Intelligent business and financial management method and system based on AI algorithm model

Abstract

The invention provides an intelligent business and financial management method and system based on an AI algorithm model, and provides an intelligent business and financial management mode. And learning and constructing a business and financial intelligent management AI model capable of identifying business characteristics (settlement characteristics and / or delivery behavior characteristics) of different clients / suppliers. The model is used for carrying out intelligent identification on settlement or delivery on data blocks in different stages in the business data, and the system intelligently and automatically completes settlement processing and / or delivery processing of the business data and generates a corresponding settlement report and / or delivery report; and finally, integrating the settlement report and / or the delivery report of each data block to obtain financial data. Therefore, intelligent identification and processing of the business data can be realized, manual operation is replaced, the business finance and tax processing efficiency is improved, the business data accessed by the front end is automatically refined and classified, financial statistics is conveniently classified, and the accounting statement progress is improved.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to an intelligent business and financial management method and system based on an AI algorithm model, an electronic device, and a computer-readable storage medium. Background Art

[0002] As attached Figure 1 As shown in the figure, the technical principle of realizing "business-finance integration" in the existing "business-finance integration" software on the market is generally to configure different accounting voucher templates according to different business types. In this way, when business personnel enter business data such as "orders" and "collections and payments", the system will regenerate "financial data" based on the template.

[0003] Although in the prior art, business data can be manipulated using accounting voucher templates, etc., it still mainly relies on manual operations by accountants, and the conversion and generation between business and finance needs to be classified and processed, and finally confirmed by accountants. This method is suitable for small-scale businesses of small-scale companies, but it is stretched to the limit when facing batches of business data, and cannot meet the efficient processing of large-scale business data sets. In addition, it is impossible to automatically refine and classify the business data accessed by the front end, and it is necessary to manually organize the business data before manual operations, which will delay the progress of accounting reports.

[0004] In addition, the traditional method requires accountants to intervene and use their professional knowledge to compile "financial data" based on actual business situations, which also brings high labor costs and low efficiency. Administrators cannot monitor accounting operation logs in real time and cannot supervise their accounting work. Summary of the invention

[0005] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions: On the one hand, a business and financial intelligent management method based on an AI algorithm model is provided, the method is implemented by an electronic device, and the method includes: S1. Obtain business data from the front end, use the LLM large language model to filter the business data based on the large language model prompt words, and separate the business data into several sub-business data blocks of different business stages; S2. Importing each of the sub-business data blocks into a pre-deployed business and finance intelligent management AI model in sequence, and having the business and finance intelligent management AI model identify and output the settlement characteristics and / or delivery behavior characteristics of the sub-business data blocks; S3. Based on the settlement characteristics and / or the delivery behavior characteristics, the corresponding settlement rule template and / or delivery rule is directed to be called, settlement processing and / or delivery processing is automatically performed on the sub-business data block, and a corresponding settlement report and / or delivery report is generated; S4. Output and integrate the settlement report and / or the delivery report of each of the sub-business data blocks to obtain financial data corresponding to the business data.

[0006] Preferably, S1, obtaining business data from the front end, using the LLM large language model based on the large language model prompt words to filter the business data, and separating the business data into a number of sub-business data blocks of different business stages, including: Pre-build phase keywords and division logic corresponding to different business attributes; Combining the phase keywords and the segmentation logic, constructing the large language model prompt words and inputting them into the pre-loaded LLM large language model; The business data is traversed by the LLM large language model, and business data of different business stages are identified on the business data based on the large language model prompt words, and business data belonging to different business stages are separated to obtain the sub-business data blocks of several different business stages; Output and save the sub-business data blocks corresponding to different business stages.

[0007] Preferably, the method for generating the business and financial intelligent management AI model includes: Collect historical business, finance and tax processing big data of several customers / suppliers, including historical business data sets of each customer / supplier and corresponding historical settlement data sets and historical delivery behaviors; Performing feature engineering on the historical business, finance and tax processing big data to extract business, finance and tax data features of each customer / supplier, wherein the business, finance and tax data features include: extracting the identity and business transaction type of the corresponding customer / supplier from the historical business data set, and / or extracting the corresponding settlement features from the historical business data set, and / or extracting the corresponding delivery behavior features from the historical delivery behavior; The business, finance and taxation data features are marked with a template IP corresponding to the settlement features or a delivery rule corresponding to the delivery behavior features, wherein the template IP is used to define the storage address of the corresponding settlement rule template; Count and label the business, finance and tax data features of each customer / supplier and form a feature set; Dividing the feature set into a training set and a validation set according to a preset ratio; Input the training set into a preset random forest model to perform feature training and learning, and construct and generate the business and financial intelligent management AI model; The feature recognition performance of the business and financial intelligent management AI model is verified using the delivery verification set: If the verification is successful, the business and financial intelligent management AI model is deployed and applied; If the verification fails, repeat the above steps to retrain and build the business and financial intelligent management AI model.

[0008] Preferably, after feature engineering is performed on the historical business, finance and tax processing big data to extract the business, finance and tax data features of each customer / supplier, the method further includes: Determine whether the business, finance and taxation data characteristics of each customer / supplier at least include the settlement characteristics and / or the delivery behavior characteristics: If so, the included features are labeled with corresponding identity tags and transaction type tags; If not, delete the business, finance and taxation data characteristics described in this article.

