Claim Self-Check Rule Recommendation Method, Device, Electronic Device and Storage Medium

Abstract

The present invention relates to the technical field of data processing, and also relates to the technical field of artificial intelligence. In particular, it relates to a claim self-verification rule recommendation method, device, electronic device and storage medium. Obtain a claim self-verification rule scenario factor configuration table; obtain multiple claim rule information in a newly uploaded product requirement document, match the claim rule information with the rule factors in the configuration table, and use the rule factors that match the claim rule information as the characteristic values of the claim rule information; obtain the data pool of the product requirement document, wherein the data pool includes target liability items and characteristic data of each target liability item, and the characteristic data includes the characteristic values of each claim rule information that matches the corresponding target liability item; obtain self-verification recommendation items from the data pool according to the characteristic data; through the above method, the technical problems of incomplete and inaccurate acquisition of mandatory claim liability items caused by manual analysis to obtain mandatory claim liability items in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and also relates to the technical field of artificial intelligence, and particularly relates to a claim self-verification rule recommendation method, device, electronic device and storage medium. Background Art

[0002] Insurance companies generally have many products, and each new product needs to be tested before going online. To speed up the product launch speed, before testing, testers need to analyze the product requirement document, manually compare the claim rules defined in the product requirement document with the liability items defined in the claim self-verification rules, and find out the claim liability items that must be covered by the test scenarios. Since it is manual analysis and comparison, it not only takes a long time and wastes human resources, but also there are significant differences in the experience, ability, etc. of different testers, resulting in omissions or errors in the key scenarios that need to be tested for new products, thus affecting the product launch plan. Since there are many liability items in the claim self-verification rules, if all test scenarios are covered, a large amount of data needs to be generated in batches to cover all rule scenarios, which takes even longer and seriously affects the product launch.

[0003] Therefore, there is an urgent need for a claim self-verification rule recommendation method that can quickly and batch recommend the claim liability items that must be tested. Summary of the Invention

[0004] The purpose of the present invention is to provide a claim self-verification rule recommendation method, device, electronic device and storage medium, which can quickly, accurately and batch recommend the claim liability items that must be tested, so as to solve the technical problems of long time consumption, incomplete and inaccurate acquisition of the claim liability items that must be tested caused by manual analysis in the prior art.

[0005] The technical solution of the present invention is as follows: A claim self-verification rule recommendation method is provided, including:

[0006] Obtain a claim self-verification rule scenario factor configuration table, where the configuration table includes multiple rule factors and the weight value of each rule factor;

[0007] Obtain multiple claim rule information in the newly uploaded product requirement document, match the claim rule information with the rule factors in the configuration table, and use the rule factors that match the claim rule information as the characteristic values of the claim rule information;

[0008] Obtain the claim self-verification rules corresponding to the newly uploaded product requirement document, match the claim rule information with the liability items in the claim self-verification rules to obtain the data pool of the product requirement document, where the data pool includes target liability items and characteristic data of each target liability item, the target liability items match at least one claim rule information, and the characteristic data includes the characteristic values of each claim rule information matching the corresponding target liability item;

[0009] Obtain the target liability items that meet the recommendation rules from the data pool according to the characteristic data as the self-verification recommendation items.

[0010] As an optional implementation manner, the obtaining the claim self-verification rule scenario factor configuration table includes:

[0011] Obtain a batch of product requirement documents and the claim self-verification rules corresponding to each product requirement document;

[0012] Compare the product requirement document and the claim self-verification rules corresponding to the product requirement document to obtain the rule factors that exist in both the product requirement document and the claim self-verification rules;

[0013] Configure corresponding weight values for each rule factor according to preset rules;

[0014] Generate a claim self-verification rule scenario factor configuration table according to the rule factors and the weight values corresponding to each rule factor.

[0015] As an optional implementation manner, before forming the configuration table, it further includes: extracting the attributes of each rule factor according to the product requirement document and the corresponding claim self-verification rules, and the attributes of the rule factors are general or special.

[0016] As an optional implementation manner, the matching the claim rule information with the liability items in the claim self-verification rules to obtain the data pool of the product requirement document includes:

[0017] Input the claim rule information and the claim self-verification rules into the trained self-verification configuration rule model, and output the target liability items matching the claim rule information;

[0018] Obtain the data pool according to the target liability items matching the claim rule information and the characteristic values of the claim rule information.

