Home relation network construction method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of data analysis and financial science and technology, and discloses a family relationship network construction method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining to-be-processed insurance policy data; cleaning family relationship pairs in the to-be-processed insurance policy data to obtain an initial relationship pair set; performing relation pair expansion on the set based on the initial relation pair through a connected graph algorithm to obtain a target relation pair set; and according to the target relationship pair set, extracting all personnel and personnel relationships belonging to the same family, and generating a family information record. According to the invention, the family relationship between different areas is expanded, the problem of family relationship conflict is avoided, and the accuracy of family relationship network construction is improved.

Description

Technical Field

[0001] The present application relates to the fields of data analysis and financial technology, and in particular to a method, device, computer equipment and storage medium for constructing a family relationship network. Background Art

[0002] Nowadays, all walks of life have entered the era of stock customer operation, and how to dig out value clues from complex relationships is becoming more and more important. Especially in the insurance system, because a large part of insurance protection is purchased by family members, but the traditional relationship between the policyholder (policyholder), the insured (insured person), and the beneficiary (beneficiary) is only based on the insurance policy as the smallest dimension, and there are obvious differences between the insured and the beneficiaries involved in the insurance policy protection type. How to expand the corresponding family relationship network through different insurance policies and tap into more family members' needs has become the key to the performance growth of the insurance industry.

[0003] The existing family relationship network construction scheme adopts the method of institutional slicing to construct the family network. However, due to the large amount of data in the insurance system, the existing method cannot expand the family relationships between different regions. If a family purchases insurance policies from different institutions, there will be family relationship conflicts, resulting in low accuracy in the construction of the family relationship network. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method, apparatus, computer device and storage medium for constructing a family relationship network, so as to improve the accuracy of constructing a family relationship network.

[0005] In order to solve the above technical problems, the present application embodiment provides a method for constructing a family relationship network, including:

[0006] Get the policy data to be processed;

[0007] Cleaning the family relationship pairs in the to-be-processed insurance policy data to obtain an initial relationship pair set;

[0008] Expanding the relationship pairs based on the initial relationship pair set by using a connected graph algorithm to obtain a target relationship pair set;

[0009] All persons and person relationships belonging to the same family are extracted according to the target relationship pair set, and a family information record is generated.

[0010] In order to solve the above technical problems, the embodiment of the present application provides a device for constructing a family relationship network, including:

[0011] A policy data acquisition unit, used to acquire policy data to be processed;

[0012] A relationship pair cleaning unit, used for cleaning the family relationship pairs in the to-be-processed insurance policy data to obtain an initial relationship pair set;

[0013] A relationship pair expansion unit, configured to expand the relationship pairs based on the initial relationship pair set by using a connectivity graph algorithm to obtain a target relationship pair set;

[0014] The family information recording unit is used to extract all persons and person relationships belonging to the same family according to the target relationship pair set, and generate a family information record.

[0015] In order to solve the above technical problems, a technical solution adopted by the present invention is: to provide a computer device, including one or more processors; a memory for storing one or more programs, so that the one or more processors can implement any one of the above methods for constructing a family relationship network.

[0016] In order to solve the above technical problems, a technical solution adopted by the present invention is: a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements any one of the above methods for constructing a family relationship network.

[0017] The embodiment of the present invention provides a method, device, computer equipment and storage medium for constructing a family relationship network. The method includes: obtaining the policy data to be processed; cleaning the family relationship pairs in the policy data to be processed to obtain an initial relationship pair set; expanding the relationship pairs based on the initial relationship pair set by a connected graph algorithm to obtain a target relationship pair set; extracting all persons and personnel relationships belonging to the same family according to the target relationship pair set to generate family information records. The embodiment of the present invention uses a connected graph algorithm to expand the cleaned relationship pair set and extract the family information in the expanded relationship pair set, thereby expanding the family relationships between different regions, avoiding the problem of family relationship conflicts, and facilitating the accuracy of family relationship network construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 is a schematic diagram of an application environment of a method for constructing a family relationship network in an embodiment of the present invention;

[0020] Figure 2It is a flowchart of the implementation process of the method for constructing a family relationship network provided in an embodiment of the present application;

[0021] Figure 3 yes Figure 2 A schematic flow chart of a specific implementation of step S2;

[0022] Figure 4 yes Figure 2 A schematic flow chart of a specific implementation of step S3;

[0023] Figure 5 yes Figure 4 A schematic flow chart of a specific implementation of step S31;

[0024] Figure 6 yes Figure 4 A schematic flow chart of a specific implementation of step S32;

[0025] Figure 7 yes Figure 4 A schematic flow chart of a specific implementation of step S33;

[0026] Figure 8 yes Figure 2 A schematic flow chart of a specific implementation of step S4;

[0027] Fig. 9 It is a schematic diagram of a device for constructing a family relationship network provided in an embodiment of the present application;

[0028] Fig.10 It is a schematic diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0030] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0031] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0032] The present invention is described in detail below with reference to the accompanying drawings and embodiments.