[0009] Preferably, S3, based on the settlement characteristics and / or the delivery behavior characteristics, the corresponding settlement rule template and / or delivery rule is directed to be called, settlement processing and / or delivery processing is automatically performed on the sub-business data block, and a corresponding settlement report and / or delivery report is generated, including: Read the marked information on the settlement feature or the delivery behavior feature, and obtain the corresponding template IP and / or delivery rules marked on the business, finance and taxation data feature; Through the storage address of the template IP1, the preset settlement rule template is called from the corresponding storage location, and the sub-business data block is written into the settlement rule template, and the corresponding settlement report is automatically calculated and generated; and / or, According to the delivery rules, a delivery report for the sub-business data block is generated and sent to the corresponding delivery end.

[0010] On the other hand, a business and financial intelligent management system based on an AI algorithm model is provided, and the business and financial intelligent management system based on the AI ​​algorithm model is used to implement the business and financial intelligent management method based on the AI ​​algorithm model described above, and the system includes: A business screening module is used to obtain business data from the front end, screen the business data based on the large language model prompt words using the LLM large language model, and separate the business data into several sub-business data blocks of different business stages; A business feature processing module, used to import each of the sub-business data blocks into a pre-deployed business and financial intelligent management AI model in sequence, so that the business and financial intelligent management AI model identifies and outputs the settlement features and / or delivery behavior features of the sub-business data blocks; A business and financial automation execution module, for invoking the corresponding settlement rule template and / or delivery rule based on the settlement characteristics and / or the delivery behavior characteristics, automatically performing settlement processing and / or delivery processing on the sub-business data block, and generating a corresponding settlement report and / or delivery report; The integration module is used to output and integrate the settlement report and / or the delivery report of each sub-business data block to obtain financial data corresponding to the business data.

[0011] On the other hand, an electronic device is provided, comprising: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned intelligent business and financial management methods based on the AI ​​algorithm model is implemented.

[0012] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned intelligent business and financial management methods based on the AI ​​algorithm model.

[0013] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: The present invention proposes an intelligent business, finance and tax management model. Through the historical business, finance and tax processing big data of each customer / supplier, it learns and builds an intelligent business and finance management AI model that can identify the business characteristics (settlement characteristics and / or delivery behavior characteristics) of different customers / suppliers. The model is used to intelligently identify the settlement or delivery of data blocks at different stages in the business data. The system intelligently and automatically completes the settlement processing and / or delivery processing of the business data and generates corresponding settlement reports and / or delivery reports. Finally, the settlement reports and / or delivery reports of each data block are generated and integrated to obtain financial data. Therefore, it is possible to realize the intelligent identification and processing of business data, replace manual operations and improve the processing efficiency of business, finance and taxation, and automatically refine and classify the business data accessed by the front end, facilitate classification for financial statistics, and improve the progress of accounting reports. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 It is a logical diagram of manual accounting operations in traditional schemes; Figure 2 This is a flow chart of a business and financial intelligent management method based on an AI algorithm model provided by an embodiment of the present invention; Figure 3 It is a logical schematic diagram of a business data screening process using an LLM large language model provided by an embodiment of the present invention; Figure 4It is a schematic diagram of a generation process of a business and financial intelligent management AI model provided by an embodiment of the present invention; Figure 5 It is a block diagram of a business and financial intelligent management system based on an AI algorithm model provided by an embodiment of the present invention; Figure 6 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0017] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0018] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0019] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0020] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0021] The embodiment of the present invention provides a business and financial intelligent management method based on an AI algorithm model, which can be implemented by an electronic device, which can be a terminal or a server. Figure 2 The flowchart of the business and financial intelligent management method based on the AI ​​algorithm model is shown, and the processing flow of the method may include the following steps: S1. Obtain business data from the front end, use the LLM large language model to filter the business data based on the large language model prompt words, and separate the business data into several sub-business data blocks of different business stages; S2. Importing each of the sub-business data blocks into a pre-deployed business and finance intelligent management AI model in sequence, and having the business and finance intelligent management AI model identify and output the settlement characteristics and / or delivery behavior characteristics of the sub-business data blocks; S3. Based on the settlement characteristics and / or the delivery behavior characteristics, the corresponding settlement rule template and / or delivery rule is directed to be called, settlement processing and / or delivery processing is automatically performed on the sub-business data block, and a corresponding settlement report and / or delivery report is generated; S4. Output and integrate the settlement report and / or the delivery report of each of the sub-business data blocks to obtain financial data corresponding to the business data.

[0022] The present invention uses the historical business, finance and tax processing big data of each customer / supplier to learn and build a business and finance intelligent management AI model that can identify the business characteristics (settlement characteristics and / or delivery behavior characteristics) of different customers / suppliers. The model is used to intelligently identify the settlement or delivery of data blocks at different stages in the business data, and the system intelligently and automatically completes the settlement processing and / or delivery processing of the business data and generates the corresponding settlement report and / or delivery report. Finally, the settlement report and / or delivery report of each data block is used to obtain financial data.