[0019] As an optional implementation manner, in the matching of the claim rule information with the rule factors in the configuration table, each claim rule information matches one rule factor and the rule factors matched by each claim rule information are different from each other.

[0020] As an optional implementation, obtaining, from the data pool according to the feature data, the target liability items that meet the recommendation rules as self-verification recommendation items includes:

[0021] Sorting the feature values in descending order of the rule factor weight values to obtain the first feature value to the Nth feature value;

[0022] Obtaining all the target liability items in the data pool that have the first feature value and merging them into a first recommendation group, taking the target liability item with the most feature values in the first recommendation group as the first self-verification recommendation item, and deleting the target liability item that is the first self-verification recommendation item from the data pool;

[0023] Obtaining all the target liability items in the data pool that have the second feature value and merging them into a second recommendation group, taking the target liability item with the most feature values in the second recommendation group as the second self-verification recommendation item, and deleting the target liability item that is the second self-verification recommendation item from the data pool;

[0024] Repeating the above steps until all the target liability items in the data pool that have the Nth feature value are obtained and merged into an Nth recommendation group, and taking the target liability item with the most feature values in the Nth recommendation group as the Nth self-verification recommendation item.

[0025] As an optional implementation, before taking the target liability item with the most feature values in the first recommendation group as the first self-verification recommendation item, it further includes:

[0026] Using the merge sort algorithm to sort the target liability items included in the first recommendation group to obtain the target liability item with the most feature values in the first recommendation group;

[0027] Correspondingly, before taking the target liability item with the most feature values in the second recommendation group as the second self-verification recommendation item, it further includes:

[0028] Using the merge sort algorithm to sort the target liability items included in the second recommendation group to obtain the target liability item with the most feature values in the second recommendation group;

[0029] Correspondingly, before taking the target liability item with the most feature values in the Nth recommendation group as the Nth self-verification recommendation item, it further includes:

[0030] Using the merge sort algorithm to sort the target liability items included in the Nth recommendation group to obtain the target liability item with the most feature values in the Nth recommendation group.

[0031] Another technical solution of the present invention is as follows: Provide a claim self-review rule recommendation device, including:

[0032] A configuration table acquisition module, configured to acquire a claim self-review rule scenario factor configuration table, where the configuration table includes multiple rule factors and the weight value of each rule factor;

[0033] A claim rule information and its eigenvalue acquisition module, configured to acquire multiple claim rule information in a newly uploaded product requirement document, match the claim rule information with the rule factors in the configuration table, and use the rule factors that match the claim rule information as the eigenvalues of the claim rule information;

[0034] A liability item and its characteristic data acquisition module, configured to acquire the claim self-review rule corresponding to the newly uploaded product requirement document, match the claim rule information with the liability items in the claim self-review rule to obtain the data pool of the product requirement document, where the data pool includes target liability items and the characteristic data of each target liability item, the target liability item matches at least one claim rule information, and the characteristic data includes the eigenvalues of each claim rule information that matches the corresponding target liability item;

[0035] A self-review recommendation item acquisition module, configured to acquire the target liability items that meet the recommendation rules from the data pool according to the characteristic data as self-review recommendation items.

[0036] Another technical solution of the present invention is as follows: Provide an electronic device, including a processor and a memory coupled to the processor, where the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the above-mentioned claim self-review rule recommendation method is implemented.

[0037] Another technical solution of the present invention is as follows: Provide a storage medium, where program instructions are stored in the storage medium, and when the program instructions are executed by a processor, the above-mentioned claim self-review rule recommendation method is implemented.

