CN114529747A - Policy detection method, policy detection device, electronic apparatus, and storage medium - Google Patents
Policy detection method, policy detection device, electronic apparatus, and storage medium Download PDFInfo
- Publication number
- CN114529747A CN114529747A CN202210234391.8A CN202210234391A CN114529747A CN 114529747 A CN114529747 A CN 114529747A CN 202210234391 A CN202210234391 A CN 202210234391A CN 114529747 A CN114529747 A CN 114529747A
- Authority
- CN
- China
- Prior art keywords
- information
- score
- policy
- network
- case
- 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
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 69
- 238000012545 processing Methods 0.000 claims abstract description 40
- 238000000605 extraction Methods 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims description 43
- 230000015654 memory Effects 0.000 claims description 19
- 238000007621 cluster analysis Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 13
- 238000005516 engineering process Methods 0.000 description 18
- 238000004891 communication Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment relates to the technical field of artificial intelligence, in particular to a policy detection method, a policy detection device, electronic equipment and a storage medium. The policy detection method comprises the following steps: acquiring a policy to be tested; performing information extraction processing on the policy to be tested to obtain case-involved information; matching service connection information in a preset time period according to the case-related information; the service connection information comprises LBS information and network connection information; establishing a social network based on LBS information, network connection information and case-involved information; performing clustering analysis processing on network nodes of the social network according to a preset clustering analysis model to obtain a plurality of social clustering clusters; the social clustering cluster is used for representing the relationship between the network nodes; and determining the detection category of the policy to be detected according to the plurality of social clustering clusters and the preset decision condition. According to the technical scheme, the policy deposit fraud can be accurately and effectively detected, and the policy deposit detection efficiency is improved.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a policy detection method, a policy detection apparatus, an electronic device, and a storage medium.
Background
Insurance companies often need to process various policies to determine whether claims need to be made to an insured life.
In the related art, insurance companies often check various information on insurance policies manually to determine whether or not a claim for an insured life is required. However, checking the policy manually has a problem of low checking efficiency.
Disclosure of Invention
The present disclosure provides a policy making method, a policy making apparatus, an electronic device, and a storage medium, which are capable of detecting a type of a policy and improving a policy making efficiency.
In order to achieve the above object, a first aspect of an embodiment of the present application provides a policy detection method, including:
acquiring a policy to be tested;
carrying out information extraction processing on the insurance policy to be tested to obtain case-involved information;
matching service connection information in a preset time period according to the case-related information; wherein the service connection information includes LBS information and network connection information;
building a social network based on the LBS information, the network connection information and the case-involved information;
performing clustering analysis processing on network nodes of the social network according to a preset clustering analysis model to obtain a plurality of social clustering clusters; the social clustering cluster is used for representing the relation between the network nodes;
and determining the detection category of the policy to be detected according to the plurality of social clustering clusters and preset decision conditions.
In some embodiments, the case-involved information comprises a plurality of case-involved person information and case-involved associated information;
the building of a social network based on the LBS information, the network connection information and the case-involved information comprises the following steps:
performing relation extraction on the LBS information based on the case-involved person information to obtain a plurality of LBS distance relation sets;
extracting the relationship of the network connection information based on the case-involved person information to obtain a plurality of network relationship sets;
performing relation extraction on the case-involved associated information based on the case-involved person information to obtain a plurality of case-involved associated relation sets;
inputting each LBS distance relation set, the corresponding network relation set and the corresponding involved case association relation set into a preset score calculation model for score calculation to obtain a corresponding target score;
and building the social network according to the information of each involved person and the corresponding target score.
In some embodiments, the inputting each LBS distance relationship set, the corresponding network relationship set, and the corresponding involved association set into a preset score calculation model for score calculation to obtain a corresponding target score includes:
carrying out classification matching processing on the LBS distance relation set to obtain an LBS distance score;
carrying out classification matching processing on the network relation set to obtain a network connection score;
carrying out classification matching processing on the case-involved association set to obtain case-involved association scores;
and obtaining the target score according to the LBS distance score, the network connection score and the case-involved association score.
In some embodiments, the performing classification matching processing on the network relationship set to obtain a network connection score includes:
acquiring the product purchase time score of the insurance policy to be tested; the product purchase time score is used for representing the product purchase time corresponding to the policy to be tested;
acquiring the time type score of the case-involved information; the time type scores are used for representing the time of common occurrence among the information of the involved persons;
classifying the network relation set to obtain a network connection type;
determining a corresponding network type score according to the network connection type and a preset mapping rule;
and obtaining the network connection score according to the product purchase time score, the time type score and the network type score.
In some embodiments, said deriving said network connection score from said product purchase time score, said time type score, and a network type score comprises:
calculating the product purchase time score, the time type score and the network type score to obtain a target connection score;
and carrying out normalization processing on the target connection score to obtain the network connection score.
In some embodiments, said deriving the target score according to the LBS distance score, the network connection score, and the involved association score comprises:
acquiring preset product association coefficients, network connection coefficients and LBS distance coefficients;
weighting the product association score according to the product association coefficient to obtain a product association weighted value;
weighting the network connection scores according to the network connection coefficients to obtain network connection weighted values;
carrying out weighting processing on the LBS distance score according to the LBS distance coefficient to obtain an LBS distance weighted value;
and summing the product association weighted value, the network connection weighted value and the LBS distance weighted value to obtain the target score.
In some embodiments, the detection categories include fraud warranties and normal warranties;
the determining the detection category of the policy to be tested according to the plurality of social clustering clusters and the preset decision condition comprises the following steps:
when a plurality of the social clustering clusters are a main clustering cluster, the policy to be tested is the fraud policy;
and when the plurality of social clustering clusters comprise a plurality of normal clustering clusters, the policy to be tested is the normal policy.