[0033] It should be noted that the method for constructing a family relationship network provided in the embodiment of the present application is generally executed by a server, and accordingly, the device for constructing a family relationship network is generally configured in the server.

[0034] The method for constructing a family relationship network provided by the embodiment of the present invention can be applied in the following aspects: Figure 1 In an application environment, the client communicates with the server through a network. The server can receive the construction requirement of the family relationship network through the client, and obtain the policy data to be processed; clean the family relationship pairs in the policy data to be processed to obtain an initial relationship pair set; expand the relationship pairs based on the initial relationship pair set through a connectivity graph algorithm to obtain a target relationship pair set; extract all personnel and personnel relationships belonging to the same family according to the target relationship pair set, and generate a family information record. The server in the present invention can send the constructed family information record to the client. Among them, the client can be but not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices. The server can be implemented with an independent server or a server cluster consisting of multiple servers. The present invention is described in detail below through specific embodiments.

[0035] See also Figure 2 , Figure 2 A specific implementation of a method for constructing a family relationship network is shown.

[0036] It should be noted that if there are substantially the same results, the method of the present invention is not limited to Figure 1 The process sequence shown is limited to the following steps:

[0037] S1: Get the policy data to be processed.

[0038] The embodiment of the present application is applied to the scenario of constructing a family relationship network in the insurance field. Specifically, the pending policy data is obtained, and the pending policy data is data that has not been constructed through family relationships, and the policy data includes family relationship pairs. For example, in a pending policy data, the insured persons are father and son respectively, so the pending policy data contains a father-son relationship pair.

[0039] S2: Clean the family relationship pairs in the to-be-processed insurance policy data to obtain an initial relationship pair set.

[0040] Specifically, before constructing the family relationship network, the family relationship pairs in the insurance policy data to be processed need to be cleaned to remove the relationship pairs between each customer number that are not within the normal range.

[0041] Among them, family relationships include couples, parents, children, parents-in-law, grandparents and grandchildren, etc.

[0042] See also Figure 3 , Figure 3 A specific implementation of step S2 is shown, which is described in detail as follows:

[0043] S21: removing the repeated family relationship pairs in the to-be-processed insurance policy data according to the uniqueness of the customer number, and obtaining a first processing relationship pair set.

[0044] Specifically, check each family relationship pair in the policy data to be processed to ensure that the customer number in each relationship pair is unique, that is, there is no duplicate relationship pair. For example, if customer numbers A and B are the same but the recorded relationship is not "self", this type of relationship pair needs to be deleted.

[0045] S22: Delete the husband-wife relationship pairs with the same gender in the first processing relationship pair set according to gender consistency, and obtain a second processing relationship pair set.

[0046] Specifically, it is necessary to check whether the husband-wife relationship in the first processing relationship pair set is of opposite sex, if not, delete it. Further, it is necessary to determine whether there is an error in the gender of the father-son, mother-son, mother-daughter, father-son, etc. relationship, if so, delete it.

[0047] S23: Identify incorrect relationship pairs in the second processing relationship pair set according to age and generation relationship, and delete the incorrect relationship pairs to obtain the initial relationship pair set.

[0048] Specifically, the remaining relationship pairs are further verified using age and generation information. This includes checking whether the age difference between parents and children is reasonable, and whether the age relationship between grandparents and grandchildren is logical. If the age and generation information in the relationship pairs is inconsistent or obviously unreasonable (for example, marked as father and son but the age difference is almost the same), these relationship pairs should be identified as incorrect relationship pairs and deleted.

[0049] Furthermore, it is necessary to ensure that each relationship pair in the initial relationship pair set is logically consistent, such as the age difference between grandfather and grandson should be greater than the age difference between parents and children.

[0050] S3: Expand the relationship pairs based on the initial relationship pair set by using a connectivity graph algorithm to obtain a target relationship pair set.

[0051] Specifically, the target relationship pair set is obtained by expanding the relationship pairs based on the initial relationship pair set through the connected graph algorithm. For example, if A and B are husband and wife, and A and C are father and son, then it can be inferred that B and C are mother and son, and this can be repeated for multiple rounds to expand more family relationship pairs.

