CN114581917A

CN114581917A - Insurance claim settlement service processing method and device combining RPA and AI and electronic equipment

Info

Publication number: CN114581917A
Application number: CN202210173950.9A
Authority: CN
Inventors: 王维强; 彭名
Original assignee: Laiye Technology Beijing Co Ltd
Current assignee: Laiye Technology Beijing Co Ltd
Priority date: 2022-02-24
Filing date: 2022-02-24
Publication date: 2022-06-03

Abstract

The application relates to an insurance claim settlement service processing method, device and electronic equipment combining RPA and AI, relating to the technical field of RPA and AI, applied to a man-machine cooperation platform, and comprising the following steps: acquiring a to-be-processed cooperative identification task, and acquiring target claim settlement data associated with the cooperative identification task from a preset position; processing the collaborative identification task based on the target claim settlement data to obtain a second identification result corresponding to the target claim settlement data; and storing the second recognition result to a preset position, so that the RPA robot acquires the second recognition result from the preset position and carries out claim settlement according to the second recognition result. The method has the advantages that the insurance claim settlement service is automatically processed in a mode of combining the RPA robot with the AI and the human-computer cooperation platform, labor cost is reduced, service processing efficiency is improved, a more accurate second recognition result corresponding to target claim settlement data can be obtained by the human-computer cooperation platform, claim settlement is carried out according to the second recognition result, and accuracy of insurance claim settlement service processing can be improved.

Description

Insurance claim settlement service processing method and device combining RPA and AI and electronic equipment

Technical Field

The application relates to the technical field of robot flow automation and artificial intelligence, in particular to an insurance claim settlement service processing method and device combining RPA and AI and electronic equipment.

Background

Robot Process Automation (RPA for short) simulates the operation of a human on a computer through specific robot software, and automatically executes a Process task according to rules.

Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, techniques and application systems for simulating, extending and expanding human Intelligence.

Currently, many cumbersome and repetitive services require manual handling. For example, for insurance claim settlement service, a worker is required to search a claim request mail to be processed in a mail system at regular time, download claim data such as a claim table and a bill from the claim request mail, manually identify text information required for claim settlement from the claim data, fill the text information in a corresponding position of the claim system, and submit a claim request. In the service processing mode, the whole process needs to be operated manually, and when the service volume is large, a large amount of labor cost and time cost need to be consumed, so that the service processing efficiency is low. How to improve the processing efficiency of insurance claim settlement business and reduce labor cost becomes a problem to be solved urgently.

Disclosure of Invention

The application provides an insurance claim settlement service processing method, an insurance claim settlement service processing device and electronic equipment which are combined with RPA and AI, and aims to solve the technical problems of low processing efficiency and high labor cost of the insurance claim settlement service processing method in the related technology.

An embodiment of a first aspect of the present application provides an insurance claim settlement service processing method combining an RPA and an AI, which is applied to a human-computer collaboration platform, and the method includes: acquiring a to-be-processed cooperative identification task, and acquiring target claim settlement data associated with the cooperative identification task from a preset position; the cooperative identification task is issued by the RPA robot under the condition that the first identification result does not meet the preset condition after the RPA robot performs text identification on the target claim data based on an Optical Character Recognition (OCR) technology and acquires the first identification result corresponding to the target claim data; the target claim settlement data is stored to a preset position by the RPA robot; processing the collaborative identification task based on the target claim settlement data to obtain a second identification result corresponding to the target claim settlement data; and storing the second recognition result to a preset position, so that the RPA robot acquires the second recognition result from the preset position and carries out claim settlement according to the second recognition result.

The embodiment of the second aspect of the application provides an insurance claim settlement service processing method combining RPA and AI, which is applied to an RPA robot and comprises the following steps: acquiring target claim settlement data to be processed; performing text recognition on the target claim data based on an Optical Character Recognition (OCR) technology to obtain a first recognition result corresponding to the target claim data; under the condition that the first recognition result does not meet the preset condition, issuing a collaborative recognition task related to the target claim data to the man-machine collaborative platform, and storing the target claim data to a preset position; processing the collaborative identification task based on the target claim data in response to the man-machine collaborative platform to obtain a second identification result corresponding to the target claim data, storing the second identification result to a preset position, and acquiring the second identification result from the preset position; and carrying out claim settlement according to the second recognition result.

An embodiment of a third aspect of the present application provides an insurance claim settlement service processing apparatus combining an RPA and an AI, which is applied to a human-computer collaboration platform, and the apparatus includes: the first acquisition module is used for acquiring a to-be-processed cooperative identification task and acquiring target claim settlement data associated with the cooperative identification task from a preset position; the cooperative identification task is issued by the RPA robot under the condition that the first identification result does not meet the preset condition after the RPA robot performs text identification on the target claim data based on an Optical Character Recognition (OCR) technology and acquires the first identification result corresponding to the target claim data; the target claim settlement data is stored to a preset position by the RPA robot; the first processing module is used for processing the collaborative identification task based on the target claim settlement data to obtain a second identification result corresponding to the target claim settlement data; and the first storage module is used for storing the second recognition result to a preset position so that the RPA robot can obtain the second recognition result from the preset position and carry out claim settlement according to the second recognition result.

An embodiment of a fourth aspect of the present application provides an insurance claim settlement service processing device combining an RPA and an AI, which is applied to an RPA robot, and the device includes: the fourth acquisition module is used for acquiring target claim settlement data to be processed; the recognition module is used for performing text recognition on the target claim data based on an Optical Character Recognition (OCR) technology to acquire a first recognition result corresponding to the target claim data; the third processing module is used for issuing a collaborative identification task related to the target claim settlement data to the man-machine collaborative platform and storing the target claim settlement data to a preset position under the condition that the first identification result does not meet the preset condition; the fifth acquisition module is used for responding to the human-computer cooperation platform and processing the cooperation recognition task based on the target claim data to obtain a second recognition result corresponding to the target claim data, storing the second recognition result to a preset position and acquiring the second recognition result from the preset position; and the fourth processing module is used for carrying out claim settlement according to the second recognition result.

An embodiment of a fifth aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the method according to the embodiment of the first aspect of the present application or to implement the method according to the embodiment of the second aspect of the present application.

An embodiment of a sixth aspect of the present application proposes a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements a method according to an embodiment of the first aspect of the present application or implements a method according to an embodiment of the second aspect of the present application.

An embodiment of a seventh aspect of the present application proposes a computer program product comprising a computer program which, when executed by a processor, implements a method as described in the embodiment of the first aspect of the present application above, or implements a method as described in the embodiment of the second aspect of the present application above.

The technical scheme provided by the embodiment of the application can have the following beneficial effects:

acquiring a collaborative recognition task to be processed through a man-machine collaborative platform, and acquiring target claim data associated with the collaborative recognition task from a preset position, wherein the collaborative recognition task is issued when the first recognition result does not meet the preset condition after the RPA robot performs text recognition on the target claim data based on an Optical Character Recognition (OCR) technology and acquires the first recognition result corresponding to the target claim data, the target claim data is stored in the preset position by the RPA robot, the collaborative recognition task is processed based on the target claim data to acquire a second recognition result corresponding to the target claim data, the second recognition result is stored in the preset position so that the RPA robot acquires the second recognition result from the preset position and performs claim settlement according to the second recognition result, and the automatic processing of insurance claim services through the combination of the RPA robot and the man-machine collaborative platform is realized, the labor cost is reduced, the service processing efficiency is improved, the more accurate second recognition result corresponding to the target claim settlement data can be obtained by the man-machine cooperation platform, then the claim settlement is carried out according to the second recognition result, and the accuracy of insurance claim settlement service processing can be improved.

Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.

Drawings

In the drawings, like reference characters designate like or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily to scale. It is appreciated that these drawings depict only some embodiments in accordance with the disclosure and are therefore not to be considered limiting of its scope.

Fig. 1 is a schematic flow chart of an insurance claim settlement service processing method according to a first embodiment of the present application, which combines RPA and AI;

FIG. 2 is a flow chart of an insurance claim settlement service processing method according to a second embodiment of the present application, which combines RPA and AI;

FIG. 3 is an exemplary diagram of a collaborative action creation interface according to a second embodiment of the present application;

FIG. 4 is an exemplary diagram of a process setting interface according to a second embodiment of the present application;

FIG. 5 is an exemplary diagram of a task interface according to a second embodiment of the present application;

FIG. 6 is an exemplary diagram of a task chain interface according to a second embodiment of the present application;

FIG. 7 is a flowchart illustrating a method for processing insurance claim services according to a third embodiment of the present application;

FIG. 8 is a flow chart of an insurance claim settlement service processing method according to a fourth embodiment of the present application, combining RPA and AI;

fig. 9 is a schematic flow chart of an insurance claim settlement service processing method according to a fifth embodiment of the present application, which combines RPA and AI;

fig. 10 is a schematic structural diagram of an insurance claim settlement service processing apparatus according to a sixth embodiment of the present application, which combines RPA and AI;

fig. 11 is a schematic structural diagram of an insurance claim settlement service processing apparatus according to a seventh embodiment of the present application, which combines RPA and AI;

fig. 12 is a block diagram of an electronic device for implementing the insurance claim settlement service processing method in combination with RPA and AI according to the embodiment of the present application.

