CN117408827A - Intelligent management method and system for financial reimbursement of enterprises - Google Patents
Intelligent management method and system for financial reimbursement of enterprises Download PDFInfo
- Publication number
- CN117408827A CN117408827A CN202311723981.8A CN202311723981A CN117408827A CN 117408827 A CN117408827 A CN 117408827A CN 202311723981 A CN202311723981 A CN 202311723981A CN 117408827 A CN117408827 A CN 117408827A
- Authority
- CN
- China
- Prior art keywords
- reimbursement
- certificate
- value
- amount
- risk
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 60
- 238000011156 evaluation Methods 0.000 claims abstract description 77
- 238000012502 risk assessment Methods 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000005070 sampling Methods 0.000 claims abstract description 10
- 239000000284 extract Substances 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 33
- 238000005516 engineering process Methods 0.000 claims description 24
- 230000008569 process Effects 0.000 claims description 23
- 238000007689 inspection Methods 0.000 claims description 20
- 238000007781 pre-processing Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 13
- 238000007405 data analysis Methods 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 11
- 238000013473 artificial intelligence Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 8
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000003909 pattern recognition Methods 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 3
- 238000012550 audit Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Technology Law (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent management method and system for financial reimbursement of enterprises, and relates to the technical field of financial reimbursement management, wherein the management system comprises a data acquisition module, a data archiving and processing module, a reimbursement grading module, a credential evaluation module and a management direction module, wherein the data acquisition module converts reimbursement credentials into an electronic format and automatically extracts key information; the technical key points are as follows: according to the priority order obtained by the reimbursement classification module, the reimbursement voucher risk assessment value Rarv obtained by comprehensively considering the sum difference factor and the reimbursement repetition factor is taken as a basis, the risk degree of the corresponding reimbursement voucher can be obtained efficiently and accurately after being compared with a preset assessment threshold value group, meanwhile, a specific checking interval number preset value Ygz can be obtained according to the reimbursement voucher risk assessment value Rarv, and the checking frequency can be set according to specific data when the periodic sampling checking operation is carried out subsequently, so that the rationality of management work is ensured.
Description
Technical Field
The invention relates to the technical field of financial reimbursement management, in particular to an intelligent management method and system for financial reimbursement of enterprises.
Background
The financial reimbursement management technology is a technical means for efficiently and automatically managing and controlling reimbursement flows in an organization by applying an information technology and a software system, and specifically comprises a reimbursement application system, workflow management and payment auditing; reimbursement application system: by setting up a reimbursement application system, staff can submit reimbursement applications online, including filling in related expense details, attaching related voucher pictures and the like, and appointing an approver; workflow management: through establishing an automatic workflow management system, the reimbursement application is automatically circulated to corresponding approvers for approval according to set rules and authorities; payment auditing: the payment auditing function in the financial reimbursement management technology can audit reimbursement applications, including amount checking, compliance auditing and the like.
The technical scheme pointed out in the patent of the prior application publication number CN108765123A, publication date 2018.11.06 and name of the information intelligent management system and method for logistics finance, statistics and reimbursement comprises a user registration module, a logistics bill module, a settlement standard module, a expense reimbursement module and a statistics report module; the user registration module is used for registering enterprises and individuals to be online users, or distributing accounts to individuals after registering users by the enterprises and carrying out service association; the logistics bill module is used for delegation and acceptance delegation of logistics business among enterprise users, and the individual users execute the logistics business which is issued or authorized by the enterprise users; the settlement standard module is used for calculating corresponding receipt and payment according to the settlement standard; the expense reimbursement module is used for reimbursement and approval between the individual user and the enterprise user; and the statistics report module is used for automatically and intelligently generating and outputting financial reports and business reports, and although the financial and business conditions are clear, the statistics report module cannot judge the authenticity and rationality of the reimbursement certificates, and if the reimbursement certificates are unreasonable, the reimbursement management process is greatly influenced.
For the above-mentioned patent and prior art, in the financial reimbursement management process in the enterprise, hundreds or more reimbursement certificates are received every day, and usually, the reimbursement certificates of the part are true, so that the authenticity of the reimbursement certificates is not required to be judged, but for some unreasonable reimbursement certificates, for example: the corresponding amount on the repeated reimbursement and reimbursement certificates exceeds the maximum reimbursement amount of the corresponding type, and the reimbursement and reimbursement certificates can be obtained through regular checking, however, the frequency of the regular checking is judged and adjusted manually, so that the frequency establishment of the regular checking has certain inconveniences.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an enterprise financial reimbursement intelligent management method and system, which are based on reimbursement voucher risk evaluation values Rarv obtained by comprehensively considering sum difference factors and reimbursement repetition number factors according to the priority order obtained by a reimbursement grading module, and can be used for efficiently and accurately obtaining the risk degree of corresponding reimbursement vouchers after being compared with a preset evaluation threshold group, meanwhile, a specific checking interval number preset value Ygz can be obtained according to the reimbursement voucher risk evaluation values Rarv, and the checking frequency can be set according to specific data when the follow-up regular sampling checking operation is carried out, so that the rationality of management work is ensured, and the problems in the background art are solved.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
an intelligent management system for financial reimbursement of an enterprise, comprising:
the data acquisition module converts the reimbursement certificate into an electronic format, automatically extracts key information including expiration date, reimbursement amount and invoice number, and is integrated with the financial system to acquire reimbursement information related to staff, including the affiliated departments, positions and reimbursement limits;
the data archiving processing module classifies and archives the key information in the acquired reimbursement certificates;
the reimbursement grading module is used for extracting the number of days from the date of expiration and reimbursement amount as grading parameters, constructing a data analysis model and generating a financial reimbursement grading index Frci which is used for reflecting the priority of a plurality of reimbursement certificates;
the certificate evaluation module comprises an authenticity verification unit and a risk evaluation unit, wherein the authenticity verification unit verifies authenticity of the reimbursement certificate by using an artificial intelligence technology, if the reimbursement certificate is true, the risk evaluation unit is continuously operated, a rule engine is built in the risk evaluation unit, the amount ranges corresponding to different reimbursement expense types are calibrated, evaluation parameters are obtained, and a data analysis model is built for the second time to generate a reimbursement certificate risk evaluation value Rarv;
the management direction module compares the reimbursement certificate risk evaluation value Rarv with a preset evaluation threshold value group, acquires the risk degree of the corresponding reimbursement certificate and the corresponding early warning signal according to the comparison result, calculates and generates an inspection interval number predicted value Ygz according to the reimbursement certificate risk evaluation value Rarv of the same reimbursement certificate, and carries out sampling inspection management on reimbursement certificates at different risk degrees according to the corresponding inspection interval number predicted value Ygz according to the order of priority from large to small.