[0052] Among them, the connected graph algorithm is an important graph theory algorithm used to determine the connectivity of a graph or find connected components. The embodiment of the present application adopts a circulation graph algorithm based on Hi ve, which is a powerful tool for processing and analyzing relationship pairs in large-scale data sets. Through this algorithm, a family relationship network can be efficiently constructed and expanded, and potential relationships in a data set can be revealed.

[0053] See also Figure 4 , Figure 4 A specific implementation of step S3 is shown, which is described in detail as follows:

[0054] S31: Reversing and concatenating the relationship pairs in the initial relationship pair set to obtain a concatenated relationship group set.

[0055] See also Figure 5 , Figure 5 A specific implementation of step S31 is shown, which is described in detail as follows:

[0056] S311: Reverse every two relationship pairs in the initial relationship pair set to obtain reversed relationship pairs.

[0057] S312: Splicing the inverted relationship pairs in pairs to obtain the spliced ​​relationship group set.

[0058] Specifically, the family relationship pairs (such as parent-child, husband-wife, etc.) in the initial relationship pair set are reversed to build a bidirectional relationship. For example, if the original relationship pair is (A, B), the reversed relationship pair is (B, A). Then you need to use Hive's SQL query function (such as JOIN operation) to splice these reversed relationship pairs to form a relationship group of the form XYZ. This involves finding relationship pairs that share a common vertex (here is Y) and connecting them.

[0059] S32: performing relationship pair expansion and aggregation processing on the spliced ​​relationship group set to obtain a new relationship pair set.

[0060] Specifically, the concatenated relationship groups have been obtained above. In the embodiment of the present application, the middle items of these concatenated relationship groups need to be deleted and aggregated with the initial relationship pairs to obtain a new relationship pair set.

[0061] See also Figure 6 , Figure 6 A specific implementation of step S32 is shown, which is described in detail as follows:

[0062] S321: Delete the middle item of each relationship group of the concatenated relationship pair set to generate each extended relationship pair, thereby obtaining an extended relationship pair set.

[0063] S322: Aggregate the expanded relationship pair set and the initial relationship pair set to obtain a new relationship pair set.

[0064] Specifically, the middle item of each relationship group of the spliced ​​relationship pair set is deleted to generate each extended relationship pair to obtain an extended relationship pair set. Then, the extended relationship pair set and the initial relationship pair set are aggregated to obtain a new relationship pair set. The embodiment of the present application can realize the expansion of family relationship pairs, avoid problems with different system relationship pairs, and help improve the accuracy of family relationship network construction.

[0065] After forming the relationship group of XYZ, delete the middle item Y to form a new relationship pair (X, Z). This represents a new relationship between X and Z through the middleman Y. After forming the new relationship pair, it is necessary to eliminate the same relationship pairs of X and Z because they do not provide new information. Finally, it is necessary to aggregate the initial relationship pair and the expanded new relationship pair to form a new relationship pair set. In an embodiment of the present application, Hive's SELECT and DI STINCT statements are used to eliminate duplicate relationship pairs. The UNION ALL operation is used to merge the initial relationship pair and the expanded new relationship pair.

[0066] S33: performing cyclic increment on the relationship pairs in the new relationship pair set, and stopping the cyclic increment when no new relationship pairs can be generated, to obtain the target relationship pair set.

[0067] Specifically, the above steps S31-S32 are executed in a loop, and after each round of execution, the families that cannot generate new relationship pairs are extracted, so that the number of family members does not increase after a new round of expansion, and the relationship data in each round of expansion will not increase exponentially, which optimizes the problem that the original family relationship network must be divided into regions and limited to four rounds of expansion.

[0068] See also Figure 7 , Figure 7 A specific implementation of step S33 is shown, which is described in detail as follows:

[0069] S331: cyclically increment the relationship pairs in the new relationship pair set, and after each round of increment, extract the family relationship information of the members not added from the new relationship pair set.

[0070] S332: When a new relationship pair cannot be generated, stop the loop increment and obtain the current relationship pair set.

[0071] S333: Generate the target relationship pair set based on the current relationship pair set and the family relationship information.

