Intelligent claims settlement method, device, computer equipment and storage medium

Abstract

The present invention discloses an intelligent claims settlement method, which is applied to the field of data processing and is used to improve claims settlement efficiency. The method provided by the present invention includes: obtaining user information and insurance information, building an insurance association network, querying user reimbursable drugs in a preset drug knowledge base based on the insurance association network, generating a candidate drug list, and when receiving a user's drug purchase request, based on a drug purchase recommendation model and user operation records, performing recommendation processing on historical drug purchase records and the candidate drug list, obtaining a drug recommendation purchase list and sending the drug recommendation purchase list to a client, performing drug purchase processing and generating a corresponding claim request according to a drug purchase selection result fed back by the client based on the drug recommendation purchase list, identifying a claim type for the claim request, determining a claim type, obtaining a preset claim rule from the insurance association network based on the claim type, and performing insurance claims based on the preset claim rule.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to an intelligent claims settlement method, device, computer equipment and storage medium. Background Art

[0002] As people pay more and more attention to health, more and more people buy insurance. The existing drug insurance claim method allows the insurance claim process to be started when the user finishes purchasing the medicine. However, the user needs to hold relevant invoices and other information issued by the pharmacy for on-site insurance claim review. The insurance claim needs to be verified by the claims adjuster. After the verification is successful, the claim process is initiated. When the claim process is passed, the insurance company will pay the user's claim after approval.

[0003] Among the existing methods, it is common to streamline the claims process through artificial intelligence algorithms. However, due to the many problems in the claims process, a lot of manpower is still required, and the claims application method is relatively simple. When facing multi-demand claims scenarios, the existing methods do not have good adaptability and scalability, resulting in multi-demand claims scenarios still relying mainly on manpower for judgment and review. In addition, due to the wide variety of current drugs, they are updated quickly, and in many cases the names of drugs only differ by a few words, which users are unaware of. Due to information asymmetry, various claims failures are likely to occur.

[0004] Therefore, the existing method of drug insurance claims settlement suffers from the problem of over-reliance on manpower and low claims efficiency caused by information asymmetry. Summary of the invention

[0005] Embodiments of the present invention provide an intelligent claims settlement method, apparatus, computer equipment and storage medium to improve claims settlement efficiency.

[0006] An intelligent claims settlement method, comprising:

[0007] Obtain user information and insurance information to build an insurance association network, where user information includes historical drug purchase records;

[0008] Based on the insurance association network, query the user's reimbursable drugs in a preset drug knowledge base to generate a list of candidate drugs;

[0009] When receiving a user's drug purchase request, based on the drug purchase recommendation model and the user's operation record, the historical drug purchase record and the candidate drug list are recommended to obtain a drug purchase recommendation list and send the drug purchase recommendation list to the client, wherein the user operation record is the operation record information stored by the server within a preset time period;

[0010] According to the drug purchase selection result fed back by the client based on the drug recommendation purchase list, drug purchase processing is performed and a corresponding claim request is generated;

[0011] Identify the claim type of the claim request and determine the claim type;

[0012] Based on the claim type, a preset claim rule is obtained from the insurance association network, and an insurance claim is made based on the preset claim rule.

[0013] An intelligent claims settlement device, comprising:

[0014] An insurance association network construction module is used to obtain user information and insurance information and construct an insurance association network, wherein the user information includes historical drug purchase records;

[0015] A candidate drug list generation module is used to query the user's reimbursable drugs in a preset drug knowledge base based on the insurance association network to generate a candidate drug list;

[0016] The drug recommendation purchase module is used for, when receiving a drug purchase request from a user, recommending the historical drug purchase records and the candidate drug list based on the drug purchase recommendation model and the user operation record, obtaining a drug recommendation purchase list and sending the drug recommendation purchase list to the client, wherein the user operation record is the operation record information stored by the server within a preset time period;

[0017] A claim request acquisition module, used to process drug purchases and generate corresponding claim requests according to the drug purchase selection results fed back by the client based on the drug recommendation purchase list;

[0018] A claim type determination module, used to identify the claim type of the claim request and determine the claim type;

[0019] The claim settlement module is used to obtain preset claim settlement rules from the insurance association network based on the claim settlement type, and to make insurance claims based on the preset claim settlement rules.

[0020] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned intelligent claims settlement method when executing the computer program.

[0021] A computer-readable storage medium stores a computer program, which implements the steps of the above-mentioned intelligent claims settlement method when executed by a processor.