[0023] The implementation principles of each step of the specific model are described below.

[0024] like Figure 3 As shown, preferably, S1, obtain business data from the front end, use the LLM large language model based on the large language model prompt words to filter the business data, and separate the business data into several sub-business data blocks of different business stages, including: Pre-build phase keywords and division logic corresponding to different business attributes; Combining the phase keywords and the segmentation logic, constructing the large language model prompt words and inputting them into the pre-loaded LLM large language model; The business data is traversed by the LLM large language model, and business data of different business stages are identified on the business data based on the large language model prompt words, and business data belonging to different business stages are separated to obtain the sub-business data blocks of several different business stages; Output and save the sub-business data blocks corresponding to different business stages.

[0025] Because the business data input by the front end, such as an order, involves installment payments or executing the debit and credit income and expenditure of the order business in multiple stages. Take the engineering industry as an example: If a renovation engineering company receives a 1 million project (with a 9% special invoice), it needs to enter an "income order (or contract)" into the system. The contract stipulates that the payment will be made in two installments: 30% upon completion of the demolition and the remaining 70% upon completion of the entire project.

[0026] 10 days after the project started, the demolition was completed. At this time, the project manager of the decoration company needs to click "Settlement" in the system, and the settlement amount is "0.3". At this time, the "Financial Data" is generated: Debit: Accounts receivable 300,000; Credit: Accounts received in advance - deferred income 273,000; Credit: Taxes payable - VAT payable 27,000; At this time, a "receivable" of 300,000 is generated in the system. Then, you can issue an invoice to the customer and collect the payment at the agreed time.

[0027] Since the project has been completed by 30%, 30% of the revenue can be confirmed financially, so the project manager only needs to click "delivery" and enter a delivery order to confirm 30% of the revenue. Write down: Debit: Accounts received in advance - deferred income 273,000; Loan: Main business income: RMB 273,000.

[0028] Therefore, we separate the business data of different stages (that is, the corresponding sub-business data blocks) here to facilitate the subsequent segmentation of business accounting reports for each stage and to help administrators view the income, expenditure, and borrowing and lending situations of the corresponding stages.

[0029] We use a big language model to separate data. We can load the big language model on the accounting system or call a third-party big language model (such as Wenxinyiyan) through the API. In order to implement the technical solution of obtaining business data from the front end, filtering the business data based on business attribute prompt words using LLM (Large Language Model), and then separating the business data into several sub-business data blocks of different business stages, you can refer to the following steps: 1. Front-end data acquisition ‌Interface design‌: Design the data interaction interface between the front-end and the back-end to ensure that the front-end can smoothly send business data to the back-end for processing.

[0030] The interface should support multiple data formats (such as JSON, XML, etc.) to meet the needs of different front-end technologies.

[0031] ‌Data sending‌: When front-end users perform relevant operations (such as submitting forms, clicking buttons, etc.), the front-end code should capture these operations and collect corresponding business data.

[0032] Through the designed interface, the collected business data is sent to the back-end server in the form of a request.

[0033] 2. LLM Large Language Model Screening Data ‌Model loading‌: Load the pre-trained LLM large language model on the backend server. The model should have the ability to understand and process natural language text.

[0034] ‌Business attribute prompt word definition‌: Define a set of business attribute prompt words according to business needs. These prompt words should correspond to the attributes of each stage of business data and be used to guide the model on how to filter and classify data.

[0035] For example, for sales business, prompt words may include "order number", "customer name", "product name", "transaction amount", "installment payment keywords", etc.

[0036] The division logic, for example, is based on three installment payments.

[0037] ‌Data Filter‌: The business data obtained from the front end is input into the LLM large language model.

[0038] The model understands and analyzes business data based on business attribute prompt words, and filters out data fragments related to each prompt word.

[0039] 3. Data Separation and Sub-Business Data Block Generation ‌Data separation logic‌: Design data separation logic based on the screening results of the LLM large language model.

[0040] This logic should combine the filtered data fragments into sub-business data blocks for different business stages based on the business process and business stages.

[0041] By combining keywords and logic to construct prompt words, you can construct several prompt words in combination and input them into the model, allowing the model to poll and separate the business data; then integrate the results into sub-data blocks at different stages to improve efficiency.

[0042] And the sub-business data block generates: According to the data separation logic, several sub-business data blocks for different business stages are generated.

[0043] Each sub-business data block should contain all relevant data for that stage to facilitate subsequent processing and analysis.

[0044] ‌Data Storage and Access‌: The generated sub-business data blocks are stored in a database or file system for subsequent access and processing.

[0045] Design corresponding data access interfaces so that other systems or modules can easily obtain and use these sub-business data blocks.

[0046] ‌Model update and optimization‌: As the business develops and changes, the LLM large language model should be updated and optimized in a timely manner to ensure that it can accurately understand and process new business data.

[0047] Regularly evaluate the performance of the model and make adjustments and optimizations based on the evaluation results.

[0048] Regularly maintain and upgrade the system to ensure its continuous and stable operation.

