CN114358707A - Man-machine cooperative hybrid examination order decision method and system - Google Patents
Man-machine cooperative hybrid examination order decision method and system Download PDFInfo
- Publication number
- CN114358707A CN114358707A CN202111459250.8A CN202111459250A CN114358707A CN 114358707 A CN114358707 A CN 114358707A CN 202111459250 A CN202111459250 A CN 202111459250A CN 114358707 A CN114358707 A CN 114358707A
- Authority
- CN
- China
- Prior art keywords
- document
- examination
- information
- approval
- approved
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012550 audit Methods 0.000 claims abstract description 74
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000012795 verification Methods 0.000 claims description 15
- 238000012015 optical character recognition Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 7
- 239000000463 material Substances 0.000 description 6
- 241001178520 Stomatepia mongo Species 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004806 packaging method and process Methods 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000945 filler Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012946 outsourcing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a man-machine cooperative hybrid examination and approval decision method and a man-machine cooperative hybrid examination and approval decision system, which are applied to a robot examination and approval system, wherein the robot examination and approval system is in data connection with a document examination and approval system and receives an examination and approval request of the document examination and approval system; acquiring form data of the financial documents to be approved from the document approval system and storing the form data; acquiring and storing image attachments of the financial documents to be approved; integrating the form data and the accessory image into information to be audited; a rule engine is called to audit the information to be audited to obtain an audit result; when the auditing result does not contain error reporting information and manual processing information, marking the financial document to be audited as approved, and sending the approved financial document to the document auditing and approving system; according to the document examination and approval system and the document examination and approval method, the information to be examined is examined through the preset rules in the rule engine to obtain the examination and approval result, and the corresponding processing information is sent to the document examination and approval system according to the examination and approval result, so that the document examination and approval efficiency can be improved, and the financial risk can be reduced.
Description
Technical Field
The invention belongs to the technical field of document auditing, and particularly relates to a man-machine collaborative hybrid document auditing decision method and system.
Background
The receipt refers to a receipt for paying money or goods, such as a receipt, an invoice, a bill of delivery, a receipt, and the like. In daily work, documents usually require auditing and approval by the responsible persons of the departments of the work unit. However, for a working unit with a large business volume, documents are various in forms, auditing rules of various documents are different, and manual auditing has a certain error rate. Therefore, various financial software or office software appears, in such software, a filler usually uploads a document to be checked in a software system, after the document is filled, the software sends the document to be checked to accounts of the approvers of each layer by layer, and then the approvers of each layer perform layer by layer approval.
However, for a group company with a large business volume, the number of documents is very large, and although manual signing, examination and approval by taking paper documents layer by layer are omitted, each layer of auditors is required to log in a financial system for manual examination and approval, which wastes a large amount of flow time. Moreover, the auditors can add their own judgment in the process of examining the bills, and are influenced by various factors such as their own experience and business capability, each person has different understanding on the same business and rule, different judgment standards and different auditing results, and some errors or problems are possibly missed and not found under the condition of inattentive attention or auditing fatigue, thus leaving hidden dangers and having uncontrollable risks.
Disclosure of Invention
The invention aims to provide a man-machine cooperative hybrid examination decision method and a man-machine cooperative hybrid examination decision system.
The invention adopts the following technical scheme: a man-machine cooperative hybrid examination and decision method is applied to an autonomous robot auditing system, the autonomous robot auditing system is in data connection with a document approval system, and the method comprises the following steps:
receiving a document examination request of a document examination and approval system;
acquiring form data of the financial documents to be approved from the document approval system and storing the form data; acquiring and storing image attachments of the financial documents to be approved;
integrating the form data and the accessory image into information to be audited;
a rule engine is called to audit the information to be audited to obtain an audit result;
and when the audit result does not contain error reporting information and manual processing information, marking the financial document to be audited as approved, and sending the audit result, all the approved audit rule lists corresponding to the audit result, all the checked risk early warning rule lists and the risk early warning prompts to the document approval system.
Further, obtaining and storing form data for the pending financial document from the document approval system comprises:
and respectively acquiring document information, statement information, invoice information, accessory information and examination and approval opinions.
