Privacy-preserving intersection-based insurance anti-ring fraud method and system, electronic device
By employing a multi-faceted privacy intersection method based on insurance claims records, the problems of low efficiency and insufficient data utilization in traditional insurance fraud prevention have been solved, enabling efficient identification of organized fraud and improving the anti-fraud capabilities of insurance companies.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHEJIANG LAB
- Filing Date
- 2023-05-06
- Publication Date
- 2026-05-29
AI Technical Summary
Existing technologies are insufficient to effectively identify organized fraud in insurance claims, and traditional methods rely on manual review, which is inefficient and costly, and cannot effectively utilize data from multiple insurance companies for anti-fraud purposes.
By constructing a multi-faceted privacy intersection method for insurance claim records, including joint privacy intersection, privacy intersection between similar sub-databases, and cross-privacy intersection between different types of sub-databases, the intersection results are generated for fraud auditing by insurance companies.
This technology improves the efficiency of insurance companies in identifying organized fraud cases without exposing trade secrets, and enhances the ability of insurance companies to identify organized fraud.
Smart Images
Figure CN117036048B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of insurance anti-fraud technology, and in particular to an insurance anti-gang fraud method, system, and electronic device based on privacy intersection. Background Technology
[0002] With the increasing number of insurance claims each year, insurance fraud in these claims is also on the rise. Identifying suspected insurance fraud cases is therefore crucial. Traditional insurance anti-fraud methods rely heavily on human experience, requiring significant manual review and verification, resulting in high costs, low efficiency, and susceptibility to subjective biases among reviewers. As the insurance industry rapidly develops, relying on human experience to identify fraud cases is becoming increasingly inadequate. The insurance industry has existed and developed for decades, and insurance companies have accumulated massive amounts of data related to claims. Utilizing big data and artificial intelligence technologies to mine this data is essential for efficiently implementing insurance anti-fraud efforts. Furthermore, insurance fraud often targets multiple insurance companies and frequently occurs in the form of organized fraud. Existing methods for combating organized fraud based on big data and artificial intelligence technologies are mostly based on data from a single company; currently, there is a lack of concrete methods for comprehensively utilizing data from multiple insurance companies to combat organized fraud without exposing the companies' trade secrets. Summary of the Invention
[0003] To address the shortcomings of existing technologies, this invention proposes a method and system for combating group fraud in insurance based on privacy-based intersection.
[0004] To achieve the above-mentioned technical objectives, the technical solution of the present invention is as follows:
[0005] A first aspect of this invention provides an insurance anti-fraud method based on privacy intersection, the method specifically including the following steps:
[0006] Step S1: Extract information on the parties involved in claims involving two individuals from the insurance claim records of each data provider, construct a database of claims involving two individuals for each data provider, and further construct a sub-database of information on the responsible party and the claimant for each data provider.
[0007] Step S2: Perform multi-faceted privacy intersection on the dual-person claims case database, the responsible party information sub-database, and the claimant information sub-database constructed in Step S1 to obtain the first privacy intersection result;
[0008] Step S3: Each company acting as a data purchaser and / or each company acting as a data provider performs a privacy cross-validation with the first privacy cross-validation result obtained in Step S2 and their own list of insured customers to obtain a second privacy cross-validation result. The second privacy cross-validation result is used as the basis for each data purchaser and / or each data provider to review and identify group fraud in claims cases.
[0009] Furthermore, the dual-person claim case database consists of several claim records, each containing information on the responsible party and the claimant; the information on the responsible party and the claimant is extracted from each dual-person claim case database to construct a sub-database of responsible party information and a sub-database of claimant information respectively.
[0010] Furthermore, the privacy intersection in step S2 includes joint privacy intersection, privacy intersection between similar sub-databases, and cross privacy intersection between different types of sub-databases.
[0011] Furthermore, the joint privacy intersection process includes:
[0012] Perform pairwise privacy intersections on the database of two-person claims constructed in step S1, and record the results of each joint privacy intersection as the joint intersection.