Further, the specific process of extracting the key information is as follows: the method comprises the steps of obtaining an image, scanning a paper version of a reimbursement certificate by using scanning equipment, and converting the paper version into a digital image; preprocessing an image, namely preprocessing the acquired image, including image denoising, image enhancement and adjustment of brightness and contrast of the image; OCR recognition, which is to use OCR technology to recognize the preprocessed image and convert the characters and the numbers into computer-readable characters; and analyzing the text data, and extracting key information by any algorithm of regular expression-based, keyword matching and pattern recognition.
Further, the process of generating the financial reimbursement ranking index Frci is as follows:
preprocessing rating parameters, calculating the number of days Dt of the phase difference between the current day and the expiration date, and carrying out dimensionless processing on the number of days Dt and the reimbursement amount Rr in the corresponding reimbursement certificate;
calculating a financial reimbursement grading index Frci, and generating the financial reimbursement grading index Frci according to the grading parameter, wherein the formula is as follows:
；
in the method, in the process of the invention,respectively when (when)A preset proportionality coefficient of the number of days Dt and the reimbursement amount Rr, which differ between the date and the expiration date, and +.>0，/>Is a constant correction coefficient.
Further, the artificial intelligence technology utilized in the authentication unit includes an image recognition algorithm, a machine learning technology and a deep learning technology, when the reimbursement certificate is authenticated, if the reimbursement certificate is false, the data related to the reimbursement certificate is deleted, including the key information and reimbursement information extracted by the data acquisition module, and an alarm signal is sent out.
Further, the evaluation parameters in the risk evaluation unit include a difference between the reimbursement amount and the maximum amount of the corresponding type, and a frequency of reimbursement of the same reimbursement fee type in a predetermined period, and a difference between the reimbursement amount of the corresponding employee and the maximum reimbursement amount corresponding to the job position.
Further, the process of generating the reimbursement credential risk assessment value Rarv is as follows:
the evaluation parameters are calculated, and the formula according to the difference value between the reimbursement amount and the maximum amount of the corresponding type is as follows: difference = corresponding type maximum amount-reimbursement amount; the formula according to which the same reimbursement fee type reimburses for the frequency of reimbursement in a predetermined period is: frequency = number of times of reimbursement fees of the same type reimbursement in a predetermined period/predetermined period; the formula according to which the corresponding employee reimbursement amount and the corresponding reimbursement maximum limit of the job position are based is as follows: difference = maximum reimbursement value corresponding to the position where the corresponding employee is located-maximum reimbursement amount corresponding to the employee, wherein the maximum reimbursement value is the maximum value in the amount range corresponding to the reimbursement cost type, and the corresponding type is the maximum amountCorresponding to the maximum reimbursement limit value corresponding to the position of the employee;
preprocessing evaluation parameters, namely, preprocessing the difference value between the reimbursement amount and the maximum amount of the corresponding typeFrequency of reimbursement in a predetermined period for the same reimbursement fee type>Difference value of maximum reimbursement amount corresponding to employee reimbursement amount and position corresponding to employee reimbursement amount>Performing dimensionless treatment;
calculating a reimbursement evidence risk assessment value Rarv, and generating a formula according to the reimbursement evidence risk assessment value Rarv as follows:
；
in the method, in the process of the invention,the difference between the reimbursement amount and the maximum amount of the corresponding type is +.>Frequency of reimbursement in a predetermined period for the same reimbursement fee type>Difference value of maximum reimbursement amount corresponding to employee reimbursement amount and position corresponding to employee reimbursement amount>Is a preset proportionality coefficient of>Int is a rounding function, ++>Is a constant correction coefficient.
Further, the check interval number predicted value Ygz is calculated and generated in the management direction module according to the following formula:
；
where, int is a rounding function,is a constant correction coefficient.