[0022] The intelligent claims method, apparatus, computer equipment and storage medium provided by the embodiments of the present invention obtain user information and insurance information, and construct an insurance association network, wherein the user information includes historical drug purchase records; based on the insurance association network, the user's reimbursable drugs are queried in a preset drug knowledge base to generate a candidate drug list; when a user's drug purchase request is received, based on a drug purchase recommendation model and user operation records, the historical drug purchase records and the candidate drug list are recommended and processed to obtain a recommended drug purchase list and send the recommended drug purchase list to a client, wherein the user operation record is the operation record information stored by the server within a preset time period; according to the drug purchase selection result fed back by the client based on the recommended drug purchase list, drug purchase processing is performed and a corresponding claim request is generated; the claim type is identified for the claim request to determine the claim type; based on the claim type, a preset claim rule is obtained from the insurance association network, and an insurance claim is performed based on the preset claim rule. Through the above steps, users, insurance companies and pharmacies are integrated into the insurance claims system. The insurance claims system can intelligently recommend users to purchase medicines and automatically process claims, and conduct a series of online automated reviews of the claims process, thereby reducing manual processing procedures and improving claims efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0024] Figure 1 is a schematic diagram of an application environment of an intelligent claims settlement method in one embodiment of the present invention;

[0025] Figure 2 is a flow chart of an intelligent claims settlement method in one embodiment of the present invention;

[0026] Figure 3 is a schematic diagram of the structure of an intelligent claims settlement device in one embodiment of the present invention;

[0027] Figure 4 is a schematic diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] 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 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.

[0029] The intelligent claims settlement method provided in this application can be applied in Figure 1 In an application environment, a computer device communicates with a server via a network. The computer device may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server may be implemented as an independent server or a server cluster consisting of multiple servers.

[0030] In one embodiment, if Figure 2 As shown, an intelligent claims settlement method is provided, which is applied in Figure 1 The server in the example is used as an example to illustrate, including the following steps S101 to S106:

[0031] S101. Obtain user information and insurance information and build an insurance association network, wherein the user information includes historical drug purchase records.

[0032] In step S101, the user information refers to information related to the user, including but not limited to user identification, basic user information, location information of the user, information on insurance purchased by the user, information on claims settled by the user, information on pending claims settled by the user, and information on drug purchases by the user. Among them, the user identification refers to the unique identification code of the user when logging in and registering in the insurance claims system, the basic user information includes but is not limited to the user ID information and the user's mobile phone number, and the location information of the user refers to the user's current longitude and latitude position or the selected longitude and latitude position.

[0033] The above insurance information refers to information related to existing insurance content, including but not limited to insurance types, reimbursable drugs, and drug reimbursement ratios. The above insurance information is adaptively modified according to the insurance types promoted by the insurance company.

[0034] The above-mentioned methods for constructing the insurance association network include but are not limited to big data dictionary and keyword matching.

[0035] The insurance claims system obtains user information and insurance information, binds users to the insurance they purchased, and thus builds an insurance association network. Based on the constructed insurance association network, users can clearly view the drugs that can be compensated by the insurance they purchased, which improves the degree of information symmetry between users and insurance, and can effectively solve the problem of low claims efficiency caused by information asymmetry, thereby optimizing user experience and improving claims efficiency.

[0036] S102: Based on the insurance association network, the user's reimbursable drugs are searched in a preset drug knowledge base to generate a list of candidate drugs.

[0037] In step S102, the construction method of the preset drug knowledge base includes but is not limited to a big data dictionary and a knowledge graph. A knowledge graph is a network knowledge base formed by entities with attributes linked by relationships. The knowledge graph is essentially a conceptual network, in which nodes represent entities (or concepts) in the physical world, and various semantic relationships between entities constitute edges in the network.

[0038] Preferably, drugs, insurance, and drug stores are taken as three entities, and knowledge bases with connection relationships are generated based on the relationships between the three entities to obtain a drug knowledge base.

[0039] The above-mentioned list of candidate drugs includes but is not limited to drug price information, drug corresponding pharmacy address information, and drug reimbursement ratio.

[0040] Through the connection between the insurance management network and drugs, all drug information can be stored in the drug knowledge base. When making drug recommendations, drug information can be quickly located through the drug knowledge base, thereby providing users with drug recommendation services efficiently and accurately, improving the speed of drug recommendations, and reducing the probability of claims failure due to drug purchase errors, thereby indirectly improving claims efficiency.

