CN117336723A - User identification card issuing control method and device, electronic equipment and storage medium - Google Patents

User identification card issuing control method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN117336723A
CN117336723A CN202311125281.9A CN202311125281A CN117336723A CN 117336723 A CN117336723 A CN 117336723A CN 202311125281 A CN202311125281 A CN 202311125281A CN 117336723 A CN117336723 A CN 117336723A
Authority
CN
China
Prior art keywords
longitude
cluster
latitude coordinates
fraud
address
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
CN202311125281.9A
Other languages
Chinese (zh)
Inventor
马俊华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Telecom Corp Ltd
Original Assignee
China Telecom Corp Ltd
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 China Telecom Corp Ltd filed Critical China Telecom Corp Ltd
Priority to CN202311125281.9A priority Critical patent/CN117336723A/en
Publication of CN117336723A publication Critical patent/CN117336723A/en
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/12—Detection or prevention of fraud
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/60—Context-dependent security
    • H04W12/63—Location-dependent; Proximity-dependent
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/60—Context-dependent security
    • H04W12/63—Location-dependent; Proximity-dependent
    • H04W12/64—Location-dependent; Proximity-dependent using geofenced areas
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/60—Context-dependent security
    • H04W12/67—Risk-dependent, e.g. selecting a security level depending on risk profiles
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/80—Arrangements enabling lawful interception [LI]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W8/00—Network data management
    • H04W8/18—Processing of user or subscriber data, e.g. subscribed services, user preferences or user profiles; Transfer of user or subscriber data

Abstract

The application discloses a method, a device, electronic equipment and a storage medium for controlling the issuing of a user identification card, wherein the method comprises the following steps: acquiring longitude and latitude coordinates of historical fraud addresses, wherein the longitude and latitude coordinates of each historical fraud address belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates; clustering longitude and latitude coordinates of the historic fraud addresses by using a distance-based clustering algorithm and a density-based clustering algorithm to obtain a first target cluster; determining a fraud-related high-risk area corresponding to each first target cluster; under the condition that the address to be detected is obtained, whether the user identification card to be issued to the address to be detected is intercepted or not is determined according to whether longitude and latitude coordinates of the address to be detected are in a fraud-related high-risk area or not. By applying the technical scheme provided by the application, the distance-based clustering algorithm and the density-based clustering algorithm are utilized to carry out the delineating of the high-risk area involved in the fraud, and the risk management and control are carried out before the user identification card is accessed to the network, so that the risk involved in the fraud after the access to the network can be effectively reduced.

Description

User identification card issuing control method and device, electronic equipment and storage medium
Technical Field
The present invention relates to the field of computer application technologies, and in particular, to a method and apparatus for controlling issuing of a user identification card, an electronic device, and a storage medium.
Background
Currently, telecommunication fraud approaches are endless and anti-fraud approaches are also continually following.
The existing anti-fraud means are mostly applied to the anti-fraud interception after the user identification card is accessed to the network, namely, after the user identification card is accessed to the network, the anti-fraud interception is carried out through modes such as manual statistical analysis or big data modeling. This approach is prone to interception hysteresis problems and is difficult to form a powerful hold-down for fraud situations.
Disclosure of Invention
The purpose of the application is to provide a user identification card issuing control method, a device, electronic equipment and a storage medium, so that risk management and control are carried out before the user identification card is accessed to the network, and the risk of fraud after the user identification card is accessed to the network is effectively reduced.
In order to solve the technical problems, the application provides the following technical scheme:
in a first aspect, a method for controlling issuance of a subscriber identity module card is provided, including: :
acquiring longitude and latitude coordinates of historical fraud addresses, wherein the longitude and latitude coordinates of each historical fraud address belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates;
clustering longitude and latitude coordinates of the historical fraud-related addresses to obtain a first target cluster;
Determining a fraud-related high-risk area corresponding to each first target cluster;
under the condition that an address to be detected is obtained, determining whether to intercept a user identification card to be issued to the address to be detected according to whether longitude and latitude coordinates of the address to be detected are in the fraud-related high-risk area;
the first target cluster comprises a first cluster and a second cluster, the first cluster is obtained by clustering sparse longitude and latitude coordinates by using a distance-based clustering algorithm, and the second cluster is obtained by clustering dense longitude and latitude coordinates by using a density-based clustering algorithm.
Optionally, the latitude and longitude coordinates of each historic fraud-related address are determined to belong to sparse latitude and longitude coordinates or dense latitude and longitude coordinates by the following steps:
clustering longitude and latitude coordinates of the historic fraud addresses by using the density-based clustering algorithm to obtain a plurality of initial clusters;
and determining that the longitude and latitude coordinates included in each initial cluster belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates.
Optionally, the determining that the longitude and latitude coordinates included in each initial cluster belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates includes:
For each initial cluster, if the number of longitude and latitude coordinates included in the current initial cluster is smaller than or equal to a first threshold, determining the longitude and latitude coordinates included in the current initial cluster as sparse longitude and latitude coordinates.
Optionally, the method further comprises:
if the number of longitude and latitude coordinates included in the current initial cluster is larger than the first threshold, determining an average spherical distance between the longitude and latitude coordinates in the current initial cluster; the method comprises the steps of carrying out a first treatment on the surface of the
If the average spherical distance is greater than or equal to a second threshold value, determining longitude and latitude coordinates included in the current initial cluster as sparse longitude and latitude coordinates;
and if the average spherical distance is smaller than the second threshold value, determining longitude and latitude coordinates included in the current initial cluster as dense longitude and latitude coordinates.
Optionally, the first cluster and the second cluster are obtained by:
clustering the sparse longitude and latitude coordinates according to a first clustering parameter by using a distance-based clustering algorithm to obtain a third cluster;
clustering the dense longitude and latitude coordinates according to a second clustering parameter by using the density-based clustering algorithm to obtain a fourth cluster;
Determining the region range corresponding to each third cluster and each fourth cluster; the method comprises the steps of carrying out a first treatment on the surface of the
And if the adjustment instruction for the clustering parameters is not received, determining the third cluster as the first cluster and the fourth cluster as the second cluster.
Optionally, the method further comprises:
if an adjustment instruction for the clustering parameters is received, adjusting the first clustering parameters and/or the second clustering parameters;
and repeatedly executing the step of clustering the sparse longitude and latitude coordinates according to a first clustering parameter by using the distance-based clustering algorithm, and the step of clustering the dense longitude and latitude coordinates according to a second clustering parameter by using the density-based clustering algorithm.
Optionally, after the determining the area ranges corresponding to each third cluster and each fourth cluster, the method further includes:
and visually displaying the longitude and latitude coordinates of the historic fraud addresses and the area range on a map.
Optionally, after the determining the area ranges corresponding to each third cluster and each fourth cluster, the method further includes:
for each second target cluster, determining whether the current second target cluster meets the control requirement according to the ratio of the historical traffic of the area range corresponding to the current second target cluster to the historical traffic of the service area where the current second target cluster is located;
If the control requirement is not met, outputting prompt information;
wherein the second target cluster includes the third cluster and the fourth cluster.
Optionally, the determining the area range corresponding to each third cluster and each fourth cluster includes:
for each third target cluster, if the current third target cluster comprises at least two longitude and latitude coordinates, determining the center point coordinates of the current third target cluster and the maximum spherical distance from the center point coordinates to the longitude and latitude coordinates of the current third target cluster; the method comprises the steps of carrying out a first treatment on the surface of the
Determining a region range corresponding to the current third target cluster by taking the center point coordinate as a center and the maximum spherical distance as a radius;
wherein the third target cluster includes the third cluster and the fourth cluster.
Optionally, the determining the area range corresponding to each third cluster and each fourth cluster includes:
for each fourth target cluster, if the current fourth target cluster only comprises a longitude and latitude coordinate, determining a region range corresponding to the current fourth target cluster by taking the longitude and latitude coordinate of the current fourth target cluster as a center and setting a spherical distance as a radius;
Wherein the fourth target cluster includes the third cluster and the fourth cluster.
Optionally, after the obtaining the latitude and longitude coordinates of the historical fraud address, before the clustering the latitude and longitude coordinates of the historical fraud address to obtain the first target cluster, the method further includes:
and converting the longitude and latitude coordinates of the historical fraud addresses to unify coordinate systems corresponding to the longitude and latitude coordinates of different historical fraud addresses.
Optionally, the address to be detected is obtained by:
obtaining registration information, wherein the registration information at least comprises a registration address;
filtering the registration information to determine whether the registration address is valid; the method comprises the steps of carrying out a first treatment on the surface of the
And determining the registration address as the address to be detected in the case that the registration address is valid.