Further, the process of obtaining the risk degree of the corresponding reimbursement certificate and the corresponding early warning signal is as follows: comparing the reimbursement evidence risk assessment value Rarv with a preset assessment threshold set, wherein the assessment threshold set comprises a first assessment thresholdAnd a second evaluation threshold->And a first evaluation threshold +.>Two evaluation threshold->If yes, the reimbursement evidence risk assessment value Rarv is less than a first assessment threshold +.>The corresponding reimbursement certificate is indicated to be low in risk, and a primary early warning signal is sent; if it is the first evaluation threshold->The reimbursement evidence risk assessment value Rarv is less than or equal to a second assessment threshold value +.>The corresponding reimbursement certificate is indicated as the middle risk, and a secondary early warning signal is sent out; if it is the second evaluation threshold->And if the risk assessment value Rarv of the reimbursement certificate is less than the risk assessment value Rarv of the reimbursement certificate, the corresponding reimbursement certificate is high risk, and a three-level early warning signal is sent.
An intelligent management method for financial reimbursement of enterprises comprises the following steps:
step one, converting a reimbursement certificate into an electronic format, automatically extracting key information including expiration date, reimbursement amount and invoice number, integrating with a financial system, and acquiring reimbursement information related to staff including a belonging department, a job position and reimbursement limit;
classifying and archiving the key information in the acquired reimbursement certificates;
step three, extracting the number of days and reimbursement amount of the day from the expiration date as rating parameters, building a data analysis model, and generating a financial reimbursement grading index Frci for reflecting the priority of a plurality of reimbursement certificates;
step four, verifying authenticity of the reimbursement evidence by utilizing an artificial intelligence technology, if the reimbursement evidence is true, building a rule engine, calibrating the amount ranges corresponding to different reimbursement expense types, acquiring evaluation parameters, and secondarily building a data analysis model to generate a reimbursement evidence risk evaluation value Rarv; if the reimbursement certificate is false, deleting the data related to the reimbursement certificate, including the key information and reimbursement information of the first step, and sending out an alarm signal;
fifthly, comparing the reimbursement certificate risk evaluation value Rarv with a preset evaluation threshold set, acquiring a risk degree and a corresponding early warning signal of a corresponding reimbursement certificate according to a comparison result, calculating and generating an inspection interval number preset value Ygz according to the reimbursement certificate risk evaluation value Rarv of the same reimbursement certificate, and carrying out sampling inspection management on reimbursement certificates at different risk degrees according to the corresponding inspection interval number preset value Ygz according to the order of priority from large to small.
The invention provides an intelligent management method and system for financial reimbursement of enterprises, which have the following beneficial effects:
1. by designing the reimbursement analysis module, the expiration date and reimbursement amount of different reimbursement vouchers are comprehensively considered to obtain the financial reimbursement grading index Frci, and the financial reimbursement grading index Frci with specific values is sequenced from large to small, so that the emergency degree of the corresponding reimbursement vouchers reflected according to the financial reimbursement grading index Frci when a large number of reimbursement vouchers are encountered can be accurately and effectively known, and automatic reimbursement management operation according to sequencing is realized;
2. the reimbursement certificate risk assessment value Rarv obtained by comprehensively considering the sum difference factor and reimbursement repetition factor is taken as a basis according to the priority sequence obtained by the reimbursement grading module, and is compared with a preset assessment threshold group to obtain the risk degree of the corresponding reimbursement certificate efficiently and accurately, meanwhile, a specific checking interval number pre-evaluation value Ygz can be obtained according to the reimbursement certificate risk assessment value Rarv, so that the follow-up regular sampling checking operation can be conveniently completed according to the preset checking interval number pre-evaluation value Ygz, the checking frequency is set according to specific data, and the rationality of management work is ensured.
Drawings
FIG. 1 is a schematic diagram of a modular system for intelligent management of financial reimbursement for an enterprise in accordance with the present invention;
FIG. 2 is an overall flow chart of an intelligent management method for financial reimbursement of enterprises in the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1: referring to fig. 1, the present embodiment provides an intelligent management system for financial reimbursement of enterprises, which includes a data acquisition module, a data archiving and processing module, a reimbursement grading module, a credential evaluation module and a management direction module, and is applied to enterprises, where the reimbursement credentials for coping cover the whole unit, and generally, hundreds of reimbursement credentials exist for the units of the grade every day, so that the management system needs to be equipped to realize the determination of priority and risk evaluation of financial reimbursement of enterprises, so as to facilitate the subsequent management work;
the data acquisition module converts the reimbursement certificate into an electronic format through scanning or photographing, automatically extracts key information including expiration date, reimbursement amount and invoice number, is integrated with the financial system, and automatically acquires reimbursement information related to staff including the affiliated department, position and reimbursement limit;
the specific process for extracting the key information comprises the following steps:
the method comprises the steps of obtaining an image, scanning or photographing a paper version of a reimbursement certificate by using scanning equipment, and converting the paper version of the reimbursement certificate into a digital image, wherein the scanning equipment is a high-definition camera;
preprocessing an image, namely preprocessing the acquired image, including image denoising, image enhancement and adjustment of brightness and contrast of the image so as to improve the subsequent recognition accuracy;
OCR recognition, which is to use OCR technology to recognize the preprocessed image, and to convert the characters and the numbers into computer-readable characters, wherein the OCR technology can recognize the characters in the image and convert the characters into text data;
text analysis, further analyzing the identified text data, and extracting key information, namely expiration date, reimbursement amount and invoice number, through any algorithm based on regular expression, keyword matching and pattern recognition;
the financial system herein is integrated with the management system of the present application, which is a conventional and commercially common configuration system, and is now briefly described as being a software system within an enterprise for managing and processing financial related data and processes, which is typically comprised of a plurality of modules, including accounting, financial reporting, budget management, cost control, and reimbursement management; the primary functions of the financial system include, accounting: recording and processing financial transactions of the business, including revenue, expenditure, assets, and liabilities, to generate accurate financial statements; budget management: establishing and managing a budget plan of an enterprise, and comparing and analyzing budget and actual data; financial reporting: generating relevant financial statements, such as liability statement, profit statement, and cash flow statement, to provide internal and external stakeholders with reference; cost control: monitoring and managing the costs of the enterprise, including budget control, cost allocation, and cost auditing, to ensure the operational benefits of the enterprise; and (5) reimbursement management: managing and approving reimbursement applications of staff, including auditing reimbursement certificates, checking fees and tracking reimbursement flows;
integration of financial systems with other departments and systems may enable sharing and automated processing of data, such as: the system is integrated with a human resource system, so that employee information can be obtained; the system is integrated with a purchasing system, and related purchasing order and invoice information can be automatically acquired; and the system is integrated with a banking system, so that fund checking can be realized.