[0072] Specifically, the relationship pairs in the new relationship pair set are incremented cyclically, and after each round of increment, the family relationship information of the members that have not been added is extracted from the new relationship pair set. It is determined whether the relationship pairs generated in the previous cycle are equal to the newly generated relationship pairs. If they are equal, it is determined that no new relationship pairs have been added. Therefore, when it is impossible to generate new relationship pairs, the cyclic increment is stopped, and the current relationship pair set is obtained; the target relationship pair set is generated based on the current relationship pair set and the family relationship information.

[0073] The embodiment of the present application uses the query function of Hi ve to check whether the family member has been added. The final relationship pair set is exported to external storage (such as HDFS or S3) using the EXPORT function of Hi ve for subsequent analysis or visualization.

[0074] S4: extracting all persons and person relationships belonging to the same family according to the target relationship pair set, and generating a family information record.

[0075] Specifically, the above steps have generated a target relationship pair set, which includes personnel and personnel relationships of multiple families. In an embodiment of the present application, all personnel and personnel relationships belonging to the same family can be extracted based on the target relationship pair set. When all families are extracted successfully, family information records are generated, which constitutes a family relationship network.

[0076] See also Figure 8 , Figure 8 A specific implementation of step S4 is shown, which is described in detail as follows:

[0077] S41: Using a connected component identification algorithm to identify each household connected component based on the target relationship pair set.

[0078] S42: Construct a unique home number for each of the home connectivity components.

[0079] S43: Extracting the personnel and personnel relationships of each family number from the target relationship pair set to generate the family information record.

[0080] Specifically, a connected component identification algorithm is used to identify the connected components of each family based on the target relationship pair set. The connected components here are sets of nodes (i.e., people) composed of interconnected relationship pairs (i.e., edges) in graph theory, and each of these sets represents an independent family. Then, a unique family number is constructed for each family connected component, and the personnel and personnel relationships of each family number are extracted from the target relationship pair set to generate a family information record. When all family information records are extracted, all family information records can be generated, that is, the family relationship network.

[0081] In a specific embodiment, a graph traversal algorithm such as depth-first search (DFS) or breadth-first search (BFS) can be used to find all connected components. These algorithms start from a node in the graph and traverse all reachable nodes along the edges until no new nodes can be found, thus obtaining a connected component. Then, a node that has not been visited is selected as the starting point, and the above process is repeated until all nodes have been visited, so that all connected components can be found.

[0082] In the embodiment of the present application, the insurance policy data to be processed is obtained; the family relationship pairs in the insurance policy data to be processed are cleaned to obtain an initial relationship pair set; the relationship pairs are expanded based on the initial relationship pair set by a connected graph algorithm to obtain a target relationship pair set; all persons and personnel relationships belonging to the same family are extracted according to the target relationship pair set to generate family information records. The embodiment of the present invention uses a connected graph algorithm to expand the cleaned relationship pair set and extracts the family information in the expanded relationship pair set, thereby expanding the family relationships between different regions, avoiding the problem of family relationship conflicts, and is conducive to improving the accuracy of family relationship network construction.

[0083] The embodiment of the present application is different from the existing relationship pair expansion scheme. The present application expands all the policyholders, recipients, and salesperson input data together, avoiding the expansion of cross-institutional family data to multiple families due to data slicing by institution. At the end of each round of expansion cycle, the embodiment of the present application will make a comparison. If the number of family members before and after aggregation is the same, it proves that the family has completed the expansion, avoiding the limitation of the number of times resulting in many family relationships not being expanded. The later the number of cycles, the less data there will be, and the resource consumption will be significantly reduced.

[0084] Please refer to Fig. 9 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a device for constructing a family relationship network. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0085] like Fig. 9 As shown, the family relationship network construction device of this embodiment includes: a policy data acquisition unit 51, a relationship pair cleaning unit 52, a relationship pair expansion unit 53 and a family information recording unit 54, wherein:

[0086] The policy data acquisition unit 51 is used to acquire the policy data to be processed;

[0087] A relationship pair cleaning unit 52 is used to clean the family relationship pairs in the to-be-processed insurance policy data to obtain an initial relationship pair set;

[0088] A relationship pair expansion unit 53, configured to expand the relationship pairs based on the initial relationship pair set by using a connectivity graph algorithm to obtain a target relationship pair set;

[0089] The family information recording unit 54 is used to extract all persons and person relationships belonging to the same family according to the target relationship pair set, and generate a family information record.

[0090] Further, the relationship pair expansion unit 53 includes:

[0091] A splicing unit, used for reversing and splicing the relationship pairs in the initial relationship pair set to obtain a spliced ​​relationship group set;

[0092] an aggregation unit, used for performing relationship pair expansion and aggregation processing on the spliced ​​relationship group set to obtain a new relationship pair set;

[0093] The incrementing unit is used to perform cyclic increment on the relationship pairs in the new relationship pair set, and when no new relationship pairs can be generated, stop the cyclic increment to obtain the target relationship pair set.

