WO2018120427A1 - 基于位置服务的风险评估方法、装置、设备和存储介质 - Google Patents

基于位置服务的风险评估方法、装置、设备和存储介质 Download PDF

Info

Publication number
WO2018120427A1
WO2018120427A1 PCT/CN2017/076473 CN2017076473W WO2018120427A1 WO 2018120427 A1 WO2018120427 A1 WO 2018120427A1 CN 2017076473 W CN2017076473 W CN 2017076473W WO 2018120427 A1 WO2018120427 A1 WO 2018120427A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
office
address
location
user
Prior art date
Application number
PCT/CN2017/076473
Other languages
English (en)
French (fr)
Inventor
吴振宇
王建明
肖京
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2018120427A1 publication Critical patent/WO2018120427A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance

Definitions

  • the present invention relates to the field of information processing technologies, and in particular, to a location service based risk assessment method, apparatus, device, and storage medium.
  • the user portrait (ie Persona) data is a virtual representative of the real user, and is a target user model built on the Marketing Data/Usability Data.
  • the user portrait (ie Persona) data is used to understand the user through user research, and according to the difference of the user's goals, behaviors and opinions, they are divided into different types to extract typical features such as user name and identification features (such as fingerprints). ), photos, contact information, home address, office space, occupation and income.
  • Each business form includes detailed data for improving user image data, including but not limited to user name, home address, and office space. , occupation and income.
  • an existing financial institution collects user portrait data by filling out a business form by a user
  • the financial institution cannot review the authenticity and accuracy of the user portrait data provided by the user, and the service that the payment cannot be recovered when the user provides the virtual user portrait data risk.
  • the financial institution can only collect the user portrait data in the process of handling the financial business, and cannot follow up the change of the user's portrait data in real time, and there is a business risk when the user portrait data changes greatly. If the user's home address and office space change, the financial institution cannot follow up the user's portrait data in real time, which may cause the financial institution to fail to recover the loan problem smoothly.
  • the invention provides a location service-based risk assessment method, device, device and storage medium, so as to solve the problem that the prior art cannot follow up the change of user portrait data in real time and cause business risk.
  • the present invention provides a location service based risk assessment method, including:
  • the geographic location information including POI information associated with the time
  • All POI information of the user in the preset period is divided into an office area data set and an address area data set according to a preset time limit;
  • the user portrait data includes a user ID, an office place, and a home address.
  • the present invention provides a location service based risk assessment apparatus, including:
  • An information acquiring unit configured to acquire geographic location information of the user based on the location service, where the geographic location information includes POI information associated with the time;
  • the information dividing unit is configured to divide all POI information of the user into the office area data set and the address area data set according to a preset time limit in the preset period;
  • a clustering analysis unit configured to cluster and analyze the office area data set and the address area data set respectively, and obtain office location dynamic information and address location dynamic information respectively;
  • An evaluation result output unit configured to compare the office location dynamic information and the address location dynamic information with pre-stored user image data, and output user risk assessment information
  • the user portrait data includes a user ID, an office place, and a home address.
  • the present invention provides a location service based risk assessment device comprising a processor and a memory, the memory storing computer executable instructions for executing the computer executable instructions to perform the following steps:
  • the geographic location information including POI information associated with the time
  • All POI information of the user in the preset period is divided into an office area data set and an address area data set according to a preset time limit;
  • the user portrait data includes a user ID, an office place, and a home address.
  • the present invention provides a non-transitory computer readable storage medium for storing one or more computer-executable instructions that are executed by one or more processors such that the one A location service based risk assessment method as described by multiple processors.
  • the present invention has the following advantages: in the location service-based risk assessment method, apparatus, device and storage medium provided by the present invention, the location information is obtained based on the location service, and the geographical location information has objectivity and real-time.
  • cluster analysis is performed on the office area data set and the address area data set respectively to obtain the office location dynamics.
  • the office area data set and the address area data set are respectively clustered, so that the data amount of the POI information in the office area data set and the address area data set is small, which is beneficial to improving the clustering effect and saving the clustering processing time.
  • the office location dynamic information and the address location dynamic information have objectivity
  • the office location dynamic information and the address location dynamic information are compared with the pre-stored user portrait data, and the output user risk assessment information has objectivity and can be effectively evaluated. Whether or not the user image data has changed can improve the risk of the risk of changes in the user's image data.
  • the office location dynamic information and the address location dynamic information obtained by clustering and analyzing the geographical location information in the preset period can objectively reflect the user's user portrait data, and the office location dynamic information can be dynamically collected. And the location location dynamic information is updated in real time to new user portrait data to improve the accuracy of the user risk assessment information.
  • FIG. 1 is a flow chart of a location service based risk assessment method in a first embodiment of the present invention.
  • FIG. 2 is a schematic block diagram of a location service based risk assessment apparatus in a second embodiment of the present invention.
  • FIG. 3 is a schematic diagram of a location service based risk assessment device in a third embodiment of the present invention.
  • FIG. 1 shows a flow chart of a location service based risk assessment method in this embodiment.
  • the location-based risk assessment method can be based on location-based risk assessment of financial institutions such as banks, insurance, and securities. Execution in preparation.
  • the location service based risk assessment method includes:
  • S1 Obtain geographical location information of the user based on the location service, where the geographic location information includes POI information associated with the time.
  • the geographical location information includes POI information of 0:00-24:00, and each POI information is used to indicate a point in the electronic map, including POI point name, longitude and latitude. And other information. Based on the user's geographic location information, you can find out the home address, office space, shopping places, entertainment places, fitness places, etc. that the user passes every day. It can be understood that obtaining the geographic location information of the user based on the location service has strong objectivity and reliability.
  • LBS Location Based Service
  • GIS Geographic Information System
  • LBS is to obtain the location information (geographic coordinates, or geodetic) of the mobile terminal user through the telecommunication mobile operator's radio communication network (such as GSM network, CDMA network) or external positioning method (such as GPS). Coordinates, a value-added service that provides users with corresponding services, supported by the Geographic Information System (GIS) platform.
  • GIS Geographic Information System
  • LBS is a combination of a mobile communication network and a computer network, and the two networks interact through a gateway.
  • the mobile terminal sends a request through the mobile communication network and transmits it to the LBS service platform through the gateway; the LBS service platform processes according to the user request and the current location of the user, and returns the result to the user through the gateway.
  • POI Point Of Interest
  • the POI can be presented on the electronic map to indicate a certain landmark, attraction and other location information on the electronic map.
  • the location service-based mobile terminal is a smart phone
  • the location function of the smart phone is obtained by enabling the LBS service platform to obtain the geographical location information of the smart phone in real time.
  • the LBS service platform is connected to a location service based risk assessment device in a financial institution such as a bank, a securities, an insurance, etc., so that the location service based risk assessment device can obtain the geographical location information of the user corresponding to the smart phone in real time.
  • the POI information is associated with time, and each POI information includes a date and a time, by which the POI information of the user at any time can be known. It can be understood that the geographical location information is associated with the user ID, and the user ID is used to identify the uniquely identified user, which may be an identity card number or a mobile phone number.
  • the time threshold may be preset, so that when the location service obtains the geographic location information of the user, only the POI information that the user stays at any location reaches the time threshold is obtained. The amount of data of the collected POI information associated with time is avoided, resulting in a problem of low processing efficiency.
  • S2 All POI information of the user in the preset period is divided into an office area data set and an address area data set according to a preset time limit.
  • the preset period may be any period of time before the current system time, and may be one month, three months, or Half a year, etc., can be set up according to the needs.
  • the preset time limit is the boundary used to divide office hours and rest time. All POI information can be divided into an office area data set and an address area data set based on the preset time limit to follow up the user portrait data based on the office area data set and the address area data set.
  • 8:00-20:00 is used as the office time
  • the corresponding geographical location information is the office area data set; correspondingly, the 20:00-the next day is 8:00 as the rest time, and the corresponding geographical position
  • the information is the address area data set.
  • S3 Perform cluster analysis on the office area data set and the address area data set respectively, and obtain the office location dynamic information and the address location dynamic information respectively.
  • the office location dynamic information is the result of cluster analysis of all POI information in the office area data set; the address location dynamic information is the result of cluster analysis of all POI information in the address area data set.
  • the office location dynamic information and the address location dynamic information can objectively reflect the daily life trajectory of the user during the preset period.
  • the office location dynamic information and the address location dynamic information can be used to realize the real-time follow-up of the user portrait data to ensure the follow-up user.
  • the objectivity of the image data is the result of cluster analysis of all POI information in the office area data set.
  • all POI information of the user in the preset period is divided into an office area data set and an address area data set according to a preset time limit, and then cluster analysis is performed on the office area data set and the address area data set respectively.
  • the data amount of the POI information in the office area data set and the address area data set is small, which is beneficial to improve the clustering effect and save the cluster processing time.
  • Step S3 specifically includes:
  • the DBSCAN clustering algorithm is used to cluster the POI information in the office area data set to obtain a plurality of office sub-clusters, and each office sub-cluster includes at least one office POI information.
  • the DBSCAN clustering algorithm is used to cluster the POI information in the address area data set to obtain a plurality of address sub-clusters, and each address sub-cluster includes at least one address POI information.
  • DBSCAN Density-Based Spatial Clustering of Applications with Noise
  • the algorithm divides regions of sufficient density into clusters and finds clusters of arbitrary shape in a spatial database with noise, which defines the cluster as the largest set of points connected by density.
  • the DBSCAN clustering algorithm has the advantages of fast clustering speed, efficient processing of noise and discovery of spatial clustering of arbitrary formation.
  • the scan radius (hereinafter referred to as eps) and the minimum inclusion point (minPts) of the preset office area data set are selected from an unvisited POI information, and the distance is within the eps (including All POI information of eps), the POI information and all POI information within the eps are output as an office sub-cluster, and the POI information in the office sub-cluster is the office POI information.
  • the information is output as a residential sub-cluster, and the POI information in the residential sub-cluster is the address POI information.
  • S32 Performing iterative clustering on each office sub-cluster by using K-MEANS clustering algorithm to obtain office centroid POI information of the office sub-cluster; the office location dynamic information includes office POI information and office centroid POI information.
  • the K-MEANS clustering algorithm is used to iteratively cluster each sub-cluster to obtain the address centroid POI information of the sub-cluster of the address; the address location dynamic information includes the address POI information and the address centroid POI information.
  • the K-MEANS algorithm is a typical distance-based algorithm.
  • the distance is used as the evaluation index of similarity. That is, the closer the distance between two objects is, the greater the similarity is.
  • Its calculation formula is Among them, the selection of the k initial cluster center points has a great influence on the clustering result, because in the first step of the algorithm, any k objects are randomly selected as the center of the initial cluster, initially representing a cluster. .
  • the algorithm reassigns each object to the nearest cluster for each object remaining in the dataset in each iteration based on its distance from each cluster center. If the value of J does not change before and after an iteration, the algorithm has converged.
  • K-MEANS algorithm can quickly and easily cluster data, has high efficiency and scalability for large data sets, time complexity is nearly linear, and is suitable for mining large-scale data sets.
  • the K-MEANS algorithm is used to iteratively aggregate the POI information in each office sub-cluster, and the value of the office centroid POI information of the office sub-cluster is obtained when the value of the office sub-cluster is not changed after the last iteration.
  • the K-MEANS algorithm is used to iteratively aggregate the POI information in each sub-cluster of the address. Until the last iteration, the values of the address centroid of the sub-cluster of the address sub-cluster are not changed. Address location dynamic information of address POI information and address centroid POI information.
  • the geographic location information of the user one day includes the following POI information associated with the time: A, B, C, D, E, F, G, H, F, I, J, K... E, D, A, if A is the home address, B and C are the locations in the eps near the home address, D and E are the locations acquired on the work road, F is the office address, and G is the location in the eps near the office address, H, I, J, K For consumer places and so on.
  • step S31 When the DBSCAN clustering algorithm is used for clustering in step S31, all the POI information in the eps near the home address and the home address can be clustered into an address sub-cluster output by setting the scan radius (eps) and the minimum inclusion point (minPts). All POI information in the eps near the office and office is clustered into an office sub-cluster output.
  • Step S32 uses the K-MEANS clustering algorithm to perform iterative aggregation for each office sub-cluster and the address sub-cluster to obtain the office centroid POI information of each office sub-cluster, and obtain the address centroid POI information of each sub-cluster.
  • the office centroid POI information is one of the office POI information of the office sub-cluster, and the address centroid POI information is the address sub-cluster.
  • One of the address POI information; the office location dynamic information includes the office POI information and the office centroid POI information, and the address location dynamic information includes the address POI information and the address centroid POI information.
  • the user portrait data includes a user ID, an office place, and a home address.
  • the user portrait data may be user portrait data collected by the user when the related business is handled, or may be user portrait data stored after the real-time follow-up based on the location service.
  • the office location dynamic information and the address location dynamic information are compared with the pre-stored user portrait data. Since the office location dynamic information and the address location dynamic information have objectivity, the user risk assessment information output after the comparison is objective.
  • the user risk assessment information includes low risk assessment information, medium risk assessment information, and high risk assessment information.
  • the office can be The position dynamic information and the address location dynamic information are updated in real time to new user portrait data, so that the new user portrait data can be compared in the next evaluation to improve the accuracy of the user risk assessment information.
  • Step S4 specifically includes:
  • S41 Determine whether the office location matches the office centroid POI information, and determine whether the home address matches the address centroid POI information.
  • a is an office space
  • b is a home address
  • A is an office centroid POI information
  • U is an office sub-cluster
  • B is an address centroid POI information
  • Y is an address sub-cluster