Further, obtaining and storing form data for the pending financial document from the document approval system comprises:
the form data is stored in a first database.
Further, acquiring and storing image attachments of the financial documents to be examined and approved;
the image attachment is stored in a second database.
Further, obtaining an image attachment of the pending financial document comprises:
acquiring a URL (uniform resource locator) of an accessory in a document approval system;
acquiring an attachment according to the URL;
generating a picture attachment according to the attachment;
processing the picture attachment using an optical character recognition method to generate structured data.
Further, the fusing the form data and the attachment image into the information to be audited includes:
calling the form data in the JSON format from the first database;
calling the structured data in the JSON format from the second database;
and performing character string splicing on the form data in the JSON format and the structured data to obtain the information to be audited.
And further, when the audit result contains error reporting information, marking the financial document to be audited as rejected audit, and sending the audit result, all the corresponding approved audit rule lists, all the non-approved audit rule lists and reasons, all the checked risk early warning rule lists and the risk early warning prompts to the document approval system.
And further, when the audit result contains manual processing information, marking the financial document to be audited as manual audit, and sending the audit result, all the approved audit rule lists corresponding to the audit result, all the audit rule lists which are triggered to be audited, all the reasons for the audit rule lists, all the checked risk early warning rule lists and all the checked risk early warning prompts to the document auditing system.
The other technical scheme of the invention is as follows: a man-machine cooperative hybrid examination decision making system is applied to an autonomous robot auditing system, the autonomous robot auditing system is in data connection with a document approval system, and the system comprises:
the receiving module is used for receiving a document examination request of the document examination and approval system;
the acquisition module is used for acquiring and storing form data of the financial document to be approved from the document approval system; acquiring and storing image attachments of the financial documents to be approved;
the fusion module is used for fusing the form data and the image attachment into information to be audited;
the auditing module is used for calling the rule engine to audit the information to be audited to obtain an auditing result;
and the sending module is used for marking the financial documents to be approved as approved when the audit result does not contain error reporting information and manual processing information, and sending the audit result, all the approved audit rule lists corresponding to the audit result, all the checked risk early warning rule lists and the risk early warning prompts to the document approval system.
The other technical scheme of the invention is as follows: a man-machine cooperative hybrid examination and decision making system comprises a document examination and approval system and a robot auditing system which are connected by data, wherein the robot auditing system comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, and the man-machine cooperative hybrid examination and decision making method is realized when the processor executes the computer program.
The invention has the beneficial effects that: according to the invention, the mixed examination and approval decision method is applied to the robot examination and approval system, the document examination and approval system is used for acquiring the data of the document to be examined and approved, the data are subjected to unified format conversion storage and are fused into the information to be examined and approved, the information to be examined and approved is examined and approved through the preset rule in the rule engine to obtain the examination and approval result, and the corresponding processing information is sent to the document examination and approval system according to the examination and approval result, so that the examination and approval efficiency can be improved, and the financial risk can be reduced.
Drawings
FIG. 1 is a diagram illustrating table master information in an embodiment of the present invention;
FIG. 2 is a schematic diagram of a form statement and invoice information in accordance with an embodiment of the present invention;
FIG. 3 is a diagram illustrating image regions and approval opinions according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an attachment list in an embodiment of the present invention;
FIG. 5 is a flow chart of a human-computer collaborative hybrid examination order decision method according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating the general rules of a labor statement in accordance with an embodiment of the present invention;
FIG. 7 is a diagram illustrating the private rules of the labor statement of the present invention;
fig. 8 is a diagram illustrating an audit result list according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
The invention discloses a man-machine cooperative hybrid examination and decision method, which is applied to a robot examination and verification system, wherein the robot examination and verification system is in data connection with a document examination and approval system, and the method comprises the following steps: receiving a document examination request of a document examination and approval system; acquiring form data of the financial documents to be approved from the document approval system and storing the form data; acquiring and storing image attachments of the financial documents to be approved; integrating the form data and the accessory image into information to be audited; a rule engine is called to audit the information to be audited to obtain an audit result; and when the audit result does not contain error reporting information and manual processing information, marking the financial document to be audited as approved, and sending the audit result, all the approved audit rule lists corresponding to the audit result, all the checked risk early warning rule lists and the risk early warning prompts to the document approval system.
