Target population selection method, device, electronic device and storage medium

Abstract

The present application relates to the field of Internet technology, and in particular to a method, device, electronic device, and storage medium for selecting a target population. The method comprises: crawling the parking location data of all vehicles within a target range; identifying at least one hotspot location where the number of vehicle parking times is greater than a preset number based on the parking location data; determining a valid hotspot location that meets a preset target condition among the at least one hotspot location, clustering the valid hotspot locations of all vehicles to obtain the center point of the valid hotspot, and selecting a target population within a preset area around the center point. This solves the problems of manually selecting a target population in the related art, which leads to poor selection accuracy, narrow radiation range, low sustainability, and poor user experience.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a method, device, electronic device, and storage medium for selecting a target population. Background Art

[0002] One of the most important factors in car sales is the accurate selection of target groups. Target groups refer to potential customers who may purchase cars. Therefore, accurate selection of target groups can effectively increase car sales.

[0003] In the prior art, car dealers primarily acquire customers through in-store visits, phone calls, auto shows, and referrals from friends. However, while some customers may be high-potential and have a high conversion rate, their reach is narrow, resulting in low sustainability in car sales. This makes it difficult to efficiently and accurately target these customers, leading to a poor user experience. Summary of the Invention

[0004] The present application provides a method, device, electronic device and storage medium for selecting a target population to solve the problems in the related art of manually selecting a target population, resulting in poor selection accuracy, narrow radiation range, low sustainability and poor user experience.

[0005] A first aspect of the present application provides a method for selecting a target population, comprising the following steps: crawling parking location data of all vehicles within a target range; identifying at least one hotspot location where the vehicle has been parked more than a preset number of times based on the parking location data; determining a valid hotspot location that meets a preset target condition among the at least one hotspot location, clustering the valid hotspot locations of all vehicles to obtain a center point of the valid hotspot, and selecting a target population within a preset area around the center point.

[0006] Furthermore, determining the effective hotspot location that meets the preset target conditions in the at least one hotspot location includes: grouping according to the number of parking location data, and extracting the same number of vehicles from each group to form a sample set to be tested; clustering the hotspot location of each vehicle in the sample set to be tested to obtain an effective hotspot location; calculating the effective hotspot ratio of each group, and determining the minimum data volume of the parking location data of each vehicle based on the effective hotspot ratio of each group; testing the sample set to be tested according to different test clustering radii until the clustering density corresponding to the test clustering radius meets the preset stability condition, and obtaining the target clustering radius; adjusting the coverage data volume and the coverage data volume ratio in the sample set to be tested according to a preset adjustment strategy until the preset change trend is met, and determining the target coverage data volume and the target coverage data volume ratio; filtering out effective hotspot locations from the at least one hotspot location based on the minimum data volume, the target clustering radius, the target coverage data volume and the target coverage data volume ratio.

[0007] Furthermore, the method of determining the minimum data amount of the parking position data of each vehicle based on the proportion of each group of valid hotspots includes: generating a fluctuation curve according to the proportion of each group of valid hotspots; identifying the position in the fluctuation curve whose changing trend satisfies the preset smoothing trend, and obtaining the minimum data amount based on the number of parking position data corresponding to the position.

[0008] Furthermore, before clustering the effective hotspot positions of all vehicles, the method further includes: optimizing the effective hotspot positions of all vehicles by a preset search algorithm to determine the optimal effective hotspot of each vehicle.

[0009] Furthermore, the target group is circled in a preset area around the center point, including: calling a preset map to convert the center point into a point of interest, and circled in the preset area around the point of interest.

[0010] A second aspect of the present application provides a device for selecting a target population, including: a crawling module for crawling parking location data of all vehicles within a target range; an identification module for identifying at least one hotspot location where the vehicle has been parked more than a preset number of times based on the parking location data; a processing module for determining a valid hotspot location that meets a preset target condition among the at least one hotspot location, clustering the valid hotspot locations of all vehicles to obtain a center point of the valid hotspot, and selecting a target population within a preset area around the center point.