[0013] Furthermore, the privacy-preserving intersection process between the aforementioned sub-databases includes:
[0014] Perform pairwise privacy intersection on the responsible party information sub-database constructed in step S1, and record the results of each privacy intersection as the responsible party intersection;
[0015] Perform pairwise privacy intersections on the claimant information sub-database constructed in step S1, and record the results of each privacy intersection as the claimant intersection.
[0016] Furthermore, the cross-privacy intersection process between the different types of sub-databases includes:
[0017] Perform pairwise privacy intersection calculations on the responsible party information sub-database and the claimant information sub-database constructed in step S1, and record the results of each privacy intersection as the mixed intersection.
[0018] Furthermore, the process of performing pairwise cross-privacy intersection of the responsible party information sub-database and the claimant information sub-database includes: performing cross-privacy intersection of the responsible party information sub-database of each data provider with the claimant information sub-database of other data providers to obtain a mixed intersection; the mixed intersection consists of several pieces of information about the parties involved, who are responsible parties in the aforementioned responsible party information sub-database and claimants in the aforementioned claimant information sub-database.
[0019] A second aspect of this invention provides an insurance anti-fraud system based on privacy intersection, used to implement the above-described insurance anti-fraud method based on privacy intersection, the system comprising:
[0020] The database construction module is used to extract information on the parties involved in claims involving two individuals from the insurance claim records of various data providers, and to build a database of claims involving two individuals, a sub-database of information on the responsible party, and a sub-database of information on the claimant for each data provider.
[0021] The privacy intersection module is used to perform multi-faceted privacy intersection on the constructed database of two-person claims cases, the sub-database of responsible party information, and the sub-database of claimant information to obtain the first privacy intersection result;
[0022] The privacy cross-cutting result application module enables each company acting as a data purchaser and / or each company acting as a data provider to cross-cut the first privacy cross-cutting result with their own list of insured customers to obtain a second privacy cross-cutting result. The second privacy cross-cutting result is used as the basis for each data purchaser and / or each data provider to review and identify group fraud in claims cases.
[0023] A third aspect of the present invention provides an electronic device including a memory and a processor, wherein the memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the above-described privacy-based intersection-based insurance anti-fraud method.
[0024] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described privacy-based intersection method for preventing insurance fraud.
[0025] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention proposes an insurance anti-fraud method and system based on privacy intersection. By introducing privacy intersection, insurance companies can share information with other insurance companies without exposing trade secrets. Through multi-faceted privacy intersection, potential groups of people who may be involved in insurance fraud can be identified, thereby effectively improving the efficiency of the corresponding companies in identifying insurance fraud cases. Attached Figure Description
[0026] Figure 1 This is a flowchart of the method of the present invention;
[0027] Figure 2 This is a schematic diagram illustrating the extraction of information about involved persons and the establishment of a database for dual-person claims in an embodiment of the present invention.
[0028] Figure 3This is a schematic diagram of the structure of database A and the establishment of the responsible party information sub-database and the claimant information sub-database in an embodiment of the present invention;
[0029] Figure 4 This is a schematic diagram of joint privacy intersection in an embodiment of the present invention;
[0030] Figure 5 This is a schematic diagram of the joint intersection AB in an embodiment of the present invention;
[0031] Figure 6 This is a schematic diagram illustrating the privacy intersection process of the responsible party information sub-database in an embodiment of the present invention;
[0032] Figure 7 This is a schematic diagram of the intersection of the responsible parties AB in an embodiment of the present invention;
[0033] Figure 8 This is a schematic diagram illustrating the privacy-preserving intersection process of the claimant information sub-database in an embodiment of the present invention;
[0034] Figure 9 This is a schematic diagram of the intersection AB of the claimants in an embodiment of the present invention;
[0035] Figure 10 This is a schematic diagram illustrating the process of cross-privacy calculation between the responsible party and the claimant in an embodiment of the present invention;
[0036] Figure 11 This is a schematic diagram of the mixed intersection AB in an embodiment of the present invention;
[0037] Figure 12 A schematic diagram of an insurance anti-fraud system based on privacy intersection provided in an embodiment of the present invention;
[0038] Figure 13 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation
[0039] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.