According to the invention, the mixed examination and approval decision method is applied to the robot examination and approval system, the document examination and approval system is used for acquiring the data of the document to be examined and approved, the data are subjected to unified format conversion storage and are fused into the information to be examined and approved, the information to be examined and approved is examined and approved through the preset rule in the rule engine to obtain the examination and approval result, and the corresponding processing information is sent to the document examination and approval system according to the examination and approval result, so that the examination and approval efficiency can be improved, and the financial risk can be reduced.
In this embodiment, obtaining and storing form data of the pending financial document from the document approval system includes: and respectively acquiring document information, statement information, invoice information, accessory information and examination and approval opinions.
In this embodiment, as shown in fig. 1, fig. 2 and fig. 3, taking the labor settlement sheet as an example, the form data includes: document information, detailed lists, invoice information and examination and approval opinions. Form data can be directly extracted from an approval interface (namely a document approval system) of a sharing platform through an RPA data crawling technology without accessing a background database of the financial sharing platform. Therefore, according to the auditing requirement, the main table field is captured: the system comprises a document number, a client name, a tax payment identification number, a legal subject, an invoicing name, an organization name, a single making person, a tax counting mode, a project tax counting mode, a company tax counting mode, a current settlement amount, an entry tax amount to be settled, an entry cost amount, an account entry mode, a certificate making date, a common ticket value-added tax amount, an organization name, whether the settlement is carried out at the last time, an account attribute, a settlement mode and a payment route. Fetch list field: project job number, application, private assistance, expense category assistance, scientific research project, amount of money, tax amount and invoice category. And capturing the opinion of the project manager and the project bookmarking examination and approval and all invoice line information. And directly packaging the form data information into JSON and storing the JSON into a system Mongo database.
As one implementation, obtaining and storing form data of a pending financial document from a document approval system includes: the form data is stored in a first database. In one embodiment, image attachments to the financial documents to be approved are obtained and stored; the image attachment is stored in a second database. The form data and the accessory data are stored separately, so that data maintenance and later verification can be facilitated.
When an image attachment needs to be acquired, the following steps are typically included: acquiring a URL (uniform resource locator) of an accessory in a document approval system; acquiring an attachment according to the URL; the picture attachment is generated from the attachment, and the structured data is generated by processing the picture attachment using an optical character recognition method (i.e., OCR technology).
And capturing the image data to obtain an attachment URL through a form image area file list, obtaining a picture URL through an attachment converter, identifying image data information through OCR (optical character recognition), packaging by JSON (java server object notation) and storing in a MySQL database. The image attachment types generally include invoices and homemade documents.
In the accessory, the more important is the invoice, and in order to guarantee the accuracy and the authenticity of the invoice information, a special verification mechanism is adopted for extracting the invoice information in the embodiment.
Firstly, identifying the full invoice surface information of the invoice through OCR, and calling a navigation communication interface according to four invoice factors (invoice code, invoice number, invoice date and amount) to obtain invoice authenticity verification information and full invoice surface information of the invoice. However, there is instability in invoking the airline interface or OCR recognition, and therefore, an invoice verity-check exception handling mechanism is employed. For the abnormal situation occurring in the invoice true checking process, if the interface is abnormal during calling, the interface is repeatedly called for 2 times; if the four-element information of the invoice is identified wrongly, adopting an invoice machine to print numbers and codes to replace the invoice numbers and the codes, and checking the authenticity of the invoice; if the invoice true-checking result cannot be obtained, extracting four-element information of the invoice by adopting the invoice two-dimensional code to obtain the true-checking result; if the abnormal condition still occurs, invoice truth-checking information is pushed from the intermediate library of the intelligent examination order and the financial sharing platform. If the operation is not successful and the verification fails, the invoice information is replaced by the full-ticket information identified by the OCR.