[0011] Furthermore, the processing module is used to: group parking location data according to the number of vehicles, and extract the same number of vehicles from each group to form a sample set to be tested; cluster the hotspot position of each vehicle in the sample set to be tested to obtain an effective hotspot position; calculate the effective hotspot ratio of each group, and determine the minimum data volume of parking location data of each vehicle based on the effective hotspot ratio of each group; test the sample set to be tested according to different test clustering radii until the clustering density corresponding to the test clustering radius meets the preset stability condition, and obtain the target clustering radius; adjust the coverage data volume and the coverage data volume ratio in the sample set to be tested according to the preset adjustment strategy until the preset change trend is met, and determine the target coverage data volume and the target coverage data volume ratio; filter out an effective hotspot position from the at least one hotspot position based on the minimum data volume, the target clustering radius, the target coverage data volume and the target coverage data volume ratio.

[0012] Furthermore, the processing module is further used to: generate a fluctuation curve based on the proportion of each group of effective hotspots; identify the position in the fluctuation curve where the change trend meets the preset smooth trend, and obtain the minimum data volume based on the number of parking position data corresponding to the position.

[0013] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the target population selection method as described in the above embodiment.

[0014] The fourth aspect of the present application provides a computer-readable storage medium on which a computer program is stored. The program is executed by a processor to implement the target population selection method as described in the above embodiment.

[0015] Therefore, this application has at least the following beneficial effects:

[0016] The embodiments of the present application can automatically select a target group based on vehicle parking data. Since vehicle parking data can effectively reflect the user's living habits, the target group can be accurately and efficiently selected, with a wide coverage, which can improve sales sustainability and enhance the user experience. This solves the problem of manual selection of target groups in related technologies, which leads to poor selection accuracy, a narrow coverage, low sustainability, and a poor user experience.

[0017] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0019] Figure 1 A flowchart of a target population selection method according to an embodiment of the present application;

[0020] Figure 2 This is a flow chart of a method for selecting a target population according to one embodiment of the present application;

[0021] Figure 3 This is an example diagram of a device for selecting a target group according to an embodiment of the present application;

[0022] Figure 4 Schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0024] Currently, car dealers primarily acquire customers through in-store visits, phone calls, auto shows, and referrals from friends. While these customers are high-potential and have a high conversion rate, their reach is narrow and sustainability is low. Related technologies include:

[0025] (1) Determine the vehicle's stop information and number of stops based on vehicle trajectory data. By presetting the number of stops, obtain the vehicle's stop point. By presetting the number of stops, obtain the permanent stop point. By matching the permanent stop point with map data, obtain the point of interest. The stop point of a vehicle is primarily determined based on the number of stops, without considering the density (how close most points are to the effective hotspot) and frequency (the number of points around the effective hotspot) of the stops around the stop point.

[0026] (2) Input the predicted sample set, target brand category to be tested, delivery information, delivery channels, and delivery effect indicators into the pre-built target population selection model to obtain the target population package. The population selection model requires many indicators, while the Internet of Vehicles data has few indicators, which will limit the target population selection.

[0027] To this end, the embodiment of the present application can obtain a sample set to be tested based on the vehicle parking location data uploaded by the T-box, and determine whether the center point of the clustered sample set to be tested is a valid hotspot through the Kmeans (partition-based clustering method) clustering algorithm and restriction conditions, and find the optimal model for obtaining the valid hotspot by searching the optimal model algorithm; then, the center point of the valid hotspot is obtained through the Kmeans clustering algorithm; finally, the marketable community and target population are obtained by matching the center point with the map data. The target population selection method, device, electronic device and storage medium of the embodiment of the present application will be described below with reference to the accompanying drawings.

[0028] Specifically, Figure 1 A flowchart of a target population selection method provided in an embodiment of the present application.

[0029] like Figure 1 As shown, the target population selection method includes the following steps:

[0030] In step S101, the parking location data of all vehicles within the target range are crawled.

[0031] Among them, the parking location data can be the vehicle's longitude, latitude and other data; the target range can be determined by province, city, etc., and no specific limitation is made here.

[0032] It is understandable that the embodiment of the present application can crawl the parking location data of all vehicles within the target range to achieve subsequent target population selection by obtaining more comprehensive data.

[0033] Specifically, the vehicle parking location in the embodiment of the present application can be obtained using driving data uploaded by a T-box (Telematics BOX). The constraint data is the end-of-trip status, from which the vehicle VIN (Vehicle Identification Number) and parking location data (vehicle longitude and latitude) are extracted. The data acquisition cycle can be adjusted according to the data volume and server resources.

[0034] In step S102, at least one hotspot location where the vehicle has been parked more than a preset number of times is identified based on the parking location data.

[0035] Among them, the preset number of times can be set according to actual conditions, such as 10 times, and there is no specific limit here; hot spots refer to places where users frequently park or places that are more popular with the public, such as large shopping malls, tourist attractions, etc., and there is no specific limit here.

[0036] It is understandable that the embodiments of the present application can determine hotspot locations based on the frequency of user parking locations, thereby accurately identifying locations preferred by users or the public.

[0037] In an embodiment of the present application, determining a valid hotspot location that meets a preset target condition in at least one hotspot location may include: grouping according to the number of parking location data, and extracting the same number of vehicles from each group to form a sample set to be tested; clustering the hotspot location of each vehicle in the sample set to be tested to obtain a valid hotspot location; calculating the effective hotspot ratio of each group, and determining the minimum data volume of the parking location data of each vehicle based on the effective hotspot ratio of each group; testing the sample set to be tested according to different test clustering radii until the clustering density corresponding to the test clustering radius meets the preset stability condition, and obtaining the target clustering radius; adjusting the coverage data volume and the coverage data volume ratio in the sample set to be tested according to a preset adjustment strategy until the preset change trend is met, and determining the target coverage data volume and the target coverage data volume ratio; screening out a valid hotspot location from at least one hotspot location based on the minimum data volume, target clustering radius, target coverage data volume and the target coverage data volume ratio.

[0038] The sample set to be tested is obtained by grouping vehicles according to the vehicle parking location data, and sampling the same number of vehicles in each group as the sample set to be tested.

[0039] Among them, the preset target conditions can be range conditions, such as: urban shopping malls, near suburban tourist attractions, etc., or location conditions, such as the latitude and longitude of the vehicle, etc., or keywords, such as: hotel names, etc., which are not specifically limited here.

[0040] Among them, the effective hotspot location can be a location where many vehicles are parked around a central point and the density is relatively high, or it can be a location where vehicles are more active around a certain area.

[0041] The effective hotspot ratio refers to the ratio of the number of vehicles with effective hotspots in a group divided by the total number of vehicles in the group, when the vehicles are grouped by the amount of parking location data. The amount of parking location data is also a key factor influencing the model. For example, the more parking location data a vehicle has, the greater the probability of identifying its effective hotspot.

[0042] Among them, the minimum data volume is determined by applying an algorithm to the test sample set to find the effective hotspots of each vehicle, calculate the proportion of effective hotspots in each group, observe the fluctuation trend of the effective hotspot proportion, and find the position where the change gradually becomes smooth, so as to determine the minimum data volume that each vehicle's parking location data needs to meet.

[0043] The test cluster radius refers to testing vehicles within a certain radius of a certain location as the center point of the test sample set. For example, testing vehicles within a radius of 50 meters from a shopping mall as the center point. There is no specific limitation here.

[0044] The target clustering radius refers to the target clustering radius obtained when the clustering density corresponding to the test clustering radius meets the preset stability condition. The preset stability condition can be set according to actual conditions, such as the clustering density reaching 70%, which is not specifically limited here.

[0045] The target coverage data volume refers to the data volume covered by the target effective hotspots in the test sample set.