[0038] The method, device, electronic device and storage medium for recommending claims self-verification rules of the present invention obtain a claims self-verification rule scenario factor configuration table, wherein the configuration table includes multiple rule factors and weight values ​​of each rule factor; obtain multiple claims rule information in a newly uploaded product requirement document, match the claims rule information with the rule factors in the configuration table, and use the rule factors matching the claims rule information as feature values ​​of the claims rule information; obtain the claims self-verification rule corresponding to the newly uploaded product requirement document, match the claims rule information with the responsibility items in the claims self-verification rule, and obtain a data pool of the product requirement document, wherein the data pool includes target responsibility items and feature data of each target responsibility item. The target responsibility item matches at least one of the claims rule information, and the characteristic data includes a characteristic value of each of the claims rule information matching the corresponding target responsibility item; the target responsibility item that meets the recommendation rule is obtained from the data pool according to the characteristic data as a self-verification recommendation item; through the above method, the required claims responsibility items, namely the self-verification recommendation items, can be recommended quickly, accurately and in batches, and the tester can make targeted data coverage test scenarios according to the self-verification recommendation items, which solves the technical problems of long time caused by manual analysis to obtain the required claims responsibility items and incomplete and inaccurate acquisition of the required claims responsibility items in the prior art, and the recommendation of specific claims self-verification rules for each product can be realized by adjusting the weight value of the rule factor according to the product functions and characteristics. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flowchart of a method for recommending claims self-verification rules according to a first embodiment of the present invention;

[0040] Figure 2 It is a structural schematic diagram of a claim settlement self-verification rule recommendation device according to a second embodiment of the present invention;

[0041] Figure 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention;

[0042] Figure 4 FIG. 4 is a schematic diagram of the structure of a storage medium according to a fourth embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] The terms "first", "second", and "third" in the present invention are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", and "third" may explicitly or implicitly include at least one of such features. In the description of the present invention, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative positional relationship, movement conditions, etc. between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will also change accordingly. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0045] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0046] Figure 1 is a schematic flowchart of the claim self-verification rule recommendation method according to the first embodiment of the present invention. It should be noted that if there are substantially the same results, the claim self-verification rule recommendation method of the present invention is not limited to Figure 1 the shown process sequence. As Figure 1 shown, the claim self-verification rule recommendation method includes steps S101 to S104:

[0047] S101, obtain a claim self-verification rule scenario factor configuration table, where the configuration table includes a plurality of rule factors and the weight value of each rule factor.

[0048] In some alternative embodiments, the obtaining of the claim self-verification rule scenario factor configuration table includes: obtaining a batch of product requirement documents and the claim self-verification rules corresponding to each of the product requirement documents;

[0049] Compare the product requirement documents with the claim self-verification rules corresponding to the product requirement documents to obtain the rule factors that exist in both the product requirement documents and the claim self-verification rules;

[0050] Configure corresponding weight values for each of the rule factors according to preset rules;

[0051] Generate a claim self-review rule scenario factor configuration table based on the rule factors and the corresponding weight values for each of the rule factors. In this embodiment, the claim rule information includes: for example, information related to the total insured amount, information related to the critical illness insurance benefit, information related to the mild illness insurance benefit, information related to the deductible, information related to the insured area, etc. Specifically, such as "the deductible is 10,000 yuan" and "the insured area is limited to Guangdong Province".

[0052] In this embodiment, the configuration table records all the extracted rule factors and the weight values of each rule factor. In some alternative embodiments, the value range of the weight value is 0 - 100. The weight values of the rule factors are configured manually, and the weight values of each rule factor can be set and adjusted by testers according to the product functions and characteristics.

[0053] In some alternative embodiments, before forming the configuration table, it further includes: extracting the attributes of each rule factor according to the product requirement document and the corresponding claim self-review rules, and the attributes of the rule factors are general or special. Correspondingly, the configuration table records all the extracted rule factors, the weight values of each rule factor, and the attributes of each rule factor.

[0054] In a more specific embodiment, after obtaining a batch of product requirement documents and the claim self-review rules corresponding to each of the product requirement documents, obtain all the claim rule information from each product requirement document, compare the claim rule information in the product requirement document with the claim self-review rules corresponding to the product requirement document one by one, obtain all the general rule liability items related to claims and all the special rule liability items related to claims in the claim self-review rules, and obtain the rule factors corresponding to the claim rule information and the attributes of each rule factor from the obtained general rule liability items and special rule liability items, and then set the corresponding weight values for each rule factor. For example, the configuration table contains the following information: "total insured amount, general 1, 50" (the rule factor is "total insured amount", the attribute of the rule factor is "general 1", and the weight value of the rule factor is "50"); "specific medical insurance benefit, special 2, 90" (the rule factor is "specific medical insurance benefit", the attribute of the rule factor is "special 2", and the weight value of the rule factor is "90"); "deductible, general 5, 60" (the rule factor is "deductible", the attribute of the rule factor is "general 5", and the weight value of the rule factor is "60"); "insured area, special 7, 70" (the rule factor is "insured area", the attribute of the rule factor is "special 7", and the weight value of the rule factor is "70").