[0094] Furthermore, the splicing unit comprises:

[0095] A reversal unit, used for reversing any two relationship pairs in the initial relationship pair set to obtain reversed relationship pairs;

[0096] The relationship pair splicing unit is used to splice the inverted relationship pairs in pairs to obtain the spliced ​​relationship group set.

[0097] Further, the polymerization unit comprises:

[0098] An intermediate item deletion unit, used for deleting the intermediate item of each relationship group of the concatenated relationship pair set to generate each extended relationship pair and obtain an extended relationship pair set;

[0099] The relationship pair aggregation unit is used to aggregate the expanded relationship pair set with the initial relationship pair set to obtain a new relationship pair set.

[0100] Furthermore, the incrementing unit comprises:

[0101] A cyclic increment unit, used for cyclically incrementing the relationship pairs in the new relationship pair set, and extracting family relationship information whose members have not been added from the new relationship pair set after each round of increment;

[0102] The stop incrementing unit is used to stop the loop incrementing and obtain the current relationship pair set when a new relationship pair cannot be generated;

[0103] A set generating unit is used to generate the target relationship pair set based on the current relationship pair set and the family relationship information.

[0104] Further, the relationship to the cleaning unit 52 includes:

[0105] A first processing unit, configured to remove repeated family relationship pairs in the to-be-processed insurance policy data according to the uniqueness of the customer number, to obtain a first processing relationship pair set;

[0106] A second processing unit is used to delete the husband-wife relationship pairs with the same gender in the first processing relationship pair set according to gender consistency, so as to obtain a second processing relationship pair set;

[0107] The third processing unit is used to identify the wrong relationship pairs in the second processing relationship pair set according to the age and generation relationship, and delete the wrong relationship pairs to obtain the initial relationship pair set.

[0108] Furthermore, the family information recording unit 54 includes:

[0109] A family connected component identification unit, configured to identify each family connected component based on the target relationship pair set using a connected component identification algorithm;

[0110] A family number construction unit, used to construct a unique family number for each of the family connectivity components;

[0111] A family information generation unit is used to extract the personnel and personnel relationships of each family number from the target relationship pair set to generate the family information record.

[0112] In the embodiment of the present application, the insurance policy data to be processed is obtained; the family relationship pairs in the insurance policy data to be processed are cleaned to obtain an initial relationship pair set; the relationship pairs are expanded based on the initial relationship pair set by a connected graph algorithm to obtain a target relationship pair set; all persons and personnel relationships belonging to the same family are extracted according to the target relationship pair set to generate family information records. The embodiment of the present invention uses a connected graph algorithm to expand the cleaned relationship pair set and extracts the family information in the expanded relationship pair set, thereby expanding the family relationships between different regions, avoiding the problem of family relationship conflicts, and is conducive to improving the accuracy of family relationship network construction.

[0113] To solve the above technical problems, the present application also provides a computer device. Fig.10 , Fig.10 This is a basic structural block diagram of the computer device in this embodiment.

[0114] The computer device 7 includes a memory 71, a processor 72, and a network interface 73 which are interconnected and communicated with each other through a system bus. It should be noted that: Fig.10Only a computer device 7 having three components, a memory 71, a processor 72, and a network interface 73, is shown in the figure, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0115] Computer devices can be computing devices such as desktop computers, notebooks, PDAs, and cloud servers. Computer devices can interact with users through keyboards, mice, remote controls, touch pads, or voice control devices.

[0116] The memory 71 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 71 can be an internal storage unit of the computer device 7, such as a hard disk or memory of the computer device 7. In other embodiments, the memory 71 can also be an external storage device of the computer device 7, such as a plug-in hard disk equipped on the computer device 7, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 71 can also include both the internal storage unit of the computer device 7 and its external storage device. In this embodiment, the memory 71 is generally used to store the operating system and various application software installed on the computer device 7, such as the program code of the method for constructing a family relationship network, etc. In addition, the memory 71 can also be used to temporarily store various types of data that have been output or are to be output.

[0117] The processor 72 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 72 is generally used to control the overall operation of the computer device 7. In this embodiment, the processor 72 is used to run the program code stored in the memory 71 or process data, such as running the program code of the method for constructing the family relationship network described above, so as to implement various embodiments of the method for constructing the family relationship network.