In order to achieve the above object, a second aspect of an embodiment of the present application provides a policy detection apparatus, including:
the acquisition module is used for acquiring the policy to be tested;
the extraction module is used for extracting information of the policy to be tested to obtain case-related information;
the matching module is used for matching the service connection information in a preset time period according to the case-related information; wherein the service connection information includes LBS information and network connection information;
the building module is used for building a social network based on the LBS information, the network connection information and the case-related information;
the cluster analysis module is used for carrying out cluster analysis processing on the network nodes of the social network according to a preset cluster analysis model to obtain a plurality of social cluster clusters; the social clustering cluster is used for representing the relation between the network nodes;
and the decision module is used for determining the detection category of the policy to be detected according to the plurality of social clustering clusters and preset decision conditions.
To achieve the above object, a third aspect of an embodiment of the present application provides an electronic apparatus, including:
at least one memory;
at least one processor;
at least one program;
the programs are stored in the memory, and the processor executes the at least one program to implement:
the method of any one of the embodiments of the first aspect.
To achieve the above object, a fourth aspect of the embodiments of the present application provides a storage medium, which is a computer-readable storage medium storing computer-executable instructions for causing a computer to execute:
the method of any one of the embodiments of the first aspect.
According to the policy-related information extraction method, the policy-related information matching LBS information and network connection information in the preset time period according to the policy-related information, the social network is built according to the LBS information, the network connection information and the policy-related information, the network nodes in the social network are subjected to cluster analysis to obtain the social cluster clusters for representing the relation between the network nodes, and the detection category of the policy to be detected is determined according to the social cluster clusters and the preset decision conditions.
Drawings
FIG. 1 is a flow chart of a policy detection method provided by an embodiment of the present application;
FIG. 2 is a flowchart of a specific method of step S104 in FIG. 1;
FIG. 3 is a flowchart of a specific method of step S204 in FIG. 2;
FIG. 4 is a flowchart of a specific method of step S302 in FIG. 3;
FIG. 5 is a flowchart of a specific method of step S304 in FIG. 3;
FIG. 6 is a flowchart of a specific method of step S106 in FIG. 1;
FIG. 7 is a block diagram of a policy detection device provided in an embodiment of the present application;
fig. 8 is a schematic hardware structure diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It should be noted that although functional blocks are partitioned in a schematic diagram of an apparatus and a logical order is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the partitioning of blocks in the apparatus or the order in the flowchart. The terms first, second and the like in the description and in the claims, and the drawings described above, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the disclosure.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
First, several terms referred to in the present application are resolved:
artificial Intelligence (AI): is a new technical science for researching and developing theories, methods, technologies and application systems for simulating, extending and expanding human intelligence; artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produces a new intelligent machine that can react in a manner similar to human intelligence, and research in this field includes robotics, language recognition, image recognition, natural language processing, and expert systems, among others. The artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is also a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results.
Medical cloud: the medical cloud is a medical health service cloud platform established by using cloud computing on the basis of new technologies such as cloud computing, mobile technology, multimedia, 4G communication, big data, Internet of things and the like and combining medical technology, so that sharing of medical resources and expansion of medical scope are realized. Due to the combination of the cloud computing technology, the medical cloud improves the efficiency of medical institutions and brings convenience to residents to see medical advice. Like the appointment register, the electronic medical record, the medical insurance and the like of the existing hospital are all products combining cloud computing and the medical field, and the medical cloud also has the advantages of data security, information sharing, dynamic expansion and overall layout.
DBSCAN (sensitivity-Based Spatial Clustering of Applications with Noise, Density-Based Noise application Spatial Clustering): DBSCAN is a relatively representative density-based clustering algorithm. Unlike the partitioning and hierarchical clustering method, which defines clusters as the largest set of density-connected points, it is possible to partition areas with sufficiently high density into clusters and find clusters of arbitrary shape in a spatial database of noise.
LBS (Location Based Services ): the LBS is to use various types of positioning technology to obtain the current location of the positioning equipment, and provide information resources and basic services to the positioning equipment through the mobile internet. First, the user can determine the spatial position of the user by using a positioning technology, and then the user can acquire resources and information related to the position through the mobile internet. The LBS service integrates various information technologies such as mobile communication, internet, space positioning, position information, big data and the like, and a mobile internet service platform is utilized to update and interact data, so that a user can obtain corresponding services through space positioning.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The policy maintenance detection method provided by the embodiment of the application can be applied to artificial intelligence. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
Insurance companies are experiencing significant losses each year due to moral problems such as policy fraud. Policy fraud not only infringes the benefits of insureds and insurers, hampers the healthy development of the insurance market, but also disturbs social public order. Therefore, some technical means must be used to strengthen the anti-fraud strength of the policy.
In the related art, the identification method for insurance claims depends on manual verification, but the efficiency of manual verification is low, and in general, only a large number of people injured cases are strictly inspected so as to achieve the purpose of risk management and control. A large number of small-amount injury cases are directly settled due to limited human resources and the fact that strict examination links can not be entered. Lawless persons seize the loophole, and a series of welfare and loss-assessment personal injury cases are manufactured for the purpose of preventing the highest claim amount from being cheated in the examination, so that the loss of insurance companies is huge.
Based on this, the embodiment of the application provides a policy detection method, a policy detection device, an electronic device and a storage medium, which can analyze the relationship of people in the policy through a social network for building policy case-related people information, thereby accurately and effectively realizing the detection of policy fraud, improving the policy detection efficiency and reducing the loss of insurance companies.
The following embodiments are specifically provided to describe a policy detection method, a policy detection apparatus, an electronic device, and a storage medium, and first describe the policy detection method in the embodiments of the present disclosure.