[0040] The terminology used in this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular forms “a,” “the,” and “the” used in this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.
[0041] The present invention will now be described in detail with reference to the accompanying drawings. Unless otherwise specified, the features of the following embodiments and implementations can be combined with each other.
[0042] like Figure 1 As shown, this invention proposes a privacy-based intersection method for combating group fraud in insurance, which specifically includes the following steps:
[0043] Step S1: Extract information on the persons involved in claims involving two individuals from the insurance claim records of each insurance company, construct a database of claims involving two individuals for each company, and further construct a sub-database of information on the responsible party and the claimant for each company.
[0044] The insurance companies that provide claims records are defined as data providers; the information on the parties involved includes the responsible party and the claimant; the responsible party is the person who purchased an insurance product from a certain company and bears primary responsibility for the accident; the claimant is the victim in the accident who seeks compensation from the responsible party.
[0045] Based on the insurance claim records of each data provider, a dual-claims case database is constructed for each company. Each dual-claims case database consists of several claim records, and each claim record contains information on the responsible party and the claimant. In addition, information on the responsible party and the claimant is extracted from each dual-claims case database to construct separate sub-databases for the responsible party and the claimant.
[0046] Step S2 involves performing a multi-faceted privacy cross-reference on the dual-person claims case database, the responsible party information sub-database, and the claimant information sub-database constructed in Step S1.
[0047] The multi-faceted privacy intersection in step S2 includes joint privacy intersection, privacy intersection between similar sub-databases, and cross privacy intersection between different types of sub-databases. The processes of joint privacy intersection, privacy intersection between similar sub-databases, and cross privacy intersection between different sub-databases will be described in detail below.
[0048] (A) Joint Privacy Request
[0049] Perform pairwise privacy intersection on the database of two-person claims established in step S1. Each intersection yields a set, which is denoted as the joint intersection. Each joint intersection consists of several claims records.
[0050] (B) Privacy-preserving intersection between similar sub-databases
[0051] Perform pairwise privacy intersection on the sub-database of responsible party information. Each intersection yields a set, which is denoted as the responsible party intersection. Each responsible party intersection consists of several pieces of responsible party information.
[0052] Perform pairwise privacy intersection on the claimant information sub-database. Each intersection yields a set, which is denoted as the claimant intersection. Each claimant intersection consists of several claimant information entries.
[0053] (C) Privacy-preserving intersection of different sub-databases
[0054] Cross-intersection is performed between the responsible party information sub-database and the claimant information sub-database. That is, each company's responsible party information sub-database is cross-intersected with the claimant information sub-databases of other companies. Each intersection yields a set, which is denoted as the mixed intersection. Each mixed intersection consists of several pieces of information about the parties involved. The parties involved are the responsible parties in the company that provides the responsible party information sub-database and the claimants in the company that provides the claimant information sub-database.
[0055] Step S3: Each company acting as a data purchaser and / or each company acting as a data provider performs a privacy cross-validation with the first privacy cross-validation result obtained in Step S2 and their own list of insured customers to obtain a second privacy cross-validation result. The second privacy cross-validation result is used as the basis for each data purchaser and / or each data provider to review and identify group fraud in claims cases.
[0056] The data purchaser refers to a company that has not provided claims records, but intends to use the above-mentioned data collection results to understand which of its insured customers may be suspected of being involved in group fraud.
[0057] For data providers: Using the joint intersection, responsible party intersection, claimant intersection, and mixed intersection generated in step 2, perform privacy intersections with the insured customer lists of each data provider. When reviewing and verifying claims, the intersection results can provide a basis for identifying customers suspected of gang fraud.
[0058] For data buyers: Using the joint intersection, responsible party intersection, claimant intersection, and mixed intersection generated in step 2, perform privacy intersection with the insured customer lists of each data buyer. When reviewing and verifying claims, the intersection results can provide a basis for identifying customers suspected of gang fraud.