[0055] S102. Obtain all claim settlement rule information in the newly uploaded product requirement document, match the claim settlement rule information with the rule factors in the configuration table, and use the rule factors that match the claim settlement rule information as the characteristic values of the claim settlement rule information.

[0056] In this embodiment, in the process of matching the claim settlement rule information with the rule factors in the configuration table, each claim settlement rule information is matched with one rule factor, and the rule factors matched by each claim settlement rule information in the same product requirement document are different. For example, if there are 20 claim settlement rule information in a product requirement document, then these 20 claim settlement rule information will be matched with 20 different rule factors in total.

[0057] S103. Obtain the claim self-verification rule corresponding to the newly uploaded product requirement document, match the claim settlement rule information with the liability items in the claim self-verification rule to obtain the data pool of the product requirement document, where the data pool includes target liability items and characteristic data of each target liability item, the target liability item is matched with at least one claim settlement rule information, and the characteristic data includes the characteristic values of each claim settlement rule information that matches the corresponding target liability item.

[0058] In some alternative embodiments, the process of matching the claim settlement rule information with the liability items in the claim self-verification rule to obtain the data pool of the product requirement document includes steps S201 to S202:

[0059] S201. Input the claim settlement rule information in the newly uploaded product requirement document and the claim self-verification rule corresponding to the newly uploaded product requirement document into the trained self-verification configuration rule model, and output the target liability items that match the claim settlement rule information.

[0060] S202. Obtain the data pool according to the target liability items matched by the claim settlement rule information and the characteristic values of the claim settlement rule information.

[0061] S104. Obtain the target liability items that meet the recommendation rules from the data pool according to the characteristic data, and use them as self-verification recommendation items.

[0062] In some preferred embodiments, step S104 specifically includes steps S301 to S304:

[0063] S301. Sort the characteristic values in descending order of the rule factor weight values to obtain the first characteristic value to the Nth characteristic value;

[0064] S302. Obtain all the target liability items in the data pool that have the first eigenvalue, merge them into a first recommended group, take the target liability item with the most eigenvalues in the first recommended group as the first self-check recommended item, and delete the target liability item that is the first self-check recommended item from the data pool;

[0065] S303. Obtain all the target liability items in the data pool that have the second eigenvalue, merge them into a second recommended group, take the target liability item with the most eigenvalues in the second recommended group as the second self-check recommended item, and delete the target liability item that is the second self-check recommended item from the data pool;

[0066] S304. Repeat the above steps until all the target liability items in the data pool that have the Nth eigenvalue are obtained and merged into the Nth recommended group, and take the target liability item with the most eigenvalues in the Nth recommended group as the Nth self-check recommended item.

[0067] In some more preferred embodiments, in step S302, before taking the target liability item with the most eigenvalues in the first recommended group as the first self-check recommended item, it further includes:

[0068] Use the merge sort algorithm to sort the target liability items included in the first recommended group, and obtain the target liability item with the most eigenvalues in the first recommended group;

[0069] Correspondingly, in step S303, before taking the target liability item with the most eigenvalues in the second recommended group as the second self-check recommended item, it further includes:

[0070] Use the merge sort algorithm to sort the target liability items included in the second recommended group, and obtain the target liability item with the most eigenvalues in the second recommended group;

[0071] Correspondingly, in step S304, before taking the target liability item with the most eigenvalues in the Nth recommended group as the Nth self-check recommended item, it further includes:

[0072] Use the merge sort algorithm to sort the target liability items included in the Nth recommended group, and obtain the target liability item with the most eigenvalues in the Nth recommended group.

[0073] For example, in a specific embodiment, step S104 includes:

[0074] First, obtain all the eigenvalues included in the feature data of all the target liability items in the data pool, and then sort all the obtained eigenvalues in descending order according to the rule factor weight value to obtain the first eigenvalue to the tenth eigenvalue.