The data archiving processing module classifies and archives the key information in the collected reimbursement certificates, the classification is to distinguish according to the category of the key information, namely, the expiration date, reimbursement amount and invoice number in the key information are classified, and the archiving is to archive the classified information, so that the follow-up audit and inquiry are convenient.
The reimbursement classification module is used for extracting the number of days and reimbursement amount from the date of day to the expiration date as rating parameters, constructing a data analysis model, generating a financial reimbursement classification index Frci which is used for reflecting the priority of a plurality of reimbursement certificates, and the higher the financial reimbursement classification index Frci is, the higher the corresponding reimbursement certificate priority is;
wherein, the process of generating the financial reimbursement rating index Frci is as follows:
preprocessing the rating parameter, calculating the number of days Dt of the phase difference between the current day and the expiration date, and carrying out dimensionless processing on the number of days Dt and the reimbursement amount Rr in the corresponding reimbursement certificate so as to remove units of the rating parameter;
calculating a financial reimbursement grading index Frci, and generating the financial reimbursement grading index Frci according to the grading parameter, wherein the formula is as follows:
；
in the method, in the process of the invention,preset proportionality coefficients of the number of days Dt and the reimbursement amount Rr, respectively, which differ between the current day and the expiration date, and +.>，/>Is a constant correction factor whose specific value can be set by user adjustment or generated by fitting an analytical function, in practice,/->I.e. +.>Always greater than +.>In the course of the evaluation of the priority, the number of days Dt is limited in comparison with the reimbursement amount Rr, and if the expiration date is exceeded, a subsequent default or late fee is generated, <' >>The specific value range for the constant correction coefficient is between 1 and 2.
Specifically, by designing the reimbursement analysis module, the expiration date and reimbursement amount of different reimbursement certificates are comprehensively considered to obtain the financial reimbursement grading index Frci, and the financial reimbursement grading index Frci with specific values is sequenced from large to small, so that when more reimbursement certificates are encountered, the emergency degree of the corresponding reimbursement certificates reflected according to the financial reimbursement grading index Frci can be accurately and effectively known, and the automatic reimbursement management operation according to the sequencing is realized.
The certificate evaluation module comprises an authenticity verification unit and a risk evaluation unit;
the authentication verification unit performs authentication verification on the reimbursement certificate by using an artificial intelligence technology, detects whether the reimbursement certificate is tampered or forged, if the reimbursement certificate is true, continues the subsequent steps, if the reimbursement certificate is false, deletes data related to the reimbursement certificate, including key information and reimbursement information extracted by the data acquisition module, and sends out a warning signal, and the unit is designed only for preventing the existence of the forged reimbursement certificate, but the forged reimbursement certificate is rarely or never generated in the actual application process, so the unit is designed behind the data acquisition module and the data archiving processing module;
the artificial intelligence technology comprises an image recognition algorithm, a machine learning technology and a deep learning technology, and the specific process of verifying the authenticity of the reimbursement evidence comprises the following steps: firstly, extracting an image of a reimbursement certificate by using an image processing technology, and processing and analyzing the extracted image of the reimbursement certificate by means of an artificial intelligent image recognition algorithm, namely, extracting and comparing features of the image to detect whether the image is tampered, forged and reused; for example, analyzing pixel distribution, image texture and edge information of the image to identify whether an excessive processing trace exists; meanwhile, combining machine learning and deep learning technologies, distinguishing a real reimbursement evidence image from a forged reimbursement evidence image through training a model, and establishing a data set comprising the real reimbursement evidence image and the known forged reimbursement evidence image, so that the model learns the true and false distinction, thereby improving the accuracy of true and false verification;
for example, if an image of a reimbursement document is tampered, assuming that the amount of money on the original reimbursement document is 100 yuan, and the tampered amount of money is 200 yuan, by means of an artificial intelligence image recognition algorithm, pixel change and color change characteristics of the image can be compared, and a tampered trace of the image can be detected, so that the counterfeit reimbursement document is recognized.