In this embodiment, as shown in fig. 5, the front-end service (i.e., the method of this embodiment) receives the data pushed by the RPA, stores the single data information in the Mongo database, and stores the attachment information in the MySQL database. And calling an attachment conversion interface, calling a financial sharing platform image system through an attachment URL, acquiring a picture URL, storing the picture URL into a MySQL database, and uniformly converting the formats of attachments such as word, PDF, excel, png, GIF and the like into a jpg format. And calling an OCR interface, acquiring picture information through the picture URL, further generating structured data, and storing the identified image information into a MySQL database.
And then the preposed service completes data packaging work, namely converting the field name or the auditing node of the data identified by the OCR or the data acquired by invoice verification into the data required by the rule engine and storing the data into the MySQL database. The pre-service takes out the encapsulated JSON format structured data from the MySQL database, takes out the JSON format form information from the Mongo database, carries out analysis splicing (character string splicing), calls a rule engine interface, obtains the auditing result of the JSON format, and stores the auditing result of the form, including whether the form auditing is passed, the early warning level, the wrong reporting operation and the number of form auditing rules into the MySQL database. The rules Engine Login Authority store uses the Redis database. And finally, the prepositive service transmits the data of the checking result back to the RPA, and the RPA executes the action of the robot according to the checking result to finish the checking process of the robot.
That is, in order to audit the document to be approved, fusing the form data and the attachment image into the information to be audited includes: calling the form data in the JSON format from the first database; calling the structured data in the JSON format from the second database; and carrying out character string splicing on the form data in the JSON format and the image attachment to obtain the information to be audited.
Financial forms can be classified into seven categories according to business characteristics: settlement type, income type, expense type, payment type, tax type, material type, and other types. The settlement type form relates to a labor settlement form, a material settlement form, a labor settlement form (cost push), a material settlement form (cost push), other direct expense settlement forms (cost), a mechanical lease settlement form and a material settlement form (company).
In the embodiment, the explanation is given by taking the audit rule of the labor settlement statement as an example because the documents are of various types. As shown in fig. 6, the general rules of the settlement type forms are extracted to complete invoice information verification, and if the verification fails, manual processing is performed.
The settlement type general rule is suitable for 9 settlement types of forms, namely the 9 settlement types of forms are verified by the general rule. And (3) extracting general rules of 5 new forms of a labor settlement bill, a material settlement bill, other direct expense settlement bills, a mechanical lease settlement bill and a material settlement bill (company), wherein the rules are suitable for partial settlement type forms, and according to form verification requirements, the other 4 forms of the settlement type do not need to verify the partial general rules.
These rules are preset during the audit of the statement. And auditing according to the acquired form name, settlement mode, payment path, account attribute data information and bank receipt in the image list. First, when the name of the form is judged as 'labor settlement form', the rule is checked. And judging that when the settlement mode is 'online banking', the payment way is 'medium iron fund', and the account attribute is 'direct connection' or 'non-direct connection', the image accessory needs to have a bank receipt, and if the bank receipt does not exist, the auditing result displays the early warning information 'lack of the bank receipt'.
And each form of the settlement type has a corresponding private rule, and routing selection is performed according to the condition judgment of the form name. Taking the labor settlement sheet as an example, when the name of the form is judged to be the labor settlement sheet, the private and regular decision judgment is carried out, and when the name of the form is not the labor settlement sheet, the decision judgment is not carried out.
As shown in fig. 7, when the form name is "labor settlement form" and the form invoice type is "special invoice", the form detail table tax amount field and the form invoice information tax amount field are compared to check the special invoice tax amount, if they are not equal, the total of the listed tax amount and the invoice tax amount does not conform, and the rule is not approved and rejected.
The outsourcing project inspection worker settlement table is a self-made receipt, fields need to be acquired through OCR image recognition, and when the name of the form is 'labor settlement table', whether the name of a form information client is consistent with the field of the image recognition party B or not is verified. If not, the unit name of the second party of the settlement list is not consistent with the client name of the form, and manual verification is carried out.