[0049] Through the implementation of the above technical solutions, it is possible to obtain business data from the front end, and use the LLM large language model to filter and separate business data to generate sub-business data blocks for different business stages. This will provide strong support for subsequent business processing and analysis, and improve the efficiency and accuracy of the company's business processing.

[0050] like Figure 4 As shown, preferably, the method for generating the business and financial intelligent management AI model includes: Collect historical business, finance and tax processing big data of several customers / suppliers, including historical business data sets of each customer / supplier and corresponding historical settlement data sets and historical delivery behaviors; Performing feature engineering on the historical business, finance and tax processing big data to extract business, finance and tax data features of each customer / supplier, wherein the business, finance and tax data features include: extracting the identity and business transaction type of the corresponding customer / supplier from the historical business data set, and / or extracting the corresponding settlement features from the historical business data set, and / or extracting the corresponding delivery behavior features from the historical delivery behavior; The business, finance and taxation data features are marked with a template IP corresponding to the settlement features or a delivery rule corresponding to the delivery behavior features, wherein the template IP is used to define the storage address of the corresponding settlement rule template; Count and label the business, finance and tax data features of each customer / supplier and form a feature set; Dividing the feature set into a training set and a validation set according to a preset ratio; Input the training set into a preset random forest model to perform feature training and learning, and construct and generate the business and financial intelligent management AI model; The feature recognition performance of the business and financial intelligent management AI model is verified using the delivery verification set: If the verification is successful, the business and financial intelligent management AI model is deployed and applied; If the verification fails, repeat the above steps to retrain and build the business and financial intelligent management AI model.

[0051] The present invention processes business, finance and taxation big data based on historical business data, and realizes intelligent business, finance and taxation identification and processing of input business data, automatic settlement / delivery, and generation of AI algorithm models for financial data.

[0052] When processing the debit and credit income and expenditure of a certain business data, the corresponding settlement data and delivery mode will be recorded. Therefore, the present invention utilizes the business, finance and taxation data characteristics of massive business data to conduct model training and construction, so as to construct an AI model that can identify the settlement characteristics and delivery behavior characteristics of business data, which will facilitate the subsequent intelligent and automated settlement and delivery identification of business data, and assist the system to automatically complete settlement and delivery.

[0053] In order to refine and execute the above model training scheme, you can refer to the following detailed steps to build a business and financial intelligent management AI model: 1. Data Collection and Preparation ‌Data Collection‌: Collect historical financial and tax processing big data of several customers / suppliers from the company's ERP system, CRM system, financial software and other systems.

[0054] The data should include historical business data sets of each customer / supplier (such as order information, transaction records, etc.), historical settlement data sets (such as invoice information, payment records, etc.) and historical delivery behaviors (such as delivery time, delivery method, etc.).

[0055] ‌Data cleaning and integration‌: Clean the collected data to remove duplicate, erroneous or incomplete data.

[0056] Integrate the cleaned data into a unified data warehouse to ensure data integrity and consistency.

[0057] 2. Feature Engineering ‌Feature Extraction‌: Extract the corresponding customer / supplier identity (such as customer number, supplier name, etc.) and business transaction type (such as sales, procurement, etc.), settlement rules for different customers / suppliers (such as tax rates) and delivery behavior characteristics (delivery conditions, processes, delivery standards and objects, etc.) from historical business data sets.

[0058] Extract settlement characteristics, such as settlement tax rate, settlement method, settlement time, etc.

[0059] Extract delivery behavior characteristics, such as delivery time, delivery location, delivery method, delivery standards and objects, etc.

[0060] The feature extraction method or algorithm is determined by the administrator. For example, using the RF algorithm: select features related to settlement and delivery according to business needs. For example, settlement features may include settlement amount, settlement method, settlement date, etc.; delivery features may include delivery time, delivery location, delivery method, etc. Domain knowledge and business rules can be used to determine which features have the greatest impact on model performance. The selected features are further processed and processed to improve the performance of the model. For example, time features can be timestamp converted and categorical features can be one-hot encoded. New features such as settlement cycle and delivery delay can be created to enrich the feature set. Use the random forest model to extract features from the processed data. The random forest model is an ensemble learning method that extracts key features from the data by building multiple decision trees. During the model training process, the random forest automatically selects the most useful features for classification or regression tasks. These features can be regarded as settlement and delivery features of business data.

[0061] ‌Feature annotation‌: The extracted business, finance and tax data features are marked with the corresponding settlement feature template IP or delivery rules of the delivery behavior features. The template IP is used to point to the address where the settlement rule template is stored for subsequent calls. The template IP is bound to each feature and saved in the system. The settlement rule template can be constructed and saved according to habit, and can be constructed by referring to the settlement reports of various types of customers.

[0062] Make sure each feature is clearly labeled to facilitate model learning and recognition.

[0063] ‌Feature set assembly‌: The business, finance and tax data features of each customer / supplier are statistically labeled and organized into a feature set.

[0064] The feature set should contain all feature data used for model training.

[0065] 3. Dataset Division and Model Training ‌Dataset Division‌: The feature set is divided into a training set and a validation set according to a preset ratio (such as 70% training set and 30% validation set).

[0066] The training set is used for model training, and the validation set is used to verify model performance.

[0067] ‌Model Training‌: Select the preset random forest model as the training model.