[0118] The network interface 73 may include a wireless network interface or a wired network interface, and the network interface 73 is generally used to establish a communication connection between the computer device 7 and other electronic devices.

[0119] The present application also provides another implementation, namely, providing a computer-readable storage medium, which stores a computer program. The computer program can be executed by at least one processor to enable the at least one processor to perform the steps of the method for constructing a family relationship network as described above.

[0120] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods of each embodiment of the present application.

[0121] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to replace some of the technical features therein with equivalents. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for constructing a family relationship network, characterized in that: include: Get the policy data to be processed; Cleaning the family relationship pairs in the to-be-processed insurance policy data to obtain an initial relationship pair set; Expanding the relationship pairs based on the initial relationship pair set by using a connected graph algorithm to obtain a target relationship pair set; All persons and person relationships belonging to the same family are extracted according to the target relationship pair set, and a family information record is generated.

2. The method for constructing a family relationship network according to claim 1, characterized in that: The method of performing relationship pair expansion based on the initial relationship pair set by using a connectivity graph algorithm to obtain a target relationship pair set includes: Reversing and concatenating the relationship pairs in the initial relationship pair set to obtain a concatenated relationship group set; Performing relationship pair expansion and aggregation processing on the spliced ​​relationship group set to obtain a new relationship pair set; The relationship pairs in the new relationship pair set are incremented cyclically, and when no new relationship pairs can be generated, the cyclic increment is stopped to obtain the target relationship pair set.

3. The method for constructing a family relationship network according to claim 2, characterized in that: The step of reversing and splicing the relationship pairs in the initial relationship pair set to obtain a spliced ​​relationship group set includes: Reversing every two relationship pairs in the initial relationship pair set to obtain reversed relationship pairs; The inverted relationship pairs are spliced ​​in pairs to obtain the spliced ​​relationship group set.

4. The method for constructing a family relationship network according to claim 2, characterized in that: The step of performing relationship pair expansion and aggregation processing on the spliced ​​relationship pair set to obtain a new relationship pair set includes: Deleting the middle item of each relationship group of the concatenated relationship pair set to generate each extended relationship pair, thereby obtaining an extended relationship pair set; The expanded relationship pair set and the initial relationship pair set are aggregated to obtain a new relationship pair set.

5. The method for constructing a family relationship network according to claim 2, characterized in that: The step of cyclically increasing the relationship pairs in the new relationship pair set and stopping the cyclic increasing when no new relationship pairs can be generated to obtain the target relationship pair set includes: Cyclic incrementing of the relationship pairs in the new relationship pair set, and after each round of incrementing, extracting family relationship information of which members have not been added from the new relationship pair set; When a new relationship pair cannot be generated, stop looping and get the current relationship pair set; The target relationship pair set is generated based on the current relationship pair set and the family relationship information.

6. The method for constructing a family relationship network according to any one of claims 1 to 5, characterized in that: The family relationship pairs in the to-be-processed insurance policy data are cleaned to obtain an initial relationship pair set, including: According to the uniqueness of the customer number, the repeated family relationship pairs in the to-be-processed insurance policy data are removed to obtain a first processing relationship pair set; According to gender consistency, the husband-wife relationship pairs with the same gender in the first processing relationship pair set are deleted to obtain a second processing relationship pair set; According to the age and generation relationship, the wrong relationship pairs in the second processing relationship pair set are identified, and the wrong relationship pairs are deleted to obtain the initial relationship pair set.

7. The method for constructing a family relationship network according to any one of claims 1 to 5, characterized in that: The step of extracting all persons and person relationships belonging to the same family according to the target relationship pair set and generating a family information record includes: Using a connected component identification algorithm to identify each household connected component based on the target relationship pair set; Constructing a unique home number for each of the home connectivity components; The personnel and personnel relationships of each family number are extracted from the target relationship pair set to generate the family information record.

8. A device for constructing a family relationship network, characterized in that: include: A policy data acquisition unit, used to acquire policy data to be processed; A relationship pair cleaning unit, used for cleaning the family relationship pairs in the to-be-processed insurance policy data to obtain an initial relationship pair set; A relationship pair expansion unit, configured to expand the relationship pairs based on the initial relationship pair set by using a connectivity graph algorithm to obtain a target relationship pair set; The family information recording unit is used to extract all persons and person relationships belonging to the same family according to the target relationship pair set, and generate a family information record.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the method for constructing a family relationship network as claimed in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for constructing a family relationship network according to any one of claims 1 to 7 is implemented.

Images