After the audit is completed, as shown in fig. 8, there are various audit results. And when the audit result contains error reporting information, marking the to-be-audited financial document as rejected audit, and sending the audit result, all the corresponding passed audit rule lists, all the failed audit rule lists and reasons, all the checked risk early warning rule lists and risk early warning prompts to the document approval system, so that the problem can be directly found out and pertinently processed during later manual investigation. And when the audit result contains manual processing information, marking the financial documents to be audited as manual audit, and sending the audit result, all the corresponding approved audit rule lists, all the audit rule lists and reasons for triggering manual audit, all the checked risk early warning rule lists and the risk early warning prompts to the document approval system. Similarly, the method can be conveniently and pertinently processed during manual examination, saves examination and verification time, and improves examination and verification efficiency
The prepositive service transmits the rule engine checking result back to the RPA, and the RPA executes the checking and approving process according to the checking result and the error reporting operation. When the refund action is executed, the financial auditing process returns to a service node (in a document auditing system) to modify form information, and the service is approved again, and the process is completed through robot auditing; when the robot executes manual operation, financial audit nodes are added in the process to assist the robot in approval, and manual verification is completed; and when the robot executes the agreement action, the financial auditing process is carried out in sequence, and the financial auditing process is circulated to the financial processing node to finish the auditing process.
The invention also discloses a man-machine cooperative hybrid examination and decision system, which is applied to an autonomous robot auditing system, wherein the autonomous robot auditing system is in data connection with a document approval system, and the system comprises: the receiving module is used for receiving a document examination request of the document examination and approval system; the acquisition module is used for acquiring and storing form data of the financial document to be approved from the document approval system; acquiring and storing image attachments of the financial documents to be approved; the fusion module is used for fusing the form data and the image attachment into information to be audited; the auditing module is used for calling the rule engine to audit the information to be audited to obtain an auditing result; and the sending module is used for marking the financial documents to be approved as approved when the audit result does not contain error reporting information and manual processing information, and sending the audit result, all the approved audit rule lists corresponding to the audit result, all the checked risk early warning rule lists and the risk early warning prompts to the document approval system.
It should be noted that, for the information interaction, execution process, and other contents between the modules of the apparatus, the specific functions and technical effects of the embodiments of the method are based on the same concept, and thus reference may be made to the section of the embodiments of the method specifically, and details are not described here.
It will be clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely illustrated, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules to perform all or part of the above described functions. Each functional module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional modules are only used for distinguishing one functional module from another, and are not used for limiting the protection scope of the application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The embodiment of the invention also discloses a man-machine cooperative hybrid examination and decision making system, which is applied to a robot auditing system, wherein the robot auditing system is in data connection with the document approval system, the robot auditing system comprises a memory, a processor and a computer program which is stored in the memory and can be operated on the processor, and the man-machine cooperative hybrid examination and decision making method is realized when the processor executes the computer program.
The device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing equipment. The apparatus may include, but is not limited to, a processor, a memory. Those skilled in the art will appreciate that the apparatus may include more or fewer components, or some components in combination, or different components, and may also include, for example, input-output devices, network access devices, etc.
The Processor may be a Central Processing Unit (CPU), or other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may in some embodiments be an internal storage unit of the device, such as a hard disk or a memory of the device. The memory may also be an external storage device of the apparatus in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the apparatus. Further, the memory may also include both an internal storage unit and an external storage device of the apparatus. The memory is used for storing an operating system, application programs, a BootLoader (BootLoader), data, and other programs, such as program codes of the computer programs. The memory may also be used to temporarily store data that has been output or is to be output.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment. Those of ordinary skill in the art will appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
Claims (10)
1. A man-machine cooperative hybrid examination and decision method is characterized by being applied to an autonomous robot auditing system, wherein the autonomous robot auditing system is in data connection with a document approval system, and the method comprises the following steps:
receiving a document examination request of a document examination and approval system;
acquiring form data of the financial documents to be approved from the document approval system and storing the form data; acquiring and storing the image attachments of the to-be-approved financial documents;
fusing the form data and the accessory image into information to be audited;
a rule engine is called to audit the information to be audited to obtain an audit result;
and when the audit result does not contain error reporting information and manual processing information, marking the to-be-audited financial document as approved, and sending the audit result, all the corresponding approved audit rule lists, all checked risk early warning rule lists and risk early warning prompts to the document approval system.