[0046] Among them, the target coverage data volume ratio refers to the ratio of the location data volume belonging to the valid hotspot to the total vehicle location data volume.

[0047] It can be understood that the embodiment of the present application can be that the amount of vehicle parking location data is an important factor affecting the model. The more parking location data a vehicle has, the greater the probability of finding its effective hotspot. The vehicles are grouped according to the amount of parking location data, and the same number of vehicles are sampled in each group as the sample set to be tested; then the algorithm is used to find the effective hotspots of each vehicle, and the proportion of effective hotspots in each group is calculated. By observing the wave trend of the proportion of effective hotspots, the minimum parking location data volume, aggregation density and frequency are evaluated, and the effective hotspot location is screened out from at least one hotspot location based on the minimum data volume, target aggregation radius, target coverage data volume and target coverage data volume proportion. This method further optimizes the effective hotspot through the search algorithm.

[0048] In an embodiment of the present application, determining the minimum data volume of the parking position data of each vehicle based on the proportion of each group of valid hotspots may include: generating a fluctuation curve based on the proportion of each group of valid hotspots; identifying the position in the fluctuation curve where the change trend satisfies the preset smooth trend, and obtaining the minimum data volume based on the number of parking position data corresponding to the position.

[0049] The preset smoothing trend may be set according to actual conditions, for example, close to a horizontal level, etc., and is not specifically limited here.

[0050] It can be understood that the embodiment of the present application can generate a fluctuation curve based on the effective heat ratio of each group in the sample set. When its changing trend tends to be smooth, the minimum data amount is obtained based on the number of parking position data, and observation through the curve is more convenient, intuitive and reliable.

[0051] In an embodiment of the present application, before clustering the effective hotspot positions of all vehicles, the method may further include: optimizing the effective hotspot positions of all vehicles through a preset search algorithm to determine the optimal effective hotspot for each vehicle.

[0052] The preset search algorithm may be set according to actual conditions, and may be a K-means clustering algorithm or an optimal search algorithm, which is not specifically limited here.

[0053] It is understandable that the embodiments of the present application may vary depending on the distribution of different vehicle parking locations. For some vehicles, the best results are achieved when the number of clusters is 3, while for others, the best results are achieved when the number of clusters is 5. Here, the search algorithm can be used to further optimize the effective hotspots. The algorithm logic is to repeatedly perform clustering operations with added constraints on the same vehicle according to different cluster numbers from low to high, then compare the results and obtain the best result as the final result for that vehicle. This makes the operation more convenient and faster, and the acquisition of the vehicle's effective hotspots is more accurate.

[0054] In step S103, a valid hotspot location that meets the preset target conditions is determined in at least one hotspot location, and the valid hotspot locations of all vehicles are clustered to obtain the center point of the valid hotspot, and the target population is circled in a preset area around the center point.

[0055] Among them, the center point of the effective hotspot is an area where the density of vehicle parking positions around it is high or vehicles are more active near this position; the preset area can be an area within 50m or 100m, etc., which can be specifically set and is not specifically limited here.

[0056] It is understandable that the embodiments of the present application can make the marketable community and target population more focused by obtaining the center point of the effective hotspot and circling the target population within the range around the center point.

[0057] Specifically, the embodiment of the present application may have two criteria for judging effective hotspots based on the characteristics of effective hotspots: 1. Whether the density of points around the center point is high. If most of the points are very close to the center point, the center point can be considered to have a high quality because this reflects that the vehicle parking position is near the center point, which is the aggregation density; 2. Whether there are many points around the center point. Only when there are multiple points around the center point can it be said that vehicles are active frequently near this position, which is the frequency.

[0058] In an embodiment of the present application, selecting a target group of people within a preset area around a center point may include: calling a preset map to convert the center point into a point of interest, and selecting a target group of people within a preset area around the point of interest.

[0059] Among them, the preset map can be set according to actual conditions, and can be an API (Application Programming Interface) and the like, and is not specifically limited here; among them, the points of interest are areas that can be used as areas for carrying out marketing activities.