[0059] Example 1
[0060] Next, using a scenario with three data providers, namely Company A, Company B, and Company C, as an example, this invention will describe in detail a privacy-based intersection method for combating group fraud in insurance, which includes the following steps:
[0061] Step 1, as follows Figure 2 , Figure 3 As shown, information on individuals involved in claims involving two individuals is extracted from the insurance claim records of various companies that serve as data providers. This information is then used to construct a database of claims involving two individuals, a sub-database of information on the responsible party, and a sub-database of information on the claimant for each data provider.
[0062] Step 1-1: Extract claims cases involving the two individuals from the insurance claim records of various companies. The companies providing the claim records are defined as data providers. In this embodiment 1, for ease of explanation, it is assumed that there are 3 insurance companies as data providers. In practice, the number of data providers is not limited and can be any number, such as... Figure 2 As shown, these three companies are named Company A, B, and C respectively. The extracted individual claim records mainly contain information about the parties involved, including the responsible party and the claimant. Taking a claim record extracted from Company A as an example, the responsible party is the person who purchased insurance products from Company A and bears primary responsibility for the accident; the claimant is the victim in the accident who seeks compensation from the responsible party. Since the responsible party purchased insurance products from Company A, in the absence of fraud, Company A should assume the obligation to compensate the claimant on behalf of the responsible party.
[0063] Step 1-2: Based on the data collected from companies A, B, and C in Step 1-1, construct two-person claim case databases A, B, and C respectively. Taking database A as an example, it consists of several claim records, named claim record A1, claim record A2, etc. Taking claim record A1 as an example, each claim record contains information about the responsible party and the claimant, named responsible party A1 and claimant A2 respectively. Figure 3 As shown. In addition, information of the responsible party is extracted from the dual-person claim case databases A, B, and C, and sub-databases of responsible party information A, B, and C are constructed respectively. Then, information of the claimant is extracted from the claimant information, and sub-databases of claimant information A, B, and C are constructed respectively.
[0064] Step 2, as follows Figures 4-11As shown, a multi-faceted privacy intersection is performed on the dual-person claims case database, the responsible party information sub-database, and the claimant information sub-database constructed in step 1 to obtain the first privacy intersection result.
[0065] The multi-faceted privacy intersection in step 2 includes joint privacy intersection, privacy intersection between similar sub-databases, and cross-privacy intersection between different types of sub-databases. The processes of joint privacy intersection, privacy intersection between similar sub-databases, and cross-privacy intersection between different types of sub-databases will be described in detail below.
[0066] (A) Joint Privacy Crossover: Perform pairwise privacy crossovers on the two-person claims case databases A, B, and C established in steps 1-2, resulting in a total of 3 privacy crossovers. In these 3 privacy crossovers, if... Figure 4 As shown, the result of performing a privacy intersection on databases A and B for claims involving two individuals is denoted as the joint intersection AB; the result of performing a privacy intersection on databases A and C for claims involving two individuals is denoted as the joint intersection AC; and the result of performing a privacy intersection on databases B and C for claims involving two individuals is denoted as the joint intersection BC. Figure 5 As shown, taking the joint intersection AB as an example, it consists of several claim records, named claim record AB1, claim record AB2, etc., and each claim record also contains information about the responsible party and the claimant.
[0067] (B) Privacy Intersection Between Similar Sub-databases: Perform pairwise privacy intersections on sub-databases A, B, and C containing the responsible party information, resulting in a total of three privacy intersections. In these three intersections, the participating responsible party information sub-databases are A and B, A and C, and B and C, respectively. Each intersection yields a set, named the Responsible Party Intersection AB, Responsible Party Intersection AC, and Responsible Party Intersection BC, respectively. Figure 6 Taking the intersection of responsible parties AB as an example, it consists of several pieces of information about responsible parties, named responsible party AB1, responsible party AB2, etc. Figure 7 Then, pairwise privacy intersections are performed on the claimant information sub-databases A, B, and C, resulting in a total of three privacy intersections. In these three privacy intersections, the claimant information sub-databases involved are A and B, A and C, and B and C, respectively. Each intersection yields a set, named claimant intersection AB, claimant intersection AC, and claimant intersection BC, respectively. Figure 8 Taking the intersection of claimants AB as an example, it consists of several claimant information entries, named claimant AB1, claimant AB2, etc. Figure 9 ).
