CN114881600A - Evaluation method and system for reimbursement items - Google Patents
Evaluation method and system for reimbursement items Download PDFInfo
- Publication number
- CN114881600A CN114881600A CN202210526762.XA CN202210526762A CN114881600A CN 114881600 A CN114881600 A CN 114881600A CN 202210526762 A CN202210526762 A CN 202210526762A CN 114881600 A CN114881600 A CN 114881600A
- Authority
- CN
- China
- Prior art keywords
- reimbursement
- item
- items
- approval
- credit
- 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
Images
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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Human Resources & Organizations (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to the technology of reimbursement item management, and discloses a method and a system for evaluating reimbursement items, wherein reimbursement item information is submitted through a reimbursement system, and comprises at least 2 reimbursement item participants; sending reimbursement information to all reimbursement item participants through an reimbursement system, wherein all reimbursement item participants receive credit requests; all the reimbursement item participants feed back the information of the credit result of the reimbursement item to the reimbursement system; the reimbursement system processes the received reimbursement item credit result information through the credit evaluation model, and therefore reimbursement item credit scores are obtained. The evaluation method for reimbursement items designed by the invention can effectively reduce the management cost of enterprises and save a lot of manpower and material resources in the process of approving reimbursement items.
Description
Technical Field
The invention relates to a reimbursement item management technology, in particular to an assessment method and system for reimbursement items.
Background
Reimbursement management is a common operation in enterprise operations. The auditing process of reimbursement mainly aims at judging the authenticity and compliance of invoices and business items. The authenticity of the invoice can be checked through a verification service or an interface provided by the tax system; the compliance can be confirmed by setting detailed reimbursement rules and checking one by one in the approval process; the service item authenticity judgment is to confirm whether the reimbursement cost is a reasonable cost for developing company services, and to prevent dishonest behavior in the reimbursement process.
The existing method for judging the authenticity of reimbursement items mainly comprises the following steps: providing more detailed supporting information: such as the start and end of ticketing; details of consumption in lodging invoices; a list of participants in the catering invoice, etc.; artificially checking the authenticity of the service: for critical reimbursements, full or spot verification is performed by a specific person to related participants, such as colleagues, customers, suppliers, or other related persons.
For example, in the prior art, CN202011381995.2 only evaluates bills, and spends a lot of manpower and material resources on other information, thereby increasing the enterprise management cost, and at the same time, lengthening the reimbursement period and affecting the user experience.
Disclosure of Invention
Aiming at the problems of high operation cost and time and labor waste of reimbursement in the prior art for enterprises, the invention provides an assessment method and a system for reimbursement items, aiming at solving the technical problems, the invention solves the problems by the following technical scheme:
an evaluation method of reimbursement items, comprising a reimbursement system, the method comprising:
step 1, submitting reimbursement items, namely submitting reimbursement item information through a reimbursement system, wherein the reimbursement item information comprises at least 2 reimbursement item participants;
step 2, sending the reimbursement information to all reimbursement item participators through the reimbursement system for the credit request of reimbursement items, wherein all reimbursement item participators receive the credit request;
step 3, feedback of the reimbursement item credit information, wherein all reimbursement item participants feed back reimbursement item credit result information to the reimbursement system; the reimbursement item credit result information comprises real reimbursement item information, reimbursement item information to be verified and unreal reimbursement item information;
and 4, generating a reimbursement item credit score, and processing the received reimbursement item credit result information by the reimbursement item credit evaluation model through the reimbursement item credit evaluation system so as to obtain the reimbursement item credit score.
Preferably, the method further comprises the steps of approving the reimbursement items, receiving reimbursement item credit scores of the reimbursement system, analyzing the reimbursement item credit scores, and determining the approval state of the reimbursement items, wherein the approval state of the reimbursement items comprises reimbursement items rejected for approval and reimbursement items to be approved through the reimbursement items approved;
directly carrying out approval through approved reimbursement items;
the reimbursement items refusing to be approved obtain the information of refusing to be approved through measurement learning and feed back the information;
and submitting the reimbursement items to be approved to manual approval, taking the reimbursement items as supplementary samples to enter a sample pool of the information quantity to be evaluated after approval is finished, and actively learning and screening high-information-quantity samples when the data quantity of the sample pool of the information quantity to be evaluated reaches a sample threshold value.
Preferably, the credit evaluation model is an Xgboost-based machine learning classification model, and the method for establishing the Xgboost-based machine learning classification model includes:
determining a reimbursement feature vector, wherein the feature vector of the reimbursement item comprises a reimbursement personnel feature vector, a reimbursement time vector feature and a reimbursement type vector feature;
the method comprises the steps of distributing and canceling characteristic values, and performing chi-square distribution according to the type of each characteristic vector in the characteristic vectors, wherein the characteristic vectors with fewer categories do not need to be distributed, and the characteristic vectors with more categories are distributed through ordered characteristics, so that the ordering of distribution is guaranteed;
calculation of reimbursement evaluation IV value by Calculating an IV value; wherein, WOE i For evaluating the index value, p yi Is the proportion of positive samples in the bin in the class, p ni Is the proportion of negative examples in the bin in the category;
wherein, y i Is the amount of positive sample data in the category; n is i Is the amount of negative sample data in the category; y is T Is the total amount of data in the positive sample; n is T Is the total data amount of negative examples;
and screening out feature data in a reasonable range through the IV value of each feature, wherein the feature data comprises a training set, a verification set and a test set.
Preferably, the metric learning method includes:
and (3) SI: input a data set D, wherein
D=(x 1 ,y 1 ),(x 2 ,y 2 ),...(x i ,y i )...(x n ,y n ) Where arbitrary sample x i Is an n-dimensional vector, y i ∈C 1 ,C 2 …C k ;
S2: computing a sample neighbor distribution p ij ;
S3: predicting the ith sample as y k Predicting the probability of the i-th sample being correct as p i Wherein
S4: optimizing the target score f (a);
s5: updating A by utilizing the gradient, judging the updated A, and refusing reimbursement items to be similar samples in the reimbursement system when A is minimum; otherwise, returning to the step S2;
preferably, the method for screening high-information-content samples by active learning comprises the following steps
(1) Classifying the data of the reimbursement items through a classifier, wherein the data of the reimbursement items are divided into a training set of the reimbursement items, a verification set of the reimbursement items and an unannotated reimbursement item data set;
(2) initializing an approval item model, and initializing the approval item model when approval data is larger than an approval threshold;
(3) adding newly added approval data of the reimbursement items into a data set which is not marked with the approval items;
(4) predicting the data sets which are not marked with the examination and approval items, and when the data sets which are not marked with the examination and approval items are accumulated to the unmarked data threshold, predicting the samples of the unmarked data sets one by using an examination and approval item model to obtain the prediction result of each sample;
(5) predicting the value of the marked sample, namely measuring the value prediction of the marked sample according to an uncertainty sampling strategy;
(6) updating the approval item model, selecting the predicted labeled sample, and adding the selected labeled sample into the approval item model in the step (2) in combination with the approval state result for training so as to obtain a new approval item model;
(7) and (4) verifying the approval item data, namely verifying the approval item data through the approval item model (6), ending the iterative process if the performance of the approval item model reaches the target, and otherwise, executing the step (3).
In order to solve the above technical problem, the present application further provides an evaluation system for reimbursement items, including:
the submitting module of the reimbursement items submits reimbursement item information through the reimbursement system, wherein the reimbursement item information comprises at least 2 reimbursement item participants;
the credit request module of the reimbursement items sends reimbursement information to all reimbursement item participants through the reimbursement system, and all reimbursement item participants receive credit requests;
the feedback module of the reimbursement item credit information feeds back the reimbursement item credit result information to the reimbursement system by all reimbursement item participants; the reimbursement item credit result information comprises real reimbursement item information, reimbursement item information to be verified and unrealistic reimbursement item information;
and the reimbursement item credit score generation module is used for processing the received reimbursement item credit result information by the reimbursement system through the credit evaluation model so as to obtain the reimbursement item credit score.
Preferably, the method further comprises the following steps: the system comprises an approval module for the reimbursement items, and an approval module for the reimbursement items, wherein the approval module for the reimbursement items is used for scoring reimbursement item credit of a receiving reimbursement system, analyzing the reimbursement item credit score and determining approval states of the reimbursement items, and the approval states of the reimbursement items comprise reimbursement items rejected for approval and reimbursement items to be approved through the reimbursement items for approval.
In order to solve the above technical problem, the present application further provides an electronic device implemented by an evaluation method of reimbursement items.
In order to solve the above technical problem, the present application also provides a storage medium implemented by an evaluation method of reimbursement items.
Due to the adoption of the technical scheme, the invention has the remarkable technical effects that:
the evaluation method for reimbursement items designed by the invention can effectively reduce the management cost of enterprises, and can reduce a large amount of manpower and material resources for approving the reimbursement items.
Drawings
FIG. 1 is a flow chart of example 1 of the present invention.
Fig. 2 is a flow chart of embodiment 2 of the present invention.
FIG. 3 is a flow chart of the method for screening high information content samples by active learning according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
Example 1
An evaluation method of reimbursement items, comprising a reimbursement system, the method comprising:
step 1, submitting reimbursement items, namely submitting reimbursement item information through a reimbursement system, wherein the reimbursement item information comprises at least 2 reimbursement item participants; there are 2 participants of reimbursement affairs, one of them is direct participant, the other is indirect participant;
step 2, sending the reimbursement information to all reimbursement item participants through the reimbursement system for the credit request of reimbursement items, wherein all the participants receive the credit request;
step 3, feedback of the reimbursement item credit information, wherein all reimbursement item participants feed back reimbursement item credit result information to the reimbursement system; the reimbursement item credit result information comprises real reimbursement item information, reimbursement item information to be verified and unreal reimbursement item information;
and 4, generating a reimbursement item credit score, and processing the received reimbursement item credit result information by the reimbursement system through a credit evaluation model so as to obtain the reimbursement item credit score.
The credit evaluation model is an Xgboost-based machine learning classification model, and the method for establishing the Xgboost-based machine learning classification model comprises the following steps:
determining a reimbursement feature vector, wherein the feature vector of reimbursement items comprises a reimbursement personnel feature vector, a reimbursement time vector feature and a reimbursement type vector feature;
the method comprises the steps of distributing and canceling characteristic values, and performing chi-square distribution according to the type of each characteristic vector in the characteristic vectors, wherein the characteristic vectors with fewer categories do not need to be distributed, and the characteristic vectors with more categories are distributed through ordered characteristics, so that the ordering of distribution is guaranteed;
reimbursement evaluation IV valueIs calculated by Calculating an IV value; wherein, WOE i For evaluating the index value, p yi Is the proportion of positive samples in the bin in the class, p ni Is the proportion of negative examples in the bin in the category;
wherein, y i Is the amount of positive sample data in the category; n is i Is the amount of negative sample data in the category; y is T Is the total amount of data in the positive sample; n is T Is the total data amount of negative examples;
and screening out feature data in a reasonable range through the IV value of each feature, wherein the feature data comprises a training set, a verification set and a test set. Wherein the training set, the validation set, and the test set are separated by a ratio of 70%, 15%, and 15%, wherein the training set and the validation set are used in training the xgboost model. The test set is used for evaluating the accuracy and AUC area index of the model after the model is trained.
Example 2
On the basis of the embodiment 1, the embodiment further comprises approval of the reimbursement items, receiving reimbursement item credit scores of the reimbursement system, analyzing the reimbursement item credit scores, and determining approval states of the reimbursement items, wherein the approval states of the reimbursement items comprise reimbursement items approved, reimbursement items rejected for approval and reimbursement items to be approved;
directly carrying out approval through approved reimbursement items;
the reimbursement items refusing to be approved obtain the information of refusing to be approved through measurement learning and feed back the information;
and submitting the reimbursement items to be approved by manual approval, taking the reimbursement items as supplementary samples to enter a sample pool of the information quantity to be evaluated after the approval is finished, enabling the data quantity of the sample pool of the information quantity to be evaluated to reach a sample threshold value, setting the range of the sample threshold value as 100 plus 150, actively learning and screening the high-information-quantity samples, and selecting the screened samples into a data set of model training.
The credit evaluation model is an Xgboost-based machine learning classification model, and the method for establishing the Xgboost-based machine learning classification model comprises the following steps:
determining a reimbursement feature vector, wherein the feature vector of the reimbursement item comprises a reimbursement personnel feature vector, a reimbursement time vector feature and a reimbursement type vector feature;
the distribution of the reimbursement characteristic values is realized by distributing the determined reimbursement characteristic vectors and distributing according to the discrete attributes of the characteristic vectors;
presetting a chi-square threshold, wherein the set threshold is 0.95, sorting the examples according to the attributes to be dispersed, and each example belongs to an interval merging interval; calculating the chi-square value of each pair of adjacent intervals, combining the pair of intervals with the minimum chi-square value to judge whether the stopping condition is met, if not, continuing the operation, otherwise, stopping the operation; the stop conditions were as follows:
the chi-square value of the adjacent sub-box of which the number of sub-boxes reaches the minimum limiting condition is larger than the threshold value. The threshold value here is set to
Calculation of reimbursement evaluation IV value by Calculating the IV value; wherein, WOE i For evaluating the index value, p yi Is the proportion of positive samples in the bin in the class, p ni Is the proportion of negative samples in the bin in the category;
wherein, y i Is the amount of positive sample data in the category; n is i Is negative in this categorySample data size; y is T Is the total amount of data in the positive sample; n is T Is the total data amount of negative examples;
determining the evaluation score of the reimbursement items according to the AUC area; AUC area was calculated by screening IV values.
The metric learning method comprises the following steps:
s1: input a data set D, wherein
D=(x 1 ,y 1 ),(x 2 ,y 2 ),...(x i ,y i )...(x n ,y n ) Where arbitrary sample x i Is an n-dimensional vector, y i ∈C 1 ,C 2 …C k ;
S2: computing a sample neighbor distribution p ij ;
S3: predicting the ith sample as y k Predicting the probability of the i-th sample being correct as p i Wherein
S4: optimizing the target score f (a);
s5: updating A by utilizing the gradient, judging the updated A, and refusing reimbursement items to be similar samples in the reimbursement system when A is minimum; otherwise, returning to the step S2;
through measurement learning, after approval of the reimbursement items is rejected, the reimbursement system can automatically give similar reimbursement items existing in the reimbursement system as evidences for rejecting approval of the reimbursement items, and similarity of learning samples is determined so as to find the closest reimbursement item sample.
The method for screening the high-information-content sample by active learning comprises the following steps:
(1) classifying the data of the reimbursement items through a classifier, wherein the data of the reimbursement items are divided into a training set of the reimbursement items, a verification set of the reimbursement items and an unannotated reimbursement item data set;
(2) initializing an approval item model, and initializing the approval item model when approval data is greater than an approval threshold and the maximum approval threshold is greater than 1500;
(3) adding newly added approval data of the reimbursement items into a data set which is not marked with the approval items;
(4) predicting the data set which is not marked with the examination and approval items, and when the data set which is not marked with the examination and approval items is accumulated to the threshold value of the examination and approval items of the unmarked data, wherein the threshold value range of the examination and approval items is 100-150, predicting the samples of the data set which is not marked with the examination and approval items one by using an examination and approval item model to obtain the prediction result of each sample;
(5) predicting the value of the marked sample, namely measuring the value prediction of the marked sample according to an uncertainty sampling strategy;
(6) updating the approval item model, selecting the predicted labeled sample, and adding the selected labeled sample into the approval item model in the step (2) in combination with the approval state result for training so as to obtain a new approval item model;
(7) and (4) verifying the approval item data, namely verifying the approval item data through the approval item model (6), ending the iterative process if the performance of the approval item model reaches the target, and otherwise, executing the step (3).
Example 3
On the basis of embodiment 1, an evaluation system for reimbursement items, comprising:
the submitting module of the reimbursement items submits reimbursement item information through the reimbursement system, wherein the reimbursement item information comprises at least 2 participants;
the credit request module of the reimbursement items sends reimbursement information to all participants through the reimbursement system, and all the participants receive the credit request;
the feedback module of the reimbursement item credit information feeds back the reimbursement item credit result information to the reimbursement system by all participants; the reimbursement item credit result information comprises real reimbursement item information, reimbursement item information to be verified and unreal reimbursement item information;
and the reimbursement item credit score generation module is used for processing the received reimbursement item credit result information by the reimbursement system through the credit evaluation model so as to obtain the reimbursement item credit score.
Example 4
On the basis of the above embodiment, the present embodiment further includes: the system comprises an approval module for the reimbursement items, and an approval module for the reimbursement items, wherein the approval module for the reimbursement items is used for scoring the reimbursement items credit of the receiving reimbursement system, analyzing the credit score, and determining the approval state of the reimbursement items, and the approval state of the reimbursement items comprises the reimbursement items which pass approval, the reimbursement items which reject approval and the reimbursement items which are to be approved.
Example 5
On the basis of the above embodiments, the present embodiment provides an electronic device.
Example 6
On the basis of the above embodiments, the present embodiment provides a storage medium.
Claims (9)
1. An evaluation method of reimbursement items, comprising a reimbursement system, the method comprising:
step 1, submitting reimbursement items, namely submitting reimbursement item information through a reimbursement system, wherein the reimbursement item information comprises at least 2 reimbursement item participants;
step 2, sending the reimbursement information to all reimbursement item participators through the reimbursement system for the credit request of reimbursement items, wherein all reimbursement item participators receive the credit request;
step 3, feedback of the reimbursement item credit information, wherein all reimbursement item participants feed back reimbursement item credit result information to the reimbursement system; the reimbursement item credit result information comprises real reimbursement item information, reimbursement item information to be verified and unreal reimbursement item information;
and 4, generating a reimbursement item credit score, and processing the received reimbursement item credit result information by the reimbursement system through a credit evaluation model so as to obtain the reimbursement item credit score.
2. The method of claim 1, further comprising approving the reimbursement item, receiving a reimbursement item credit score of the reimbursement system, analyzing the credit score, and determining an approval status of the reimbursement item, wherein the approval status of the reimbursement item includes the reimbursement item approved by the approval, the reimbursement item rejected for approval, and the reimbursement item to be approved;
directly carrying out approval through approved reimbursement items;
the reimbursement items refusing to be approved are obtained through metric learning and fed back;
and taking the reimbursement items to be examined and approved as reimbursement items to supplement samples to enter a sample pool of reimbursement items to be evaluated, actively learning and screening high-information-quantity samples when the data volume of the sample pool of reimbursement items to be evaluated reaches a reimbursement items sample threshold value, and selecting the screened samples into a data set of model training.
3. The method of claim 1, wherein the reimbursement credit evaluation model is an Xgboost-based machine learning classification model, and the method of building the Xgboost machine learning classification model comprises:
determining a characteristic vector of the reimbursement item, wherein the characteristic vector of the reimbursement item comprises reimbursement personnel, reimbursement time and reimbursement type;
the distribution box of the reimbursement characteristic values is used for performing card square distribution according to the type of each characteristic vector in the reimbursement characteristic vectors;
calculation of reimbursement evaluation IV value byCalculating an IV value; wherein, WOE i For evaluating the index value, p yi Is the proportion of positive samples in the bin in the class, p ni Is the proportion of negative examples in the bin in the category;
wherein, y i Is the positive sample data size in the bin; (ii) a n is i Is the amount of negative sample data in the category; y is T Is the total amount of data in the positive sample; n is T Is the total data amount of negative examples;
and screening reimbursement item feature data in a reasonable range through the IV value of each feature, wherein the feature data comprises a training set, a verification set and a test set.
4. The method of claim 2, wherein the method of reimbursement metric learning comprises:
s1: input data set D, D ═ x 1 ,y 1 ),(x 2 ,y 2 ),…(x i ,y i )…(x n ,y n ) Wherein an arbitrary sample x i Is an n-dimensional vector, y i ∈C 1 ,C 2 …C k ;
S2: computing a sample neighbor distribution p ij ,
S3: predicting the ith sample as y k Predicting the probability of the i-th sample being correct as p i Wherein
S4: optimizing the target score f (a);
s5: updating A by utilizing the gradient, judging the updated A, and refusing reimbursement items to be similar samples in the reimbursement system when A is minimum; otherwise, returning to the step S2;
5. the method of claim 2, wherein the method of actively learning and screening high information content samples comprises:
(1) classifying the data of the reimbursement items, wherein the data of the reimbursement items are divided into an accumulated training set of the reimbursement items, a verification set of the reimbursement items and an unlabeled reimbursement item data set;
(2) initializing an approval item model, namely initializing the approval item model when the approved approval items and the approval items which do not pass the approval reach an approval item threshold value;
(3) adding newly added approval data of the reimbursement items into a data set which is not marked with the approval items;
(4) predicting the data set which is not marked with the examination and approval items, and when the data set which is not marked with the examination and approval items is accumulated to an unmarked data threshold value, carrying out gradual prediction on the samples of the unmarked data set by using an examination and approval item model to obtain a prediction result of each sample;
(5) predicting the value of the marked sample, namely measuring the value prediction of the marked sample according to an uncertainty sampling strategy;
(6) updating the approval item model, selecting the predicted labeled sample, and adding the selected labeled sample into the approval item model in the step (2) in combination with the approval state result for training so as to obtain a new approval item model;
(7) and (4) verifying the approval item data, namely verifying the approval item data through the approval item model (6), ending the iterative process if the performance of the approval item model reaches the target, and otherwise, executing the step (3).
6. An assessment system for reimbursement items, comprising:
the submitting module of the reimbursement items submits reimbursement item information through the reimbursement system, wherein the reimbursement item information comprises at least 2 reimbursement item participants;
the credit request module of the reimbursement items sends reimbursement information to all reimbursement item participants through the reimbursement system, and all reimbursement item participants receive credit requests;
the feedback module of the reimbursement item credit information feeds back the reimbursement item credit result information to the reimbursement system by all reimbursement item participants; the reimbursement item credit result information comprises real reimbursement item information, reimbursement item information to be verified and unreal reimbursement item information;
and the reimbursement item credit score generation module is used for processing the received reimbursement item credit result information by the reimbursement item credit evaluation model through the reimbursement item credit evaluation system so as to obtain the reimbursement item credit score.
7. The system for evaluating an reimbursement item according to claim 6, further comprising: the system comprises an approval module for the reimbursement items, and an approval module for the reimbursement items, wherein the approval module for the reimbursement items is used for scoring reimbursement item credit of a receiving reimbursement system, analyzing the reimbursement item credit score and determining approval states of the reimbursement items, and the approval states of the reimbursement items comprise reimbursement items rejected for approval and reimbursement items to be approved through the reimbursement items for approval.
8. An electronic device, characterized by being realized by the evaluation method of a reimbursement item according to any one of claims 1 to 5.
9. A storage medium implemented by the evaluation method of a reimbursement item according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210526762.XA CN114881600A (en) | 2022-05-16 | 2022-05-16 | Evaluation method and system for reimbursement items |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210526762.XA CN114881600A (en) | 2022-05-16 | 2022-05-16 | Evaluation method and system for reimbursement items |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114881600A true CN114881600A (en) | 2022-08-09 |
Family
ID=82676688
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210526762.XA Pending CN114881600A (en) | 2022-05-16 | 2022-05-16 | Evaluation method and system for reimbursement items |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114881600A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
-
2022
- 2022-05-16 CN CN202210526762.XA patent/CN114881600A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN115423586B (en) * | 2022-08-26 | 2023-09-29 | 重庆财经职业学院 | Financial invoice reimbursement uploading auditing system based on network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109558429B (en) | Talent service bidirectional recommendation method and system based on Internet big data | |
CN110837931B (en) | Customer churn prediction method, device and storage medium | |
US20230004590A1 (en) | Ai-augmented auditing platform including techniques for automated adjudication of commercial substance, related parties, and collectability | |
US8942470B2 (en) | Sentiment classification using out of domain data | |
CN110852856A (en) | Invoice false invoice identification method based on dynamic network representation | |
CN111612519B (en) | Method, device and storage medium for identifying potential customers of financial products | |
Hsu | A hybrid multiple criteria decision-making model for investment decision making | |
WO2022262752A1 (en) | Information recommendation method and apparatus based on data interaction, and device and storage medium | |
CN111709826A (en) | Target information determination method and device | |
CN114881600A (en) | Evaluation method and system for reimbursement items | |
CN115543973A (en) | Data quality rule recommendation method based on knowledge spectrogram and machine learning | |
CN116468273A (en) | Customer risk identification method and device | |
CN117151647A (en) | Auxiliary auditing method, equipment and medium for bill | |
CN112634048A (en) | Anti-money laundering model training method and device | |
Latypova | Reviewer assignment decision support in an academic journal based on multicriteria assessment and text mining | |
CN115809930A (en) | Anti-fraud analysis method, device, equipment and medium based on data fusion matching | |
CN112506930B (en) | Data insight system based on machine learning technology | |
CN113298447A (en) | Financing lease management system based on data processing | |
Domashova et al. | Detection of non-typical users of the electronic marketplace" Freight transportation" to prevent the competitive intelligence | |
CN112785154A (en) | Safety evaluation method of cloud ERP system | |
CN113919937A (en) | KS monitoring system based on loan assessment wind control | |
CN114548620A (en) | Logistics punctual insurance service recommendation method and device, computer equipment and storage medium | |
CN108153829B (en) | Resume evaluation method and device | |
Wang et al. | Research on Credit Decision Issues of the Small and Medium-Sized Enterprises Based on TOPSIS and Hierarchical Cluster Analysis | |
Ji et al. | The hidden information content: Evidence from the tone of independent director reports |
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 |