[0075] Then, after obtaining all the target liability items in the data pool whose characteristic data includes the first eigenvalue and merging them into the first recommendation group, the merge sort algorithm is used to sort the target liability items in the first recommendation group, so that the target liability items in the first recommendation group are sorted according to the number of eigenvalues included in the characteristic data of the target liability items. Among them, the target liability item with the largest number of eigenvalues included in the characteristic data (i.e., the target liability item corresponding to the largest number of claim settlement rule information) is ranked first. This target liability item ranked first is the first self-verification recommendation item, and the target liability item serving as the first self-verification recommendation item is deleted from the data pool. For example, there are 5 target liability items in the first recommendation group, namely target liability item A, target liability item B, target liability item C, target liability item D, and target liability item E. Target liability item A corresponds to 3 claim settlement rule information, target liability item B corresponds to 2 claim settlement rule information, target liability item C corresponds to 4 claim settlement rule information, target liability item D corresponds to 5 claim settlement rule information, and target liability item E corresponds to 1 claim settlement rule information. After sorting the 5 target liability items in the first recommendation group, target liability item D is ranked first, that is, target liability item D is the first self-verification recommendation item.

[0076] Then, after obtaining all the target liability items in the data pool whose characteristic data includes the second eigenvalue and merging them into the second recommendation group, the merge sort algorithm is used to sort the target liability items in the second recommendation group, so that the target liability items in the second recommendation group are sorted according to the number of eigenvalues included in the characteristic data of the target liability items. Among them, the target liability item with the largest number of eigenvalues included in the characteristic data (i.e., the target liability item corresponding to the largest number of claim settlement rule information) is ranked first. This target liability item ranked first is the second self-verification recommendation item, and the target liability item serving as the second self-verification recommendation item is deleted from the data pool.

[0077] Then, after obtaining all the target liability items in the data pool whose characteristic data includes the third eigenvalue and merging them into the third recommendation group, the merge sort algorithm is used to sort the target liability items in the third recommendation group, so that the target liability items in the third recommendation group are sorted according to the number of eigenvalues included in the characteristic data of the target liability items. Among them, the target liability item with the largest number of eigenvalues included in the characteristic data (i.e., the target liability item corresponding to the largest number of claim settlement rule information) is ranked first. This target liability item ranked first is the third self-verification recommendation item, and the target liability item serving as the third self-verification recommendation item is deleted from the data pool.

[0078] By analogy, until all the target liability items in the data pool whose characteristic data includes the tenth eigenvalue are obtained and merged into the tenth recommendation group, the merge sort algorithm is used to sort the target liability items in the tenth recommendation group, so that the target liability items in the tenth recommendation group are sorted according to the number of eigenvalues included in the characteristic data of the target liability items. Among them, the target liability item with the largest number of eigenvalues included in the characteristic data (that is, the target liability item corresponding to the largest number of claim settlement rule information) is ranked first, and the target liability item ranked first is the tenth self-verification recommendation item.

[0079] The claim settlement self-verification rule recommendation method in this embodiment can quickly, accurately, and batch recommend the required claim settlement liability items, that is, the self-verification recommendation items. Testers can perform data coverage test scenarios based on the self-verification recommendation items. It solves the technical problems of incomplete and inaccurate acquisition of the required claim settlement liability items caused by manual analysis to obtain the required claim settlement liability items in the prior art, and is significantly helpful for shortening the test time of new products launched and improving the test quality. Moreover, testers can adjust the weight values of the rule factors according to the product functions and characteristics to realize the recommendation of specific claim settlement self-verification rules for each product.