[0068] (C) Cross-Privacy Intersection between Responsible Parties and Claimants: Cross-privacy intersections are performed between each responsible party's information sub-database and each claimant's information sub-database, for a total of 6 cross-privacy intersections: Responsible party information sub-database A is cross-privacy intersected with claimant information sub-databases B and C respectively, obtaining mixed intersections AB and AC; Responsible party information sub-database B is cross-privacy intersected with claimant information sub-databases A and C respectively, obtaining mixed intersections BA and BC; Responsible party information sub-database C is cross-privacy intersected with claimant information sub-databases A and B respectively, obtaining mixed intersections CA and CB. Figure 10 Taking the mixed intersection AB as an example, it consists of several pieces of information about the parties involved. The parties involved are the responsible party in Company A and the claimant in Company B. The parties involved in the mixed intersection AB are named as Party AB1, Party AB2, ... ( Figure 11 ).
[0069] Step 3: Each company acting as a data purchaser and / or each company acting as a data provider shall perform a privacy cross-check between the first privacy cross-check result obtained in Step 2 and its own list of insured customers to obtain a second privacy cross-check result. The second privacy cross-check result shall be used as the basis for each data purchaser and / or each data provider to review and identify group fraud in the claims case.
[0070] Step 3 regarding the use of multi-faceted privacy request results includes the use of privacy request results by various data providers and data purchasers. The data purchasers refer to companies that have not provided claims records but intend to use the aforementioned request results to understand which of their insured customers may be involved in group fraud.
[0071] For data providers: Using the joint intersection, responsible party intersection, claimant intersection, and mixed intersection generated in step 2, perform privacy intersections with the insured customer lists of companies A, B, and C respectively. The intersection results can be used as the basis for the aforementioned companies to review and identify group fraud in claims cases.
[0072] For the data purchasers: In this embodiment 1, it is assumed that there are 3 insurance companies as data purchasers. In reality, there is no limit to the number of companies purchasing data; these 3 companies are named companies D, E, and F, respectively. Using the joint intersection, liability party intersection, claimant intersection, and mixed intersection generated in step 2, privacy intersections are performed with the insured customer lists of companies D, E, and F, respectively. The intersection results can serve as the basis for the aforementioned companies to review and identify group fraud in claims cases.
[0073] In summary, this invention proposes a method and system for combating insurance fraud gangs based on privacy intersection. By introducing privacy intersection technology, insurance companies can share information with other insurance companies without exposing trade secrets. Through multi-faceted privacy intersection, potential individuals involved in insurance fraud gangs can be identified, thereby effectively improving the efficiency of identifying insurance fraud gangs for the relevant companies.
[0074] On the other hand, the present invention also provides an insurance anti-fraud system based on privacy intersection, used to implement the above-mentioned insurance anti-fraud method based on privacy intersection. The system includes a database construction module, a privacy intersection module, and a privacy intersection result application module.
[0075] The database construction module is used to extract information on persons involved in claims involving two individuals from the insurance claim records of various companies that are data providers, and to construct a database of claims involving two individuals, a sub-database of information on the responsible party, and a sub-database of information on the claimant for each data provider.
[0076] The privacy intersection module is used to perform multi-faceted privacy intersection on the constructed database of two-person claims cases, the sub-database of responsible party information, and the sub-database of claimant information to obtain the first privacy intersection result.
[0077] The privacy cross-cutting result application module enables each company acting as a data purchaser and / or each company acting as a data provider to perform a privacy cross-cutting between the first privacy cross-cutting result and their own list of insured customers to obtain a second privacy cross-cutting result. The second privacy cross-cutting result is used as the basis for each data purchaser and / or each data provider to review and identify group fraud in claims cases.
[0078] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.
[0079] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.
[0080] Accordingly, this application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the above-described privacy-based intersection method for insurance anti-fraud. Figure 13 The diagram shown illustrates a hardware structure of any data processing device for the privacy-based intersection-based insurance anti-fraud method provided in this embodiment of the invention. (Except for...) Figure 13 In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.