The embodiment of the application provides a policy detection method, and relates to the technical field of artificial intelligence. The policy maintenance detection method provided by the embodiment of the application can be applied to a terminal, a server side and software running in the terminal or the server side. In some embodiments, the terminal may be a smartphone, tablet, laptop, desktop computer, smart watch, or the like; the server side can be configured as an independent physical server, or a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, cloud functions, cloud storage, Network service, cloud communication, middleware service, domain name service, security service, Content Delivery Network (CDN) and a big data and artificial intelligence platform; the software may be an application or the like that implements a policy detection method, but is not limited to the above form.
The disclosed embodiments are operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
Referring to fig. 1, in a first aspect, some embodiments of the present application provide a policy detection method, including step S101, step S102, step S103, step S104, step S105, and step S106, it should be understood that the policy detection method of the embodiments of the present application, including but not limited to step S101 to step S106, is explained in detail below with reference to fig. 1.
Step S101: acquiring a policy to be tested;
specifically, in step S101 of some embodiments, the policy under test may be a policy of medical insurance, and may be a policy of other types of insurance, such as vehicle insurance. If the policy is the policy of medical insurance, the policy to be tested can be acquired through the medical cloud server or other channels. Similarly, other types of policy can be obtained through the corresponding cloud server, and the staff of the insurance company inputs the policy to be tested into the cloud server, so that the computer can obtain the policy to be tested, and fraud detection of the policy to be tested is realized.
Step S102: carrying out information extraction processing on the policy to be tested to obtain case-related information;
in step S102 of some embodiments, information of the policy to be tested is extracted, and information included in the policy to be tested is extracted to obtain case-related information, which includes but is not limited to case-related person information and case-related associated information. The information of the person involved in the case includes but is not limited to the identity information of the person involved in the case, and the associated information of the case includes but is not limited to the product type information, the replacement information and the like.
For example, taking the policy to be tested as the policy for vehicle insurance, the information of the involved person includes but is not limited to at least two of the following: wounded information, owner information, claimant information, repair shop employee information, and the like. The case-related associated information is used for representing the relation generated between the case-related person information, and includes but is not limited to: the insurance applicant, the passing car, the car changing owner, the insurance applicant reporting person, the insurance applicant and the reporting person, etc.
Step S103: matching service connection information in a preset time period according to the case-related information; wherein, the service connection information comprises LBS information and network connection information;
in step S103 of some embodiments, service connection information of the involved person information within a preset time period is acquired, and the service connection information includes LBS information and network connection information. For example, all LBS information and network connection information of all involved persons within three months before the case is acquired.
Step S104: building a social network based on the LBS information, the network connection information and the case-related information;
step S105: performing clustering analysis processing on network nodes of the social network according to a preset clustering analysis model to obtain a plurality of social clustering clusters; the social clustering cluster is used for representing the relationship between the network nodes;
in step S105 of some embodiments, the network nodes of the social network are the case-involved persons, and the clustering analysis model adopts a DBSCAN clustering algorithm, which is a density-based clustering algorithm. By using a DBSCAN clustering algorithm to perform clustering analysis on network nodes of the social network, social clustering clusters for representing relations among involved persons can be obtained.
Step S106: and determining the detection category of the policy to be detected according to the plurality of social clustering clusters and the preset decision conditions.
According to the policy detection method, the case-involved information is extracted from the policy to be detected, the LBS information and the network connection information in the preset time period are matched according to the case-involved information, the social network is built according to the LBS information, the network connection information and the case-involved information, the network nodes in the social network are subjected to cluster analysis, the social cluster used for representing the relation among the network nodes is obtained, the detection category of the policy to be detected is determined according to the social cluster and the preset decision condition, through the arrangement, policy fraud detection can be accurately and effectively achieved, the policy detection efficiency is improved, and the loss of insurance companies is reduced.
In some embodiments, the case-involved information includes a plurality of case-involved person information and case-involved association information. Step S104 includes step S201, step S202, step S203, step S204 and step S205, it being understood that step S104 includes, but is not limited to, step S201 to step S205, which are described in detail below with reference to fig. 2.
Step S201: extracting LBS information based on case-involved person information to obtain a plurality of LBS distance relation sets;
specifically, in step S201 of some embodiments, a plurality of LBS distance relationship sets are obtained by extracting LBS information based on the information of the involved person.
For example, taking the policy to be tested as the vehicle insurance as an example for explanation, the information of the involved person includes: the information of the wounded, the information of the owner of the vehicle, the information of the claim settlement personnel and the information of the staff of the repair shop are obtained through the steps, and the service connection information of each involved person within 3 months before the case is sent is obtained to obtain the LBS information and the network connection information. Then, extracting LBS information between every two involved persons to obtain a plurality of LBS distance relationship sets, wherein the LBS distance relationship sets comprise LBS distance types and corresponding times of the LBS distance types, and the LBS distance types are classified according to the LBS distances between the involved persons, and can be divided into: within 10 meters, within 10 meters to 20 meters, within 20 to 50 meters, within 50 to 100 meters, and the like. For example, LBS information corresponding to the wounded information and the owner information is extracted to obtain an LBS distance relationship set, and the LBS distance relationship set displays: the LBS distance between the two is within 10 meters for 5 times and within 10 to 20 meters for 1 time.
It should be noted that the LBS distance types described above are merely exemplary, and may be classified according to other criteria, and the embodiments of the present application are not particularly limited.
Step S202: extracting network connection information based on case-involved person information to obtain a plurality of network relation sets;
in step S202 of some embodiments, in this embodiment, the network connection relationship is mainly a wifi connection relationship, and the wifi connection relationship type includes: common connection, one connection one scanning and common scanning. Similar to the step S201, the network connection relationship is extracted based on the information of the involved persons to obtain a plurality of network relationship sets, and the network relationship sets include: the network connection type and the number of times corresponding to the network connection type. Similarly, in this embodiment, taking the car owner information and the claim holder information as an example, the network connection information corresponding to the car owner information and the claim holder information is extracted to obtain the corresponding network relationship set. If so, the set of network relationships displays: the two are connected to the same wifi together for 1 time, and scan the same wifi together for 5 times, etc.
