtained according to the boundary information of the target region, that is, in some embodiments of the present application, the step of "obtaining a region area of a target region" can specifically include:

[0078] determining newly added region data, and generating a target region based on the newly added region data;

[0079] obtaining a region area of a target region according to boundary information of the target region.

[0080] The boundary information of the target region is used to define the range of the target region, so that the area of the target region can be obtained according to the boundary information of the target region. It should be noted that the Internet electronic map contains two concepts of a point of interest (POI) and an area of interest (AOI). A POI contains at least four basic information: name, address, category, and latitude and longitude coordinates. It can be a house, a shop, a community entrance, or a bus stop, etc. An AOI also contains four basic information, which is mainly used to express regional geographical entities in a map, such as a residential area, a university, an office building, an industrial park, a comprehensive commercial complex, a hospital, a scenic spot, or a stadium, etc. It can be a square, a rectangle, a circle, or any irregular shape. Alternatively, in some embodiments of the present application, the target region is an AOI, so its corresponding boundary can be a square boundary, a rectangular boundary, a circular boundary, or an irregular boundary, depending on the actual situation.

[0081] It should also be noted that the region database can be pre-constructed to store the polygon boundary of the region. The description and storage of the polygon can be stored by latitude and longitude of each vertex, and of course it can also be stored by geometry object (a compiled geographic information object). Alternatively, in some embodiments of the present application, the region category estimation method of the present application can further include:

[0082] Obtaining boundary information of at least one candidate region;

[0083] According to a predetermined manner, the boundary information of the candidate region is stored in the region database.

[0084] Alternatively, in some embodiments of the present application, the candidate region can be an AOI, that is, if the newly added region data is the same as the data stored in the region database, the region corresponding to the newly added region data (i.e. the target region) can be determined according to the data stored in the region database. Therefore, when the region classification method is applied to a real-time intelligent transportation system, there is no need to regenerate the target region, which improves the subsequent data processing efficiency.

[0085] After obtaining the area of the target region, it is detected whether the area of the target region is located in a predetermined area range. If the area of the target region is located in the predetermined area range, step 102 is performed. If the area of the target region is not located in the predetermined area range, that is, the area of the target region is greater than the upper limit of the predetermined area range or less than the lower limit of the predetermined area range, the region category estimation process is not performed.

[0086] It should be noted that, in order to avoid the area of the estimated region being too large or too small when the region category estimation is performed, resulting in the estimated region category not having reference significance, in some embodiments of the present application, the estimated area range can be set in advance, for example, the lower limit of the area range is set as:

[0087] area_min≤area(target region)≤area_max

[0088] Wherein, area_min and area_max are minimum and maximum values corresponding to the area range. Generally, area_min=10000 square meters and area_max=100000 square meters. The maximum and minimum values can also be set according to actual needs.

[0089] 102、When the area of the region is in the preset area range, the historical positioning information of the target region in the historical period is obtained.

[0090] When the area of the region is in the preset area range, it indicates that the target region meets the condition for region category estimation, and at this time, the historical positioning information of the target region in the historical period can be obtained, which can include historical positioning points and object identifiers corresponding to the historical positioning points, that is, optionally, in some embodiments of the present application, the step of "when the area of the region is in the preset area range, the historical positioning information of the target region in the historical period is obtained" can specifically include:

[0091] When the area of the region is in the preset area range, the historical positioning database is obtained;

[0092] The positioning of the historical positioning database in the target region is determined as a historical positioning point, and the object identifier corresponding to the historical positioning point is obtained.

[0093] Wherein, the historical positioning database can be a car positioning database, which is used to save the positioning of the car, or a device positioning data, which can be a mobile phone, a tablet computer or a notebook computer, and the specific selection can be made according to actual conditions, for example, in the scene of intelligent transportation, the historical positioning data can be a car positioning database.

[0094] The historical period is a period before the region category estimation operation is triggered, and the range of the historical period can be set by an engineer, for example, 3 days, 7 days or 15 days, and the embodiments of the present application do not limit this.

[0095] In the target area, there can be a case that one object identification corresponds to multiple historical positioning points, or a case that one object identification corresponds to one historical positioning point. For example, for a car A, the corresponding object identification is A, and the historical positioning points generated in the target area include positioning point a1, positioning point a2, positioning point a3, positioning point a4 and positioning point a5, that is, A corresponds to positioning point a1, positioning point a2, positioning point a3, positioning point a4 and positioning point a5; for example, for a car B, the corresponding object identification is B, and the historical positioning point generated in the target area is positioning point b, so in the target area and in the historical period, the historical positioning point corresponding to B is positioning point b.

[0096] 103. dividing the historical period into a first time period and a second time period according to the historical positioning information.

