CN114445836A

CN114445836A - Information auditing method and device combining RPA and AI and electronic equipment

Info

Publication number: CN114445836A
Application number: CN202210111728.6A
Authority: CN
Inventors: 刘宝利
Original assignee: Laiye Technology Beijing Co Ltd
Current assignee: Laiye Technology Beijing Co Ltd
Priority date: 2022-01-26
Filing date: 2022-01-26
Publication date: 2022-05-06

Abstract

The application relates to an information auditing method, device and electronic equipment combining RPA and AI, relates to the technical field of RPA and AI, is applied to an RPA robot, and comprises the following steps: acquiring contract information and information to be checked in a service system; based on OCR and NLP technologies, first key information corresponding to at least one first key field is obtained from contract information, and a first identifier corresponding to the contract information is obtained; and comparing each piece of first key information with the first to-be-checked information corresponding to the first identifier in the to-be-checked information, and storing the obtained first comparison result in a preset mode. The information to be checked is obtained through the RPA robot, the key information in the contract data is obtained based on the OCR and NLP technologies, the information to be checked and the key information are accurately obtained, the key information is compared with the information to be checked, an accurate comparison result can be obtained, the RPA robot replaces manpower to obtain the information and compare the information, the labor cost is reduced, and the checking efficiency is improved.

Description

Information auditing method and device combining RPA and AI and electronic equipment

Technical Field

The application relates to the technical field of robot process automation and artificial intelligence, in particular to an information auditing method and device combining RPA and AI and an electronic device.

Background

Robot Process Automation (RPA) is a Process task automatically executed according to rules by simulating human operations on a computer through specific robot software.

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, in some removal projects, a removal resident (removed person) needs to fill information such as a removed person, a house area, a house address and the like in an online business system, meanwhile, a scanning piece of a certificate such as an identity card, a house property card and the like is uploaded to the business system as an accessory, and a paper removal contract is signed, and an old rework worker needs to record contract information such as a first party (removed person) and a second party (removed person) in the paper removal contract into the business system. When the information in the business system is checked, people need to rely on to extract the information from the online business system, and the information is compared with the information in the scanned pieces of certificates such as identity cards, house property cards and the like and the information in the paper removal contract one by one. When a large amount of information needs to be audited, the information auditing method needs to consume a large amount of labor cost and time cost, and information auditing errors are easy to occur. How to improve the efficiency and accuracy of information auditing and reduce labor cost becomes a problem to be solved urgently.

Disclosure of Invention

The application provides an information auditing method and device combining RPA and AI and electronic equipment, and aims to solve the technical problems of low information auditing efficiency, low accuracy and high labor cost of the information auditing method in the related technology.

An embodiment of a first aspect of the present application provides an information auditing method combining an RPA and an AI, which is applied to an RPA robot, and the method includes: acquiring contract data to be processed and information to be checked in a service system; identifying the contract information based on an Optical Character Recognition (OCR) technology to obtain first text information in the contract information; extracting first key information corresponding to at least one first key field from the first text information based on a Natural Language Processing (NLP) technology; acquiring a first identifier corresponding to contract information from first key information corresponding to at least one first key field; comparing the first key information corresponding to at least one first key field with the first to-be-audited information corresponding to the first identifier in the to-be-audited information to obtain a first comparison result, and storing the first comparison result in a preset mode.

The embodiment of the second aspect of the present application provides an information auditing device combining RPA and AI, which is applied to an RPA robot, and the device includes: the first acquisition module is used for acquiring contract information to be processed and information to be checked in the service system; the first identification module is used for identifying the contract information based on an Optical Character Recognition (OCR) technology so as to acquire first text information in the contract information; the extraction module is used for extracting first key information corresponding to at least one first key field from the first text information based on a Natural Language Processing (NLP) technology; the second acquisition module is used for acquiring a first identifier corresponding to the contract information from the first key information corresponding to the at least one first key field; the first processing module is used for comparing the first key information corresponding to the at least one first key field with the first to-be-audited information corresponding to the first identifier in the to-be-audited information to obtain a first comparison result, and storing the first comparison result in a preset mode.

An embodiment of the third aspect of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the method according to the embodiment of the first aspect of the present application is implemented.

An embodiment of a fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method according to the embodiment of the first aspect of the present application.

An embodiment of the fifth aspect of the present application provides a computer program product, which includes a computer program, and when executed by a processor, the computer program implements the method according to the above embodiment of the first aspect of the present application.

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

the RPA robot is used for acquiring contract information to be processed and information to be checked in the service system, key information in the contract information is acquired based on OCR and NLP technologies, the RPA and AI technologies are combined, the information to be checked in the service system and the key information in the contract information are accurately acquired, the key information is compared with the information to be checked, an accurate comparison result can be obtained, the RPA robot replaces manpower to acquire and compare the information, labor cost is greatly reduced, and information checking efficiency is 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 numerals refer to the same 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 information auditing method by combining RPA and AI according to a first embodiment of the present application;

FIG. 2 is a schematic flow chart of an information auditing method according to a second embodiment of the present application in combination with RPA and AI;

FIG. 3 is an architecture diagram of an information auditing method incorporating RPA and AI according to a second embodiment of the present application;

FIGS. 4-6 are exemplary diagrams of treaty material according to a second embodiment of the present application;

FIG. 7 is an exemplary graph of a first alignment result according to a second embodiment of the present application;

FIG. 8 is a schematic flow chart of an information auditing method according to a third embodiment of the present application in combination with RPA and AI;

fig. 9 is a schematic structural diagram of an information auditing apparatus according to a fourth embodiment of the present application, which combines RPA and AI;

fig. 10 is a block diagram of an electronic device for implementing an information auditing method in conjunction with RPA and AI according to an 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.