2. The human-computer collaborative hybrid invoice decision method of claim 1, wherein obtaining and storing form data of pending financial documents from the document approval system comprises:
and respectively acquiring document information, statement information, invoice information, accessory information and examination and approval opinions.
3. The human-computer collaborative hybrid approval decision method of claim 2, wherein obtaining and storing form data of pending financial documents from the document approval system comprises:
storing the form data in a first database.
4. The human-computer collaborative hybrid invoice decision method of claim 3, wherein image attachments to the pending financial documents are obtained and stored;
storing the image attachment in a second database.
5. The human-computer collaborative hybrid invoice decision method of any one of claims 2-4, wherein obtaining an image attachment to the pending financial document comprises:
acquiring a URL (uniform resource locator) of an accessory in the document approval system;
acquiring the attachment according to the URL;
generating a picture attachment according to the attachment;
processing the picture attachment using an optical character recognition method to generate structured data.
6. The human-computer collaborative hybrid checklist decision method of claim 4, wherein fusing the form data and the attachment image into information to be audited comprises:
calling form data in a JSON format from the first database;
calling the structured data in JSON format from the second database;
and carrying out character string splicing on the form data in the JSON format and the structured data to obtain the information to be audited.
7. The human-computer collaborative hybrid examination-order decision method of claim 1 or 6, wherein when the audit result contains error reporting information, the to-be-approved financial document is marked as rejected audit, and the audit result, and all the corresponding approved audit rule lists, all non-approved audit rule lists and reasons, all checked risk early warning rule lists and risk early warning prompts are sent to the document examination-approval system.
8. The human-computer collaborative hybrid examination and decision method of claim 7, wherein when the audit result includes manual processing information, the financial document to be audited is marked as manual audit, and the audit result, all the approved audit rule lists corresponding to the audit result, all the verification rule lists corresponding to the approval result, all the reasons for triggering manual review, all the checked risk early warning rule lists, and the risk early warning prompt are sent to the document approval system.
9. A man-machine cooperative hybrid examination decision making system is applied to an autonomous robot auditing system, and the autonomous robot auditing system is in data connection with a document approval system, and comprises:
the receiving module is used for receiving a document examination request of the document examination and approval system;
the acquisition module is used for acquiring and storing form data of the financial document to be approved from the document approval system; acquiring and storing the image attachments of the to-be-approved financial documents;
the fusion module is used for fusing the form data and the image attachment into information to be audited;
the auditing module is used for calling a rule engine to audit the information to be audited to obtain an auditing result;
and the sending module is used for marking the financial document to be approved as approved when the audit result does not contain error reporting information and manual processing information, and sending the audit result, all the approved audit rule detail lists corresponding to the audit result, all the checked risk early warning rule lists and the risk early warning prompt to the document approval system.
10. A man-machine cooperative hybrid examination and decision making system is applied to a robot examination and decision making system, the robot examination and decision making system is in data connection with a document examination and approval system, the robot examination and approval system comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, and the processor realizes the man-machine cooperative hybrid examination and decision making method according to any one of claims 1-8 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111459250.8A CN114358707A (en) | 2021-12-02 | 2021-12-02 | Man-machine cooperative hybrid examination order decision method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111459250.8A CN114358707A (en) | 2021-12-02 | 2021-12-02 | Man-machine cooperative hybrid examination order decision method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114358707A true CN114358707A (en) | 2022-04-15 |
Family
ID=81097188