Step S203: extracting case-involved associated information based on the case-involved person information to obtain a plurality of case-involved associated relationship sets;
similar to the above steps, in step S203, the case-related information is extracted based on the case-related person information to obtain a plurality of case-related relationship sets. And if the case-related associated information corresponding to the owner information and the claimant information is extracted, a case-related associated relation set is obtained. If so, the set of case-related associations shows: the vehicle owner information and the claimant information generate 2 times of vehicle changing owners, 1 time of insured persons and declaring persons in the preset time period.
Step S204: inputting each LBS distance relation set, the corresponding network relation set and the corresponding involved case association relation set into a preset score calculation model for score calculation to obtain a corresponding target score;
step S205: and establishing a social network according to the information of each involved person and the corresponding target score.
Specifically, in step S205 of some embodiments, the information of the involved persons is taken as a network node, and the target score obtained in the foregoing steps is taken as an edge, so as to build a social network. The social network can represent the strength of the connection relation among the involved persons.
Referring to fig. 3, in some embodiments, step S204 includes, but is not limited to, step S301, step S302, step S303, step S304. These four steps are described in detail below.
Step S301: carrying out classification matching processing on the LBS distance relation set to obtain LBS distance scores;
step S302: carrying out classification matching processing on the network relation set to obtain a network connection score;
step S303: carrying out classification matching processing on the case-involved association set to obtain case-involved association scores;
step S304: and obtaining a target score according to the LBS distance score, the network connection score and the involved case correlation score.
Specifically, in this embodiment, the network connection relationship is a wifi connection relationship, please refer to table 1, where table 1 is a weight score table corresponding to different types of relationships.
TABLE 1
According to table 1, the LBS distance relationship set is subjected to a classification matching process to obtain an LBS distance score, for example, the LBS distance relationship set includes: 0-10 m for 1 time, 10-20 m for 2 times, and 50-100 m for 4 times, the corresponding LBS distance score is: 10 × 1+2 × 8+4 × 4 ═ 42. Similarly, according to table 1, the network relationship set is subjected to classification matching processing to obtain a network connection score, and the case-involved relationship set is subjected to classification matching processing to obtain a case-involved association score. And then determining a target score according to the obtained LBS distance score, the network connection score and the case-involved association score.
Referring to fig. 4, in some embodiments of the present application, step S302 includes, but is not limited to, step 401, step S402, step S403, step S404, and step S405. These five steps are described in detail below in conjunction with fig. 4.
Step S401: acquiring a product purchase time score of a policy to be tested; the product purchase time score is used for representing the product purchase time corresponding to the policy to be tested;
in step S401 of some embodiments, the product purchase time of the policy under test is obtained, and the product purchase time score is determined according to the product purchase time matching. For example, taking the policy to be tested as the policy for vehicle insurance as an example, if the product purchase time of the policy to be tested is in the same year as the case time, the corresponding product purchase time score is 1; if the product purchase time of the policy to be tested is one year earlier than the case time, the corresponding product purchase time is 0.8; if the product purchase time of the policy to be tested is two years earlier than the case time, the corresponding product purchase time is 0.6; if the purchase time of the product of the policy to be tested is three years or more earlier than the case time, the corresponding purchase time of the product is 0.4.
Step S402: acquiring time type scores of case-related information; the time type score is used for representing the time of co-occurrence of the information of the involved persons;
in step S402 of some embodiments, the co-occurrence time of the case-related information is obtained, and then the corresponding time type score is determined. For example, if the owner and the claimant co-occur during work hours, the corresponding time type score is 0.5; if the vehicle owner and the claimant appear together in the non-working time, the probability that the vehicle owner and the claimant are connected to form a cheating group is higher, and the corresponding time type score can be 1.
Step S403: classifying the network relation set to obtain a network connection type;
step S404: determining a corresponding network type score according to the network connection type and a preset mapping rule;
in steps S403 to S404 of some embodiments, the network relationship set is classified according to the foregoing table 1 to obtain a network connection type and a corresponding number of times of the network connection type, and then a corresponding network type score is determined according to a mapping rule. For example, if the set of network relationships includes 2 common connections and 1 common scan, the corresponding network type score is: 2 x 10+1 x 1 ═ 21.
Step S405: and obtaining a network connection score according to the product purchase time score, the time type score and the network type score.
Specifically, step S405 includes the steps of:
calculating the product purchase time score, the time type score and the network type score to obtain a target connection score;
and carrying out normalization processing on the target connection score to obtain a network connection score.
Specifically, in this embodiment, normalization processing needs to be performed on the calculated target connection score, for example, normalization is performed to within [1, 10], and similarly, the calculation processes of the case-related association score and the LBS distance score are similar to those of the network connection score in this embodiment, and both normalization processing needs to be performed. By the arrangement, the case-involved association score, the LBS distance score and the network connection score can be balanced, so that the constructed social network can represent the relation among the case-involved persons more closely, and the accuracy of policy detection is improved.
Referring to fig. 5, in some embodiments of the present application, step S304 includes, but is not limited to, step S501, step S502, step S503, step S504, and step S505.
Step S501: acquiring preset product association coefficients, network connection coefficients and LBS distance coefficients;
step S502: weighting the product association score according to the product association coefficient to obtain a product association weighted value;
step S503: weighting the network connection scores according to the network connection coefficients to obtain network connection weighted values;
step S504: carrying out weighting processing on the LBS distance score according to the LBS distance coefficient to obtain an LBS distance weighted value;
step S505: and summing the product association weighted value, the network connection weighted value and the LBS distance weighted value to obtain a target score.