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

The application provides a thought of carrying out information audit instead of manual work automatically through the mode that RPA and AI combine. The RPA robot is used for acquiring contract information to be processed and information to be checked in the service system, key information in the contract information is acquired based on OCR and NLP technologies, the RPA and AI technologies are combined, the information to be checked in the service system and the key information in the contract information are accurately acquired, the key information is compared with the information to be checked, an accurate comparison result can be obtained, the RPA robot replaces manpower to acquire and compare the information, labor cost is greatly reduced, and information checking efficiency is 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, a "service system" refers to an online system handling services, and various services can be processed on the service system, for example, the service system may be a service system handling old-to-new services for old-to-new workers, or may be a service system handling other services.

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" refers to a software robot that can automatically perform information auditing 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 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 embodiment of the application, the RPA robot can recognize characters in documents, bills, tables and pictures by combining an OCR technology, wherein the documents can be various types of documents such as contracts, reports and documents, and can also be documents in various formats such as jpeg, jpg, png, pdf, bmp and tiff. Moreover, the RPA robot can process various complex scenes such as rotation, shading, inclination, dense characters, complex background, uneven illumination, shaking blur and the like, and the accuracy rate of print recognition can reach 99%. In addition, for the recognition of handwriting, a training algorithm model can be customized, so that the recognition accuracy rate of the model can meet the ideal requirement.

In addition, the RPA robot can automatically detect whether a seal is stamped on the data such as a contract, a bill, a card and a form data based on an OCR technology, and return information such as the position, the color, the content and the like of the seal. In addition, the RPA robot can accurately identify the seals with various colors such as red, blue and the like, the seals with various shapes such as a circle, an ellipse, a rhombus and the like, and the incomplete seals. In addition, in the case where a plurality of stamps are included in one drawing, the RPA robot can also realize accurate recognition of the stamps.

In the description of the present application, "NLP (Natural Language Processing)" refers to the ability of a machine to understand and interpret human writing and speech. The goal of NLP is to let computers/machines be as intelligent as humans in understanding language, the task of which is to understand human language and convert it to machine language.

In the embodiment of the application, the RPA robot can understand the content of the text and make a decision by combining with the NLP technology, and extract structured data from the unstructured text, such as the name, address, amount, date and the like of an enterprise in the text. In addition, the user can extract the template by self-definition, the customized information extraction capability is quickly realized, and the mixed mode of the model and the template is supported in a section of text.

An information auditing method, apparatus, electronic device, and storage medium in combination with an RPA and an AI according to the embodiments of the present application/disclosure are described below with reference to the accompanying drawings.

Fig. 1 is a flowchart of an information auditing method combining RPA and AI according to a first embodiment of the present application. As shown in fig. 1, the method may include the steps of:

step 101, acquiring contract data to be processed and information to be checked in a service system.

It should be noted that the information auditing method according to the embodiment of the present application that combines the RPA and the AI may be executed by an information auditing apparatus that combines the RPA and the AI, and the information auditing apparatus that combines the RPA and the AI will be simply referred to as an information auditing apparatus hereinafter. The information auditing device may be implemented by an RPA robot, for example, the information auditing device may be an RPA robot, or the information auditing device may be configured in an 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 information auditing 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 activated upon receiving an activation instruction. For example, the staff of the service system 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.

The information to be checked is information about whether the information to be checked is accurate in the service system. Moreover, the information to be audited is structured data, that is, includes at least one key field and corresponding key information. For example, taking the information audit scene of the removed project as an example, the service system can be a service system for processing the old repurposing service for the old repurposing staff; the information to be audited may include key information corresponding to key fields such as "a migrator", "a house address", "a telephone", and "a house area" filled in by the migrant tenant in the service system, and key information corresponding to key fields such as "a party", "b party", and "a file number" entered by the old modified staff.

The contract information to be processed is the contract information according to which the accuracy of the information to be checked is checked. The contract information to be processed may include various types of contract information, for example, the contract information may include a removal contract, an entry contract, and the like, which is not limited in this application. The contract information to be processed may include contract information in various formats, which is not limited in this application. In addition, the contract information to be processed may be obtained in any manner, for example, the contract information may be scanned contract information obtained by scanning paper contract information, or may be electronic contract information downloaded from an online service system, and the application is not limited thereto.

Taking an information auditing scene of an demolition project as an example, a demolition resident needs to fill in key information corresponding to key fields such as a "demolition person", "a house address", "a telephone", "a house area" and the like in an online service system and sign a paper demolition contract, an old remanufacturing worker can input the key information corresponding to the key fields such as a "contract number (also called an agreement number or a file number)", "a" party A "," a "party B" and the like in the demolition contract into the service system, so as to generate form information, wherein the form information comprises the information filled by the demolition resident and the contract information input by the worker. When form information in the business system needs to be checked, a worker can scan the paper removal contract, so that the RPA robot can obtain a scanned piece of the paper removal contract, and the scanned piece is contract information to be processed in the embodiment of the application. Moreover, the RPA robot can log in the service system, and collect form information from a display interface of the service system, where the form information is to-be-checked information in the embodiment of the present application.