[0041] S103. When a user's request to purchase medicines is received, based on the medicine purchase recommendation model and the user's operation records, the historical medicine purchase records and the candidate medicine list are recommended, and a recommended medicine purchase list is obtained and sent to the client, wherein the user operation record is the operation record information stored by the server within a preset time period.

[0042] In step S103, the above historical purchase records include but are not limited to the user's location information, user preference information, and drug information, wherein the user preference information refers to the indicator field that the user prioritizes, and the indicator field includes but is not limited to the price field and the distance field.

[0043] The above-mentioned client refers to the end where the user performs operations.

[0044] The above-mentioned candidate drug list refers to a list used to store various information of candidate recommended drugs.

[0045] The above-mentioned recommended drug purchase list refers to a list formed by selecting multiple drugs from the candidate drug list that best meet the user's needs and are most likely to be purchased by the user.

[0046] Methods for implementing the above-mentioned drug purchase recommendation model include but are not limited to content-based recommendation algorithms, collaboration-based recommendation algorithms, association-based recommendation algorithms, weighted hybrid recommendation algorithms, and merged hybrid recommendation algorithms.

[0047] Preferably, a weighted hybrid recommendation algorithm is used to implement the above-mentioned drug purchase recommendation model, wherein the weighted hybrid recommendation algorithm refers to an algorithm that generates recommendations by weighted mixing of the calculation results of multiple recommendation technologies. For example, taking price as a recommendation factor, the candidate drug list is sorted to generate a price-priority drug list based on price, and then taking distance as a recommendation factor, the candidate drug list is sorted to generate a distance-priority drug list based on distance, and the user's historical purchase records are combined to obtain user preference information, and different weights are assigned to the price-priority drug list and the distance-priority drug list, and then the corresponding addition is performed to obtain a drug purchase recommendation list.

[0048] By making drug purchase recommendations through the drug purchase recommendation model and user-related information, personalized recommendations can be effectively implemented for individuals, and drug recommendation services can be provided efficiently and accurately to any user, thereby improving the speed of drug recommendations and reducing the probability of claims failure due to drug purchase errors, thereby improving claims efficiency.

[0049] S104: According to the drug purchase selection result fed back by the client based on the drug recommendation purchase list, drug purchase processing is performed and a corresponding claim request is generated.

[0050] The above-mentioned drug purchase selection result refers to the drug purchase recommendation list generated by the drug purchase recommendation model based on which the user purchases drugs suitable for his / her needs. The user can choose to purchase all or part of the drugs on the drug purchase recommendation list.

[0051] The above-mentioned claim request refers to a request related to claim reimbursement for purchased drugs. The form of the claim request includes but is not limited to automatic generation by the backend and active application by the user. Among them, the automatic generation by the backend refers to the claim request generated according to the nature of the purchased drugs after the backend receives the drug purchase selection results fed back by the client and processes the drug purchase.

[0052] After the drug purchase process, a claim request is generated, allowing users to make claims online anytime and anywhere, reducing the time and labor costs brought by offline reimbursement, as well as the corresponding time consumption, speeding up the claims process and thus improving claims efficiency.

[0053] S105: Identify the claim type of the claim request and determine the claim type.

[0054] In step S105, the above-mentioned claim types include but are not limited to direct claim and post-claim. Among them, direct claim refers to the type of claim that can be directly claimed when the user purchases the medicine in the insurance claim system. Post-claim refers to the type of claim that the user does not purchase the medicine in the insurance claim system, but makes after purchasing the medicine elsewhere.

[0055] The above-mentioned method for determining the claim type includes but is not limited to type matching and content query. Among them, the content query method refers to querying whether there is a user purchase record in the insurance claim system. If so, it is directly determined as a direct payment claim. If not, it is determined as a post-claim.

[0056] By first determining the claim type, different claims processes can be effectively selected for different claims scenarios when faced with multiple claims demands, thereby enhancing the adaptability of the insurance claims system without affecting the efficiency of each claims scenario.

[0057] S106. Based on the claim type, obtain preset claim rules from the insurance association network, and make insurance claims based on the preset claim rules.

[0058] In step S106, the above-mentioned preset claim rules refer to the claim rules corresponding to the claim type, and the above-mentioned method for obtaining the preset claim rules includes but is not limited to the type matching method.

[0059] By obtaining preset claims rules and making insurance payments for claim requests of different claim types, the efficiency of insurance claims can be effectively improved in multi-demand claims scenarios.

[0060] The intelligent claims settlement method provided by the embodiment of the present invention obtains user information and insurance information and constructs an insurance association network. Based on the insurance association network, the user's reimbursable drugs are queried in the preset drug knowledge base to generate a candidate drug list. When a user's drug purchase request is received, the historical drug purchase record and the candidate drug list are recommended based on the drug purchase recommendation model and the user operation record to obtain a drug recommendation purchase list and send the drug recommendation purchase list to the client. According to the drug purchase selection result fed back by the client based on the drug recommendation purchase list, the drug purchase process is performed and the corresponding claim request is generated; the claim type is identified for the claim request to determine the claim type. Based on the claim type, the preset claim rules are obtained from the insurance association network, and the insurance claim is made based on the preset claim rules. Through the above steps, the three ends of the user, insurance and pharmacy are integrated into the insurance claim settlement system. The insurance claim settlement system can intelligently recommend users to purchase drugs and automatically settle claims, and perform a series of online automated audits on the claim settlement process. At the same time, information symmetry is achieved, thereby reducing the manual processing process and improving the claim settlement efficiency.

[0061] In some optional implementations of this embodiment, step S101 includes the following steps S1010 to S1012:

[0062] S1010: Obtain user information, and perform keyword extraction on the user information to obtain user keywords.

[0063] S1011. Obtain insurance information, and extract keywords from the insurance information to obtain insurance keywords.

[0064] S1012: Based on user keywords and insurance keywords, user information and insurance information are mapped and processed to construct an insurance association network.

[0065] Regarding the above step S1010, the above user keywords include but are not limited to the policy number purchased by the user and the insurance type number corresponding to the policy.

[0066] For the above step S1011, the above insurance keywords include but are not limited to the insurance type number and the drug information that can be reimbursed by the insurance type.

[0067] By obtaining the insurance type code corresponding to the insurance policy in the user's keyword and mapping it with the insurance type code in the insurance keyword, an insurance association network is constructed.

[0068] In some optional implementations of this embodiment, step S101 includes step S001:

[0069] S001. Save user information to the blockchain network node.

[0070] Through blockchain storage, data information can be shared between different platforms and data can be prevented from being tampered with.

[0071] Blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0072] In some optional implementations of this embodiment, the process before step S102 includes steps S201 to S203:

[0073] S201. Determine the drug attributes based on drug knowledge and insurance policy claim conditions, and use the drug attributes as drug entities.

[0074] S202: Obtain drug information from the pharmacy database.

[0075] S203: Mapping the drug information and the corresponding drug entities to obtain a preset drug knowledge base.

[0076] For the above step S201, the above insurance claim conditions refer to the compensation conditions and corresponding compensation ratios for drugs in different insurance types.

[0077] The above-mentioned drug knowledge refers to knowledge related to drug properties and is used to classify drugs, for example, drugs can be classified into prescription drugs / over-the-counter drugs, oral / external drugs, and diseases treated by drugs.

[0078] The above-mentioned drug attributes include but are not limited to the drug name, drug classification, whether it can be reimbursed under different insurance types, and the reimbursement ratio.

[0079] The drug attributes are used as entities of the knowledge graph to construct the knowledge graph corresponding to the drug entity. For example, the drug name is compound borax, and the drug classification can be Chinese patent medicine and western medicine. It can be reimbursed in the insurance type coded as 001, and the reimbursement ratio is full reimbursement. Then the relationship of the compound borax entity can be obtained as "compound borax: western medicine, 001, full reimbursement".

[0080] Regarding the above step S202, the above pharmacy database is a database formed for storing pharmacies that support online drug purchases in the insurance claim system.

[0081] The above-mentioned drug information includes drug name and drug classification.

[0082] It should be understood that pharmacies can configure drugs and drug prices in real time based on their own inventory and actual conditions, and then update the pharmacy database.

[0083] For the above step S203, a knowledge graph is constructed to obtain knowledge for constructing a drug database from a pharmacy database, and the drug information and drug entities in the pharmacy database are used to generate a preset drug knowledge base.

[0084] Preferably, a pre-trained classification model is used to classify drug entities to obtain a drug knowledge base.

[0085] By building a drug knowledge base through knowledge graphs, we can intelligently recommend users' drug shopping lists, solve the information asymmetry problem caused by the wide variety of drugs and their rapid updates, improve the accuracy of users' purchase of drugs that meet the insurance claim conditions, reduce the probability of claims failure due to non-compliance with insurance claim conditions, and further improve the efficiency of insurance claims.

[0086] In some optional implementations of this embodiment, step S103 includes the following steps S301 to S305:

[0087] S301. When receiving a user's request to purchase medicine, obtain historical purchase records.

