Claim settlement auditing method and system

Abstract

The embodiment of the invention provides a claim settlement auditing method and system. The method comprises the following steps: in response to a claim settlement request submitted by a user for a target case in an interactive interface, obtaining case information of the target case; based on the case information, performing an adjustment operation and a claim settlement operation in parallel to obtain an adjustment result and a claim settlement result, and prompting that the target case supports second-level auditing in an interactive interface when it is determined that the target case supports second-level auditing; and determining an auditing result of second-level auditing based on the claim checking result and the adjustment result, and displaying the auditing result of the target case in the interactive interface. Wherein the adjustment result at least represents the claim amount of the target case. The claim checking result at least represents whether the target case supports second-level auditing and claim settlement. The audit result comprises whether claim settlement is supported or not and / or the claim amount.

Description

Technical Field

[0001] This specification relates to the field of Internet technologies, and in particular, to a claims settlement review method and system. Background Art

[0002] Nowadays, more and more users choose to purchase insurance. When a user suffers personal injury or property loss, they can initiate a claims request to the claims settlement service provider to obtain financial compensation. After receiving the claims request, the claims settlement service provider reviews the actual cases of the user to determine whether to provide claims settlement. With the rapid development of the insurance industry and the intensification of market competition, the efficiency of claims settlement review has become an important criterion for measuring the level of claims settlement services.

[0003] However, claims settlement review involves a large amount of information verification and complex operations such as liability determination, often requiring the intervention of reviewers. Therefore, claims settlement review is restricted by multiple factors such as the number of reviewers and their professional capabilities, taking a long time and affecting the user experience.

[0004] The content in the background art section is only the information known to the inventor personally, and does not represent that the above information has entered the public domain before the filing date of this disclosure, nor does it represent that it can become the prior art of this disclosure. Summary of the Invention

[0005] This specification provides a claims settlement review method and system, which can immediately notify whether the case submitted by the user supports second-level review within a short time. For cases that meet the second-level review requirements, the review result can be informed to the user within the second-level time limit, improving the review efficiency and the user experience at the same time.

[0006] In a first aspect, this specification provides a claims settlement review method, including: in response to a claims request submitted by a user for a target case in an interaction interface, obtaining the case information of the target case; based on the case information, performing a loss adjustment operation and a claims verification operation in parallel to obtain a loss adjustment result and a claims verification result, where the loss adjustment result at least represents the claims amount of the target case, and the claims verification result at least represents whether the target case supports second-level review and whether it supports claims settlement; and in the case where it is determined based on the claims verification result that the target case supports second-level review, prompting in the interaction interface that the target case supports second-level review, determining the review result of the second-level review based on the claims verification result and the loss adjustment result, and displaying the review result of the target case in the interaction interface, where the review result includes whether claims settlement is supported and / or the claims amount, and the time duration between the submission time of the claims request and the display time of the review result is a second-level time limit.

[0007] In some embodiments, the case information includes loss adjustment voucher information and claims settlement voucher information. Performing the loss adjustment operation and the claims settlement operation in parallel based on the case information to obtain a loss adjustment result and a claims settlement result includes performing the following two operations in parallel: performing the loss adjustment operation on the loss adjustment voucher information through a loss adjustment model to obtain the loss adjustment result, where the loss adjustment model is a pre-trained model and has the ability to determine the loss adjustment result based on the loss adjustment voucher information; and performing the claims settlement operation on the claims settlement voucher information through a claims settlement model to obtain the claims settlement result, where the claims settlement model is a pre-trained model and has the ability to determine the claims settlement result based on the claims settlement voucher information.

[0008] In some embodiments, obtaining the case information of the target case includes: obtaining the claims settlement voucher document and the loss adjustment voucher document of the target case based on the claims settlement request; and performing information extraction on the claims settlement voucher document and the loss adjustment voucher document through a text recognition model to obtain the claims settlement voucher information and the loss adjustment voucher information.

[0009] In some embodiments, the method is applied to a claims settlement review system. Obtaining the loss adjustment voucher document of the target case based on the claims settlement request includes one of the following: in the case where the user has uploaded the loss adjustment voucher document, parsing the loss adjustment voucher document uploaded by the user from the claims settlement request; or in the case where the user has not uploaded the loss adjustment voucher document, parsing the basic information filled in by the user for the target case from the claims settlement request, and obtaining the loss adjustment voucher document from an external data source based on the basic information, where the external data source is a data source outside the claims settlement review system.

[0010] In some embodiments, the method is applied to a claims settlement review system. Obtaining the claims settlement voucher document of the target case based on the claims settlement request includes one of the following: in the case where the user has uploaded the claims settlement voucher document, parsing the claims settlement voucher document uploaded by the user from the claims settlement request; or in the case where the user has not uploaded the claims settlement voucher document, parsing the basic information filled in by the user for the target case from the claims settlement request, and obtaining the claims settlement voucher document from an external data source based on the basic information, where the external data source is a data source outside the claims settlement review system.

[0011] In some embodiments, performing the loss adjustment operation on the loss adjustment voucher information through a loss adjustment model to obtain the loss adjustment result includes: determining the case type of the target case; determining the target loss adjustment rule corresponding to the target case based on the case type; and inputting the target loss adjustment rule and the loss adjustment voucher information into the loss adjustment model to obtain the loss adjustment result.

[0012] In some embodiments, the adjustment model is pre-trained based on a plurality of first sample data, and each first sample data includes an adjustment rule and adjustment voucher information corresponding to a sample claim case.

[0013] In some embodiments, performing the claims settlement operation on the claims settlement voucher information by the claims settlement model to obtain the claims settlement result includes: determining the case type of the target case; determining a target claims settlement rule corresponding to the target case based on the case type; and inputting the target claims settlement rule and the claims settlement voucher information into the claims settlement model to obtain the claims settlement result.

[0014] In some embodiments, the claims settlement model is pre-trained based on a plurality of second sample data, and each second sample data includes a claims settlement rule and claims settlement voucher information corresponding to a sample claim case.

[0015] In some embodiments, determining the audit result of the second-level audit based on the claims settlement result and the adjustment result, and displaying the audit result in the interaction interface includes: determining a first audit result of the target case based on the claims settlement result and / or the adjustment result; sending the first audit result and the case information to the indemnitor; and if a second audit result is received from the indemnitor within a target duration specified for the second-level audit, displaying the second audit result in the interaction interface, where the second audit result is consistent with the first audit result, or the second audit result is an audit result obtained by the indemnitor based on the case information to correct the first audit result.

[0016] In some embodiments, the method further includes: if the second audit result is not received from the indemnitor within the target duration, displaying the first audit result in the interaction interface.

[0017] In some embodiments, when the claims settlement result indicates that the target case does not support claim settlement, the first audit result includes non-support for claim settlement; or when the claims settlement result indicates that the target case supports claim settlement, the first audit result includes support for claim settlement and the claim amount.

[0018] In some embodiments, when the first audit result includes support for claim settlement and the claim amount, the first audit result further includes detailed content corresponding to the claim amount.

[0019] In some embodiments, when the first audit result includes non-support for claim settlement, the first audit result further includes the basis for the conclusion of non-support for claim settlement.

[0020] In some embodiments, determining that the target case supports second-level auditing based on the claims settlement result includes: when the claims settlement result indicates that the target case supports second-level auditing, determining that the target case supports second-level auditing.

[0021] In some embodiments, the adjustment result further indicates a first credibility corresponding to the claim amount, and the claims settlement result further indicates a second credibility corresponding to whether second-level auditing is supported. The method further includes: determining a comprehensive credibility based on the first credibility and the second credibility; determining that the target case supports second-level auditing based on the claims settlement result includes: when the comprehensive credibility is greater than or equal to a preset threshold and the claims settlement result indicates that the target case supports second-level auditing, determining that the target case supports second-level auditing.

[0022] In some embodiments, the method further includes: when it is determined based on the claims settlement result that the target case does not support second-level auditing, prompting in the interaction interface that the target case does not support second-level auditing, and prompting the user not to wait online for the audit result.

[0023] In a second aspect, this specification also provides a system, including: at least one storage medium storing at least one instruction set; and at least one processor communicatively connected to the at least one storage medium, wherein when the at least one processor runs, it reads the at least one instruction set and implements the claims auditing method as described in the first aspect according to the instructions of the at least one instruction set.

[0024] Other functions of the claims auditing method and system provided in this specification will be partially listed in the following description. The creative aspects of the claims auditing method and system provided in this specification can be fully explained through practice or use of the methods, systems, and combinations described in the detailed examples below. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] To more clearly illustrate the technical solutions in the embodiments of this specification, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of this specification. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0026] Figure 1 Shows a schematic diagram of an application scenario of a claims auditing provided according to an embodiment of this specification;

[0027] Figure 2 Shows a hardware structure diagram of a system provided according to an embodiment of this specification;

[0028] Figure 3Shows a flowchart of a claims review method provided according to an embodiment of the present specification;

[0029] Figure 4 Shows a schematic diagram of a claims review process provided according to an embodiment of the present specification;

[0030] Figure 5 Shows a schematic diagram of the change of an interactive page supporting second-level review provided according to an embodiment of the present specification;

[0031] Figure 6 Shows a schematic diagram of another claims review process provided according to an embodiment of the present specification; and

[0032] Figure 7 Shows a schematic diagram of the change of an interactive page not supporting second-level review provided according to an embodiment of the present specification. Detailed implementation manners

[0033] The following description provides specific application scenarios and requirements of the present specification, aiming to enable those skilled in the art to manufacture and use the content in the present specification. For those skilled in the art, various partial modifications to the disclosed embodiments are obvious, and the general principles defined here can be applied to other embodiments and applications without departing from the spirit and scope of the present specification. Therefore, the present specification is not limited to the shown embodiments, but has the widest scope consistent with the claims.

[0034] The terms used here are only for the purpose of describing specific example embodiments and are not restrictive. For example, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" used here may also include the plural forms. When used in the present specification, the terms "include", "comprise", and / or "contain" mean that the associated integers, steps, operations, elements, and / or components exist, but do not exclude the existence of one or more other features, integers, steps, operations, elements, components, and / or groups, or the addition of other features, integers, steps, operations, elements, components, and / or groups in the system / method.

[0035] Considering the following description, these features and other features of the present specification, as well as the operations and functions of the related elements of the structure, and the combination and manufacturing economy of the components can be significantly improved. Referring to the accompanying drawings, all of these form a part of the present specification. However, it should be clearly understood that the drawings are only for the purpose of illustration and description and are not intended to limit the scope of the present specification. It should also be understood that the drawings are not drawn to scale.

[0036] The flowcharts used in this specification illustrate the operations implemented by a system according to some embodiments in this specification. It should be clearly understood that the operations in the flowchart may not be implemented in sequence. On the contrary, the operations may be implemented in reverse order or simultaneously. In addition, one or more other operations may be added to the flowchart. One or more operations may be removed from the flowchart.

[0037] In the traditional claims review process, when a user initiates a claims request after a target case (such as a traffic accident, disease treatment, consumption matter, etc.), the user needs to submit voucher documents related to the target case to the claims review system. After the claims review system obtains the relevant voucher documents, it needs to perform multiple steps based on the relevant voucher documents to obtain the review result of the target case. For example, steps such as extracting information from the relevant voucher documents, a determination step of determining whether claims can be made based on the extracted document information, and a calculation step of determining the claim amount.

[0038] Among them, the claims review system is a platform provided by the claims service provider for users to initiate claims requests. It can collect materials and information related to the case from users and can also feedback the review results of the case to users.

[0039] It should be noted that the claims review system can be the claims service provider itself; it can also be a partner of the claims service provider, specifically providing claims review services for the claims service provider. The claims service provider provides actual financial compensation to users.

[0040] In the above-mentioned multiple steps, at least some steps require the intervention of reviewers. The coverage rate of the steps automatically executed by the claims review system in the entire claims review process is relatively low, the review cost is high, the time consumption is long, and the user experience is not good.

[0041] In view of this, the embodiments of this specification provide a claims review method and system, aiming to shorten the review duration of cases and improve the user experience.

[0042] The following combines Figure 1 to introduce the application scenarios of the claims review provided in this specification.

[0043] Figure 1 Shows a schematic diagram of the application scenario of claims review provided according to the embodiments of this specification. As Figure 1 shown, the application scenario 001 includes a user 100 and a claims review system 200. In some embodiments, the application scenario 001 further includes a compensator 300.

[0044] User 100 can submit a claim request for a target case in the claim review system 200. The claim review system 200 can obtain the case information of the target case based on the claim request, and obtain the review result of the target case based on the case information, and display it to user 100.

[0045] In some embodiments, the claim review system 200 can be an application (APP) or a mini-program embedded in an APP, etc., and this specification does not limit this.

[0046] In some embodiments, the claim review system 200 includes a client 10 and a server 20. The client 10 can be deployed on a terminal device. The terminal device can display an interaction page of the client 10 to user 100. User 100 can submit a claim request for a target case in the interaction page. The client 10 can obtain the case information of the target case in response to the claim request and send it to the server 20. The server 20 can determine the review result of the target case based on the case information.

[0047] The terminal device can include mobile devices such as mobile phones and smart watches, tablet computers, laptop computers, built-in devices of motor vehicles or the like, or any combination thereof, and this specification does not limit this.

[0048] Exemplarily, user 100 can submit a voucher document related to the target case in the client 10, and the client 10 can send the voucher document to the server 20. The server 20 can sequentially execute multiple links based on the voucher document to complete the claim review. The multiple links include but are not limited to: information extraction, information classification, information integration, external data query, claim assessment and liability determination, cost calculation, conclusion integration, data synchronization, and conclusion display.

[0049] Among them, information classification is, for example, after extracting information from the voucher document, classifying the extracted document information. Information integration is, for example, integrating the classified document information. External data query is, for example, querying information related to the target case from a data source outside the claim review system 200. Claim assessment and liability determination is, for example, based on the integrated document information, determining whether the claim service provider (hereinafter referred to as the compensating party) needs to bear the liability for compensation to the user. Cost calculation is, for example, when it is determined that the compensating party needs to bear the liability for compensation to the user, calculating the amount of compensation paid by the compensating party to the user. Conclusion integration is, for example, organizing the results obtained from claim assessment and liability determination and cost calculation to obtain the review result of the target case. Data synchronization is, for example, if the compensating party and the claim review system 200 do not correspond to the same party, the claim review system 200 and the compensating party need to synchronize the case information and review conclusions regarding the target case. Conclusion display is, for example, the claim review system 200 displays the review result of the target case to the user.

[0050] In this example, the claim review system 200 needs to sequentially execute each link in a predetermined order in series. Only after the result of the previous link is obtained can the next link be executed. The cumulative review duration of all links is relatively long, and there is a risk of instability in individual links, resulting in an extended review duration.

[0051] In view of this, to improve the user experience, the embodiments of this specification further provide a claim review method P300 to further shorten the review duration of claim review.

[0052] In some embodiments, the claim review system 200 may store data and instructions for implementing the claim review method P300 and may execute or be used to execute the data and instructions. In some embodiments, the claim review system 200 may include a hardware device with data information processing functions and necessary programs required to drive the hardware device to work.

[0053] Exemplarily, as Figure 1 shown, when the claim review system 200 is the compensator itself, the compensator 300 may not be included in the application scenario 001. At this time, after the server 20 determines the review result based on the method P300, it may send the review result to the client 10, and the client 10 may display the review result to the user 100.

[0054] Exemplarily, as Figure 1 shown, when the claim review system 200 is a partner of the compensator, the compensator 300 (such as an insurance company) may be included in the application scenario 001. At this time, as a partner of the compensator 300, the claim review system 200 provides claim review services for the compensator 300, sends suggestions on the review result and case information of the target case to the compensator 300, and the compensator 300 gives the final review result. After receiving the suggestion on the review result, the compensator 300 may obtain the final review result based on the case information of the target case and feedback the final review result to the server 20 in the claim review system 200, and the server 20 may display the final review result to the user through the client 10.

[0055] Specifically, the technical details of the claim review method P300 will be described in detail later and will not be elaborated here.

[0056] Figure 2 Shows the hardware structure diagram of the claim review system 200 provided according to the embodiments of this specification.

[0057] As Figure 2As shown, the claims review system 200 may include at least one storage medium 230 and at least one processor 220. In some embodiments, the claims review system 200 may further include a communication port 250 and an internal communication bus 210. Additionally, the claims review system 200 may further include I / O components 260.

[0058] The internal communication bus 210 may connect different system components. For example, the internal communication bus 210 may connect the storage medium 230, the processor 220, the communication port 250, and the I / O components 260.

[0059] The I / O components 260 support input / output between the claims review system 200 and other components.

[0060] The communication port 250 is used for data communication between the claims review system 200 and the outside world. For example, the communication port 250 may be used for data communication between the claims review system 200 and a network. The communication port 250 may be a wired communication port or a wireless communication port.

[0061] In some embodiments, the network may be any type of wired or wireless network, or a combination thereof. For example, the network may include a cable network, a wired network, an optical fiber network, a telecommunication network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network TM, a short-range wireless network (ZigBee TM), a near field communication (NFC) network, or a similar network.

[0062] In some embodiments, the network may include one or more network access points. For example, the network may include wired or wireless network access points, such as base stations or Internet exchange points. Through this access point, one or more components of each device corresponding to the claims review system 200 may be connected to the network to exchange data or information.

[0063] The storage medium 230 may include a data storage device. The data storage device may be a non-transitory storage medium or a transitory storage medium. For example, the data storage device may include one or more of a magnetic disk 232, a read-only storage medium (ROM) 234, or a random access storage medium (RAM) 236. The storage medium 230 further includes at least one set of instructions stored in the data storage device. The set of instructions may include computer program code, and the computer program code may include programs, routines, objects, components, data structures, procedures, modules, etc. for executing the claim review method provided in this specification.

[0064] The processor 220 may be communicatively connected to the storage medium 230. The processor 220 is configured to execute the above at least one set of instructions. When the claim review system 200 runs, the processor 220 reads the at least one set of instructions and, according to the instructions of the at least one set of instructions, executes the claim review method provided in this specification.

[0065] The processor 220 may be in the form of one or more processors. In some embodiments, the processor 220 may include one or more hardware processors, such as a microcontroller, a microprocessor, a reduced instruction set computer (RISC), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), a central processing unit (CPU), a graphics processing unit (GPU), a physics processing unit (PPU), a microcontroller unit, a digital signal processor (DSP), a field programmable gate array (FPGA), an advanced RISC machine (ARM), a programmable logic device (PLD), any circuit or processor capable of executing one or more functions, etc., or any combination thereof.

[0066] For illustrative purposes only, only one processor 220 is shown in the claim review system 200 in the accompanying Figure 2 However, it should be noted that the claim review system 200 in this specification may further include multiple processors. Therefore, the operations and / or method steps disclosed in this specification may be executed by one processor as described in this specification or jointly executed by multiple processors. For example, if the processor 220 of the claim review system 200 in this specification executes step A and step B, it should be understood that step A and step B may also be jointly or separately executed by two different processors 220 (e.g., the first processor executes step A, the second processor executes step B, or the first and second processors jointly execute steps A and B).

[0067] Figure 3 A flowchart of a claim review method P300 provided according to an embodiment of this specification is shown. The claim review system 200 may execute the claim review method P300. As Figure 3As shown, the claims settlement review method P300 includes the following steps.

[0068] S310: In response to a claims request submitted by a user for a target case in an interaction interface, obtain the case information of the target case.

[0069] The target case is an event that actually occurs to the user and requires claims settlement, such as a traffic accident, disease treatment, consumption items (such as travel, accommodation, etc.). The claims request is an act by which the user informs the compensator of the event situation and applies for claims settlement. The compensator is the claims service provider agreed upon in the contract pre-signed by the user, which can be an insurance company or other entity that can provide reimbursement or compensation to the user. This specification does not limit this. The target case in this specification can be a compensation-based claims case, a benefit-based claims case, or a reimbursement-based claims case, etc. This specification does not limit this.

[0070] Compensation-based claims case: After the user has a compensation-based claims case, the compensator makes an economic compensation for the actual losses suffered by the user in the case. The insurance contracts corresponding to compensation-based claims cases include but are not limited to: property insurance or vehicle insurance contracts, etc.

[0071] Benefit-based claims case: After the user has a benefit-based claims case, the compensator makes a claims settlement of a fixed amount to the user for economic compensation, and the fixed amount has nothing to do with the user's actual losses in the case. The insurance contracts corresponding to benefit-based claims cases include but are not limited to: life insurance, critical illness insurance, or accidental injury insurance contracts, etc.

[0072] Reimbursement-based claims case: After the user has a reimbursement-based claims case, the compensator reimburses the user's actual losses in the case according to the agreement of the insurance contract. The insurance contracts corresponding to reimbursement-based claims cases include but are not limited to medical insurance, some vehicle insurance contracts, or labor contracts (including reimbursement clauses for travel, accommodation, etc.).

[0073] Exemplarily, as Figure 4 shown, the user can submit a claims request for the target case on the client 10. Specifically, as Figure 5 shown, the user can fill in the basic information of the target case on interaction page A displayed on the client 10, upload the voucher documents required for claims settlement, and then perform the submission operation of the claims request. The basic information includes but is not limited to: the user's identity information, payment information, time and place of occurrence of the target case, etc.

[0074] It should be noted that the interaction page for the user to fill in the basic information and the interaction page for uploading voucher documents can be different. This specification does not limit this.

[0075] Continue to refer to Figure 4, after the user performs a submission operation, the client 10 can obtain the case information of the target case based on the claim request and send it to the server 20; or the client 10 can send the claim request to the server 20, and the server 20 obtains the case information based on the claim request. The case information is the relevant information required by the claim review system 200 when reviewing the claim for the target case, including but not limited to: the basic information and the information extracted from the voucher document.

[0076] In some embodiments, the claim review system 200 obtains the underwriting voucher document and the adjustment voucher document of the target case based on the claim request; and extracts information from the underwriting voucher document and the adjustment voucher document through a text recognition model to obtain the underwriting voucher information and the adjustment voucher information. The underwriting voucher information and the adjustment voucher information serve as the case information of the target case. In this embodiment, the claim review system 200 performs automated information extraction on each voucher document through the text recognition model, which can reduce manual participation in the information extraction stage, improve the information extraction efficiency, and speed up the claim review.

[0077] Among them, the underwriting voucher document is the material required for the claim review system 200 to determine whether the target case supports second-level review and whether the target case supports claim settlement. The adjustment voucher document is the material required for the claim review system 200 to calculate the specific amount of compensation to be paid to the user in the claim settlement.

[0078] Whether it supports second-level review can be understood as: whether it meets the conditions for second-level review, or whether the claim review system 200 can inform the user of the review result within the second-level time limit.

[0079] Whether it supports claim settlement can be understood as: whether it meets the conditions for claim settlement, or whether the compensating party can compensate the user to provide economic compensation.

[0080] Second-level review can be understood as: completing the claim review within a short period of time, such as completing the review within the second-level time limit. The second-level time limit can be the online waiting time for the review result that the user can tolerate or has a good experience, and can be a time limit in seconds. For example, the second-level time limit can be any time within 1 minute (min), or a time close to 1 min (the difference from 1 min is less than the preset value), and this specification does not limit it.

[0081] It can be understood that when the case types of the target cases are different, the claim settlement voucher documents and calculation voucher documents corresponding to the target cases can also be different. For example, when the target case is a reimbursement-type claim settlement case, the claim settlement voucher documents include but are not limited to: medical record materials, diagnosis certificates, inspection reports, prescriptions, medical manuals, transfer application forms, etc. The calculation voucher documents include but are not limited to: medical expense invoices and medical expense lists, etc. When the target case is a case of other types, the claim settlement voucher documents and calculation voucher documents need to be adjusted adaptively, which are not listed one by one here.

[0082] There can be multiple ways for the claim settlement review system 200 to obtain the claim settlement voucher documents and calculation voucher documents. Here, three of them will be introduced as examples.

[0083] Method 1

[0084] In the case where the user uploads the claim settlement voucher documents and calculation voucher documents, the claim settlement review system 200 parses and obtains the claim settlement voucher documents and calculation voucher documents uploaded by the user from the claim settlement request.

[0085] Exemplarily, when the user fills in the basic information on the interaction page presented on the client 10, the client 10 can determine whether it can obtain the claim settlement voucher documents and calculation voucher documents related to the target case from an external data source (a data source outside the claim settlement review system 200) based on the basic information.

[0086] If it is determined that the documents cannot be obtained from the external data source, the client 10 can prompt the user to upload the claim settlement voucher documents and calculation voucher documents through the interaction page. Or, if the client 10 determines that the documents can be obtained from the external data source and the user refuses when asked whether to authorize through the interaction page, the user can be prompted to upload the claim settlement voucher documents and calculation voucher documents by themselves through the interaction page.

[0087] After the user submits the claim settlement request, the client 10 can parse and obtain the claim settlement voucher documents and calculation voucher documents from the claim settlement request.

[0088] In Method 1, the claim settlement review system 200 can prompt the user for the types of documents that need to be uploaded, avoiding the problem that the user uploads incompletely by themselves, resulting in multiple supplementary uploads and a poor experience.

[0089] Method 2

[0090] In the case where the user does not upload the claim settlement voucher documents and calculation voucher documents, the claim settlement review system 200 parses and obtains the basic information filled in by the user for the target case from the claim settlement request, and obtains the claim settlement voucher documents and calculation voucher documents from the external data source based on the basic information.

[0091] Exemplarily, after the client 10 obtains the basic information filled in by the user, when it determines that the claim settlement voucher document and the adjustment voucher document can be obtained from an external data source and the user agrees to authorize, it can prompt the user not to upload the voucher document and directly submit a claim settlement request. After the user submits the claim settlement request, the client 10 parses the basic information therefrom and obtains the claim settlement voucher document and the adjustment voucher document from the external data source based on the basic information.

[0092] Method 3

[0093] When the user uploads some of the claim settlement voucher document and the adjustment voucher document, the claim settlement review system 200 parses the obtained some of the documents and the basic information filled in by the user for the target case from the claim settlement request, and obtains the other part of the claim settlement voucher document and the adjustment voucher document from the external data source based on the basic information.

[0094] Exemplarily, after the client 10 obtains the basic information filled in by the user, when it determines that some of the documents can be obtained from an external data source and the user agrees to authorize, it can prompt the user to upload some of the documents and submit a claim settlement request. After the user submits the claim settlement request, the client 10 parses the basic information therefrom and obtains the other part of the documents from the external data source based on the basic information.

[0095] The external data source mentioned above can be one or more data sources, including but not limited to: data sources of official platforms that provide medical insurance data, medical treatment data, ticket data, expense lists, etc. This specification does not limit this.

[0096] In Method 2 and Method 3, the claim settlement review system 200 can obtain at least some of the voucher documents from the external data source, which can reduce the number of voucher documents provided by the user and reduce the operation complexity of the user submitting a claim settlement request; it can also avoid the problem that the user loses individual documents or submits some documents incorrectly, resulting in incomplete document upload, thus affecting the accuracy of claim settlement review, and can improve the user's claim settlement experience; in addition, the method of obtaining all voucher documents from the external data source can also avoid the risk problem caused by the user forging some voucher documents.

[0097] It should be noted that the embodiments of this specification do not limit the timing for the claim settlement review system 200 to obtain each voucher document. For example, in Method 2 and Method 3, the client 10 can also synchronously obtain the voucher documents that do not need to be uploaded by the user from the external data source when the user agrees to authorize and before submitting the claim settlement request. Thus, the external data query link is preposed to before the user submits the claim settlement request, further accelerating the review progress, reducing the time waiting for the user to submit the claim settlement request, and improving the review efficiency.

[0098] In addition, in the above three methods, the server 20 may also obtain the voucher documents from the external data source and the claims request, and this specification does not limit this. The server 20 may obtain the claims request from the client 10. The method by which the server 20 obtains each voucher document based on the claims request is similar and will not be elaborated here.

[0099] The text recognition model may be a pre-trained model capable of extracting information such as text in the voucher document. The text recognition model is, for example, a large model, and this specification does not limit the specific type of the text recognition model.

[0100] Exemplarily, the claims review system 200 performs automated recognition and information structured extraction on the underwriting voucher document through the text recognition model, obtains the document information corresponding to each document in the underwriting voucher document, and classifies and organizes the document information corresponding to each document to obtain the underwriting voucher information. The claims review system 200 performs automated recognition and information structured extraction on the calculation voucher document through the text recognition model, obtains the document information corresponding to each document in the calculation voucher document, and classifies and organizes the document information corresponding to each document to obtain the calculation voucher information.

[0101] It should be noted that the text recognition model may be one or more. The claims review system 200 may determine the type of the voucher document based on information such as the location of the document uploaded by the user, call a suitable text recognition model based on the type, and extract information from the corresponding voucher document.

[0102] When the claims review system 200 extracts information from the underwriting voucher document and the calculation voucher document through the text recognition model, the information extraction may be performed sequentially or simultaneously, and this specification does not limit this.

[0103] For example, in the case where the user does not upload the calculation voucher document, the claims review system 200 may synchronously obtain the calculation voucher document from the external data source during the process of parsing the underwriting voucher document in the claims request. If the claims review system 200 has parsed the underwriting voucher document but the acquisition of the calculation voucher document has not been completed, the information extraction of the underwriting voucher document may be performed first, so as to perform the information extraction and the external data query link simultaneously and speed up the review progress.

[0104] For another example, in the case where the user uploads the underwriting voucher document and the calculation voucher document, the claims review system 200 may simultaneously extract information from the underwriting voucher document and the calculation voucher document.

[0105] It can be understood that when the types of the target cases are different, the underwriting voucher information and the calculation voucher information may also be different.

[0106] For example, if the target case is a reimbursement claim case, the claim settlement voucher information corresponding to the target case includes, but is not limited to: type of medical treatment, hospital information, treatment time, disease diagnosis, past medical history, claim history, etc. The calculation voucher information includes, but is not limited to: invoice header information, invoicing information, name of expense item, quantity of each expense item, unit price, total amount, etc. The claim settlement voucher information and the calculation voucher information corresponding to other types of cases can be adjusted accordingly and will not be listed one by one.

[0107] S320: Based on the case information, perform the calculation operation and the claim settlement operation in parallel to obtain a calculation result and a claim settlement result. The calculation result at least represents the claim amount of the target case, and the claim settlement result at least represents whether the target case supports second-level review and whether it supports claim settlement.

[0108] Performing in parallel can be understood as: the calculation operation and the claim settlement operation are independent of each other and do not affect each other, and the two can be executed independently. For example, the claim review system 200 can perform the calculation operation through the first thread and the claim settlement operation through the second thread. The execution of the calculation operation does not need to depend on the execution result of the claim settlement operation, and the execution of the claim settlement operation does not need to depend on the execution result of the calculation operation. The execution periods of the calculation operation and the claim settlement operation can completely overlap or partially overlap.

[0109] In some embodiments, the claim review system 200 can perform the calculation operation on the calculation voucher information in the case information through the calculation model in parallel to obtain a calculation result, and perform the claim settlement operation on the claim settlement voucher information in the case information through the claim settlement model to obtain a claim settlement result. Among them, the calculation model is a pre-trained model and has the ability to determine the calculation result based on the calculation voucher information. The claim settlement model is a pre-trained model and has the ability to determine the claim settlement result based on the claim settlement voucher information.

[0110] In this embodiment, models specifically for the calculation operation and the claim settlement operation are pre-trained, which can improve the accuracy of claim review. And performing the calculation operation and the claim settlement operation in parallel can avoid the waiting delay in the serial execution process, shorten the claim review duration, and improve the review efficiency.

[0111] Before the claim review system 200 performs the claim settlement operation and the calculation operation in parallel, it is necessary to train the calculation model and the claim settlement model. For example, the claim review system 200 can train the calculation model and the claim settlement model by itself. Or, other systems train the calculation model and the claim settlement model and deploy the trained models to the claim review system 200. The following mainly introduces the self-training of the claim review system 200, but this specification is not limited thereto.

[0112] In some embodiments, the claims settlement review system 200 may obtain a plurality of first sample data and train a loss adjustment model based on the plurality of first sample data. Each first sample data includes the loss adjustment rules and loss adjustment voucher information corresponding to a sample claims case.

[0113] The case types of the sample claims cases corresponding to the plurality of first sample data may include multiple types, so that the loss adjustment model can learn different loss adjustment rules during the training process, improving the applicability of the trained loss adjustment model. The loss adjustment rules may be rules common to different types of cases or rules unique to individual types of cases, and this specification does not limit this.

[0114] For each first sample data, the loss adjustment rules corresponding to the first sample data include but are not limited to: the compensation ratio agreed in the contract corresponding to the sample claims case, the types of expenses that can be compensated, the types of expenses that cannot be compensated, etc.

[0115] The claims settlement review system 200 may also obtain the actual claims settlement amount corresponding to each first sample data and calculate the loss during the training process using this as a label. After multiple iterative trainings, a trained loss adjustment model can be obtained.

[0116] In some embodiments, the claims settlement review system 200 may obtain a plurality of second sample data and train a claims verification model based on the plurality of second sample data. Each second sample data includes the claims verification rules and claims verification voucher information corresponding to a sample claims case.

[0117] The case types of the sample claims cases corresponding to the plurality of second sample data may also include multiple types, so that the claims verification model can learn different claims verification rules during the training process, improving the applicability of the trained claims verification model. The claims verification rules may be rules common to different types of cases or rules unique to individual types of cases, and this specification does not limit this.

[0118] It can be understood that the claims verification rules include two aspects of rules. One aspect is used for the claims settlement review system 200 to determine whether a case supports second-level review, and the other aspect is used for the claims settlement review system 200 to determine whether a case supports claims settlement.

[0119] For each second sample data, the claims verification rules corresponding to the second sample data include but are not limited to: whether the sample claims case belongs to the case type that can be second-level reviewed, whether the claims settlement amount agreed in the contract corresponding to the sample claims case belongs to the amount range of second-level review, the liability division regulations agreed in the contract corresponding to the sample claims case, whether the sample claims case belongs to the case type range agreed in the contract, whether the submission time of the sample claims case belongs to the claims settlement time range agreed in the contract, whether the subject involved in the sample claims case belongs to the subject range agreed in the contract, etc.

[0120] The claims settlement review system 200 can obtain the actual claims settlement results corresponding to each second sample data, and use these as labels to calculate the loss during the training process. After multiple iterative trainings, a trained claims settlement model can be obtained.

[0121] The adjustment model and the claims settlement model in this specification are models specifically trained for the claims settlement scenario, and are more targeted when performing adjustment operations and claims settlement operations, which can ensure the accuracy of claims settlement review.

[0122] The following describes the process of the claims settlement review system 200 parallelly performing adjustment operations and claims settlement operations after calling the adjustment model and the claims settlement model.

[0123] In some embodiments, the claims settlement review system 200 determines the case type of the target case, determines the target adjustment rule corresponding to the target case based on the case type, and inputs the target adjustment rule and the adjustment voucher information into the adjustment model to obtain the adjustment result.

[0124] In some embodiments, the claims settlement review system 200 determines the case type of the target case, determines the target claims settlement rule corresponding to the target case based on the case type, and inputs the target claims settlement rule and the claims settlement voucher information into the claims settlement model to obtain the claims settlement result.

[0125] In the above embodiments, the claims settlement review system 200 inputs the target adjustment rule into the adjustment model and the target claims settlement rule into the claims settlement model, which can enable the model to have accurate and targeted basis during prediction, thereby improving the accuracy of the model output result.

[0126] Exemplarily, the server 20 can pre-store the corresponding relationships between different case types, different adjustment rules, and different claims settlement rules, and determine the case type of the target case based on the identification information of the target case, and further determine the target adjustment rule and the target claims settlement rule corresponding to the case type from the stored corresponding relationships. Alternatively, the server 20 can obtain the target adjustment rule and the target claims settlement rule from the insurance contract corresponding to the target case.

[0127] Continue to refer to Figure 4 , the server 20 inputs the adjustment voucher information and the target adjustment rule in the case information into the adjustment model to obtain the adjustment result output by the adjustment model; parallelly inputs the claims settlement voucher information and the target claims settlement rule in the case information into the claims settlement model to obtain the claims settlement result output by the claims settlement model.

[0128] Exemplarily, the claims settlement result includes a first sub-result and a second sub-result. The first sub-result represents whether second-level review is supported, and the second sub-result represents whether claims settlement is supported.

[0129] S330: When it is determined that the target case supports second-level review based on the claims settlement result, prompt in the interaction interface that the target case supports second-level review, determine the review result of the second-level review based on the claims settlement result and the adjustment result, and display the review result of the second-level review in the interaction interface. Wherein, the review result includes whether to support claims settlement and / or the claims settlement amount. The time duration between the submission time of the claims request and the display time of the review result is the second-level time duration.

[0130] Before executing S330, the claims review system 200 needs to determine whether the target case supports second-level review. There can be multiple determination methods. Here are two examples, and this specification is not limited to this.

[0131] Method 1

[0132] In some embodiments, when the claims settlement result indicates that the target case supports second-level review, the claims review system 200 determines that the target case supports second-level review; when the claims settlement result indicates that the target case does not support second-level review, the claims review system 200 determines that the target case does not support second-level review.

[0133] In this embodiment, the claims review system 200 can directly determine whether the target case supports second-level review based on the first sub-result without making other judgments, and the execution logic is simple, which can further improve the efficiency of claims review.

[0134] Method 2

[0135] In some embodiments, the adjustment result also indicates the first credibility corresponding to the claims settlement amount, and the claims settlement result also indicates the second credibility corresponding to whether to support second-level review. The claims review system 200 determines the comprehensive credibility based on the first credibility and the second credibility. When the comprehensive credibility is greater than or equal to the preset threshold and the claims settlement result indicates that the target case supports second-level review, determine that the target case supports second-level review; when the comprehensive credibility is greater than or equal to the preset threshold and the claims settlement result indicates that the target case does not support second-level review, or when the comprehensive credibility is less than the preset threshold, determine that the target case does not support second-level review.

[0136] In this embodiment, when the comprehensive credibility is not lower than the preset threshold, the claims review system 200 uses the first sub-result in the claims settlement result as the basis for judging whether to support second-level review, and the judgment result is more reliable.

[0137] Exemplarily, the first credibility can characterize the credibility level, credibility grade, or accuracy of the claim settlement amount output by the claim adjustment model. The second credibility can characterize the credibility level, credibility grade, or accuracy of the first sub-result and the second sub-result output by the claim verification model. The claim review system 200 can determine the weights corresponding to the first credibility and the second credibility respectively, and perform weighted summation on the first credibility and the second credibility to obtain the comprehensive credibility.

[0138] In addition, the claim review system 200 can also preset risk rules in advance. When it is determined based on the comprehensive credibility and the first sub-result in the claim verification result that the target case supports second-level review, the claim review system 200 can further make a judgment based on the risk rules. If it is determined that the risks involved in the risk rules cannot be avoided, the claim review system 200 finally determines that the target case does not support second-level review; if it is determined that the risks involved in the risk rules can be avoided, the claim review system 200 finally determines that the target case supports second-level review. The risk rules include but are not limited to: whether the claim settlement amount is less than or equal to the amount threshold, whether the type of the target case belongs to the range of case types for which the claim verification result is given within a short time, etc.

[0139] It should be noted that this specification does not limit the sequence of the claim review system 200's judgment of the comprehensive credibility, the first sub-result, and the risk rules.

[0140] Exemplarily, the claim review system 200 can also make a judgment on the risk rules before making a judgment based on the first sub-result, or based on the first sub-result and the comprehensive credibility. If it is determined that the risks involved in the risk rules cannot be avoided, the claim review system 200 can directly determine that the target case does not support second-level review without subsequent further judgment to save computing resources. If it is determined that the risks involved in the risk rules can be avoided, the claim review system 200 makes a further judgment based on the first sub-result, or based on the first sub-result and the comprehensive credibility. The judgment method refers to the description above and will not be elaborated.

[0141] Through the above method, the claim review system 200 can determine whether the target case supports second-level review. First, the execution process of the claim review system 200 when the target case supports second-level review will be introduced below.

[0142] Continue to refer to Figure 4 , when the server 20 determines that the target case supports second-level review, it can prompt the user through the client 10 that the target case supports second-level review.

[0143] Specifically, refer to Figure 5 , the client 10 displays on the interactive page B that the second-level review is supported for the user, or can also display the following prompt information on the interactive page B: "The review result will be out soon. Please wait online." (Figure 5 (not shown). After prompting the user, the client 10 can also display a countdown to the user through the interaction page C, and the countdown can be displayed based on the second-level duration preconfigured by the claims review system 200. For example, if the preconfigured second-level duration is 10 s (seconds), the countdown on the interaction page C starts from 10 s.

[0144] In some embodiments, after determining that the target case supports second-level review, the server 20 can determine the first review result of the target case based on the claims settlement result and / or the adjustment result.

[0145] When the claims review system 200 is the payor itself, the server 20 can display the first review result online to the user through the interaction interface of the client 10. The duration from the moment when the user submits the claims request to the moment when the first review result is displayed to the user is the second-level duration.

[0146] When the claims review system 200 is a partner of the payor, as Figure 4 shown, the server 20 sends the first review result and the case information to the payor. After receiving the case information, the payor can determine the second review result based on the case information and send the second review result to the server 20. If the server 20 receives the second review result from the payor within the target duration specified for the second-level review, the second review result is used as the review result of the second-level review, and the review result of the second-level review is displayed online through the interaction interface of the client 10. The target duration is less than the second-level duration. The second review result and the first review result may be the same, or the second review result is the review result obtained by the payor based on the case information to correct the first review result.

[0147] It should be noted that this specification does not limit the specific content fed back by the payor to the server 20. For example, if the second review result determined by the payor is the same as the first review result, the payor can feedback instruction information such as agreeing to the first review result to the server 20 within the target duration.

[0148] The claims review system 200 can interact with the payor by using an interaction task asynchronous to the claims review task. As Figure 4 shown, when the target duration has passed and the server 20 has not received the second review result from the payor, the server 20 uses the first review result as the review result of the second-level review and displays the review result of the second-level review through the interaction interface of the client 10. This avoids the problem that the claims review system 200 cannot display the review conclusion to the user due to the untimely response of the payor, resulting in the failure of the second-level review.

[0149] Continue to refer to Figure 4The duration from the submission time of the claim request to the display time of the audit result of the second-level audit is the second-level duration T 1 The claim audit system 200 can immediately inform the user of the audit result of the target case within a short time, improving the user's claim experience.

[0150] It should be noted that if the second sub-result in the claim settlement result indicates non-support for claim settlement, the server 20 can directly determine the first audit result based on the claim settlement result. If the second sub-result in the claim settlement result indicates support for claim settlement, the server 20 can determine the first audit result based on the claim settlement result and the adjustment result.

[0151] In some embodiments, when the second sub-result in the claim settlement result indicates that the target case does not support claim settlement, the first audit result includes non-support for claim settlement; or, when the second sub-result indicates that the target case supports claim settlement, the first audit result includes support for claim settlement and the claim amount.

[0152] Exemplarily, when the first audit result includes support for claim settlement and the claim amount, the first audit result may further include the detailed content corresponding to the claim amount. Thus, the claim audit system 200 can record the detailed content of the claim amount for subsequent verification. The claim audit system 200 can also display the detailed content to the user through the interaction page, enabling the user to be more clear about the details of the claim amount and comprehensively understand the specific situation of the claim settlement, thereby improving the user's claim experience.

[0153] Exemplarily, when the first audit result includes non-support for claim settlement, the first audit result further includes the basis for the conclusion of non-support for claim settlement. Thus, the claim audit system 200 can reverse-infer the reliability of the first audit result based on the basis for the conclusion, and thus more accurately display the audit result to the user.

[0154] The content format and content dimension of the second audit result are similar to those of the first audit result. For details, please refer to the above description of the first audit result and will not be elaborated here.

[0155] Continue to refer to Figure 5 , when the audit result of the second-level audit includes support for claim settlement and the claim amount, the client 10 can display the audit result to the user through the interaction page D1. When the audit result of the second-level audit includes non-support for claim settlement, the client 10 can display the audit result to the user through the interaction page D2. In addition, the interaction page D1 can also display the detailed content of the claim amount to the user, and the interaction page D2 can also display the basis for the conclusion of non-support for claim settlement to the user ( Figure 5 not shown).

[0156] In some embodiments, when the claims settlement review system 200 determines that the target case does not support second-level review based on the underwriting results, it prompts in the interaction interface that the target case does not support second-level review and prompts the user not to wait online for the review results.

[0157] Specifically, the manner in which the server 20 determines that the target case does not support second-level review refers to the above and will not be elaborated here.

[0158] Exemplarily, as Figure 6 shown, when the server 20 determines that the target case does not support second-level review, it can display to the user the non-support for second-level review and the above prompt information through the client 10. Thus, the user can know the review progress of the target case and whether they need to continue waiting online for the review results based on the display content of the client 10.

[0159] Continuing to refer to Figure 6 , when it is determined that the target case does not support second-level review, the server 20 can generate a normal review task for the target case without considering the limit of the second-level duration and conduct manual review or other review methods. After the server 20 obtains the review results of the target case, it sends the review results to the client 10. The client 10 can prompt the user of the review results in the form of a background notification.

[0160] Continuing to refer to Figure 6 , the duration from the submission moment of the claims request to the moment when the prompt information is displayed to the user is the second-level duration T 2 . The claims settlement review system 200 can immediately inform the user within a short time whether they need to wait online for the review results, avoiding the problem that the user blindly waits without perception, thus affecting the claims experience.

[0161] Specifically, referring to Figure 7 , when the target case does not support second-level review, after the user submits a claims request on the interaction page A, they can learn from the interaction page B within the second-level duration that the target case does not support second-level review and prompt information such as not needing to continue waiting online.

[0162] It should be noted that in the claims settlement review method P300 provided in this specification, the loss adjustment operation and the underwriting operation are parallel and do not affect each other. Therefore, some parts of the loss adjustment operation and some parts of the underwriting operation can be carried out simultaneously. The above examples illustrate some parts that can be executed simultaneously, but this specification is not limited to this. For example, there can be other implementation methods that conform to the execution logic of the claims settlement review system 200 and execute some parts simultaneously to shorten the review duration, which will not be listed one by one.

[0163] In addition, when introducing the claims settlement review method P300 in this specification, the reimbursement-based claims settlement cases are mainly taken as examples for introduction. Therefore, the specific content involved (such as voucher documents, voucher information, adjustment rules, claims verification rules, or risk rules, etc.) is also based on this type of cases. However, this specification is not limited thereto. When applying the claims settlement review method P300 to other types of cases, the specific content can be adaptively adjusted based on the case types of other cases, and will not be listed one by one.

[0164] In summary, the claims settlement review method and system provided in this specification can, after a user submits a claims settlement request for a target case, perform adjustment operations and claims verification operations in parallel based on the case information of the target case, and can immediately notify whether the submitted case supports second-level review within a short time. For cases that meet the second-level review requirements, the claims settlement review duration can be shortened to the second-level duration, and the review conclusion of the second-level review can be immediately feedback to the user. The solution provided in this specification can improve the review efficiency and enhance the user's claims settlement experience on the premise of ensuring the accuracy of the review results, and promote the progress of the claims settlement industry in terms of review timeliness and accuracy.

[0165] On the other hand, this specification provides a computer-readable non-transitory storage medium storing at least one set of executable instructions for performing claims settlement review. When the executable instructions are executed by a processor, the executable instructions direct the processor to implement the steps of method P300 described in this specification. In some possible implementation manners, various aspects of this specification may also be implemented in the form of a program product, which includes program code. When the program product runs on a claims settlement review system 200, the program code is used to cause the claims settlement review system 200 to execute the steps of method P300 described in this specification. The program product for implementing the above method may be a portable compact disc read-only memory (CD-ROM) including program code and may run on the claims settlement review system 200. However, the program product of this specification is not limited thereto. In this specification, the readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in conjunction with an instruction execution system. The program product may be any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. The computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium may also be any readable medium other than the readable storage medium, and the readable medium may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code included on the readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above. The program code for performing the operations of this specification may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the claims settlement review system 200, partially on the claims settlement review system 200, executed as a stand-alone software package, partially on the claims settlement review system 200 and partially on a remote computing device, or entirely on a remote computing device.

[0166] The term "and / or" in the embodiments of this specification describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0167] The terms "first", "second", etc. in this specification are used to distinguish similar or like objects or entities, and do not necessarily imply a limitation on a specific order or sequence.

[0168] The "plurality" mentioned in this specification should be understood to mean two or more if there is no special statement.

[0169] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require a specific order or a sequential order to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0170] In summary, after reading this detailed disclosure, those skilled in the art will understand that the foregoing detailed disclosure may be presented only by way of example and may not be restrictive. Although not explicitly stated here, those skilled in the art can understand that this specification is intended to encompass various reasonable changes, improvements, and modifications to the embodiments. These changes, improvements, and modifications are intended to be proposed by this specification and are within the spirit and scope of the exemplary embodiments of this specification.

[0171] In addition, certain terms in this specification have been used to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" mean that the specific features, structures, or characteristics described in connection with that embodiment may be included in at least one embodiment of this specification. Therefore, it should be emphasized and understood that two or more references to "an embodiment" or "one embodiment" or "alternative embodiments" in various parts of this specification do not necessarily all refer to the same embodiment. Additionally, the specific features, structures, or characteristics may be appropriately combined in one or more embodiments of this specification.

[0172] It should be understood that in the foregoing description of the embodiments of this specification, for the purpose of helping to understand a feature and for the purpose of simplifying this specification, this specification combines various features in a single embodiment, drawing or its description. However, this does not mean that the combination of these features is necessary. When reading this specification, those skilled in the art may very well mark out some of the devices as separate embodiments for understanding. That is to say, the embodiments in this specification can also be understood as the integration of multiple sub-embodiments. And it also holds when the content of each sub-embodiment is less than all the features of a single foregoing disclosed embodiment.

[0173] Each patent, patent application, published patent application, and other materials cited in this disclosure, such as articles, books, specifications, publications, documents, literature, etc. (excluding any historical examination documents related thereto), are cited for all purposes related to this disclosure. For example, they are cited in the specification and claims of this disclosure. However, if there are any inconsistencies or conflicts between the descriptions, definitions, and / or terms of the above materials and the descriptions, definitions, and / or terms used in this disclosure, the descriptions, definitions, and / or terms used in this disclosure shall prevail.

[0174] Finally, it should be understood that the embodiments of the application disclosed herein are illustrative of the principles of the embodiments of this specification. Other modified embodiments are also within the scope of this specification. Therefore, the embodiments disclosed in this specification are merely examples and not limitations. Those skilled in the art can adopt alternative configurations based on the embodiments in this specification to implement the application in this specification. Therefore, the embodiments of this specification are not limited to the embodiments precisely described in the application.

Claims

1. A claims review method, comprising: In response to a claim settlement request submitted by a user in an interactive interface for a target case, obtaining case information of the target case; Based on the case information, a settlement operation and a claims verification operation are performed in parallel to obtain a settlement result and a claims verification result, wherein the settlement result at least represents the claims amount of the target case, and the claims verification result at least represents whether the target case supports second-level review and whether it supports claims; as well as In the case where it is determined based on the claims verification result that the target case supports second-level review, a prompt is given in the interactive interface that the target case supports second-level review, a review result of the second-level review is determined based on the claims verification result and the settlement result, and the review result is displayed in the interactive interface, the review result including whether the claim is supported and / or the claim amount, The time between the submission of the claim request and the display of the review result is in seconds.

2. The method according to claim 1, wherein: The case information includes settlement voucher information and claim verification voucher information. The parallel execution of settlement operations and claim verification operations based on the case information to obtain settlement results and claim verification results includes the parallel execution of the following two items: Performing the adjustment operation on the adjustment voucher information by using an adjustment model to obtain the adjustment result, wherein the adjustment model is a pre-trained model and has the ability to determine the adjustment result based on the adjustment voucher information; as well as The claim verification operation is performed on the claim verification voucher information through a claim verification model to obtain the claim verification result. The claim verification model is a pre-trained model and has the ability to determine the claim verification result based on the claim verification voucher information.

3. The method according to claim 2, wherein: The obtaining of case information of the target case includes: Obtaining the claim verification voucher document and the settlement voucher document of the target case based on the claim settlement request; and Information is extracted from the claim verification voucher document and the settlement voucher document through a text recognition model to obtain the claim verification voucher information and the settlement voucher information.

4. The method according to claim 3, wherein: The method is applied to a claim review system, and obtaining the settlement voucher document of the target case based on the claim request includes one of the following: If the user has uploaded the settlement voucher document, the settlement voucher document uploaded by the user is parsed from the claim request; or In the case that the user has not uploaded the settlement voucher document, the basic information filled in by the user for the target case is parsed from the claim request, and the settlement voucher document is obtained from an external data source based on the basic information. The external data source is a data source outside the claim review system.

5. The method according to claim 3, wherein: The method is applied to a claim review system, and obtaining the claim verification document of the target case based on the claim request includes one of the following: If the user has uploaded the claim verification document, the claim verification document uploaded by the user is parsed from the claim request; or In the case that the user has not uploaded the claim verification document, the basic information filled in by the user for the target case is parsed from the claim request, and the claim verification document is obtained from an external data source based on the basic information. The external data source is a data source outside the claim review system.

6. The method according to claim 2, wherein: The performing the adjusting operation on the adjusting voucher information through the adjusting model to obtain the adjusting result includes: Determining the case type of the target case; Determining a target settlement rule corresponding to the target case based on the case type; and The target adjustment rule and the adjustment voucher information are input into the adjustment model to obtain the adjustment result.

7. The method according to claim 6, wherein: The settlement model is pre-trained based on a plurality of first sample data, each of which includes settlement rules and settlement voucher information corresponding to a sample claim case.

8. The method according to claim 2, wherein: The performing the claim verification operation on the claim verification voucher information through the claim verification model to obtain the claim verification result includes: Determining the case type of the target case; Determining a target claims settlement rule corresponding to the target case based on the case type; and The target claims verification rule and the claims verification voucher information are input into the claims verification model to obtain the claims verification result.

9. The method according to claim 8, wherein: The claims verification model is pre-trained based on a plurality of second sample data, each second sample data including claims verification rules and claims verification voucher information corresponding to a sample claims case.

10. The method according to claim 1, wherein: The step of determining the audit result of the second-level audit based on the claim verification result and the settlement result, and displaying the audit result in the interactive interface, includes: Determine a first review result of the target case based on the claims verification result and / or the settlement result; Sending the first review result and the case information to the payee; and If a second audit result is received from the payee within the target time specified for the second-level audit, the second audit result will be displayed in the interactive interface, wherein the second audit result is consistent with the first audit result, or the second audit result is an audit result obtained by the payee after modifying the first audit result based on the case information.

11. The method according to claim 10, wherein: The method further comprises: If the second review result is not received from the payee within the target time period, the first review result is displayed in the interactive interface.

12. The method according to claim 10, wherein: When the claim verification result indicates that the target case does not support claim settlement, the first review result includes not supporting claim settlement; or When the claim verification result indicates that the target case supports the claim, the first review result includes supporting the claim and the claim amount.

13. The method according to claim 12, wherein: In the case where the first audit result includes support for claim settlement and the claim amount, the first audit result also includes detailed content corresponding to the claim amount.

14. The method according to claim 12, wherein: When the first audit result includes not supporting the claim, the first audit result also includes the basis for the conclusion of not supporting the claim.

15. The method according to claim 1, wherein: The determination of the target case based on the claim verification result supports a second-level review, including: When the claims settlement result indicates that the target case supports second-level review, it is determined that the target case supports second-level review.

16. The method according to claim 1, wherein: The settlement result further represents a first credibility corresponding to the claim amount, and the claim verification result further represents a second credibility corresponding to whether the second-level review is supported. The method further includes: determining a comprehensive credibility based on the first credibility and the second credibility; The determination of the target case based on the claim verification result supports a second-level review, including: When the comprehensive credibility is greater than or equal to a preset threshold and the claim settlement result indicates that the target case supports second-level review, it is determined that the target case supports second-level review.

17. The method according to claim 1, wherein: The method further comprises: When it is determined based on the claims verification result that the target case does not support second-level review, the interactive interface prompts that the target case does not support second-level review, and prompts the user that there is no need to wait online for the review result.

18. A system comprising: at least one storage medium storing at least one instruction set; as well as At least one processor is communicatively connected to the at least one storage medium, wherein the at least one processor reads the at least one instruction set when running, and executes the method as described in any one of claims 1-17 according to the instructions of the at least one instruction set.

Images