Step 102, identifying the contract information based on an Optical Character Recognition (OCR) technology to obtain first text information in the contract information.

In an embodiment of the application, the RPA robot may identify the contract material based on OCR technology to obtain the first text information in the contract material. The first text information may include text content in the contract data and text information corresponding to the seal content.

Step 103, extracting first key information corresponding to at least one first key field from the first text information based on a natural language processing NLP technology.

Wherein, the first key field can be set as required. For example, all key fields that can be extracted from the contract data can be set; alternatively, certain key fields may be set, for example, the fields may be set to "age", "address", "protocol number", "party a", "party b", etc., which is not limited in this application.

It can be understood that the contract information usually does not have a fixed format, the first text information obtained by identifying the contract information based on the OCR technology is usually unstructured data, and in order to compare the text information in the contract information with the structured information to be checked in the business system, the structured data in the first text information needs to be extracted. Then, in this embodiment of the present application, the RPA robot may extract, based on the NLP technology, the first key information corresponding to the at least one first key field from the first text information through context understanding. Each first key field and the corresponding first key information are a piece of structured data.

Step 104, obtaining a first identifier corresponding to the contract information from the first key information corresponding to the at least one first key field.

The first mark is used for uniquely marking the contract information. For example, the first identifier may be a contract number of the contract information, or may also be an identity number of a signer who signs the contract information, and the application is not limited thereto.

In the embodiment of the application, taking the first identifier as the contract number as an example, after the RPA robot acquires the first key information corresponding to at least one first key field, the first key information corresponding to the "contract number" key field in the first key field may be used as the first identifier.

And 105, comparing the first key information corresponding to the at least one first key field with the first to-be-audited information corresponding to the first identifier in the to-be-audited information to obtain a first comparison result, and storing the first comparison result in a preset mode.

The first information to be audited is structured data, that is, includes at least one key field and corresponding key information. For convenience of distinction in the following embodiments, a key field included in the first review information is referred to as a first key field to be reviewed, and key information included in the first review information is referred to as first key information to be reviewed.

The preset mode can be set arbitrarily according to the requirement. For example, the first comparison result may be saved in a table with a specific format; alternatively, the first comparison result may be entered into a business system or other systems, which is not limited in this application.

In the embodiment of the application, after acquiring the first identifier of the contract information, the RPA robot may acquire first information to be checked corresponding to the first identifier from information to be checked of the service system, compare the first key information corresponding to the at least one first key field with the first information to be checked to obtain a first comparison result, and further store the first comparison result in a preset manner.

According to the information auditing method combining the RPA and the AI, the RPA robot acquires contract information to be processed and information to be audited in a business system, identifies the same information based on an Optical Character Recognition (OCR) technology to acquire first text information in the contract information, extracts first key information corresponding to at least one first key field from the first text information based on a Natural Language Processing (NLP) technology, acquires a first identifier corresponding to the contract information from the first key information corresponding to the at least one first key field, compares the first key information corresponding to the at least one first key field with the first information to be audited corresponding to the first identifier in the information to be audited to acquire a first comparison result, and stores the first comparison result in a preset mode. Therefore, the RPA robot is used for acquiring contract information to be processed and information to be checked in the service system, key information in the contract information is acquired based on OCR and NLP technologies, the RPA and AI technologies are combined, the information to be checked in the service system and the key information in the contract information are accurately acquired, the key information and the information to be checked are compared, an accurate comparison result can be obtained, the RPA robot replaces manpower to acquire and compare the information, the labor cost is greatly reduced, and the information checking efficiency is improved.

The information auditing method combining the RPA and the AI provided in the embodiment of the present application is further described below with reference to fig. 2. Fig. 2 is a flowchart of an information auditing method by combining RPA and AI according to a second embodiment of the present application, and as shown in fig. 2, the method includes:

step 201, acquiring contract data to be processed and information to be checked in the service system.

Step 202, recognizing the contract information based on an Optical Character Recognition (OCR) technology to obtain first text information in the contract information.

Step 203, extracting first key information corresponding to at least one first key field from the first text information based on a natural language processing NLP technology.

Step 204, obtaining a first identifier corresponding to the contract information from the first key information corresponding to the at least one first key field.

The specific implementation process and principle of steps 201-204 can refer to the description of the above embodiments, and are not described herein again.

Step 205, obtaining first target key information corresponding to a first target key field from first to-be-audited key information corresponding to each first to-be-audited key field, where the first target key field is the first to-be-audited key field corresponding to the first key field.

The first target key field may include one key field or a plurality of key fields, which is not limited in this application.

In an embodiment of the application, the first to-be-audited information may include first to-be-audited key information corresponding to at least one first to-be-audited key field, and the RPA robot may determine, for each first key field, a first to-be-audited key field corresponding to the first key field from each first to-be-audited key field, further use the first to-be-audited key field corresponding to the first key field as a first target key field, and obtain, from the first to-be-audited information, first target key information corresponding to the first target key field. Therefore, the RPA robot can acquire the first target key fields corresponding to the first key fields respectively and the first target key information corresponding to the first target key fields.

It should be noted that, in the embodiment of the present application, the first key field corresponds to the first key field to be audited, and the field contents of the first key field and the first key field to be audited may be completely the same, for example, the "house area" of the first key field corresponds to the "house area" of the first key field to be audited; or, the first key field corresponds to the first key field to be audited, or the first key field and the first key field to be audited have the same field meaning, in this case, the corresponding relationship between the first key field and the first key field to be audited may be preset, for example, the first key field "third party" may be set to correspond to the first key field "moved person", which is not limited in this application.