Setting up a rule engine in a risk assessment unit, calibrating the sum ranges corresponding to different reimbursement expense types, and obtaining assessment parameters, wherein the assessment parameters comprise the difference value between reimbursement amount and the maximum sum of the corresponding types, the reimbursement frequency of the same reimbursement expense type in a preset period, the reimbursement amount of the corresponding staff and the difference value of the reimbursement maximum sum corresponding to the positions of the corresponding staff, establishing a data analysis model for the second time, and generating a reimbursement evidence risk assessment value Rarv according to the assessment parameters;
the process of generating the reimbursement evidence risk assessment value Rarv is as follows:
the evaluation parameters are calculated, and the formula according to the difference value between the reimbursement amount and the maximum amount of the corresponding type is as follows: difference = corresponding type maximum amount-reimbursement amount; the formula according to which the same reimbursement fee type reimburses for the frequency of reimbursement in a predetermined period is: frequency = number of times of reimbursement fees of the same type reimbursement in a predetermined period/predetermined period; the formula according to which the corresponding employee reimbursement amount and the corresponding reimbursement maximum limit of the job position are based is as follows: difference = maximum reimbursement value corresponding to the position where the corresponding employee is located-maximum reimbursement amount corresponding to the employee, wherein the maximum reimbursement value is the maximum value in the amount range corresponding to the reimbursement cost type, and the corresponding type is the maximum amountCorresponding to the maximum reimbursement limit value corresponding to the position of the employee;
preprocessing evaluation parameters, namely, preprocessing the difference value between the reimbursement amount and the maximum amount of the corresponding typeFrequency of reimbursement in a predetermined period for the same reimbursement fee type>Difference value of maximum reimbursement amount corresponding to employee reimbursement amount and position corresponding to employee reimbursement amount>Performing dimensionless treatment, taking a week from a preset period T, and setting according to actual requirements;
calculating a reimbursement evidence risk assessment value Rarv, and generating a formula according to the reimbursement evidence risk assessment value Rarv as follows:
；
in the method, in the process of the invention,respectively the difference between the reimbursement amount and the maximum amount of the corresponding typeValue->Frequency of reimbursement in a predetermined period for the same reimbursement fee type>Difference value of maximum reimbursement amount corresponding to employee reimbursement amount and position corresponding to employee reimbursement amount>Is a preset proportionality coefficient of>Int is a rounding function, which facilitates the subsequent comparison,/->Is a constant correction factor whose specific value can be set by user adjustment or generated by fitting an analytical function,/->The value range of (2) is 1 to 3;
it should be noted that: the difference in the above formulaAnd the difference value->The accumulated value of (2) is denominator, so that no matter what is the difference +.>Or a difference value->The smaller the corresponding reimbursement evidence risk assessment value Rarv is, the higher the risk representing the corresponding type of reimbursement evidence is, and the frequency +.>Is molecular, so the frequency->The larger the corresponding reimbursement evidence risk evaluation value Rarv is, the higher the risk of the reimbursement evidence of the corresponding type is, each evaluation parameter is an influence factor, the instruction function is provided for acquiring the reimbursement evidence risk evaluation value Rarv, the reimbursement evidence risk evaluation value Rarv is only one piece of data for evaluating the reimbursement evidence risk, and the instruction function is provided for the subsequent management;
a person skilled in the art collects a plurality of groups of sample data and sets a corresponding preset scaling factor for each group of sample data; substituting the preset proportionality coefficient, which can be the preset proportionality coefficient and the acquired sample data, into a formula, forming a ternary once equation set by any three formulas, screening the calculated coefficient, taking an average value, and obtaining a value; the magnitude of the coefficient is a specific numerical value obtained by quantizing each parameter, so that the subsequent comparison is convenient, the magnitude of the coefficient depends on the number of sample data and the corresponding preset proportional coefficient preliminarily set by a person skilled in the art for each group of sample data, that is, the coefficient is preset according to the actual practice, so long as the proportional relation between the parameter and the quantized numerical value is not influenced, and the above description is also adopted for the preset proportional coefficient and the constant correction coefficient described in other formulas.
The management direction module compares the reimbursement certificate risk evaluation value Rarv with a preset evaluation threshold group, acquires a risk early warning prompt signal corresponding to the reimbursement certificate according to a comparison result, calculates and generates an inspection interval number pre-estimated value Ygz according to the reimbursement certificate risk evaluation value Rarv of the same reimbursement certificate, and the following formula is adopted:
；
where, int is a rounding function,is a constant correction factor whose specific value can be set by user adjustment or generated by fitting an analytical function,/->The value range of (2) is 2 to 3; when the reimbursement risk evaluation value is higher, the inspection interval number is smaller, namely the risk is higher, and the inspection interval time is smaller;
the process for acquiring the risk degree of the corresponding reimbursement certificate and the corresponding early warning signal comprises the following steps:
comparing the reimbursement evidence risk assessment value Rarv with a preset assessment threshold set, wherein the assessment threshold set comprises a first assessment thresholdAnd a second evaluation threshold->And a first evaluation threshold +.>Two evaluation threshold->If yes, the reimbursement evidence risk assessment value Rarv is less than a first assessment threshold +.>If the rationality of the corresponding reimbursement certificate is low, a first-level early warning signal is sent out, and if the first evaluation threshold is +.>The reimbursement evidence risk assessment value Rarv is less than or equal to a second assessment threshold value +.>The corresponding reimbursement certificate is indicated as being at risk in the rationality, a second-level early warning signal is sent out, and if the second evaluation threshold value is +.>If the risk assessment value Rarv of the reimbursement certificates is less than the risk assessment value Rarv of the reimbursement certificates, the reasonability of the corresponding reimbursement certificates is high risk, and a three-level early warning signal is sent;
the different degrees of risk are alerts and hints for abnormal reimbursement vouchers, such as high reimbursement and frequent reimbursement;
and sampling inspection management is carried out on the reimbursement certificates at different risk degrees according to the order of the priority from large to small and according to the corresponding inspection interval number predicted value Ygz so as to finish efficient and accurate management of the reimbursement certificates.