[0088] S302: Determine an interest factor based on historical purchase records, wherein the interest factor is the first influencing factor for the user to make a purchase.

[0089] S303: Input the interest factor and the candidate drug list into a drug purchase recommendation model, wherein the candidate drug list includes candidate drugs and at least two fields.

[0090] S304. Select the fields corresponding to the interest factors in the candidate drug list, and use the fields corresponding to the interest factors as interest fields, and use the fields corresponding to non-interest factors in the candidate drug list as other fields.

[0091] S305: Fusion processing is performed on the interest field and other fields of the candidate drug list to obtain a recommended drug purchase list and send the recommended drug purchase list to the client.

[0092] For the above step S301, the above historical purchase records include but are not limited to the user's location information, user preference information, and drug information, wherein the user preference information refers to the indicator field that the user prioritizes, and the indicator field includes but is not limited to the price field and the distance field.

[0093] For the above step S302, the above interest factor refers to the first influencing factor for the user to purchase. For example, when the user's preference information is price, the price is the first influencing factor for the user to purchase medicine, that is, the price is the interest factor.

[0094] For the above step S303, the above drug purchase recommendation model may be a recommendation model based on a neural network. The drug purchase recommendation model may include functions such as a rule engine, an update mechanism, and easy confusion reminders.

[0095] It should be understood that for the candidate drug list, there is an initial sorting method in the candidate drug list, and the sorting method can be based on the interest factor corresponding to the last shopping, and the sorting method can also be a random sorting.

[0096] For the above step S305, the fusion process includes but is not limited to weighted fusion, random fusion, etc.

[0097] Through the above steps, a series of processing is performed on the candidate drug list to select drugs that meet the user's interests and make intelligent drug recommendations, which reduces the user's time and energy in screening drugs at the pharmacy, improves the accuracy of drug purchases, and reduces the time for subsequent insurance claims review that do not meet the claim conditions.

[0098] In some optional implementations of this embodiment, step S305 further includes the following steps S3051 to S3055:

[0099] S3051. Determine the interest weight corresponding to the interest field and the secondary weights corresponding to other fields.

[0100] S3052. Based on the interest weight, update the content corresponding to the interest field in the candidate drug list to obtain an interest list corresponding to the interest field.

[0101] S3053. Based on the secondary weights, update the contents corresponding to other fields in the candidate drug list to obtain the secondary lists corresponding to the other fields.

[0102] S3054. Select corresponding candidate drugs in the interest list and the secondary list as fusion drugs.

[0103] S3055. Based on the fused drugs, the corresponding fields of the interest list and the secondary list are combined to obtain a recommended drug purchase list and send the recommended drug purchase list to the client.

[0104] For the above step S3052, the above update processing refers to the process of multiplying the content corresponding to the interest field in the candidate drug list by the interest weight, and updating the content corresponding to the interest field according to the result obtained.

[0105] For the above step S3053, the above update processing refers to the process of multiplying the content corresponding to other fields in the candidate drug list by the secondary weight, and updating the content corresponding to other fields according to the obtained result.

[0106] Through the above-mentioned preset weight assignment method, the factors that users prioritize can be identified more accurately for different users, thereby making drug recommendations intelligent and personalized, improving the accuracy of drug purchases, and reducing the time for subsequent insurance claims review that do not meet claim conditions.

[0107] In some optional implementations of this embodiment, step S106 further includes the following steps S601 to S604:

[0108] S601. If the claim type is post-claim, obtain a preset post-claim rule, and use the preset post-claim rule as the claim rule.

[0109] S602: If the claim type is direct payment claim, obtain the preset direct payment claim rule, and use the preset direct payment claim rule as the claim rule.

[0110] S603: Obtain user materials from the user information, wherein the user materials are materials required for the user to make an insurance claim.

[0111] S604: Based on the claim settlement rules and user materials, insurance claims are settled for the user.

[0112] Regarding the above step S601, the above post-claim refers to the type of claim filed by the user after purchasing the medicine in other places instead of in the insurance claim system.

[0113] Regarding the above step S602, the above direct payment claim refers to the type of claim that a user can directly make a claim for the medicines purchased in the insurance claim system.

[0114] For the above step S603, the above user materials refer to materials related to insurance claims, including but not limited to medical records and user medical insurance card information.