[0097] From the foregoing description, it can be known that the historical positioning information includes historical positioning points and object identifications, and in the embodiments of the present application, the historical period can be divided into a first time period and a second time period by the historical positioning points, wherein the first time period is a time period belonging to a first classification in the historical period, and the second time period is a time period belonging to a second classification in the historical period, and the first classification and the second classification can be pre-set. Alternatively, in some embodiments of the present application, the first classification can be a peak classification, and the second classification can be a low estimation classification, that is, the first time period can be a peak period, and the second time period can be a low estimation period. For example, the historical period can be divided into a first time period and a second time period according to the number of historical positioning points, for example, a time period in which the number of positioning points in one hour is greater than 1h / 1000 vehicles is determined as the first time period, and the remaining time periods are determined as the second time period, that is, the step of “dividing the historical period into a first time period and a second time period according to the historical positioning information” can specifically include:

[0098] obtaining the historical positioning point corresponding to the target area in the historical period from the historical positioning information;

[0099] dividing the historical period into a first time period and a second time period based on the historical positioning point.

[0100] It should be noted that the historical period is divided into the first time period and the second time period directly by using the number of historical positioning points, and the first time period and the second time period divided are extremely susceptible to maximum or minimum values, that is, the historical positioning points of the a period are 1000, the historical positioning points of the b period are 300, and the positioning points of the c period are 100, and if only the number of historical positioning points is used, the a period may be determined as the first time period, and the b period and the c period are determined as the second time period, and in an actual scene, the a period and the b period are both time periods in which the flow classification of the target region in the historical period is large, and therefore, in some embodiments of the present application, the historical period is divided into the first time period and the second time period by using the median corresponding to the historical positioning points, that is, the step of "dividing the historical period into the first time period and the second time period based on the historical positioning points" can specifically include:

[0101] The median corresponding to the historical positioning points in the historical period is calculated.

[0102] The number of points corresponding to the historical positioning points in a preset time interval of the historical period is determined.

[0103] The historical period is divided into the first time period and the second time period based on the median and the number of points.

[0104] It should be noted that the median is obtained by sorting, and it is not affected by the maximum and minimum extreme values. The variation of part of the data has no effect on the median, and when individual data in a group of data varies greatly, therefore, the historical period is divided into the first time period and the second time period by using the median corresponding to the historical positioning points.

[0105] The historical period can be divided into the first time period and the second time period by using a preset clustering algorithm, the median corresponding to the historical positioning points, and the number of points, for example, the median squared difference of the historical positioning points in the preset time interval can be calculated based on the median and the number of points, and then the historical period is divided into the first time period and the second time period according to the preset clustering algorithm and the median squared difference, that is, in some embodiments of the present application, the step of "dividing the historical period into the first time period and the second time period based on the median and the number of points" can specifically include:

[0106] An initial clustering center corresponding to the preset clustering algorithm is determined.

[0107] The median squared difference corresponding to the median squared difference is calculated.

[0108] The initial clustering center is updated according to the median squared difference mean to obtain the first clustering center and the second clustering center.

[0109] The historical period is divided into a first time period and a second time period according to a first distance between the historical positioning point and the first cluster center and a second distance between the historical positioning point and the second cluster center.

[0110] For example, specifically, the median square difference in the preset time interval is calculated according to the number of point positions corresponding to the historical positioning point and the median corresponding to the historical positioning point, and can be specifically represented by the following formula:

[0111] x p =(PV p –PV_median) 2

[0112] Wherein, x p is the median square difference in the preset time interval p, PV p is the number of historical positioning points in the target area in the preset time interval p, and PV_median is the median of the number of historical positioning points of the target area at all times.

[0113] It should be noted that the length of the preset time interval is the same as the length of the first time period and the second time period, that is, the preset time interval is one hour, and the first time period and the second time period are also one hour.

[0114] Further, the median square difference of the target area at all time points is classified by an unsupervised clustering method, the clustering algorithm can adopt a one-dimensional K-means clustering algorithm, the classification number is set to 2, and the clustering of each historical positioning point to the cluster center is calculated by using the Euclidean algorithm, which is specifically as follows:

[0115] Put into the following formula, the point set of the i-th class in the t-th iteration is recorded as

[0116]

[0117] Wherein, is the median square difference on the i-th cluster center in the t-th iteration, k is the total number of classifications, k=2, is the median square difference on the j-th cluster center in the t-th iteration, and the physical meaning of this step is that all historical positioning points are classified into the class to which the cluster center point closest to them belongs.

[0118] Then, the above process is executed again to recalculate the cluster center, that is, the centroid of the i-th class in the t+1-th iteration is calculated as the average of the median square differences of all points assigned to the i-th class in the t-th iteration, which is specifically as follows:

[0119]

[0120] For the initial allocation state before the first iteration (i.e. algorithm initialization), a completely random classification method can be used to randomly allocate all positioning points to two cluster centers, and then start the iteration of the above two-step algorithm. When the points in the two cluster centers are unchanged after the algorithm iteration, or when the iteration is N times (N is determined according to the calculation efficiency and accuracy requirements, such as N is 100), the algorithm is stopped, and the classification result vector of each point is output in a vector manner according to the mean size of the two classes. Assuming that the mean of the class with the higher mean in the classification result is m_higher, and the mean of the class with the lower mean is m_lower, the classification result vector is:

[0121] {res_p | res_p = 1 if (res_p - m_higher) ^ 2 ≥ (res_p - m_lower) 2 else 0}

[0122] In the formula, res_p is the classification result of the pth preset time interval, and takes the value of 0 or 1.

[0123] In addition, the tightness and discrimination of the clustering result can be evaluated by the silhouette score, so as to improve the accuracy of subsequent classification, that is, optionally, in some embodiments, the regional category estimation method of the application can further include:

[0124] determining a first silhouette score of the historical positioning point belonging to the first cluster center according to a first distance between the historical positioning point and the first cluster center, and;

[0125] determining a second silhouette score of the historical positioning point belonging to the second cluster center according to a second distance between the historical positioning point and the second cluster center;

[0126] verifying the first cluster center and the second cluster center based on the first silhouette score and the second silhouette score.

[0127] It should be noted that the silhouette score (SC) is used to evaluate the tightness and discrimination of the clustering result, and its value range is from -1 to 1, wherein 1 indicates that the tightness and discrimination of the clustering result are very good, and -1 indicates that the clustering result is very poor, that is, the closer SC is to 1, the better the classification effect is, and the calculation formula is as follows:

[0128] SC_p = (b_p - a_p) / max(a_p, b_p)

[0129] Wherein, a_p is the average distance from all other points in the class of point p to point p, and b_p is the minimum distance from point p to another class of points, which are calculated as follows:

[0130] a_p = sum((x_p - x_i)^2) / (N_1 - 1)

[0131] b_p = min((x_p - x_j)^2)

[0132] where x_i is any other point in the same class as point p, N is the number of points in the class of p; x_j is any point in another class (i.e. the class that does not contain point p), and for SC of a classification result, the calculation is the average of SC of all points.

[0133] 104. Estimate the category of the target area in the target period based on the historical positioning information, the first time period and the second time period.

[0134] Optionally, in some embodiments of the present application, after the first clustering center and the second clustering center pass the verification, the category of the target area in the target period is estimated based on the historical positioning information, the first time period and the second time period.

[0135] Further, the corresponding time period of res_p = 1 in step 103 can be defined as the peak time period, and the remaining time points can be defined as the valley time period, and then whether the result set satisfies the following preset conditions is detected respectively.

[0136] (1) Time determination condition:

[0137] The minimum time point (lower limit value of the first time period) of the peak time period (i.e. the first time period) is greater than or equal to a preset time, such as 12:00, and all time points of the peak time period are continuous time points (i.e. single peak);

[0138] (2) Device number and positioning number determination condition:

[0139] The average number of object identifiers in the peak time period (the first time period) is greater than or equal to a preset number, such as 250;

[0140] (3) Device number density determination condition:

[0141] The unit area object identifier density of the target area in the peak time period is within a preset interval, such as [2500, 50000];

[0142] (4) Rapid dispersion condition determination condition:

[0143] Within three hours after the peak, the decline rate (rel_pv_diff) of the historical positioning points and the actual value of the decline of the historical positioning points (pv_diff) are determined, and any of the following conditions is satisfied:

[0144] Condition 1: Rel_pv_diff >= 90% and pv_diff >= 90;

[0145] Condition 2: rel_pv_diff >= 75% and pv_diff >= 200;

[0146] Condition 3: rel_pv_diff >= 50% and pv_diff >= 500;

[0147] It should be noted that the falling rate Wherein, P t1 is the number of historical positioning points at t1 moment, P t2 is the number of historical positioning points at t2 moment, P t1 -P t2 is the falling actual value (pv_diff).