[0068] The training set is input into the random forest model for feature training and learning.

[0069] Adjust model parameters and optimize model performance until the model achieves good performance on the training set.

[0070] 4. Model Validation and Deployment ‌Model Validation‌: The validation set is used to verify the feature recognition performance of the business and financial intelligent management AI model.

[0071] Evaluate the model's accuracy, recall, F1 score and other indicators on the validation set to ensure that the model has good generalization ability.

[0072] Model deployment and application: If the verification is passed, the business and financial intelligent management AI model will be deployed to the company's business system to realize intelligent business, financial and tax processing.

[0073] The model can be applied to scenarios such as automatic settlement, automatic delivery, and financial data generation to improve the efficiency and accuracy of the company's financial management.

[0074] ‌Model optimization and iteration‌: If the verification fails, analyze the reasons for the poor model performance, such as improper feature selection, unreasonable model parameter settings, etc.

[0075] Based on the analysis results, adjust feature engineering, model parameters, etc., and retrain and build the business and financial intelligent management AI model.

[0076] Continuously iterate and optimize the model until it meets business needs.

[0077] 5. Notes ‌Data Privacy Protection‌: During data processing and model training, we strictly comply with data privacy protection regulations to ensure customer / supplier data security.

[0078] ‌Model Interpretability‌: Choose a random forest model with interpretability to facilitate understanding of the model's decision-making process and output results.

[0079] ‌Performance Monitoring and Maintenance‌: After the model is deployed, the model performance should be monitored and evaluated regularly to ensure that the model continues to run stably.

[0080] Update and optimize the model in a timely manner according to business needs and market changes.

[0081] Through the above detailed execution steps, an efficient and accurate business and financial intelligent management AI model can be built and deployed to realize the intelligent and automated business, financial and tax processing.

[0082] The structure and training application of the random forest model will not be described in detail here.

[0083] Preferably, after feature engineering is performed on the historical business, finance and tax processing big data to extract the business, finance and tax data features of each customer / supplier, the method further includes: Determine whether the business, finance and taxation data characteristics of each customer / supplier at least include the settlement characteristics and / or the delivery behavior characteristics: If so, the included features are labeled with corresponding identity tags and transaction type tags; If not, delete the business, finance and taxation data characteristics described in this article.

[0084] Labeling different features (identity tags and transaction type tags) facilitates targeted accounting processing for major customers. The settlement rules and delivery methods used can be quickly determined for the business data of major customers according to their identity tags and transaction types. Later, it can be determined whether the features identified by the model have tags to perform differentiated settlement and delivery for certain major customers. The tagging method also facilitates users to perform special management on tagged customers.

[0085] Among the business, finance and tax data characteristics of each customer / supplier, at least one settlement characteristic or delivery characteristic must be retained (because a business order may be delivered directly). If none of them are present, they are invalid characteristics and should be deleted. When processing the business, finance and tax data characteristics of customers / suppliers, in order to effectively identify and mark data containing settlement characteristics and / or delivery behavior characteristics, the following steps can be followed: Step 1: Feature Check ‌Traversing the data‌: Go through the business, finance and tax data characteristics of each customer / supplier one by one.

[0086] ‌Inspect Features‌: For each piece of data, check whether it contains at least one settlement feature (such as settlement amount, settlement method, settlement date, etc.) or delivery behavior feature (such as delivery time, delivery location, delivery method, etc.).

[0087] Step 2: Feature marking and deletion ‌Features Exist‌: If the data contains at least one settlement characteristic or delivery behavior characteristic, the following actions are performed: The data is labeled with corresponding identity tags (such as customer number, supplier name, etc.) for subsequent identification.

[0088] At the same time, label the transaction type (such as sales, purchases, etc.) to distinguish different business types.

[0089] ‌Feature does not exist‌: If the data contains neither settlement features nor delivery behavior features, the business, finance and tax data features will be deleted. This is because these data are of no value for subsequent settlement and delivery analysis.

[0090] Step 3: Data organization and storage ‌Organize the data‌: Organize the labeled data into a structured format for subsequent processing and analysis.

[0091] ‌Storage Data‌: Store the organized data in a database or file system for subsequent access and use.

[0092] Through the above steps, the business, finance and taxation data characteristics containing settlement characteristics and / or delivery behavior characteristics can be effectively judged and marked, while deleting worthless data, providing strong support for subsequent business processing and analysis.

[0093] Preferably, S3, based on the settlement characteristics and / or the delivery behavior characteristics, the corresponding settlement rule template and / or delivery rule is directed to be called, settlement processing and / or delivery processing is automatically performed on the sub-business data block, and a corresponding settlement report and / or delivery report is generated, including: Read the marked information on the settlement feature or the delivery behavior feature, and obtain the corresponding template IP and / or delivery rules marked on the business, finance and taxation data feature; Through the storage address of the template IP1, the preset settlement rule template is called from the corresponding storage location, and the sub-business data block is written into the settlement rule template, and the corresponding settlement report is automatically calculated and generated; and / or, According to the delivery rules, a delivery report for the sub-business data block is generated and sent to the corresponding delivery end.