[0115] The following is an example of a specific embodiment to illustrate the above steps S601 to S604. In a specific example, when the claim type is post-claim, the preset post-claim rules are obtained. Based on the preset post-claim rules and user information, the user materials are obtained, and the user materials are checked and processed to obtain a first verification result. If the first verification result is that the verification is passed, the claim is passed, and the user needs to wait for the insurance company to check with the bank before making a claim. If the first verification result is that there are missing materials, the method for supplementing the missing materials is fed back to the user for the user to supplement the materials.

[0116] In another specific example, when the claim type is direct payment claim, a preset direct payment claim rule is obtained. Based on the preset direct payment claim rule, user materials are obtained, and the user materials are checked to obtain a second check result. If the second check result is passed, the user is paid compensation according to the compensation ratio. If the second check result is not passed, the user is asked to update the information so that direct compensation can be made.

[0117] It should be understood that during the insurance claim process, when the user applies for a claim for the first time, the user needs to submit relevant materials for review. The insurance claim system will record the materials submitted by the user. When applying for a claim later, the insurance claim system will directly bring out the materials that have been uploaded. If modification is required, the user can submit it again based on the original information. The insurance claim system will modify the basic information such as the user, medicine, and pharmacy based on the previously filled content. If it is not necessary, the original materials will be submitted directly. Important materials related to reimbursement, such as medical records, need to be submitted manually by the user.

[0118] By determining the claim type and then making insurance claims, it has the adaptability to multiple claim scenarios. If the claim types increase, the claim rules can be directly imported, and the claim process can be carried out, which is conducive to realizing the diversification of claim applications.

[0119] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0120] In one embodiment, an intelligent claims settlement device is provided, which corresponds one-to-one to the intelligent claims settlement method in the above embodiment. Figure 3 As shown, the intelligent claim settlement device includes an insurance association network construction module 11, a candidate drug list generation module 12, a drug recommendation purchase module 13, a claim request acquisition module 14, a claim type determination module 15 and a claim settlement module 16. The functional modules are described in detail as follows:

[0121] The insurance association network construction module 11 is used to obtain user information and insurance information and construct an insurance association network, wherein the user information includes historical drug purchase records.

[0122] The candidate drug list generation module 12 is used to query the user's reimbursable drugs in a preset drug knowledge base based on the insurance association network and generate a candidate drug list.

[0123] The drug recommendation and purchase module 13 is used to, when receiving a user's drug purchase request, recommend historical drug purchase records and a list of candidate drugs based on a drug purchase recommendation model and user operation records, obtain a drug recommendation purchase list, and send the drug recommendation purchase list to the client, wherein the user operation record is the operation record information stored by the server within a preset time period.

[0124] The claim request acquisition module 14 is used to process the drug purchase and generate a corresponding claim request according to the drug purchase selection result fed back by the client based on the drug recommendation purchase list.

[0125] The claim type determination module 15 is used to identify the claim type of the claim request and determine the claim type.

[0126] The claim settlement module 16 is used to obtain preset claim settlement rules from the insurance association network based on the claim settlement type, and to make insurance claims based on the preset claim settlement rules.

[0127] In one embodiment, the insurance association network construction module 11 further includes:

[0128] The user keyword acquisition unit is used to acquire user information and perform keyword extraction on the user information to obtain user keywords.

[0129] The insurance keyword acquisition unit is used to acquire insurance information and extract keywords from the insurance information to obtain insurance keywords.

[0130] The insurance association network construction unit is used to map user information and insurance information based on user keywords and insurance keywords to construct an insurance association network.

[0131] In one embodiment, before the candidate drug list generation module 12, the intelligent claims settlement device further includes:

[0132] The drug entity determination module is used to determine drug attributes based on drug knowledge and insurance policy claim conditions, and use drug attributes as drug entities.

[0133] The drug information acquisition module is used to obtain drug information from the pharmacy database.

[0134] The drug knowledge base acquisition module is used to map drug information and corresponding drug entities to obtain a preset drug knowledge base.

[0135] In one embodiment, the drug recommendation purchase module 13 further includes:

[0136] The historical purchase record acquisition unit is used to acquire the historical purchase record when receiving a user's drug purchase request.

[0137] The interest factor determination unit is used to determine the interest factor based on the historical purchase record, wherein the interest factor is the first influencing factor for the user to make a purchase.

[0138] An input unit is used to input the interest factor and the candidate drug list into the drug purchase recommendation model, wherein the candidate drug list includes candidate drugs and at least two fields.

[0139] The field determination unit is used to select the fields corresponding to the interest factors in the candidate drug list, and use the fields corresponding to the interest factors as interest fields, and the fields corresponding to non-interest factors in the candidate drug list as other fields.

[0140] The fusion unit is used to fuse the interest field and other fields of the candidate drug list to obtain a recommended drug purchase list and send the recommended drug purchase list to the client.

[0141] In one embodiment, the fusion unit further comprises:

[0142] The weight assignment unit is used to determine the interest weight corresponding to the interest field and the secondary weights corresponding to other fields.

[0143] The interest list acquisition unit is used to update the content corresponding to the interest field in the candidate drug list based on the interest weight to obtain the interest list corresponding to the interest field.

[0144] The secondary list acquisition unit is used to update the contents corresponding to other fields in the candidate drug list based on the secondary weights to obtain the secondary lists corresponding to the other fields.

[0145] The fusion drug determination unit is used to select corresponding candidate drugs in the interest list and the secondary list as fusion drugs.

[0146] The field fusion unit is used to combine the corresponding fields of the interest list and the secondary list based on the fused drugs, obtain the drug purchase recommendation list and send the drug purchase recommendation list to the client.

[0147] In one embodiment, the claim module 16 further includes:

[0148] The first claim settlement unit is used to obtain a preset post-claim settlement rule if the claim type is post-claim settlement, and use the preset post-claim settlement rule as the claim settlement rule.

[0149] The second claim settlement unit is used to obtain a preset direct payment claim settlement rule if the claim type is a direct payment claim, and use the preset direct payment claim settlement rule as the claim settlement rule.

[0150] The user material acquisition unit is used to acquire user materials from user information, wherein the user materials are materials required by the user for insurance claims.

[0151] The insurance claim unit is used to make insurance claims for users based on claim rules and user materials.

[0152] The meaning of "first" and "second" in the above modules / units is only to distinguish different modules / units, and is not used to define which module / unit has a higher priority or other limiting meanings. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The division of modules in this application is only a logical division, and there may be other division methods when implemented in actual applications.

[0153] For the specific definition of the intelligent claims settlement device, please refer to the definition of the intelligent claims settlement method above, which will not be repeated here. Each module in the above-mentioned intelligent claims settlement device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0154] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data involved in the intelligent claims method. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an intelligent claims method is implemented.

[0155] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the intelligent claims settlement method in the above embodiment are implemented, such as Figure 2 Steps S101 to S106 and other extensions of the method and related steps are shown. Alternatively, when the processor executes the computer program, the functions of each module / unit of the intelligent claims settlement device in the above embodiment are realized, for example Figure 3 The functions of modules 11 to 16 are shown in Figure 1. To avoid repetition, they will not be described here.

[0156] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the computer device, and various interfaces and lines are used to connect various parts of the entire computer device.

[0157] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the computer device by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, video data, etc.), etc.

[0158] The memory may be integrated into the processor or may be arranged separately from the processor.

[0159] In one embodiment, a computer-readable storage medium is provided on which a computer program is stored. When the computer program is executed by a processor, the steps of the intelligent claims settlement method in the above embodiment are implemented, such as Figure 2 Steps S101 to S106 and other extensions of the method and related steps are shown. Alternatively, when the computer program is executed by the processor, the functions of each module / unit of the intelligent claims settlement device in the above embodiment are realized, for example Figure 3 The functions of modules 11 to 16 are shown in Figure 1. To avoid repetition, they will not be described here.

[0160] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. 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. As an 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 (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0161] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0162] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. An intelligent claims settlement method, characterized in that: include: Obtain user information and insurance information to build an insurance association network, where user information includes historical drug purchase records; Based on the insurance association network, query the user's reimbursable drugs in a preset drug knowledge base to generate a list of candidate drugs; When a user's request to purchase medicine is received, the historical medicine purchase records and the candidate medicine list are recommended based on the medicine purchase recommendation model and the user operation record to obtain a recommended medicine purchase list and send the recommended medicine purchase list to the client, wherein the user operation record is the operation record information stored by the server within a preset time period, and the steps include: when a user's request to purchase medicine is received, the historical purchase record is obtained; based on the historical purchase record, an interest factor is determined, wherein the interest factor is the first influencing factor for the user to purchase; the interest factor and the candidate medicine list are input into the medicine purchase recommendation model, wherein the candidate medicine list includes candidate medicines and at least two fields; the field corresponding to the interest factor in the candidate medicine list is selected, and the field corresponding to the interest factor is used as the interest field, and the field not corresponding to the interest factor in the candidate medicine list is used as other fields; Determine an interest weight corresponding to the interest field and a secondary weight corresponding to the other fields; Based on the interest weight, updating the content corresponding to the interest field in the candidate drug list to obtain an interest list corresponding to the interest field; Based on the secondary weights, updating the contents corresponding to other fields in the candidate drug list to obtain secondary lists corresponding to other fields; Selecting corresponding candidate drugs in the interest list and the secondary list as fusion drugs; Based on the fused drugs, the corresponding fields of the interest list and the secondary list are combined to obtain a drug purchase recommendation list and send the drug purchase recommendation list to the client; According to the drug purchase selection result fed back by the client based on the drug recommendation purchase list, drug purchase processing is performed and a corresponding claim request is generated; Identify the claim type of the claim request and determine the claim type; Based on the claim type, a preset claim rule is obtained from the insurance association network, and an insurance claim is made based on the preset claim rule.

2. The method according to claim 1, characterized in that The step of obtaining user information and insurance information and building an insurance association network, wherein the user information includes historical drug purchase records, comprises: Acquire user information, and perform keyword extraction on the user information to obtain user keywords; Obtaining insurance information, and performing keyword extraction on the insurance information to obtain insurance keywords; Based on the user keywords and the insurance keywords, the user information and the insurance information are mapped to construct an insurance association network.

3. The method according to claim 1, characterized in that Before searching for reimbursable drugs for users in a preset drug knowledge base based on the insurance association network and generating a candidate drug list, the method further includes: Determine the drug attributes based on drug knowledge and insurance policy claim conditions, and use the drug attributes as drug entities; Get drug information from the pharmacy database; The drug information and the corresponding drug entity are mapped to obtain the drug knowledge base.

4. The method according to claim 1, characterized in that The step of obtaining a preset claim settlement rule from the insurance association network based on the claim settlement type, and making an insurance claim settlement based on the preset claim settlement rule comprises: If the claim type is post-claim, then obtain the preset post-claim rule, and use the preset post-claim rule as the claim rule; If the claim type is direct payment claim, obtain the preset direct payment claim rule, and use the preset direct payment claim rule as the claim rule; Acquire user materials from the user information, wherein the user materials are materials required for the user to make an insurance claim; Based on the claim settlement rules and the user materials, insurance claims are made to the user.

5. An intelligent claims settlement device, characterized in that: include: An insurance association network construction module is used to obtain user information and insurance information and construct an insurance association network, wherein the user information includes historical drug purchase records; A candidate drug list generation module is used to query the user's reimbursable drugs in a preset drug knowledge base based on the insurance association network to generate a candidate drug list; The drug recommendation purchase module is used to, when receiving a user's drug purchase request, recommend the historical drug purchase records and the candidate drug list based on the drug purchase recommendation model and the user operation record, obtain the drug recommendation purchase list and send the drug recommendation purchase list to the client, wherein the user operation record is the operation record information stored by the server within a preset time period; the drug recommendation purchase module includes: a historical purchase record acquisition unit, which is used to acquire the historical purchase record when receiving a user's drug purchase request; an interest factor determination unit, which is used to determine the interest factor based on the historical purchase record, wherein the interest factor is the first influencing factor for the user to purchase; an input unit, which is used to input the interest factor and the candidate drug list into the drug purchase recommendation model, wherein the candidate drug list includes candidate drugs and at least two fields; a field determination unit, which is used to select Take the field corresponding to the interest factor in the candidate drug list, and use the field corresponding to the interest factor as the interest field, and use the field not corresponding to the interest factor in the candidate drug list as other fields; the fusion unit determines the interest weight corresponding to the interest field and the secondary weight corresponding to the other field; based on the interest weight, update the content corresponding to the interest field in the candidate drug list to obtain the interest list corresponding to the interest field; based on the secondary weight, update the content corresponding to the other fields in the candidate drug list to obtain the secondary list corresponding to the other fields; select the candidate drugs corresponding to the interest list and the secondary list as fused drugs; based on the fused drugs, combine the fields corresponding to the interest list and the secondary list to obtain a recommended drug purchase list and send the recommended drug purchase list to the client; A claim request acquisition module, used to process drug purchases and generate corresponding claim requests according to the drug purchase selection results fed back by the client based on the drug recommendation purchase list; A claim type determination module, used to identify the claim type of the claim request and determine the claim type; The claim settlement module is used to obtain preset claim settlement rules from the insurance association network based on the claim settlement type, and to make insurance claims based on the preset claim settlement rules.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the intelligent claims settlement method as described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the intelligent claims settlement method as claimed in any one of claims 1 to 4 are implemented.

Images