Specifically, in this embodiment, the target score is calculated by using formula (1), where formula (1) is specifically:
in the formula (1), RijRepresenting a mobileiAnd mobilejThe strength of the relationship(s), i.e. the target score, mobileiAnd mobilejAll belong to the information of the involved persons. For example, to calculate a target score between owner information and claimant information, a mobile may be usediIndicating owner information, mobilejRepresenting the claimant information. Alpha is alphaCRepresenting the product correlation coefficient, αLDenotes LBS distance coefficient, αWThe network connection coefficient is represented by a coefficient,
representing a mobileiAnd mobilejThe product association score of (a) is,
representing a mobileiAnd mobilejThe LBS distance score of (a) is,
representing a mobileiAnd mobilejThe network connection score of (1). Wherein the content of the first and second substances,
the method is obtained by the formula (2) and the formula (3), wherein the formula (2) and the formula (3) are as follows:
in the formula (2) and the formula (3), CRijIs a total of mobileiAnd mobilejScore, CW, derived for all product association typeskAnd (3) representing the case-involved incidence relation type weight fraction, namely the assumed value corresponding to the type value of the case-involved incidence relation in the table 1. WyPurchasing time points for products, CikRepresenting a mobileiNumber of times of generating association relation of k-class case with other mobile, CjkRepresenting a mobilejThe number of times other mobile generates a class k case-related association. For example, the information on the involved persons includes: when calculating the target scores of the owner information and the wounded information, assuming that the case-related correlation between the owner information and the wounded information is "throwing insurer" in table 1, then CikAnd the relation frequency of 'insurant' generated by the persons involved in the case in the owner information and the other persons involved in the case information is represented. CjkAnd CikThe same is not illustrated here.
And in the formula (3), the scores obtained by calculation in the formula (2) are normalized, and the scores obtained by calculation in the formula (2) are normalized to [1, 10] to obtain the product association scores. The purpose of normalization processing is to balance the case-involved association score, the LBS distance score and the network connection score, so that the constructed social network can represent the relation among the case-involved persons more closely, thereby improving the accuracy of policy detection, and in the normalization processing, a maximum value and a minimum value need to be removed to eliminate the influence of an extreme value.
Similarly, LRijThe method is calculated by formula (4) and formula (5), wherein formula (4) and formula (5) are specifically as follows:
in the formulae (4) and (5), LRijIs a total of mobileiAnd mobilejAll LBS distance types, scores obtained on all dates. LWkThe weight score representing the LBS distance type, i.e. the assumed value, W, corresponding to the type value of the LBS distance in table 1yPurchasing a time score, W, for a producttIs a time type score, WpScore for POI type, LijkRepresenting a mobileiAnd mobilejLBS points that generate LBS relationships have the logarithm of the set of class k LBS relationships, LikRepresents a mobileiNumber of times other mobile generates a class k LBS relationship, LjkAnd LikFor the same reason, for representing mobilejNumber of times other mobile generates a class k LBS relationship.
It should be noted that the POI is called point of interests for all, which means the point of interest, and the term point of interest comes from the navigation map manufacturer at the earliest. In order to provide as much location information as possible, map manufacturers spend a great deal of effort searching for destinations such as gas stations, restaurants, hotels, attractions, etc., which can be understood as a single POI type. In the present embodiment, the POI type weight means that different weight values are set according to different POI types. By means of the arrangement, the constructed social network can more closely represent the degree of affinity of the concerned persons.
The formula (5) is to normalize the score calculated by the formula (4), normalize the score calculated by the formula (4) to [1, 10] to obtain LBS distance score, and balance the association score of involved cases, LBS distance score and network connection score, so that the constructed social network can represent the connection between involved cases more closely, thereby improving the accuracy of policy detection.
And similarly.
Calculated by formula (6) and formula (7), formula (6) and formula (7) are as follows:
in formula (6)And in the formula (7) and,
summing mobileiAnd mobilejAll network connection types and scores obtained on all dates, and in this embodiment, the network connection type is mainly a wifi connection type. WW (world Wide Web)kThe weight score representing the network connection type, i.e. the assumed value, W, corresponding to the type value of the wifi connection in table 1yPurchasing a time score, W, for a producttIs a time type score, WpAs POI type score, WijkRepresenting a mobileiAnd mobilejWifi for generating connection relation, logarithm of k-type wifi connection relation set, WikRepresenting a mobilejNumber of times other mobile generates wifi connection relation of k type, WjkAnd WikFor the same reason, for representing mobilejThe number of times other mobile generated a wifi connection of class k.
It should be noted that the POI type score in this embodiment is consistent with the POI type in the formula (4), and is not described herein again.
The formula (7) is to normalize the score calculated by the formula (6), normalize the score calculated by the formula (6) to [1, 10] to obtain LBS distance score, and balance the association score of involved cases, LBS distance score and network connection score, so that the constructed social network can represent the connection between involved cases more closely, thereby improving the accuracy of policy detection.
Target scores among the case-related person information can be calculated through the formulas (1) to (7), after the target scores are obtained, a social network is built by taking the case-related person information as nodes and the corresponding target scores as sides, so that a DBSCAN clustering algorithm can perform clustering analysis conveniently, and the detection category of the policy to be detected is obtained.
It should be noted that, in the present embodiment, the product correlation coefficient α isCLBS distance coefficient alphaLNetwork connection coefficient alphaWIs preset, three ofThe sum is 1.
For example, the product correlation coefficient αCLBS distance coefficient alphaLNetwork connection coefficient alphaWThe settings of table 2 may be taken, table 2 being specifically as follows:
TABLE 2
For example, the corresponding assumed values of network connection relation, LBS distance, case-related association relation, etc. may be taken
Table 3, table 3 specifically is:
TABLE 3
It should be noted that the data in table 2 and table 3 are only for exemplary illustration and are not to be understood as specific limitations of the present application, and specific values may be adaptively modified according to actual situations, and the present application is not limited specifically.
Referring to FIG. 6, in some embodiments, the detection categories include fraud warranties and normal warranties, and step S106 includes, but is not limited to, step S601 and step S602.
Step S601: when the plurality of social clustering clusters are one main clustering cluster, the policy to be tested is a fraud policy;
step S602: and when the plurality of social clustering clusters comprise a plurality of normal clustering clusters, the policy to be tested is a normal policy.
Specifically, in this embodiment, the specific clustering process for the network nodes of the social network is as follows:
step 1: the whole social network is scanned, and then a network node in the social network is taken as a core point to be expanded. An extended method is to find all density connected data points starting from the core point. All core points in the neighborhood of the core point are traversed (because the boundary points are not expandable) and points connected to the density of these data points are found until there are no expandable data points. And finally, the boundary nodes of the clustered clusters are all non-core data points, so that a social clustering cluster is obtained.
Step 2: rescanning the social network (excluding any data points in previously found clusters), finding core points that are not clustered, and repeating step 1 to expand the newly found core points. Until there are no new core points in the social network.
Through the step 1 and the step 2, clustering analysis is carried out on the network nodes of the social network, and a plurality of social clustering clusters can be obtained. If a plurality of social clustering clusters are a main clustering cluster, the contact degree between network nodes (case-related person information) is over high, at the moment, the possibility of forming a fraud group between case-related persons is high, the possibility of the policy to be tested being a fraud policy is very high, and the policy to be tested can be judged as the fraud policy. If the plurality of social clustering clusters are a plurality of normal clustering clusters, namely each network node is a clustering cluster or most of the network nodes are characterized as one clustering cluster, at the moment, the degree of contact among the network nodes (case-related person information) is not high, the probability that the policy to be tested is a normal policy is high, and the policy to be tested can be judged to be the normal policy.
Referring to fig. 7, in a second aspect, some embodiments of the present application further provide a policy detection apparatus, which includes an obtaining module 701, an extracting module 702, a matching module 703, a building module 704, a cluster analysis module 705, and a decision module 706.
An obtaining module 701, configured to obtain a policy to be tested.
And the extraction module 702 is configured to perform information extraction processing on the policy to be tested to obtain case-related information.
A matching module 703, configured to match service connection information in a preset time period according to the case-related information; wherein the service connection information includes LBS information and network connection information.
And the building module 704 is used for building a social network based on the LBS information, the network connection information and the case-related information.
The cluster analysis module 705 is configured to perform cluster analysis processing on network nodes of the social network according to a preset cluster analysis model to obtain a plurality of social cluster clusters; social clustering clusters are used to characterize relationships between network nodes.
And the decision module 706 is configured to determine the detection category of the policy to be tested according to the plurality of social clustering clusters and a preset decision condition.
The policy detection device extracts case-related information from a policy to be detected, matches LBS information and network connection information in a preset time period according to the case-related information, builds a social network according to the LBS information, the network connection information and the case-related information, performs cluster analysis on network nodes in the social network to obtain a social cluster for representing the relation between the network nodes, and determines the detection category of the policy to be detected according to the social cluster and preset decision conditions.
It should be noted that the policy maintenance detection apparatus in the embodiment of the present application corresponds to the policy maintenance detection method, and the specific detection method may refer to the policy maintenance detection method, which is not described herein again.
An embodiment of the present application further provides an electronic device, including:
at least one memory;
at least one processor;
at least one program;
a program is stored in the memory and the processor executes at least one program to implement the present disclosure to implement the policy detection method described above. The electronic device may be any intelligent terminal including a mobile phone, a tablet computer, a Personal Digital Assistant (PDA), a vehicle-mounted computer, and the like.
The electronic equipment is used for executing the policy detection method, the case-related information is extracted from the policy to be detected, the LBS information and the network connection information in the preset time period are matched according to the case-related information, then the social network is built according to the LBS information, the network connection information and the case-related information, the network nodes in the social network are subjected to cluster analysis, the social cluster for representing the relation among the network nodes is obtained, the detection category of the policy to be detected is determined according to the social cluster and the preset decision condition, through the arrangement, the policy fraud detection can be accurately and effectively realized, the policy detection efficiency is improved, and the loss of insurance companies is reduced.
The electronic device according to the embodiment of the present application is described in detail below with reference to fig. 8.
Referring to fig. 8, fig. 8 illustrates a hardware structure of an electronic device according to another embodiment, where the electronic device includes:
the processor 801 may be implemented by a general Central Processing Unit (CPU), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solution provided by the embodiments of the present disclosure;
the Memory 802 may be implemented in a Read Only Memory (ROM), a static storage device, a dynamic storage device, or a Random Access Memory (RAM). The memory 802 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present disclosure is implemented by software or firmware, the relevant program codes are stored in the memory 802, and the processor 801 calls the policy-based policy-detecting method according to the embodiments of the present disclosure;
an input/output interface 803 for realizing input and output of information;
the communication interface 804 is used for realizing communication interaction between the device and other devices, and can realize communication in a wired manner (such as USB, network cable, and the like) or in a wireless manner (such as mobile network, WIFI, bluetooth, and the like);
a bus 805 that transfers information between the various components of the device (e.g., the processor 801, memory 802, input/output interface 803, and communications interface 804);
wherein the processor 801, the memory 802, the input/output interface 803 and the communication interface 804 are communicatively connected to each other within the device via a bus 805.
The embodiment of the application also provides a storage medium which is a computer-readable storage medium, and the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used for causing a computer to execute the policy detection method.
The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and these remote memories may be connected to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
According to the policy detection method, the policy detection device, the electronic equipment and the storage medium, the case-related information is extracted from the policy to be detected, the LBS information and the network connection information in the preset time period are matched according to the case-related information, the social network is built according to the LBS information, the network connection information and the case-related information, the network nodes in the social network are subjected to cluster analysis, so that the social cluster for representing the relation among the network nodes is obtained, the detection category of the policy to be detected is determined according to the social cluster and the preset decision condition, through the arrangement, the policy fraud detection can be accurately and effectively realized, the policy detection efficiency is improved, and the loss of insurance companies is reduced.
The embodiments described in the embodiments of the present disclosure are for more clearly illustrating the technical solutions of the embodiments of the present disclosure, and do not constitute a limitation to the technical solutions provided in the embodiments of the present disclosure, and it is obvious to those skilled in the art that the technical solutions provided in the embodiments of the present disclosure are also applicable to similar technical problems with the evolution of technology and the emergence of new application scenarios.
Those skilled in the art will appreciate that the solutions shown in the figures are not intended to limit embodiments of the present disclosure, and may include more or less steps than those shown, or some of the steps may be combined, or different steps.
The above-described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may also be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
One of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.
The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes multiple instructions for enabling an electronic device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method of the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing programs, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The preferred embodiments of the present disclosure have been described above with reference to the accompanying drawings, and therefore do not limit the scope of the claims of the embodiments of the present disclosure. Any modifications, equivalents and improvements within the scope and spirit of the embodiments of the present disclosure should be considered within the scope of the claims of the embodiments of the present disclosure by those skilled in the art.
Claims (10)
1. A policy detection method, comprising:
acquiring a policy to be tested;
performing information extraction processing on the policy to be tested to obtain case-involved information;
matching service connection information in a preset time period according to the case-related information; wherein the service connection information includes LBS information and network connection information;
building a social network based on the LBS information, the network connection information and the case-involved information;
performing clustering analysis processing on network nodes of the social network according to a preset clustering analysis model to obtain a plurality of social clustering clusters; the social cluster is used for representing the relationship between the network nodes;
and determining the detection category of the policy to be detected according to the plurality of social clustering clusters and preset decision conditions.
2. The method of claim 1, wherein the case-involved information comprises a plurality of case-involved person information and case-involved associated information;
the building of a social network based on the LBS information, the network connection information and the case-involved information comprises the following steps:
performing relation extraction on the LBS information based on the case-involved person information to obtain a plurality of LBS distance relation sets;
extracting the relationship of the network connection information based on the information of the involved persons to obtain a plurality of network relationship sets;
performing relation extraction on the case-involved associated information based on the case-involved person information to obtain a plurality of case-involved associated relation sets;
inputting each LBS distance relation set, the corresponding network relation set and the corresponding involved case association relation set into a preset score calculation model for score calculation to obtain a corresponding target score;
and building the social network according to the information of each involved person and the corresponding target score.
3. The method of claim 2, wherein the step of inputting each LBS distance relationship set, the corresponding network relationship set, and the corresponding case-related association set into a preset score calculation model for score calculation to obtain a corresponding target score comprises:
carrying out classification matching processing on the LBS distance relation set to obtain an LBS distance score;
carrying out classification matching processing on the network relation set to obtain a network connection score;
carrying out classification matching processing on the case-involved association set to obtain case-involved association scores;
and obtaining the target score according to the LBS distance score, the network connection score and the involved-case correlation score.
4. The method of claim 3, wherein the performing classification matching processing on the set of network relationships to obtain a network connection score comprises:
acquiring the product purchase time score of the insurance policy to be tested; the product purchase time score is used for representing the product purchase time corresponding to the policy to be tested;
acquiring the time type score of the case-involved information; the time type scores are used for representing the time of common occurrence among the information of the involved persons;
classifying the network relation set to obtain a network connection type;
determining a corresponding network type score according to the network connection type and a preset mapping rule;
and obtaining the network connection score according to the product purchase time score, the time type score and the network type score.
5. The method of claim 4, wherein said deriving the network connection score from the product purchase time score, the time type score, and a network type score comprises:
calculating the product purchase time score, the time type score and the network type score to obtain a target connection score;
and carrying out normalization processing on the target connection score to obtain the network connection score.
6. The method as claimed in any one of claims 3 to 5, wherein the obtaining the target score according to the LBS distance score, the network connection score and the case-related association score comprises:
acquiring preset product association coefficients, network connection coefficients and LBS distance coefficients;
weighting the product association score according to the product association coefficient to obtain a product association weighted value;
weighting the network connection scores according to the network connection coefficients to obtain network connection weighted values;
carrying out weighting processing on the LBS distance score according to the LBS distance coefficient to obtain an LBS distance weighted value;
and summing the product association weighted value, the network connection weighted value and the LBS distance weighted value to obtain the target score.
7. The method according to any one of claims 1 to 5, wherein the detection categories include fraud policies and normal policies;
the determining the detection category of the policy to be tested according to the plurality of social clustering clusters and the preset decision condition comprises the following steps:
when a plurality of the social clustering clusters are a main clustering cluster, the policy to be tested is the fraud policy;
and when the plurality of social clustering clusters comprise a plurality of normal clustering clusters, the policy to be tested is the normal policy.
8. A policy detection device, comprising:
the acquisition module is used for acquiring the policy to be tested;
the extraction module is used for extracting information of the policy to be tested to obtain case-related information;
the matching module is used for matching the service connection information in a preset time period according to the case-related information; wherein the service connection information includes LBS information and network connection information;
the building module is used for building a social network based on the LBS information, the network connection information and the case-related information;
the cluster analysis module is used for carrying out cluster analysis processing on the network nodes of the social network according to a preset cluster analysis model to obtain a plurality of social cluster clusters; the social clustering cluster is used for representing the relation between the network nodes;
and the decision module is used for determining the detection category of the policy to be detected according to the plurality of social clustering clusters and preset decision conditions.
9. An electronic device, comprising:
at least one memory;
at least one processor;
at least one program;
the programs are stored in the memory, and the processor executes the at least one program to implement:
the method of any one of claims 1 to 7.
10. A storage medium that is a computer-readable storage medium having stored thereon computer-executable instructions for causing a computer to perform:
the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210234391.8A CN114529747A (en) | 2022-03-09 | 2022-03-09 | Policy detection method, policy detection device, electronic apparatus, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210234391.8A CN114529747A (en) | 2022-03-09 | 2022-03-09 | Policy detection method, policy detection device, electronic apparatus, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114529747A true CN114529747A (en) | 2022-05-24 |
Family
ID=81627577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210234391.8A Pending CN114529747A (en) | 2022-03-09 | 2022-03-09 | Policy detection method, policy detection device, electronic apparatus, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114529747A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116012169A (en) * | 2022-12-21 | 2023-04-25 | 南京睿聚科技发展有限公司 | Method and system for screening risk of insurance claim settlement based on position data |
| CN116308434A (en) * | 2023-05-12 | 2023-06-23 | 杭州大鱼网络科技有限公司 | Insurance fraud identification method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080172257A1 (en) * | 2007-01-12 | 2008-07-17 | Bisker James H | Health Insurance Fraud Detection Using Social Network Analytics |
| CN105404890A (en) * | 2015-10-13 | 2016-03-16 | 广西师范学院 | Criminal gang discrimination method considering locus space-time meaning |
| CN108734479A (en) * | 2018-04-12 | 2018-11-02 | 阿里巴巴集团控股有限公司 | Data processing method, device, equipment and the server of Insurance Fraud identification |
| CN110413707A (en) * | 2019-07-22 | 2019-11-05 | 百融云创科技股份有限公司 | The excavation of clique's relationship is cheated in internet and checks method and its system |
-
2022
- 2022-03-09 CN CN202210234391.8A patent/CN114529747A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080172257A1 (en) * | 2007-01-12 | 2008-07-17 | Bisker James H | Health Insurance Fraud Detection Using Social Network Analytics |
| CN105404890A (en) * | 2015-10-13 | 2016-03-16 | 广西师范学院 | Criminal gang discrimination method considering locus space-time meaning |
| CN108734479A (en) * | 2018-04-12 | 2018-11-02 | 阿里巴巴集团控股有限公司 | Data processing method, device, equipment and the server of Insurance Fraud identification |
| CN110413707A (en) * | 2019-07-22 | 2019-11-05 | 百融云创科技股份有限公司 | The excavation of clique's relationship is cheated in internet and checks method and its system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116012169A (en) * | 2022-12-21 | 2023-04-25 | 南京睿聚科技发展有限公司 | Method and system for screening risk of insurance claim settlement based on position data |
| CN116012169B (en) * | 2022-12-21 | 2024-03-22 | 南京睿聚科技发展有限公司 | Method and system for screening risk of insurance claim settlement based on position data |
| CN116308434A (en) * | 2023-05-12 | 2023-06-23 | 杭州大鱼网络科技有限公司 | Insurance fraud identification method and system |
| CN116308434B (en) * | 2023-05-12 | 2023-08-11 | 杭州大鱼网络科技有限公司 | Insurance fraud identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10102220B2 (en) | Activity based analytics | |
| Zhong et al. | Inferring building functions from a probabilistic model using public transportation data | |
| CN109345417B (en) | Online assessment method and terminal equipment for business personnel based on identity authentication | |
| Catini et al. | Identifying geographic clusters: A network analytic approach | |
| Oliveira et al. | Evaluation of two methods for identifying trip purpose in GPS-based household travel surveys | |
| CN114529747A (en) | Policy detection method, policy detection device, electronic apparatus, and storage medium | |
| US20210174968A1 (en) | Visualization of Social Determinants of Health | |
| CN107609651A (en) | A kind of design item appraisal procedure based on learner model | |
| CN109472075A (en) | A kind of base station performance analysis method and system | |
| CN111192153A (en) | Crowd relation network construction method and device, computer equipment and storage medium | |
| CN113722617A (en) | Method and device for identifying actual office address of enterprise and electronic equipment | |
| Wei et al. | An alternative classification scheme for uncertain attribute mapping | |
| Zeng et al. | A hybrid modeling approach considering spatial heterogeneity and nonlinearity to discover the transition rules of urban cellular automata models | |
| CN114862140A (en) | Behavior analysis-based potential evaluation method, device, equipment and storage medium | |
| Mouronte-López | Modeling the public transport networks: A study of their efficiency | |
| CN113707304A (en) | Triage data processing method, device, equipment and storage medium | |
| CN116741396A (en) | Article classification method and device, electronic equipment and storage medium | |
| CN116127066A (en) | Text clustering method, text clustering device, electronic equipment and storage medium | |
| Liu et al. | Comparing regional sustainability and transportation sustainability at the metropolitan level in the US using artificial neural network clustering techniques | |
| CN115099680A (en) | Risk management method, device, equipment and storage medium | |
| CN114896294A (en) | Method, device and equipment for generating product test data table and storage medium | |
| CN114219663A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN113722484A (en) | Rumor detection method, device, equipment and storage medium based on deep learning | |
| CN111523034A (en) | Application processing method, device, equipment and medium | |
| CN114610921B (en) | Object cluster portrait determination method, device, computer equipment and storage medium |
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 |