[0094] Combined with the application steps of the above-mentioned business and financial intelligent management AI model, it can be seen that the business and financial intelligent management AI model can be used to identify the business features of each sub-database (business data in the corresponding stage, generally one-time settlement and delivery, and this embodiment also gives priority to one-time settlement and delivery orders, etc.), and output corresponding feature annotations, so that the system can automatically complete the settlement and / or delivery of business data according to the settlement template or delivery rules in the annotations (here, settlement and delivery orders are prioritized).

[0095] As for the process of using the business and financial intelligent management AI model to identify the business characteristics of business data and output the corresponding characteristic information, please understand it in conjunction with the construction principles of the above-mentioned business and financial intelligent management AI model.

[0096] In order to refine and implement the solution of automatically performing settlement processing and / or delivery processing based on settlement characteristics and / or delivery behavior characteristics, the following detailed steps can be followed: 1. Preliminary preparation ‌Data Preparation‌: Ensure that all sub-business data blocks have completed feature extraction and are labeled with settlement features and / or delivery behavior features.

[0097] Settlement rule templates and delivery rules should be pre-defined and stored in a designated location.

[0098] ‌System Configuration‌: Configure the system to be able to read annotation information, access storage locations, perform calculation tasks, and send reports.

[0099] 2. Processing Flow 1. Read the annotation information ‌Traverse data blocks‌: Traverse the sub-business data blocks containing settlement characteristics and delivery behavior characteristics one by one.

[0100] ‌Read annotations‌: Read annotation information from the settlement characteristics or delivery behavior characteristics of each data block, and obtain the corresponding template IP (for settlement rule template) and delivery rules.

[0101] 2. Settlement Processing Template call: Use the template IP obtained from the annotation information to locate the location where the settlement rule template is stored.

[0102] Call the preset settlement rule template, which should contain calculation logic and report format.

[0103] ‌Data writing and calculation‌: Write the relevant data in the sub-business data block to the specified location of the settlement rule template.

[0104] According to the calculation logic in the template, the settlement amount, tax rate, discount, etc. are automatically calculated and a settlement report is generated.

[0105] ‌Report generation and storage‌: Make sure the settlement report contains all necessary information such as customer / supplier name, transaction type, settlement amount, etc.

[0106] Store the generated settlement report in a specified location for subsequent query and audit.

[0107] 3. Delivery Processing ‌Rules applied‌: Based on the delivery rules obtained from the annotation information, determine how to generate the delivery report and to whom it will be sent.

[0108] ‌Report Generation‌: According to the delivery rules, a delivery report is generated containing information such as delivery time, delivery location, and delivery items.

[0109] ‌Report delivery‌: Send the generated delivery report to the corresponding delivery end, such as customer mailbox, supplier system or internal logistics department.

[0110] Ensure the security and timeliness of the sending process.

[0111] 3. Subsequent Operations ‌Logging‌: Record the operation log of each settlement processing and delivery processing, including processing time, processing results, exception information, etc.

[0112] Exception handling: If an exception is encountered during the processing (such as data error, template cannot be called, etc.), the exception information should be automatically captured and recorded.

[0113] Depending on the exception type, take appropriate action, such as retry, manual intervention, or sending an error report.

[0114] ‌Performance Monitoring‌: Regularly monitor the performance of the processing flow, including processing speed, resource consumption, etc.

[0115] According to the monitoring results, the processing flow is optimized and adjusted.

[0116] ‌Data Archiving‌: The processed sub-business data blocks, settlement reports and delivery reports are archived and stored.

[0117] Ensure the integrity and queryability of archived data.

[0118] Through the implementation of the above-mentioned detailed steps, automated settlement processing and delivery processing based on settlement characteristics and / or delivery behavior characteristics can be achieved, thereby improving the efficiency and accuracy of business processing.

[0119] Based on the above steps, financial statements of business data can be generated to achieve intelligent conversion of business data into financial data.

[0120] If the business data contains sub-business data blocks of multiple stages, each sub-business data block will perform the above transformation process separately, and finally integrate the execution results of the sub-business data blocks of each stage. In order to achieve intelligent integration, this department still uses the LLM large language model for integration. Please refer to the following steps: Using LLM (Large Language Model) to integrate the settlement reports and / or delivery reports of each sub-business data block to obtain the financial data corresponding to the entire business data is an innovative and efficient solution. The following is a detailed implementation step: 1. Preliminary preparation ‌Data Preparation‌: Collect settlement reports and delivery reports of all sub-business data blocks and ensure that they are stored in structured or semi-structured formats such as Excel, CSV, JSON, etc.

[0121] Perform preliminary cleaning of the report to remove invalid or duplicate data.

[0122] ‌LLM Model Preparation‌: Select or train an LLM model suitable for financial data processing and ensure that it has the ability to understand, analyze and integrate complex financial data.

[0123] If you are using a pre-trained model, you need to fine-tune it to suit your specific financial data format and business logic.

[0124] Build data processing pipelines to ensure data can be smoothly input into the LLM model and output integrated financial data.

[0125] 2. Data Integration Process 1. Data input and analysis ‌Data input‌: Input the settlement reports and delivery reports of each sub-business data block into the LLM model.

[0126] ‌Data Parsing‌: Leverage the text understanding and parsing capabilities of the LLM model to identify and extract data from reports. This includes key fields such as transaction amount, transaction date, transaction type, customer / supplier information, etc.

[0127] 2. Data alignment and verification ‌Data alignment‌: Align the extracted data into a unified financial data framework based on business logic and data model. This may require dealing with data differences and format inconsistencies between different reports.

[0128] ‌Data Verification‌: Use the logical reasoning ability of the LLM model to verify the aligned data to ensure the accuracy and consistency of the data.

[0129] 3. Data integration and aggregation ‌Data integration‌: Integrate the verified data according to business logic to form a unified data set containing the financial information of all sub-business data blocks.

[0130] ‌Data aggregation‌: Aggregate the integrated data and calculate key financial indicators such as total revenue, total expenditure, and total profit.

[0131] 4. Data output and storage ‌Data Export‌: Export the consolidated financial data in a structured format such as Excel, CSV or a database table.

[0132] ‌Data Storage‌: Store the output financial data in a secure storage medium for subsequent query and analysis.

[0133] Regularly audit and verify the consolidated financial data to ensure its accuracy and completeness.

[0134] If problematic data is found, trace back and correct the source data or adjust the data processing logic in a timely manner.

[0135] Based on actual business needs and data processing results, the data processing capabilities and accuracy of the LLM model are continuously optimized.

[0136] Update the model regularly to adapt to business changes and changes in data formats.

[0137] 5. Data Visualization and Analysis: Use data visualization tools to display and analyze integrated financial data to help business personnel better understand business conditions and financial performance.

[0138] Provide customized financial reports and dashboards to meet the needs of different levels and business units.

[0139] Through the implementation and optimization of the above steps, the LLM large language model can be used to efficiently integrate the settlement reports and delivery reports of each sub-business data block to obtain the financial data corresponding to the entire business data. This will provide strong support for the company's financial management and decision-making, and improve business operation efficiency and risk management capabilities.

[0140] Therefore, the present invention can realize the intelligent identification and processing of business data, replace manual operations and improve the processing efficiency of business finance and taxation, and can automatically refine and classify the business data accessed by the front end, facilitate classification for financial statistics, and improve the progress of accounting reports.

[0141] Figure 5The block diagram of a business and financial intelligent management system based on an AI algorithm model is shown according to an exemplary embodiment. The system is used for a business and financial intelligent management method based on an AI algorithm model. Figure 5 The system includes a business screening module 510, a business feature processing module 520, a business and financial automation execution module 530 and an integration module 540. Among them: The business screening module 510 is used to obtain business data from the front end, screen the business data based on the large language model prompt words using the LLM large language model, and separate the business data into a number of sub-business data blocks of different business stages; The business feature processing module 520 is used to sequentially import each of the sub-business data blocks into a pre-deployed business and financial intelligent management AI model, and the business and financial intelligent management AI model identifies and outputs the settlement features and / or delivery behavior features of the sub-business data blocks; The business and financial automation execution module 530 is used to call the corresponding settlement rule template and / or delivery rule based on the settlement characteristics and / or the delivery behavior characteristics, automatically perform settlement processing and / or delivery processing on the sub-business data block, and generate a corresponding settlement report and / or delivery report; The integration module 540 is used to output and integrate the settlement report and / or the delivery report of each of the sub-business data blocks to obtain financial data corresponding to the business data.

[0142] Please understand and implement the functions and interactions of the above modules in conjunction with the corresponding steps in the above method, and will not be repeated here.

[0143] Figure 6 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 6 As shown, the electronic device may include the above Figure 5 Optionally, the electronic device 410 may include a first processor 2001.

[0144] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003 .

[0145] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0146] Combine the following Figure 6 The components of the electronic device 410 are described in detail: The first processor 2001 is the control center of the electronic device 410, and may be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or may be application specific integrated circuits (ASICs), or may be one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0147] Optionally, the first processor 2001 can execute various functions of the electronic device 410 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002 .

[0148] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 6 CPU0 and CPU1 are shown in FIG.

[0149] In a specific implementation, as an embodiment, the electronic device 410 may also include multiple processors, such as Figure 6 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0150] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0151] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently and access the first processor 2001 through the interface circuit ( Figure 6 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0152] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0153] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 6 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0154] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently and communicate with the first processor 2001 through the interface circuit ( Figure 6 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0155] It should be noted that Figure 6 The structure of the electronic device 410 shown in the figure does not constitute a limitation on the router, and the actual knowledge structure recognition device may include more or fewer components than those shown in the figure, or combine certain components, or arrange the components differently.

[0156] In addition, the technical effects of the electronic device 410 can refer to the technical effects of the business and financial intelligent management method based on the AI ​​algorithm model described in the above method embodiment, and will not be repeated here.

[0157] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0158] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0159] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0160] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0161] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0162] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0163] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0164] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0165] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of the system or unit, which can be electrical, mechanical or other forms.

[0166] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple 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.