  • the office location matches the office quality POI information and the home address matches the address centroid POI information, that is, state 1, the corresponding risk assessment level is level I, and the low risk assessment information is output, indicating that the user is within the preset period.
  • the location information obtained based on the location service matches the user image data stored in advance, and the location of the office and home address does not change.
  • the risk assessment level of the VI level can be output as the high risk assessment information, indicating the geographic location information of the user acquired by the location service based on the location service and the user image data stored in advance. There is no match at all, and the office space and home address have changed.
  • the corresponding risk assessment level is Grade IV, Grade V, and Level VI.
  • the risk assessment grades of Level IV, Grade V, and Level VI can be output as high-risk assessment information, indicating that the user is The geographic location information of the user acquired based on the location service during the preset period does not partially match the user image data stored in advance, and the office location and/or home address changes.
  • the state other than the low risk assessment information and the high risk assessment information corresponds to the risk assessment information.
  • the similarity detection algorithm is used in step S4 to compare the office location dynamic information and the address location dynamic information with the pre-stored user image data, and output user risk assessment information.
  • the first detection value of the office location and office centroid POI information and the second detection value of the home address and the address centroid POI information are respectively calculated by the similarity detection algorithm. If the first detected value is greater than the first threshold, it is determined that the office location matches the office centroid POI information, and vice versa. If the second detected value is greater than the first threshold, then the family is determined to live The address matches the address POI information of the address, and vice versa.
  • the similarity detection algorithm is used to separately calculate the third detection value of the office POI information in the office space and the office sub-cluster, and/or the fourth detection value of the address POI information in the home address and the address sub-cluster. If the third detection value is greater than the second threshold, it is determined that the office location and the office POI information in the office sub-cluster match, and vice versa. If the fourth detected value is greater than the second threshold, it is determined that the home address matches the address POI information in the residential sub-cluster, and vice versa.
  • the number of user portraits also includes the manager ID and the contact details of the manager.
  • the location service based risk assessment method further includes: sending the office location dynamic information and/or the address location dynamic information to the accountant corresponding to the accountant ID when outputting the high risk assessment information.
  • the high-risk evaluation information When the high-risk evaluation information is output, it indicates that the office location dynamic information and the address location dynamic information have changed, or the office location dynamic information and/or the residential location dynamic information change, and therefore, the changed office location dynamic information needs to be changed.
  • the address location dynamic information is sent to the accountant ID, and the account personnel corresponding to the manager ID correspond to the user image data, such as verifying the information, updating the user image data, etc., to avoid dynamic information due to the office location.
  • the change in the dynamic information of the address location has led to an increase in the business risk of financial services such as loans provided by financial institutions.
  • the location information is used to obtain the geographic location information of the user, and the geographic location information has objectivity and real-time performance.
  • cluster analysis is performed on the office area data set and the address area data set respectively to obtain the office location dynamics.
  • Information and address location dynamics are respectively clustered, so that the data amount of the POI information in the office area data set and the address area data set is small, which is beneficial to improving the clustering effect and saving the clustering processing time.
  • the office location dynamic information and the address location dynamic information have objectivity
  • the office location dynamic information and the address location dynamic information are compared with the pre-stored user portrait data, and the output user risk assessment information has objectivity and can be effectively evaluated. Whether or not the user image data changes can improve the management of the risk of changes in the user's image data.
  • the office location dynamic information and the address location dynamic information obtained by clustering and analyzing the geographical location information in the preset period can objectively reflect the user's user portrait data, and the office location dynamic information can be dynamically collected. And the location location dynamic information is updated in real time to new user portrait data to improve the accuracy of the user risk assessment information.
  • FIG. 2 shows a flow chart of the location service based risk assessment apparatus in this embodiment.
  • the location service based risk assessment device may be a location based service risk assessment device installed in a financial institution such as a bank, insurance, securities, or the like.
  • the location service-based risk assessment apparatus includes an information acquisition unit 10 and an information plan.
  • the subunit 20, the cluster analysis unit 30, the evaluation result output unit 40, and the information transmitting unit 50 includes an information acquisition unit 10 and an information plan.
  • the information obtaining unit 10 is configured to acquire geographic location information of the user based on the location service, where the geographic location information includes POI information associated with the time.
  • the geographical location information includes POI information of 0:00-24:00, and each POI information is used to indicate a point in the electronic map, including POI point name, longitude and latitude. And other information. Based on the user's geographic location information, you can find out the home address, office space, shopping places, entertainment places, fitness places, etc. that the user passes every day. It can be understood that obtaining the geographic location information of the user based on the location service has strong objectivity and reliability.
  • LBS Location Based Service
  • GIS Geographic Information System
  • LBS is to obtain the location information (geographic coordinates, or geodetic) of the mobile terminal user through the telecommunication mobile operator's radio communication network (such as GSM network, CDMA network) or external positioning method (such as GPS). Coordinates, a value-added service that provides users with corresponding services, supported by the Geographic Information System (GIS) platform.
  • GIS Geographic Information System
  • LBS is a combination of a mobile communication network and a computer network, and the two networks interact through a gateway.
  • the mobile terminal sends a request through the mobile communication network and transmits it to the LBS service platform through the gateway; the LBS service platform processes according to the user request and the current location of the user, and returns the result to the user through the gateway.
  • POI Point Of Interest
  • the POI can be presented on the electronic map to indicate a certain landmark, attraction and other location information on the electronic map.
  • the location service-based mobile terminal is a smart phone
  • the location function of the smart phone is obtained by enabling the LBS service platform to obtain the geographical location information of the smart phone in real time.
  • the LBS service platform is connected to a location service based risk assessment device in a financial institution such as a bank, a securities, an insurance, etc., so that the location service based risk assessment device can obtain the geographical location information of the user corresponding to the smart phone in real time.
  • the POI information is associated with time, and each POI information includes a date and a time, by which the POI information of the user at any time can be known. It can be understood that the geographical location information is associated with the user ID, and the user ID is used to identify the uniquely identified user, which may be an identity card number or a mobile phone number.
  • the time threshold may be preset, so that when the location service obtains the geographic location information of the user, only the POI information that the user stays at any location reaches the time threshold is obtained. The amount of data of the collected POI information associated with time is avoided, resulting in a problem of low processing efficiency.
  • the information dividing unit 20 is configured to divide all POI information of the user into the office area data set and the address area data set according to a preset time limit within a preset period.
  • the preset period may be any period of time before the current system time, and may be one month, three months or half. Years, etc., can be set up according to the needs.
  • the preset time limit can be a boundary for dividing office hours and rest time. All POI information can be divided into an office area data set and an address area data set based on the preset time limit to follow up the user portrait data based on the office area data set and the address area data set.
  • 8:00-20:00 is used as the office time
  • the corresponding geographical location information is the office area data set; correspondingly, the 20:00-the next day is 8:00 as the rest time, and the corresponding geographical position
  • the information is the address area data set.
  • the cluster analysis unit 30 is configured to perform cluster analysis on the office area data set and the address area data set respectively, and obtain office location dynamic information and address location dynamic information respectively.
  • the office location dynamic information is the result of cluster analysis of all POI information in the office area data set;
  • the address location dynamic information is the result of cluster analysis of all POI information in the address area data set.
  • the office location dynamic information and the address location dynamic information can objectively reflect the daily life trajectory of the user during the preset period.
  • the office location dynamic information and the address location dynamic information can be used to realize the real-time follow-up of the user portrait data to ensure the follow-up user.
  • the objectivity of the image data is configured to perform cluster analysis on the office area data set and the address area data set respectively, and obtain office location dynamic information and address location dynamic information respectively.
  • the office location dynamic information is the result of cluster analysis of all POI information in the office area data set
  • the address location dynamic information is the result of cluster analysis of all POI information in the address area data set.
  • all POI information of the user in the preset period is divided into an office area data set and an address area data set according to a preset time limit, and then cluster analysis is performed on the office area data set and the address area data set respectively.
  • the data amount of the POI information in the office area data set and the address area data set is small, which is beneficial to improve the clustering effect and save the cluster processing time.
  • the cluster analysis unit 30 specifically includes a first cluster sub-unit 31 and a second cluster sub-unit 32.
  • the first cluster sub-unit 31 is configured to cluster the POI information in the office area data set by using the DBSCAN clustering algorithm to obtain a plurality of office sub-clusters, and each office sub-cluster includes at least one office POI information.
  • the DBSCAN clustering algorithm is used to cluster the POI information in the address area data set to obtain a plurality of address sub-clusters, and each address sub-cluster includes at least one address POI information.
  • DBSCAN Density-Based Spatial Clustering of Applications with Noise
  • the algorithm divides regions of sufficient density into clusters and finds clusters of arbitrary shape in a spatial database with noise, which defines the cluster as the largest set of points connected by density.
  • the DBSCAN clustering algorithm has the advantages of fast clustering speed, efficient processing of noise and discovery of spatial clustering of arbitrary formation.
  • the scan radius (hereinafter referred to as eps) and the minimum inclusion point (minPts) of the preset office area data set are selected from an unvisited POI information, and the distance is within the eps (including All POI information of eps), the POI information and all POI information within the eps are output as an office sub-cluster, and the POI information in the office sub-cluster is the office POI information.
  • the scan radius (eps) and the minimum inclusion point (minPts) of the preset address area data set starting with an unvisited POI message, find the distance with it in eps
  • All POI information (including eps) the POI information and all POI information within the eps are output as a residential sub-cluster, and the POI information in the sub-cluster is the address POI information.
  • the second cluster sub-unit 32 is configured to perform iterative clustering on each office sub-cluster by using a K-MEANS clustering algorithm to obtain office centroid POI information of the office sub-cluster; the office location dynamic information includes office POI information and office centroid POI information.
  • the K-MEANS clustering algorithm is used to iteratively cluster each sub-cluster to obtain the address centroid POI information of the sub-cluster of the address; the address location dynamic information includes the address POI information and the address centroid POI information.
  • the K-MEANS algorithm is a typical distance-based algorithm.
  • the distance is used as the evaluation index of similarity. That is, the closer the distance between two objects is, the greater the similarity is.
  • Its calculation formula is Among them, the selection of the k initial cluster center points has a great influence on the clustering result, because in the first step of the algorithm, any k objects are randomly selected as the center of the initial cluster, initially representing a cluster. .
  • the algorithm reassigns each object to the nearest cluster for each object remaining in the dataset in each iteration based on its distance from each cluster center. If the value of J does not change before and after an iteration, the algorithm has converged.
  • K-MEANS algorithm can quickly and easily cluster data, has high efficiency and scalability for large data sets, time complexity is nearly linear, and is suitable for mining large-scale data sets.
  • the K-MEANS algorithm is used to iteratively aggregate the POI information in each office sub-cluster, and the value of the office centroid POI information of the office sub-cluster is obtained when the value of the office sub-cluster is not changed after the last iteration.
  • the K-MEANS algorithm is used to iteratively aggregate the POI information in each sub-cluster of the address. Until the last iteration, the values of the address centroid of the sub-cluster of the address sub-cluster are not changed. Address location dynamic information of address POI information and address centroid POI information.
  • the geographic location information of the user one day includes the following POI information associated with the time: A, B, C, D, E, F, G, H, F, I, J, K... E, D, A, if A is the home address, B and C are the locations in the eps near the home address, D and E are the locations acquired on the work road, F is the office address, and G is the location in the eps near the office address, H, I, J, K For consumer places and so on.
  • the DBSCAN clustering algorithm is used for clustering in the first cluster sub-unit 31, all the POI information in the eps near the home address and the home address can be clustered by setting the scan radius (eps) and the minimum inclusion point (minPts).
  • An address sub-cluster output clusters all POI information in the eps near the office and office to an office sub-cluster output.
  • the second cluster sub-unit 32 performs an iterative aggregation on each office sub-cluster and the address sub-cluster by using a K-MEANS clustering algorithm to obtain the office centroid POI information of each office sub-cluster, and obtain the sub-cluster address of each address.
  • Centroid POI information is one of the office POI information of the office sub-cluster, and the address centroid POI information is one of the address POI information of the address sub-cluster; the address location dynamic information includes the address POI information And address centroid POI information.
  • the evaluation result output unit 40 is configured to compare the office location dynamic information and the address location dynamic information with the pre-stored user image data, and output the user risk assessment information.
  • the user portrait data includes a user ID, an office place, and a home address.
  • the user portrait data may be user portrait data collected by the user when the related business is handled, or may be user portrait data stored after the real-time follow-up based on the location service.
  • the office location dynamic information and the address location dynamic information are compared with the pre-stored user portrait data. Since the office location dynamic information and the address location dynamic information have objectivity, the user risk assessment information output after the comparison is objective.
  • the user risk assessment information includes low risk assessment information, medium risk assessment information, and high risk assessment information.
  • the office can be The position dynamic information and the address location dynamic information are updated in real time to new user portrait data, so that the new user portrait data can be compared in the next evaluation to improve the accuracy of the user risk assessment information.
  • the evaluation result output unit 40 specifically includes a first judgment subunit 41, a first processing subunit 42, a second judging subunit 43, and a second processing subunit 44.
  • the first determining sub-unit 41 is configured to determine whether the office location matches the office centroid POI information and determine whether the home address matches the address centroid POI information.
  • the first processing sub-unit 42 is configured to output low-risk evaluation information if the matches are homogeneous.
  • the second determining sub-unit 43 is configured to determine, if the non-uniform matching, the office location matches the office POI information in the office sub-cluster, and/or determine whether the home address matches the address POI information in the address sub-cluster ;