[0080] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0081] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0082] Figure 2 It is a schematic structural diagram of the claim settlement self-verification rule recommendation device according to the second embodiment of the present invention. The claim settlement self-verification rule recommendation device 20 corresponds one-to-one with the claim settlement self-verification rule recommendation method in the above embodiment. As Figure 2As shown, the claim self-verification rule recommendation device 20 includes a configuration table acquisition module 21, a claim rule information and its eigenvalue acquisition module 22, a liability item and its characteristic data acquisition module 23, and a self-verification recommendation item acquisition module 24. Among them, the configuration table acquisition module 21 is used to acquire the claim self-verification rule scenario factor configuration table, and the configuration table includes multiple rule factors and the weight value of each rule factor. The claim rule information and its eigenvalue acquisition module 22 is used to acquire multiple claim rule information in the newly uploaded product requirement document, match the claim rule information with the rule factors in the configuration table, and use the rule factors that match the claim rule information as the eigenvalues of the claim rule information. The liability item and its characteristic data acquisition module 23 is used to acquire the claim self-verification rule corresponding to the newly uploaded product requirement document, match the claim rule information with the liability items in the claim self-verification rule, and obtain the data pool of the product requirement document. Among them, the data pool includes target liability items and the characteristic data of each target liability item. The target liability item matches at least one of the claim rule information, and the characteristic data includes the eigenvalues of each claim rule information that matches the corresponding target liability item. The self-verification recommendation item acquisition module 24 is used to acquire the target liability items that meet the recommendation rules from the data pool according to the characteristic data as the self-verification recommendation items.

[0083] In an optional implementation manner, in the configuration table acquisition module 21, the acquisition of the claim self-verification rule scenario factor configuration table includes:

[0084] Acquire a batch of product requirement documents and the claim self-verification rules corresponding to each product requirement document;

[0085] Compare the product requirement document with the claim self-verification rule corresponding to the product requirement document, and acquire the rule factors that exist in both the product requirement document and the claim self-verification rule;

[0086] Configure the corresponding weight value for each rule factor according to the preset rule;

[0087] Generate a claim self-verification rule scenario factor configuration table according to the rule factors and the weight value corresponding to each rule factor.

[0088] In some optional implementation manners, in the configuration table acquisition module 21, before forming the configuration table, it further includes: extracting the attributes of each rule factor according to the product requirement document and the corresponding claim self-verification rule, and the attribute of the rule factor is general or special.

[0089] In an alternative embodiment, in the claim settlement rule information and its eigenvalue acquisition module 22, in the process of matching the claim settlement rule information with the rule factors in the configuration table, each claim settlement rule information is matched with one rule factor and the rule factors matched by each claim settlement rule information are different from each other.

[0090] In some alternative embodiments, in the liability item and its characteristic data acquisition module 23, in the process of matching the claim settlement rule information with the liability items in the claim settlement self-verification rules to obtain the data pool of the product requirement document, it includes:

[0091] Input the claim settlement rule information and the claim settlement self-verification rules into the trained self-verification configuration rule model, and output the target liability items that match the claim settlement rule information;

[0092] Obtain the data pool according to the target liability items matched by the claim settlement rule information and the eigenvalues of the claim settlement rule information.

[0093] In some preferred embodiments, in the self-verification recommendation item acquisition module 24, in the process of obtaining the target liability items that meet the recommendation rules from the data pool according to the characteristic data as self-verification recommendation items, it includes:

[0094] Sort the eigenvalues in descending order of the rule factor weight values to obtain the first eigenvalue to the Nth eigenvalue;

[0095] Obtain all the target liability items in the data pool that have the first eigenvalue and merge them into the first recommendation group, take the target liability item with the most eigenvalues in the first recommendation group as the first self-verification recommendation item, and delete the target liability item that is used as the first self-verification recommendation item from the data pool;

[0096] Obtain all the target liability items in the data pool that have the second eigenvalue and merge them into the second recommendation group, take the target liability item with the most eigenvalues in the second recommendation group as the second self-verification recommendation item, and delete the target liability item that is used as the second self-verification recommendation item from the data pool;

[0097] Repeat the above steps until all the target liability items in the data pool that have the Nth eigenvalue are obtained and merged into the Nth recommendation group, and take the target liability item with the most eigenvalues in the Nth recommendation group as the Nth self-verification recommendation item.

[0098] In some more specific embodiments, in the self-verification recommendation item acquisition module 24, before taking the target liability item with the most eigenvalues in the first recommendation group as the first self-verification recommendation item, it further includes:

[0099] Use the merge sort algorithm to sort the target liability items included in the first recommendation group, and obtain the target liability item with the most eigenvalues in the first recommendation group;

[0100] Correspondingly, before using the target liability item with the most eigenvalues in the second recommendation group as the second self-audit recommendation item, it further includes:

[0101] Use the merge sort algorithm to sort the target liability items included in the second recommendation group, and obtain the target liability item with the most eigenvalues in the second recommendation group;

[0102] Correspondingly, before using the target liability item with the most eigenvalues in the Nth recommendation group as the Nth self-audit recommendation item, it further includes:

[0103] Use the merge sort algorithm to sort the target liability items included in the Nth recommendation group, and obtain the target liability item with the most eigenvalues in the Nth recommendation group.

[0104] Figure 3 It is a schematic structural diagram of the electronic device according to the third embodiment of the present invention. As Figure 3 shown, the electronic device 30 includes a processor 31 and a memory 32 coupled to the processor 31. The memory 32 stores program instructions for implementing the method according to any one of the above embodiments. When the processor 31 executes the program instructions stored in the memory 32, it implements the steps of the claim self-audit rule recommendation method in the above embodiments. For example Figure 1 the steps S101 to S104 shown, and the extensions and extensions of other related steps of the method. Or, when the processor 31 executes the program instructions stored in the memory 32, it implements the functions of each module / unit of the claim self-audit rule recommendation device in the above embodiments. For example Figure 2 the functions of the configuration table acquisition module 21, the claim rule information and its eigenvalue acquisition module 22, the liability item and its feature data acquisition module 23, and the self-audit recommendation item acquisition module 24 shown. To avoid repetition, it will not be elaborated here.

[0105] The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the computer device, connecting various parts of the entire computer device using various interfaces and lines.

[0106] The memory can be used to store the computer program and / or modules. The processor realizes various functions of the computer device by running or executing the computer program and / or modules stored in the memory, and by calling the data stored in the memory. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, video data, etc.).

[0107] The memory can be integrated in the processor or can be separately provided from the processor.

[0108] Refer to Figure 4 , Figure 4 , which is a schematic structural diagram of the storage medium according to the fourth embodiment of the present invention. The storage medium 40 of the embodiment of the present invention stores program instructions 41 that can implement all the above methods. When the program instructions 41 are executed by the processor, the steps of the claim self-verification rule recommendation method in the above embodiments are implemented. For example Figure 1 the steps S101 to S104 shown, and the extension of other extended and related steps of the method. Or, when the program instructions 41 are executed by the processor, the functions of each module / unit of the claim self-verification rule recommendation device in the above embodiments are implemented. For example Figure 2 the functions of the configuration table acquisition module 21, the claim rule information and its eigenvalue acquisition module 22, the liability item and its characteristic data acquisition module 23, and the self-verification recommendation item acquisition module 24 shown. To avoid repetition, it will not be elaborated here.

[0109] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0110] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, indirect couplings or communication connections of devices or units, and can be in electrical, mechanical, or other forms.

[0111] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units. The above are only the implementation manners of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

[0112] The above are only the embodiments of the present invention. It should be noted here that for those of ordinary skill in the art, improvements can be made without departing from the inventive concept of the present invention, but these all fall within the protection scope of the present invention.

Claims

1. A claim self-verification rule recommendation method, characterized in that, Including: Obtain the claim self-verification rule scenario factor configuration table, where the configuration table includes multiple rule factors and the weight value of each rule factor; Obtain multiple claim rule information in the newly uploaded product requirement document, match the claim rule information with the rule factors in the configuration table, and use the rule factors that match the claim rule information as the characteristic values of the claim rule information; Obtain the claim self-verification rule corresponding to the newly uploaded product requirement document, match the claim rule information with the liability items in the claim self-verification rule to obtain the data pool of the product requirement document, where the data pool includes target liability items and the characteristic data of each target liability item, the target liability item matches at least one claim rule information, and the characteristic data includes the characteristic values of each claim rule information that matches the corresponding target liability item; Obtain the target liability items that meet the recommendation rules from the data pool according to the characteristic data as the self-verification recommendation items.

2. The claim settlement self-verification rule recommendation method according to claim 1, wherein The obtaining of the claim self-verification rule scenario factor configuration table includes: Obtain a batch of product requirement documents and the claim self-verification rules corresponding to each product requirement document; Compare the product requirement document with the claim self-verification rule corresponding to the product requirement document to obtain the rule factors that exist in both the product requirement document and the claim self-verification rule; Configure the corresponding weight value for each rule factor according to the preset rule; Generate a claim self-verification rule scenario factor configuration table according to the rule factors and the weight value corresponding to each rule factor.

3. The claim settlement self-verification rule recommendation method according to claim 2, wherein Before forming the configuration table, it also includes: extracting the attributes of each rule factor according to the product requirement document and the corresponding claim self-verification rule, and the attributes of the rule factor are general or special.

4. The claim settlement self-verification rule recommendation method according to claim 1, wherein The matching of the claim rule information with the liability items in the claim self-verification rule to obtain the data pool of the product requirement document includes: Input the claim rule information and the claim self-verification rule into the trained self-verification configuration rule model to output the target liability items that match the claim rule information; Obtain the data pool according to the target liability items that match the claim rule information and the characteristic values of the claim rule information.

5. The claim settlement self-verification rule recommendation method according to claim 1, wherein In the matching of the claim rule information with the rule factors in the configuration table, each claim rule information matches one rule factor and the rule factors matched by each claim rule information are different from each other.

6. The claim settlement self-verification rule recommendation method according to claim 5, wherein The obtaining of the target liability items that meet the recommendation rules from the data pool according to the characteristic data as the self-verification recommendation items includes: Sort the characteristic values in descending order of the weight value of the rule factor to obtain the first characteristic value to the Nth characteristic value; Obtain all the target liability items in the data pool that have the first characteristic value and merge them into the first recommendation group, use the target liability item with the most characteristic values in the first recommendation group as the first self-verification recommendation item, and delete the target liability item that is used as the first self-verification recommendation item from the data pool; Obtain all the target liability items with the second eigenvalue in the data pool and merge them into a second recommendation group. Take the target liability item with the most eigenvalues in the second recommendation group as the second self-verification recommendation item, and delete the target liability item that is the second self-verification recommendation item from the data pool; Repeat the above steps until all the target liability items with the Nth eigenvalue in the data pool are obtained and merged into the Nth recommendation group. Take the target liability item with the most eigenvalues in the Nth recommendation group as the Nth self-verification recommendation item.

7. The claim settlement self-verification rule recommendation method according to claim 6, wherein Before taking the target liability item with the most eigenvalues in the first recommendation group as the first self-verification recommendation item, it further includes: Using the merge sort algorithm to sort the target liability items included in the first recommendation group, and obtain the target liability item with the most eigenvalues in the first recommendation group; Correspondingly, before taking the target liability item with the most eigenvalues in the second recommendation group as the second self-verification recommendation item, it further includes: Using the merge sort algorithm to sort the target liability items included in the second recommendation group, and obtain the target liability item with the most eigenvalues in the second recommendation group; Correspondingly, before taking the target liability item with the most eigenvalues in the Nth recommendation group as the Nth self-verification recommendation item, it further includes: Using the merge sort algorithm to sort the target liability items included in the Nth recommendation group, and obtain the target liability item with the most eigenvalues in the Nth recommendation group.

8. A claim self-verification rule recommendation device, characterized in that, It includes: A configuration table acquisition module, configured to acquire a claim self-verification rule scenario factor configuration table, where the configuration table includes multiple rule factors and the weight value of each rule factor; A claim rule information and its eigenvalue acquisition module, configured to acquire multiple claim rule information in a newly uploaded product requirement document, match the claim rule information with the rule factors in the configuration table, and use the rule factor that matches the claim rule information as the eigenvalue of the claim rule information; A liability item and its characteristic data acquisition module, configured to acquire the claim self-verification rule corresponding to the newly uploaded product requirement document, match the claim rule information with the liability items in the claim self-verification rule to obtain the data pool of the product requirement document, where the data pool includes target liability items and the characteristic data of each target liability item, the target liability item matches at least one claim rule information, and the characteristic data includes the eigenvalues of each claim rule information that matches the corresponding target liability item; A self-verification recommendation item acquisition module, configured to obtain the target liability items that meet the recommendation rules from the data pool according to the characteristic data as self-verification recommendation items.

9. An electronic device, characterized in that, It includes a processor and a memory coupled to the processor, where the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, it implements the claim self-verification rule recommendation method according to any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores program instructions, and when the program instructions are executed by a processor, the claim settlement self-verification rule recommendation method described in any one of claims 1 to 7 is implemented.

Images