[0060] It can be understood that the embodiment of the present application can obtain the map data of the center point through the API. The map data called here should be consistent with the map used by the vehicle. The center point is obtained and converted into a point of interest. Marketing activities are carried out based on the interest, making the data more stable and reliable.

[0061] The target population method will be described below through a specific embodiment. Figure 2 As shown, the following steps are included:

[0062] S1: Extract vehicle parking location data:

[0063] The vehicle parking location in this embodiment is obtained using driving data uploaded by the T-box. The constraint data is the end-of-trip status, from which the vehicle VIN code and parking location data (vehicle longitude and latitude) are extracted. The data acquisition cycle can be adjusted based on the data volume and server resources.

[0064] S2: Group the vehicles according to the amount of location data and select the sample set to be tested:

[0065] The amount of parking location data is a key factor influencing the model. The more parking location data a vehicle has, the greater the probability of identifying a valid hotspot. Here, the vehicles can be grouped based on the amount of parking location data, with each group sampling the same number of vehicles as the test sample set.

[0066] S3: Evaluate the minimum amount of parking location data:

[0067] The same Kmeans clustering algorithm is used on the test sample set to find the effective hotspots of each vehicle, calculate the proportion of effective hotspots in each group, observe the fluctuation trend of the effective hotspot proportion (the number of vehicles with effective hotspots in this group / the total number of vehicles in this group), and find the position where the change gradually becomes smooth, so as to determine the minimum data volume required for the parking location data of each vehicle.

[0068] S4: Evaluate cluster density:

[0069] Select different R values ​​(aggregation radius), substitute the R values ​​into the model, test the test sample set, and observe the effective hotspot ratio and close distance point ratio corresponding to different R values Find the R value corresponding to the effective hot spot ratio and the close distance point ratio with relatively stable changes to determine the R value;

[0070] Set different thresholds for p, observe the fluctuation trends of the proportion of effective hot spots and the proportion of close-range points at different thresholds, find the position where the changes gradually become smooth, and use it to determine the minimum value of p.

[0071] S5: Evaluation frequency:

[0072] Adjust the coverage data volume (the amount of data covered by an effective hotspot, N) and the proportion of coverage data volume (the proportion of location data belonging to the effective hotspot to the total vehicle location data, P). By observing the changing trends of the effective hotspot proportion and the coverage data volume proportion, find the position where the change gradually becomes smoother and determine N and P.

[0073] S6: Get the vehicle's valid hotspot:

[0074] Apply the minimum data volume, R, p, N, and P values ​​determined by S3, S4, and S5 to all vehicles to screen for valid hotspots;

[0075] Different vehicles have different parking location distributions. Some vehicles perform best with 3 clusters, while others perform best with 5. This allows for further optimization of effective hotspots through a search algorithm. The algorithm repeatedly performs constrained clustering operations on the same vehicle, starting with the lowest number of clusters and increasing the highest number of clusters. The results are then compared, and the best one is selected as the final result for that vehicle.

[0076] S7: Get the center point and group members:

[0077] The Kmeans clustering algorithm is used to obtain the center points and group members of all vehicles. The center point is the center point clustered based on valid hotspots, and the group members are the vehicles near the center point. Depending on business needs, clustering can also be performed on a city basis to obtain the center point and group members for that city.

[0078] S8: Call the API (Application Programming Interface) to convert the center point into POI (Point of Interest) information:

[0079] Call the API to obtain map data for the center point. This location data can be used as the area for marketing activities. The map data called here should be consistent with the map used by the vehicle.

[0080] In summary, the embodiment of the present application is to obtain the effective hotspot of a single vehicle by clustering the parking location data (longitude and latitude of the vehicle) in the driving data of a single vehicle, further cluster the effective hotspots of all vehicles, obtain the center point of all vehicles, and combine the Kmeans clustering algorithm and the search algorithm to form a new form of target population selection. Mainly based on the Kmeans clustering algorithm, some restrictions are added to determine whether the center point position of the cluster is a valid hotspot, and then the search for the optimal model algorithm is added to perform multiple clustering operations on each vehicle to search for the best model, providing site selection and population selection data support for marketing activities on the marketing side.

[0081] According to the target population selection method proposed in the embodiment of this application, the method introduces an algorithm based on the different clustering densities and frequencies of various stop points around the vehicle's stop point, making the vehicle's effective hotspots more accurate and flexible. The effective hotspots of the vehicle are further clustered to obtain the center point of the effective hotspot, making the marketable community and target population more focused, and the information more accurate and referenceable. This solves the problems of manual selection of target populations in related technologies, which leads to poor selection accuracy, narrow coverage, low sustainability, and poor user experience.

[0082] Next, the target population selection device proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0083] Figure 3 2 is a block diagram of a target population selection device according to an embodiment of the present application.

[0084] like Figure 3 As shown, the target population selection device 10 includes: a crawling module 100, an identification module 200 and a processing module 300.

[0085] Among them, the crawling module 100 is used to crawl the parking location data of all vehicles within the target range; the identification module 200 is used to identify at least one hot spot location where the number of vehicle parking times is greater than a preset number based on the parking location data; the processing module 300 is used to determine the effective hot spot location that meets the preset target conditions in at least one hot spot location, and cluster the effective hot spot locations of all vehicles to obtain the center point of the effective hot spot, and circle the target population in the preset area around the center point.

[0086] In an embodiment of the present application, the processing module 300 can be used to: group according to the number of parking position data, and extract the same number of vehicles from each group to form a sample set to be tested; cluster the hotspot positions of each vehicle in the sample set to be tested to obtain effective hotspot positions; calculate the effective hotspot ratio of each group, and determine the minimum data volume of the parking position data of each vehicle based on the effective hotspot ratio of each group; test the sample set to be tested according to different test clustering radii until the clustering density corresponding to the test clustering radius meets the preset stability condition, and obtain the target clustering radius; adjust the coverage data volume and the coverage data volume ratio in the sample set to be tested according to the preset adjustment strategy until the preset change trend is met, and determine the target coverage data volume and the target coverage data volume ratio; filter out effective hotspot positions from at least one hotspot position based on the minimum data volume, target clustering radius, target coverage data volume and the target coverage data volume ratio.

[0087] In an embodiment of the present application, the processing module 300 is further used to: generate a fluctuation curve based on the proportion of each group of effective hotspots; identify the position corresponding to the preset smooth trend in the fluctuation curve where the change trend meets the preset smooth trend, and obtain the minimum data volume based on the number of parking position data corresponding to the position.

[0088] It should be noted that the aforementioned explanation of the target population selection method embodiment is also applicable to the target population selection device of this embodiment, and will not be repeated here.

[0089] According to the target population selection device proposed in the embodiment of the present application, the device introduces an algorithm based on the different clustering densities and frequencies of various stop points around the vehicle's stop point, making the vehicle's effective hotspots more accurate and flexible. The effective hotspots of the vehicle are further clustered to obtain the center point of the effective hotspot, making the marketable community and target population more focused, and the information more accurate and referenceable. This solves the problems of manual selection of target populations in related technologies, which leads to poor selection accuracy, narrow coverage, low sustainability, and poor user experience.

[0090] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0091] Memory 401 , processor 402 , and computer programs stored in the memory 401 and executable on the processor 402 .

[0092] When the processor 402 executes the program, the target population selection method provided in the above embodiment is implemented.

[0093] Furthermore, the vehicle further comprises:

[0094] The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0095] The memory 401 is used to store computer programs that can be run on the processor 402 .

[0096] The memory 401 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0097] If the memory 401, the processor 402, and the communication interface 403 are implemented independently, the communication interface 403, the memory 401, and the processor 402 can be connected to each other via a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0098] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0099] The processor 402 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0100] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned target population selection method when executed by a processor.

[0101] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0102] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0103] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0104] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.

[0105] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0106] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for selecting a target population, characterized in that: The following steps are involved: Crawl the parking location data of all vehicles within the target range; identifying, based on the parking location data, at least one hotspot location where the vehicle has been parked a number of times greater than a preset number; Determine an effective hotspot location that meets a preset target condition among the at least one hotspot location, cluster the effective hotspot locations of all vehicles to obtain a center point of the effective hotspot, and circle a target population within a preset area around the center point, wherein determining an effective hotspot location that meets the preset target condition among the at least one hotspot location includes: The parking location data are grouped according to the number of the parking location data, and the same number of vehicles are extracted from each group to form a sample set to be tested; the hotspot position of each vehicle in the sample set to be tested is clustered to obtain the effective hotspot position; the effective hotspot ratio of each group is calculated, and the minimum data volume of the parking location data of each vehicle is determined based on the effective hotspot ratio of each group; the sample set to be tested is tested according to different test clustering radii until the clustering density corresponding to the test clustering radius meets the preset stability condition, and the target clustering radius is obtained; the coverage data volume and coverage data ratio of the sample set to be tested are adjusted according to the preset adjustment strategy until the preset change trend is met, and the target coverage data is determined. the minimum data volume, the target aggregation radius, the target coverage data volume and the target coverage data volume ratio; based on the minimum data volume, the target aggregation radius, the target coverage data volume and the target coverage data volume ratio, a valid hotspot position is screened out from the at least one hotspot position; the valid hotspot positions of all vehicles are optimized by a preset search algorithm to determine the optimal valid hotspot for each vehicle, wherein the minimum data volume of the parking position data of each vehicle based on the ratio of each group of valid hotspots comprises: generating a fluctuation curve according to the ratio of each group of valid hotspots; identifying the position in the fluctuation curve whose changing trend satisfies the preset smoothing trend, and obtaining the minimum data volume based on the number of parking position data corresponding to the position.

2. The method according to claim 1, characterized in that The target group is circled in the preset area around the center point, including: The preset map is called to convert the center point into a point of interest, and the target group is circled in a preset area around the point of interest.

3. A target population selection device, characterized in that: include: The crawling module is used to crawl the parking location data of all vehicles within the target range; an identification module, configured to identify, based on the parking location data, at least one hotspot location where the vehicle has been parked a number of times greater than a preset number; A processing module is used to determine the effective hotspot position that meets the preset target condition in the at least one hotspot position, cluster the effective hotspot positions of all vehicles, obtain the center point of the effective hotspot, and circle the target population in the preset area around the center point, wherein the processing module is further used to: group according to the number of parking position data, and extract the same number of vehicles from each group to form a sample set to be tested; cluster the hotspot position of each vehicle in the sample set to be tested to obtain the effective hotspot position; calculate the effective hotspot ratio of each group, and determine the minimum data volume of the parking position data of each vehicle based on the effective hotspot ratio of each group; test the sample set to be tested according to different test clustering radii until the clustering density corresponding to the test clustering radius meets the preset stability condition, and obtain the target clustering radius; Assume that an adjustment strategy adjusts the coverage data volume and the coverage data volume ratio of the sample to be tested until a preset change trend is met, and the target coverage data volume and the target coverage data volume ratio are determined; based on the minimum data volume, the target aggregation radius, the target coverage data volume and the target coverage data volume ratio, a valid hotspot position is screened out from the at least one hotspot position; the valid hotspot positions of all vehicles are optimized through a preset search algorithm to determine the optimal valid hotspot for each vehicle, wherein the minimum data volume of the parking position data of each vehicle based on the ratio of each group of valid hotspots is determined, including: generating a fluctuation curve according to the ratio of each group of valid hotspots; identifying the position in the fluctuation curve corresponding to the change trend that meets the preset smooth trend, and obtaining the minimum data volume based on the number of parking position data corresponding to the position.

4. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the target population selection method according to any one of claims 1 to 2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the target population selection method according to any one of claims 1 to 2.

Images