Step 206, comparing the first key information corresponding to each first key field with the first target key information corresponding to the first target key field to obtain a first comparison result.

In the embodiment of the application, after the RPA robot acquires the first target key fields corresponding to the first key fields respectively and the first target key information corresponding to the first target key fields, the first target key information corresponding to the first key information is determined according to the corresponding relationship between the first key fields and the first target key fields, and then the first key information is compared with the corresponding first target key information to obtain a first comparison result. The first comparison result comprises comparison results corresponding to each first target key field or each first key field respectively, and the comparison results are matched or not matched.

For example, assume that the first key information corresponding to the first key field "third party" is "third-piece", the first key information corresponding to the first key field "second party" is "b limited", and the first key information corresponding to the first key field "house area" is "80 square meters". The first target key information corresponding to the first target key field 'moved person' is 'Zhang III', the first target key information corresponding to the first target key field 'B Fang' is 'b Limited company', and the first target key information corresponding to the first target key field 'house area' is '81 square meters'. The first key field 'third party' corresponds to the first target key field 'moved person', the first key field 'second party' corresponds to the first target key field 'second party', and the first key field 'house area' corresponds to the first target key field 'house area'.

The RPA robot may compare the first key information "zhang san" corresponding to the first key field "third party" with the first target key information "zhang san" corresponding to the first target key field "moved person", compare the first key information "b limited company" corresponding to the first key field "second party" with the first target key information "b limited company" corresponding to the first target key field "second party", compare the first key information "80 square meters" corresponding to the first key field "house area" with the first target key information "81 square meters" corresponding to the first target key field "house area", and obtain a first comparison result. Wherein, the first comparison result comprises: the comparison result corresponding to the 'moved person' is matching, the comparison result corresponding to the 'second party' is matching, and the comparison result corresponding to the 'house area' is mismatching.

Through the process, the RPA robot can automatically and accurately compare the first key information in the contract data with the first target key information in the first information to be audited, manual assistance is not needed, labor cost is greatly reduced, and information auditing efficiency is improved.

And step 207, storing the first comparison result in a preset mode.

The preset mode can be set arbitrarily according to the requirement. For example, the first comparison result may be saved in a table with a specific format; alternatively, the first comparison result may be recorded in a service system or other systems, which is not limited in this application.

In a possible implementation form of the embodiment of the present application, step 207 may be implemented by: acquiring a first abnormal key field of each first target key field, wherein the corresponding comparison result is unmatched; and storing each first target key field, corresponding first target key information and a first abnormal key field into a preset table.

In another possible implementation form of the embodiment of the present application, step 207 may be implemented by: acquiring a first abnormal key field of each first target key field, wherein the corresponding comparison result is unmatched; generating remark information according to the first abnormal key field; and storing each first target key field, corresponding first target key information and remark information into a preset table.

Through the process, the RPA robot is combined with OCR and NLP technologies, the same data and the information to be checked are automatically compared, the labor cost of information checking is reduced, the efficiency of information checking is improved, in addition, the first comparison result obtained by the RPA robot can be used as a preliminary comparison result, the intelligent automatic information filtering is completed in an auxiliary mode, the first comparison result is stored in a preset table and can be provided for a worker, the worker can further check the information, and therefore the accuracy of the information checking is ensured.

It should be noted that, in practical applications, the contract material may include a seal in addition to the text content, in this embodiment, when the RPA robot identifies the contract material based on the OCR technology, it may identify whether the contract material includes a seal and text information corresponding to the seal content, that is, the first text information may include the text content in the contract material and the text information corresponding to the seal content. The RPA robot can compare text information corresponding to the text content with first target key information corresponding to a first target key field in first to-be-audited information, and can also compare the text information corresponding to the identified seal content with specific key information corresponding to a specific key field in the first to-be-audited information when the contract data is identified to contain the seal, so as to obtain a comparison result corresponding to the seal content, and store the comparison result into a preset table. Wherein the specific key field can be set as required.

For example, a specific key field may be set as an "agreement signing situation", and specific key information corresponding to the specific key field is a company name or a person name of the signing contract information, so that after the RPA robot recognizes that the contract information contains a seal and text information corresponding to the seal content, the text information may be compared with the specific key information corresponding to the "agreement signing situation" in the first information to be verified, and a comparison result corresponding to the seal content is obtained. If the text information is not matched with the specific key information corresponding to the protocol signing condition in the first information to be audited, generating remark information according to the protocol signing condition, wherein signature comparison fails, and storing the specific key field, the corresponding specific key information and the remark information into a preset table.

The following describes an information auditing method combining RPA and AI provided by the present application, with reference to fig. 3 to 7, taking an information auditing scenario of a removed item as an example.

As shown in fig. 3, the AI technology can provide machine learning, deep learning, target detection, entity recognition, text classification, semantic understanding, OCR technology, and NLP technology, in this embodiment of the application, the RPA robot can automatically audit to-be-audited information according to-be-processed contract information by combining the OCR technology and the NLP technology in the AI technology, so as to implement end-to-end intelligent automation.

Specifically, during information auditing, the RPA robot can acquire a scanned part of the paper removal contract and use the scanned part as contract information to be processed, and can log in a business system, collect form information from a display interface of the business system and use the form information as information to be audited. Thus, the RPA robot can acquire multiple types of data from multiple data sources.