Specifically, the reimbursement certificate risk assessment value Rarv obtained by comprehensively considering the sum difference factor and reimbursement repetition factor is taken as a basis according to the priority sequence obtained by the reimbursement grading module, and compared with a preset assessment threshold group, the risk degree of the corresponding reimbursement certificate can be obtained efficiently and accurately, meanwhile, a specific checking interval number preset value Ygz can be obtained according to the reimbursement certificate risk assessment value Rarv, the follow-up regular sampling checking operation is conveniently completed according to the preset checking interval number preset value Ygz, and the checking frequency is set according to specific data, so that the rationality of management work is ensured.
Example 2: referring to fig. 2, based on embodiment 1, this embodiment further provides an intelligent management method for financial reimbursement of enterprises, which includes the following specific steps:
step one, converting a reimbursement certificate into an electronic format, automatically extracting key information including expiration date, reimbursement amount and invoice number, integrating with a financial system, and acquiring reimbursement information related to staff including a belonging department, a job position and reimbursement limit;
classifying and archiving the key information in the acquired reimbursement certificates;
step three, extracting the number of days and reimbursement amount of the day from the expiration date as rating parameters, building a data analysis model, and generating a financial reimbursement grading index Frci for reflecting the priority of a plurality of reimbursement certificates;
step four, verifying authenticity of the reimbursement evidence by utilizing an artificial intelligence technology, if the reimbursement evidence is true, building a rule engine, calibrating the amount ranges corresponding to different reimbursement expense types, acquiring evaluation parameters, and secondarily building a data analysis model to generate a reimbursement evidence risk evaluation value Rarv; if the reimbursement certificate is false, deleting the data related to the reimbursement certificate, including the key information and reimbursement information of the first step, and sending out an alarm signal;
fifthly, comparing the reimbursement certificate risk evaluation value Rarv with a preset evaluation threshold set, acquiring a risk degree and a corresponding early warning signal of a corresponding reimbursement certificate according to a comparison result, calculating and generating an inspection interval number preset value Ygz according to the reimbursement certificate risk evaluation value Rarv of the same reimbursement certificate, and carrying out sampling inspection management on reimbursement certificates at different risk degrees according to the corresponding inspection interval number preset value Ygz according to the order of priority from large to small.
In the application, the related formulas are all the numerical calculation after dimensionality removal, and the formulas are one formulas for obtaining the latest real situation by software simulation through collecting a large amount of data, and the formulas are set by a person skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art will appreciate that the various illustrative elements 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 solution.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application.
Claims (9)
1. An intelligent management system for financial reimbursement of an enterprise, comprising:
the data acquisition module converts the reimbursement certificate into an electronic format, automatically extracts key information including expiration date, reimbursement amount and invoice number, and is integrated with the financial system to acquire reimbursement information related to staff, including the affiliated departments, positions and reimbursement limits;
the data archiving processing module classifies and archives the key information in the acquired reimbursement certificates;
the reimbursement grading module is used for extracting the number of days from the date of expiration and reimbursement amount as grading parameters, constructing a data analysis model and generating a financial reimbursement grading index Frci which is used for reflecting the priority of a plurality of reimbursement certificates;
the certificate evaluation module comprises an authenticity verification unit and a risk evaluation unit, wherein the authenticity verification unit verifies authenticity of the reimbursement certificate by using an artificial intelligence technology, if the reimbursement certificate is true, the risk evaluation unit is continuously operated, a rule engine is built in the risk evaluation unit, the amount ranges corresponding to different reimbursement expense types are calibrated, evaluation parameters are obtained, and a data analysis model is built for the second time to generate a reimbursement certificate risk evaluation value Rarv;
the management direction module compares the reimbursement certificate risk evaluation value Rarv with a preset evaluation threshold value group, acquires the risk degree of the corresponding reimbursement certificate and the corresponding early warning signal according to the comparison result, calculates and generates an inspection interval number predicted value Ygz according to the reimbursement certificate risk evaluation value Rarv of the same reimbursement certificate, and carries out sampling inspection management on reimbursement certificates at different risk degrees according to the corresponding inspection interval number predicted value Ygz according to the order of priority from large to small.
2. An intelligent management system for financial reimbursement of an enterprise as set forth in claim 1, wherein: the specific process for extracting the key information comprises the following steps: scanning the paper version of the reimbursement certificate by using a scanning device, and converting the paper version of the reimbursement certificate into a digital image; preprocessing the acquired image, including image denoising, image enhancement and image brightness and contrast adjustment; recognizing the preprocessed image by using OCR technology, and converting the characters and the numbers into computer-readable characters; and analyzing the identified text data, and extracting key information through any algorithm based on regular expression, keyword matching and pattern recognition.
3. An intelligent management system for financial reimbursement of enterprises as set forth in claim 2, wherein: the process of generating the financial reimbursement rating index Frci is as follows:
preprocessing rating parameters, calculating the number of days Dt of the phase difference between the current day and the expiration date, and carrying out dimensionless processing on the number of days Dt and the reimbursement amount Rr in the corresponding reimbursement certificate;
calculating a financial reimbursement grading index Frci, and generating the financial reimbursement grading index Frci according to the grading parameter, wherein the formula is as follows:
；
in the method, in the process of the invention,preset proportionality coefficients of the number of days Dt and the reimbursement amount Rr, respectively, which differ between the current day and the expiration date, and +.>0，/>Is a constant correction coefficient.
4. An intelligent management system for financial reimbursement of an enterprise in accordance with claim 3, wherein: the artificial intelligence technology utilized in the authentication unit comprises an image recognition algorithm, a machine learning technology and a deep learning technology, and when the reimbursement certificate is authenticated, if the reimbursement certificate is fake, the data related to the reimbursement certificate is deleted, and the data comprises key information and reimbursement information extracted by the data acquisition module and sends out an alarm signal.
5. The intelligent management system for financial reimbursement of an enterprise according to claim 4, wherein: the evaluation parameters in the risk evaluation unit comprise the difference value between the reimbursement amount and the maximum amount of the corresponding type, the reimbursement frequency of the same reimbursement cost type in a preset period, and the difference value of the reimbursement maximum amount of the corresponding employee reimbursement amount and the corresponding position.
6. The intelligent management system for financial reimbursement of an enterprise according to claim 5, wherein: the process of generating the reimbursement credential risk assessment value Rarv is as follows:
the evaluation parameters are calculated, and the formula according to the difference value between the reimbursement amount and the maximum amount of the corresponding type is as follows: difference = corresponding type maximum amount-reimbursement amount; the formula according to which the same reimbursement fee type reimburses for the frequency of reimbursement in a predetermined period is: frequency = number of times of reimbursement fees of the same type reimbursement in a predetermined period/predetermined period; the formula according to which the corresponding employee reimbursement amount and the corresponding reimbursement maximum limit of the job position are based is as follows: difference = maximum reimbursement value corresponding to the position where the corresponding employee is located-maximum reimbursement amount corresponding to the employee, wherein the maximum reimbursement value is the maximum value in the amount range corresponding to the reimbursement cost type, and the corresponding type is the maximum amountCorresponding to the maximum reimbursement limit value corresponding to the position of the employee;
preprocessing evaluation parameters, namely, preprocessing the difference value between the reimbursement amount and the maximum amount of the corresponding typeFrequency of reimbursement in a predetermined period for the same reimbursement fee type>Difference value of maximum reimbursement amount corresponding to employee reimbursement amount and position corresponding to employee reimbursement amount>Performing dimensionless treatment;
calculating a reimbursement evidence risk assessment value Rarv, and generating a formula according to the reimbursement evidence risk assessment value Rarv as follows:
；
in the method, in the process of the invention,the difference between the reimbursement amount and the maximum amount of the corresponding type is +.>Frequency of reimbursement in a predetermined period for the same reimbursement fee type>Difference value of maximum reimbursement amount corresponding to employee reimbursement amount and position corresponding to employee reimbursement amount>Is a preset proportionality coefficient of>Int is a rounding function, ++>Is a constant correction coefficient.
7. The intelligent management system for financial reimbursement of an enterprise according to claim 6, wherein: the check interval number pre-estimation value Ygz is calculated and generated in the management direction module according to the following formula:
；
where, int is a rounding function,is a constant correction coefficient.
8. The intelligent management system for financial reimbursement of an enterprise according to claim 7, wherein: the process of obtaining the risk degree of the corresponding reimbursement certificate and the corresponding early warning signal is as follows: comparing the reimbursement evidence risk assessment value Rarv with a preset assessment threshold set, wherein the assessment threshold set comprises a first assessment thresholdAnd a second evaluation threshold->And a first evaluation threshold valueTwo evaluation threshold->If yes, the reimbursement evidence risk assessment value Rarv is less than a first assessment threshold +.>The corresponding reimbursement certificate is indicated to be low in risk, and a primary early warning signal is sent; if it is the first evaluation threshold->The reimbursement evidence risk assessment value Rarv is less than or equal to a second assessment threshold value +.>The corresponding reimbursement certificate is indicated as the middle risk, and a secondary early warning signal is sent out; if it is the second evaluation threshold->And if the risk assessment value Rarv of the reimbursement certificate is less than the risk assessment value Rarv of the reimbursement certificate, the corresponding reimbursement certificate is high risk, and a three-level early warning signal is sent.
9. An intelligent management method for financial reimbursement of enterprises, which uses the system as set forth in any one of claims 1 to 8, characterized in that: the method comprises the following steps:
step one, converting a reimbursement certificate into an electronic format, automatically extracting key information including expiration date, reimbursement amount and invoice number, integrating with a financial system, and acquiring reimbursement information related to staff including a belonging department, a job position and reimbursement limit;
classifying and archiving the key information in the acquired reimbursement certificates;
step three, extracting the number of days and reimbursement amount of the day from the expiration date as rating parameters, building a data analysis model, and generating a financial reimbursement grading index Frci for reflecting the priority of a plurality of reimbursement certificates;
step four, verifying authenticity of the reimbursement evidence by utilizing an artificial intelligence technology, if the reimbursement evidence is true, building a rule engine, calibrating the amount ranges corresponding to different reimbursement expense types, acquiring evaluation parameters, and secondarily building a data analysis model to generate a reimbursement evidence risk evaluation value Rarv; if the reimbursement certificate is false, deleting the data related to the reimbursement certificate, including the key information and reimbursement information of the first step, and sending out an alarm signal;
fifthly, comparing the reimbursement certificate risk evaluation value Rarv with a preset evaluation threshold set, acquiring a risk degree and a corresponding early warning signal of a corresponding reimbursement certificate according to a comparison result, calculating and generating an inspection interval number preset value Ygz according to the reimbursement certificate risk evaluation value Rarv of the same reimbursement certificate, and carrying out sampling inspection management on reimbursement certificates at different risk degrees according to the corresponding inspection interval number preset value Ygz according to the order of priority from large to small.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311723981.8A CN117408827A (en) | 2023-12-15 | 2023-12-15 | Intelligent management method and system for financial reimbursement of enterprises |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311723981.8A CN117408827A (en) | 2023-12-15 | 2023-12-15 | Intelligent management method and system for financial reimbursement of enterprises |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117408827A true CN117408827A (en) | 2024-01-16 |
Family
ID=89487494
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311723981.8A Pending CN117408827A (en) | 2023-12-15 | 2023-12-15 | Intelligent management method and system for financial reimbursement of enterprises |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117408827A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117876139A (en) * | 2024-03-04 | 2024-04-12 | 天讯瑞达通信技术有限公司 | Financial information management system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876166A (en) * | 2018-06-27 | 2018-11-23 | 平安科技（深圳）有限公司 | Financial risk authentication processing method, device, computer equipment and storage medium |
| CN111583180A (en) * | 2020-04-03 | 2020-08-25 | 苏宁云计算有限公司 | Image tampering identification method and device, computer equipment and storage medium |
| CN112396346A (en) * | 2020-12-01 | 2021-02-23 | 湖北航天信息技术有限公司 | Enterprise invoice checking and reimbursement method |
| CN114611909A (en) * | 2022-03-07 | 2022-06-10 | 石杨 | Risk analysis system and method for financial data |
| CN115423586A (en) * | 2022-08-26 | 2022-12-02 | 重庆财经职业学院 | Financial invoice reimbursement, uploading and auditing system based on network |
| CN115564544A (en) * | 2022-10-10 | 2023-01-03 | 杭州申能信息科技有限公司 | Intelligent accounting business processing method and device, computer equipment and storage medium |
| CN116012127A (en) * | 2022-12-23 | 2023-04-25 | 深圳市雁联计算系统有限公司 | Risk scoring rating method and system for account |
-
2023
- 2023-12-15 CN CN202311723981.8A patent/CN117408827A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876166A (en) * | 2018-06-27 | 2018-11-23 | 平安科技（深圳）有限公司 | Financial risk authentication processing method, device, computer equipment and storage medium |
| CN111583180A (en) * | 2020-04-03 | 2020-08-25 | 苏宁云计算有限公司 | Image tampering identification method and device, computer equipment and storage medium |
| CN112396346A (en) * | 2020-12-01 | 2021-02-23 | 湖北航天信息技术有限公司 | Enterprise invoice checking and reimbursement method |
| CN114611909A (en) * | 2022-03-07 | 2022-06-10 | 石杨 | Risk analysis system and method for financial data |
| CN115423586A (en) * | 2022-08-26 | 2022-12-02 | 重庆财经职业学院 | Financial invoice reimbursement, uploading and auditing system based on network |
| CN115564544A (en) * | 2022-10-10 | 2023-01-03 | 杭州申能信息科技有限公司 | Intelligent accounting business processing method and device, computer equipment and storage medium |
| CN116012127A (en) * | 2022-12-23 | 2023-04-25 | 深圳市雁联计算系统有限公司 | Risk scoring rating method and system for account |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117876139A (en) * | 2024-03-04 | 2024-04-12 | 天讯瑞达通信技术有限公司 | Financial information management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108090823B (en) | Accounting data management system based on software as a service (SaaS) | |
| WO2006099674A1 (en) | Risk based data assessment | |
| CN117408827A (en) | Intelligent management method and system for financial reimbursement of enterprises | |
| US20100121746A1 (en) | Financial statement risk assessment and management system and method | |
| CN110866832A (en) | Risk control method, system, storage medium and computing device | |
| CN112907356A (en) | Overdue collection method, device and system and computer readable storage medium | |
| US11966970B2 (en) | Method and system for performing income analysis from source documents | |
| CN113159796A (en) | Trade contract verification method and device | |
| CN112037039A (en) | Loan assessment method and device | |
| CN115564549A (en) | Enterprise intelligent tax meter payment declaration method and system | |
| CN115796826A (en) | Management method, system, device and storage medium for ship safety management and control | |
| CN112037006A (en) | Credit risk identification method and device for small and micro enterprises | |
| CN113159874B (en) | Method and device for detecting value-added tax invoice and readable storage medium | |
| CN116385193A (en) | Automatic account setting processing method and system based on artificial intelligence | |
| CN115577983B (en) | Enterprise task matching method based on block chain, server and storage medium | |
| CN113077355B (en) | Insurance claim settlement method and device, electronic equipment and storage medium | |
| CN115564591A (en) | Financing product determination method and related equipment | |
| CN117575828B (en) | Financial reimbursement data processing system and method based on cloud computing | |
| WO2019028620A1 (en) | Big data and artificial intelligence based trademark application method | |
| Achim et al. | A methodological approach to developing and validating IFRS 9-LGD parameters | |
| CN117522135A (en) | Cross-border electronic commerce big data intelligent wind control strategy method and system | |
| Sova et al. | Analysis of The Implementation of PSAK No. 71 on Impairment Loss Reserves: A Case Study of State-Owned Pharmaceutical Companies Listed on The Indonesia Stock Exchange (BEI) | |
| CN114429395A (en) | Enterprise credit rating method, system and storage medium based on semi-supervised learning | |
| CN117726468A (en) | Financial tax management method, system and application of AI financial tax robot | |
| CN116151623A (en) | User scoring card model construction method, device, equipment and storage 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 |