[0148] (5) Classification effect comprehensive judgment condition:

[0149] Calculate the ratio (pv_ratio) of the number of flat historical positioning points pv_high in peak period and the average number of historical positioning points pv_low in trough period, and the difference (m_dist) between the first clustering center C_high and the second clustering center C_low:

[0150] Pv_ratio = pv_high / pv_low

[0151] Pv_dist = C_high - C_low

[0152] The classification effect comprehensive judgment condition is to satisfy any of the following conditions:

[0153] Condition 1: when the classification result SC >= 0.9, satisfy: pv_ratio >= 10 or m_dist >= 1000^2;

[0154] Condition 2: when the classification result 0.83 <= SC < 0.9, satisfy: pv_ratio >= 120 or m_dist >= 3000^2;

[0155] Condition 3: when the classification result 0.8 <= SC < 0.83, satisfy: pv_ratio >= 120 or m_dist >= 4000^2.

[0156] Optionally, in some embodiments of the present application, the step of "estimating the category of the target area in the target period based on historical positioning information, the first time period and the second time period" can be specifically used for:

[0157] Determining the falling information of the historical positioning points in the preset time interval of the first time period;

[0158] Calculating the average value of the positioning identifier corresponding to the identifier in the first time period;

[0159] calculate a first point average value corresponding to the historical positioning points in the first time period, and

[0160] calculate a second point average value corresponding to the historical positioning points in the second time period;

[0161] estimate the category of the target region in the target time period according to the falling information, the first point average value and the second point average value.

[0162] The target region can be divided into a large-scale activity region and a non-large-scale activity region. Optionally, in some embodiments of the present application, if the target region meets all the preset conditions, it is determined that the classification of the target region is a large-scale activity region, otherwise, it is a non-large-scale activity region.

[0163] The above is the region category estimation process of the embodiments of the present application.

[0164] The embodiments of the present application provide a region category estimation method. After obtaining the region area of a target region and detecting whether the region area is located in a preset area range, when the region area is located in the preset area range, historical positioning information of the target region in a historical time period is obtained, then the historical time period is divided into a first time period and a second time period according to the historical positioning information, and finally, the category of the target region in a target time period is estimated based on the historical positioning information, the first time period and the second time period. The region category estimation scheme provided by the present application, when the region area of the target region is detected to be located in the preset area range, the historical time period is divided into a first time period and a second time period according to the historical positioning information of the target region in the historical time period, and finally, the category of the target region in a target time period is estimated based on the historical positioning information, the first time period and the second time period. The entire region category estimation process does not depend on the video or picture captured by the video device, and the estimation of the region category can be completed. It can be seen that the region category estimation scheme of the present application can adapt to various region category estimation scenarios of different ranges, and improve the universality of the region category scheme.

[0165] Please refer to Figure 4 In order to facilitate understanding of the region category estimation scheme of the present application, the determination of the online large-scale activity region is taken as an example for illustration, as follows:

[0166] First, a real-time scanning area database (AOI database) is scanned, and the scanning result is compared with the result of the last scan to determine the identification and boundary information of the newly input AOI. For the newly input AOI, the area is determined, and if the area of the AOI is within a preset area range, the historical positioning points and object identification of the AOI on each day of the last week are obtained. Subsequently, a large event area determination process is performed, that is, the median of the historical positioning points corresponding to each day of the last week is calculated, and the number of points corresponding to the historical positioning points in each hour of the day is determined. Then, the initial clustering center corresponding to the preset clustering algorithm is determined, and the median square difference corresponding to the median square difference is calculated. Next, the initial clustering center is updated according to the median square difference, to obtain a first clustering center and a second clustering center. Finally, the historical period is divided into a first time period and a second time period according to the first distance between the historical positioning points and the first clustering center, and the second distance between the historical positioning points and the second clustering center, and whether the AOI is a large event area is determined according to the first time period and the second time period. If the determination result is yes, the loop is exited, and the determination result of the AOI is yes. If the determination result is no, the step of obtaining the historical positioning points and object identification of the AOI on each day of the last week is performed. If the set number of loops (set to 12 in the embodiment of the present application, but can also be set according to efficiency and accuracy requirements) is reached, the loop is exited, and the AOI determination result is no.

[0167] To better implement the above method, the embodiment of the present application also provides a region category estimation device, as shown in Figure 5 The region category estimation device can include a first acquisition module 301, a detection module 302, a second acquisition module 303, a division module 304, and an estimation module 305, as follows:

[0168] The first acquisition module 301 is configured to acquire the area of the target region.

[0169] For example, specifically, the target region can be a region corresponding to a certain cell, a region corresponding to a certain street, or a region corresponding to a certain city, which can be determined according to actual conditions. Further, the target region is generated by newly added data of the region database.

[0170] Optionally, in some embodiments of the present application, the first acquisition module 301 can be specifically configured to determine newly added region data, and generate a target region based on the newly added region data; and acquire the area of the target region based on the boundary information of the target region.

[0171] Optionally, in some embodiments of the present application, the first obtaining module 301 can be further configured to: obtain boundary information of the at least one candidate region; and store data of the candidate region into a region database according to the boundary information of the candidate region in a preset manner.

[0172] The detection module 302 is configured to detect whether the area of the region is within a preset area range.

[0173] In order to avoid the area of the estimated region being too large or too small when the region category is estimated, which results in that the estimated region category is not meaningful, in some embodiments of the present application, a preset area range can be set, for example, the lower limit of the area range is set as:

[0174] area_min≤area(target region)≤area_max

[0175] wherein area_min and area_max are minimum and maximum values of the area range respectively. Generally, area_min=10000 square meters and area_max=100000 square meters. The maximum and minimum values can also be set according to actual requirements.

[0176] The second obtaining module 303 is configured to obtain historical positioning information of the target region in a historical period when the area of the region is within the preset area range.

[0177] When the area of the region is within the preset area range, it indicates that the target region meets the condition for estimating the region category, and at this time, the historical positioning information of the target region in the historical period can be obtained, which can include historical positioning points and object identifiers corresponding to the historical positioning points.

[0178] Optionally, in some embodiments of the present application, the second obtaining module 303 can be configured to:

[0179] obtain a historical positioning database when the area of the region is within the preset area range;

[0180] determine a positioning of the historical positioning database in the target region as a historical positioning point, and obtain an object identifier corresponding to the historical positioning point.

[0181] The division module 304 is configured to divide the historical period into a first time period and a second time period according to the historical positioning information.

[0182] In the embodiments of the present application, the historical period can be divided into a first time period and a second time period by the historical positioning point, the first time period is a time period belonging to a first classification in the historical period, the second time period is a time period belonging to a second classification in the historical period, and the first classification and the second classification can be pre-set. Optionally, in some embodiments of the present application, the first classification can be a peak classification, and the second classification can be a low estimation classification, that is, the first time period can be a peak period, and the second time period can be a low estimation period.

[0183] Optionally, in some embodiments of the present application, the division module 304 can specifically include:

[0184] The acquisition sub-module is configured to acquire the historical positioning point of the target area in the historical period from the historical positioning information.

[0185] The division sub-module is configured to divide the historical period into a first time period and a second time period based on the historical positioning point.

[0186] Optionally, in some embodiments of the present application, the division sub-module can specifically include:

[0187] The acquisition unit is configured to acquire the historical positioning point of the target area in the historical period from the historical positioning information.

[0188] The division unit is configured to divide the historical period into a first time period and a second time period based on the historical positioning point.

[0189] Optionally, in some embodiments of the present application, the division unit includes:

[0190] The calculation sub-unit is configured to calculate the median corresponding to the historical positioning point in the historical period.

[0191] The determination sub-unit is configured to determine the number of points corresponding to the historical positioning point in a preset time interval of the historical period.

[0192] The division sub-unit is configured to divide the historical period into a first time period and a second time period based on the median and the number of points.

[0193] Optionally, in some embodiments of the present application, the division sub-unit can be specifically used for:

[0194] According to the median and the number of points, the median squared difference of the historical positioning point in the corresponding preset time interval is calculated.

[0195] The historical period is divided into a first time period and a second time period based on the median squared difference and a preset clustering algorithm.

[0196] Optionally, in some embodiments of the present application, the division sub-unit can be specifically used for:

[0197] determining an initial clustering center corresponding to the preset clustering algorithm;

[0198] calculating a median square difference mean corresponding to a median square difference;

[0199] updating the initial clustering center according to the median square difference mean, to obtain a first clustering center and a second clustering center;

[0200] dividing the historical period into a first time period and a second time period according to a first distance between the historical positioning point and the first clustering center, and a second distance between the historical positioning point and the second clustering center.

[0201] Optionally, in some embodiments of the present application, the area category estimation apparatus of the present application can further include a verification subunit, which is configured to: determine a second silhouette score of the historical positioning point belonging to the second clustering center according to the second distance between the historical positioning point and the second clustering center; and verify the first clustering center and the second clustering center based on the first silhouette score and the second silhouette score.

[0202] The dividing subunit is further configured to: when the verification is passed, divide the historical period into the first time period and the second time period according to the first distance between the historical positioning point and the first clustering center, and the second distance between the historical positioning point and the second clustering center.

[0203] The estimation module 305 is configured to estimate a category of a target area in a target period based on historical positioning information, the first time period and the second time period.

[0204] Optionally, in some embodiments of the present application, when the verification of the first clustering center and the second clustering center is passed, the category of the target area in the target period is estimated based on the historical positioning information, the first time period and the second time period.

[0205] Optionally, in some embodiments of the present application, the estimation module 305 is specifically configured to:

[0206] obtain a historical positioning point and a positioning identifier of the target area in the historical period from the historical positioning information;

[0207] determine falling information of the historical positioning point in a preset time interval of the first time period;

[0208] calculate an identifier average value corresponding to the positioning identifier in the first time period;

[0209] calculate a first point average value corresponding to the historical positioning point in the first time period; and

[0210] calculate a second point average value corresponding to the historical positioning point in the second time period.

[0211] According to the falling information, the first point average and the second point average, a category of the target region in the target period is estimated.

[0212] As can be seen from the above, the embodiment of the application provides a region category estimation device, the first acquisition module 301 acquires the region area of the target region, the detection module 302 detects whether the region area is located in the preset area range, when the region area is located in the preset area range, the second acquisition module 303 acquires the historical positioning information of the target region in the historical period, then, the division module 304 divides the historical period into the first time period and the second time period according to the historical positioning information, finally, the estimation module 305 estimates the category of the target region in the target period based on the historical positioning information, the first time period and the second time period. The region category estimation scheme provided by the application is when it is detected that the region area of the target region is located in the preset area range, the historical period is divided into the first time period and the second time period according to the historical positioning information of the target region in the historical period, finally, the category of the target region in the target period is estimated based on the historical positioning information, the first time period and the second time period. The whole region category estimation process does not depend on the video or picture shot by the video device, and the estimation of the region category can be completed. It can be seen that the region category estimation scheme of the application can adapt to various region category estimation scenes of different ranges, and the universality of the region category scheme is improved.

[0213] The embodiment of the application also provides an electronic device, as shown in the figure, which shows a structural schematic diagram of the electronic device related to the embodiment of the application, in particular: Figure 6 As shown in the figure, which shows a structural schematic diagram of the electronic device related to the embodiment of the application, in particular:

[0214] The electronic device can include a processor 401 with one or more processing cores, a memory 402 with one or more computer readable storage media, a power supply 403 and an input unit 404 and the like. Those skilled in the art can understand that the structure of the electronic device shown in the figure does not constitute a limitation on the electronic device, and can include more or fewer components than the figure, or combine certain components, or different component arrangements. Among them: Figure 6 The structure of the electronic device shown in the figure does not constitute a limitation on the electronic device, and can include more or fewer components than the figure, or combine certain components, or different component arrangements. Among them:

[0215] The processor 401 is the control center of the electronic device, connects each part of the entire electronic device by various interfaces and lines, and performs various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 402 and calling data stored in the memory 402. Optionally, the processor 401 can include one or more processing cores; preferably, the processor 401 can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application program, and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 401.

[0216] The memory 402 can be used to store software programs and modules, and the processor 401 executes various functions and areas by running the software programs and modules stored in the memory 402. The memory 402 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), and the like; the data storage area can store data created according to the use of the electronic device, etc. In addition, the memory 402 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device. Accordingly, the memory 402 can also include a memory controller to provide access for the processor 401 to the memory 402.

[0217] The electronic device also includes a power supply 403 for supplying power to each component, and preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 403 can also include one or more than one direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power state indicator, and any other components.

[0218] The electronic device can also include an input unit 404, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0219] Although not shown, the electronic device can also include a display unit, etc., which will not be described here. Specifically, in the present embodiment, the processor 401 in the electronic device will load the executable file corresponding to the process of one or more than one application program into the memory 402 according to the following instructions, and run the application program stored in the memory 402 by the processor 401, so as to realize various functions, as follows:

[0220] acquire a region area of the target region, and detect whether the region area is located in a preset area range; when the region area is located in the preset area range, acquire historical positioning information of the target region in a historical period; divide the historical period into a first time period and a second time period according to the historical positioning information; and estimate a category of the target region in a target period based on the historical positioning information, the first time period and the second time period.

[0221] Optionally, in some embodiments of the present application, based on the scheduling information of the target access layer, the target access layer is processed, and when the region category estimation request is processed according to the processed target access layer, the processor 401 is specifically configured to:

[0222] When the target access layer has a fault, a temporary access layer is determined in the multiple access layers, and the region category estimation request is sent to the temporary access layer;

[0223] The region category estimation request is processed according to the temporary access layer, and when the temporary access layer establishes communication with the target access layer, the region category estimation request is sent from the temporary access layer to the target access layer.

[0224] Optionally, in some embodiments of the present application, the processor 401 is specifically configured to:

[0225] When the region area is located in the preset area range, a historical positioning database is acquired;

[0226] A positioning of the historical positioning database located in the target region is determined as a historical positioning point, and an object identifier corresponding to the historical positioning point is acquired.

[0227] Optionally, in some embodiments of the present application, the processor 401 is specifically configured to:

[0228] Newly added region data is determined, and a target region is generated based on the newly added region data;

[0229] According to the boundary information of the target region, a region area of the target region is acquired.

[0230] Optionally, in some embodiments of the present application, the processor 401 is specifically configured to:

[0231] From the historical positioning information, a historical positioning point corresponding to the target region in the historical period is acquired;

[0232] Based on the historical positioning point, the historical period is divided into a first time period and a second time period.

[0233] Optionally, in some embodiments of the present application, the processor 401 is specifically configured to:

[0234] In the historical period, a median corresponding to the historical positioning point is calculated.

[0235] determine a number of point-of-interest corresponding to the historical location point in a preset time interval of the historical period;

[0236] divide the historical period into a first time period and a second time period based on the median and the number of point-of-interest.

[0237] Optionally, in some embodiments of the present application, the processor 401 is specifically configured to:

[0238] determine an initial clustering center corresponding to a preset clustering algorithm;

[0239] calculate a median squared difference mean corresponding to a median squared difference;

[0240] update the initial clustering center according to the median squared difference mean to obtain a first clustering center and a second clustering center;

[0241] divide the historical period into a first time period and a second time period according to a first distance between the historical location point and the first clustering center and a second distance between the historical location point and the second clustering center.

[0242] Optionally, in some embodiments of the present application, the processor 401 is specifically configured to:

[0243] determine a first silhouette score of the historical location point belonging to the first clustering center according to a first distance between the historical location point and the first clustering center, and;

[0244] determine a second silhouette score of the historical location point belonging to the second clustering center according to a second distance between the historical location point and the second clustering center;

[0245] verify the first clustering center and the second clustering center based on the first silhouette score and the second silhouette score.

[0246] Optionally, in some embodiments of the present application, the processor 401 is specifically configured to:

[0247] determine falling information of the historical location point in a preset time interval of the first time period;

[0248] calculate an identification average value corresponding to the location identification in the first time period;

[0249] calculate a first point-of-interest average value corresponding to the historical location point in the first time period, and;

[0250] calculate a second point-of-interest average value corresponding to the historical location point in the second time period;

[0251] According to the falling information, the first point average value and the second point average value, a category of the target region in a target period is estimated.

[0252] The electronic device provided in the embodiments of the present application acquires the area of the target region and detects whether the area is in a preset area range. When the area is in the preset area range, the electronic device acquires historical positioning information of the target region in a historical period. Then, according to the historical positioning information, the historical period is divided into a first time period and a second time period. Finally, based on the historical positioning information, the first time period and the second time period, a category of the target region in a target period is estimated. The region category estimation scheme provided in the present application detects whether the area of the target region is in the preset area range. When the area is in the preset area range, the historical positioning information of the target region in the historical period is used to divide the historical period into the first time period and the second time period. Finally, based on the historical positioning information, the first time period and the second time period, a category of the target region in a target period is estimated. The entire region category estimation process does not depend on a video or a picture captured by a video device, and the estimation of the region category can be completed. It can be seen that the region category estimation scheme provided in the present application can be adapted to various region category estimation scenarios of different ranges, and the universality of the region category estimation scheme is improved.

[0253] The specific implementation of each operation can be seen from the foregoing embodiments, which will not be described here.

[0254] The computer readable storage medium can include a read only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0255] The computer readable storage medium stores instructions, and the instructions can be used to execute the steps of any of the region category estimation methods provided in the embodiments of the present application. Therefore, the beneficial effects of any of the region category estimation methods provided in the embodiments of the present application can be achieved. Details can be seen from the foregoing embodiments, which will not be described here.

[0256] According to an aspect of the present application, a computer program product or a computer program is provided, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium. The processor executes the computer instructions, so that the computer device executes the method provided in any of the various optional implementation manners of the region category estimation aspect.

[0257] The above describes in detail a regional category estimation method, device, electronic device, computer readable storage medium and computer program product provided by the embodiments of the present application. The principles and implementation manners of the present application are described by applying specific examples. The above description of the embodiments is only used to help understand the method of the present application and its core idea. Meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manners and application ranges will be changed. In conclusion, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method of area category estimation, characterized by, The method comprises the following steps: acquiring a region area of a target region, and detecting whether the region area is within a preset area range; when the region area is within the preset area range, acquiring historical positioning information of the target region in a historical period; dividing the historical period into a first time period and a second time period according to the historical positioning information; estimating a category of the target region in a target period based on the historical positioning information, the first time period and the second time period.

2. The region class estimation method according to claim 1, characterized by, The step of dividing the historical period into a first time period and a second time period according to the historical positioning information comprises the following steps: acquiring historical positioning points of the target region in the historical period from the historical positioning information; dividing the historical period into a first time period and a second time period based on the historical positioning points.

3. The region class estimation method according to claim 2, characterized by, The step of dividing the historical period into a first time period and a second time period based on the historical positioning points comprises the following steps: calculating a median corresponding to the historical positioning points in the historical period; determining a number of points corresponding to the historical positioning points in a preset time interval of the historical period; dividing the historical period into a first time period and a second time period based on the median and the number of points.

4. The region class estimation method according to claim 3, characterized by, The step of dividing the historical period into a first time period and a second time period based on the median and the number of points comprises the following steps: calculating a median squared difference of the historical positioning points in a corresponding preset time interval according to the median and the number of points; dividing the historical period into a first time period and a second time period based on the median squared difference and a preset clustering algorithm.

5. The region class estimation method according to claim 4, characterized by, The step of dividing the historical period into a first time period and a second time period based on the median squared difference and a preset clustering algorithm comprises the following steps: determining an initial clustering center corresponding to the preset clustering algorithm; calculating a mean value of the median squared difference corresponding to the median squared difference; updating the initial clustering center according to the mean value of the median squared difference to obtain a first clustering center and a second clustering center; dividing the historical period into a first time period and a second time period according to a first distance between the historical positioning points and the first clustering center and a second distance between the historical positioning points and the second clustering center.

6. The region class estimation method according to claim 5, characterized by, The method further comprises the following steps: determining a first silhouette score of the historical positioning points belonging to the first clustering center according to the first distance between the historical positioning points and the first clustering center; and determining a second silhouette score of the historical positioning points belonging to the second clustering center according to the second distance between the historical positioning points and the second clustering center; verifying the first clustering center and the second clustering center based on the first silhouette score and the second silhouette score. The first distance between the historical positioning point and the first cluster center and the second distance between the historical positioning point and the second cluster center are used to divide the historical period into a first time period and a second time period, including: when the verification passes, the first distance between the historical positioning point and the first cluster center and the second distance between the historical positioning point and the second cluster center are used to divide the historical period into a first time period and a second time period.

7. The region class estimation method according to any one of claims 1 to 6, characterized by, The area of the target region is obtained, including: New region data is determined, and the target region is generated based on the new region data; The area of the target region is obtained according to the boundary information of the target region.

8. The region class estimation method according to claim 7, characterized by, Before the new region data is determined and the target region is generated based on the new region data, the method further includes: Boundary information of at least one candidate region is obtained; The boundary information of the candidate region is stored in the region database according to a preset mode.

9. The region class estimation method according to any one of claims 1 to 6, characterized by, When the area of the target region is located in a preset area range, historical positioning information of the target region in a historical period is obtained, including: When the area of the target region is located in a preset area range, a historical positioning database is obtained; The positioning of the target region in the historical positioning database is determined as a historical positioning point, and an object identifier corresponding to the historical positioning point is obtained.

10. The region class estimation method according to Claim 1, characterized by, The category of the target region in a target period is estimated based on the historical positioning information, a first time period and a second time period, including: The historical positioning point corresponding to the target region in a historical period is obtained from the historical positioning information; The falling information of the historical positioning point in a preset time interval of the first time period is determined; The average value of the identifier corresponding to the positioning identifier in the first time period is calculated; The first point average value corresponding to the historical positioning point in the first time period is calculated, and The second point average value corresponding to the historical positioning point in the second time period is calculated; The category of the target region in a target period is estimated according to the falling information, the first point average value and the second point average value.

11. A region category estimation device characterized by comprising: Including: The first acquisition module is used for obtaining the area of the target region; The detection module is used for detecting whether the area of the target region is located in a preset area range; The second acquisition module is used for obtaining the historical positioning information of the target region in a historical period when the area of the target region is located in a preset area range; The division module is used for dividing the historical period into a first time period and a second time period according to the historical positioning information; The estimation module is used for estimating the category of the target region in a target period based on the historical positioning information, a first time period and a second time period.

12. The region category estimation device according to claim 11, wherein The division module includes: The acquisition submodule is used for obtaining the historical positioning point corresponding to the target region in a historical period from the historical positioning information; The division submodule is used for dividing the historical period into a first time period and a second time period based on the historical positioning point.

13. An electronic device, comprising: The computer program or instructions, when executed by the processor, implement the steps of the area category estimation method according to any one of claims 1-10.

14. A computer-readable storage medium, characterized in that, The computer program or instructions, when executed by the processor, implement the steps of the area category estimation method according to any one of claims 1-10.

15. A computer program product comprising computer programs or instructions, characterized in that, The computer program or instructions, when executed by the processor, implement the steps of the area category estimation method according to any one of claims 1-10.

Images