Further, the RPA robot may identify the contract information through a custom template based on an OCR technology to obtain first text information in the contract information, and extract structured data from the first text information through a template-based or model-based manner based on an NLP technology, where the structured data includes first key information corresponding to at least one first key field.

Taking the contract data as the form shown in fig. 4-6 as an example, it is assumed that the contents of the contract data that need to be compared with the information to be verified are the contents in

fields

401, 402, and 403 in fig. 4, the contents in field 501 in fig. 5, and the contents in

seals

601, 602, and 603 in fig. 6.

The RPA robot may identify the contract information based on OCR technology to obtain the first text information in the contract information. The first text information includes text information corresponding to text content (including all characters in the contract information), and text information corresponding to the

stamps

601, 602, and 603, respectively. Furthermore, the RPA robot may extract the first key fields and the first key information corresponding to the

fields

401, 402, 403, and 501 from the text information corresponding to the text content based on the NLP technique.

Further, the RPA robot may perform the verification step based on a preset rule. Specifically, the RPA robot may obtain a first identifier corresponding to the contract information from first key information corresponding to at least one first key field, and compare the first key information corresponding to the at least one first key field with first to-be-audited information corresponding to the first identifier in the to-be-audited information to obtain a first comparison result. Moreover, the RPA robot may compare the text information corresponding to the

seals

601, 602, and 603 with the specific key information corresponding to the "protocol signing status" in the first information to be verified, so as to obtain the comparison result corresponding to the seal content.

Further, the RPA robot may store the first comparison result and the comparison result corresponding to the stamp content in a preset manner. Specifically, for the first comparison result, the RPA robot may obtain first abnormal key fields, of the first target key fields, whose corresponding comparison result is unmatched, generate remark information according to the first abnormal key fields, and then store the first target key fields, the corresponding first target key information, and the remark information in a preset table. For the comparison result corresponding to the seal content, if the RPA robot determines that the text information corresponding to the seal content is not matched with the specific key information corresponding to the "protocol signing situation" in the first information to be verified, the RPA robot may generate remark information "signature comparison failure" according to the "protocol signing situation", and store the specific key field, the corresponding specific key information and the remark information into a preset table.

For example, referring to fig. 7, when determining that text information corresponding to the content of the seal in a certain contract document does not match specific key information corresponding to the "agreement signing situation" in the first information to be verified, the RPA robot may generate remark information "signature comparison failure", and store the specific key information corresponding to the "agreement signing situation" and the remark information "signature comparison failure" in the table shown in fig. 7. When the RPA robot determines that the first key information corresponding to the first key field "house location" in a certain contract document is not matched with the first target key information corresponding to the first target key field "house name" in the first information to be audited, the remark information "house name comparison failure" may be generated, and each first target key field, the corresponding first target key information, and the remark information "house name comparison failure" are stored in the table shown in fig. 7.

To sum up, in the information auditing method combining the RPA and the AI provided in the embodiment of the present application, the RPA robot acquires contract information to be processed and information to be audited in the business system, identifies the same information based on an optical character recognition OCR technology to acquire first text information in the contract information, extracts first key information corresponding to at least one first key field from the first text information based on a natural language processing NLP technology, acquires a first identifier corresponding to the contract information from the first key information corresponding to the at least one first key field, acquires first target key information corresponding to a first target key field from the first key information to be audited corresponding to each first key field to be audited, wherein the first target key field is the first key information to be audited corresponding to the first key field, and the first key information corresponding to each first key field is obtained, and comparing the first target key information with the first target key information corresponding to the first target key field to obtain a first comparison result, and storing the first comparison result in a preset mode. Therefore, the RPA robot is used for acquiring contract information to be processed and information to be checked in the service system, key information in the contract information is acquired based on OCR and NLP technologies, the RPA and AI technologies are combined, the information to be checked in the service system and the key information in the contract information are accurately acquired, the key information and the information to be checked are compared, an accurate comparison result can be obtained, the RPA robot replaces manpower to acquire and compare the information, the labor cost is greatly reduced, and the information checking efficiency is improved.

In a possible implementation form, the service system may further include some accessories, for example, in an information auditing scene of the removed project, when key information corresponding to key fields such as "removed person", "house address", "telephone", "house area" and the like is filled in the online service system of the removed resident, a scanning piece of a certificate such as an identity card, a house property card and the like is used as an accessory to upload the service system. In the embodiment of the application, the RPA robot can also compare the certificate information with the information to be checked in the service system. With reference to fig. 8, an information auditing method combining RPA and AI according to an embodiment of the present application will be described below.

Fig. 8 is a flowchart of an information auditing method according to a third embodiment of the present application, where as shown in fig. 8, the method may further include:

step 801, acquiring the certificate information to be processed with the second identifier.

It should be noted that, in the embodiment of the present application, the processes of acquiring the credential data and comparing the credential data with the information to be checked may be executed simultaneously with the processes of acquiring the contract data and comparing the contract data with the information to be checked in the method shown in fig. 1, or may be executed sequentially, which is not limited in the present application.

The certificate information can be any certificate information with a fixed format, such as an identity card, a household notebook and the like.

The second identifier is used for uniquely identifying the certificate information, and may be an identification number, a telephone number, or the like, which is not limited in this application.

In the embodiment of the application, the certificate information can be acquired in any way. For example, the certificate information may be scanned certificate information obtained by scanning paper certificate information, or may be electronic certificate information downloaded from an online service system, and the application is not limited thereto.

Taking an information auditing scene of a removal project as an example, a removal resident needs to fill in key information corresponding to key fields such as a 'removal person', 'house address', 'telephone', 'house area' and the like in a service system on line, meanwhile, a scanning piece of certificates such as an identity card, a house certificate and the like is uploaded to the service system as an accessory and signed with a paper removal contract, and old modified workers can input the key information corresponding to the key fields such as 'contract number', 'party A', 'party B' and the like in the removal contract into the service system, so that form information is generated, wherein the form information comprises the information filled in by the removal resident and the contract information input by the workers. When form information in the business system needs to be checked, a worker can scan the paper removal contract, so that the RPA robot can obtain a scanned piece of the paper removal contract, and the scanned piece is contract information to be processed in the embodiment of the application. Moreover, the RPA robot can log in the service system, and collect form information from a display interface of the service system, where the form information is to-be-checked information in the embodiment of the present application. In addition, the RPA robot can download the scanning pieces of the identity card, the house property card and other certificates uploaded by the removed residents from the service system, and the scanning pieces are certificate information in the embodiment of the application.

It should be noted that, when the RPA robot downloads the credential data, it knows which user corresponds to the downloaded credential data, so that the RPA robot can simultaneously obtain the second identifier corresponding to the credential data when downloading the credential data.

Step 802, identifying the certificate information based on an Optical Character Recognition (OCR) technology to obtain second key information corresponding to at least one second key field in the certificate information.

And the second key field can be set as required. For example, all key fields that can be extracted from the certificate information can be set; alternatively, certain key fields may be set, for example, the fields may be set to "name", "birth", "address", etc., which is not limited in this application.

It will be appreciated that the credential material is typically in a fixed format, and that the RPA robot recognizes the credential material based on OCR technology to obtain the structured data in the credential material. The structured data includes second key information corresponding to at least one second key field, and each second key field and the corresponding second key information are a piece of structured data.

Step 803, comparing the second key information corresponding to the at least one second key field with the second to-be-checked information corresponding to the second identifier in the to-be-checked information to obtain a second comparison result.

The second information to be audited is structured data, that is, includes at least one key field and corresponding key information. For convenience of distinction in the following embodiments, the key field included in the second review information is referred to as a second key field to be reviewed, and the key information included in the second review information is referred to as second key information to be reviewed. That is, the second to-be-audited information includes second to-be-audited key information corresponding to at least one second to-be-audited key field.

In the embodiment of the application, the RPA robot may obtain second information to be checked corresponding to the second identifier from the information to be checked of the service system, and compare the second key information corresponding to the at least one second key field with the second information to be checked to obtain a second comparison result.

Specifically, step 803 may be implemented as follows: acquiring second target key information corresponding to a second target key field from second to-be-audited key information corresponding to each second to-be-audited key field, wherein the second target key field is the second to-be-audited key field corresponding to the second key field; and comparing the second key information corresponding to each second key field with the second target key information corresponding to the second target key field to obtain a second comparison result.

The second target key field may include one key field or a plurality of key fields, which is not limited in this application.

In an embodiment of the application, the second to-be-audited information may include second to-be-audited key information corresponding to at least one second to-be-audited key field, and for each second key field, the RPA robot may determine, from each second to-be-audited key field, a second to-be-audited key field corresponding to the second key field, further use the second to-be-audited key field corresponding to the second key field as a second target key field, and obtain, from the second to-be-audited information, second target key information corresponding to the second target key field. Therefore, the RPA robot can acquire the second target key fields corresponding to the second key fields respectively and the second target key information corresponding to the second target key fields.

It should be noted that, in the embodiment of the present application, the second key field corresponds to the second key field to be audited, the field contents of the second key field and the second key field to be audited may be completely the same, or the second key field corresponds to the second key field to be audited, or the field meanings of the second key field and the second key field to be audited are the same, in this case, the corresponding relationship between the first key field and the first key field to be audited may be preset, which is not limited in this application.

Furthermore, after the RPA robot acquires the second target key fields corresponding to the second key fields and the second target key information corresponding to the second target key fields, the RPA robot determines the second target key information corresponding to the second key information according to the corresponding relationship between the second key fields and the second target key fields, and then compares the second key information with the corresponding second target key information to obtain a second comparison result. The second comparison result comprises comparison results corresponding to each second target key field or each second key field respectively, and the comparison results are matched or not matched.

Through the process, the RPA robot can automatically and accurately compare each second key information in the certificate data with each second target key information in the second information to be audited, manual assistance is not needed, labor cost is greatly reduced, and information auditing efficiency is improved.

And step 804, storing the second comparison result in a preset mode.

In a possible implementation form of the embodiment of the present application, step 804 may be implemented by: acquiring second abnormal key fields of which the corresponding comparison results are unmatched from the second target key fields; and storing each second target key field, the corresponding second target key information and the second abnormal key field into a preset table.

In another possible implementation form of the embodiment of the present application, step 804 may be implemented by: acquiring second abnormal key fields of which the corresponding comparison results are unmatched from the second target key fields; generating remark information according to the second abnormal key field; and storing each second target key field, corresponding second target key information and remark information into a preset table.

According to the information auditing method combining the RPA and the AI, the RPA robot acquires to-be-processed certificate information with a second identifier, identifies the certificate information based on an Optical Character Recognition (OCR) technology to acquire second key information corresponding to at least one second key field in the certificate information, compares the second key information corresponding to the at least one second key field with the second to-be-audited information corresponding to the second identifier in the to-be-audited information to obtain a second comparison result, and stores the second comparison result in a preset mode. Therefore, the certificate information with the second identification to be processed and the information to be checked in the service system are acquired through the RPA robot, the key information in the certificate information is acquired based on OCR, the fact that the information to be checked in the service system and the key information in the certificate information are accurately acquired by combining RPA and AI technologies is achieved, the key information and the information to be checked are compared, an accurate comparison result can be obtained, the RPA robot replaces manpower to acquire the information and compare the information, labor cost is greatly reduced, and information checking efficiency is improved.

In order to implement the above embodiments, the present application further provides an information auditing apparatus combining an RPA and an AI. Fig. 9 is a schematic structural diagram of an information auditing apparatus according to a fourth embodiment of the present application, which combines RPA and AI.

As shown in fig. 9, the information auditing apparatus 900 combining RPA and AI is applied to an RPA robot, and includes: a first obtaining module 901, a first identifying module 902, an extracting module 903, a second obtaining module 904 and a first processing module 905.

The first obtaining module 901 is configured to obtain contract information to be processed and information to be checked in the service system;

the first recognition module 902 is configured to recognize the contract information based on an optical character recognition OCR technology to obtain first text information in the contract information;

an extraction module 903, configured to extract, based on a natural language processing NLP technique, first key information corresponding to at least one first key field from the first text information;

a second obtaining module 904, configured to obtain a first identifier corresponding to the contract information from the first key information corresponding to the at least one first key field;

the first processing module 905 is configured to compare the first key information corresponding to the at least one first key field with the first to-be-audited information corresponding to the first identifier in the to-be-audited information to obtain a first comparison result, and store the first comparison result in a preset manner.

It should be noted that the information auditing device combining the RPA and the AI according to the embodiment of the present application may perform the information auditing method combining the RPA and the AI according to the embodiment described above. For example, the information auditing device combining the RPA and the AI may be an RPA robot, or the information auditing device may be configured in the RPA robot, which is not limited in this application.

In an embodiment of the present application, the first to-be-audited information includes first to-be-audited key information corresponding to at least one first to-be-audited key field;

a first processing module 905 comprising:

the first obtaining unit is used for obtaining first target key information corresponding to a first target key field from first to-be-audited key information corresponding to each first to-be-audited key field, wherein the first target key field is the first to-be-audited key field corresponding to the first key field;

and the first comparison unit is used for comparing the first key information corresponding to each first key field with the first target key information corresponding to the first target key field to obtain a first comparison result.

In an embodiment of the application, the first comparison result includes comparison results corresponding to the first target key fields respectively, and the comparison results are matching or non-matching;

a first processing module 905, comprising:

the second acquisition unit is used for acquiring the first abnormal key fields of which the corresponding comparison results are unmatched in each first target key field;

and the storage unit is used for storing each first target key field, the corresponding first target key information and the first abnormal key field into a preset table.

In an embodiment of the present application, the information auditing apparatus combining RPA and AI further includes:

the third acquisition module is used for acquiring certificate data to be processed with a second identifier;

the second identification module is used for identifying the certificate information based on an Optical Character Recognition (OCR) technology so as to acquire second key information corresponding to at least one second key field in the certificate information;

and the second processing module is used for comparing second key information corresponding to at least one second key field with second to-be-checked information corresponding to a second identifier in the to-be-checked information to obtain a second comparison result, and storing the second comparison result in a preset mode.

In an embodiment of the application, the second information to be audited includes second key information to be audited corresponding to at least one second key field to be audited; a second processing module comprising:

a third obtaining unit, configured to obtain second target key information corresponding to a second target key field from second to-be-inspected key information corresponding to each second to-be-inspected key field, where the second target key field is a second to-be-inspected key field corresponding to the second key field;

and the second comparison unit is used for comparing the second key information corresponding to each second key field with the second target key information corresponding to the second target key field to obtain a second comparison result.

It should be noted that the foregoing explanation of the embodiment of the information auditing method combining RPA and AI is also applicable to the information auditing device combining RPA and AI of this embodiment, and details that are not published in the embodiment of the information auditing device combining RPA and AI are not described here again.

To sum up, in the information auditing device combining the RPA and the AI according to the embodiment of the present application, the RPA robot acquires contract information to be processed and information to be audited in the business system, identifies the identical information based on an optical character recognition OCR technology to acquire first text information in the contract information, extracts first key information corresponding to at least one first key field from the first text information based on a natural language processing NLP technology, acquires a first identifier corresponding to the contract information from the first key information corresponding to the at least one first key field, compares the first key information corresponding to the at least one first key field with the first information to be audited corresponding to the first identifier in the information to be audited to obtain a first comparison result, and stores the first comparison result in a preset manner. Therefore, the RPA robot is used for acquiring contract information to be processed and information to be checked in the service system, key information in the contract information is acquired based on OCR and NLP technologies, the RPA and AI technologies are combined, the information to be checked in the service system and the key information in the contract information are accurately acquired, the key information and the information to be checked are compared, an accurate comparison result can be obtained, the RPA robot replaces manpower to acquire and compare the information, the labor cost is greatly reduced, and the information checking efficiency is 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 information auditing method combining RPA and AI according to any one of the foregoing method embodiments.

In order to implement the foregoing embodiments, the present application further proposes a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the information auditing method by combining 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 of the computer program product, the information auditing method combining RPA and AI according to any one of the foregoing method embodiments is implemented.

FIG. 10 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. 10 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in FIG. 10, 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. 10, and commonly referred to as a "hard drive"). Although not shown in FIG. 10, 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. 10, the network adapter 20 communicates with the other modules of the electronic device 12 over the bus 18. It should be appreciated that although not shown in FIG. 10, 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 specifically limited 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, the various steps or methods may be implemented in software or firmware stored in 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 out in the method of 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 the program, when executed, 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. While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are exemplary and should not be construed as limiting the present application and that changes, modifications, substitutions and alterations in the above embodiments may be made by those of ordinary skill in the art within the scope of the present application.

Claims

1. An information auditing method combining Robot Process Automation (RPA) and Artificial Intelligence (AI), which is applied to an RPA robot, and comprises the following steps:

acquiring contract data to be processed and information to be checked in a service system;

identifying the contract information based on an Optical Character Recognition (OCR) technology to acquire first text information in the contract information;

extracting first key information corresponding to at least one first key field from the first text information based on a Natural Language Processing (NLP) technology;

acquiring a first identifier corresponding to the contract information from first key information corresponding to at least one first key field;

comparing first key information corresponding to at least one first key field with first to-be-audited information corresponding to the first identification in the to-be-audited information to obtain a first comparison result, and storing the first comparison result in a preset mode.

2. The method according to claim 1, wherein the first to-be-audited information includes first to-be-audited key information corresponding to at least one first to-be-audited key field;

the comparing the first key information corresponding to at least one first key field with the first to-be-audited information corresponding to the first identifier in the to-be-audited information to obtain a first comparison result includes:

acquiring first target key information corresponding to a first target key field from first to-be-audited key information corresponding to each first to-be-audited key field, wherein the first target key field is the first to-be-audited key field corresponding to the first key field;

and comparing the first key information corresponding to each first key field with the first target key information corresponding to the first target key field to obtain the first comparison result.

3. The method according to claim 2, wherein the first comparison result comprises a comparison result corresponding to each of the first target key fields, and the comparison result is a match or a mismatch;

the storing the first comparison result in a preset mode includes:

acquiring a first abnormal key field of each first target key field, wherein the corresponding comparison result is unmatched;

and storing each first target key field, corresponding first target key information and the first abnormal key field into a preset table.

4. The method according to any one of claims 1-3, further comprising:

acquiring certificate data to be processed with a second identifier;

based on an Optical Character Recognition (OCR) technology, recognizing the certificate data to acquire second key information corresponding to at least one second key field in the certificate data;

and comparing second key information corresponding to at least one second key field with second to-be-checked information corresponding to the second identifier in the to-be-checked information to obtain a second comparison result, and storing the second comparison result in a preset mode.

5. The method according to claim 4, wherein the second information to be audited includes second key information to be audited corresponding to at least one second key field to be audited;

the comparing the second key information corresponding to at least one second key field with the second to-be-checked information corresponding to the second identifier in the to-be-checked information to obtain a second comparison result includes:

acquiring second target key information corresponding to a second target key field from second to-be-audited key information corresponding to each second to-be-audited key field, wherein the second target key field is the second to-be-audited key field corresponding to the second key field;

and comparing the second key information corresponding to each second key field with the second target key information corresponding to the second target key field to obtain a second comparison result.

6. An information auditing device combining RPA and AI, which is applied to an RPA robot, and comprises:

the first acquisition module is used for acquiring contract information to be processed and information to be checked in the service system;

the first identification module is used for identifying the contract information based on an Optical Character Recognition (OCR) technology so as to acquire first text information in the contract information;

the extraction module is used for extracting first key information corresponding to at least one first key field from the first text information based on a Natural Language Processing (NLP) technology;

the second obtaining module is used for obtaining a first identifier corresponding to the contract information from first key information corresponding to at least one first key field;

the first processing module is configured to compare first key information corresponding to at least one first key field with first to-be-audited information corresponding to the first identifier in the to-be-audited information to obtain a first comparison result, and store the first comparison result in a preset manner.

7. The apparatus according to claim 6, wherein the first to-be-audited information includes first to-be-audited key information corresponding to at least one first to-be-audited key field;

the first processing module comprises:

a first obtaining unit, configured to obtain first target key information corresponding to a first target key field from first to-be-inspected key information corresponding to each first to-be-inspected key field, where the first target key field is a first to-be-inspected key field corresponding to the first key field;

and the first comparison unit is used for comparing the first key information corresponding to each first key field with the first target key information corresponding to the first target key field to obtain the first comparison result.

8. The apparatus of claim 7, wherein the first comparison result comprises a comparison result corresponding to each of the first target key fields, and the comparison result is a match or a mismatch;

the first processing module comprises:

the second obtaining unit is used for obtaining first abnormal key fields, of the first target key fields, of which the corresponding comparison results are unmatched;

9. The apparatus of any of claims 6-8, further comprising:

and the second processing module is used for comparing second key information corresponding to at least one second key field with second to-be-checked information corresponding to the second identifier in the to-be-checked information to obtain a second comparison result, and storing the second comparison result in a preset mode.

10. The apparatus according to claim 9, wherein the second information to be audited includes second key information to be audited corresponding to at least one second key field to be audited;

the second processing module comprises:

11. 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 one of claims 1-5 when executing the computer program.

12. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-5.