Detailed Description

Reference will now be made in detail to the embodiments of the present application/disclosure, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application/disclosure, and should not be construed as limiting the present application/disclosure.

These and other aspects of the embodiments of the present application/disclosure will be apparent with reference to the following description and attached drawings. In the description and drawings, particular embodiments of the present application/disclosed embodiments are disclosed in detail as being indicative of some of the ways in which the principles of the present application/disclosed embodiments may be practiced, but it is understood that the scope of the present application/disclosed embodiments is not limited thereby. Rather, the embodiments of the application/disclosure include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.

It should be noted that, in the technical solution of the present disclosure, the acquisition, storage, application, and the like of the personal information of the related user all conform to the regulations of the related laws and regulations, and do not violate the customs of the public order.

The application provides a way of combining RPA, AI and man-machine cooperation platform to process the idea of insurance claim settlement service. After target claim data to be processed is obtained through the RPA robot, text recognition is carried out on the target claim data, a first recognition result corresponding to the target claim data is obtained, when the first recognition result does not meet preset conditions, a collaborative recognition task is issued to a man-machine collaborative platform, the target claim data is stored in a preset position, the man-machine collaborative platform obtains the target claim data managed by the collaborative recognition task from the preset position, the collaborative recognition task is processed based on the target claim data, a second recognition result corresponding to the target claim data is obtained, the second recognition result is stored in the preset position, then the RPA robot obtains the second recognition result from the preset position, claim is carried out according to the second recognition result, automatic processing of insurance claim services through a mode that the RPA robot combines AI and the man-machine collaborative platform is achieved, labor cost is reduced, the service processing efficiency is improved, the more accurate second recognition result corresponding to the target claim settlement data can be obtained by using the man-machine cooperation platform, and then the claim settlement is carried out according to the second recognition result, so that the accuracy of insurance claim settlement service processing can be improved.

For the purpose of clearly explaining the embodiments of the present invention, terms related to the embodiments of the present invention will be explained first.

In the description of the present application/disclosure, the term "plurality" means two or more.

In the description of the present application, the "RPA robot" refers to a software robot that can automatically perform business processing in conjunction with AI technology and RPA technology. The RPA robot has two characteristics of 'connector' and 'non-invasion', and extracts, integrates and communicates data of different systems in a non-invasive mode on the premise of not changing an information system by simulating an operation method of a human.

In the description of the application, the man-machine cooperation platform refers to a platform for connecting the cooperation of an artificial and a robot, tasks needing manual judgment and decision can be distributed to the artificial in an automatic process by using the man-machine cooperation platform, and the artificial provides accurate input for the robot through operations such as form information input and information secondary check and confirmation, so that more and safer automatic opportunities are created.

In the description of the application, the "cooperative identification task" refers to an identification task that needs to be completed by a human-computer cooperation platform in cooperation with an RPA robot. The cooperative classification task refers to a classification task which needs to be finished by a man-machine cooperation platform and an RPA robot in a cooperative mode.

In the description of the present application, the "flow management and control platform" refers to a flow management and control platform of the RPA robot, and provides functions of designing and managing an execution flow of the RPA robot belonging to the control platform.

In the description of the present application, "target claim data" refers to data required for claim settlement in the current insurance claim settlement business process, such as a claim table filled by a user, a bill issued by a medical institution, and the like.

In the description of the present application, "OCR (Optical Character Recognition)", specifically refers to a process in which an electronic device checks a Character printed on paper, determines its shape by detecting dark and light patterns, and then translates the shape into a computer text by a Character Recognition method; the method is characterized in that characters in a paper document are converted into an image file with a black-white dot matrix in an optical mode aiming at print characters, and the characters in the image are converted into a text format through recognition software for further editing and processing by word processing software.

In the description of the present application, "key field" and "key information" are both fragments composed of a single character or a plurality of continuous characters, and "key field" and "key information" may be understood as an attribute item key and an attribute value, respectively, and have a corresponding relationship between the key field and the key information, and the key field and the corresponding key information together constitute a piece of structured data. For example, "zhang san" is key information corresponding to the key field "name", and "name" and "zhang san" constitute a piece of structured data; "157 XXXXXXXX" is key information corresponding to the key field "phone number", and "phone number" and "157 XXXXXXXX" constitute a piece of structured data; "street, a city, B county, C" is key information corresponding to the key field "address", and "address" and "street, a city, B county, C" constitute one piece of structured data.

In the description of the present application, the "RPA robot control platform" refers to a management platform of an RPA robot, and provides functions of monitoring RPA robot clients belonging to the control platform, managing scheduled tasks, managing users and authorities, managing authorized permissions, and the like.

In the description of the present application, the "file transfer server" refers to a file server controlled by the RPA robot control platform, deployed on the RPA robot control platform, and capable of storing the RPA robot process generation and required files.

In the description of the present application, the "mail system" refers to a system that can realize processes of mail sending and receiving, editing, and the like. The "information management system" refers to a system that can implement management operations such as deletion, addition, modification, and the like of user information.

In the description of the present application, "confidence", also referred to as reliability or confidence level, confidence coefficient, is used to indicate the reliability of the processing result, such as the text recognition result or the classification result. The higher the confidence, the more accurate the processing result.

An insurance claim settlement service processing method, apparatus, electronic device, and storage medium according to embodiments of the present application/disclosure are described below with reference to the accompanying drawings.

First, a method for processing insurance claim settlement services by combining RPA and AI provided by the present application is described by taking a man-machine cooperation platform side as an example.

Fig. 1 is a flowchart illustrating an insurance claim settlement service processing method according to a first embodiment of the present application, in which RPA and AI are combined. As shown in fig. 1, the method may include the steps of:

step 101, acquiring a to-be-processed collaborative identification task, and acquiring target claim settlement data associated with the collaborative identification task from a preset position.

The cooperative identification task is issued by the RPA robot under the condition that the first identification result does not meet the preset condition after the RPA robot performs text identification on the target claim data based on an Optical Character Recognition (OCR) technology and acquires the first identification result corresponding to the target claim data; the target claim data is saved to a preset position by the RPA robot.

It should be noted that the insurance claim service processing method combining the RPA and the AI according to the embodiment of the present application may be executed by an insurance claim service processing apparatus combining the RPA and the AI, and hereinafter, the insurance claim service processing apparatus combining the RPA and the AI is simply referred to as an insurance claim service processing apparatus. For example, the insurance claim settlement service processing apparatus may be a human-computer cooperation platform, or the insurance claim settlement service processing apparatus may be configured in the human-computer cooperation platform, which is not limited in this application.

The human-machine cooperation platform may be configured in an electronic device, and the electronic device may include, but is not limited to, a terminal device, a server, and the like. The embodiment of the application takes an insurance claim settlement service processing device as an example of a man-machine cooperation platform installed in a terminal device.

The man-machine cooperation platform in this embodiment may execute the method in real time in a specific time period or all day, which is not limited in this application. Wherein the specific time period can be set as desired.

Or, the human-computer cooperation platform can be started based on the received starting instruction. For example, the worker can trigger the starting instruction for the man-machine cooperation platform in a dialogue mode. The triggering of the start instruction for the human-computer cooperation platform may be implemented in various ways, for example, the start instruction for the human-computer cooperation platform may be triggered in a manner of voice and/or text, and for example, the start instruction for the human-computer cooperation platform may also be triggered in a manner of triggering a designated control on a dialog interaction interface, which is not specifically limited in this embodiment of the present application.

The preset position is a preset file storage position and can be set according to needs, for example, the preset position can be a certain folder in the transit server.

Wherein the preset condition may include: the first identification result comprises second key information corresponding to at least one target key field, and a first confidence corresponding to each second key information is higher than a first preset threshold. The first preset threshold value can be set arbitrarily according to needs. And the target key field is a key field which needs to be identified from the target claim settlement data in the process of processing the insurance claim settlement service.

The first recognition result does not satisfy the preset condition, and may include the following cases: the first identification result does not include second key information corresponding to all target key fields; the first identification result comprises second key information corresponding to all target key fields, but the condition that the first confidence corresponding to one or more second key information is not higher than a first preset threshold exists; the first identification result does not include second key information corresponding to all target key fields, and a condition that a first confidence degree corresponding to the second key information corresponding to one or more target key fields included in the first identification result is not higher than a first preset threshold value exists; the first identification result does not include second key information and the like corresponding to a specific target key field in all the target key fields.

In the embodiment of the application, the RPA robot can acquire target claim data to be processed, and perform text recognition on the target claim data based on an Optical Character Recognition (OCR) technology to acquire a first recognition result corresponding to the target claim data. Under the condition that the RPA robot determines that the first recognition result meets the preset condition, namely that the key information corresponding to all the target key fields is determined and recognized, and the accuracy of the recognized key information is high, the claim settlement can be carried out according to the first recognition result; under the condition that the RPA robot determines that the first recognition result does not meet the preset condition, namely that the key information corresponding to all target key fields is not recognized and/or the certainty of the recognized key information is low, the RPA robot can issue a cooperative recognition task to the man-machine cooperative platform, so that the man-machine cooperative platform and the RPA robot cooperate to complete accurate recognition of the target claim data.

And 102, processing the collaborative identification task based on the target claim settlement data to obtain a second identification result corresponding to the target claim settlement data.

In the embodiment of the application, under the condition that the RPA robot determines that the first recognition result corresponding to the target claim data does not meet the preset condition, the cooperative recognition task can be issued to the human-computer cooperative platform, and the target claim data is stored in a preset position in a correlated manner, so that after the human-computer cooperative platform acquires the cooperative recognition task, the target claim data correlated to the cooperative recognition task can be acquired from the preset position, and the cooperative recognition task is processed based on the target claim data to acquire the second recognition result corresponding to the target claim data.

It should be noted that, in a possible implementation form, the RPA robot may further store the target claim data and the first recognition result in a preset position at the same time, so that after the human-computer collaboration platform obtains the collaborative recognition task, the target claim data and the first recognition result associated with the collaborative recognition task may be obtained from the preset position, and the collaborative recognition task is processed based on the target claim data and the first text recognition result to obtain a second recognition result corresponding to the target claim data.

The second recognition result corresponding to the target claim data may be obtained by automatically recognizing the target claim data based on an AI technology through the human-computer cooperation platform, or may be obtained by manually recognizing the target claim data, for example, directly recognizing the target claim data through manual work, or manually correcting the first recognition result corresponding to the target claim data, which is not limited in the present application.

Under the condition that the first recognition result corresponding to the target claim data acquired by the RPA robot does not meet the preset condition, the man-machine cooperation platform is utilized to acquire the corresponding second recognition result based on the target claim data, so that a more accurate and reliable recognition result of the target claim data can be acquired.

And 103, storing the second recognition result to a preset position, so that the RPA robot acquires the second recognition result from the preset position and carries out claim settlement according to the second recognition result.

In the embodiment of the application, the man-machine cooperation platform can store the second recognition result to the preset position, and then the RPA robot can obtain the second recognition result from the preset position and carry out claim settlement according to the second recognition result.

The insurance claim settlement service processing method combining the RPA and the AI, provided by the embodiment of the application, includes the steps of obtaining a to-be-processed collaborative recognition task through a man-machine collaborative platform, and obtaining target claim settlement data associated with the collaborative recognition task from a preset position, wherein the collaborative recognition task is issued by the RPA robot under the condition that the first recognition result does not meet the preset condition after text recognition is carried out on the target claim settlement data by the RPA robot based on an Optical Character Recognition (OCR) technology, processing the collaborative recognition task based on the target claim settlement data to obtain a second recognition result corresponding to the target claim settlement data, storing the second recognition result to the preset position to enable the RPA robot to obtain the second recognition result from the preset position and carry out claim settlement according to the second recognition result, the method has the advantages that the insurance claim settlement service is automatically processed in a mode of combining the RPA robot with the AI and the human-computer cooperation platform, labor cost is reduced, service processing efficiency is improved, a more accurate second recognition result corresponding to target claim settlement data can be obtained by the human-computer cooperation platform, claim settlement is carried out according to the second recognition result, and accuracy of insurance claim settlement service processing can be improved.

With reference to fig. 2, a process of processing the collaborative recognition task based on the target claim data by the human-computer collaborative platform and manually implementing the method for processing the insurance claim service by combining the RPA and the AI provided in the embodiment of the present application to obtain a second recognition result corresponding to the target claim data is further described. Fig. 2 is a flowchart illustrating a method for processing an insurance claim service by combining RPA and AI according to a second embodiment of the present application, where, as shown in fig. 2, the method includes:

step 201, obtaining a collaborative recognition task to be processed, and obtaining target claim settlement data associated with the collaborative recognition task from a preset position.

The cooperative identification task is issued by the RPA robot under the condition that the first identification result does not meet the preset condition after the RPA robot performs text identification on the target claim data based on an Optical Character Recognition (OCR) technology and acquires the first identification result corresponding to the target claim data; the target claim data is stored to a preset position by the RPA robot.

The specific implementation process and principle of step 201 may refer to the description of the foregoing embodiments, and are not described herein again.

Step 202, displaying the target claim settlement data and the input box corresponding to the second text result through the task interface corresponding to the collaborative recognition task.

And step 203, responding to the detected input information in the input box of the task interface, and acquiring a second identification result.

In the embodiment of the application, after the human-computer cooperation platform acquires the cooperative identification task to be processed, the task notification can be sent to the staff of the human-computer cooperation platform, so that the staff of the human-computer cooperation platform can log in the human-computer cooperation platform to perform task processing. When a worker of the human-computer cooperation platform logs in the human-computer cooperation platform to perform task processing, the human-computer cooperation platform can display a task interface corresponding to the cooperative identification task, target claim settlement data and an input box are displayed in the task interface, and the input box is used for inputting a manual identification result of the target claim settlement data. After the target claim settlement data are manually identified and a second identification result is obtained, the second identification result can be input into the input box, and then the man-machine cooperation platform can respond to the detected input information in the input box of the task interface and obtain the manually input second identification result.

Under the condition that a first recognition result corresponding to the target claim data acquired by the RPA robot does not meet a preset condition, a man-machine cooperation platform is utilized, and a second recognition result corresponding to the target claim data is acquired manually, so that a more accurate and reliable recognition result of the target claim data can be acquired.

In an embodiment of the application, the target claim settlement data may include structured data such as a ticket issued by a medical institution, and correspondingly, the second recognition result may include first key information corresponding to at least one target key field. In the embodiment of the application, the human-computer collaboration platform can display the input boxes corresponding to the first key information respectively through the task interface, so that after the target claim data are manually identified and the first key information corresponding to the target key fields is obtained, the first key information obtained through identification can be correspondingly input into the input boxes corresponding to the first key information, and then the human-computer collaboration platform can respond to the input information in the input boxes corresponding to the detected first key information of the task interface respectively and obtain the first key information corresponding to the target key fields manually input.

In the embodiment of the application, in order to enable the human-computer cooperation platform to process the cooperation recognition task in the above manner to obtain the second recognition result, a cooperation action may be created in the human-computer cooperation platform manually in advance. When creating the cooperative action, task content that needs to be processed manually in the cooperative identification task may be configured according to business needs, for example, which key fields in the form need to be identified manually, and field attribute information of the key fields to be identified. And moreover, task paths of the collaborative identification tasks can be configured according to business needs, namely, the human-computer collaborative platform obtains target claim settlement data associated with the collaborative identification tasks from which path, and stores the processing results of the tasks in which path after processing the collaborative identification tasks to obtain the processing results. In addition, a processing flow for processing the insurance claim service by combining the RPA robot and the human-computer cooperation platform may be written, in the process of executing the flow by the RPA robot, a link requiring manual assistance (for example, in the case where the RPA robot determines that the first recognition result corresponding to the target claim data does not satisfy the preset condition in the embodiment of the present application), a human-computer cooperation command is added, and the human-computer cooperation command is associated with the corresponding cooperation action, so that in the process of processing the insurance claim service, the RPA robot executes the link requiring manual assistance (for example, in the case where the RPA robot determines that the first recognition result corresponding to the target claim data does not satisfy the preset condition in the embodiment of the present application), the human-computer cooperation command may be triggered, the cooperation recognition task associated with the cooperation action is generated by the human-computer cooperation platform, and when the human-computer cooperation platform obtains the cooperation recognition task to be processed, target claim data associated with the collaborative recognition task can be acquired from the configured task path, the target claim data and input boxes of first key information corresponding to each configured key field are displayed through a task interface of the collaborative recognition task, and then the first key information corresponding to each target key field is acquired according to the input information in the input boxes corresponding to each first key information of the task interface. The field attribute information may include, for example, field identification of the field, field name, and other attribute information.

In the embodiment of the application, the human-computer collaboration platform may provide a collaboration action creation interface, and after manually selecting or inputting which key fields (i.e., target key fields in the embodiment of the application) need to be manually identified in the collaboration identification task through the collaboration action creation interface, setting field attribute information of the target key fields, and a task path of the collaboration identification task, an action configuration command may be triggered to create a collaboration action. Correspondingly, the human-computer cooperation platform can obtain an action configuration command, wherein the action configuration command comprises a field configuration command and a path configuration command, the field configuration command is used for configuring a target key field of the cooperation recognition task and field attribute information corresponding to the target key field, the path configuration command is used for configuring a task path of the cooperation recognition task, and further the human-computer cooperation platform can configure the target key field as the target key field to be recognized by the cooperation recognition task and configure the path corresponding to the preset position as the task path of the cooperation recognition task based on the field configuration command and the path configuration command.

In the embodiment of the application, a man-machine cooperative command can be added to a link needing manual assistance in the process of executing the flow of the RPA robot through the flow management and control platform, and the man-machine cooperative command is associated with the corresponding cooperative action in the man-machine cooperative platform, so that when the RPA robot encounters the link needing manual assistance in the process of executing the flow, the man-machine cooperative command can be triggered, a cooperative identification task associated with the cooperative action is generated on the man-machine cooperative platform, and the cooperative identification task is processed through the man-machine cooperative platform.

Correspondingly, in this embodiment of the present application, before step 201, the method may further include: acquiring an action configuration command associated with the collaborative identification task, wherein the action configuration command comprises a field configuration command and a path configuration command; configuring a target identification field of the cooperative identification task as a target key field based on the field configuration command, and configuring field attribute information of the target key field; and configuring the task path of the collaborative identification task as a path corresponding to the preset position based on the path configuration command.

Referring to fig. 3, in the embodiment of the present application, a human-machine collaboration platform may provide a collaboration action creation interface as shown in fig. 3, for example. The input box below the action name in the collaborative action creation interface is used for naming the action name of the collaborative action; the input box below "description" is used to roughly describe the cooperative action; "code" refers to the unique identification of a key field.

Taking an identification scene of the medical bill in the target claim settlement data as an example, when the medical bill needs to be identified in a manual cooperation mode, the cooperation action can be created through the cooperation action creation interface, wherein in the scene, the cooperation action can comprise reading, checking and modifying of a cooperation form, and the cooperation form can be created through the cooperation action creation interface, so that when the follow-up manual intervention is needed, workers of the human-computer cooperation platform only need to read, check and modify the cooperation form. Specifically, as shown below the "basic field" in fig. 3, the human-computer collaboration platform provides a plurality of form elements such as texts, dates and pictures, and as shown below the "layout field", the human-computer collaboration platform provides layout patterns such as dividing lines and grids for form design, and can manually drag each form element and layout pattern in a flexible dragging manner to quickly create a clear collaboration form. And, the target key fields in the collaborative form that need to be read, checked and modified manually, such as "bill number", "business flow", "medical institution type" and "medical insurance type" in fig. 3, can be manually input, and the attribute information of the fields is set through the input boxes below the "field attribute" shown on the right side in fig. 3. After the 'confirm' button is manually clicked, the man-machine cooperation platform can acquire a field configuration command, configure the target identification field of the cooperation identification task as a target key field based on the field configuration command, and configure the field attribute information of the target key field.

Referring to fig. 4, in the embodiment of the present application, the flow management and control platform may provide a flow setting interface as shown in fig. 4, for example, and a human-computer collaboration command may be added through the flow setting interface and associated with a corresponding collaboration form. As shown in the lower left corner of fig. 4, in the process of executing the process by the RPA robot, when it is determined that the first identification result corresponding to the target claim data does not meet the preset condition, the process setting interface may trigger the human-computer collaboration command, send the form to the human-computer collaboration platform, wait for the filling result, and obtain the content of the filling result of the form after manually filling the content of the form through the human-computer collaboration platform.

Referring to fig. 5, the human-computer collaboration platform can display medical tickets and collaboration forms that need to be manually identified through a task interface as shown in fig. 5. Wherein the medical ticket is shown in the position 501 in figure 5. Each target key field set through the action creation interface of fig. 3 and the corresponding input box of the first key information may be included in the collaboration form. When the RPA robot does not store the first recognition result in the preset position, the input box may not contain information, and a worker of the man-machine cooperation platform may input first key information corresponding to each target key field recognized manually in the input box; when the RPA robot stores the first recognition result in the preset position, the input box may include second key information corresponding to each target key field recognized by the RPA robot based on an OCR technology, and a worker of the human-computer collaboration platform may check and modify each second key information in the input box according to the first key information corresponding to each target key field recognized manually. After the staff of the human-computer cooperation platform clicks the 'confirm' button shown in fig. 5, the human-computer cooperation platform can respond to the detected input information in the input box corresponding to each first key information of the task interface, and acquire the first key information corresponding to each target key field.

And step 204, storing the second recognition result to a preset position, so that the RPA robot acquires the second recognition result from the preset position and carries out claim settlement according to the second recognition result.

Continuing with the above example, after the human-computer collaboration platform obtains the first key information corresponding to each target key field, the first key information corresponding to each target key field may be stored in the preset position, so that the RPA robot obtains the second recognition result from the preset position, and carries out claim settlement according to the second recognition result.

Referring to the example diagram of the task chain interface shown in fig. 6, in the embodiment of the present application, the human-computer collaboration platform may further provide a task chain, and record in detail the steps performed by the RPA robot and the manual operation steps of the human-computer collaboration task, so that the result of the manual processing may be tracked.

To sum up, in the method for processing an insurance claim service by combining an RPA and an AI provided in the embodiment of the present application, the human-computer collaboration platform obtains a collaborative recognition task to be processed, obtains target claim data associated with the collaborative recognition task from a preset position, displays the target claim data and an input box corresponding to a second text result through a task interface corresponding to the collaborative recognition task, obtains a second recognition result in response to input information in the input box of the detected task interface, stores the second recognition result in the preset position, so that the RPA robot obtains the second recognition result from the preset position, and carries out claim settlement according to the second recognition result, thereby realizing automatic processing of the insurance claim service by combining the RPA robot with the AI and the human-computer collaboration platform, and realizing automation for a flow needing manual review, only needing to manually check part of information, the labor cost is reduced, the service processing efficiency is improved, the more accurate second recognition result corresponding to the target claim settlement data can be obtained by the man-machine cooperation platform, then the claim settlement is carried out according to the second recognition result, and the accuracy of insurance claim settlement service processing can be improved.

In one possible implementation form, the preset location may be a first folder in the file relay server. With reference to fig. 7, a method for processing an insurance claim settlement service by combining RPA and AI according to an embodiment of the present application will be described below.

Fig. 7 is a flowchart illustrating a method for processing an insurance claim settlement service by combining RPA and AI according to a third embodiment of the present application, where as shown in fig. 7, the method may further include:

step 701, obtaining a collaborative identification task to be processed, and obtaining target claim settlement data associated with the collaborative identification task from a first folder in the file transfer server.

The file transfer server is deployed on the RPA robot control platform. The cooperative identification task is issued by the RPA robot under the condition that the first identification result does not meet the preset condition after the RPA robot performs text identification on the target claim data based on an Optical Character Recognition (OCR) technology and acquires the first identification result corresponding to the target claim data; the target claim data is of a first folder saved by the RPA robot to the file transfer server.

In an embodiment of the application, the human-computer collaboration platform may obtain target claim settlement data associated with the collaboration recognition task from a first folder in the file transfer server in the following manner: and sending a file downloading request to the RPA robot control platform, so that the RPA robot control platform obtains target claim settlement data from a first folder in the file transfer server based on the file downloading request, and transmits the target claim settlement data back to the man-machine cooperation platform.

Specifically, the human-computer cooperation platform may send a file downloading request to the RPA robot control platform, where the file downloading request carries a location path of the first folder and identification information of the target claim data, so that the RPA robot control platform finds the corresponding first folder in the file transfer server based on the location path in the file downloading request, downloads the target claim data from the corresponding first folder according to the identification information of the target claim data, and returns the target claim data to the human-computer cooperation platform.

Through the combination of the man-machine cooperation center and the file transfer server, the target claim settlement data associated with the cooperation recognition task can be stored in the first folder of the file transfer server, and the checking and processing of workers of the man-machine cooperation platform are facilitated.

And 702, displaying the target claim settlement data and the input box corresponding to the second text result through a task interface corresponding to the collaborative identification task.

And step 703, responding to the detected input information in the input box of the task interface, and acquiring a second identification result.

The specific implementation process and principle of step 702-703 may refer to the description of the foregoing embodiments, and are not described herein again.

Step 704, saving the second recognition result to the first folder in the file transfer server, so that the RPA robot obtains the second recognition result from the first folder in the file transfer server, and makes a claim according to the second recognition result.

In an embodiment of the application, the man-machine cooperation platform may store the second recognition result in the first folder in the file transfer server in the following manner: and sending a file uploading request to the RPA robot control platform so that the RPA robot control platform receives a second identification result based on the file uploading request and stores the second identification result to a first folder of the file transfer server.

Specifically, the man-machine cooperation platform may send a file uploading request to the RPA robot control platform, where the file downloading request carries a location path of the first folder, so that the RPA robot control platform finds the corresponding first folder in the file transfer server based on the location path in the file uploading request, and stores the second identification result to the first folder in the file transfer server based on the location path.

The RPA robot stores target claim settlement data associated with a collaborative identification task which needs to be processed by the human-computer collaboration platform into a first folder in the file transfer server, the human-computer collaboration platform obtains the target claim settlement data associated with the collaborative identification task from the first folder in the file transfer server, the human-computer collaboration platform also stores a processing result of the processed collaborative identification task, namely a second identification result into the first folder in the file transfer server, namely the target claim settlement data associated with the collaborative identification task which needs to be processed by the human-computer collaboration platform is stored by using the same folder in the file transfer server, and the second identification result is obtained after the collaborative identification task is processed by the human-computer collaboration platform, so that the path of the insurance claim settlement service in the automatic processing process can be ensured to be unique, and the error report of the process can be avoided.

It should be noted that, after the human-computer collaboration platform stores the second recognition result in the first folder of the file transfer server, a deletion mark may be added to the target claim data, so that after the file transfer server determines that the RPA robot obtains the second recognition result from the file transfer server, the target claim data is deleted from the first folder of the file transfer server according to the deletion mark, thereby avoiding the repeated work of the RPA robot and the human-computer collaboration platform.

It is understood that, in a possible implementation form, before the RPA robot performs text recognition on the target claim data, the target claim data may be classified first, and then the text recognition is performed on the target claim data based on the text recognition model corresponding to the category to which the target claim data belongs. And the classification of the target claim data determined by the RPA robot through classification of the target claim data may be less accurate.

In order to improve the accuracy of the classification result of the target claim data, in the embodiment of the application, when the accuracy of determining the category to which the target claim data belongs is low, the RPA robot may be further configured to issue a collaborative classification task to the human-computer collaborative platform, and store the target claim data associated with the collaborative classification task to a preset position, where the preset position may be a third folder in the file transfer server, and further, the human-computer collaborative platform is used to realize the classification of the target claim data in combination with manual work. For the convenience of distinguishing, the category to which the target claim data determined by the RPA robot belongs is called a first category, and the category to which the human-computer cooperation platform and the manually determined target claim data belong is called a second category.

Specifically, after the to-be-processed collaborative classification task is obtained, the human-computer collaboration platform can obtain target claim settlement data associated with the collaborative classification task from a preset position, and further can process the collaborative classification task based on the target claim settlement data to obtain a second category to which the target claim settlement data belongs, and the second category is stored in the preset position, so that the RPA performs text recognition on the target claim settlement data based on a text recognition model corresponding to the second category. The man-machine cooperation platform processes the cooperation classification task based on the target claim data to obtain a second category mode to which the target claim data belongs, and the mode can be as follows: displaying the target claim settlement data and an input box corresponding to the classification result through a task interface corresponding to the collaborative identification task; and responding to the detected input information in the input box of the task interface, and acquiring the second category.

Therefore, under the condition that the accuracy of the first category to which the target claim data belongs, which is determined by the RPA robot, is low, the target claim data are classified by combining a man-machine cooperation platform and manpower, and therefore the accuracy of the classification result of the target claim data is improved.

The following takes the RPA robot side as an example, and in combination with the description, an insurance claim settlement service processing method combining RPA and AI is also proposed in the present application.

Fig. 8 is a flowchart illustrating an insurance claim settlement service processing method according to a fourth embodiment of the present application, in which RPA and AI are combined.

As shown in fig. 8, the method may include the steps of:

step 801, obtain the target claims data to be processed.

It should be noted that the insurance claim service processing method combining the RPA and the AI according to the embodiment of the present application may be executed by an insurance claim service processing apparatus combining the RPA and the AI, and hereinafter, the insurance claim service processing apparatus combining the RPA and the AI is simply referred to as an insurance claim service processing apparatus. For example, the insurance claim service processing device may be an RPA robot, or the insurance claim service processing device may be configured in the RPA robot, which is not limited in this application.

The RPA robot may be configured in an electronic device, and the electronic device may include, but is not limited to, a terminal device, a server, and the like. In the embodiment of the present application, an insurance claim settlement service processing apparatus is taken as an example of an RPA robot installed in a terminal device.

The RPA robot in this embodiment may execute the method in real time in a specific time period or all day, which is not limited in this application. Wherein the specific time period can be set as desired.

Alternatively, the RPA robot may be started upon receiving a start instruction. For example, the worker may trigger the above-mentioned start instruction for the RPA robot by means of a dialog. The triggering of the starting instruction for the RPA robot may be implemented in various ways, for example, the starting instruction for the RPA robot may be triggered in a manner of voice and/or text, and for example, the starting instruction for the RPA robot may also be triggered in a manner of triggering a designated control on a dialog interaction interface, which is not limited in this embodiment of the present application.

Step 802, performing text recognition on the target claim data based on an Optical Character Recognition (OCR) technology to obtain a first recognition result corresponding to the target claim data.

And 803, under the condition that the first recognition result does not meet the preset condition, issuing a collaborative recognition task associated with the target claim settlement data to the man-machine collaborative platform, and storing the target claim settlement data to a preset position.

Wherein the preset condition may include: the first identification result comprises second key information corresponding to at least one target key field, and a first confidence corresponding to each second key information is higher than a first preset threshold. The first preset threshold value can be set arbitrarily as required. And the target key field is a key field which needs to be identified from the target claim settlement data in the process of processing the insurance claim settlement service.

In the embodiment of the application, under the condition that the RPA robot determines that the first recognition result meets the preset condition, the claim settlement can be carried out according to the first recognition result; under the condition that the RPA robot determines that the first recognition result does not meet the preset condition, the RPA robot can issue a collaborative recognition task to the human-computer collaborative platform, and store the target claim data in a preset position in a correlated manner, so that accurate recognition of the target claim data is completed by the cooperation of the human-computer collaborative platform and the RPA robot.

Step 804, responding to the human-computer cooperation platform, processing the cooperation recognition task based on the target claim data to obtain a second recognition result corresponding to the target claim data, storing the second recognition result to a preset position, and obtaining the second recognition result from the preset position.

And step 805, carrying out claim settlement according to the second recognition result.

In the embodiment of the application, after the human-computer collaboration platform obtains the collaboration recognition task, target claim settlement data associated with the collaboration recognition task can be obtained from a preset position, the collaboration recognition task is processed based on the target claim settlement data, a second recognition result corresponding to the target claim settlement data is obtained, and the second recognition result is stored in the preset position, so that the RPA robot can obtain the second recognition result from the preset position and carry out claim settlement according to the second recognition result.

In an embodiment of the present application, the process of the RPA robot making a claim according to the second recognition result may be: the RPA robot logs in the claim settlement system, inputs information required by any claim settlement such as name, date of birth, identification number, address and the like in the second recognition result into a corresponding position in the claim settlement system, uploads target claim settlement data as an attachment to the claim settlement system, and submits a claim settlement request. Further, after the RPA robot submits a claim settlement request, the RPA robot may log in a mail system, and send an e-mail to a claim settlement and payment department using a pre-configured e-mail template, so that the claim settlement service is submitted by the claim settlement and payment department to request for preparing payment.

According to the insurance claim settlement service processing method combining the RPA and the AI, the RPA robot is used for obtaining target claim settlement data to be processed, text recognition is carried out on the target claim settlement data on the basis of an Optical Character Recognition (OCR) technology to obtain a first recognition result corresponding to the target claim settlement data, a cooperative recognition task related to the target claim settlement data is issued to the man-machine cooperative platform under the condition that the first recognition result does not meet a preset condition, the target claim settlement data is stored in a preset position, the cooperative recognition task is processed on the basis of the target claim settlement data in response to the man-machine cooperative platform, a second recognition result corresponding to the target claim settlement data is obtained, the second recognition result is stored in the preset position, the second recognition result is obtained from the preset position, and a claim is settled according to the second recognition result. Therefore, the insurance claim settlement service is automatically processed in a mode of combining the RPA robot with the AI and the man-machine cooperation platform, the labor cost is reduced, the service processing efficiency is improved, a more accurate second recognition result corresponding to the target claim settlement data can be obtained by using the man-machine cooperation platform, then claim settlement is carried out according to the second recognition result, and the accuracy of the insurance claim settlement service processing can be improved.

The insurance claim settlement service processing method combining the RPA and the AI provided in the embodiment of the present application is further described below with reference to fig. 9. Fig. 9 is a schematic flowchart of an insurance claim settlement service processing method according to a fifth embodiment of the present application, where, as shown in fig. 9, the method includes:

step 901, obtaining target claim settlement data from the candidate claim settlement data in the second folder in the file transfer server.

In the embodiment of the application, the RPA robot may periodically search for a claim mail to be processed in the mail system, and after acquiring a new claim mail, may download an attachment from the claim mail to obtain candidate claim data, and store the candidate claim data in the second folder in the file transfer server. Furthermore, the RPA robot may obtain target claim settlement data to be processed from the second folder in the file transfer server, and perform the following steps on the target claim settlement data until the processing of the candidate target claim settlement data in the second folder in the file transfer server is completed. The candidate claim data with the earliest receiving date in the second folder in the file transfer server can be used as the target claim data.

Accordingly, before step 901, the method may further include: searching in a mail system to obtain a claim mail to be processed; and acquiring candidate claim data from the claim mail, and storing the candidate claim data into a second folder in the file transfer server.

The file transfer server is deployed on the RPA robot control platform.

Step 902, performing text recognition on the target claim data based on an Optical Character Recognition (OCR) technology to obtain a first recognition result corresponding to the target claim data.

Specifically, the RPA robot may classify the target claim data based on the classification model to obtain a first category to which the target claim data belongs and a second confidence degree corresponding to the first category, and when the second confidence degree is lower than a second preset threshold, it may be determined that the accuracy of the first category is low, and then the RPA robot may issue a collaborative classification task associated with the target claim data to the human-computer collaborative platform, and store the target claim data in a preset position, so that the human-computer collaborative platform obtains the target claim data associated with the collaborative classification task from the preset position after obtaining the collaborative classification task to be processed, and processes the collaborative classification task based on the target claim data to obtain a second category to which the target claim data belongs, and stores the second category in the preset position. The RPA robot responds to the human-computer cooperation platform to store the second category to the preset position, can acquire the second category from the preset position, and then performs text recognition on the target claim settlement data based on the text recognition model corresponding to the second category. The second preset threshold value can be set arbitrarily according to needs.

Accordingly, step 902 may be replaced with: and performing text recognition on the target claim data based on the text recognition model corresponding to the second category.

Therefore, under the condition that the accuracy of the first category to which the target claim data belong, which is determined by the RPA robot, is low, the classification of the target claim data is achieved by the man-machine cooperation platform and the manpower, the more accurate second category to which the target claim data belong can be obtained, and then the text recognition is performed on the target claim data on the basis of the text recognition model corresponding to the second category, so that the accuracy of the text recognition can be improved.

Step 903, determining whether the first recognition result meets a preset condition, if so, executing step 907, otherwise, executing step 904.

And 904, issuing a collaborative identification task associated with the target claim data to the man-machine collaborative platform, and storing the target claim data in a first folder in the file transfer server.

The preset conditions include: the first identification result comprises key information corresponding to at least one target key field, and a first confidence corresponding to each key information is higher than a first preset threshold.

In an embodiment of the application, the RPA robot may save the target claim data to the first folder in the file transfer server by: and sending a file uploading request to the RPA robot control platform so that the RPA robot control platform receives the target claim data based on the file uploading request and stores the target claim data in a first folder of a file transfer server.

Specifically, the RPA robot may send a file upload request to the RPA robot control platform, where the file download request carries a location path of the first folder, so that the RPA robot control platform finds the corresponding first folder in the file transfer server based on the location path in the file upload request, and stores the target claim settlement data in the file transfer server under the first folder based on the location path.

Step 905, in response to the human-computer collaboration platform, processing the collaboration recognition task based on the target claim settlement data to obtain a second recognition result corresponding to the target claim settlement data, storing the second recognition result in the first folder in the file transfer server, and obtaining the second recognition result from the first folder in the file transfer server.

In an embodiment of the present application, the RPA robot may obtain the second recognition result from the first folder in the file relay server by: and sending a file downloading request to the RPA robot control platform, so that the RPA robot control platform obtains a second identification result from the first folder in the file transfer server based on the file downloading request, and transmits the second identification result back to the RPA robot.

And step 906, carrying out claim settlement according to the second recognition result.

And step 907, carrying out claim settlement according to the first recognition result.

It will be appreciated that in practice, it may not be necessary to claim claims for claim applications of certain users for some reasons, for example, the insurance premiums of the users who claim the claims are not paid on time. In the embodiment of the application, a user who does not need to carry out claim settlement is called an illegal user, and a user who needs to carry out claim settlement is called a legal user. Then, before carrying out claims according to the second recognition result or the first recognition result, the user corresponding to the obtained target claims data can be determined to be a legal user.

That is, before

step

906 or 907, it may further include: acquiring a user identifier corresponding to the target claim settlement data; inputting a user identifier on a query page of the information management system to query user information corresponding to the user identifier; and determining the user corresponding to the user identification as a legal user according to the user information corresponding to the user identification.

In an embodiment of the application, the user identifier corresponding to the target claim settlement data may be obtained from the first recognition result or the second recognition result. The user identifier is used for uniquely identifying the user, and can be a mailbox address for sending target claim data, an identity card number of the user and the like. The user information may include the user's application information, identity information, etc.

In the insurance claim service processing method combining the RPA and the AI provided in the embodiment of the application, the RPA robot acquires target claim data from candidate claim data in a second folder in the file transfer server, performs text recognition on the target claim data based on an optical character recognition OCR technology to acquire a first recognition result corresponding to the target claim data, determines whether the first recognition result meets a preset condition, if so, performs claim settlement according to the first recognition result, if not, issues a collaborative recognition task associated with the target claim data to the human-computer collaborative platform, stores the target claim data in the first folder in the file transfer server, processes the collaborative recognition task based on the target claim data in response to the human-computer collaborative platform to acquire a second recognition result corresponding to the target claim data, and stores the second recognition result in the first folder in the file transfer server, and acquiring a second identification result from the first folder in the file transfer server, and carrying out claim settlement according to the second identification result. Therefore, the insurance claim settlement service is automatically processed in a mode of combining the RPA robot with the AI and the man-machine cooperation platform, the labor cost is reduced, the service processing efficiency is improved, a more accurate second recognition result corresponding to the target claim settlement data can be obtained by using the man-machine cooperation platform, then claim settlement is carried out according to the second recognition result, and the accuracy of insurance claim settlement service processing can be improved.

In order to implement the above embodiments, the present application further provides an insurance claim settlement service processing apparatus combining an RPA and an AI. Fig. 10 is a schematic structural diagram of an insurance claim settlement service processing apparatus according to a sixth embodiment of the present application, which combines RPA and AI.

As shown in fig. 10, the insurance claim settlement service processing apparatus 1000 combining RPA and AI is applied to a human-computer cooperation platform, and includes: a first obtaining module 1001, a first processing module 1002 and a first saving module 1003.

The first obtaining module 1001 is configured to obtain a collaborative identification task to be processed, and obtain target claim settlement data associated with the collaborative identification task from a preset position; the cooperative identification task is issued by the RPA robot under the condition that the first identification result does not meet the preset condition after the RPA robot performs text identification on the target claim data based on an Optical Character Recognition (OCR) technology and acquires the first identification result corresponding to the target claim data; the target claim settlement data is stored to a preset position by the RPA robot;

the first processing module 1002 is configured to process the collaborative identification task based on the target claim settlement data to obtain a second identification result corresponding to the target claim settlement data;

the first saving module 1003 is configured to save the second recognition result to a preset position, so that the RPA robot obtains the second recognition result from the preset position, and performs claim settlement according to the second recognition result.

It should be noted that, the insurance claim service processing apparatus combining RPA and AI according to the embodiment of the present application may execute the insurance claim service processing method combining RPA and AI provided in the foregoing embodiment. For example, the insurance claim settlement service processing device combining the RPA and the AI may be a human-computer cooperation platform, or the insurance claim settlement service processing device may be configured in the human-computer cooperation platform, which is not limited in this application.

In one embodiment of the present application, the first processing module 1002 includes:

the display unit is used for displaying the target claim settlement data and the input box corresponding to the second text result through the task interface corresponding to the collaborative identification task;

and the first acquisition unit is used for responding to the detected input information in the input box of the task interface and acquiring a second identification result.

In an embodiment of the application, the second text result includes key information corresponding to at least one target key field, and the input box includes input boxes corresponding to the key information respectively;

a first acquisition unit configured to:

and responding to the detected input information in the input box corresponding to each piece of key information of the task interface, and acquiring the key information corresponding to each target key field.

In an embodiment of the present application, the insurance claim settlement service processing apparatus 1000 combining RPA and AI further includes:

the second acquisition module is used for acquiring action configuration commands related to the collaborative identification task, and the action configuration commands comprise field configuration commands and path configuration commands;

the first configuration module is used for configuring a target identification field of the collaborative identification task as a target key field and configuring field attribute information of the target key field based on the field configuration command;

and the second configuration module is used for configuring the task path of the collaborative identification task into a path corresponding to the preset position based on the path configuration command.

In an embodiment of the application, the preset position is a first folder in a file transfer server, and the file transfer server is deployed on an RPA robot control platform;

a first obtaining module 1001, comprising:

and the first sending unit is used for sending a file downloading request to the RPA robot control platform so that the RPA robot control platform obtains target claim settlement data from a first folder in the file transfer server based on the file downloading request and transmits the target claim settlement data back to the man-machine cooperation platform.

In an embodiment of the present application, the insurance claim settlement service processing apparatus combining RPA and AI further includes:

the third acquisition module is used for acquiring the collaborative classification tasks to be processed and acquiring target claim settlement data associated with the collaborative classification tasks from a preset position;

the second processing module is used for processing the collaborative classification task based on the target claim settlement data to obtain a second category to which the target claim settlement data belongs;

and the second storage module is used for storing the second category to a preset position so that the RPA performs text recognition on the target claim settlement data based on the text recognition model corresponding to the second category.

It should be noted that the foregoing explanation of the embodiment of the method for processing insurance claims with RPA and AI is also applicable to the apparatus for processing insurance claims with RPA and AI in this embodiment, and details that are not published in the embodiment of the apparatus for processing insurance claims with RPA and AI in this application are not repeated here.

To sum up, the insurance claim settlement service processing apparatus combining the RPA and the AI according to the embodiment of the present application obtains the cooperative identification task to be processed, and obtains the target claim settlement data associated with the cooperative identification task from the preset position, where the cooperative identification task is issued by the RPA robot under the condition that the first identification result does not satisfy the preset condition after text recognition is performed on the target claim settlement data based on the optical character recognition OCR technology to obtain the first identification result corresponding to the target claim settlement data, the target claim settlement data is stored in the preset position by the RPA robot, the cooperative identification task is processed based on the target claim settlement data to obtain the second identification result corresponding to the target claim settlement data, and the second identification result is stored in the preset position, so that the RPA robot obtains the second identification result from the preset position and performs claim settlement according to the second identification result, the method has the advantages that the insurance claim settlement service is automatically processed in a mode of combining the RPA robot with the AI and the human-computer cooperation platform, labor cost is reduced, service processing efficiency is improved, a more accurate second recognition result corresponding to target claim settlement data can be obtained by the human-computer cooperation platform, claim settlement is carried out according to the second recognition result, and accuracy of insurance claim settlement service processing can be improved.

In order to implement the above embodiments, the present application further provides an insurance claim settlement service processing apparatus combining an RPA and an AI. Fig. 11 is a schematic structural diagram of an insurance claim settlement service processing apparatus according to a seventh embodiment of the present application, which combines RPA and AI.

As shown in fig. 11, the insurance claim settlement service processing apparatus 1100 combining RPA and AI is applied to an RPA robot, and includes: a fourth obtaining module 1101, a recognition module 1102, a third processing module 1103, a fifth obtaining module 1104 and a fourth processing module 1105.

The fourth obtaining module 1101 is configured to obtain target claim settlement data to be processed;

the recognition module 1102 is configured to perform text recognition on the target claim data based on an Optical Character Recognition (OCR) technology to obtain a first recognition result corresponding to the target claim data;

the third processing module 1103 is configured to, when the first recognition result does not meet the preset condition, issue a collaborative recognition task associated with the target claim settlement data to the human-computer collaborative platform, and store the target claim settlement data in a preset position;

a fifth obtaining module 1104, configured to process the collaborative recognition task based on the target claim data in response to the human-computer collaborative platform, obtain a second recognition result corresponding to the target claim data, store the second recognition result in a preset position, and obtain the second recognition result from the preset position;

and a fourth processing module 1105, configured to carry out an claim settlement according to the second recognition result.

It should be noted that, the insurance claim service processing apparatus combining RPA and AI according to the embodiment of the present application may execute the insurance claim service processing method combining RPA and AI provided in the foregoing embodiment. For example, the insurance claim service processing device combining the RPA and the AI may be an RPA robot, or the insurance claim service processing device may be configured in the RPA robot, which is not limited in this application.

In one embodiment of the present application, the preset conditions include: the first identification result comprises second key information corresponding to at least one target key field, and a first confidence corresponding to each second key information is higher than a first preset threshold.

In an embodiment of the present application, the preset location is a first folder in the file transfer server; the file transfer server is deployed on the RPA robot control platform;

a third processing module 1103 comprising:

and the second sending unit is used for sending a file uploading request to the RPA robot control platform so that the RPA robot control platform receives the target claim data based on the file uploading request and stores the target claim data under the first folder of the file transfer server.

the search module is used for searching in the mail system to obtain a claim mail to be processed;

the third storage module is used for acquiring candidate claim data from the claim mail and storing the candidate claim data into a second folder in the file transfer server;

a fourth obtaining module 1101, comprising:

and the second acquisition unit is used for acquiring target claim settlement data from the candidate claim settlement data in the second folder.

the sixth acquisition module is used for acquiring the user identification corresponding to the target claim settlement data;

the query module is used for inputting a user identifier on a query page of the information management system so as to query user information corresponding to the user identifier;

and the determining module is used for determining the user corresponding to the user identification as a legal user according to the user information corresponding to the user identification.

the classification module is used for classifying the target claim data based on the classification model so as to obtain a first class to which the target claim data belongs and a second confidence coefficient corresponding to the first class;

the fifth processing module is used for issuing a collaborative classification task related to the target claim settlement data to the man-machine collaborative platform and storing the target claim settlement data to a preset position under the condition that the second confidence coefficient is lower than a second preset threshold value;

the seventh obtaining module is used for responding to the human-computer cooperation platform and processing the cooperation classification task based on the target claim data to obtain a second category to which the target claim data belongs, storing the second category to a preset position, and obtaining the second category from the preset position;

accordingly, the identifying module 1102 includes:

and the recognition unit is used for performing text recognition on the target claim settlement data based on the text recognition model corresponding to the second category.

and the sixth processing module is used for carrying out claim settlement according to the first recognition result under the condition that the first recognition result meets the preset condition.

To sum up, the insurance claim settlement service processing device combining the RPA and the AI according to the embodiment of the present application performs text recognition on the target claim settlement data by obtaining target claim settlement data to be processed, based on an optical character recognition OCR technology, to obtain a first recognition result corresponding to the target claim settlement data, issues a collaborative recognition task associated with the target claim settlement data to the human-computer collaborative platform when the first recognition result does not meet a preset condition, stores the target claim settlement data in a preset position, processes the collaborative recognition task based on the target claim settlement data in response to the human-computer collaborative platform, obtains a second recognition result corresponding to the target claim settlement data, stores the second recognition result in the preset position, obtains the second recognition result from the preset position, and performs claim settlement according to the second recognition result. Therefore, the insurance claim settlement service is automatically processed in a mode of combining the RPA robot with the AI and the man-machine cooperation platform, the labor cost is reduced, the service processing efficiency is improved, a more accurate second recognition result corresponding to the target claim settlement data can be obtained by using the man-machine cooperation platform, then claim settlement is carried out according to the second recognition result, and the accuracy of insurance claim settlement service processing can be improved.

In order to implement the foregoing embodiments, an electronic device is further provided in an embodiment of the present application, and includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the method for processing an insurance claim service in combination with RPA and AI according to any one of the foregoing method embodiments.

In order to implement the foregoing embodiments, the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for processing insurance claim settlement service in combination with RPA and AI according to any of the foregoing method embodiments.

In order to implement the foregoing embodiments, the present application further provides a computer program product, wherein when being executed by an instruction processor in the computer program product, the method for processing the insurance claim settlement service in combination with the RPA and the AI according to any of the foregoing method embodiments is implemented.

FIG. 12 illustrates a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present application. The electronic device 12 shown in fig. 12 is only an example, and should not bring any limitation to the functions and the use range of the embodiment of the present application.

As shown in FIG. 12, electronic device 12 is embodied in the form of a general purpose computing device. The components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the memory 28 and the processing unit 16.

Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. These architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus, to name a few.

Electronic device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

Memory 28 may include computer system readable media in the form of volatile Memory, such as Random Access Memory (RAM) 30 and/or cache Memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 12, and commonly referred to as a "hard drive"). Although not shown in FIG. 12, a disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk Read Only Memory (CD-ROM), a Digital versatile disk Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the application.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the embodiments described herein.

Electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with electronic device 12, and/or with any devices (e.g., network card, modem, etc.) that enable electronic device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public Network such as the Internet) via the Network adapter 20. As shown in FIG. 12, the network adapter 20 communicates with the other modules of the electronic device 12 via the bus 18. It should be appreciated that although not shown in FIG. 12, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

The processing unit 16 executes various functional applications and data processing by executing programs stored in the memory 28, for example, implementing the methods mentioned in the foregoing embodiments.

In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless explicitly specified otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.

The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.

In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.

The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.

Claims

1. An insurance claim settlement service processing method combining Robot Process Automation (RPA) and Artificial Intelligence (AI), which is applied to a man-machine cooperation platform, and comprises the following steps:

acquiring a cooperative identification task to be processed, and acquiring target claim settlement data associated with the cooperative identification task from a preset position; the cooperative identification task is issued by the RPA robot under the condition that the first identification result does not meet the preset condition after the RPA robot performs text identification on the target claim data based on an Optical Character Recognition (OCR) technology and acquires the first identification result corresponding to the target claim data; the target claim settlement data is stored to the preset position by the RPA robot;

processing the collaborative identification task based on the target claim settlement data to obtain a second identification result corresponding to the target claim settlement data;

and storing the second recognition result to the preset position, so that the RPA robot acquires the second recognition result from the preset position and carries out claim settlement according to the second recognition result.

2. The method according to claim 1, wherein the processing the collaborative recognition task based on the target claim material to obtain a second recognition result corresponding to the target claim material comprises:

displaying the target claim settlement data and an input box corresponding to the second text result through a task interface corresponding to the collaborative recognition task;

and responding to the detected input information in the input box of the task interface, and acquiring the second recognition result.

3. The method of claim 2, wherein the second text result includes first key information corresponding to at least one target key field, and the input boxes include input boxes corresponding to the first key information respectively;

the obtaining of the second recognition result in response to the detected input information in the input box of the task interface comprises:

and responding to the detected input information in the input box corresponding to each piece of first key information of the task interface, and acquiring the first key information corresponding to each target key field.

4. The method according to claim 3, wherein before the obtaining the co-recognition task to be processed, the method further comprises:

acquiring an action configuration command associated with the collaborative identification task, wherein the action configuration command comprises a field configuration command and a path configuration command;

configuring a target identification field of the cooperative identification task as the target key field and configuring field attribute information of the target key field based on the field configuration command;

and configuring the task path of the collaborative identification task as a path corresponding to the preset position based on the path configuration command.

5. The method according to any one of claims 1 to 4, wherein the predetermined location is a first folder in a file relay server deployed on the RPA robot control platform;

the obtaining of the target claim settlement data associated with the collaborative recognition task from the preset position includes:

and sending a file downloading request to the RPA robot control platform, so that the RPA robot control platform acquires the target claim settlement data from a first folder in the file transfer server based on the file downloading request, and transmits the target claim settlement data back to the man-machine cooperation platform.

6. The method according to any one of claims 1-4, further comprising:

acquiring a to-be-processed collaborative classification task, and acquiring the target claim settlement data associated with the collaborative classification task from the preset position;

processing the collaborative classification task based on the target claim settlement data to obtain a second category to which the target claim settlement data belongs;

and storing the second category to the preset position, so that the RPA performs text recognition on the target claim settlement data based on a text recognition model corresponding to the second category.

7. An insurance claim settlement service processing method combining RPA and AI, which is applied to an RPA robot, and comprises the following steps:

acquiring target claim settlement data to be processed;

performing text recognition on the target claim data based on an Optical Character Recognition (OCR) technology to obtain a first recognition result corresponding to the target claim data;

under the condition that the first recognition result does not meet the preset condition, issuing a collaborative recognition task related to the target claim settlement data to a man-machine collaborative platform, and storing the target claim settlement data to a preset position;

processing the collaborative identification task based on the target claim data in response to the human-computer collaborative platform to obtain a second identification result corresponding to the target claim data, storing the second identification result to the preset position, and acquiring the second identification result from the preset position;

and carrying out claim settlement according to the second recognition result.

8. The method according to claim 7, wherein the preset conditions include: the first identification result comprises second key information corresponding to at least one target key field, and a first confidence corresponding to each second key information is higher than a first preset threshold.

9. The method of claim 7, wherein the predetermined location is a first folder in the file relay server; the file transfer server is deployed on the RPA robot control platform;

the storing the target claim settlement data to the preset position comprises:

and sending a file uploading request to the RPA robot control platform so that the RPA robot control platform receives the target claim data based on the file uploading request and stores the target claim data in a first folder of the file transfer server.

10. The method according to claim 9, wherein before obtaining the target claims data to be processed, the method further comprises:

searching in a mail system to obtain a claim mail to be processed;

acquiring candidate claim settlement data from the claim settlement mail, and storing the candidate claim settlement data into a second folder in the file transfer server;

the acquiring of the target claim settlement data to be processed comprises:

and acquiring the target claim settlement data from the candidate claim settlement data in the second folder.

11. The method according to any one of claims 7-10, wherein before performing text recognition on the target claims material based on Optical Character Recognition (OCR), the method further comprises:

classifying the target claim data based on a classification model to obtain a first class to which the target claim data belongs and a second confidence coefficient corresponding to the first class;

under the condition that the second confidence degree is lower than a second preset threshold value, issuing a collaborative classification task related to the target claim data to the man-machine collaborative platform, and storing the target claim data to the preset position;

processing the collaborative classification task based on the target claim data in response to the human-computer collaborative platform to obtain a second category to which the target claim data belongs, storing the second category to the preset position, and acquiring the second category from the preset position;

the OCR technology based on optical character recognition performs text recognition on the target claim data, and comprises the following steps:

and performing text recognition on the target claim settlement data based on the text recognition model corresponding to the second category.

12. An insurance claim settlement service processing device combining RPA and AI, which is applied to a man-machine cooperation platform, the device comprises:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a cooperative identification task to be processed and acquiring target claim settlement data related to the cooperative identification task from a preset position; the cooperative identification task is issued by the RPA robot under the condition that the first identification result does not meet the preset condition after the RPA robot performs text identification on the target claim data based on an Optical Character Recognition (OCR) technology and acquires the first identification result corresponding to the target claim data; the target claim settlement data is stored in the preset position by the RPA robot;

the first processing module is used for processing the collaborative identification task based on the target claim settlement data to obtain a second identification result corresponding to the target claim settlement data;

and the first storage module is used for storing the second recognition result to the preset position so that the RPA robot can obtain the second recognition result from the preset position and carry out claim settlement according to the second recognition result.

13. An insurance claim settlement service processing device combining RPA and AI, which is applied to RPA robot, the device includes:

the fourth acquisition module is used for acquiring target claim settlement data to be processed;

the recognition module is used for performing text recognition on the target claim data based on an Optical Character Recognition (OCR) technology to obtain a first recognition result corresponding to the target claim data;

the third processing module is used for issuing a collaborative recognition task related to the target claim data to a man-machine collaborative platform and storing the target claim data to a preset position under the condition that the first recognition result does not meet a preset condition;

a fifth obtaining module, configured to respond to the human-computer collaboration platform, process the collaborative identification task based on the target claim settlement data, obtain a second identification result corresponding to the target claim settlement data, store the second identification result in the preset position, and obtain the second identification result from the preset position;

and the fourth processing module is used for carrying out claim settlement according to the second recognition result.

14. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the method of any of claims 1-6 or implementing the method of any of claims 7-11 when executing the computer program.

15. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1 to 6, or carries out the method of any one of claims 7 to 11.