In a second aspect, there is provided a user identification card issuance control apparatus, comprising: :
the first obtaining module is used for obtaining longitude and latitude coordinates of the historical fraud addresses, and the longitude and latitude coordinates of each historical fraud address belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates;
the second obtaining module is used for carrying out clustering processing on longitude and latitude coordinates of the historic fraud addresses to obtain a first target cluster;
The first determining module is used for determining a fraud-related high-risk area corresponding to each first target cluster;
the second determining module is used for determining whether to intercept the user identification card to be issued to the address to be detected according to whether the longitude and latitude coordinates of the address to be detected are in the fraud-related high-risk area or not under the condition that the address to be detected is obtained;
the first target cluster comprises a first cluster and a second cluster, the first cluster is obtained by clustering sparse longitude and latitude coordinates by using a distance-based clustering algorithm, and the second cluster is obtained by clustering dense longitude and latitude coordinates by using a density-based clustering algorithm.
In a third aspect, an electronic device is provided, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the user identification card issuance control method according to the first aspect when executing the computer program.
In a fourth aspect, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the user identification card issuance control method according to the first aspect.
In a fifth aspect, there is provided a computer program product comprising computer instructions stored in a computer readable storage medium and adapted to be read and executed by a processor to cause a computer device having the processor to perform the steps of the user identification card issuance control method according to the first aspect.
By applying the technical scheme provided by the embodiment of the application, after the longitude and latitude coordinates of the historical fraud-related addresses are obtained, clustering is carried out on the longitude and latitude coordinates of the historical fraud-related addresses to obtain first target clusters, the first target clusters comprise first clusters and second clusters, the first clusters are obtained by clustering sparse longitude and latitude coordinates through a distance-based clustering algorithm, the second clusters are obtained by clustering dense longitude and latitude coordinates through a density-based clustering algorithm, the fraud-related high-risk area corresponding to each first target cluster is determined, and under the condition that the address to be detected is obtained, whether a user identification card to be issued to the address to be detected is intercepted is determined according to whether the longitude and latitude coordinates of the address to be detected are in the fraud-related high-risk area. Namely, the distance-based clustering algorithm and the density-based clustering algorithm are utilized to carry out the delineating of the high-risk area involved in the fraud, and the risk management and control are carried out before the user identification card is accessed to the network, so that the risk involved in the fraud after the user identification card is accessed to the network can be effectively reduced.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic business flow diagram of an application scenario in an embodiment of the present application; the method comprises the steps of carrying out a first treatment on the surface of the
Fig. 2 is a flowchart of an implementation of a method for controlling issuance of a subscriber identity module card according to an embodiment of the present application;
fig. 3 is a schematic diagram of an interception rule generating flow in the embodiment of the present application;
fig. 4 is a schematic diagram of a control flow for issuing a user identification card in the embodiment of the present application;
fig. 5 is a schematic structural diagram of a user identification card issuing control device in an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Detailed Description
In order to provide a better understanding of the present application, those skilled in the art will now make further details of the present application with reference to the drawings and detailed description. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
The method can be applied to an anti-fraud management and control server, the anti-fraud management and control server can control the on-line or off-line number platform to issue the user identification card, after the longitude and latitude coordinates of the historical fraud addresses are obtained, the longitude and latitude coordinates of the historical fraud addresses are clustered to obtain first target clusters, the first target clusters comprise first clusters and second clusters, the first clusters are obtained by clustering sparse longitude and latitude coordinates through a distance-based clustering algorithm, the second clusters are obtained by clustering dense longitude and latitude coordinates through a density-based clustering algorithm, a fraud high risk area corresponding to each first target cluster is determined, and whether the user identification card to be issued to the address to be detected is intercepted or not is determined according to whether the longitude and latitude coordinates of the address to be detected are in the fraud high risk area or not under the condition that the address to be detected is obtained. Namely, the distance-based clustering algorithm and the density-based clustering algorithm are utilized to carry out the delineating of the high-risk area involved in the fraud, and the risk management and control are carried out before the user identification card is accessed to the network, so that the risk involved in the fraud after the user identification card is accessed to the network can be effectively reduced.
Taking the mobile phone card number-placing anti-fraud management and control scene of the on-line channel of the operator facing the national area as an example, the business flow is shown in fig. 1, and the explanation of each link is as follows:
on-line number placing channel: the online number placing channel comprises an operator own operation platform and an agent self-built operation platform, and a user can perform number selecting operation on a relevant platform and submit a number application;
collecting registration information: collecting user registration information collected from an online channel number platform, wherein the user has to provide at least four items of information including names, certificate numbers, contact phones and delivery addresses according to real-name systems and telephone card delivery requirements; the delivery address is a receiving address of the user;
high-risk interception related to fraud: according to registration information provided by a user, the technical scheme provided by the embodiment of the application is applied to judging the risk of the fraud, and interception feedback is carried out on suspected high-risk fraud personnel to a number placing platform;
the auditing is as follows: giving a telephone card acceptance feedback to the user application safely intercepted by the fraud, and feeding back an acceptance result to the number release platform;
anti-fraud management and control after network access: and carrying out normalized fraud-related high-risk behavior monitoring on the numbers after network access.
Referring to fig. 2, a flowchart of an implementation of a method for controlling user identification card issuance according to an embodiment of the present application may include the following steps:
s210: longitude and latitude coordinates of the historic fraud addresses are obtained.
The longitude and latitude coordinates of each historic fraud address belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates.
In the embodiment of the application, the historical fraud-related address can be obtained through a data acquisition mode such as a web crawler or an information reporting mode.
Alternatively, the historical fraud-related address may be a fraud-related address within a set period of time from the current time, such as a fraud-related address within three or six months from the current time. Alternatively, the historical fraud involving address may be a registered address of the fraud involving person when purchasing the user identification card, such as a delivery address of the fraud involving person when purchasing the user identification card on-line with the listing platform, or a resident address provided by the fraud involving person when purchasing the user identification card on-line with the listing platform.
After the historical fraud-related addresses are obtained, the historical fraud-related addresses can be converted into corresponding longitude and latitude coordinates, namely geographic position information through geocoding. Geocoding may convert a readable address description into computer-processable geographic location information.
Alternatively, the historic fraud-related address may be input to an application programming interface (Application Programming Interface, API) of the map application, and longitude and latitude coordinates corresponding to the historic fraud-related address output by the API interface may be obtained.
Or a geographic data set website containing an address and corresponding longitude and latitude coordinates can be logged in, a developer tool (such as a developer console) is used for acquiring the position and format of the address and the longitude and latitude coordinates in a hypertext markup language (Hyper Text Markup Language, HTML) source code of the geographic data set website, then based on the position and format of the address and the longitude and latitude coordinates in the HTML source code of the geographic data set website, a web crawler code which corresponds to the geographic data set website and is based on Requests or a script library is written through a Python programming language, a hypertext transfer protocol (Hypertext Transfer Protocol, HTTP) request is sent through the web crawler code, the web page content of the geographic data set website is acquired, finally, the web page content is analyzed through an HTML analysis library (such as Beautiful so or lxml), and the historical fraud addresses and the longitude and latitude coordinates corresponding to the historical fraud addresses are extracted.
The obtained historical fraud-related addresses can be one or more, and the longitude and latitude coordinates of each historical fraud-related address belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates.
S220: and clustering longitude and latitude coordinates of the historic fraud addresses to obtain a first target cluster.
The first target cluster comprises a first cluster and a second cluster, wherein the first cluster is obtained by clustering sparse longitude and latitude coordinates by using a distance-based clustering algorithm, and the second cluster is obtained by clustering dense longitude and latitude coordinates by using a density-based clustering algorithm.
In the embodiment of the application, after obtaining the longitude and latitude coordinates of the historic fraud addresses and determining that the longitude and latitude coordinates of each historic fraud address belong to the sparse longitude and latitude coordinates or the dense longitude and latitude coordinates, clustering the sparse longitude and latitude coordinates by using a distance-based clustering algorithm to obtain a first cluster, and clustering the dense longitude and latitude coordinates by using a density-based clustering algorithm to obtain a second cluster. The first cluster and the second cluster form a first target cluster.
Alternatively, the distance-based clustering algorithm may be a K-means (kmens) clustering algorithm that may treat data points that are relatively close in distance as similar points, divided into the same cluster. Alternatively, the Density-based clustering algorithm may be a Density-based spatial clustering application with noise (Density-Based Spatial Clustering of Applications with Noise, DBSCAN) algorithm that may process data points based on Density, dividing sufficiently dense points in feature space into the same cluster.