[0167] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0168] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0169] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A business and financial intelligent management method based on an AI algorithm model, characterized in that: The method comprises: S1. Obtain business data from the front end, use the LLM large language model to filter the business data based on the large language model prompt words, and separate the business data into several sub-business data blocks of different business stages; S2. Importing each of the sub-business data blocks into a pre-deployed business and finance intelligent management AI model in sequence, and having the business and finance intelligent management AI model identify and output the settlement characteristics and / or delivery behavior characteristics of the sub-business data blocks; S3. Based on the settlement characteristics and / or the delivery behavior characteristics, the corresponding settlement rule template and / or delivery rule is directed to be called, settlement processing and / or delivery processing is automatically performed on the sub-business data block, and a corresponding settlement report and / or delivery report is generated; S4. Output and integrate the settlement report and / or the delivery report of each of the sub-business data blocks to obtain financial data corresponding to the business data.

2. The intelligent financial management method based on the AI ​​algorithm model according to claim 1 is characterized in that: S1. Obtain business data from the front end, use the LLM large language model to filter the business data based on the large language model prompt words, and separate the business data into several sub-business data blocks of different business stages, including: Pre-build phase keywords and division logic corresponding to different business attributes; Combining the phase keywords and the segmentation logic, constructing the large language model prompt words and inputting them into the pre-loaded LLM large language model; The business data is traversed by the LLM large language model, and business data of different business stages are identified on the business data based on the large language model prompt words, and business data belonging to different business stages are separated to obtain the sub-business data blocks of several different business stages; Output and save the sub-business data blocks corresponding to different business stages.

3. The intelligent financial management method based on the AI ​​algorithm model according to claim 1 is characterized in that: The method for generating the business and financial intelligent management AI model includes: Collect historical business, finance and tax processing big data of several customers / suppliers, including historical business data sets of each customer / supplier and corresponding historical settlement data sets and historical delivery behaviors; Performing feature engineering on the historical business, finance and tax processing big data to extract business, finance and tax data features of each customer / supplier, wherein the business, finance and tax data features include: extracting the identity and business transaction type of the corresponding customer / supplier from the historical business data set, and / or extracting the corresponding settlement features from the historical business data set, and / or extracting the corresponding delivery behavior features from the historical delivery behavior; The business, finance and taxation data features are marked with a template IP corresponding to the settlement features or a delivery rule corresponding to the delivery behavior features, wherein the template IP is used to define the storage address of the corresponding settlement rule template; Count and label the business, finance and tax data features of each customer / supplier and form a feature set; Dividing the feature set into a training set and a validation set according to a preset ratio; Input the training set into a preset random forest model to perform feature training and learning, and construct and generate the business and financial intelligent management AI model; The feature recognition performance of the business and financial intelligent management AI model is verified using the delivery verification set: If the verification is successful, the business and financial intelligent management AI model is deployed and applied; If the verification fails, repeat the above steps to retrain and build the business and financial intelligent management AI model.

4. The intelligent financial management method based on the AI ​​algorithm model according to claim 3 is characterized in that: After feature engineering is performed on the historical business, finance and tax processing big data to extract the business, finance and tax data features of each customer / supplier, the following is also included: Determine whether the business, finance and taxation data characteristics of each customer / supplier at least include the settlement characteristics and / or the delivery behavior characteristics: If so, the included features are labeled with corresponding identity tags and transaction type tags; If not, delete the business, finance and taxation data characteristics described in this article.

5. The intelligent business and financial management method based on the AI ​​algorithm model according to claim 3 is characterized in that: S3. Based on the settlement characteristics and / or the delivery behavior characteristics, the corresponding settlement rule template and / or delivery rule is directed to be called, settlement processing and / or delivery processing is automatically performed on the sub-business data block, and a corresponding settlement report and / or delivery report is generated, including: Read the marked information on the settlement feature or the delivery behavior feature, and obtain the corresponding template IP and / or delivery rules marked on the business, finance and taxation data feature; Through the storage address of the template IP1, the preset settlement rule template is called from the corresponding storage location, and the sub-business data block is written into the settlement rule template, and the corresponding settlement report is automatically calculated and generated; and / or, According to the delivery rules, a delivery report for the sub-business data block is generated and sent to the corresponding delivery end.

6. An intelligent business and financial management system based on an AI algorithm model, wherein the intelligent business and financial management system based on an AI algorithm model is used to implement the intelligent business and financial management method based on an AI algorithm model as claimed in any one of claims 1 to 5, characterized in that: The system comprises: A business screening module is used to obtain business data from the front end, screen the business data based on the large language model prompt words using the LLM large language model, and separate the business data into several sub-business data blocks of different business stages; A business feature processing module, used to import each of the sub-business data blocks into a pre-deployed business and financial intelligent management AI model in sequence, so that the business and financial intelligent management AI model identifies and outputs the settlement features and / or delivery behavior features of the sub-business data blocks; A business and financial automation execution module, for invoking the corresponding settlement rule template and / or delivery rule based on the settlement characteristics and / or the delivery behavior characteristics, automatically performing settlement processing and / or delivery processing on the sub-business data block, and generating a corresponding settlement report and / or delivery report; The integration module is used to output and integrate the settlement report and / or the delivery report of each sub-business data block to obtain financial data corresponding to the business data.

7. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 5.

Images