  • the second processing sub-unit 44 is configured to output high-risk assessment information or medium-risk assessment information according to the determination result.
  • a is an office space
  • b is a home address
  • A is an office centroid POI information
  • U is an office sub-cluster
  • B is an address centroid POI information
  • Y is an address sub-cluster
  • the office location matches the office quality POI information and the home address matches the address centroid POI information, that is, state 1, the corresponding risk assessment level is level I, and the low risk assessment information is output, indicating that the user is within the preset period.
  • the location information obtained based on the location service matches the user image data stored in advance, and the location of the office and home address does not change.
  • the risk assessment level of the VI level can be output as the high risk assessment information, indicating the geographic location information of the user acquired by the location service based on the location service and the user image data stored in advance. There is no match at all, and the office space and home address have changed.
  • the corresponding risk assessment level is Grade IV, Grade V, and Level VI.
  • the risk assessment grades of Level IV, Grade V, and Level VI can be output as high-risk assessment information, indicating that the user is The geographic location information of the user acquired based on the location service during the preset period does not partially match the user image data stored in advance, and the office location and/or home address changes.
  • the state other than the low risk assessment information and the high risk assessment information corresponds to the risk assessment information.
  • the evaluation result output unit 40 compares the office location dynamic information and the address location dynamic information with the pre-stored user image data by using a similarity detection algorithm, and outputs user risk assessment information.
  • the first detection value of the office location and office centroid POI information and the second detection value of the home address and the address centroid POI information are respectively calculated by the similarity detection algorithm. If the first detected value is greater than the first threshold, it is determined that the office location matches the office centroid POI information, and vice versa. If the second detected value is greater than the first threshold, then the family is determined to live The address matches the address POI information of the address, and vice versa.
  • the similarity detection algorithm is used to separately calculate the third detection value of the office POI information in the office space and the office sub-cluster, and/or the fourth detection value of the address POI information in the home address and the address sub-cluster. If the third detection value is greater than the second threshold, it is determined that the office location and the office POI information in the office sub-cluster match, and vice versa. If the fourth detected value is greater than the second threshold, it is determined that the home address matches the address POI information in the residential sub-cluster, and vice versa.
  • the number of user portraits also includes the manager ID and the contact details of the manager.
  • the location service based risk assessment apparatus further includes an information sending unit 50, configured to send the office location dynamic information and/or the address location dynamic information to the account personnel corresponding to the accountant ID when outputting the high risk assessment information.
  • the high-risk evaluation information When the high-risk evaluation information is output, it indicates that the office location dynamic information and the address location dynamic information have changed, or the office location dynamic information and/or the residential location dynamic information change, and therefore, the changed office location dynamic information needs to be changed.
  • the address location dynamic information is sent to the accountant ID, and the account personnel corresponding to the manager ID correspond to the user image data, such as verifying the information, updating the user image data, etc., to avoid dynamic information due to the office location.
  • the change in the dynamic information of the address location has led to an increase in the business risk of financial services such as loans provided by financial institutions.
  • the geographic location information of the user is obtained based on the location service, and the geographic location information has objectivity and real-time performance.
  • cluster analysis is performed on the office area data set and the address area data set respectively to obtain the office location dynamics.
  • the office area data set and the address area data set are respectively clustered, so that the data amount of the POI information in the office area data set and the address area data set is small, which is beneficial to improving the clustering effect and saving the clustering processing time.
  • the office location dynamic information and the address location dynamic information have objectivity
  • the office location dynamic information and the address location dynamic information are compared with the pre-stored user portrait data, and the output user risk assessment information has objectivity and can be effectively evaluated. Whether or not the user image data changes can improve the management of the risk of changes in the user's image data.
  • the office location dynamic information and the address location dynamic information obtained by clustering and analyzing the geographical location information in the preset period can objectively reflect the user's user portrait data, and the office location dynamic information can be dynamically collected. And the location location dynamic information is updated in real time to new user portrait data to improve the accuracy of the user risk assessment information.
  • the device 300 can be a mobile terminal, a desktop computer, a server, or the like having a certain data processing capability, such as a mobile phone, a tablet computer, a personal digital assistant (PDA), or an on-board computer.
  • a mobile terminal such as a mobile phone, a tablet computer, a personal digital assistant (PDA), or an on-board computer.
  • PDA personal digital assistant
  • the device 300 The radio frequency (RF) circuit 301, the memory 302, the input module 303, the display module 304, the processor 305, the audio circuit 306, the WiFi (Wireless Fidelity) module 307, and the power source 308 are included.
  • RF radio frequency
  • the input module 303 and the display module 304 are used as user interaction devices of the device 300 for implementing interaction between the user and the device 300, for example, receiving a risk assessment instruction input by the user and displaying corresponding user risk assessment information.
  • the input module 303 is configured to receive a risk assessment instruction input by the user, and send the risk assessment instruction to the processor 305, where the risk assessment instruction includes office location dynamic information and address location dynamic information.
  • the processor 305 is configured to acquire user risk assessment information based on the risk assessment instruction, and send the user risk assessment information to the display module 304.
  • the display module 304 receives and displays the user risk assessment information.
  • the input module 303 can be configured to receive numeric or character information input by a user, and to generate signal inputs related to user settings and function control of the device 300.
  • the input module 303 can include a touch panel 3031.
  • the touch panel 3031 also referred to as a touch screen, can collect touch operations on or near the user (such as the operation of the user using any suitable object or accessory such as a finger or a stylus on the touch panel 3031), and according to the preset The programmed program drives the corresponding connection device.
  • the touch panel 3031 may include two parts of a touch detection device and a touch controller.
  • the touch detection device detects the touch orientation of the user, and detects a signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts the touch information into contact coordinates, and sends the touch information.
  • the processor 305 is provided and can receive commands from the processor 305 and execute them.
  • the touch panel 3031 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves.
  • the input module 303 may further include other input devices 3032.
  • the other input devices 3032 may include but are not limited to physical keyboards, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, joysticks, and the like. One or more of them.
  • display module 304 can be used to display information entered by a user or information provided to a user and various menu interfaces of device 300.
  • the display module 304 can include a display panel 3041.
  • the display panel 3041 can be configured in the form of an LCD or an Organic Light-Emitting Diode (OLED).
  • the touch panel 3031 can cover the display panel 3041 to form a touch display screen.
  • the touch display screen detects a touch operation on or near it, it is transmitted to the processor 305 to determine the type of the touch event, and then processed.
  • the 305 provides a corresponding visual output on the touch display based on the type of touch event.
  • the touch display includes an application interface display area and a common control display area.
  • the arrangement manner of the application interface display area and the display area of the common control is not limited, and the arrangement manner of the two display areas can be distinguished by up-and-down arrangement, left-right arrangement, and the like.
  • the application interface display area can be used to display the interface of the application. Each interface can contain interface elements such as at least one application's icon and/or widget desktop control.
  • the application interface display area can also be an empty interface that does not contain any content.
  • the common control display area is used to display controls with high usage, for example, setting buttons, Application icons such as interface numbers, scroll bars, and phone book icons.
  • the WiFi module 307 can be used as the network interface of the device 300 to implement data interaction between the device 300 and other devices.
  • the network interface can be connected to the remote storage device and the external display device through network communication.
  • the network interface is configured to receive the geographic location information of the user based on the location service sent by the remote storage device, and send the geographic location information to the processor 305; User risk assessment information, and the user risk information is sent to the external display device.
  • the external display device can receive and display the user risk information.
  • the remote storage device connected to the network interface through the WiFi network may be a cloud server or other database, where the remote storage device stores location information of the user based on the location service, where the geographic location information can be obtained.
  • the WiFi network is sent to the WiFi module 307, and the WiFi module 307 sends the acquired geographic location information to the processor 305, and sends the user risk information received from the processor 305 to the external display screen.
  • the memory 302 includes a first memory 3021 and a second memory 3022.
  • the first memory 3021 can be a non-transitory computer readable storage medium having an operating system, a database, and computer executable instructions stored thereon.
  • Computer executable instructions are executable by processor 305 for implementing a location based service based risk assessment method of the embodiment shown in FIG.
  • the database on the memory 302 is used to store various types of data, such as various data involved in the above-described location service based risk assessment method, such as geographic location information and user portrait data.
  • the second memory 3021 can be an internal memory of the device 300 that provides a cached operating environment for operating systems, databases, and computer executable instructions in a non-transitory computer readable storage medium.
  • processor 305 is the control center of device 300, which connects various portions of the entire handset using various interfaces and lines, by running or executing computer-executable collections and/or databases stored in first memory 3021. The data, performing various functions and processing data of the device 300, thereby performing overall monitoring of the device 300.
  • processor 305 can include one or more processing modules.
  • the processor 305 by executing the stored computer executable instructions and/or data in the database in the first memory 3021, the processor 305 is configured to perform the following steps: acquiring geographic location information of the user based on the location service, the geographic The location information includes POI information associated with time; all POI information of the user is divided into an office area data set and an address area data set according to a preset time limit within a preset period; and the office area data set and the address area data set are Performing cluster analysis separately to obtain office location dynamic information and address location dynamic information respectively; comparing the office location dynamic information and the address location dynamic information with pre-stored user portrait data, and outputting user risk assessment information;
  • the user image data includes a user ID, an office location, and a home address.
  • the clustering analysis is performed on the office area data set and the address area data set respectively, respectively Office location dynamic information and address location dynamic information, including:
  • the DBSCAN clustering algorithm is used to cluster the POI information in the office area data set to obtain a plurality of office sub-clusters, each office sub-cluster includes at least one office POI information; and the address area data is concentrated by using a DBSCAN clustering algorithm.
  • the POI information is clustered to obtain a plurality of address sub-clusters, and each address sub-cluster includes at least one address POI information;
  • Performing iterative clustering on each of the office sub-clusters by using a K-MEANS clustering algorithm acquiring office centroid POI information of the office sub-cluster, and outputting the office centroid POI information as the office location dynamic information;
  • the K-MEANS clustering algorithm performs iterative clustering on each of the address sub-clusters, acquires the address centroid POI information of the address sub-cluster, and outputs the address centroid POI information as the address location dynamic information.
  • the comparing the office location dynamic information and the address location dynamic information with the pre-stored user image data, and outputting the user risk assessment information including:
  • the low risk assessment information is output
  • the high risk evaluation information or the medium risk evaluation information is output according to the judgment result.
  • the processor 305 further performs the step of comparing the office location dynamic information and the address location dynamic information with pre-stored user portrait data by using a similarity detection algorithm.
  • the number of user portraits further includes a manager ID
  • the processor 305 further performs the step of: transmitting the office location dynamic information and/or the address location dynamic information to the accountant corresponding to the accountant ID when outputting the high risk assessment information.
  • the location service-based risk assessment device 300 acquires the geographic location information of the user based on the location service, and the geographic location information has objectivity and real-time performance.
  • cluster analysis is performed on the office area data set and the address area data set respectively to obtain the office location dynamics.
  • Information and address location dynamics are respectively clustered, so that the data amount of the POI information in the office area data set and the address area data set is small, which is beneficial to improving the clustering effect and saving the clustering processing time.
  • the office location dynamic information and the address location dynamic information have objectivity
  • the office location dynamic information and the address location dynamic information are compared with the pre-stored user portrait data, and the output user risk assessment information has objectivity and can be effectively evaluated.
  • User Whether or not the image data has changed can improve the risk of the risk of changes in the user's image data.
  • the office location dynamic information and the address location dynamic information obtained by clustering and analyzing the geographical location information in the preset period can objectively reflect the user's user portrait data, and the office location dynamic information can be dynamically collected. And the location location dynamic information is updated in real time to new user portrait data to improve the accuracy of the user risk assessment information.
  • the embodiment provides a non-transitory computer readable storage medium.
  • the non-transitory computer readable storage medium is for storing one or more computer executable instructions.
  • the computer executable instructions are executed by one or more processors, such that the one or more processors perform the location service based risk assessment method described in the first embodiment. To avoid repetition, details are not described herein again.
  • modules and algorithm steps of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods for implementing the described functions for each particular application, but such implementation should not be considered to be beyond the scope of the present invention.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the modules is only a logical function division.
  • there may be another division manner for example, multiple modules or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or module, and may be electrical, mechanical or otherwise.
  • the modules described as separate components may or may not be physically separated.
  • the components displayed as modules may or may not be physical modules, that is, may be located in one place, or may be distributed to multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.
  • the functions, if implemented in the form of software functional modules and sold or used as separate products, may be stored in a computer readable storage medium.
  • the machine software product is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种基于位置服务的风险评估方法、装置、设备和存储介质，该方法包括：基于位置服务获取用户的地理位置信息，地理位置信息包括与时间相关联的POI信息（S1）；对用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集（S2）；对办公区域数据集和住址区域数据集分别进行聚类分析，分别获取办公位置动态信息和住址位置动态信息（S3）；将办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息（S4）。该基于位置服务的风险评估方法中，输出的用户风险度评估信息具有客观性，可有效评估用户画像数据是否发生变化，可提高用户画像数据变动产生的风险的管控。

Description

基于位置服务的风险评估方法、装置、设备和存储介质 技术领域
本发明涉及信息处理技术领域，尤其涉及一种基于位置服务的风险评估方法、装置、设备和存储介质。
背景技术
现有银行、证券、保险等金融机构在给用户提供金融业务时，需采集并审核用户画像数据，以审核用户身份及财富状态，从而实现对其提供的金融业务的风险控制。其中，用户画像(即Persona)数据是真实用户的虚拟代表，是建立在一系统真实数据(Marketing Data/Usability Data)之上的目标用户模型。用户画像(即Persona)数据是通过用户调研去了解用户，并根据用户的目标、行为和观点的差异，将他们区分为不同类型，以抽取出典型特征，如用户姓名、身份识别特征(如指纹)、照片、联系方式、家庭住址、办公场所、职业和收入等。
现有金融机构在提供贷款或其他金融业务时，需用户填写相关的业务表格，每一业务表格中包括多项可完善用户画像数据的详细数据，包括但不限于用户姓名、家庭住址、办公场所、职业和收入等。现有金融机构通过用户填写业务表格方式采集用户画像数据时，金融机构无法对用户提供的用户画像数据的真实性和准确性进行审核，在用户提供虚拟的用户画像数据时存在货款无法收回的业务风险。而且，金融机构只能采集到用户在办理金融业务过程中的用户画像数据，无法实时跟进用户画像数据的变化情况，在用户画像数据发生较大变化时存在业务风险。如用户的家庭住址和办公场所等发生变化时，金融机构无法对用户画像数据实时跟进，可能导致金融机构无法顺利追讨贷款问题发生。
发明内容
本发明提供一种基于位置服务的风险评估方法、装置、设备和存储介质，以解决现有技术无法实时跟进用户画像数据变化而导致业务风险存在的问题。
本发明解决其技术问题所采用的技术方案是：
第一方面，本发明提供一种基于位置服务的风险评估方法，包括：
基于位置服务获取用户的地理位置信息，所述地理位置信息包括与时间相关联的POI信息；
对用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集；
对所述办公区域数据集和住址区域数据集分别进行聚类分析，分别获取办公位置动态信息和住址位置动态信息；
将所述办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息；
其中，所述用户画像数据包括用户ID、办公场所和家庭住址。
第二方面，本发明提供一种基于位置服务的风险评估装置，包括：
信息获取单元，用于基于位置服务获取用户的地理位置信息，所述地理位置信息包括与时间相关联的POI信息；
信息划分单元，用于对用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集；
聚类分析单元，用于对所述办公区域数据集和住址区域数据集分别进行聚类分析，分别获取办公位置动态信息和住址位置动态信息；
评估结果输出单元，用于将所述办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息；
其中，所述用户画像数据包括用户ID、办公场所和家庭住址。
第三方面，本发明提供一种基于位置服务的风险评估设备，包括处理器及存储器，所述存储器存储有计算机可执行指令，所述处理器用于执行所述计算机可执行指令以执行如下步骤：
基于位置服务获取用户的地理位置信息，所述地理位置信息包括与时间相关联的POI信息；
对用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集；
对所述办公区域数据集和住址区域数据集分别进行聚类分析，分别获取办公位置动态信息和住址位置动态信息；
将所述办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息；
其中，所述用户画像数据包括用户ID、办公场所和家庭住址。
第四方面，本发明提供一种非易失性计算机可读存储介质，用于存储一个或多个计算机可执行指令，所述计算机可执行指令被一个或多个处理器执行，使得所述一个或多个处理器所述的基于位置服务的风险评估方法。
本发明与现有技术相比具有如下优点：本发明所提供的基于位置服务的风险评估方法、装置、设备和存储介质中，基于位置服务获取用户的地理位置信息，地理位置信息具有客观性和实时性。通过对用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集，再对办公区域数据集和住址区域数据集分别进行聚类分析，以获取办公位置动态信息和住址位置动态信息。其中，划分办公区域数据集和住址区域数据集并分别聚类，使得办公区域数据集和住址区域数据集中的POI信息的数据量较小，有利于提高聚类效果，节省聚类处理时间。由于办公位置动态信息和住址位置动态信息具有客观性，使得利用办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行比对，输出的用户风险度评估信息具有客观性，可有效评估用户画像数据是否发生变化，可提高用户画像数据变动产生的风险的管控。由于实时采集用户的地理位置信息，并对预设期间内的地理位置信息进行聚类分析获取到的办公位置动态信息和住址位置动态信息可客观反映用户的用户画像数据，可将办公位置动态信息和住址位置动态信息实时更新为新的用户画像数据，以提高用户风险度评估信息的准确性。
附图说明
下面将结合附图及实施例对本发明作进一步说明，附图中：
图1是本发明第一实施例中基于位置服务的风险评估方法的一流程图。
图2是本发明第二实施例中基于位置服务的风险评估装置的一原理框图。
图3是本发明第三实施例中基于位置服务的风险评估设备的一示意图。
具体实施方式
为了对本发明的技术特征、目的和效果有更加清楚的理解，现对照附图详细说明本发明的具体实施方式。
第一实施例
图1示出本实施例中基于位置服务的风险评估方法的一流程图。如图1所示，该基于位置服务的风险评估方法可以由银行、保险、证券等金融机构的基于位置服务的风险评估设 备中执行。如图1所示，该基于位置服务的风险评估方法包括：
S1：基于位置服务获取用户的地理位置信息，地理位置信息包括与时间相关联的POI信息。
以任一用户一天的地理位置信息为例，该地理位置信息中包括0：00—24：00的POI信息，每一POI信息用于指示电子地图中的一点，包括POI点名称、经度和纬度等信息。基于用户的地理位置信息，可了解用户每天经过的家庭住址、办公场所、购物场所、娱乐场所、健身场所等信息。可以理解地，基于位置服务获取用户的地理位置信息，具有较强的客观性和可靠性。
基于位置服务(Location Based Service，简称LBS)是通过电信移动运营商的无线电通讯网络(如GSM网、CDMA网)或外部定位方式(如GPS)获取移动终端用户的位置信息(地理坐标，或大地坐标)，在地理信息系统(Geographic Information System，简称GIS)平台的支持下，为用户提供相应服务的一种增值业务。总体来看，LBS由移动通信网络和计算机网络结合而成，两个网络之间通过网关实现交互。移动终端通过移动通信网络发出请求，经过网关传递给LBS服务平台；LBS服务平台根据用户请求和用户当前位置进行处理，并将结果通过网关返回给用户。POI(Point Of Interest,即兴趣点或信息点)，包括名称、类型、经度、纬度等资料，以使POI可在电子地图上呈现，以标示电子地图上的某个地标、景点等地点信息。
本实施例中，基于位置服务的移动终端为智能手机，通过开启智能手机上的定位功能，以使LBS服务平台实时获取智能手机的地理位置信息，从而获取该智能手机对应的用户的地理位置信息。该LBS服务平台与银行、证券、保险等金融机构中的基于位置服务的风险评估设备相连，以使该基于位置服务的风险评估设备能够实时获取该智能手机对应的用户的地理位置信息。其中，POI信息与时间相关联，每一POI信息包括日期和时刻，通过该地理位置信息可了解用户在任一时刻所处的POI信息。可以理解地，地理位置信息与用户ID相关联，用户ID用于识别唯一识别用户，可以是身份证号或手机号。
可以理解地，为了减少数据处理量，提高处理效率，可预先设置时间阈值，以使基于位置服务获取用户的地理位置信息时，只获取用户在任一地点停留时间达到该时间阈值的POI信息，以避免采集到的与时间相关联的POI信息的数据量较多，导致处理效率低的问题。
S2：对用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集。
其中，预设期间可以是当前系统时间之前的任意一段时间，可以为一个月、三个月或 半年等，可根据需求自主设置。预设时间界限是用于划分办公时间和休息时间的界限。基于预设时间界限可将所有POI信息划分为办公区域数据集和住址区域数据集，以便基于办公区域数据集和住址区域数据集对用户画像数据进行跟进处理。本实施例中，将8：00-20：00作为办公时间，其对应的地理位置信息为办公区域数据集；相应地，20：00-次日8：00作为休息时间，其对应的地理位置信息为住址区域数据集。
S3：对办公区域数据集和住址区域数据集分别进行聚类分析，分别获取办公位置动态信息和住址位置动态信息。
其中，办公位置动态信息是对办公区域数据集中所有POI信息进行聚类分析的结果；住址位置动态信息是对住址区域数据集中所有POI信息进行聚类分析的结果。办公位置动态信息和住址位置动态信息可客观反映用户在预设期间内的日常生活轨迹，可利用办公位置动态信息和住址位置动态信息实现对用户画像数据实时跟进，以保证跟进后的用户画像数据的客观性。
本实施例中，先将用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集，再对办公区域数据集和住址区域数据集分别进行聚类分析，使得办公区域数据集和住址区域数据集中的POI信息的数据量较小，有利于提高聚类效果，节省聚类处理时间。
步骤S3具体包括：
S31：采用DBSCAN聚类算法对办公区域数据集中的POI信息进行聚类，以获取若干办公子集群，每一办公子群集包括至少一个办公POI信息。采用DBSCAN聚类算法对住址区域数据集中的POI信息进行聚类，以获取若干住址子集群，每一住址子群集包括至少一个住址POI信息。
其中，DBSCAN(Density-Based Spatial Clustering of Applications with Noise，具有噪声的基于密度的聚类方法)是一种基于密度的空间聚类算法。该算法将具有足够密度的区域划分为簇，并在具有噪声的空间数据库中发现任意形状的簇，它将簇定义为密度相连的点的最大集合。DBSCAN聚类算法具有聚类速度快且能够有效处理噪声和发现任意形成的空间聚类的优点。
具体地，预设办公区域数据集的扫描半径(以下简称为eps)和最小包含点数(minPts)，任选一个未被访问(unvisited)的POI信息开始，找出与其距离在eps之内(包括eps)的所有POI信息，将POI信息与距离在eps之内的所有POI信息作为一个办公子集群输出，办公子集群中的POI信息为办公POI信息。相应地，预设住址区域数据集的扫描半径(eps)和最 小包含点数(minPts)，任选一个未被访问(unvisited)的POI信息开始，找出与其距离在eps之内(包括eps)的所有POI信息，将POI信息与距离在eps之内的所有POI信息作为一个住址子集群输出，住址子集群中的POI信息为住址POI信息。
S32：采用K-MEANS聚类算法对每一办公子集群进行迭代聚类，以获取办公子集群的办公质心POI信息；办公位置动态信息包括办公POI信息和办公质心POI信息。采用K-MEANS聚类算法对每一住址子集群进行迭代聚类，以获取住址子集群的住址质心POI信息；住址位置动态信息包括住址POI信息和住址质心POI信息。
K-MEANS算法是很典型的基于距离的算法，采用距离作为相似性的评价指标，即认为两个对象的距离越近，其相似度就越大。其计算公式为
Figure PCTCN2017076473-appb-000001
其中，k个初始类聚类中心点的选取对聚类结果具有较大的影响，因为在该算法第一步中是随机的选取任意k个对象作为初始聚类的中心，初始地代表一个簇。该算法在每次迭代中对数据集中剩余的每个对象，根据其与各个簇中心的距离将每个对象重新赋给最近的簇。若一次迭代前后，J的值没有发生变化，说明算法已经收敛。K-MEANS算法可快速简单地对数据进行聚类，对大数据集具有较高的效率且可伸缩性，时间复杂度近于线性，而且适合挖掘大规模数据集。
本实施例中，采用K-MEANS算法对每一办公子集群中的POI信息进行迭代聚合，直到最后一次迭代时，迭代前后数值没有发生变化，则获取该办公子集群的办公质心POI信息，从而获取包括办公POI信息和办公质心POI信息的办公位置动态信息。相应地，采用K-MEANS算法对每一住址子集群中的POI信息进行迭代聚合，直到最后一次迭代时，迭代前后数值没有发生变化，则获取该住址子集群的住址质心POI信息，从而获取包括住址POI信息和住址质心POI信息的住址位置动态信息。
若用户某天的地理位置信息包括与时间相关联的如下POI信息：A、B、C、D、E、F、G、H、F、I、J、K……E、D、A，若A为家庭住址，B和C分别为家庭住址附近eps内的地点，D和E为工作路上获取的地点，F为办公地址，G为办公地址附近eps内的地点，H、I、J、K为消费场所等。步骤S31中采用DBSCAN聚类算法进行聚类时，通过设置扫描半径(eps)和最小包含点数(minPts)，可将家庭住址和家庭住址附近eps内所有的POI信息聚类为一住址子集群输出，将办公场所和办公场所附近eps内所有的POI信息聚类为一办公子集群输出。步骤S32对每一办公子集群和住址子集群分别采用K-MEANS聚类算法进行迭代聚合，以获取每一办公子集群的办公质心POI信息，并获取每一住址子集群的住址质心POI信息。其中，办公质心POI信息是办公子集群的办公POI信息中的一个，住址质心POI信息是住址子集群 的住址POI信息中的一个；办公位置动态信息包括办公POI信息和办公质心POI信息，住址位置动态信息包括住址POI信息和住址质心POI信息。
S4：将办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息。
其中，用户画像数据包括用户ID、办公场所和家庭住址。用户画像数据可以是用户在办理相关业务时采集到的用户画像数据，也可以是基于位置服务实时跟进后存储的用户画像数据。利用办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行比对，由于办公位置动态信息和住址位置动态信息具有客观性，使得比对后输出的用户风险度评估信息具有客观性。其中，用户风险度评估信息包括低风险度评估信息、中风险度评估信息和高风险度评估信息。
进一步地，由于实时采集用户的地理位置信息，并对预设期间内的地理位置信息进行聚类分析获取到的办公位置动态信息和住址位置动态信息可客观反映用户的用户画像数据，可将办公位置动态信息和住址位置动态信息实时更新为新的用户画像数据，使得下次评估时可利用新的用户画像数据进行对比，以提高用户风险度评估信息的准确性。
步骤S4具体包括：
S41：判断办公场所是否与办公质心POI信息相匹配，并判断家庭住址是否与住址质心POI信息相匹配。
S42：若均相匹配，输出低风险度评估信息。
S43：若不均相匹配，则判断办公场所是否与办公子集群中的办公POI信息相匹配，和/或判断家庭住址是否与住址子集群中的住址POI信息相匹配；
S44：根据判断结果输出高风险度评估信息或中风险度评估信息。
本实施例中，设a为办公场所，b为家庭住址，A为办公质心POI信息，U为办公子集群，B为住址质心POI信息，Y为住址子集群；将办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行比对的结果如下表所示，其中，＝表示匹配，≠表示不匹配。
Figure PCTCN2017076473-appb-000002
Figure PCTCN2017076473-appb-000003
本实施例中，办公场所与办公质心POI信息或办公子集群的匹配状态有如下三种情况：办公场所与办公质心POI信息相匹配(a＝A)、办公场所与办公子集群中的办公POI信息相匹配(a＝U)和办公场所与办公子集群中的办公POI信息不相匹配(a≠U)。相应地，家庭住址与住址质心POI信息或住址子集群的匹配状态有如下三种情况：家庭住址与住址质心POI信息相匹配(b＝B)、家庭住址与住址子集群中的住址POI信息相匹配(b＝Y)和家庭住址与住址子集群中的住址POI信息不相匹配(b≠Y)。因此，将办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行比对的结果有如上表所示九种状态。
若办公场所与办公质心POI信息相匹配且家庭住址与住址质心POI信息相匹配，即状态1，其对应的风险度评估等级为I级，输出低风险度评估信息，表示用户在预设期间内基于位置服务获取到的地理位置信息与其预先存储的用户画像数据相匹配，办公场所和家庭住址位置均没有变化。
在一具体实施方式中，若办公场所与办公子集群中的办公POI信息不相匹配，且家庭住址在住址子集群中的住址POI信息不相匹配，即状态9，其对应的风险度评估等级为VI级，根据业务需求，可将VI级的风险度评估等级作为高风险度评估信息输出，表示用户在预设期间内基于位置服务获取到的用户的地理位置信息与其预先存储的用户画像数据完全不相匹配，办公场所和家庭住址均发生变化。
在另一具体实施方式中，若办公场所与办公子集群中的办公POI信息不相匹配和/或家庭住址在住址子集群中的住址POI信息不相匹配，即状态3、6、7、8和9，其对应的风险度评估等级为IV级、V级和VI级，根据业务需求，可将IV级、V级和VI级的风险度评估等级作为高风险度评估信息输出，表示用户在预设期间内基于位置服务获取到的用户的地理位置信息与其预先存储的用户画像数据局部不相匹配，办公场所和/或家庭住址发生变化。
其中，在风险度评估信息中，低风险度评估信息和高风险度评估信息之外的状态对应中风险度评估信息。
在一具体实施方式中，步骤S4中采用相似度检测算法将办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息。
具体地，采用相似度检测算法分别计算办公场所与办公质心POI信息的第一检测值和家庭住址与住址质心POI信息的第二检测值。若第一检测值大于第一阈值，则认定办公场所与办公质心POI信息相匹配，反之则不相匹配。若第二检测值大于第一阈值，则认定家庭住 址与住址质心POI信息相匹配，反之则不相匹配。
相应地，采用相似度检测算法分别计算办公场所与办公子集群中的办公POI信息的第三检测值，和/或家庭住址与住址子集群中的住址POI信息的第四检测值。若第三检测值大于第二阈值，则认定办公场所与办公子集群中的办公POI信息相匹配，反之则不相匹配。若第四检测值大于第二阈值，则认定家庭住址与住址子集群中的住址POI信息相匹配，反之则不相匹配。
在一具体实施方式中，用户画像数还包括管户人员ID和管户人员联系方式。该基于位置服务的风险评估方法还包括：在输出高风险度评估信息时，将办公位置动态信息和/或住址位置动态信息发送给管户人员ID对应的管户人员。在输出高风险度评估信息时，表示其办公位置动态信息和住址位置动态信息均发生变化，或者办公位置动态信息和/或住址位置动态信息发生变化，因此，需将发生变化的办公位置动态信息和/或住址位置动态信息发送给管户人员ID，由管户人员ID对应的管户人员对用户画像数据进行跟进处理，如进行信息核实，用户画像数据更新等，避免因办公位置动态信息和/或住址位置动态信息发生变化而导致金融机构提供的贷款等金融业务的业务风险增大的问题出现。
本实施例所提供的基于位置服务的风险评估方法中，基于位置服务获取用户的地理位置信息，地理位置信息具有客观性和实时性。通过对用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集，再对办公区域数据集和住址区域数据集分别进行聚类分析，以获取办公位置动态信息和住址位置动态信息。其中，划分办公区域数据集和住址区域数据集并分别聚类，使得办公区域数据集和住址区域数据集中的POI信息的数据量较小，有利于提高聚类效果，节省聚类处理时间。由于办公位置动态信息和住址位置动态信息具有客观性，使得利用办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行比对，输出的用户风险度评估信息具有客观性，可有效评估用户画像数据是否发生变化，可提高对用户画像数据变动产生的风险的管控。由于实时采集用户的地理位置信息，并对预设期间内的地理位置信息进行聚类分析获取到的办公位置动态信息和住址位置动态信息可客观反映用户的用户画像数据，可将办公位置动态信息和住址位置动态信息实时更新为新的用户画像数据，以提高用户风险度评估信息的准确性。
第二实施例
图2示出本实施例中基于位置服务的风险评估装置的一流程图。如图2所示，该基于位置服务的风险评估装置可以是设置在银行、保险、证券等金融机构中的基于位置服务的风险评估设备。如图2所示，该基于位置服务的风险评估装置包括信息获取单元10、信息划 分单元20、聚类分析单元30、评估结果输出单元40和信息发送单元50。
信息获取单元10，用于基于位置服务获取用户的地理位置信息，地理位置信息包括与时间相关联的POI信息。
以任一用户一天的地理位置信息为例，该地理位置信息中包括0：00—24：00的POI信息，每一POI信息用于指示电子地图中的一点，包括POI点名称、经度和纬度等信息。基于用户的地理位置信息，可了解用户每天经过的家庭住址、办公场所、购物场所、娱乐场所、健身场所等信息。可以理解地，基于位置服务获取用户的地理位置信息，具有较强的客观性和可靠性。
基于位置服务(Location Based Service，简称LBS)是通过电信移动运营商的无线电通讯网络(如GSM网、CDMA网)或外部定位方式(如GPS)获取移动终端用户的位置信息(地理坐标，或大地坐标)，在地理信息系统(Geographic Information System，简称GIS)平台的支持下，为用户提供相应服务的一种增值业务。总体来看，LBS由移动通信网络和计算机网络结合而成，两个网络之间通过网关实现交互。移动终端通过移动通信网络发出请求，经过网关传递给LBS服务平台；LBS服务平台根据用户请求和用户当前位置进行处理，并将结果通过网关返回给用户。POI(Point Of Interest,即兴趣点或信息点)，包括名称、类型、经度、纬度等资料，以使POI可在电子地图上呈现，以标示电子地图上的某个地标、景点等地点信息。
本实施例中，基于位置服务的移动终端为智能手机，通过开启智能手机上的定位功能，以使LBS服务平台实时获取智能手机的地理位置信息，从而获取该智能手机对应的用户的地理位置信息。该LBS服务平台与银行、证券、保险等金融机构中的基于位置服务的风险评估设备相连，以使该基于位置服务的风险评估设备能够实时获取该智能手机对应的用户的地理位置信息。其中，POI信息与时间相关联，每一POI信息包括日期和时刻，通过该地理位置信息可了解用户在任一时刻所处的POI信息。可以理解地，地理位置信息与用户ID相关联，用户ID用于识别唯一识别用户，可以是身份证号或手机号。
可以理解地，为了减少数据处理量，提高处理效率，可预先设置时间阈值，以使基于位置服务获取用户的地理位置信息时，只获取用户在任一地点停留时间达到该时间阈值的POI信息，以避免采集到的与时间相关联的POI信息的数据量较多，导致处理效率低的问题。
信息划分单元20，用于对用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集。
其中，预设期间可以是当前系统时间之前任意一段时间，可以为一个月、三个月或半 年等，可根据需求自主设置。预设时间界限可以是用于划分办公时间和休息时间的界限。基于预设时间界限可将所有POI信息划分为办公区域数据集和住址区域数据集，以便基于办公区域数据集和住址区域数据集对用户画像数据进行跟进处理。本实施例中，将8：00-20：00作为办公时间，其对应的地理位置信息为办公区域数据集；相应地，20：00-次日8：00作为休息时间，其对应的地理位置信息为住址区域数据集。
聚类分析单元30，用于对办公区域数据集和住址区域数据集分别进行聚类分析，分别获取办公位置动态信息和住址位置动态信息。其中，办公位置动态信息是对办公区域数据集中所有POI信息进行聚类分析的结果；住址位置动态信息是对住址区域数据集中所有POI信息进行聚类分析的结果。办公位置动态信息和住址位置动态信息可客观反映用户在预设期间内的日常生活轨迹，可利用办公位置动态信息和住址位置动态信息实现对用户画像数据实时跟进，以保证跟进后的用户画像数据的客观性。
本实施例中，先将用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集，再对办公区域数据集和住址区域数据集分别进行聚类分析，使得办公区域数据集和住址区域数据集中的POI信息的数据量较小，有利于提高聚类效果，节省聚类处理时间。
聚类分析单元30具体包括第一聚类子单元31和第二聚类子单元32。
第一聚类子单元31，用于采用DBSCAN聚类算法对办公区域数据集中的POI信息进行聚类，以获取若干办公子集群，每一办公子群集包括至少一个办公POI信息。采用DBSCAN聚类算法对住址区域数据集中的POI信息进行聚类，以获取若干住址子集群，每一住址子群集包括至少一个住址POI信息。
其中，DBSCAN(Density-Based Spatial Clustering of Applications with Noise，具有噪声的基于密度的聚类算法)是一种基于密度的空间聚类算法。该算法将具有足够密度的区域划分为簇，并在具有噪声的空间数据库中发现任意形状的簇，它将簇定义为密度相连的点的最大集合。DBSCAN聚类算法具有聚类速度快且能够有效处理噪声和发现任意形成的空间聚类的优点。
具体地，预设办公区域数据集的扫描半径(以下简称为eps)和最小包含点数(minPts)，任选一个未被访问(unvisited)的POI信息开始，找出与其距离在eps之内(包括eps)的所有POI信息，将POI信息与距离在eps之内的所有POI信息作为一个办公子集群输出，办公子集群中的POI信息为办公POI信息。相应地，预设住址区域数据集的扫描半径(eps)和最小包含点数(minPts)，任选一个未被访问(unvisited)的POI信息开始，找出与其距离在eps 之内(包括eps)的所有POI信息，将POI信息与距离在eps之内的所有POI信息作为一个住址子集群输出，住址子集群中的POI信息为住址POI信息。
第二聚类子单元32，用于采用K-MEANS聚类算法对每一办公子集群进行迭代聚类，以获取办公子集群的办公质心POI信息；办公位置动态信息包括办公POI信息和办公质心POI信息。采用K-MEANS聚类算法对每一住址子集群进行迭代聚类，以获取住址子集群的住址质心POI信息；住址位置动态信息包括住址POI信息和住址质心POI信息。
K-MEANS算法是很典型的基于距离的算法，采用距离作为相似性的评价指标，即认为两个对象的距离越近，其相似度就越大。其计算公式为
Figure PCTCN2017076473-appb-000004
其中，k个初始类聚类中心点的选取对聚类结果具有较大的影响，因为在该算法第一步中是随机的选取任意k个对象作为初始聚类的中心，初始地代表一个簇。该算法在每次迭代中对数据集中剩余的每个对象，根据其与各个簇中心的距离将每个对象重新赋给最近的簇。若一次迭代前后，J的值没有发生变化，说明算法已经收敛。K-MEANS算法可快速简单地对数据进行聚类，对大数据集具有较高的效率且可伸缩性，时间复杂度近于线性，而且适合挖掘大规模数据集。
本实施例中，采用K-MEANS算法对每一办公子集群中的POI信息进行迭代聚合，直到最后一次迭代时，迭代前后数值没有发生变化，则获取该办公子集群的办公质心POI信息，从而获取包括办公POI信息和办公质心POI信息的办公位置动态信息。相应地，采用K-MEANS算法对每一住址子集群中的POI信息进行迭代聚合，直到最后一次迭代时，迭代前后数值没有发生变化，则获取该住址子集群的住址质心POI信息，从而获取包括住址POI信息和住址质心POI信息的住址位置动态信息。
若用户某天的地理位置信息包括与时间相关联的如下POI信息：A、B、C、D、E、F、G、H、F、I、J、K……E、D、A，若A为家庭住址，B和C分别为家庭住址附近eps内的地点，D和E为工作路上获取的地点，F为办公地址，G为办公地址附近eps内的地点，H、I、J、K为消费场所等。第一聚类子单元31中采用DBSCAN聚类算法进行聚类时，通过设置扫描半径(eps)和最小包含点数(minPts)，可将家庭住址和家庭住址附近eps内所有的POI信息聚类为一住址子集群输出，将办公场所和办公场所附近eps内所有的POI信息聚类为一办公子集群输出。第二聚类子单元32对每一办公子集群和住址子集群分别采用K-MEANS聚类算法进行迭代聚合，以获取每一办公子集群的办公质心POI信息，并获取每一住址子集群住址质心POI信息。其中，办公质心POI信息是办公子集群的办公POI信息中的一个，住址质心POI信息是住址子集群的住址POI信息中的一个；住址位置动态信息包括住址POI信息 和住址质心POI信息。
评估结果输出单元40，用于将办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息。
其中，用户画像数据包括用户ID、办公场所和家庭住址。用户画像数据可以是用户在办理相关业务时采集到的用户画像数据，也可以是基于位置服务实时跟进后存储的用户画像数据。利用办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行比对，由于办公位置动态信息和住址位置动态信息具有客观性，使得比对后输出的用户风险度评估信息具有客观性。其中，用户风险度评估信息包括低风险度评估信息、中风险度评估信息和高风险度评估信息。
进一步地，由于实时采集用户的地理位置信息，并对预设期间内的地理位置信息进行聚类分析获取到的办公位置动态信息和住址位置动态信息可客观反映用户的用户画像数据，可将办公位置动态信息和住址位置动态信息实时更新为新的用户画像数据，使得下次评估时可利用新的用户画像数据进行对比，以提高用户风险度评估信息的准确性。
评估结果输出单元40具体包括第一判断子单元41、第一处理子单元42、第二判断子单元43和第二处理子单元44。
第一判断子单元41，用于判断办公场所是否与办公质心POI信息相匹配并判断家庭住址是否与住址质心POI信息相匹配。
第一处理子单元42，用于若均相匹配，输出低风险度评估信息。
第二判断子单元43，用于若不均相匹配，则判断办公场所是否与办公子集群中的办公POI信息相匹配，和/或判断家庭住址是否与住址子集群中的住址POI信息相匹配；
第二处理子单元44，用于根据判断结果输出高风险度评估信息或中风险度评估信息。
本实施例中，设a为办公场所，b为家庭住址，A为办公质心POI信息，U为办公子集群，B为住址质心POI信息，Y为住址子集群；将办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行比对的结果如下表所示，其中，＝表示匹配，≠表示不匹配。
Figure PCTCN2017076473-appb-000005
Figure PCTCN2017076473-appb-000006
本实施例中，办公场所与办公质心POI信息或办公子集群的匹配状态有如下三种情况：办公场所与办公质心POI信息相匹配(a＝A)、办公场所与办公子集群中的办公POI信息相匹配(a＝U)和办公场所与办公子集群中的办公POI信息不相匹配(a≠U)。相应地，家庭住址与住址质心POI信息或住址子集群的匹配状态有如下三种情况：家庭住址与住址质心POI信息相匹配(b＝B)、家庭住址与住址子集群中的住址POI信息相匹配(b＝Y)和家庭住址与住址子集群中的住址POI信息不相匹配(b≠Y)。因此，将办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行比对的结果有如上表所示九种状态。
若办公场所与办公质心POI信息相匹配且家庭住址与住址质心POI信息相匹配，即状态1，其对应的风险度评估等级为I级，输出低风险度评估信息，表示用户在预设期间内基于位置服务获取到的地理位置信息与其预先存储的用户画像数据相匹配，办公场所和家庭住址位置均没有变化。
在一具体实施方式中，若办公场所与办公子集群中的办公POI信息不相匹配，且家庭住址在住址子集群中的住址POI信息不相匹配，即状态9，其对应的风险度评估等级为VI级，根据业务需求，可将VI级的风险度评估等级作为高风险度评估信息输出，表示用户在预设期间内基于位置服务获取到的用户的地理位置信息与其预先存储的用户画像数据完全不相匹配，办公场所和家庭住址均发生变化。
在另一具体实施方式中，若办公场所与办公子集群中的办公POI信息不相匹配和/或家庭住址在住址子集群中的住址POI信息不相匹配，即状态3、6、7、8和9，其对应的风险度评估等级为IV级、V级和VI级，根据业务需求，可将IV级、V级和VI级的风险度评估等级作为高风险度评估信息输出，表示用户在预设期间内基于位置服务获取到的用户的地理位置信息与其预先存储的用户画像数据局部不相匹配，办公场所和/或家庭住址发生变化。
其中，在风险度评估信息中，低风险度评估信息和高风险度评估信息之外的状态对应中风险度评估信息。
在一具体实施方式中，评估结果输出单元40采用相似度检测算法将办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息。
具体地，采用相似度检测算法分别计算办公场所与办公质心POI信息的第一检测值和家庭住址与住址质心POI信息的第二检测值。若第一检测值大于第一阈值，则认定办公场所与办公质心POI信息相匹配，反之则不相匹配。若第二检测值大于第一阈值，则认定家庭住 址与住址质心POI信息相匹配，反之则不相匹配。
相应地，采用相似度检测算法分别计算办公场所与办公子集群中的办公POI信息的第三检测值，和/或家庭住址与住址子集群中的住址POI信息的第四检测值。若第三检测值大于第二阈值，则认定办公场所与办公子集群中的办公POI信息相匹配，反之则不相匹配。若第四检测值大于第二阈值，则认定家庭住址与住址子集群中的住址POI信息相匹配，反之则不相匹配。
在一具体实施方式中，用户画像数还包括管户人员ID和管户人员联系方式。该基于位置服务的风险评估装置还包括信息发送单元50，用于在输出高风险度评估信息时，将办公位置动态信息和/或住址位置动态信息发送给管户人员ID对应的管户人员。在输出高风险度评估信息时，表示其办公位置动态信息和住址位置动态信息均发生变化，或者办公位置动态信息和/或住址位置动态信息发生变化，因此，需将发生变化的办公位置动态信息和/或住址位置动态信息发送给管户人员ID，由管户人员ID对应的管户人员对用户画像数据进行跟进处理，如进行信息核实，用户画像数据更新等，避免因办公位置动态信息和/或住址位置动态信息发生变化而导致金融机构提供的贷款等金融业务的业务风险增大的问题出现。
本实施例所提供的基于位置服务的风险评估装置中，基于位置服务获取用户的地理位置信息，地理位置信息具有客观性和实时性。通过对用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集，再对办公区域数据集和住址区域数据集分别进行聚类分析，以获取办公位置动态信息和住址位置动态信息。其中，划分办公区域数据集和住址区域数据集并分别聚类，使得办公区域数据集和住址区域数据集中的POI信息的数据量较小，有利于提高聚类效果，节省聚类处理时间。由于办公位置动态信息和住址位置动态信息具有客观性，使得利用办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行比对，输出的用户风险度评估信息具有客观性，可有效评估用户画像数据是否发生变化，可提高对用户画像数据变动产生的风险的管控。由于实时采集用户的地理位置信息，并对预设期间内的地理位置信息进行聚类分析获取到的办公位置动态信息和住址位置动态信息可客观反映用户的用户画像数据，可将办公位置动态信息和住址位置动态信息实时更新为新的用户画像数据，以提高用户风险度评估信息的准确性。
第三实施例
图3是本发明第三实施例的基于位置服务的风险评估设备300的框图。其中，设备300可为手机、平板电脑、个人数字助理(PersonalDigital Assistant，PDA)和或车载电脑等具有一定的数据处理能力的移动终端、或者台式电脑、服务器等。如图3所示，设备300 包括射频(RadioFrequency，RF)电路301、存储器302、输入模块303、显示模块304、处理器305、音频电路306、WiFi(WirelessFidelity)模块307和电源308。
输入模块303和显示模块304作为设备300的用户交互装置，用于实现用户与设备300之间的交互，例如，接收用户输入的风险评估指令并显示对应的用户风险度评估信息。输入模块303用于接收用户输入的风险评估指令，并将所述风险评估指令发送给所述处理器305，所述风险评估指令包括办公位置动态信息和住址位置动态信息。所述处理器305用于基于所述风险评估指令，获取用户风险度评估信息，并将所述用户风险度评估信息发送给所述显示模块304。显示模块304接收并显示所述用户风险度评估信息。
在一些实施例中，输入模块303可用于接收用户输入的数字或字符信息，以及产生与设备300的用户设置以及功能控制有关的信号输入。在一些实施例中，该输入模块303可以包括触控面板3031。触控面板3031，也称为触摸屏，可收集用户在其上或附近的触摸操作(比如用户使用手指、触笔等任何适合的物体或附件在触控面板3031上的操作)，并根据预先设定的程式驱动相应的连接装置。可选地，触控面板3031可包括触摸检测装置和触摸控制器两个部分。其中，触摸检测装置检测用户的触摸方位，并检测触摸操作带来的信号，将信号传送给触摸控制器；触摸控制器从触摸检测装置上接收触摸信息，并将它转换成触点坐标，再送给该处理器305，并能接收处理器305发来的命令并加以执行。此外，可以采用电阻式、电容式、红外线以及表面声波等多种类型实现触控面板3031。除了触控面板3031，输入模块303还可以包括其他输入设备3032，其他输入设备3032可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆等中的一种或多种。
在一些实施例中，显示模块304可用于显示由用户输入的信息或提供给用户的信息以及设备300的各种菜单界面。显示模块304可包括显示面板3041，可选地，可以采用LCD或有机发光二极管(Organic Light-Emitting Diode，OLED)等形式来配置显示面板3041。
可以理解地，触控面板3031可以覆盖显示面板3041，形成触摸显示屏，当该触摸显示屏检测到在其上或附近的触摸操作后，传送给处理器305以确定触摸事件的类型，随后处理器305根据触摸事件的类型在触摸显示屏上提供相应的视觉输出。
触摸显示屏包括应用程序界面显示区及常用控件显示区。该应用程序界面显示区及该常用控件显示区的排列方式并不限定，可以为上下排列、左右排列等可以区分两个显示区的排列方式。该应用程序界面显示区可以用于显示应用程序的界面。每一个界面可以包含至少一个应用程序的图标和/或widget桌面控件等界面元素。该应用程序界面显示区也可以为不包含任何内容的空界面。该常用控件显示区用于显示使用率较高的控件，例如，设置按钮、 界面编号、滚动条、电话本图标等应用程序图标等。
WiFi模块307作为设备300的网络接口，可以实现设备300与其他设备的数据交互，本实施例中，网络接口可与远端存储设备和外部显示设备通过网络通信相连。所述网络接口用于接收所述远端存储设备发送的基于位置服务获取用户的地理位置信息，并将所述地理位置信息发送给所述处理器305；还用于接收所述处理器305发送的用户风险度评估信息，并将所述用户风险度信息发送给所述外部显示设备。外部显示设备可接收并显示所述用户风险度信息。本实施例中，与该网络接口通过WiFi网络相连的远端存储设备可以是云服务器或其他数据库，该远端存储设备上存储有基于位置服务获取用户的地理位置信息，该地理位置信息可通过WiFi网络发送给WiFi模块307，WiFi模块307将获取到的所述地理位置信息发送给所述处理器305，并将从所述处理器305接收到的所述用户风险度信息发送给所述外部显示设备。
存储器302包括第一存储器3021及第二存储器3022。在一些实施例中，第一存储器3021可为非易失性计算机可读存储介质，其上存储有操作系统、数据库及计算机可执行指令。计算机可执行指令可被处理器305所执行，用于实现如图1所示的实施例的基于位置服务的风险评估方法。存储器302上的数据库用于存储各类数据，例如，上述基于位置服务的风险评估方法中所涉及的各种数据，如地理位置信息和用户画像数据。第二存储器3021可为设备300的内存储器，为非易失性计算机可读存储介质中的操作系统、数据库和计算机可执行指令提供高速缓存的运行环境。
在本实施例中，处理器305是设备300的控制中心，利用各种接口和线路连接整个手机的各个部分，通过运行或执行存储在第一存储器3021内的计算机可执行搜集和/或数据库内的数据，执行设备300的各种功能和处理数据，从而对设备300进行整体监控。可选地，处理器305可包括一个或多个处理模块。
在本实施例中，通过执行存储该第一存储器3021内的计算机可执行指令和/或数据库内的数据，处理器305用于执行如下步骤：基于位置服务获取用户的地理位置信息，所述地理位置信息包括与时间相关联的POI信息；对用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集；对所述办公区域数据集和住址区域数据集分别进行聚类分析，分别获取办公位置动态信息和住址位置动态信息；将所述办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息；其中，所述用户画像数据包括用户ID、办公场所和家庭住址。
优选地，所述对所述办公区域数据集和住址区域数据集分别进行聚类分析，分别获取 办公位置动态信息和住址位置动态信息，包括：
采用DBSCAN聚类算法对所述办公区域数据集中的POI信息进行聚类，以获取若干办公子集群，每一办公子群集包括至少一个办公POI信息；采用DBSCAN聚类算法对所述住址区域数据集中的POI信息进行聚类，以获取若干住址子集群，每一住址子群集包括至少一个住址POI信息；
采用K-MEANS聚类算法对每一所述办公子集群进行迭代聚类，获取所述办公子集群的办公质心POI信息，并将所述办公质心POI信息作为所述办公位置动态信息输出；采用K-MEANS聚类算法对每一所述住址子集群进行迭代聚类，获取所述住址子集群的住址质心POI信息，并将所述住址质心POI信息作为所述住址位置动态信息输出。
优选地，所述将所述办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息，包括：
判断所述办公场所是否与所述办公质心POI信息相匹配，并判断所述家庭住址是否与所述住址质心POI信息相匹配；
若均相匹配，输出低风险度评估信息；
若不均相匹配，则判断所述办公场所是否与所述办公子集群中的办公POI信息相匹配，和/或判断所述家庭住址是否与所述住址子集群中的住址POI信息相匹配；
根据判断结果输出高风险度评估信息或中风险度评估信息。
优选地，所述处理器305还执行如下步骤：采用相似度检测算法将所述办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比。
优选地，所述用户画像数还包括管户人员ID；
所述处理器305还执行如下步骤：在输出高风险度评估信息时，将所述办公位置动态信息和/或住址位置动态信息发送给所述管户人员ID对应的管户人员。
本实施例所提供的基于位置服务的风险评估设备300，处理器305基于位置服务获取用户的地理位置信息，地理位置信息具有客观性和实时性。通过对用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集，再对办公区域数据集和住址区域数据集分别进行聚类分析，以获取办公位置动态信息和住址位置动态信息。其中，划分办公区域数据集和住址区域数据集并分别聚类，使得办公区域数据集和住址区域数据集中的POI信息的数据量较小，有利于提高聚类效果，节省聚类处理时间。由于办公位置动态信息和住址位置动态信息具有客观性，使得利用办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行比对，输出的用户风险度评估信息具有客观性，可有效评估用户 画像数据是否发生变化，可提高用户画像数据变动产生的风险的管控。由于实时采集用户的地理位置信息，并对预设期间内的地理位置信息进行聚类分析获取到的办公位置动态信息和住址位置动态信息可客观反映用户的用户画像数据，可将办公位置动态信息和住址位置动态信息实时更新为新的用户画像数据，以提高用户风险度评估信息的准确性。
第四实施例
本实施例提供一种非易失性计算机可读存储介质。该非易失性计算机可读存储介质用于存储一个或多个计算机可执行指令。具体地，计算机可执行指令被一个或多个处理器执行，使得所述一个或多个处理器执行第一实施例所述的基于位置服务的风险评估方法，为避免重复，这里不再赘述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的模块及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述模块的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个模块或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或模块的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个地方，或者也可以分布到多个网络模块上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能模块可以集成在一个处理模块中，也可以是各个模块单独物理存在，也可以两个或两个以上模块集成在一个模块中。
所述功能如果以软件功能模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算 机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以权利要求的保护范围为准。

Claims (19)

  1. 一种基于位置服务的风险评估方法，其特征在于，包括：
    基于位置服务获取用户的地理位置信息，所述地理位置信息包括与时间相关联的POI信息；
    对用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集；
    对所述办公区域数据集和住址区域数据集分别进行聚类分析，分别获取办公位置动态信息和住址位置动态信息；
    将所述办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息；
    其中，所述用户画像数据包括用户ID、办公场所和家庭住址。
  2. 根据权利要求1所述的基于位置服务的风险评估方法，其特征在于，所述对所述办公区域数据集和住址区域数据集分别进行聚类分析，分别获取办公位置动态信息和住址位置动态信息，包括：
    采用DBSCAN聚类算法对所述办公区域数据集中的POI信息进行聚类，以获取若干办公子集群，每一办公子群集包括至少一个办公POI信息；采用DBSCAN聚类算法对所述住址区域数据集中的POI信息进行聚类，以获取若干住址子集群，每一住址子群集包括至少一个住址POI信息；
    采用K-MEANS聚类算法对每一所述办公子集群进行迭代聚类，获取所述办公子集群的办公质心POI信息，并将所述办公质心POI信息作为所述办公位置动态信息输出；采用K-MEANS聚类算法对每一所述住址子集群进行迭代聚类，获取所述住址子集群的住址质心POI信息，并将所述住址质心POI信息作为所述住址位置动态信息输出。
  3. 根据权利要求2所述的基于位置服务的风险评估方法，其特征在于，所述将所述办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息，包括：
    判断所述办公场所是否与所述办公质心POI信息相匹配，并判断所述家庭住址是否与所述所述住址质心POI信息相匹配；
    若均相匹配，输出低风险度评估信息；
    若不均相匹配，则判断所述办公场所是否与所述办公子集群中的办公POI信息相匹配， 和/或判断所述家庭住址是否与所述住址子集群中的住址POI信息相匹配；
    根据判断结果输出高风险度评估信息或中风险度评估信息。
  4. 根据权利要求2所述的基于位置服务的风险评估方法，其特征在于，还包括：采用相似度检测算法将所述办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比。
  5. 根据权利要求2所述的基于位置服务的风险评估方法，其特征在于，所述用户画像数还包括管户人员ID；
    还包括：在输出高风险度评估信息时，将所述办公位置动态信息和/或住址位置动态信息发送给所述管户人员ID对应的管户人员。
  6. 一种基于位置服务的风险评估装置，其特征在于，包括：
    信息获取单元，用于基于位置服务获取用户的地理位置信息，所述地理位置信息包括与时间相关联的POI信息；
    信息划分单元，用于对用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集；
    聚类分析单元，用于对所述办公区域数据集和住址区域数据集分别进行聚类分析，分别获取办公位置动态信息和住址位置动态信息；
    评估结果输出单元，用于将所述办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息；
    其中，所述用户画像数据包括用户ID、办公场所和家庭住址。
  7. 根据权利要求6所述的基于位置服务的风险评估装置，其特征在于，所述聚类分析单元包括：
    第一聚类子单元，用于采用DBSCAN聚类算法对所述办公区域数据集中的POI信息进行聚类，以获取若干办公子集群，每一办公子群集包括至少一个办公POI信息；采用DBSCAN聚类算法对所述住址区域数据集中的POI信息进行聚类，以获取若干住址子集群，每一住址子群集包括至少一个住址POI信息；
    第二聚类子单元，用于采用K-MEANS聚类算法对每一所述办公子集群进行迭代聚类，获取所述办公子集群的办公质心POI信息，并将所述办公质心POI信息作为所述办公位置动态信息输出；采用K-MEANS聚类算法对每一所述住址子集群进行迭代聚类，获取所述住址子集群的住址质心POI信息，并将所述住址质心POI信息作为所述住址位置动态信息输出。
  8. 根据权利要求7所述的基于位置服务的风险评估装置，其特征在于，所述评估结果 输出单元包括：
    第一判断子单元，用于判断所述办公场所是否与所述办公质心POI信息相匹配并判断所述家庭住址是否与所述所述住址质心POI信息相匹配；
    第一处理子单元，用于若均相匹配，输出低风险度评估信息；
    第二判断子单元，用于若不均相匹配，则判断所述办公场所是否与所述办公子集群中的办公POI信息相匹配，和/或判断所述家庭住址是否与所述住址子集群中的住址POI信息相匹配；
    第二处理子单元，用于根据判断结果输出高风险度评估信息或中风险度评估信息。
  9. 根据权利要求7所述的基于位置服务的风险评估装置，其特征在于，所述评估结果输出单元，用于采用相似度检测算法将所述办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比。
  10. 根据权利要求7所述的基于位置服务的风险评估装置，其特征在于，所述用户画像数还包括管户人员ID；
    还包括信息发送单元，用于在输出高风险度评估信息时，将所述办公位置动态信息和/或住址位置动态信息发送给所述管户人员ID对应的管户人员。
  11. 一种基于位置服务的风险评估设备，其特征在于，包括处理器及存储器，所述存储器存储有计算机可执行指令，所述处理器用于执行所述计算机可执行指令以执行如下步骤：
    基于位置服务获取用户的地理位置信息，所述地理位置信息包括与时间相关联的POI信息；
    对用户在预设期间内所有POI信息按预设时间界限划分成办公区域数据集和住址区域数据集；
    对所述办公区域数据集和住址区域数据集分别进行聚类分析，分别获取办公位置动态信息和住址位置动态信息；
    将所述办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息；
    其中，所述用户画像数据包括用户ID、办公场所和家庭住址。
  12. 根据权利要求11所述的设备，其特征在于，所述对所述办公区域数据集和住址区域数据集分别进行聚类分析，分别获取办公位置动态信息和住址位置动态信息，包括：
    采用DBSCAN聚类算法对所述办公区域数据集中的POI信息进行聚类，以获取若干办公子集群，每一办公子群集包括至少一个办公POI信息；采用DBSCAN聚类算法对所述住址 区域数据集中的POI信息进行聚类，以获取若干住址子集群，每一住址子群集包括至少一个住址POI信息；
    采用K-MEANS聚类算法对每一所述办公子集群进行迭代聚类，获取所述办公子集群的办公质心POI信息，并将所述办公质心POI信息作为所述办公位置动态信息输出；采用K-MEANS聚类算法对每一所述住址子集群进行迭代聚类，获取所述住址子集群的住址质心POI信息，并将所述住址质心POI信息作为所述住址位置动态信息输出。
  13. 根据权利要求12所述的设备，其特征在于，所述将所述办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比，输出用户风险度评估信息，包括：
    判断所述办公场所是否与所述办公质心POI信息相匹配，并判断所述家庭住址是否与所述住址质心POI信息相匹配；
    若均相匹配，输出低风险度评估信息；
    若不均相匹配，则判断所述办公场所是否与所述办公子集群中的办公POI信息相匹配，和/或判断所述家庭住址是否与所述住址子集群中的住址POI信息相匹配；
    根据判断结果输出高风险度评估信息或中风险度评估信息。
  14. 根据权利要求12所述的设备，其特征在于，所述处理器还执行如下步骤：采用相似度检测算法将所述办公位置动态信息和住址位置动态信息与预先存储的用户画像数据进行对比。
  15. 根据权利要求12所述的设备，其特征在于，所述用户画像数还包括管户人员ID；
    所述处理器还执行如下步骤：在输出高风险度评估信息时，将所述办公位置动态信息和/或住址位置动态信息发送给所述管户人员ID对应的管户人员。
  16. 根据权利要求11所述的设备，其特征在于，所述设备还包括与所述处理器相连的用户交互装置；所述用户交互装置用于接收用户输入的风险评估指令，并将所述风险评估指令发送给所述处理器，所述风险评估指令包括办公位置动态信息和住址位置动态信息；
    所述处理器用于基于所述风险评估指令，获取用户风险度评估信息，并将所述用户风险度评估信息发送给所述用户交互装置；
    所述用户交互装置还用于接收并显示所述用户风险度评估信息。
  17. 根据权利要求11所述的设备，其特征在于，所述设备还包括与所述处理器相连的网络接口，所述网络接口与远端存储设备和外部显示设备相连；所述网络接口用于接收所述远端存储设备发送的基于位置服务获取用户的地理位置信息，并将所述地理位置信息发送给所述处理器；还用于接收所述处理器发送的用户风险度评估信息，并将所述用户风险度信息 发送给所述外部显示设备。
  18. 根据权利要求11所述的设备，其特征在于，所述存储器中存储有数据库，用于存储所述地理位置信息和所述用户画像数据。
  19. 一种非易失性计算机可读存储介质，其特征在于，用于存储一个或多个计算机可执行指令，所述计算机可执行指令被一个或多个处理器执行，使得所述一个或多个处理器执行权利要求1-5任一项所述的基于位置服务的风险评估方法。
PCT/CN2017/076473 2016-12-29 2017-03-13 基于位置服务的风险评估方法、装置、设备和存储介质 WO2018120427A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201611249860.4A CN106651603A (zh) 2016-12-29 2016-12-29 基于位置服务的风险评估方法及装置
CN201611249860.4 2016-12-29

Publications (1)

Publication Number Publication Date
WO2018120427A1 true WO2018120427A1 (zh) 2018-07-05

Family

ID=58836003

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/076473 WO2018120427A1 (zh) 2016-12-29 2017-03-13 基于位置服务的风险评估方法、装置、设备和存储介质

Country Status (2)

Country Link
CN (1) CN106651603A (zh)
WO (1) WO2018120427A1 (zh)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109861985A (zh) * 2019-01-02 2019-06-07 平安科技（深圳）有限公司 基于风险等级划分的ip风控方法、装置、设备和存储介质
CN110348703A (zh) * 2019-06-21 2019-10-18 平安科技（深圳）有限公司 基于用户行为画像的数据处理方法、装置及电子设备
CN112131321A (zh) * 2020-08-06 2020-12-25 亿存(北京)信息科技有限公司 用户画像标签的生成方法和装置、计算机设备、存储介质
CN112580882A (zh) * 2020-12-23 2021-03-30 平安银行股份有限公司 行程制定方法、装置、设备及介质
CN112907360A (zh) * 2021-03-25 2021-06-04 深圳前海微众银行股份有限公司 风险评估方法、设备、存储介质及程序产品
CN113435762A (zh) * 2020-05-06 2021-09-24 支付宝(杭州)信息技术有限公司 一种企业风险识别方法、装置及设备
CN113535495A (zh) * 2021-06-01 2021-10-22 成都雅信安科技服务有限公司 一种智能设备的硬件及其组件唯一性判断方法
CN113610517A (zh) * 2021-07-27 2021-11-05 浙江惠瀜网络科技有限公司 基于照片位置信息的家装分期业务应用方法及装置
CN114785616A (zh) * 2022-06-13 2022-07-22 深圳红途科技有限公司 数据风险检测方法、装置、计算机设备及存储介质
CN114969566A (zh) * 2022-06-27 2022-08-30 中国测绘科学研究院 一种距离度量的政务服务事项协同过滤推荐方法
CN117237123A (zh) * 2023-11-15 2023-12-15 山东政信大数据科技有限责任公司 基于区块链的金融信用风险智能管控方法及系统
CN112907360B (zh) * 2021-03-25 2024-06-07 深圳前海微众银行股份有限公司 风险评估方法、设备、存储介质及程序产品

Families Citing this family (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107580069A (zh) * 2017-09-22 2018-01-12 挖财网络技术有限公司 用户地址的确定方法及装置
CN107657527A (zh) * 2017-09-29 2018-02-02 平安科技（深圳）有限公司 贷款产品匹配方法、装置及计算机可读存储介质
CN107818506A (zh) * 2017-09-30 2018-03-20 上海壹账通金融科技有限公司 电子装置、信贷风险控制方法及存储介质
CN107798597A (zh) * 2017-10-09 2018-03-13 上海二三四五金融科技有限公司 一种动态高风险客群检测方法及系统
CN107798118A (zh) * 2017-11-08 2018-03-13 北京奇虎科技有限公司 基于大数据的用户画像构造方法、装置及计算设备
CN108537542B (zh) * 2018-04-02 2021-06-29 北京天材科技有限公司 用于社交网络的数据处理方法
CN110648213A (zh) * 2018-06-27 2020-01-03 百度在线网络技术（北京）有限公司 地址验证方法、装置、设备及计算机可读介质
CN109345947B (zh) * 2018-08-13 2022-02-22 中国平安人寿保险股份有限公司 基于数据关联性分析的工作区域划分方法及终端设备
CN110942275A (zh) * 2018-09-21 2020-03-31 北京京东尚科信息技术有限公司 反馈用户办公信息的方法、装置、介质及电子设备
CN109522923B (zh) * 2018-09-25 2023-07-04 中国平安人寿保险股份有限公司 客户地址聚合方法、装置及计算机可读存储介质
CN109672984B (zh) * 2018-09-26 2022-08-19 平安普惠企业管理有限公司 金融业务的用户位置画像评估方法、评估设备及存储介质
CN109447689A (zh) * 2018-09-27 2019-03-08 深圳壹账通智能科技有限公司 用户风险画像生成方法、装置、设备及可读存储介质
US20200387839A1 (en) * 2019-06-07 2020-12-10 Didi Research America, Llc Estimating passenger income level on a ridesharing platform
CN110689218A (zh) * 2019-08-13 2020-01-14 平安科技（深圳）有限公司 风险用户识别方法、装置、计算机设备及存储介质
CN111200782B (zh) * 2019-11-26 2022-08-09 深圳壹账通智能科技有限公司 定位服务数据清洗方法、装置、计算机设备和存储介质
CN111178932A (zh) * 2019-11-26 2020-05-19 深圳壹账通智能科技有限公司 用户地理画像生成方法、装置、计算机设备和存储介质
CN111210201B (zh) * 2020-01-02 2021-02-26 平安科技（深圳）有限公司 职业标签建立方法、装置、电子设备及存储介质
CN111339741B (zh) * 2020-02-26 2021-08-24 腾讯科技（深圳）有限公司 账户申请方法、装置、计算机可读存储介质及电子设备
CN112802231B (zh) * 2021-03-19 2021-07-06 四川万网鑫成信息科技有限公司 基于gps数据的车辆风险评估方法、装置、设备和介质
CN113516302B (zh) * 2021-06-23 2022-01-04 平安科技（深圳）有限公司 业务风险分析方法、装置、设备及存储介质
CN114219053B (zh) * 2022-02-23 2023-04-18 北京淇瑀信息科技有限公司 用户位置信息处理方法、装置及电子设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140122401A1 (en) * 2012-10-29 2014-05-01 Sas Institute Inc. System and Method for Combining Segmentation Data
CN104866969A (zh) * 2015-05-25 2015-08-26 百度在线网络技术（北京）有限公司 个人信用数据处理方法和装置
CN104965913A (zh) * 2015-07-03 2015-10-07 重庆邮电大学 一种基于gps地理位置数据挖掘的用户分类方法
CN105808698A (zh) * 2016-03-03 2016-07-27 江苏大学 一种面向物联网用户查询请求的TOP-k位置兴趣点推荐方法
CN105894323A (zh) * 2016-03-29 2016-08-24 乐视控股（北京）有限公司 用户评测方法、指标项模型训练方法和装置
CN105894089A (zh) * 2016-04-21 2016-08-24 百度在线网络技术（北京）有限公司 一种征信模型的建立方法、征信确定方法及对应装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150235222A1 (en) * 2014-02-18 2015-08-20 Mastercard International Incorporated Investment Risk Modeling Method and Apparatus
US20160246966A1 (en) * 2015-02-24 2016-08-25 Vertafore, Inc. Method and system of assessing risk associated with users based at least in part on online presence of the user

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140122401A1 (en) * 2012-10-29 2014-05-01 Sas Institute Inc. System and Method for Combining Segmentation Data
CN104866969A (zh) * 2015-05-25 2015-08-26 百度在线网络技术（北京）有限公司 个人信用数据处理方法和装置
CN104965913A (zh) * 2015-07-03 2015-10-07 重庆邮电大学 一种基于gps地理位置数据挖掘的用户分类方法
CN105808698A (zh) * 2016-03-03 2016-07-27 江苏大学 一种面向物联网用户查询请求的TOP-k位置兴趣点推荐方法
CN105894323A (zh) * 2016-03-29 2016-08-24 乐视控股（北京）有限公司 用户评测方法、指标项模型训练方法和装置
CN105894089A (zh) * 2016-04-21 2016-08-24 百度在线网络技术（北京）有限公司 一种征信模型的建立方法、征信确定方法及对应装置

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109861985B (zh) * 2019-01-02 2022-12-27 平安科技（深圳）有限公司 基于风险等级划分的ip风控方法、装置、设备和存储介质
CN109861985A (zh) * 2019-01-02 2019-06-07 平安科技（深圳）有限公司 基于风险等级划分的ip风控方法、装置、设备和存储介质
CN110348703A (zh) * 2019-06-21 2019-10-18 平安科技（深圳）有限公司 基于用户行为画像的数据处理方法、装置及电子设备
CN110348703B (zh) * 2019-06-21 2024-03-01 平安科技（深圳）有限公司 基于用户行为画像的数据处理方法、装置及电子设备
CN113435762A (zh) * 2020-05-06 2021-09-24 支付宝(杭州)信息技术有限公司 一种企业风险识别方法、装置及设备
CN113435762B (zh) * 2020-05-06 2023-08-08 支付宝(杭州)信息技术有限公司 一种企业风险识别方法、装置及设备
CN112131321A (zh) * 2020-08-06 2020-12-25 亿存(北京)信息科技有限公司 用户画像标签的生成方法和装置、计算机设备、存储介质
CN112580882A (zh) * 2020-12-23 2021-03-30 平安银行股份有限公司 行程制定方法、装置、设备及介质
CN112580882B (zh) * 2020-12-23 2023-08-18 平安银行股份有限公司 行程制定方法、装置、设备及介质
CN112907360A (zh) * 2021-03-25 2021-06-04 深圳前海微众银行股份有限公司 风险评估方法、设备、存储介质及程序产品
CN112907360B (zh) * 2021-03-25 2024-06-07 深圳前海微众银行股份有限公司 风险评估方法、设备、存储介质及程序产品
CN113535495A (zh) * 2021-06-01 2021-10-22 成都雅信安科技服务有限公司 一种智能设备的硬件及其组件唯一性判断方法
CN113610517A (zh) * 2021-07-27 2021-11-05 浙江惠瀜网络科技有限公司 基于照片位置信息的家装分期业务应用方法及装置
CN114785616A (zh) * 2022-06-13 2022-07-22 深圳红途科技有限公司 数据风险检测方法、装置、计算机设备及存储介质
CN114969566A (zh) * 2022-06-27 2022-08-30 中国测绘科学研究院 一种距离度量的政务服务事项协同过滤推荐方法
CN114969566B (zh) * 2022-06-27 2023-03-24 中国测绘科学研究院 一种距离度量的政务服务事项协同过滤推荐方法
CN117237123A (zh) * 2023-11-15 2023-12-15 山东政信大数据科技有限责任公司 基于区块链的金融信用风险智能管控方法及系统
CN117237123B (zh) * 2023-11-15 2024-03-01 山东政信大数据科技有限责任公司 基于区块链的金融信用风险智能管控方法及系统

Also Published As

Publication number Publication date
CN106651603A (zh) 2017-05-10

Similar Documents

Publication Publication Date Title
WO2018120427A1 (zh) 基于位置服务的风险评估方法、装置、设备和存储介质
WO2018120424A1 (zh) 基于位置服务的人群分类方法、装置、设备和存储介质
WO2018120428A1 (zh) 个性化场景预测方法、装置、设备和存储介质
WO2018120425A1 (zh) 个人财产状态评估方法、装置、设备和存储介质
US10528811B2 (en) Building footprint extraction apparatus, method and computer program product
US11379754B2 (en) Entity resolution incorporating data from various data sources which uses tokens and normalizes records
US10948526B2 (en) Non-parametric statistical behavioral identification ecosystem for electricity fraud detection
CN105404629B (zh) 确定地图界面的方法和装置
WO2018120426A1 (zh) 基于位置服务的个人健康状态评估方法、装置、设备和存储介质
US9179253B2 (en) Map service method and system of providing target contents based on location
US9418377B2 (en) System and method for visualizing property based listing on a mobile device
US11538121B2 (en) Location-based verification of user requests and generation of notifications on mobile devices
WO2016081782A1 (en) Parking identification and availability prediction
US11663282B2 (en) Taxonomy-based system for discovering and annotating geofences from geo-referenced data
US11886495B2 (en) Predictively presenting search capabilities
EP3095013B1 (en) Method and system for use in connection with an industrial control system
KR20160027848A (ko) 콘텐츠 검색 방법 및 이를 구현하는 전자 장치
AU2017389350A1 (en) Method of acquiring biometric data and electronic device therefor
CN103390013A (zh) 电子装置和手写文档处理方法
WO2018107727A1 (zh) 一种信息处理方法、装置及终端
CN106506771B (zh) 联系人对象分类展示方法、装置及移动终端
CN106372090B (zh) 一种查询聚类方法及装置
US11100424B2 (en) Control system for learning and surfacing feature correlations
JP7336780B1 (ja) プログラム、方法、情報処理装置、システム
US10419555B2 (en) Computing system and methods for associating computing devices

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17889462

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC , EPO FORM 1205A DATED 01.10.19.

122 Ep: pct application non-entry in european phase

Ref document number: 17889462

Country of ref document: EP

Kind code of ref document: A1