For sparse data points, the distance between the data points is larger, when a distance-based clustering algorithm is used, it is generally assumed that each cluster is represented by one center point (centroid), the center of the cluster can be accurately represented by selecting a proper centroid, each data point is allocated to the cluster represented by the centroid closest to the data point, so that a better clustering effect is achieved, and the distance between the centroid and the data point can better represent the compactness of clustering.
For dense data points, the distance between the data points is smaller, and when a density-based clustering algorithm is used, the cluster boundary can be effectively determined through density accessibility, so that a better clustering result is obtained in a complex data set. The density-based clustering algorithm does not require a pre-specified number of clusters, and can automatically determine the number of clusters based on the density between data points. For dense data points, clusters in the data points can be large in number and complex in shape, and a density-based clustering algorithm can be better suitable for the situation, and areas with different densities can be automatically identified and corresponding clusters can be formed.
In the embodiment of the application, the sparse longitude and latitude coordinates are clustered by using a distance-based clustering algorithm, and the dense longitude and latitude coordinates are clustered by using a density-based clustering algorithm, so that the accuracy of clustering the longitude and latitude coordinates is improved, the high-risk area involved in the fraud is determined according to a comprehensive and accurate clustering result, and the interception involved in the fraud is accurately performed.
S230: and determining a fraud-related high-risk area corresponding to each first target cluster.
Clustering is carried out on longitude and latitude coordinates of the historic fraud-related addresses, and after the first target clusters are obtained, the fraud-related high-risk areas corresponding to each first target cluster can be respectively determined.
Optionally, for each first target cluster, if the current first target cluster includes at least two longitude and latitude coordinates, determining a center point coordinate of the current first target cluster and a maximum spherical distance from the center point coordinate to the longitude and latitude coordinates included in the current first target cluster, and determining a fraud-related high-risk area corresponding to the current first target cluster by taking the center point coordinate as a center and the maximum spherical distance as a radius;
if the current first target cluster only comprises one longitude and latitude coordinate, the current first target cluster is taken as a center, a spherical distance is set as a radius, and a fraud-related high-risk area corresponding to the current first target cluster is determined.
S240: under the condition that the address to be detected is obtained, whether the user identification card to be issued to the address to be detected is intercepted or not is determined according to whether longitude and latitude coordinates of the address to be detected are in a fraud-related high-risk area or not.
The high risk area of the fraud corresponding to the first target cluster has historical fraud addresses, the historical fraud behaviors occur, and the risk of the fraud of longitude and latitude coordinates in the high risk area of the fraud is high, so that under the condition that the address to be detected is obtained, whether the longitude and latitude coordinates of the address to be detected are in the high risk area of the fraud can be determined, and whether the user identification card to be issued to the address to be detected is intercepted or not is further determined.
Optionally, after the address to be detected is obtained, the spherical distance may be calculated based on the longitude and latitude coordinates of the address to be detected and the center point coordinates of each fraud-related high-risk area, and if there is a fraud-related high-risk area with the spherical distance smaller than or equal to the maximum spherical radius distance, it is determined that the longitude and latitude coordinates of the address to be detected are in the fraud-related high-risk area.
Optionally, if the longitude and latitude coordinates of the address to be detected are in a high risk area of fraud, the risk of fraud of the user located at the address to be detected can be considered to be high, and the user identification card to be issued to the address to be detected can be determined to be intercepted. Optionally, if it is determined to intercept the subscriber identity card to be issued to the address to be detected, an interception instruction may be sent to the online or offline number platform to avoid issuing the subscriber identity card to the address to be detected.
Optionally, if the longitude and latitude coordinates of the address to be detected are not in the fraud-related high-risk area, the fraud-related risk of the user located at the address to be detected can be considered to be low, the user identification card to be issued to the address to be detected can be determined not to be intercepted, and the verification is passed, so that the online or offline number-releasing platform issues the user identification card to the address to be detected normally.
By applying the method provided by the embodiment of the application, after the longitude and latitude coordinates of the historical fraud-related addresses are obtained, clustering is carried out on the longitude and latitude coordinates of the historical fraud-related addresses to obtain first target clusters, the first target clusters comprise first clusters and second clusters, the first clusters are obtained by clustering sparse longitude and latitude coordinates through a distance-based clustering algorithm, the second clusters are obtained by clustering dense longitude and latitude coordinates through a density-based clustering algorithm, the fraud-related high risk area corresponding to each first target cluster is determined, and under the condition that the address to be detected is obtained, whether a user identification card to be issued to the address to be detected is intercepted is determined according to whether the longitude and latitude coordinates of the address to be detected are in the fraud-related high risk area. Namely, the distance-based clustering algorithm and the density-based clustering algorithm are utilized to carry out the delineating of the high-risk area involved in the fraud, and the risk management and control are carried out before the user identification card is accessed to the network, so that the risk involved in the fraud after the user identification card is accessed to the network can be effectively reduced.
In some embodiments of the present application, it may be determined that the latitude and longitude coordinates of each historic fraud address belong to sparse latitude and longitude coordinates or dense latitude and longitude coordinates by:
step one: clustering longitude and latitude coordinates of the historic fraud addresses by using a density-based clustering algorithm to obtain a plurality of initial clusters;
step two: and determining that the longitude and latitude coordinates included in each initial cluster belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates.
For ease of understanding, the two steps described above are described in combination.
In clustering multiple data points, there are many outliers, and distance-based clustering algorithms do not treat these outliers as separate clusters, but rather group them into clusters that include more data points, resulting in less accurate clustering. An outlier may be understood as a point that is significantly different in value from other data points. And density-based clustering algorithms can solve such problems.
In the embodiment of the application, the longitude and latitude coordinates of the historic fraud addresses can be clustered by using a density-based clustering algorithm to obtain a plurality of initial clusters, and then the longitude and latitude coordinates included in each initial cluster are determined to belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates, so that the dividing accuracy can be improved.
The clustering parameters to be set for the density-based clustering algorithm can comprise a neighborhood radius eps and a minimum sample number min_samples in the neighborhood, and based on the parameters, clustering and grouping can be carried out on longitude and latitude coordinates of the historic fraud addresses to obtain a plurality of initial clustering clusters.
Wherein the neighborhood radius eps is a distance measure for locating points within the neighborhood of any point; the minimum number of samples in the neighborhood, min_samples, is the minimum number of points clustered together (a threshold), leaving a region defined as dense. Illustratively, in the embodiment of the present application, the neighborhood radius eps=0.5, and the minimum number of samples min_samples=1 in the neighborhood, which may allow a single longitude and latitude coordinate to be used as a cluster.
In some embodiments of the present application, determining that the longitude and latitude coordinates included in each initial cluster belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates may include the following steps:
for each initial cluster, if the number of longitude and latitude coordinates included in the current initial cluster is smaller than or equal to a first threshold, determining the longitude and latitude coordinates included in the current initial cluster as sparse longitude and latitude coordinates.
In the embodiment of the application, the longitude and latitude coordinates of the historical fraud-related addresses are clustered by using a density-based clustering algorithm, after a plurality of initial clustering clusters are obtained, the number of the longitude and latitude coordinates included in the current initial clustering cluster can be compared with a first threshold value for each initial clustering cluster, if the number of the longitude and latitude coordinates included in the current initial clustering cluster is smaller than or equal to the first threshold value, the number of the longitude and latitude coordinates included in the current initial clustering cluster is smaller, and the longitude and latitude coordinates included in the current initial clustering cluster can be determined to be sparse longitude and latitude coordinates.
The current initial cluster is the initial cluster for which the current operation is directed. The first threshold may be set and adjusted according to the actual situation, for example, a value of 1 to 3.
Optionally, if the number of longitude and latitude coordinates included in the current initial cluster is greater than the first threshold, the longitude and latitude coordinates included in the current initial cluster may be determined as dense longitude and latitude coordinates.
In some embodiments of the present application, for each initial cluster, if the number of longitude and latitude coordinates included in the current initial cluster is greater than a first threshold, an average spherical distance between the longitude and latitude coordinates in the current initial cluster may be determined, if the average spherical distance is greater than or equal to a second threshold, the longitude and latitude coordinates included in the current initial cluster may be determined as sparse longitude and latitude coordinates, and if the average spherical distance is less than the second threshold, the longitude and latitude coordinates included in the current initial cluster may be determined as dense longitude and latitude coordinates.
In the embodiment of the present application, an initial cluster including longitude and latitude coordinates with a number greater than a first threshold may be used as a pending cluster, and an average spherical distance between every two longitude and latitude coordinates in a cluster corresponding to each pending cluster may be calculated. That is, for each initial cluster, if the number of longitude and latitude coordinates included in the current initial cluster is greater than a first threshold, determining an average spherical distance between the longitude and latitude coordinates in the current initial cluster. And then taking the longitude and latitude coordinates included in the initial cluster with the average spherical distance larger than or equal to the second threshold value as sparse longitude and latitude coordinates, and taking the longitude and latitude coordinates included in the initial cluster with the average spherical distance smaller than the second threshold value as dense longitude and latitude coordinates.
The current initial cluster is the initial cluster for which the current operation is directed. The second threshold may be set and adjusted according to the actual situation, for example, 10 or 15.
For example, for each initial cluster, specific algorithm logic for determining that the longitude and latitude coordinates included in the current initial cluster belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates is as follows:
(1) If the current initial cluster only comprises one longitude and latitude coordinate, taking the longitude and latitude coordinate comprising the current initial cluster as a sparse longitude and latitude coordinate;
(2) If the number of longitude and latitude coordinates included in the current initial cluster is greater than one, calculating the average spherical distance between every two longitude and latitude coordinates in the cluster according to the following algorithm:
assuming that the obtained longitude and latitude coordinates are expressed as (lng, lat), the coordinates of the radian system are expressed as (λ, Φ), the radian system representation of the longitude and latitude coordinates can be calculated by the following conversion formula:
where pi is a constant circumference ratio.
If two longitude and latitude coordinates are respectively expressed as P 1 (λ 1 ，φ 1 ) And P 2 (λ 2 ，φ 2 ) The spherical distance D (P) of two longitude and latitude coordinates can be calculated using the following spherical distance formula 1 ，P 2 )：
Wherein Δφ=φ 1 -φ 2 ，Δλ＝λ 1 -λ 2 ，R＝6371.393，(λ 1 ，φ 1 ) Is one of two longitude and latitude coordinates, (lambda) 2 ，φ 2 ) Is another longitude and latitude coordinate.
Assuming that n longitude and latitude coordinates exist in the current initial cluster, D (P i ，P j ) Representing any two different longitude and latitude coordinates P i And P j The average spherical distance d between longitude and latitude coordinates in a cluster is calculated by using the following formula:
if the average spherical distance is greater than 10, all longitude and latitude coordinates included in the current initial cluster are used as sparse longitude and latitude coordinates, otherwise, all longitude and latitude coordinates included in the current initial cluster are used as dense longitude and latitude coordinates.
Through the steps, longitude and latitude coordinates corresponding to the historic fraud addresses can be divided into dense address groups comprising dense longitude and latitude coordinates and sparse address groups comprising sparse longitude and latitude coordinates.
Determining that the longitude and latitude coordinates of each historic fraud-related address belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates is beneficial to improving the accuracy of subsequently determining the first target cluster and the fraud-related high-risk area.
In some embodiments of the present application, the first cluster and the second cluster may be obtained by:
the first step: clustering the sparse longitude and latitude coordinates according to a first clustering parameter by using a distance-based clustering algorithm to obtain a third cluster;
And a second step of: clustering the dense longitude and latitude coordinates according to the second clustering parameter by using a density-based clustering algorithm to obtain a fourth cluster;
and a third step of: determining the region range corresponding to each third cluster and each fourth cluster;
fourth step: if no adjustment instruction for the cluster parameters is received, the third cluster is determined as the first cluster, and the fourth cluster is determined as the second cluster.
For convenience of description, the above four steps are described in combination.
In the embodiment of the application, longitude and latitude coordinates of the historic fraud addresses are obtained, after the longitude and latitude coordinates of each historic fraud address are determined to belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates, the sparse longitude and latitude coordinates can be clustered according to a first clustering parameter by utilizing a distance-based clustering algorithm to obtain third clusters, each third cluster comprises one or more sparse longitude and latitude coordinates, the dense longitude and latitude coordinates are clustered according to a second clustering parameter by utilizing a density-based clustering algorithm to obtain fourth clusters, and each fourth cluster comprises one or more dense longitude and latitude coordinates. The first clustering parameter may be an initial clustering parameter of a distance-based clustering algorithm, may be set and adjusted according to actual conditions or user experience, and the second clustering parameter may be an initial clustering parameter of a density-based clustering algorithm, may be set and adjusted according to actual conditions or user experience.
The clustering parameters required to be set for the distance-based clustering algorithm can comprise the number of clustering clusters, and the clustering parameters required to be set for the density-based clustering algorithm can comprise a neighborhood radius eps and a minimum sample number min_samples in the neighborhood.
After the third cluster and the fourth cluster are obtained, the area range corresponding to each third cluster and each fourth cluster can be further determined. If the adjustment instruction for the clustering parameters is not received within the set time length, the third cluster can be determined to be the first cluster, and the fourth cluster can be determined to be the second cluster. The area range corresponding to the third cluster may be further determined as a high risk area related to fraud corresponding to the first cluster, and the area range corresponding to the fourth cluster may be determined as a high risk area related to fraud corresponding to the second cluster.
By the steps, the accuracy of determining the first cluster and the second cluster can be improved.
In some embodiments of the present application, the method may further comprise the steps of: :
if an adjustment instruction for the clustering parameters is received, adjusting the first clustering parameters and/or the second clustering parameters;
and repeatedly executing the steps of clustering the sparse longitude and latitude coordinates according to the first clustering parameter by using a distance-based clustering algorithm and clustering the dense longitude and latitude coordinates according to the second clustering parameter by using a density-based clustering algorithm.
In this embodiment of the present application, after obtaining the third cluster and the fourth cluster, and further determining the area ranges corresponding to each of the third cluster and each of the fourth cluster, if an adjustment instruction for the cluster parameter is received, the first cluster parameter and/or the second cluster parameter may be adjusted. And then clustering the sparse longitude and latitude coordinates according to the adjusted first clustering parameter by using a distance-based clustering algorithm to obtain a new third cluster, clustering the dense longitude and latitude coordinates according to the second clustering parameter by using a density-based clustering algorithm to obtain a new fourth cluster, determining each new third cluster and a region range corresponding to each new fourth cluster, determining the new third cluster as the first cluster if an adjustment instruction for the new clustering parameter is not received, determining the new fourth cluster as the second cluster, and repeating the steps of adjusting the clustering parameter, clustering, determining the region range and the like until the first cluster and the second cluster are determined if an adjustment operation for the new clustering parameter is received.
And adjusting the first clustering parameter and/or the second clustering parameter, so that the determined first clustering cluster and second clustering cluster are more accurate.
In some embodiments of the present application, after determining the area ranges corresponding to each third cluster and each fourth cluster, longitude and latitude coordinates of the historic fraud addresses and the area ranges may also be visually displayed on the map.
Optionally, the longitude and latitude coordinates of the historic fraud addresses, the area range corresponding to each third cluster and each fourth cluster can be visually displayed on the map by using a map library. For example, the map library is a Mapbox, the corresponding longitude and latitude coordinates and the region range can be used as a GeoJSON object through an API interface of the Mapbox, the GeoJSON object is added to the map by using the Mapbos GL JS library, and a custom mark is created for each longitude and latitude coordinate. The map may be a national map of a country. For another example, the API interface of the map application may be directly used to add the corresponding latitude and longitude coordinates and the area scope to the map. The respective longitude and latitude coordinates may include longitude and latitude coordinates of the historic fraud addresses, center point coordinates of each third cluster and each fourth cluster.
The area range corresponding to each third cluster and each fourth cluster is visually displayed on the map, so that a user can conveniently and intuitively check whether the currently-defined high-risk area related to the fraud meets the management and control requirements or not, the user can more conveniently adjust the first cluster parameters of the distance-based clustering algorithm and the second cluster parameters of the density-based clustering algorithm based on the visual display results on the map, the parameter adjustment accuracy and efficiency are improved, the area range on the map can be adjusted, and the finally-determined high-risk area related to the fraud is obtained.
As shown in fig. 3, a schematic diagram of a flow is generated for intercepting rules, and the flow includes: :
obtaining historical fraud addresses, such as historical recent fraud addresses;
acquiring longitude and latitude coordinates of a history fraud-related address;
clustering longitude and latitude coordinates of the historic fraud addresses by using a DBSCAN clustering algorithm to obtain a plurality of initial clusters;
determining that the longitude and latitude coordinates included in each initial cluster belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates;
obtaining a sparse address group and a dense address group;
clustering the sparse longitude and latitude coordinates in the sparse address group according to a first clustering parameter by utilizing a KMeans clustering algorithm to obtain K1 third clustering clusters, and further determining the center point coordinate and the maximum radius distance of each third clustering cluster, wherein the first clustering parameter comprises the number of the clustering clusters; the method comprises the steps of carrying out a first treatment on the surface of the
Clustering the dense longitude and latitude coordinates in the dense address group according to a second cluster parameter by using a DBSCAN clustering algorithm to obtain K2 fourth clusters, and further determining the center point coordinates and the maximum radius distance of each fourth cluster, wherein the second cluster parameter comprises a neighborhood radius and a neighborhood minimum sample number;
visual display is carried out on the map, wherein the visual display comprises longitude and latitude coordinates of historic fraud addresses, center point coordinates of each of K clusters and circles formed by corresponding maximum radiuses of each of the K clusters, and K=K1+K2;
Determining whether an area range corresponding to each cluster in the K clusters is used as a high-risk area related to fraud;
if the area range corresponding to each of the K clusters is used as a fraud-related high-risk area, the center point coordinates and the maximum radius distance of each of the K clusters are saved, and an interception rule is generated;
if the region range corresponding to part or all of the K clusters cannot be used as the high-risk region related to the fraud, the first clustering parameter and/or the second clustering parameter are adjusted, and the steps of clustering the sparse longitude and latitude coordinates and the dense longitude and latitude coordinates are repeatedly executed.
In some embodiments of the present application, after determining the region ranges corresponding to each third cluster and each fourth cluster, the method may further include the steps of:
step one: for each second target cluster, determining whether the current second target cluster meets the control requirement according to the ratio of the historical traffic of the area range corresponding to the current second target cluster to the historical traffic of the service area where the current second target cluster is located;
step two: if the control requirement is not met, outputting prompt information;
wherein the second target cluster includes a third cluster and a fourth cluster.
In the embodiment of the application, after the third cluster and the fourth cluster are obtained and the area range corresponding to each third cluster and each fourth cluster is determined, for each second target cluster, the historical traffic of the area range corresponding to the current second target cluster can be determined, then the historical traffic is compared with the historical traffic of the service area where the current second target cluster is located, the ratio of the two is obtained, and whether the current second target cluster meets the control requirement or not is determined according to the ratio.
Taking an online number placing channel as an example, the historical traffic of the service area where the current second target cluster is located can be about several months, such as about three months, of total traffic corresponding to the service area, and can be specifically understood as about several months, such as about three months, of total number of users with delivery addresses belonging to the service area for dealing with number selecting service; the historical traffic of the area range corresponding to the current second target cluster can be understood as the total number of users who distribute the number-transacted business with the address belonging to the area range in the last several months, such as the last three months.
Optionally, if the ratio is greater than or equal to the third threshold, it may be considered that the historical traffic of the area range corresponding to the current second target cluster occupies a relatively large area, and the corresponding telecommunication service handling requirement is relatively high, and if the area range is used as a fraud-related high-risk area, the influence on the normal number-placing service may be relatively large, and the delineating area is too large and unreasonable, so in this case, it may be determined that the current second target cluster does not meet the management and control requirement, and prompt information may be output, for example, prompt a user to reduce the area range corresponding to the current second target cluster when adjusting the cluster parameter. Optionally, a prompt message "do not meet the control requirement" may be output at a corresponding position of the area range visually displayed, or the area range may be highlighted.
Optionally, if the ratio is smaller than the third threshold, it may be considered that the historical traffic of the area range corresponding to the current second target cluster occupies a relatively small area, and if the area range is taken as a fraud-related high-risk area, the influence on normal traffic is relatively small, so in this case, it may be determined that the current second target cluster meets the management and control requirement, the area range corresponding to the current second target cluster may be taken as a fraud-related high-risk area, and further it is determined whether to intercept the user identification card issued to the address to be detected based on the fraud-related high-risk area.
It should be noted that the second target cluster includes a third cluster and a fourth cluster, that is, the operations of the above steps are performed for each of the third cluster and each of the fourth cluster. The current second target cluster refers to a second target cluster for which the current operation is directed. The third threshold may be set and adjusted according to the actual situation, for example, set to 90%. The service area in which the current second target cluster is located may be an area that is divided administrative, such as an administrative area or a street.
Determining whether each third cluster and each fourth cluster meet the control requirement, and outputting prompt information to adjust the corresponding area range under the condition that the third clusters and the fourth clusters do not meet the control requirement, so that the influence on normal business can be effectively reduced.
In some embodiments of the present application, determining the region ranges corresponding to each third cluster and each fourth cluster may include the steps of:
step one: for each third target cluster, if the current third target cluster comprises at least two longitude and latitude coordinates, determining the center point coordinates of the current third target cluster and the maximum spherical distance from the center point coordinates to the longitude and latitude coordinates of the current third target cluster;
step two: determining a region range corresponding to the current third target cluster by taking the center point coordinate as the center and the maximum spherical distance as the radius;
wherein the third target cluster includes a third cluster and a fourth cluster.
For convenience of description, the above two steps are described in combination.
In the embodiment of the present application, after the third cluster and the fourth cluster are obtained, for each third target cluster, if the current third target cluster includes at least two longitude and latitude coordinates, the center point coordinate of the current third target cluster may be determined. Alternatively, the center point coordinate may be obtained by calculating an average value of longitude and latitude coordinates included in the current third target cluster. The maximum spherical distance from the center point coordinate to the longitude and latitude coordinates included in the current third target cluster can be further determined. Alternatively, the spherical distance from the center point coordinate to each latitude and longitude coordinate included in the current third target cluster may be calculated by a distance formula of a spherical triangle, for example, a spherical distance from the center point in the cluster to each latitude and longitude coordinate in the cluster may be calculated by using a semi-normal formula (Haversine formula), and then the maximum spherical distance may be determined from the calculated spherical distance.
And determining a circular area formed by taking the center point coordinate as the center and the maximum spherical distance as the radius as an area range corresponding to the current third target cluster.
The third target cluster may include a third cluster and a fourth cluster, that is, for each third cluster and each fourth cluster, a corresponding area range may be obtained through the above operation, so as to improve accuracy of determining the area range. The current third target cluster refers to a third target cluster for which the current operation is directed.
In some embodiments of the present application, determining the region ranges corresponding to each third cluster and each fourth cluster may include the steps of:
for each fourth target cluster, if the current fourth target cluster only comprises one longitude and latitude coordinate, determining a region range corresponding to the current fourth target cluster by taking the longitude and latitude coordinate of the current fourth target cluster as the center and setting the spherical distance as the radius;
wherein the fourth target cluster includes a third cluster and a fourth cluster.
In this embodiment of the present application, after the third cluster and the fourth cluster are obtained, for each fourth target cluster, if the current fourth target cluster includes only one longitude and latitude coordinate, a circular area formed by using the longitude and latitude coordinate included in the current fourth target cluster as a center and setting a spherical distance as a radius may be determined as an area range corresponding to the current fourth target cluster.
The fourth target cluster may include a third cluster and a fourth cluster, that is, for each third cluster and each fourth cluster, a corresponding area range may be obtained through the above operation, so as to improve accuracy of determining the area range. The current fourth target cluster refers to a fourth target cluster for which the current operation is directed. The set spherical distance can be set and adjusted according to practical situations, such as one kilometer.
In the embodiment of the application, the map visualization is combined, the clustering parameters are adjusted in an auxiliary mode, the parameter adjustment accuracy and efficiency are improved, the final range of the delinting of the high-risk area involved in the fraud can be determined, meanwhile, the center point coordinates of the high-risk area involved in the fraud and the maximum spherical radius distance in the cluster can be saved, the interception rule is obtained, and the high-risk user is intercepted based on the interception rule.
In some embodiments of the present application, after obtaining the latitude and longitude coordinates of the historic fraud addresses, and before clustering the latitude and longitude coordinates of the historic fraud addresses to obtain the first target cluster, the method may further include the following steps:
and converting the longitude and latitude coordinates of the historical fraud addresses to unify coordinate systems corresponding to the longitude and latitude coordinates of different historical fraud addresses.
It can be understood that the coordinate systems corresponding to the longitude and latitude coordinates of the historic fraud addresses obtained in different manners may be different, for example, the longitude and latitude coordinate a is data in the GCJ02 coordinate system, and the longitude and latitude coordinate B is data in the BD09 coordinate system.
In the embodiment of the application, in order to facilitate sequential execution of subsequent steps, longitude and latitude coordinates of the historical fraud addresses can be converted first to unify coordinate systems corresponding to longitude and latitude coordinates of different historical fraud addresses.
For example, the conversion between the two coordinate systems is as follows:
1) BD09 coordinate System to GCJ02 coordinate System
Assuming that the acquired longitude and latitude coordinates under BD09 are (lng, lat), the initial offset coordinate point (x, y) is calculated using the following conversion formula:
x＝lng-0.0065；y＝lat-0.006；
next, the deflection factors η and θ are calculated by the following formula:
θ＝atan2(y，x)-0.000003cos(x*pi)；
wherein pi=3.14159265358979324×3000.0/180.0, and then obtaining longitude and latitude coordinates (a, b) under GCJ02 through the following conversion calculation:
a＝η*cos(θ)；b＝η*sin(θ)；
from this, the latitude and longitude coordinates (lng, lat) at BD09 can be converted into the latitude and longitude coordinates (a, b) at GCJ 02.
2) GCJ02 coordinate system to BD09 coordinate system
Assuming that the longitude and latitude coordinates under the obtained GCJ02 are (lng, lat), the deflection factors η and θ are calculated by the following formula:
θ＝atan2(lat，lng)+0.000003cos(lng*pi)；
Wherein pi=3.14159265358979324×3000.0/180.0, and then obtaining longitude and latitude coordinates (a, b) under BD09 through the following conversion calculation:
a＝η*cos(θ)+0.0065；b＝η*sin(θ)+0.006；
from this, the latitude and longitude coordinates (lng, lat) at GCJ02 can be converted into the latitude and longitude coordinates (a, b) at BD 09.
The coordinate system is not particularly limited, and the embodiment of the application is just obtained by converting the longitude and latitude coordinate system by using the longitude and latitude coordinate system conversion method described in the embodiment of the application when the coordinate system is converted.
In some embodiments of the present application, the address to be detected may be obtained by:
the first step: obtaining registration information, wherein the registration information at least comprises a registration address;
and a second step of: filtering the registration information to determine whether the registration address is valid;
and a third step of: in the case where the registered address is valid, the registered address is determined as the address to be detected.
For convenience of description, the above three steps are described in combination.
In the embodiment of the application, when the user purchases the user identification card, the user can register information, and the registered information at least comprises a registration address. For example, when the online number platform purchases the subscriber identity card, the registered address may be a shipping address, and when the online number platform purchases the subscriber identity card, the registered address may be a home address or an office address.
After the registration information is obtained, the registration information may be filtered to determine whether the registration address is valid. Optionally, the registration information may be filtered according to a preset fraud list, for example, a name, a certificate number, a contact phone, etc. in the registration information are matched with the fraud list, if the registration information can be matched, the registration address is considered invalid, and the interception of issuing the user identification card to the registration address can be directly determined without detection. Alternatively, the registration information may be filtered according to a preset invalid character to determine whether the registration address is valid, and if any invalid character is included in the registration information, it may be determined that the registration address is invalid. Filtering the registration information may filter out incomplete, non-compliant registration information.
Under the condition that the registration address is effective, the registration address can be determined to be the address to be detected, and whether the user identification card to be issued to the address to be detected is intercepted or not is further determined according to whether the longitude and latitude coordinates of the address to be detected are in a fraud-related high-risk area or not.
The registration information is filtered first to determine the validity of the registration address, so that the detection cost can be reduced.
For convenience of understanding, the technical solution provided in the embodiment of the present application will be described again by taking the flow shown in fig. 4 as an example. The interception rule generating flow may refer to the description of fig. 3, and will not be described in detail.
Acquiring registration information of a user;
filtering the registration information, such as fraud list filtering, invalid address filtering and the like;
obtaining an effective distribution address of a user, and determining the effective distribution address as an address to be detected;
acquiring longitude and latitude coordinates of an address to be detected;
determining whether to intercept the user identification card to be issued to the address to be detected based on the longitude and latitude coordinates of the address to be detected and the interception rule; if the user identification card to be issued to the address to be detected is determined to be intercepted, intercepting feedback is carried out; if the user identification card to be issued to the address to be detected is not intercepted, the verification is passed, and the number-releasing acceptance link is entered.
In general, most of the current telecommunication anti-fraud related technologies are applied to users to access the internet, and according to the abnormal behavior of the numbers, the technologies are judged and intercepted based on manual rules or data modeling means, a great amount of sample data are needed to be relied on for analysis, so that the effects are better, interception is delayed, and the fraud situation is difficult to be strongly suppressed; the existing geographic position-based telecommunication anti-fraud method is generally based on simple rules or simply uses a visual map to display the area where fraud has occurred, the potential risk area where no fraud report has occurred cannot be pre-judged and intercepted, and most of set alarm thresholds are fixed and cannot reflect the current latest characteristics of the area where fraud is involved in high risk in time.
Aiming at the problems that the accurate interception of fraud cannot be performed before the network access and the pre-judgment and interception of potential risk areas which are not reported by the fraud cannot be performed at present, the embodiment of the application provides the address-based user identification card number-placing control method, the pre-judgment of the risk of the fraud can be performed based on the address, the interception is performed in advance before the network access of the user, and the interception rules can be dynamically adjusted according to the latest high-risk area of the fraud, so that the following technical effects can be achieved:
1) The longitude and latitude coordinates of the historic fraud addresses can be accurately acquired through an API interface of a web crawler or a map application program, the address group is divided into a dense address group and a sparse address group by utilizing a density-based clustering algorithm such as a DBSCAN clustering algorithm and a dense sparse address grouping algorithm, so that the sparse longitude and latitude coordinates included in the sparse address group are clustered by utilizing a distance-based clustering algorithm such as a KMeans clustering algorithm, and the dense longitude and latitude coordinates included in the dense address group are clustered by utilizing a density-based clustering algorithm such as a DBSCAN clustering algorithm. The interception rule is generated by using a density-based clustering algorithm for dense longitude and latitude coordinates and a distance-based clustering algorithm for sparse longitude and latitude coordinates, so that the accuracy of clustering the longitude and latitude coordinates can be improved, a fraud-related high-risk area can be effectively determined according to comprehensive and accurate clustering results, and interception processing can be accurately performed based on the fraud-related high-risk area.
2) The distance-based clustering algorithm and the density-based clustering algorithm are used for carrying out delinting and fusion on the high-risk area involved in fraud, the interception range can be dynamically adjusted in time according to the high-risk area involved in fraud recently in history, the finally generated interception rules can be flexibly adjusted according to the management and control requirements, a better early warning effect is achieved on the potential high-risk area not involved in fraud reporting, and the risk involved in fraud after the user identification card is accessed to the network is reduced.
3) The map visualization technology is used for guiding longitude and latitude coordinate clustering, whether the preliminarily defined high-risk area related to the fraud accords with the management and control requirement can be intuitively displayed for a user, the user can conveniently adjust clustering parameters based on global map information of a map, accuracy and efficiency of parameter adjustment are improved, and therefore round areas (the preliminarily defined high-risk area related to the fraud) on the map can be adjusted, and finally the finally determined high-risk area related to the fraud is obtained.
4) The dynamic clustering analysis is carried out on the recent high-risk area related to the fraud by combining the map visualization technology, and the interception rule is generated, so that whether the user address belongs to the potential high-risk area can be prejudged in advance before the user accesses the network, the high-risk pre-judgment interception is carried out on the user identification card before the user accesses the network based on the address information, and the risk related to the fraud after the user accesses the network is reduced.
Corresponding to the above method embodiment, the embodiment of the present application further provides a user identification card issuing control device, where the user identification card issuing control device described below and the user identification card issuing control method described above may be referred to correspondingly.
Referring to fig. 5, the user identification card issuance control apparatus 800 may include the following modules:
a first obtaining module 810, configured to obtain longitude and latitude coordinates of historical fraud addresses, where the longitude and latitude coordinates of each historical fraud address belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates;
a second obtaining module 820, configured to perform clustering on longitude and latitude coordinates of the historic fraud addresses to obtain a first target cluster;
a first determining module 830, configured to determine a fraud-related high risk area corresponding to each first target cluster;
the second determining module 840 is configured to determine whether to intercept the subscriber identity card to be issued to the address to be detected according to whether the longitude and latitude coordinates of the address to be detected are in the fraud-related high risk area if the address to be detected is obtained;
the first target cluster comprises a first cluster and a second cluster, the first cluster is obtained by clustering sparse longitude and latitude coordinates by using a distance-based clustering algorithm, and the second cluster is obtained by clustering dense longitude and latitude coordinates by using a density-based clustering algorithm.
By applying the device provided by the embodiment of the application, after the longitude and latitude coordinates of the historical fraud-related addresses are obtained, the longitude and latitude coordinates of the historical fraud-related addresses are clustered to obtain the first target cluster, the first target cluster comprises a first cluster and a second cluster, the first cluster is obtained by clustering the sparse longitude and latitude coordinates by using a distance-based clustering algorithm, the second cluster is obtained by clustering the dense longitude and latitude coordinates by using a density-based clustering algorithm, the fraud-related high-risk area corresponding to each first target cluster is determined, and under the condition that the address to be detected is obtained, whether the user identification card to be issued to the address to be detected is intercepted is determined according to whether the longitude and latitude coordinates of the address to be detected are in the fraud-related high-risk area. Namely, the distance-based clustering algorithm and the density-based clustering algorithm are utilized to carry out the delineating of the high-risk area involved in the fraud, and the risk management and control are carried out before the user identification card is accessed to the network, so that the risk involved in the fraud after the user identification card is accessed to the network can be effectively reduced.
In some embodiments of the present application, the first obtaining module 810 is further configured to determine that the longitude and latitude coordinates of each historic fraud address belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates by: clustering longitude and latitude coordinates of the historic fraud addresses by using a density-based clustering algorithm to obtain a plurality of initial clusters; and determining that the longitude and latitude coordinates included in each initial cluster belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates.
In some embodiments of the present application, the first obtaining module 810 is configured to: for each initial cluster, if the number of longitude and latitude coordinates included in the current initial cluster is smaller than or equal to a first threshold, determining the longitude and latitude coordinates included in the current initial cluster as sparse longitude and latitude coordinates.
In some embodiments of the present application, the first obtaining module 810 is further configured to: if the number of the longitude and latitude coordinates included in the current initial cluster is larger than a first threshold, determining an average spherical distance between the longitude and latitude coordinates in the current initial cluster; if the average spherical distance is greater than or equal to a second threshold value, determining longitude and latitude coordinates included in the current initial cluster as sparse longitude and latitude coordinates; and if the average spherical distance is smaller than the second threshold value, determining longitude and latitude coordinates included in the current initial cluster as dense longitude and latitude coordinates.
In some embodiments of the present application, the second obtaining module 820 is further configured to obtain the first cluster and the second cluster by: clustering the sparse longitude and latitude coordinates according to a first clustering parameter by using a distance-based clustering algorithm to obtain a third cluster; clustering the dense longitude and latitude coordinates according to the second clustering parameter by using a density-based clustering algorithm to obtain a fourth cluster; determining the region range corresponding to each third cluster and each fourth cluster; if no adjustment instruction for the cluster parameters is received, the third cluster is determined as the first cluster, and the fourth cluster is determined as the second cluster.
In some embodiments of the present application, the second obtaining module 820 is further configured to: if an adjustment instruction for the clustering parameters is received, adjusting the first clustering parameters and/or the second clustering parameters; and repeatedly executing the steps of clustering the sparse longitude and latitude coordinates according to the first clustering parameter by using a distance-based clustering algorithm and clustering the dense longitude and latitude coordinates according to the second clustering parameter by using a density-based clustering algorithm.
In some embodiments of the present application, the second obtaining module 820 is further configured to: and after determining the regional scope corresponding to each third cluster and each fourth cluster, visually displaying the longitude and latitude coordinates of the historic fraud addresses and the regional scope on the map.
In some embodiments of the present application, the user identification card issuance control apparatus 800 further includes a third determination module for: after determining the area ranges corresponding to each third cluster and each fourth cluster, determining whether the current second target cluster meets the control requirement or not according to the ratio of the historical traffic of the area range corresponding to the current second target cluster to the historical traffic of the service area where the current second target cluster is located for each second target cluster; if the control requirement is not met, outputting prompt information; wherein the second target cluster includes a third cluster and a fourth cluster.
In some embodiments of the present application, the second obtaining module 820 is configured to: for each third target cluster, if the current third target cluster comprises at least two longitude and latitude coordinates, determining the center point coordinates of the current third target cluster and the maximum spherical distance from the center point coordinates to the longitude and latitude coordinates of the current third target cluster; determining a region range corresponding to the current third target cluster by taking the center point coordinate as the center and the maximum spherical distance as the radius; wherein the third target cluster includes a third cluster and a fourth cluster.
In some embodiments of the present application, the second obtaining module 820 is configured to: for each fourth target cluster, if the current fourth target cluster only comprises one longitude and latitude coordinate, determining a region range corresponding to the current fourth target cluster by taking the longitude and latitude coordinate of the current fourth target cluster as the center and setting the spherical distance as the radius; wherein the fourth target cluster includes a third cluster and a fourth cluster.
In some embodiments of the present application, the subscriber identity card issuance control apparatus 800 further includes a conversion module for: after acquiring the longitude and latitude coordinates of the historical fraud addresses, clustering the longitude and latitude coordinates of the historical fraud addresses, and converting the longitude and latitude coordinates of the historical fraud addresses before obtaining a first target cluster so as to unify coordinate systems corresponding to the longitude and latitude coordinates of different historical fraud addresses.
In some embodiments of the present application, the first obtaining module 810 is further configured to obtain the address to be detected by: obtaining registration information, wherein the registration information at least comprises a registration address; filtering the registration information to determine whether the registration address is valid; in the case where the registered address is valid, the registered address is determined as the address to be detected.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
Corresponding to the above method embodiment, the embodiment of the present application further provides an electronic device, including:
a memory for storing a computer program;
and the processor is used for realizing the steps of the user identification card issuing control method when executing the computer program.
As shown in fig. 6, which is a schematic diagram of a composition structure of an electronic device, the electronic device may include: a processor 10, a memory 11, a communication interface 12 and a communication bus 13. The processor 10, the memory 11 and the communication interface 12 all complete communication with each other through a communication bus 13.
In the present embodiment, the processor 10 may be a central processing unit (Central Processing Unit, CPU), an asic, a dsp, a field programmable gate array, or other programmable logic device, etc.
The processor 10 may call a program stored in the memory 11, and in particular, the processor 10 may perform operations in an embodiment of the user identification card issuance control method.
The memory 11 is used for storing one or more programs, and the programs may include program codes, where the program codes include computer operation instructions, and in this embodiment, at least the programs for implementing the following functions are stored in the memory 11:
acquiring longitude and latitude coordinates of historical fraud addresses, wherein the longitude and latitude coordinates of each historical fraud address belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates;
clustering longitude and latitude coordinates of the historical fraud-related addresses to obtain a first target cluster;
determining a fraud-related high-risk area corresponding to each first target cluster;
under the condition that the address to be detected is obtained, determining whether to intercept the user identification card to be issued to the address to be detected according to whether longitude and latitude coordinates of the address to be detected are in a fraud-related high-risk area; the method comprises the steps of carrying out a first treatment on the surface of the
The first target cluster comprises a first cluster and a second cluster, the first cluster is obtained by clustering sparse longitude and latitude coordinates by using a distance-based clustering algorithm, and the second cluster is obtained by clustering dense longitude and latitude coordinates by using a density-based clustering algorithm.
In one possible implementation, the memory 11 may include a storage program area and a storage data area, where the storage program area may store an operating system, and applications required for at least one function (e.g., a clustering function, a detection function), and so on; the storage data area may store data created during use, such as coordinate data, area data, and the like.
In addition, the memory 11 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device or other volatile solid-state storage device.
The communication interface 12 may be an interface of a communication module for interfacing with other devices or systems.
Of course, it should be noted that the structure shown in fig. 6 is not limited to the electronic device in the embodiment of the present application, and the electronic device may include more or fewer components than those shown in fig. 6 or may combine some components in practical applications.
Corresponding to the above method embodiments, the present application further provides a computer readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the steps of the method for controlling issuance of a subscriber identity card are implemented.
In addition, it should be noted that: embodiments of the present application also provide a computer program product or computer program that may include computer instructions that may be stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor may execute the computer instructions, so that the computer device performs the description of the method for controlling the issuance of the user identification card in the foregoing corresponding embodiment, and therefore, a detailed description will not be given here. In addition, the description of the beneficial effects of the same method is omitted. For technical details not disclosed in the computer program product or the computer program embodiments related to the present application, please refer to the description of the method embodiments of the present application.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Specific examples are used herein to illustrate the principles and embodiments of the present application, and the description of the above examples is only for aiding in understanding the technical solution of the present application and its core ideas. It should be noted that it would be obvious to those skilled in the art that various improvements and modifications can be made to the present application without departing from the principles of the present application, and such improvements and modifications fall within the scope of the claims of the present application.

Claims (15)

1. A user identification card issuance control method, comprising:
acquiring longitude and latitude coordinates of historical fraud addresses, wherein the longitude and latitude coordinates of each historical fraud address belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates;
clustering longitude and latitude coordinates of the historical fraud-related addresses to obtain a first target cluster;
Determining a fraud-related high-risk area corresponding to each first target cluster;
under the condition that an address to be detected is obtained, determining whether to intercept a user identification card to be issued to the address to be detected according to whether longitude and latitude coordinates of the address to be detected are in the fraud-related high-risk area;
the first target cluster comprises a first cluster and a second cluster, the first cluster is obtained by clustering sparse longitude and latitude coordinates by using a distance-based clustering algorithm, and the second cluster is obtained by clustering dense longitude and latitude coordinates by using a density-based clustering algorithm.
2. The method of claim 1, wherein the longitude and latitude coordinates of each historic fraud address are determined to belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates by:
clustering longitude and latitude coordinates of the historic fraud addresses by using the density-based clustering algorithm to obtain a plurality of initial clusters;
and determining that the longitude and latitude coordinates included in each initial cluster belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates.
3. The method of claim 2, wherein determining that the longitude and latitude coordinates included in each initial cluster belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates comprises:
For each initial cluster, if the number of longitude and latitude coordinates included in the current initial cluster is smaller than or equal to a first threshold, determining the longitude and latitude coordinates included in the current initial cluster as sparse longitude and latitude coordinates.
4. A method according to claim 3, characterized in that the method further comprises:
if the number of longitude and latitude coordinates included in the current initial cluster is larger than the first threshold, determining an average spherical distance between the longitude and latitude coordinates in the current initial cluster;
if the average spherical distance is greater than or equal to a second threshold value, determining longitude and latitude coordinates included in the current initial cluster as sparse longitude and latitude coordinates;
and if the average spherical distance is smaller than the second threshold value, determining longitude and latitude coordinates included in the current initial cluster as dense longitude and latitude coordinates.
5. The method of claim 1, wherein the first cluster and the second cluster are obtained by:
clustering the sparse longitude and latitude coordinates according to a first clustering parameter by using a distance-based clustering algorithm to obtain a third cluster;
clustering the dense longitude and latitude coordinates according to a second clustering parameter by using the density-based clustering algorithm to obtain a fourth cluster;
Determining the region range corresponding to each third cluster and each fourth cluster;
and if the adjustment instruction for the clustering parameters is not received, determining the third cluster as the first cluster and the fourth cluster as the second cluster.
6. The method of claim 5, wherein the method further comprises:
if an adjustment instruction for the clustering parameters is received, adjusting the first clustering parameters and/or the second clustering parameters;
and repeatedly executing the step of clustering the sparse longitude and latitude coordinates according to a first clustering parameter by using the distance-based clustering algorithm, and the step of clustering the dense longitude and latitude coordinates according to a second clustering parameter by using the density-based clustering algorithm.
7. The method of claim 5, wherein after said determining the area coverage for each third cluster and each fourth cluster, the method further comprises:
and visually displaying the longitude and latitude coordinates of the historic fraud addresses and the area range on a map.
8. The method of claim 5, wherein after said determining the area coverage for each third cluster and each fourth cluster, the method further comprises:
For each second target cluster, determining whether the current second target cluster meets the control requirement according to the ratio of the historical traffic of the area range corresponding to the current second target cluster to the historical traffic of the service area where the current second target cluster is located;
if the control requirement is not met, outputting prompt information;
wherein the second target cluster includes the third cluster and the fourth cluster.
9. The method of claim 5, wherein determining the region range corresponding to each third cluster and each fourth cluster comprises:
for each third target cluster, if the current third target cluster comprises at least two longitude and latitude coordinates, determining the center point coordinates of the current third target cluster and the maximum spherical distance from the center point coordinates to the longitude and latitude coordinates of the current third target cluster;
determining a region range corresponding to the current third target cluster by taking the center point coordinate as a center and the maximum spherical distance as a radius;
wherein the third target cluster includes the third cluster and the fourth cluster.
10. The method of claim 5, wherein determining the region range corresponding to each third cluster and each fourth cluster comprises:
for each fourth target cluster, if the current fourth target cluster only comprises a longitude and latitude coordinate, determining a region range corresponding to the current fourth target cluster by taking the longitude and latitude coordinate of the current fourth target cluster as a center and setting a spherical distance as a radius;
wherein the fourth target cluster includes the third cluster and the fourth cluster.
11. The method of claim 1, wherein after the obtaining the latitude and longitude coordinates of the historical fraud address and before the clustering the latitude and longitude coordinates of the historical fraud address, the method further comprises:
and converting the longitude and latitude coordinates of the historical fraud addresses to unify coordinate systems corresponding to the longitude and latitude coordinates of different historical fraud addresses.
12. The method according to any one of claims 1 to 11, wherein the address to be detected is obtained by:
obtaining registration information, wherein the registration information at least comprises a registration address;
Filtering the registration information to determine whether the registration address is valid;
and determining the registration address as the address to be detected in the case that the registration address is valid.
13. A user identification card issuance control apparatus, comprising:
the first obtaining module is used for obtaining longitude and latitude coordinates of the historical fraud addresses, and the longitude and latitude coordinates of each historical fraud address belong to sparse longitude and latitude coordinates or dense longitude and latitude coordinates;
the second obtaining module is used for carrying out clustering processing on longitude and latitude coordinates of the historic fraud addresses to obtain a first target cluster;
the first determining module is used for determining a fraud-related high-risk area corresponding to each first target cluster;
the second determining module is used for determining whether to intercept the user identification card to be issued to the address to be detected according to whether the longitude and latitude coordinates of the address to be detected are in the fraud-related high-risk area or not under the condition that the address to be detected is obtained;
the first target cluster comprises a first cluster and a second cluster, the first cluster is obtained by clustering sparse longitude and latitude coordinates by using a distance-based clustering algorithm, and the second cluster is obtained by clustering dense longitude and latitude coordinates by using a density-based clustering algorithm.
14. An electronic device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the user identification card issuance control method according to any one of claims 1 to 12 when executing the computer program.
15. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, which when executed by a processor, implements the steps of the user identification card issuance control method according to any one of claims 1 to 12.
CN202311125281.9A 2023-09-01 2023-09-01 User identification card issuing control method and device, electronic equipment and storage medium Pending CN117336723A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311125281.9A CN117336723A (en) 2023-09-01 2023-09-01 User identification card issuing control method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311125281.9A CN117336723A (en) 2023-09-01 2023-09-01 User identification card issuing control method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117336723A true CN117336723A (en) 2024-01-02

Family

ID=89276211

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311125281.9A Pending CN117336723A (en) 2023-09-01 2023-09-01 User identification card issuing control method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117336723A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117573952A (en) * 2024-01-16 2024-02-20 北京睿企信息科技有限公司 Map-based information display method, electronic equipment and storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117573952A (en) * 2024-01-16 2024-02-20 北京睿企信息科技有限公司 Map-based information display method, electronic equipment and storage medium
CN117573952B (en) * 2024-01-16 2024-03-29 北京睿企信息科技有限公司 Map-based information display method, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
CN108269087B (en) Method and device for processing position information
CN111290916B (en) Big data monitoring method, device and equipment and computer readable storage medium
US10496993B1 (en) DNS-based device geolocation
CN104954322A (en) Account binding method, device and system
CN106162714A (en) A kind of calling information processing method and processing device
CN117336723A (en) User identification card issuing control method and device, electronic equipment and storage medium
CN109769218A (en) A kind of Notice Of Transactions method, apparatus, terminal device and medium
CN107948274B (en) Transaction authentication method and system, server, and storage medium
CN109377389A (en) A kind of payment based reminding method, server and computer readable storage medium
CN103959092A (en) Method and system to confirm co-location of multiple devices within a geographic area
CN108830710A (en) Block chain transaction platform and implementation method
CN111245642A (en) Method and device for acquiring dependency relationship between multiple systems and electronic equipment
CN111787075A (en) Equipment positioning method and device
CN112039861A (en) Risk identification method and device, electronic equipment and computer readable storage medium
CN110992048A (en) Transaction fraud determination method and device
US10708713B2 (en) Systems and methods for beacon location verification
CN113961780A (en) Resident cell acquisition method and device, electronic equipment and storage medium
CN116703071A (en) Resource sharing method, device and equipment and storage medium
CN110766441A (en) Resource object processing method and device, storage medium and computer equipment
CN111443962A (en) Transaction limiting method and device
CN209785065U (en) Agent divides moist management device
CN114971412A (en) Order distribution method, order distribution platform, order distribution system and storage medium
CN112085590A (en) Method and device for determining safety of rule model and server
CN112215667A (en) User behavior prediction method and device
CN112035760A (en) Task allocation method and computer equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination