Financial reimbursement data processing method and device, electronic equipment and readable storage medium

Abstract

The invention provides a financial reimbursement data processing method and device, electronic equipment and a readable storage medium, the financial reimbursement data processing method is used for a server, and the financial reimbursement data processing method comprises the following steps: calling first data stored in the server; extracting a feature set in the first data to obtain a first feature set; training the initial classification model through the first feature set to obtain a data classification model; under the condition that a data processing request sent by a client is received, extracting to-be-processed data information in the data processing request; generating a first document based on the to-be-processed data information and the data classification model, and sending the first document to the client; wherein the first data at least comprises at least one of an invoice, a reimbursement bill and a payment voucher. The intelligent analysis and prediction capability of the financial reimbursement system can be improved, and valuable financial management suggestions can be provided for enterprises.

Description

Technical Field

[0001] The present invention relates to the technical field of financial accounting, and in particular to a method, device, electronic device and readable storage medium for processing financial accounting data. Background Art

[0002] At present, in the relevant technology, enterprises generally use financial accounting systems to process financial accounting data. In the process of processing financial accounting data, after the data is automatically imported, it is still necessary to manually classify and review the data, and then fill in the documents according to the classified data. However, due to manual intervention, the probability of errors or omissions in the data processing process caused by human factors will increase, which will affect the accuracy of accounting data review and classification, and is not convenient for corporate financial management. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art or related art.

[0004] To this end, a first aspect of the present invention provides a method for processing financial accounting data.

[0005] A second aspect of the present invention provides a financial accounting data processing device.

[0006] A third aspect of the present invention provides an electronic device.

[0007] A fourth aspect of the present invention provides a readable storage medium.

[0008] In view of this, a first aspect of the present invention provides a financial accounting data processing method, which is used for a server, and the financial accounting data processing method includes: calling first data stored in the server; extracting a feature set in the first data to obtain a first feature set; training an initial classification model through the first feature set to obtain a data classification model; upon receiving a data processing request sent by a client, extracting the data information to be processed in the data processing request; generating a first document based on the data information to be processed and the data classification model, and sending the first document to the client; wherein the first data includes at least one of the three types of invoice, reimbursement form, and payment voucher.

[0009] The present application provides a financial reimbursement data processing method, which is used for a server. The financial reimbursement data processing method includes: the server can automatically call or obtain historical data related to financial reimbursement, that is, call the first data stored in the server. The first data includes at least one of the three types of invoices, reimbursement forms, and payment vouchers. Based on the first data, the accuracy of financial reimbursement can be improved and the error probability can be reduced. After obtaining the first data, extract the feature set in the first data to obtain the first feature set. The feature engineering technology can be used to extract the features related to financial reimbursement, and the features are output as a feature set, that is, the first feature set. The first feature set includes multiple information such as invoice type, date, buyer and seller information, amount, invoice type, commodity description, etc. After obtaining the first feature set, the initial classification model can be trained by the first feature set to obtain a data classification model; when receiving a data processing request sent by a client, extract the data information to be processed in the data processing request; based on the data information to be processed and the data classification model, generate a first document, and send the first document to the client.

[0010] By introducing a data classification model based on a lightweight machine learning algorithm to classify data, the type of economic items to be reimbursed and the corresponding reimbursement entry can be automatically predicted based on the characteristics of the input data, avoiding filling errors caused by manual intervention in classification, reducing the probability of errors, and improving the audit efficiency of financial reimbursement data. It can improve the intelligent analysis and prediction capabilities of the financial reimbursement system, and thus provide valuable financial management suggestions for enterprises.

[0011] Specifically, a reimbursement request, i.e., a data processing request sent by a client, is received. By extracting the data information to be processed in the request and inputting the data information to be processed into a trained model, the model can automatically predict the type of economic item to be reimbursed and the corresponding reimbursement entry based on the characteristics of the input data information to be processed. At the same time, the relevant fields of the reimbursement document are automatically filled in according to the prediction results, and the first document of the meaning, expense category, account code and other fields can be generated, and the first document is sent to the client.

[0012] Specifically, the client side can provide an intuitive and easy-to-use user interface to display the prediction results and automatically filled billing documents for users to confirm or adjust. At the same time, user feedback is collected to continuously optimize the algorithm model and improve the intelligence level of the system and user satisfaction.

[0013] In addition, the financial accounting data processing method in the above technical solution provided by the present invention may also have the following additional technical features: In some technical solutions of the present invention, optionally, extracting a feature set from the first data to obtain the first feature set includes: preprocessing the first data to obtain a preprocessed data set; extracting the feature set from the preprocessed data set to obtain the first feature set.

[0014] In the technical solution, extracting a feature set from the first data to obtain the first feature set includes: preprocessing the first data to obtain a preprocessed data set; extracting a feature set from the preprocessed data set to obtain the first feature set. By preprocessing the first data, the processing efficiency of subsequent data can be improved, and the accuracy of data prediction can be improved.

[0015] Specifically, by preprocessing the data, you can filter out features that have a greater impact on the analysis results, reduce the data dimension, and improve the analysis efficiency. When classifying data, by preprocessing the data, you can adjust the data category distribution and improve the accuracy of the model's prediction of data categories.

[0016] In some technical solutions of the present invention, optionally, based on the data information to be processed and the data classification model, a first document is generated, and the first document is sent to the client, including: obtaining first prediction data based on the data information to be processed and the data classification model; obtaining an initial document template; filling the first prediction data into the initial document template to generate a first document, and sending the first document to the client.

[0017] In this technical solution, based on the data information to be processed and the data classification model, a first document is generated and sent to a client, including: based on the data information to be processed and the data classification model, first prediction data is obtained; an initial document template is obtained; the first prediction data is filled into the initial document template to generate a first document, and the first document is sent to the client. When a reimbursement request, i.e., a data processing request, is received, by extracting the data information to be processed in the request and inputting the data information to be processed into a trained model, the model can automatically predict the type of economic item to be reimbursed and the corresponding reimbursement entry according to the characteristics of the input data information to be processed, that is, automatically fill the information into the initial document template to generate the first document. The relevant fields of the reimbursement document are automatically filled according to the prediction results, so that the first document with fields such as meaning, expense category and account code can be generated, and the first document is sent to the client, so as to realize intelligent recognition and classification of reimbursement requests and improve the efficiency and accuracy of reimbursement processing.

[0018] In some technical solutions of the present invention, optionally, after generating a first document based on the data information to be processed and the data classification model, and sending the first document to the client, the financial accounting data processing method also includes: upon receiving an adjustment request sent by the client, extracting adjustment information in the adjustment request; adjusting the data information in the first document according to the adjustment information to generate a second document, and sending the second document to the client.

[0019] In the technical solution, after generating a first document based on the data information to be processed and the data classification model, and sending the first document to the client, the financial accounting data processing method further includes: extracting the adjustment information in the adjustment request when receiving the adjustment request sent by the client; adjusting the data information in the first document according to the adjustment information to generate a second document, and sending the second document to the client. If the user does not adjust the content of the first document, the first document can be directly output. At the same time, when the user needs to adjust the document, the adjustment information in the adjustment request can be extracted, and the data information in the first document can be adjusted according to the adjustment information, which is convenient for users to use and improves the flexibility and accuracy of the system.

[0020] In some technical solutions of the present invention, optionally, after generating a first document based on the data information to be processed and the data classification model, and sending the first document to the client, the financial accounting data processing method also includes: upon receiving an update request sent by the client, extracting the update data in the update request; based on the update data, updating and training the data classification model to obtain an updated data classification model.

[0021] In this technical solution, after generating a first document based on the data information to be processed and the data classification model, and sending the first document to the client, the financial accounting data processing method further includes: extracting the update data in the update request when receiving the update request sent by the client; and updating and training the data classification model based on the update data to obtain the updated data classification model. The update request of user feedback is collected, and based on the update request, the data classification model is updated and trained through the update data to obtain the updated data classification model, so as to realize the continuous optimization of the algorithm model and improve the intelligence level of the system and user satisfaction.

[0022] In some technical solutions of the present invention, optionally, a first document is generated based on the data information to be processed and the data classification model, and the first document is sent to the client, including: obtaining user personal information and second data according to the data information to be processed; generating a first document based on the user personal information, the second data and the data classification model, and sending the first document to the client.

[0023] In this technical solution, based on the data information to be processed and the data classification model, a first document is generated, and the first document is sent to the client, including: obtaining user personal information and second data based on the data information to be processed; generating a first document based on the user personal information, the second data and the data classification model, and sending the first document to the client. That is, in the financial reimbursement data processing method provided by this application, the user's personal information can be combined with historical data, a user portrait can be drawn through a data classification model, and the reimbursement information can be automatically identified and filled in based on information such as invoices. Finally, the user chooses to confirm or change on the client, thereby realizing the processing of the financial reimbursement data. After the user feedback, the data classification model can also be updated according to the user's feedback.

[0024] In some technical solutions of the present invention, optionally, the second data is data related to financial accounting.

[0025] In this technical solution, the second data is data related to financial reimbursement, that is, the reimbursement request input by the user through the client, and the data related to financial reimbursement is extracted from the reimbursement request. By inputting the second data into the trained model, the model automatically predicts the type of economic item for reimbursement and the corresponding reimbursement entry according to the input features. At the same time, the relevant fields of the reimbursement document, such as expense category, account code, etc., are automatically filled according to the prediction results.

[0026] The financial reimbursement data processing method provided in the present application introduces a data classification model based on a lightweight machine learning algorithm, which can be a simplified version of Gradient Boosting Decision, GBDT (gradient boosting decision tree) or a lightweight reimbursement classification model of a random forest algorithm.

[0027] The second aspect of the present invention provides a financial accounting data processing device, including a calling module and an acquisition module, the calling module is used to call the first data stored in the server; the acquisition module is used to extract the feature set in the first data and obtain the first feature set; the acquisition module is also used to train the initial classification model through the first feature set to obtain the data classification model; the acquisition module is also used to extract the data information to be processed in the data processing request when receiving the data processing request sent by the client; the acquisition module is also used to generate a first document based on the data information to be processed and the data classification model, and send the first document to the client.

[0028] The present application provides a financial reimbursement data processing device, including a calling module and an acquisition module, wherein the calling module is used to call the first data stored in the server; the acquisition module is used to extract the feature set in the first data and obtain the first feature set; the acquisition module is also used to train the initial classification model through the first feature set to obtain the data classification model; the acquisition module is also used to extract the pending data information in the data processing request when receiving the data processing request sent by the client; the acquisition module is also used to generate a first document based on the pending data information and the data classification model, and send the first document to the client. By introducing a data classification model based on a lightweight machine learning algorithm to classify the data, the type of economic items to be reimbursed and the corresponding reimbursement entry can be automatically predicted according to the characteristics of the input data, avoiding filling errors caused by manual intervention in the classification, reducing the probability of errors, and improving the audit efficiency of financial reimbursement data. The intelligent analysis and prediction capabilities of the financial reimbursement system can be improved, and valuable financial management suggestions can be provided to enterprises.

[0029] Specifically, a reimbursement request, i.e., a data processing request sent by a client, is received. By extracting the data information to be processed in the request and inputting the data information to be processed into a trained model, the model can automatically predict the type of economic item to be reimbursed and the corresponding reimbursement entry based on the characteristics of the input data information to be processed. At the same time, the relevant fields of the reimbursement document are automatically filled in according to the prediction results, and the first document of the meaning, expense category, account code and other fields can be generated, and the first document is sent to the client.

[0030] In the technical solution of the present invention, an electronic device is provided, including a processor and a memory, the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the financial accounting data processing method as described in any one of the above technical solutions are implemented.

[0031] The third aspect of the present invention provides an electronic device, including a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the financial accounting data processing method in any one of the above technical solutions are implemented. Therefore, the electronic device has all the beneficial effects of the financial accounting data processing method in any one of the above technical solutions.

[0032] In the technical solution of the present invention, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the financial accounting data processing method as described in any one of the above technical solutions are implemented.

[0033] A fourth aspect of the present invention provides a readable storage medium having a program or instruction stored thereon, which, when executed by a processor, implements the steps of the financial accounting data processing method in any one of the above technical solutions. Therefore, the readable storage medium has all the beneficial effects of the financial accounting data processing method in any one of the above technical solutions.

[0034] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which: Figure 1 is a flow chart of a method for processing financial accounting data according to an embodiment of the present invention; Figure 2 A structural block diagram of a financial accounting data processing device according to an embodiment of the present invention; Figure 3 is a structural block diagram of an electronic device according to an embodiment of the present invention; Figure 4 The figure is a schematic block diagram of a financial accounting data processing device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0037] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0038] Refer to the following Figures 1 to 4 A financial accounting data processing method, a financial accounting data processing device, an electronic device, and a readable storage medium according to some embodiments of the present invention are described.

[0039] like Figure 1 As shown, in an embodiment of the present application, a financial reimbursement data processing method is provided, and the financial reimbursement data processing method is used in a server, and the financial reimbursement data processing method includes: Step 102: calling the first data stored in the server; Step 104: extracting a feature set from the first data to obtain a first feature set; Step 106: training the initial classification model using the first feature set to obtain a data classification model; Step 108: extracting the data information to be processed in the data processing request when receiving the data processing request sent by the client; Step 110: Generate a first document based on the data information to be processed and the data classification model, and send the first document to the client; The first data includes at least one of invoice, reimbursement form and payment voucher.

[0040] The present application provides a financial reimbursement data processing method, which is used for a server. The financial reimbursement data processing method includes: the server can automatically call or obtain historical data related to financial reimbursement, that is, call the first data stored in the server. The first data includes at least one of the three types of invoices, reimbursement forms, and payment vouchers. Based on the first data, the accuracy of financial reimbursement can be improved and the error probability can be reduced. After obtaining the first data, extract the feature set in the first data to obtain the first feature set. The feature engineering technology can be used to extract the features related to financial reimbursement, and the features are output as a feature set, that is, the first feature set. The first feature set includes multiple information such as invoice type, date, buyer and seller information, amount, invoice type, commodity description, etc. After obtaining the first feature set, the initial classification model can be trained by the first feature set to obtain a data classification model; when receiving a data processing request sent by a client, extract the data information to be processed in the data processing request; based on the data information to be processed and the data classification model, generate a first document, and send the first document to the client.

[0041] By introducing a data classification model based on a lightweight machine learning algorithm to classify data, the type of economic items to be reimbursed and the corresponding reimbursement entry can be automatically predicted based on the characteristics of the input data, avoiding filling errors caused by manual intervention in classification, reducing the probability of errors, and improving the audit efficiency of financial reimbursement data. It can improve the intelligent analysis and prediction capabilities of the financial reimbursement system, and thus provide valuable financial management suggestions for enterprises.

[0042] Specifically, a reimbursement request, i.e., a data processing request sent by a client, is received. By extracting the data information to be processed in the request and inputting the data information to be processed into a trained model, the model can automatically predict the type of economic item to be reimbursed and the corresponding reimbursement entry based on the characteristics of the input data information to be processed. At the same time, the relevant fields of the reimbursement document are automatically filled in according to the prediction results, and the first document of the meaning, expense category, account code and other fields can be generated, and the first document is sent to the client.

[0043] Specifically, the client side can provide an intuitive and easy-to-use user interface to display the prediction results and automatically filled billing documents for users to confirm or adjust. At the same time, user feedback is collected to continuously optimize the algorithm model and improve the intelligence level of the system and user satisfaction.

[0044] This embodiment provides a method for processing financial accounting data. In addition to the technical features of the above embodiments, this embodiment further includes the following technical features.

[0045] Extracting a feature set from the first data to obtain the first feature set includes: preprocessing the first data to obtain a preprocessed data set; extracting a feature set from the preprocessed data set to obtain the first feature set.

[0046] In this embodiment, extracting a feature set from the first data to obtain the first feature set includes: preprocessing the first data to obtain a preprocessed data set; extracting a feature set from the preprocessed data set to obtain the first feature set. By preprocessing the first data, the processing efficiency of subsequent data can be improved, and the accuracy of data prediction can be improved.

[0047] Specifically, by preprocessing the data, you can filter out features that have a greater impact on the analysis results, reduce the data dimension, and improve the analysis efficiency. When classifying data, by preprocessing the data, you can adjust the data category distribution and improve the accuracy of the model's prediction of data categories.

[0048] This embodiment provides a method for processing financial accounting data. In addition to the technical features of the above embodiments, this embodiment further includes the following technical features.

[0049] Based on the data information to be processed and the data classification model, a first document is generated, and the first document is sent to the client, including: based on the data information to be processed and the data classification model, obtaining first prediction data; obtaining an initial document template; filling the first prediction data into the initial document template to generate a first document, and sending the first document to the client.

[0050] In this embodiment, based on the data information to be processed and the data classification model, a first document is generated and the first document is sent to the client, including: based on the data information to be processed and the data classification model, obtaining the first prediction data; obtaining the initial document template; filling the first prediction data into the initial document template to generate the first document, and sending the first document to the client. When receiving a reimbursement request, that is, a data processing request, by extracting the data information to be processed in the request and inputting the data information to be processed into a trained model, the model can automatically predict the type of economic item to be reimbursed and the corresponding reimbursement entry according to the characteristics of the input data information to be processed, that is, automatically fill the information into the initial document template to generate the first document. According to the prediction results, the relevant fields of the reimbursement document are automatically filled, so that the first document with fields such as meaning, expense category and account code can be generated, and the first document is sent to the client, so as to realize intelligent recognition and classification of reimbursement requests and improve the efficiency and accuracy of reimbursement processing.

[0051] This embodiment provides a method for processing financial accounting data. In addition to the technical features of the above embodiments, this embodiment further includes the following technical features.

[0052] After generating a first document based on the data information to be processed and the data classification model, and sending the first document to the client, the financial accounting data processing method also includes: upon receiving an adjustment request sent by the client, extracting adjustment information in the adjustment request; adjusting the data information in the first document according to the adjustment information to generate a second document, and sending the second document to the client.

[0053] In this embodiment, after generating a first document based on the data information to be processed and the data classification model, and sending the first document to the client, the financial accounting data processing method further includes: extracting adjustment information in the adjustment request when receiving an adjustment request sent by the client; adjusting the data information in the first document according to the adjustment information to generate a second document, and sending the second document to the client. If the user does not adjust the content of the first document, the first document can be directly output. At the same time, when the user needs to adjust the document, the adjustment information in the adjustment request can be extracted, and the data information in the first document can be adjusted according to the adjustment information, which is convenient for users to use and improves the flexibility and accuracy of the system.

[0054] This embodiment provides a method for processing financial accounting data. In addition to the technical features of the above embodiments, this embodiment further includes the following technical features.

[0055] After generating a first document based on the data information to be processed and the data classification model, and sending the first document to the client, the financial accounting data processing method also includes: extracting the update data in the update request when an update request sent by the client is received; and updating and training the data classification model based on the update data to obtain an updated data classification model.

[0056] In this embodiment, after generating a first document based on the data information to be processed and the data classification model, and sending the first document to the client, the financial accounting data processing method further includes: extracting the update data in the update request when receiving the update request sent by the client; and updating and training the data classification model based on the update data to obtain the updated data classification model. The update request of user feedback is collected, and based on the update request, the data classification model is updated and trained through the update data to obtain the updated data classification model, so as to realize the continuous optimization of the algorithm model and improve the intelligence level of the system and user satisfaction.

[0057] This embodiment provides a method for processing financial accounting data. In addition to the technical features of the above embodiments, this embodiment further includes the following technical features.

[0058] Based on the data information to be processed and the data classification model, a first document is generated, and the first document is sent to the client, including: obtaining user personal information and second data according to the data information to be processed; based on the user personal information, the second data and the data classification model, a first document is generated, and the first document is sent to the client.

[0059] In this embodiment, based on the data information to be processed and the data classification model, a first document is generated, and the first document is sent to the client, including: obtaining user personal information and second data according to the data information to be processed; generating a first document based on the user personal information, the second data and the data classification model, and sending the first document to the client. That is, in the financial reimbursement data processing method provided by this application, the user's personal information can be combined with historical data, a user portrait can be drawn through a data classification model, and the reimbursement information can be automatically identified and filled in according to information such as invoices. Finally, the user chooses to confirm or change on the client, thereby realizing the processing of the financial reimbursement data. After the user feedback, the data classification model can also be updated according to the user's feedback.

[0060] This embodiment provides a method for processing financial accounting data. In addition to the technical features of the above embodiments, this embodiment further includes the following technical features.

[0061] The second data is data related to financial accounting.

[0062] In this embodiment, the second data is data related to financial reimbursement, that is, the reimbursement request input by the user through the client, and the data related to financial reimbursement is extracted from the reimbursement request. By inputting the second data into the trained model, the model automatically predicts the type of economic item for reimbursement and the corresponding reimbursement entry according to the input features. At the same time, the relevant fields of the reimbursement document, such as expense category, account code, etc., are automatically filled according to the prediction results.

[0063] The financial reimbursement data processing method provided in the present application introduces a data classification model based on a lightweight machine learning algorithm, which can be a simplified version of Gradient Boosting Decision Tree, GBDT (gradient boosting decision tree) or a lightweight reimbursement classification model of a random forest algorithm.

[0064] Specifically, taking the random forest algorithm as an example, in the embodiments of this application: First, you can load the training data set train_data and the test data set test_data; Among them, the training data set contains invoice images, invoice texts and corresponding economic matter labels.

[0065] Then, the model is built using the Random Forest algorithm: from sklearn.ensemble import RandomForestClassifier; from sklearn.model_selection import train_test_split; from sklearn.feature_extraction.text import TfidfVectorizer; Convert invoice text into TF-IDF features: vectorizer = TfidfVectorizer(); X_train_text = vectorizer.fit_transform(train_data['text']); X_test_text = vectorizer.transform(test_data['text']); Use the economic event label as the target variable: y_train = train_data['label']; Create a random forest model: clf = RandomForestClassifier(n_estimators=100,random_state=42); clf.fit(X_train_text, y_train); Make predictions on the test data: y_pred = clf.predict(X_test_text); Output prediction results and accuracy evaluation: print("Prediction accuracy:", clf.score(X_test_text, test_data['label'])); Specifically, in practical applications, invoice images can be converted into text, features can be converted using the same vectorizer, and then input into the trained model for automatic recognition of economic matters.

[0066] like Figure 2 As shown, in an embodiment of the present invention, a financial accounting data processing device 200 is provided. The financial accounting data processing device 200 is used for a server. The financial accounting data processing device 200 includes a calling module 210 and an acquisition module 220. The calling module 210 is used to call the first data stored in the server; the acquisition module 220 is used to extract the feature set in the first data and obtain the first feature set; the acquisition module 220 is also used to train the initial classification model through the first feature set to obtain the data classification model; the acquisition module 220 is also used to extract the data information to be processed in the data processing request when receiving the data processing request sent by the client; the acquisition module 220 is also used to generate a first document based on the data information to be processed and the data classification model, and send the first document to the client.

[0067] The present application provides a financial reimbursement data processing device 200, including a calling module 210 and an acquisition module 220, wherein the calling module 210 is used to call the first data stored in the server; the acquisition module 220 is used to extract the feature set in the first data and obtain the first feature set; the acquisition module 220 is also used to train the initial classification model through the first feature set to obtain the data classification model; the acquisition module 220 is also used to extract the pending data information in the data processing request when receiving the data processing request sent by the client; the acquisition module 220 is also used to generate a first document based on the pending data information and the data classification model, and send the first document to the client. By introducing a data classification model based on a lightweight machine learning algorithm to classify the data, the economic item type and the corresponding reimbursement entry of the reimbursement can be automatically predicted according to the characteristics of the input data, avoiding filling errors caused by manual intervention in the classification, reducing the error probability, and improving the audit efficiency of the financial reimbursement data. The intelligent analysis and prediction capabilities of the financial reimbursement system can be improved, and valuable financial management suggestions can be provided to enterprises.

[0068] Specifically, a reimbursement request, i.e., a data processing request sent by a client, is received. By extracting the data information to be processed in the request and inputting the data information to be processed into a trained model, the model can automatically predict the type of economic item to be reimbursed and the corresponding reimbursement entry based on the characteristics of the input data information to be processed. At the same time, the relevant fields of the reimbursement document are automatically filled in according to the prediction results, and the first document of the meaning, expense category, account code and other fields can be generated, and the first document is sent to the client.

[0069] like Figure 3 As shown, in an embodiment of the present invention, an electronic device 300 is provided, including a processor 304 and a memory 302, the memory 302 stores programs or instructions that can be executed on the processor 304, and when the programs or instructions are executed by the processor 304, the steps of the financial accounting data processing method as in any one of the above embodiments are implemented.

[0070] The electronic device 300 provided in the present application includes a processor 304 and a memory 302. The memory 302 stores a program or instruction that can be run on the processor 304. When the program or instruction is executed by the processor 304, the steps of the financial reimbursement data processing method in any one of the above embodiments are implemented. Therefore, the electronic device 300 has all the beneficial effects of the financial reimbursement data processing method in any one of the above embodiments.

[0071] In an embodiment of the present invention, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the financial accounting data processing method as described in any one of the above embodiments are implemented.

[0072] The present application provides a readable storage medium on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the financial accounting data processing method in any one of the above embodiments are implemented. Therefore, the readable storage medium has all the beneficial effects of the financial accounting data processing method in any one of the above embodiments.

[0073] like Figure 4 As shown, when processing financial reimbursement data, the financial reimbursement data processing device 400 includes a smart reimbursement entry, and the smart reimbursement entry has relevant modules for guiding reimbursement, including an entry for task recommendation reimbursement, an entry for historical recommendation reimbursement, an entry for template reimbursement, and an entry for invoice recognition reimbursement. The above processing of input financial data is completed based on lightweight algorithms, that is, by introducing lightweight algorithms such as GBDT and random forest algorithms, user personal information is combined with reimbursement history data to draw user portraits, and reimbursement information is automatically identified and filled in based on invoice information, and the algorithm model is continuously optimized based on user confirmation or feedback data.

[0074] In the claims, specification and drawings of the present invention, the term "multiple" refers to two or more than two. Unless otherwise clearly defined, the orientation or positional relationship indicated by the terms "upper" and "lower" is based on the orientation or positional relationship shown in the drawings, which is only for the purpose of more conveniently describing the present invention and making the description process simpler, rather than indicating or implying that the device or element referred to must have the specific orientation described, be constructed and operated in a specific orientation, so these descriptions cannot be understood as limiting the present invention; the terms "connect", "install", "fix" and the like should be understood in a broad sense. For example, "connection" can be a fixed connection between multiple objects, or a detachable connection between multiple objects, or an integral connection; it can be a direct connection between multiple objects, or an indirect connection between multiple objects through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood based on the specific circumstances of the above data.

[0075] In the claims, specification and drawings of the present invention, the description of the terms "one embodiment", "some embodiments", "specific embodiments" and the like means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In the claims, specification and drawings of the present invention, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0076] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for processing financial accounting data, characterized in that: The financial reimbursement data processing method is used in a server, and the financial reimbursement data processing method includes: Calling the first data stored in the server; Extracting a feature set from the first data to obtain a first feature set; Training the initial classification model using the first feature set to obtain a data classification model; When receiving a data processing request sent by a client, extracting the data information to be processed in the data processing request; Generate a first document based on the data information to be processed and the data classification model, and send the first document to the client; The first data includes at least one of an invoice, a reimbursement form, and a payment voucher.

2. The financial accounting data processing method according to claim 1, characterized in that: The extracting the feature set from the first data to obtain the first feature set includes: Preprocessing the first data to obtain a preprocessed data set; A feature set is extracted from the preprocessed data set to obtain a first feature set.

3. The financial accounting data processing method according to claim 1, characterized in that: The step of generating a first document based on the data information to be processed and the data classification model, and sending the first document to the client includes: Based on the data information to be processed and the data classification model, obtaining first prediction data; Get the initial document template; The first forecast data is filled into the initial document template to generate a first document, and the first document is sent to a client.

4. The financial accounting data processing method according to claim 1, characterized in that: After generating a first document based on the data information to be processed and the data classification model, and sending the first document to the client, the financial accounting data processing method further includes: When receiving an adjustment request sent by the client, extracting adjustment information in the adjustment request; According to the adjustment information, the data information in the first document is adjusted to generate a second document, and the second document is sent to the client.

5. The financial accounting data processing method according to claim 1, characterized in that: After generating a first document based on the data information to be processed and the data classification model, and sending the first document to the client, the financial accounting data processing method further includes: Upon receiving an update request sent by the client, extracting update data in the update request; Based on the updated data, the data classification model is updated and trained to obtain an updated data classification model.

6. The financial accounting data processing method according to claim 3, characterized in that: The step of generating a first document based on the data information to be processed and the data classification model, and sending the first document to the client includes: According to the data information to be processed, obtaining user personal information and second data; Based on the user personal information, the second data and the data classification model, a first receipt is generated and sent to a client.

7. The financial accounting data processing method according to claim 6, characterized in that: The second data is data related to financial accounting.

8. A financial accounting data processing device, characterized in that: The financial reimbursement data processing device is used in a server, and the financial reimbursement data processing device comprises: A calling module, used for calling the first data stored in the server; An acquisition module, used for extracting a feature set from the first data to acquire a first feature set; The acquisition module is further used to train the initial classification model through the first feature set to obtain a data classification model; The acquisition module is also used to extract the data information to be processed in the data processing request when receiving the data processing request sent by the client; The acquisition module is also used to generate a first document based on the data information to be processed and the data classification model, and send the first document to the client.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the financial accounting data processing method as described in any one of claims 1 to 7 are implemented.

10. A readable storage medium having a program or instruction stored thereon, characterized in that: When the program or instruction is executed by a processor, the steps of the financial accounting data processing method according to any one of claims 1 to 7 are implemented.

Images