[0081] Accordingly, this application also provides a computer-readable storage medium storing computer instructions thereon, which, when executed by a processor, implement the aforementioned privacy-based intersection-based insurance anti-fraud method. The computer-readable storage medium can be an internal storage unit of any data-processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data-processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data-processing device, and can also be used to temporarily store data that has been output or will be output.
[0082] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only.
[0083] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.
Claims
1. A privacy-based intersection method for combating group fraud in insurance, characterized in that, The method includes: Step S1: Extract information on the parties involved in claims involving two individuals from the insurance claim records of each data provider, construct a database of claims involving two individuals for each data provider, and further construct a sub-database of information on the responsible party and the claimant for each data provider. Step S2: Perform multi-faceted privacy intersection on the databases of each double-person claim case, the sub-database of the responsible party's information, and the sub-database of the claimant's information constructed in Step S1 to obtain the first privacy intersection result; The multi-faceted privacy intersection in step S2 includes joint privacy intersection, privacy intersection between similar sub-databases, and cross privacy intersection between different types of sub-databases. The process of joint privacy intersection includes: performing pairwise privacy intersection on the database of two-person claims constructed in step S1, and recording the result of joint privacy intersection as joint intersection; The privacy intersection process between the sub-databases of the same type includes: performing pairwise privacy intersection on the responsible party information sub-database constructed in step S1, and recording the result of the privacy intersection as the responsible party intersection; performing pairwise privacy intersection on the claimant information sub-database constructed in step S1, and recording the result of the privacy intersection as the claimant intersection; The process of cross-privacy intersection between different types of sub-databases includes: performing pairwise cross-privacy intersection between the responsible party information sub-database and the claimant information sub-database, and recording the result of the cross-privacy intersection as the mixed intersection; Step S3: Each company acting as a data purchaser and / or each company acting as a data provider performs a privacy cross-validation with the first privacy cross-validation result obtained in Step S2 and their own list of insured customers to obtain a second privacy cross-validation result. The second privacy cross-validation result is used as the basis for each data purchaser and / or each data provider to review and identify group fraud in claims cases.
2. The insurance anti-fraud method based on privacy intersection as described in claim 1, characterized in that, The dual-person claim database consists of several claim records, each containing information about the responsible party and the claimant. Information about the responsible party and the claimant is extracted from each dual-person claim database to construct a sub-database of responsible party information and a sub-database of claimant information.
3. The insurance anti-fraud method based on privacy intersection as described in claim 1, characterized in that, The process of performing pairwise cross-privacy intersection of the responsible party information sub-database and the claimant information sub-database includes: performing cross-privacy intersection of the responsible party information sub-database of each data provider with the claimant information sub-database of other data providers, and obtaining corresponding mixed intersections; each mixed intersection consists of several pieces of information about the parties involved, who are responsible parties in the aforementioned responsible party information sub-database and claimants in the aforementioned claimant information sub-database.
4. A privacy-based intersection-based insurance anti-fraud system, used to implement the privacy-based intersection-based insurance anti-fraud method according to any one of claims 1-3, characterized in that, The system includes: The database construction module is used to extract information on the parties involved in claims involving two individuals from the insurance claim records of various data providers, and to build a database of claims involving two individuals for each data provider. Furthermore, it builds a sub-database of information on the responsible party and the claimant for each data provider. The privacy intersection module is used to perform multi-faceted privacy intersection on the constructed database of two-person claims cases, the sub-database of responsible party information, and the sub-database of claimant information to obtain the first privacy intersection result; The privacy cross-cutting result application module enables each company acting as a data purchaser and / or each company acting as a data provider to cross-cut the obtained first privacy cross-cutting result with their own list of insured customers to obtain a second privacy cross-cutting result. The second privacy cross-cutting result is used as the basis for each data purchaser and / or each data provider to review and identify group fraud in claims cases.
5. An electronic device, comprising a memory and a processor, characterized in that, The memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the privacy-based intersection method for insurance anti-fraud according to any one of claims 1-3.
6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the privacy-based intersection method for insurance anti-fraud as described in any one of claims 1-3.