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111459250.8A Pending CN114358707A (en) | 2021-12-02 | 2021-12-02 | Man-machine cooperative hybrid examination order decision method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114358707A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114898389A (en) * | 2022-06-11 | 2022-08-12 | 国网安徽省电力有限公司 | Intelligent auditing method and system for accounting document abstract |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109410031A (en) * | 2018-09-27 | 2019-03-01 | 苏宁消费金融有限公司 | The consumptive credit intelligence measures and procedures for the examination and approval and system |
| CN110599317A (en) * | 2019-08-26 | 2019-12-20 | 湖南大唐先一科技有限公司 | Account reporting and auditing automation method based on rule engine and OCR (optical character recognition) |
| CN111198748A (en) * | 2019-12-31 | 2020-05-26 | 航天信息股份有限公司企业服务分公司 | Automatic approval method for business document process, electronic equipment, storage medium and system |
| CN111506444A (en) * | 2020-04-20 | 2020-08-07 | 北京易点淘网络技术有限公司 | Form approval method and device, storage medium and electronic equipment |
| CN112734387A (en) * | 2021-01-14 | 2021-04-30 | 北京世纪互联宽带数据中心有限公司 | Document approval method and device, electronic equipment and storage medium |
| CN112926941A (en) * | 2021-03-04 | 2021-06-08 | 远光软件股份有限公司 | Management method and device for financial auditing rules, storage medium and server |
-
2021
- 2021-12-02 CN CN202111459250.8A patent/CN114358707A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109410031A (en) * | 2018-09-27 | 2019-03-01 | 苏宁消费金融有限公司 | The consumptive credit intelligence measures and procedures for the examination and approval and system |
| CN110599317A (en) * | 2019-08-26 | 2019-12-20 | 湖南大唐先一科技有限公司 | Account reporting and auditing automation method based on rule engine and OCR (optical character recognition) |
| CN111198748A (en) * | 2019-12-31 | 2020-05-26 | 航天信息股份有限公司企业服务分公司 | Automatic approval method for business document process, electronic equipment, storage medium and system |
| CN111506444A (en) * | 2020-04-20 | 2020-08-07 | 北京易点淘网络技术有限公司 | Form approval method and device, storage medium and electronic equipment |
| CN112734387A (en) * | 2021-01-14 | 2021-04-30 | 北京世纪互联宽带数据中心有限公司 | Document approval method and device, electronic equipment and storage medium |
| CN112926941A (en) * | 2021-03-04 | 2021-06-08 | 远光软件股份有限公司 | Management method and device for financial auditing rules, storage medium and server |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114898389A (en) * | 2022-06-11 | 2022-08-12 | 国网安徽省电力有限公司 | Intelligent auditing method and system for accounting document abstract |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7840455B1 (en) | System and method of detecting fraudulent or erroneous invoices | |
| CN109544388B (en) | Automatic claims settlement method, device, electronic equipment and storage medium | |
| US7035821B1 (en) | Methods and apparatus for processing cash advance requests | |
| CN111079397B (en) | Task file generation method and device based on image recognition | |
| US20130325706A1 (en) | System, method, apparatus, and computer program product for improved payment processing | |
| CN110188336B (en) | Method and device for generating reimbursement bill based on OA application form | |
| CN115526605A (en) | Enterprise internal control management-based approval method and system | |
| CN112348326A (en) | Bank business processing method and system | |
| CN116029843A (en) | Financial reimbursement method and device and electronic equipment | |
| CN113326684B (en) | Contract signing management method, system and device | |
| CN113902573A (en) | Method and device for processing claim settlement data, storage medium and terminal | |
| CN113469637B (en) | Patch issuing method and system | |
| CN114358707A (en) | Man-machine cooperative hybrid examination order decision method and system | |
| CN113938481A (en) | Receipt processing method, processing device, electronic equipment and readable storage medium | |
| CN115439264A (en) | Insurance business customization method, device and system | |
| CN112598038A (en) | Method and system for centralized drawing and processing of bills in same city | |
| CN109829769B (en) | Electronic invoice duplicate checking method and system | |
| CN111353833A (en) | Method and equipment for generating report | |
| CN116302974A (en) | Data testing method, device, apparatus, medium and program product | |
| CN115660607A (en) | Method and device for automatically generating approval chain and computer storage medium | |
| KR102416998B1 (en) | Appatus for automatically collecting and classification tax related documents and method thereof | |
| CN115222501A (en) | Financial accounting method, device, storage medium and accounting server | |
| CN114511318A (en) | Account accounting method and device and electronic equipment | |
| CN113537964A (en) | Application form processing method, device, storage medium and device | |
| CN113792570A (en) | Claims data processing method and device, electronic equipment and readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |