WO2021103626A1

WO2021103626A1 - Method and apparatus for generating user geographical portrait, computer device, and storage medium

Info

Publication number: WO2021103626A1
Application number: PCT/CN2020/105506
Authority: WO
Inventors: 曹煬
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2019-11-26
Filing date: 2020-07-29
Publication date: 2021-06-03
Also published as: CN111178932A

Abstract

A method for generating a user geographical portrait, relating to the technical field of big data analysis, and comprising: acquiring location service data of a service user (S201); performing density clustering processing on the location service data by means of a density-based clustering algorithm, so as to obtain a data cluster of the location service data (S203); determining, from the data cluster, a reference position cluster that geographical portrait reference positions of the service user belong to, wherein the geographical portrait reference positions comprise a reference position used when generating a user geographical portrait (S205); performing clustering processing on the reference position cluster, so as to obtain a cluster center of the reference position cluster (S207); and generating a user geographical portrait of the service user on the basis of the cluster center and the location service data (S209).

Description

Method, device, computer equipment and storage medium for generating geographic portrait of user

Cross-references to related applications

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on November 26, 2019. The application number is 2019111734073 and the application name is "User Geographic Portrait Generation Method, Device, Computer Equipment, and Storage Medium". The entire content of the application is approved. The reference is incorporated in this application.

Technical field

This application relates to the field of computer technology, and in particular to a method, device, computer equipment and storage medium for generating geographic portraits of users.

Background technique

Location-Based Services (LBS) is currently a hot spot in mobile terminal services. In the current mobile application market, LBS is widely used. In shopping applications, LBS is used to obtain the user's location, which not only saves the user the tedious process of manually inputting location information, but also provides a basis for geographic location information for the selection of distribution warehouses; In navigation applications, LBS obtains the user's location information in real time and returns it to the user, making the acquisition and query of road condition information more intuitive and simple; in addition, in various mobile applications such as social networking, weather, taxi, group buying, and travel , LBS plays an important role. The geographic location information provided by LBS can enrich application functions and greatly facilitate users’ lives.

However, the inventor realized that after data mining on location service data, various business users are generally profiled through various tags, and then corresponding services are provided based on the user profile. How to accurately generate business user profiles becomes a high-level solution. An important basis for quality service.

Summary of the invention

According to various embodiments disclosed in the present application, a method, device, computer device, and storage medium for generating a geographic portrait of a user are provided.

A method for generating geographic portraits of users includes:

Obtain location service data of business users;

Through density-based clustering algorithm, the location service data is subjected to density clustering processing to obtain the data cluster of the location service data;

From the data cluster, determine the reference position cluster to which the reference position of the geographic portrait of the business user belongs; where the reference position of the geographic portrait includes the reference position when generating the user's geographic portrait;

Perform clustering processing on the reference position cluster to obtain the cluster center of the reference position cluster; and

Based on the cluster center and location service data, generate user geographic portraits of business users.

A device for generating geographic portraits of users includes:

User data acquisition module for acquiring location service data of business users;

The data cluster obtaining module is used to perform density clustering processing on the location service data through a density-based clustering algorithm to obtain a data cluster of the location service data;

The reference position cluster determination module is used to determine the reference position cluster to which the reference position of the geographic portrait of the business user belongs from the data cluster; wherein the reference position of the geographic portrait includes the reference position when generating the user's geographic portrait;

The cluster center determination module is used to perform clustering processing on the reference position cluster to obtain the cluster center of the reference position cluster; and

The geographic portrait production module is used to generate user geographic portraits of business users based on cluster center and positioning service data.

A computer device, including a memory and one or more processors, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the one or more processors execute The following steps:

Obtain location service data of business users;

One or more computer-readable storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors perform the following steps:

Obtain location service data of business users;

The above-mentioned user geographic portrait generation method, device, computer equipment, and storage medium perform density clustering processing on the location service data through a density-based clustering algorithm, and then determine from the obtained data clusters to which the reference location of the geographic portrait of the business user belongs The reference location cluster effectively utilizes the characteristics of the density distribution of the location service data to ensure the accuracy of the reference location cluster; then based on the cluster center and location service data obtained by clustering the reference location cluster, the user geographic portrait of the business user is generated, Improve the accuracy of the user's geographic portrait.

The details of one or more embodiments of the present application are set forth in the following drawings and description. Other features and advantages of this application will become apparent from the description, drawings and claims.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings that need to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. A person of ordinary skill in the art can obtain other drawings based on these drawings without creative work.

Fig. 1 is an application scenario diagram of a method for generating a geographic portrait of a user according to one or more embodiments;

2 is a schematic flowchart of a method for generating a geographic portrait of a user according to one or more embodiments;

FIG. 3 is a schematic diagram of a flow of data cluster acquisition according to one or more embodiments;

Fig. 4 is a block diagram of an apparatus for generating a geographic portrait of a user according to one or more embodiments;

Figure 5 is a block diagram of a computer device according to one or more embodiments.

Detailed ways

In order to make the purpose, technical solutions, and advantages of this application clearer and clearer, the following further describes the application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

The user geographic portrait generation method provided in this application can be applied to the application environment as shown in FIG. 1. Wherein, the terminal 102 communicates with the server 104 through the network through the network. The terminal 102 sends the location service data of the business user to the server 104, and the server 104 performs density clustering processing on the obtained location service data through a density-based clustering algorithm, and then determines the geographic portrait reference of the business user from the obtained data cluster The reference location cluster to which the location belongs is based on the cluster center and location service data obtained by clustering the reference location cluster to generate the user geographic portrait of the business user. In addition, the location service data of the business user can be stored in the local cache of the server 104, and the server 104 can directly obtain the location service data of the business user from the local cache for subsequent user geographic portrait generation processing; it can also be directly used by the terminal 102 Perform user geographic portrait generation processing on the location service data of business users. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server 104 may be implemented by an independent server or a server cluster composed of multiple servers.

In one of the embodiments, as shown in FIG. 2, a method for generating geographic portraits of users is provided. Taking the method applied to the server or terminal in FIG. 1 as an example, the method includes the following steps:

Step S201: Obtain location service data of the business user.

Among them, location service data, that is, LBS data, is generated when the user terminal uses location services. For example, when the terminal application needs to perform positioning and navigation, it passes through the radio communication network of the telecommunications mobile operator, such as the GSM network (Global System for Mobile Communications, Global Mobile Communication System), CDMA network (Code Division Multiple Access), LTE network (Long Term Evolution) or 5G (5th-Generation, the fifth-generation mobile communication technology), or through external positioning methods , Such as the location information of the mobile terminal obtained by GPS (Global Positioning System, Global Positioning System). Generally, according to the needs of service users corresponding to mobile terminals, when performing timing or real-time positioning, a large number of LBS data will be generated.

Step S203: Perform density clustering processing on the location service data through the density-based clustering algorithm to obtain a data cluster of the location service data.

Among them, the density-based clustering algorithm is based on the density distribution of the data to perform clustering, such as DBSCAN (Density-Based Spatial Clustering of Applications with Noise, density-based spatial clustering with noise) algorithm, OPTICS (Ordering points to) identify the clustering structure, object sorting and identifying clustering structure) algorithms, etc. In this embodiment, a density-based clustering algorithm is used to perform density clustering processing on the location service data, and the location service data is clustered into clusters to obtain data clusters of the location service data. Among them, the data cluster is a cluster of data points of the same type obtained by clustering the location service data after processing the location service data through a density-based clustering algorithm.

Step S205: Determine the reference position cluster to which the reference position of the geographic portrait of the business user belongs from the data cluster; wherein the reference position of the geographic portrait includes the reference position when generating the geographic portrait of the user.

Among them, the geographic portrait reference location is the reference location data referenced for generating the user's geographic portrait, which can specifically include the reference location when generating the user's geographic portrait, such as the reference location data that needs to be referred to when determining the label of the working city in the user's geographic portrait. It is the user’s work address, and for the commute distance tag, the reference location data that needs to be referred to include the user’s work address and home address. The geographic portrait reference location is set according to the actual needs of the user’s geographic portrait, such as business users Home address, work address, etc. The reference location cluster is the geographic portrait reference location, that is, the data cluster to which the reference location cluster when generating the user's geographic portrait is performed, that is, the reference location cluster is the data cluster where the geographic portrait reference location of the business user is located. When determining the reference position cluster to which the reference position of the geographic portrait belongs, it can be determined according to the statistical result of each data point in the data cluster. For example, when the reference location of the geographic portrait includes the home address, the data cluster where the home address of the business user is located can be determined according to the day/night ratio of each data point in the data cluster, so as to determine the reference location cluster from the data cluster.

Step S207: Perform clustering processing on the reference position cluster to obtain the cluster center of the reference position cluster.

After obtaining the reference position cluster where the reference position of the geographic portrait is located, perform clustering processing on the reference position cluster. For example, a clustering algorithm based on the mean can be used, for example, through the K-means algorithm, set K to 1, and perform clustering on the reference position cluster. The clustering process obtains the cluster center of the reference location cluster. The cluster center is the actual positioning coordinate data of the geographic portrait reference location of the business user, that is, the cluster center of the reference location cluster corresponds to the geographic portrait reference location of the business user. In specific implementation, you can also match the cluster center based on preset interest points, such as cell POI, company POI, etc., and modify the coordinates of the cluster center through the preset interest points, which can further improve the cluster center position Accuracy. Specifically, the cluster center can be updated with the interest point closest to the cluster center, and the original cluster center can be replaced based on the updated cluster center.

Step S209: Generate a user geographic portrait of the business user based on the cluster center and the location service data.

After determining the cluster center, that is, the actual positioning coordinate data of the reference position of the geographic portrait of the business user, the user geographic portrait of the business user is generated based on the cluster center and the positioning service data. Among them, the user geographic portrait reflects the personal characteristics of the business user, which can be specifically composed of geographic tags of multiple business users. The geographic tags may include, but are not limited to, home location, work location, commuting distance, work city, city of residence, Whether to work across places and hometown, etc.

In the above-mentioned user geographic portrait generation method, based on big data processing technology, density clustering is performed on massive positioning service data through a density-based clustering algorithm, and then from the obtained data clusters, the geographic portrait reference position of the business user is determined The reference location clusters effectively utilize the density distribution characteristics of the location service data to ensure the accuracy of the reference location clusters; then cluster centers and location service data obtained by clustering the reference location clusters to generate user geographic portraits of business users , Improve the accuracy of the user's geographic portrait.

In one of the embodiments, as shown in FIG. 3, the process of obtaining data clusters, that is, performing density clustering processing on location service data through a density-based clustering algorithm, to obtain data clusters of location service data includes:

Step S301: Obtain a preset core point coverage radius and a core point coverage number threshold.

In this embodiment, the location service data is subjected to density clustering processing through the DBSCAN algorithm to obtain a data cluster of the location service data. Specifically, the preset core point coverage radius and the core point coverage number threshold are acquired, and the core point coverage radius and the core point coverage number threshold are flexibly set according to actual clustering requirements. Among them, the core point coverage radius is the coverage area of the core point during the clustering process, and the core point coverage threshold is the number of LBS data points that the core point covers the least. The core point is defined as the distance from an LBS data point is less than the core point. The number of other LBS data points of the point coverage radius exceeds the core point coverage threshold. The larger the core point coverage radius, and the smaller the core point coverage number threshold, the greater the number of core points in the positioning service data.

In one of the specific applications, the core point coverage radius is set to 500 meters, and the core point coverage number threshold is set to 10. That is, in the positioning service data, there are more than 10 LBS data points within 500 meters of the LBS data point. Defined as the core point.

Step S303: According to the core point coverage radius and the core point coverage number threshold, the positioning service data is clustered and iteratively processed through the DBSCAN algorithm to obtain the core point of the positioning service data.

After determining the core point coverage radius and the core point coverage number threshold, the DBSCAN algorithm is used to cluster and iteratively process all the positioning service data, and the core points that meet the core point coverage radius and core point coverage number threshold are determined from the positioning service data. Among them, the DBSCAN algorithm is a density-based spatial clustering algorithm, which divides areas with sufficient density into clusters, and finds clusters of arbitrary shapes in a noisy spatial database. It defines clusters as the density of connected points. The largest collection.

Step S305: Perform clustering iterative processing on each core point to obtain a data cluster of the positioning service data composed of the core points.

After determining the core points of the positioning service data, the clustering and iterative processing is further performed on each core point. In specific implementation, the DBSCAN algorithm can be used for clustering iterative processing to obtain a data cluster of the positioning service data composed of the core points. The data cluster is composed of the connection of core points, and the LBS data points covered by the data cluster can be considered as the same kind of data.

In one of the embodiments, performing clustering iterative processing on each core point to obtain a data cluster of positioning service data composed of core points includes: obtaining a preset core point combination distance threshold; and according to the core point combination distance threshold, passing The DBSCAN algorithm performs clustering iterative processing on each core point, and obtains a data cluster of positioning service data composed of core points.

In this embodiment, the clustering and iterative processing of each core point is continued through the DBSCAN algorithm, and a data cluster of positioning service data composed of the core points is obtained. Specifically, after the core point of the positioning service data is obtained, the preset core point combination distance threshold is obtained. The core point combination distance threshold is set according to the size requirements of the data cluster. The core point combination distance threshold is whether the core points are connected to form the data cluster. Condition, if the distance between two core points is less than the core point combination distance threshold, then the two core points are combined to obtain a data cluster. The greater the core point combination distance threshold, the more core points connected to the obtained data cluster, and the more LBS data points it covers. After obtaining the core point combination distance threshold, according to the core point combination distance threshold, clustering and iterative processing is performed on each core point through the DBSCAN algorithm to obtain a data cluster of positioning service data composed of core points. For any core point in a data cluster, the distance between at least one other core point and the core point is less than the core point combined distance threshold.

In one of the specific applications, the core point combination distance threshold is 500 meters, that is, for a core point, if there are other core points within 500 meters around it, the core point is connected with other core points to form a data cluster .

In one of the embodiments, the reference location of the geographic portrait includes home address and work address; from the data cluster, determining the reference location cluster to which the reference location of the geographic portrait of the business user belongs includes: determining the number of location service data in the data cluster and the location service Time distribution of data; determine the home address cluster to which the home address belongs and the working address cluster to which the work address belongs according to the number and time distribution of location service data in the data cluster; and obtain the reference location cluster according to the home address cluster and the working address cluster.

In this embodiment, the reference location of the geographic portrait includes the home address and work address, that is, the user geographic portrait analysis is generated based on the home address and work address of the business user, specifically according to the number of LBS data in the data cluster and the time period distribution, from the data cluster Determine the reference position cluster.

Specifically, when determining the reference location cluster to which the reference location of the geographic portrait of the business user belongs, statistical analysis is performed on the location service data covered by the data cluster, and the number of location service data and the time period distribution of the location service data are determined. Wherein, the time period distribution can be, but is not limited to, day/night, working day/non-working day, etc. Based on the number and time distribution of the location service data in the data cluster, determine the home address cluster to which the home address belongs and the work address cluster to which the work address belongs. Specifically, the proportion of the location service data in the data cluster can be analyzed in different time periods, such as day and night. To determine the home address cluster to which the home address belongs and the working address cluster to which the work address belongs. The reference location cluster can be composed of the home address cluster and the work address cluster.

In one of the specific applications, the number of data clusters for obtaining location service data is n, that is, n data clusters are obtained. If n=1, count the day and night points in each data cluster. If the time period distribution in the data cluster is day>night, then the data cluster is the reference location cluster where the work address is located. If the time period distribution in the data cluster is day<night , The data cluster is the reference location cluster where the home address is located.

If n≥2, calculate the average avg based on the total number of points/n of the location service data. For any data cluster, if the total number of data cluster points is greater than or equal to avg, the proportion of daytime points is calculated according to the number of daytime points/the total number of cluster points, and the proportion of night points is calculated according to the number of nights/total cluster points; if the total number of data cluster points is less than avg, according to ( Daytime points/avg)*(daytime points/total cluster points) calculate the proportion of daytime points, and calculate the proportion of night points according to (night points/avg)*(night points/total cluster points). After calculating the percentages of daytime points and night points for each data cluster, compare the percentages of daytime points and night points for n clusters. If the highest percentage of points during the day and the highest percentage of points at night are in different clusters, the cluster with the highest percentage during the day is the cluster where the work address is located, and the cluster where the home address is at night is the cluster with the highest percentage during the day. If the highest proportion of points in the daytime or the highest proportion of points in the evening is in the same cluster, and n clusters have only one time period (all recorded as daytime), the time period of the cluster with the highest proportion is selected as the cluster or the home address The cluster where the work address is located (only one cluster is formed at the end, that is, the cluster in the daytime). If the highest proportion of points in the daytime or the highest proportion of points in the night is in the same cluster, and n clusters have only one time period (recorded as daytime), and the daytime proportion of another cluster>this n cluster, then choose the daytime among the n clusters The cluster with the highest proportion is regarded as the cluster during the day, and the other cluster becomes the cluster at night, so as to determine the home address cluster and the work address cluster. In other cases, for a data cluster, if the proportion in the daytime>the proportion in the night, the data cluster is determined to be a home address cluster; if the proportion in the daytime<the proportion in the night, the data cluster is determined to be a work address cluster; if the proportion in the daytime is Ratio = night proportion, then randomly determine the home address cluster and work address cluster. If a cluster type has been selected for a data cluster, it is recorded as daytime, that is, the work address cluster, and the highest proportion of night is selected among the other n clusters The cluster of is regarded as the cluster at night, that is, the home address cluster.

In one of the embodiments, it further includes: when the number of data clusters is 0, generating a user geographic portrait of the business user based on the positioning service data.

In this embodiment, when the location service data is subjected to density clustering processing through the density-based clustering algorithm, no data clusters are obtained, that is, when the number of data clusters is 0, statistical analysis is performed directly based on the location service data, and the location service data. For example, you can find the city where each LBS data point is located, the number of statistical days + the number of points (first comparison days) is the city where you are, and finally the geographic tag of the business user is determined, such as the city where the business user is located, the New Year city, and the list of cities visited And so on, further generate the user geographic portrait of the business user based on the geographic tag.

In one of the embodiments, the user geographic portrait of the business user includes: home location, work location, commuting distance, working city, residential city, whether to work across regions, hometown, whether to work outside, cities frequented on holidays, and whether on weekends At least one of the house, whether there is a house, and the nature of work.

Among them, the home location and work location can be determined based on the cluster center of the home address cluster and the work address; the commuting distance can be calculated based on the distance between the home location and the location of the work unit; the working city can be determined based on the location of the work unit; the city of residence It can be determined according to the location of the family; whether to work across places can be determined according to the correspondence between the city of work and the city of residence; the hometown can be determined according to the distribution of LBS data during the Spring Festival; whether migrant workers can be determined according to the correspondence between the hometown and the city of work; Cities frequented on holidays can be determined according to the distribution of LBS data of cities frequently visited on holidays; whether a weekend house can be determined according to the distribution of LBS data on weekends. Specifically, whether the LBS data on weekends exceeds a certain range of the home location, if it exceeds a certain distance, it is considered this If you go out for a day, whether you are staying at home or not, if the number of days at home exceeds the number of days you are away, it is considered a weekend home; whether there is a room can be determined according to the changes in the location of the family within a certain period of time, such as three years; the nature of work can include travel, overtime, Night shifts, etc., can be specific when the number of non-working cities exceeds a certain value at the beginning of work. For example, when the number of working days exceeds 20% of the total working days, it is considered to be the nature of travel work. If you are working from 7 to 12 in the evening The number of LBS data points in the place exceeds a certain value. If it accounts for 30% of the total number of points, the work is considered to be overtime; if the number of LBS data points at the work place exceeds a certain value from 12pm to 7am, if it accounts for the total 50% of the credit is considered to be the nature of night shift work. Through rich geographic tags, a full user geographic portrait of the corresponding business users can be obtained, so as to ensure the corresponding provision of high-quality business services.

In one of the embodiments, after obtaining the positioning service data of the business user, it further includes: extracting the out-of-area coordinates from the positioning service data; when it is determined that the out-of-area coordinates are inverted coordinates, performing latitude and longitude replacement processing on the out-of-area coordinates to obtain Replace the replacement coordinates after replacement processing; and add the replacement coordinates to the location service data, and use the updated location service data as the location service data.

In this embodiment, the latitude and longitude inverted coordinates in the acquired positioning service data are replaced by the latitude and longitude replacement process, and the latitude and longitude are replaced to obtain the replacement coordinates, thereby correcting the data with the latitude and longitude inversion error to a certain extent to ensure This improves the accuracy of location service data, thereby improving the accuracy of user geographic portraits.

Specifically, the out-of-area coordinates are positioning service data in the range of the data area of interest, and the range of the data area of interest is determined according to the data mining requirements for the LBS data. For example, for data mining that is only applicable to specific locations, such as an application scenario that only performs data mining on LBS data in China, the data area of interest is within China, and LBS data outside of China is excluded. When extracting the out-of-area coordinates from the location service data, the range of the data area of interest can be determined, and the out-of-area coordinates that are not within the range of the data area of interest can be determined according to the location of each location service data. The out-of-area coordinates may include latitude and longitude coordinate information.

When it is determined that the coordinates outside the area are inverted coordinates, for example, based on the LBS data of the coordinates outside the area, it can be judged whether the coordinates outside the area are the inverted coordinates where the latitude and longitude are reversed. If so, perform the latitude and longitude replacement processing on the coordinates outside the area to obtain the replacement processing. If it is judged that the coordinates outside the area are not inverted coordinates, it means that the coordinates outside the area are real coordinates outside the area, and they are not the data of interest for data mining, so they are excluded. After performing replacement processing on the positioning service data with the latitude and longitude reversed, the obtained replacement coordinates are added to the positioning service data to obtain the updated positioning service data, thereby correcting the inverted error data.

It should be understood that, although the various steps in the flowchart of FIGS. 2-3 are displayed in sequence as indicated by the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless specifically stated in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least some of the steps in Figure 2-3 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. These sub-steps or stages The execution order of is not necessarily performed sequentially, but may be performed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

In one of the embodiments, as shown in FIG. 4, a device for generating geographic portraits of users is provided, including: a user data acquisition module 401, a data cluster acquisition module 403, a reference position cluster determination module 405, a cluster center determination module 407, and Geographical portrait production module 409, of which:

The user data obtaining module 401 is used to obtain location service data of business users;

The data cluster obtaining module 403 is used to perform density clustering processing on the location service data through a density-based clustering algorithm to obtain a data cluster of the location service data;

The reference position cluster determining module 405 is used to determine the reference position cluster to which the reference position of the geographic portrait of the business user belongs from the data cluster; wherein, the reference position of the geographic portrait includes the reference position when generating the geographic portrait of the user;

The cluster center determining module 407 is used to perform clustering processing on the reference position cluster to obtain the cluster center of the reference position cluster; and

The geographic portrait production module 409 is used to generate user geographic portraits of business users based on the cluster center and positioning service data.

In one of the embodiments, the data cluster obtaining module 403 includes a core point condition unit, a core point determination unit, and a data cluster determination unit; among them: the core point condition unit is used to obtain a preset core point coverage radius and core point coverage number Threshold; core point determination unit, used to cluster and iteratively process the positioning service data through the DBSCAN algorithm according to the core point coverage radius and the core point coverage number threshold to obtain the core point of the positioning service data; and the data cluster determination unit for Perform clustering iterative processing on each core point to obtain a data cluster of positioning service data composed of core points.

In one of the embodiments, the data cluster determination unit includes a combination threshold subunit and a core point combination subunit; wherein: the combination threshold subunit is used to obtain a preset core point combination distance threshold; and the core point combination subunit is used In accordance with the core point combination distance threshold, the DBSCAN algorithm is used to cluster and iteratively process each core point to obtain a data cluster of positioning service data composed of core points.

In one of the embodiments, the reference location of the geographic portrait includes a home address and a work address; the reference location cluster determination module 405 includes a data cluster analysis unit, a home work address cluster subunit, and a reference location cluster subunit; among them: a data cluster analysis unit, Used to determine the number of location service data in the data cluster and the time distribution of the location service data; the home work address cluster subunit is used to determine the home address cluster and the home address cluster to which the home address belongs according to the number and time distribution of the location service data in the data cluster The working address cluster to which the working address belongs; and the reference location cluster subunit, which is used to obtain the reference location cluster according to the home address cluster and the working address cluster.

In one of the embodiments, a clusterless processing module is further included, which is used to generate a user geographic portrait of the business user based on the positioning service data when the number of data clusters is zero.

In one of the embodiments, it further includes an out-of-area coordinate module, a replacement processing module, and a data update module; wherein: the out-of-area coordinate module is used to extract the out-of-area coordinates from the positioning service data; the replacement processing module is used to determine the area When the external coordinates are inverted coordinates, perform the latitude and longitude replacement processing on the coordinates outside the area to obtain the replacement coordinates after the replacement processing; and a data update module for adding the replacement coordinates to the positioning service data, and use the updated positioning service data as the positioning Service data.

Regarding the specific limitation of the user geographic portrait generating device, please refer to the above limitation on the user geographic portrait generating method, which will not be repeated here. Each module in the above-mentioned user geographic portrait generating device can be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules may be embedded in the form of hardware or independent of the processor in the computer equipment, or may be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

In one of the embodiments, a computer device is provided. The computer device may be a server or a terminal, and its internal structure diagram may be as shown in FIG. 5. The computer equipment includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile or volatile storage medium and internal memory. The non-volatile or volatile storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the non-volatile or volatile storage medium. The database of the computer equipment is used to store data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer readable instructions are executed by the processor, a method for generating geographic portraits of users is realized.

Those skilled in the art can understand that the structure shown in FIG. 5 is only a block diagram of part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.

A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the one or more processors execute the following steps:

Obtain location service data of business users;

In one of the embodiments, the processor further implements the following steps when executing the computer-readable instructions: obtaining the preset core point coverage radius and core point coverage number threshold; according to the core point coverage radius and core point coverage number threshold, the DBSCAN algorithm is used Perform clustering iterative processing on the positioning service data to obtain the core points of the positioning service data; and perform clustering iterative processing on each core point to obtain a data cluster of the positioning service data composed of the core points.

In one of the embodiments, the processor further implements the following steps when executing the computer-readable instructions: obtaining a preset core point combination distance threshold; and according to the core point combination distance threshold, perform clustering iterative processing on each core point through the DBSCAN algorithm , Get the data cluster of location service data composed of core points.

In one of the embodiments, the reference location of the geographic portrait includes the home address and the work address; the processor also implements the following steps when executing the computer-readable instructions: determining the number of positioning service data in the data cluster and the time distribution of the positioning service data; according to the data The number and time distribution of the location service data in the cluster determine the home address cluster to which the home address belongs and the working address cluster to which the work address belongs; and the reference location cluster is obtained according to the home address cluster and the working address cluster.

In one of the embodiments, the processor further implements the following steps when executing the computer-readable instructions: when the number of data clusters is 0, generate a user geographic portrait of the business user based on the location service data.

In one of the embodiments, the user geographic portrait of the business user includes: home location, workplace location, commuting distance, working city, residential city, whether to work across regions, hometown, whether to work outside, cities frequently visited on holidays, and whether on weekends At least one of the house, whether there is a house, and the nature of work.

In one of the embodiments, the processor further implements the following steps when executing the computer-readable instructions: extracting out-of-area coordinates from the positioning service data; when determining that the out-of-area coordinates are inverted coordinates, perform latitude and longitude replacement processing on the out-of-area coordinates to obtain Replace the replacement coordinates after replacement processing; and add the replacement coordinates to the location service data, and use the updated location service data as the location service data.

One or more computer-readable non-volatile storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors perform the following steps:

Obtain location service data of business users;

From the data cluster, determine the reference position cluster to which the reference position of the geographic portrait of the business user belongs; where the reference position of the geographic portrait includes the reference position when generating the geographic portrait of the user;

Wherein, the computer-readable storage medium may be non-volatile or volatile.

In one of the embodiments, when the computer-readable instructions are executed by the processor, the following steps are also implemented: obtaining preset core point coverage radius and core point coverage number threshold; according to the core point coverage radius and core point coverage threshold value, pass DBSCAN The algorithm performs clustering iterative processing on the positioning service data to obtain the core points of the positioning service data; and performs clustering iterative processing on each core point to obtain a data cluster of the positioning service data composed of core points.

In one of the embodiments, when the computer-readable instructions are executed by the processor, the following steps are also implemented: obtaining a preset core point combination distance threshold; and according to the core point combination distance threshold, clustering iterations of each core point through the DBSCAN algorithm After processing, a data cluster of positioning service data composed of core points is obtained.

In one of the embodiments, the reference location of the geographic portrait includes the home address and the work address; when the computer-readable instructions are executed by the processor, the following steps are also implemented: determining the number of location service data in the data cluster and the time period distribution of the location service data; The number and time distribution of the location service data in the data cluster determine the home address cluster to which the home address belongs and the working address cluster to which the work address belongs; and the reference location cluster is obtained according to the home address cluster and the working address cluster.

In one of the embodiments, when the computer-readable instructions are executed by the processor, the following steps are further implemented: when the number of data clusters is zero, a user geographic portrait of the business user is generated based on the location service data.

In one of the embodiments, when the computer-readable instructions are executed by the processor, the following steps are also implemented: extracting out-of-area coordinates from the positioning service data; when it is determined that the out-of-area coordinates are inverted coordinates, performing latitude and longitude replacement processing on the out-of-area coordinates, Obtain the replacement coordinates after replacement processing; and add the replacement coordinates to the location service data, and use the updated location service data as the location service data.

A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing relevant hardware through computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage. In the medium, when the computer-readable instructions are executed, they may include the processes of the above-mentioned method embodiments. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and/or volatile memory. Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not a limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered as the range described in this specification.

The above-mentioned embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can be made, and these all fall within the protection scope of this application. Therefore, the scope of protection of the patent of this application shall be subject to the appended claims.

Claims

A method for generating user geographic portraits, including:

Obtain location service data of business users;

Performing density clustering processing on the location service data by using a density-based clustering algorithm to obtain a data cluster of the location service data;

From the data cluster, determine the reference position cluster to which the reference position of the geographic portrait of the business user belongs; wherein the reference position of the geographic portrait includes the reference position when the geographic portrait of the user is generated;

Performing clustering processing on the reference position cluster to obtain the cluster center of the reference position cluster; and

Based on the cluster center and the positioning service data, a user geographic portrait of the business user is generated.
The method according to claim 1, wherein the performing density clustering processing on the location service data through a density-based clustering algorithm to obtain a data cluster of the location service data comprises:

Obtain preset core point coverage radius and core point coverage number threshold;

According to the core point coverage radius and the core point coverage number threshold, perform clustering iterative processing on the positioning service data through the DBSCAN algorithm to obtain the core points of the positioning service data; and

Perform clustering iterative processing on each of the core points to obtain a data cluster of the positioning service data composed of the core points.
The method according to claim 2, wherein said performing clustering iterative processing on each of said core points to obtain a data cluster of said positioning service data composed of said core points comprises:

Obtain the preset core point combination distance threshold; and

According to the core point combination distance threshold, clustering and iterative processing is performed on each of the core points through the DBSCAN algorithm to obtain the data cluster of the positioning service data composed of the core points.
The method according to claim 1, wherein the geographic portrait reference position includes a home address and a work address; and the determining the reference position cluster to which the geographic portrait reference position of the business user belongs from the data cluster includes :

Determining the number of the positioning service data in the data cluster and the time period distribution of the positioning service data;

Determine the home address cluster to which the home address belongs and the working address cluster to which the work address belongs according to the number of the location service data in the data cluster and the time period distribution; and

A reference location cluster is obtained according to the home address cluster and the work address cluster.
The method according to claim 4, wherein the determining the home address cluster to which the home address belongs and the working address cluster to which the work address belongs according to the number of the positioning service data in the data cluster and the time period distribution comprises :

According to the number of the location service data in the data cluster and the time period distribution, determine the proportion of the number of location service data corresponding to the day time period and the night time period respectively; and

The home address cluster to which the home address belongs and the working address cluster to which the work address belongs are determined according to the proportion.
The method according to claim 1, further comprising:

When the number of the data clusters is 0, the user geographic portrait of the business user is generated based on the positioning service data.
The method according to any one of claims 1 to 6, wherein the user geographic portrait of the business user includes: home location, work unit location, commuting distance, working city, residential city, whether to work across places, hometown, At least one of migrant workers, frequent visits to the city on holidays, weekend homes, availability of houses, and the nature of work.
The method according to any one of claims 1 to 6, wherein, after said obtaining the location service data of the business user, the method further comprises:

Extracting out-of-area coordinates from the positioning service data;

When it is determined that the coordinates outside the area are inverted coordinates, perform latitude and longitude replacement processing on the coordinates outside the area to obtain the replacement coordinates after the replacement processing; and

The replacement coordinates are added to the location service data, and the updated location service data is used as the location service data.
The method according to claim 8, wherein, when it is determined that the coordinates outside the area are inverted coordinates, the coordinates outside the area are subjected to latitude and longitude replacement processing to obtain the replacement coordinates after the replacement processing, the method further include:

Based on the data positioning service data before and after the outside coordinates, it is determined whether the outside coordinates are inverted coordinates.
A device for generating geographic portraits of users, which includes:

User data acquisition module for acquiring location service data of business users;

A data cluster obtaining module, configured to perform density clustering processing on the location service data through a density-based clustering algorithm to obtain a data cluster of the location service data;

The reference position cluster determining module is used to determine the reference position cluster to which the reference position of the geographic portrait of the business user belongs from the data cluster; wherein the reference position of the geographic portrait includes the reference position when generating the geographic portrait of the user;

A cluster center determination module, configured to perform clustering processing on the reference position cluster to obtain the cluster center of the reference position cluster; and

The geographic portrait production module is used to generate the user geographic portrait of the business user based on the cluster center and the positioning service data.
A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the one or more processors, the one or more Each processor performs the following steps:

Obtain location service data of business users;

Performing density clustering processing on the location service data by using a density-based clustering algorithm to obtain a data cluster of the location service data;

From the data cluster, determine the reference position cluster to which the reference position of the geographic portrait of the business user belongs; wherein the reference position of the geographic portrait includes the reference position when the geographic portrait of the user is generated;

Performing clustering processing on the reference position cluster to obtain the cluster center of the reference position cluster; and

Based on the cluster center and the positioning service data, a user geographic portrait of the business user is generated.
The computer device according to claim 11, wherein the processor further executes the following steps when executing the computer-readable instructions:

Obtain preset core point coverage radius and core point coverage number threshold;

According to the core point coverage radius and the core point coverage number threshold, perform clustering iterative processing on the positioning service data through the DBSCAN algorithm to obtain the core points of the positioning service data; and

Perform clustering iterative processing on each of the core points to obtain a data cluster of the positioning service data composed of the core points.
The computer device according to claim 12, wherein the processor further executes the following steps when executing the computer readable instruction:

Obtain the preset core point combination distance threshold; and

According to the core point combination distance threshold, clustering and iterative processing is performed on each of the core points through the DBSCAN algorithm to obtain the data cluster of the positioning service data composed of the core points.
The computer device according to claim 11, wherein the reference location of the geographic portrait includes a home address and a work address; the processor further executes the following steps when executing the computer-readable instruction:

Determining the number of the positioning service data in the data cluster and the time period distribution of the positioning service data;

Determine the home address cluster to which the home address belongs and the working address cluster to which the work address belongs according to the number of the location service data in the data cluster and the time period distribution; and

A reference location cluster is obtained according to the home address cluster and the work address cluster.
The computer device according to claim 14, wherein the processor further executes the following steps when executing the computer-readable instructions:

According to the number of the location service data in the data cluster and the time period distribution, determine the proportion of the number of location service data corresponding to the day time period and the night time period respectively; and

The home address cluster to which the home address belongs and the working address cluster to which the work address belongs are determined according to the proportion.
One or more computer-readable storage media storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform the following steps:

Obtain location service data of business users;

Performing density clustering processing on the location service data by using a density-based clustering algorithm to obtain a data cluster of the location service data;

From the data cluster, determine the reference position cluster to which the reference position of the geographic portrait of the business user belongs; wherein the reference position of the geographic portrait includes the reference position when the geographic portrait of the user is generated;

Performing clustering processing on the reference position cluster to obtain the cluster center of the reference position cluster; and

Based on the cluster center and the positioning service data, a user geographic portrait of the business user is generated.
The storage medium according to claim 16, wherein the following steps are further performed when the computer-readable instructions are executed by the processor:

Obtain preset core point coverage radius and core point coverage number threshold;

According to the core point coverage radius and the core point coverage number threshold, perform clustering iterative processing on the positioning service data through the DBSCAN algorithm to obtain the core points of the positioning service data; and

Perform clustering iterative processing on each of the core points to obtain a data cluster of the positioning service data composed of the core points.
The storage medium according to claim 17, wherein the following steps are further performed when the computer-readable instructions are executed by the processor:

Obtain the preset core point combination distance threshold; and

According to the core point combination distance threshold, clustering and iterative processing is performed on each of the core points through the DBSCAN algorithm to obtain the data cluster of the positioning service data composed of the core points.
The storage medium according to claim 16, wherein the reference location of the geographic portrait includes a home address and a work address; and the following steps are further performed when the computer-readable instructions are executed by the processor:

Determining the number of the positioning service data in the data cluster and the time period distribution of the positioning service data;

Determine the home address cluster to which the home address belongs and the working address cluster to which the work address belongs according to the number of the location service data in the data cluster and the time period distribution; and

A reference location cluster is obtained according to the home address cluster and the work address cluster.
The storage medium according to claim 19, wherein the following steps are further performed when the computer-readable instructions are executed by the processor:

According to the number of the location service data in the data cluster and the time period distribution, determine the proportion of the number of location service data corresponding to the day time period and the night time period respectively; and

The home address cluster to which the home address belongs and the working address cluster to which the work address belongs are determined according to the proportion.