Financial analysis method and system based on electronic commerce and electronic equipment

Through convolutional neural network and blockchain technology, the problems of unclear bill information and time-consuming data sorting in e-commerce financial analysis are solved, and the method of intelligently generating e-commerce data reports is realized, which improves analysis efficiency and data accuracy.

CN118967337AInactive Publication Date: 2024-11-15HENAN IND & TRADE VOCATIONAL COLLEGE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410966935.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-15
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In the era of the Internet of Things, the bill flow information in e-commerce financial analysis is unclear, which leads to inconvenient bill arrangement. Data sorting and analysis require a lot of time and energy, and a method that can intelligently generate e-commerce data reports is urgently needed.

Method used

The financial analysis method based on convolutional neural network is adopted to generate e-commerce information documents that comply with the set rules through data mapping and blockchain detection, and automatically correct data errors to intelligently generate e-commerce analysis reports.

Benefits of technology

It realizes the rapid, flexible and accurate generation of e-commerce data reports, reduces user workload, improves the intelligence and automation level of data reports, and ensures the correctness and timeliness of data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118967337A_ABST
    Figure CN118967337A_ABST
Patent Text Reader

Abstract

The invention discloses a financial analysis method and system based on e-commerce and electronic equipment, and relates to the technical field of financial accounting, and the method comprises the steps: obtaining an e-commerce subject accounting mode configuration request; inputting e-commerce element data assigned by a user, and training by using a convolutional neural network model to generate an e-commerce informatization document; mapping the e-commerce informatization document index information and the account book index information into an e-commerce account book by adopting a data mapping method; detecting the receipt index information and the account book index information based on the block chain to obtain corrected e-commerce account book information; and obtaining a corresponding e-commerce report template, calling corresponding account book index information from the corrected e-commerce account book information according to a report analysis command, mapping the account book index information to the e-commerce report template, obtaining a calculation relationship between taskbar information of the e-commerce report template, and calculating to generate a target e-commerce analysis report. The method can quickly adapt to flexible and changeable e-commerce scenes, data are active and traceable, and accuracy is guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce, and in particular to a financial analysis method, system and electronic equipment based on e-commerce. Background Art

[0002] With the continuous development and expansion of Internet of Things technology and its market scale, more and more e-commerce companies are using Internet of Things for intelligent financial management, replacing traditional manual financial accounting methods. E-commerce financial analysis is to record and analyze all economic activities of a merchant engaged in e-commerce in the account book using certain financial analysis methods, so as to adjust the business in a timely manner.

[0003] However, when people currently use the Internet of Things for smart accounting, the flow information of the bill is not clear enough, so that users cannot better understand the situation of daily bills, which brings inconvenience to users' subsequent bill arrangements, and no corresponding improvements have been made.

[0004] In addition, e-commerce reporting is an indispensable task for e-commerce personnel, whether it is quarterly reporting or annual reporting, it all revolves around data reporting. However, it often takes a lot of time and effort to organize, analyze and refine data. Therefore, there is an urgent need for a method that can intelligently generate e-commerce data reports. Summary of the invention

[0005] In order to overcome the deficiencies of the above-mentioned prior art, the present invention provides a financial analysis method, system and electronic device based on e-commerce, so as to quickly adapt to flexible and changeable e-commerce scenarios, generate the required e-commerce data reports, and the data is traceable to ensure accuracy.

[0006] To solve the above problems, the first object of the present invention is to provide a financial analysis method based on e-commerce, the accounting analysis method comprising:

[0007] Step S 100 : Get e-commerce account accounting method configuration request;

[0008] Step S 200 : Input the e-commerce element data assigned by the user, use the convolutional neural network training model for training, and generate e-commerce information documents that meet the set rules;

[0009] Step S 300 : Using a data mapping method, the document indicator information corresponding to the e-commerce informationized document and the accumulated account book indicator information are mapped to a pre-set e-commerce account book;

[0010] Step S 400:Use blockchain to detect the e-commerce information documents and accumulated account book indicator information mapped to the e-commerce account book, correct system data errors according to the detection results, and obtain corrected e-commerce account book information;

[0011] Step S 500 : Receive and transmit the report analysis command issued by the user, obtain the corresponding e-commerce report template, retrieve the corresponding account book indicator information from the corrected e-commerce account book information according to the report analysis command and map it to the e-commerce report template, and obtain the calculation relationship between the task bar information of the e-commerce report template, calculate and generate the target e-commerce analysis report.

[0012] Optionally, in step S 200 The specific steps of using the convolutional neural network training model to train and generate a fully controlled e-commerce information document include:

[0013] Step S 210 : Get the matrix parameters of the feature matrix;

[0014] Step S 220 : Reading corresponding data in the image data matrix from the first buffer space through the first bus according to the matrix parameters to obtain the e-commerce data matrix to be expanded, and sending the e-commerce data matrix to be expanded to the second preset buffer space through the second bus and saving it;

[0015] Step S 230 : reading the e-commerce data matrix to be expanded from the second preset buffer space through the second bus, and expanding the e-commerce data matrix to be expanded according to the matrix parameters to obtain expanded data;

[0016] Step S 240 : reading a preset number of unexpanded data in the image data matrix from the first buffer space through the first bus, sending the unexpanded data to the second preset buffer space through the second bus and storing them, and updating the to-be-expanded e-commerce data matrix stored in the second preset buffer space according to the unexpanded data;

[0017] Step S 250 : Return to the step of reading the e-commerce data matrix to be expanded from the second preset buffer space through the second bus, and expanding the e-commerce data matrix to be expanded according to the matrix parameters.

[0018] Optionally, in step S 300 The data mapping method is used to map the document index information corresponding to the e-commerce informationized document and the accumulated account book index information to the pre-set e-commerce account book, specifically including:

[0019] Step S310 : Establish a business data interaction channel between the e-commerce information document system and the financial system, and verify the necessary fields of the e-commerce information documents pushed to the financial system based on the set transmission verification rules to obtain the e-commerce information documents that have been successfully verified;

[0020] Step S 320 : Define the business data conversion rules between the e-commerce information document system and the financial system to meet the same business data interaction channel contains multiple mapping rule definitions, generate the mapping comparison relationship between the e-commerce information document system and the financial system according to the obtained mapping rule definitions, and maintain it according to the time series;

[0021] Step S 330 : Based on the data conversion rules defined by multiple mapping rules in the same business data interaction channel, the e-commerce account book generation rules of the financial system are constructed.

[0022] Optionally, in step S 400 Among them, the use of blockchain to detect the e-commerce information documents mapped to the e-commerce account book and the accumulated account book indicator information specifically includes:

[0023] Step S 410 : Enter the e-commerce information documents and account book indicator information through the blockchain node, and classify them according to the specific content reflected by the user after entering;

[0024] Step S 420 : Check the information of the classified accounts for duplicate information. If the comparison is consistent, the information will be confirmed in the system and saved. If the comparison is inconsistent, a request will be sent to re-enter the information;

[0025] Step S 430 : After receiving the new data information, the e-commerce company will modify it and submit it to the shared database. The shared database will receive the time period information and generate the corresponding financial bill according to the time period information;

[0026] Step S 440 :Store e-commerce account book information.

[0027] Optionally, in step S 220 The step of performing data expansion on the e-commerce data matrix to be expanded according to the matrix parameters includes:

[0028] Determine a sliding window according to the matrix parameters;

[0029] Sliding the sliding window on the to-be-expanded e-commerce data matrix according to a preset sliding direction and a preset sliding step length;

[0030] After each sliding, obtaining the storage address of the data in the sliding window in the second preset buffer space;

[0031] Corresponding data is read out from the second preset buffer space according to the storage address to complete data expansion.

[0032] Optionally, in step S 320 Among them, the business data conversion rule is: establish the same data transmission interface to support multiple mapping rule definitions, so as to process the successfully verified business data and store the business data that meets the specifications set by the financial system in the financial database.

[0033] Optionally, in step S 410 Among them, the e-commerce information documents include various orders, various sales orders, various purchase orders, various checks, various invoices, various receipts, various payment orders, various receipts, various shipping orders, various bills, various bank documents, various employee salary slips, various employee reimbursement slips and various tax bills.

[0034] Optionally, in step S 500 The process of generating the target e-commerce analysis report includes:

[0035] Receive selection instructions designed for table items in the upper title bar of the target e-commerce analysis report, and establish a command and dispatch relationship between each table item selection instruction and various related e-commerce general ledger accounts;

[0036] Receive a setting instruction for a task bar item in the target e-commerce analysis report; the setting instruction is used to set the report task bar item as a collection item or a calculation item; the collection item is used to realize a mapping conversion calculation relationship between account book indicators and report indicators, and the calculation item is used to realize calculation and reorganization of the collection item in the report task bar and its own information;

[0037] Acquire the layout design content in the e-commerce report template, and determine the lower title bar of the target e-commerce analysis report based on the layout design content;

[0038] The target e-commerce analysis report is generated in combination with the upper title bar, the task bar and the lower title bar.

[0039] A second object of the present invention is to provide a financial analysis system based on e-commerce, comprising:

[0040] Configuration module, used to obtain e-commerce account accounting configuration request;

[0041] The data assignment module is used to input the e-commerce element data assigned by the user, and use the convolutional neural network model to control the e-commerce element data during the assignment process to generate a fully controlled e-commerce information document;

[0042] A data mapping module is used to map the document indicator information corresponding to the fully controlled e-commerce information document to the pre-set e-commerce account book, and establish a mapping conversion calculation relationship between various e-commerce report task column collection items and various e-commerce general ledger account book indicators;

[0043] A detection and proofreading module, used to detect the e-commerce information documents and the accumulated account book indicator information mapped to the e-commerce account book based on the blockchain, correct the system data errors according to the detection results, and obtain the corrected e-commerce account book information;

[0044] The report generation module is used to receive and transmit the report generation command issued by the user, obtain the corresponding e-commerce report template, retrieve the corresponding account book indicator information from the corrected e-commerce account book information according to the report generation command, map it to the e-commerce report template, and obtain the calculation relationship between the task bar information of the e-commerce report template, and calculate and generate the target e-commerce report.

[0045] A third object of the present invention is to provide an electronic device, comprising:

[0046] memory for storing computer programs,

[0047] A processor is used to implement the above-mentioned e-commerce-based financial analysis method when executing the computer program.

[0048] Compared with the prior art, the present invention has significant advantages and beneficial effects, which are specifically embodied in the following aspects:

[0049] The e-commerce-based financial analysis method provided by the present application includes: obtaining an e-commerce account accounting method configuration request; inputting e-commerce element data assigned by a user, training using a convolutional neural network training model, and generating an e-commerce information document that meets the set rules; using a data mapping method, mapping the document indicator information and the accumulated cumulative account book indicator information corresponding to the e-commerce information document to a pre-set e-commerce account book; using a blockchain to detect the e-commerce information document and the accumulated cumulative account book indicator information mapped to the e-commerce account book, correcting system data errors according to the detection results, and obtaining corrected e-commerce account book information; receiving and transmitting a report analysis command issued by a user, obtaining a corresponding e-commerce report template, retrieving corresponding account book indicator information from the corrected e-commerce account book information according to the report analysis command and mapping it to the e-commerce report template, and obtaining the calculation relationship between the task bar information of the e-commerce report template, and calculating and generating a target e-commerce analysis report. During the process of assigning values ​​to e-commerce element data, it can be inspected and controlled, and the data can be inspected based on the blockchain to avoid data errors. It can also automatically retrieve the corresponding information and calculation relationships after receiving report generation instructions, and intelligently and automatically generate target e-commerce reports, ensuring the correctness of e-commerce report data, and giving e-commerce reports a normalized, timely, and intelligent error detection function. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 Schematic diagram of the process of the financial analysis method based on e-commerce in an embodiment of the present invention;

[0051] Figure 2 Step S in the embodiment of the present invention 200 Detailed process diagram of

[0052] Figure 3 Step S in the embodiment of the present invention 300 Detailed process diagram of

[0053] Figure 4 Step S in the embodiment of the present invention 400 Detailed process diagram of

[0054] Figure 5 It is a structural diagram of a financial analysis system based on e-commerce in an embodiment of the present invention;

[0055] Figure 6 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] See also Figure 1 As shown, in an embodiment of the present invention, a financial analysis method based on e-commerce is provided, and the accounting analysis method includes:

[0058] Step S 100 : Get e-commerce account accounting method configuration request;

[0059] Step S 200 : Input the e-commerce element data assigned by the user, use the convolutional neural network model for training, and generate e-commerce information documents that meet the set rules;

[0060] Step S 300 : Using a data mapping method, the document indicator information corresponding to the e-commerce informationized document and the accumulated account book indicator information are mapped to a pre-set e-commerce account book;

[0061] Step S 400 :Based on the blockchain, the e-commerce informationization documents and the accumulated account book indicator information mapped to the e-commerce account book are detected, and the system data errors are corrected according to the detection results to obtain the corrected e-commerce account book information;

[0062] Step S 500 : Receive and transmit the e-commerce report analysis command issued by the user, obtain the corresponding e-commerce analysis report template, retrieve the corresponding account book indicator information from the corrected e-commerce account book information according to the e-commerce report analysis command and map it to the e-commerce analysis report template, and obtain the calculation relationship between the task bar information of the e-commerce analysis report template, calculate and generate the target e-commerce analysis report.

[0063] For further information, see Figure 2 As shown, in step S 200 The specific steps of using the convolutional neural network model for training and generating a fully controlled e-commerce informationized document include:

[0064] Step S 210 : Get the matrix parameters of the e-commerce element feature matrix;

[0065] The feature matrix is ​​the convolution kernel of the convolution operation, also known as the weight matrix, and the feature matrix can be set according to actual needs. Among them, the matrix parameters of the feature matrix may include the number of matrix rows and columns, which can be called the size of the convolution kernel.

[0066] Step S 220 : Reading corresponding data in the e-commerce image data matrix from the first buffer space through the first bus according to the matrix parameters to obtain the e-commerce data matrix to be expanded, and sending the e-commerce data matrix to be expanded to the second preset buffer space through the second bus and saving it;

[0067] The elements in the e-commerce image data matrix are pixel data corresponding to the image pixels, such as the pixel values ​​after processing. The number of rows and columns of the image data matrix represents the size of the image. The image data matrix can be stored in an accelerator card of the convolutional neural network processing system, for example, in a memory of the accelerator card.

[0068] After obtaining the e-commerce data matrix to be expanded, the e-commerce data matrix to be expanded can be sent to the second preset buffer space through the second bus and stored. The second preset buffer space can be a preset buffer, for example, the preset buffer can be a buffer or DDR in a coprocessor, and the second bus is a bus connecting the processor or coprocessor and the preset buffer.

[0069] Step S 230 : reading the e-commerce data matrix to be expanded from the second preset buffer space through the second bus, and expanding the e-commerce data matrix to be expanded according to the matrix parameters to obtain expanded data;

[0070] Specifically, the e-commerce data matrix to be expanded can be expanded according to the number of rows and columns of the feature matrix, and several data groups can be obtained after expansion. After the data expansion of the image data matrix is ​​completed, a data matrix can be formed according to the data group, that is, the expanded data matrix. Subsequently, matrix multiplication can be performed on the expanded data matrix and the feature matrix to obtain the corresponding data and complete the data convolution operation.

[0071] Step S 240 : reading a preset number of unexpanded data in the image data matrix from the first buffer space through the first bus, sending the unexpanded data to the second preset buffer space through the second bus and storing them, and updating the to-be-expanded e-commerce data matrix stored in the second preset buffer space according to the unexpanded data;

[0072] Specifically, a preset number of unexpanded data in the image data matrix is ​​read from the first buffer space through the first bus, the read unexpanded data is sent to the second preset buffer space through the second bus and stored, and the e-commerce data matrix to be expanded stored in the second preset buffer space is updated according to the unexpanded data. A preset number of unexpanded data in the image data matrix can be read from the first buffer space through the first bus based on the convolution step. The convolution step represents the number of rows or columns of unexpanded data that need to be read from the image data matrix after the e-commerce data matrix to be expanded is expanded.

[0073] Step S 250 : Return to execute the step of reading the e-commerce data matrix to be expanded from the second preset buffer space through the second bus, and expanding the e-commerce data matrix to be expanded according to the matrix parameters.

[0074] This scheme can reuse the read-out image data during the convolution process to achieve data expansion, avoid repeated reading of certain data, and reduce the demand for data bandwidth or storage space for convolutional neural network data expansion. Therefore, it can improve the data processing capability and data expansion efficiency of the convolutional neural network processing system.

[0075] For further information, see Figure 3 As shown, in step S 300 The data mapping method is used to map the document index information corresponding to the e-commerce informationized document and the accumulated account book index information to the pre-set e-commerce account book, specifically including:

[0076] Step S 310 : Establish a business data interaction channel between the e-commerce information document system and the financial system, and verify the necessary fields of the e-commerce information documents pushed to the financial system based on the set transmission verification rules to obtain the e-commerce information documents that have been successfully verified;

[0077] Step S 320 : Define the business data conversion rules between the e-commerce information document system and the financial system to meet the same business data interaction channel contains multiple mapping rule definitions, generate the mapping comparison relationship between the e-commerce information document system and the financial system according to the obtained mapping rule definitions, and maintain it according to the time series;

[0078] Step S 330 : Based on the data conversion rules defined by multiple mapping rules in the same business data interaction channel, the e-commerce account book generation rules of the financial system are constructed.

[0079] Establish transmission verification rules for necessary fields of business data transmitted to the financial system to obtain successfully verified business data. In specific implementation, when a business transaction occurs, it is pushed to the financial system in real time through the message middleware (kafka), and the financial system performs the necessary fields.

[0080] It should be noted that the necessary fields include the time of transaction, transaction amount, and verification of the transaction party. After completion, the business data falls into MySQL (database). Since the data is in the unprocessed state at this time, an ACK mechanism needs to be added to ensure that the data is not lost. After the data is stored in the database, a message will be sent to the billing engine (the database engine is a core service for storing, processing and protecting data) saying that there is a piece of data to be processed. At this time, the data access and the calculation of the billing engine are separated to ensure that the data access in the business data and the processing speed of the billing engine are accelerated to reduce processing delays.

[0081] Therefore, through configuration, it is possible to realize the business data based on different e-commerce scenarios and generate e-commerce information documents according to financial accounting requirements, thereby reducing user workload and improving the work efficiency of business and financial personnel. At the same time, as a bridge between business data and e-commerce information documents, the present invention has scalability and supports the conversion of data from various business systems into e-commerce information documents through specific rules, and can quickly adapt to flexible and changeable e-commerce business scenarios.

[0082] For further information, see Figure 4 As shown, in step S 400 The blockchain is used to detect the e-commerce information documents mapped to the e-commerce account book and the accumulated account book indicator information, specifically including:

[0083] Step S 410 : Enter the e-commerce information documents and account book indicator information through the blockchain node, and classify them according to the specific content reflected by the user after entering;

[0084] Step S 420 : Check the information of the classified accounts for duplicate information. If the comparison is consistent, the information will be confirmed in the system and saved. If the comparison is inconsistent, a request will be sent to re-enter the information;

[0085] Step S 430 : After receiving the new data information, the e-commerce financial staff will modify it and submit it to the shared database. The shared database will receive the time period information and generate the corresponding financial bill according to the time period information;

[0086] Step S 440 :Store e-commerce account book information.

[0087] The traditional e-commerce financial accounting and record modification method is not easy to operate. Usually, when an e-commerce bill is wrong, it is necessary to look for the original voucher according to the record, which makes it extremely inconvenient to find the record and is therefore not convenient for people to use. Compared with traditional technology, through blockchain, you can upload invoice and bill information yourself, which effectively reduces the work pressure of e-commerce financial personnel and greatly reduces the error rate of bills; encryption through the HASH encryption algorithm can improve the security of user information, prevent user information from being stolen, avoid user information leakage, and protect user privacy.

[0088] Furthermore, in step S 220 The step of performing data expansion on the e-commerce data matrix to be expanded according to the matrix parameters includes:

[0089] Determine the sliding window according to the matrix parameters;

[0090] Sliding the sliding window on the e-commerce data matrix to be expanded according to a preset sliding direction and a preset sliding step length;

[0091] After each sliding, obtaining the storage address of the data in the sliding window in the second preset buffer space;

[0092] Corresponding data is read out from the second preset buffer space according to the storage address to complete data expansion.

[0093] The preset sliding direction may include: the row direction, column direction, etc. of the image data matrix. In practical applications, the preset sliding direction may correspond to the data reading method. For example, when reading a number of rows of data of the image data matrix, the preset sliding direction may be the row direction of the image data matrix;

[0094] For another example, when reading several columns of data of the image data matrix, the preset sliding direction may be the column direction of the image data matrix. The preset sliding step length is the distance to be slid, which may be set according to the actual data expansion requirements, and may be represented by the number of data to be slid on the data matrix. For example, the preset sliding step length is 1, 2, 3 data, and so on.

[0095] After obtaining the preset sliding step, the preset sliding direction and the sliding window, the window can be slid on the e-commerce data matrix to be expanded along the preset sliding direction with the preset sliding step. After each sliding of the window, the address of the data in the window in the second preset buffer space can be obtained. Then, the corresponding data is read from the preset buffer according to the address and the preset reading order to complete the data expansion, that is, the data expansion is realized by reading the data in a jump address manner.

[0096] Furthermore, in step S 320Among them, the business data conversion rule is: establish the same data transmission interface to support multiple mapping rule definitions to process the e-commerce business data that has been verified successfully, and store the e-commerce business data that meets the specifications set by the financial system in the e-commerce financial database.

[0097] Specifically, the same data transmission interface is established to support multiple mapping rule definitions to process the successfully verified e-commerce business data and store the business data that meets the specifications set by the financial system in the financial database.

[0098] It should be noted that after processing the successfully verified business data and storing the business data that meets the specifications set by the financial system in the financial database, it is also necessary to maintain the corresponding relationship of the defined conversion rules in order to maintain the mapping and corresponding relationship between the e-commerce information document system and the financial system. In specific implementation, when the business data attributes of the e-commerce information document system are inconsistent and the corresponding relationship is inconsistent, and the business data pushed to the financial system are not all required by the financial system, the financial system needs to convert the business data. At this time, the financial system provides a database-level mapping table for pre-configuring the correspondence between the fields of the business source system and the standard fields of the financial system.

[0099] For example, the business date is unified as YYYY-MM-DD, the amount attribute is uniformly reserved to 4 decimal places, and a thousand separator is used. The fields in the financial standard format are uniformly formulated by the finance department and stored in the database. When the financial system custom development program function consumes Kafka messages, it will unify the format and put it into the financial database.

[0100] Specifically, in step S 410 Among them, the e-commerce information documents include various orders, various sales orders, various purchase orders, various checks, various invoices, various receipts, various payment orders, various receipts, various shipping orders, various bills, various bank documents, various employee salary slips, various employee reimbursement slips and various tax bills.

[0101] Furthermore, in step S 500 The process of generating the target e-commerce analysis report includes:

[0102] Receive selection instructions designed for table items in the upper title bar of the target e-commerce analysis report, and establish a command and dispatch relationship between each table item selection instruction and various related e-commerce general ledger accounts;

[0103] Receive a setting instruction for a task bar item in the target e-commerce analysis report; the setting instruction is used to set the report task bar item as a collection item or a calculation item; the collection item is used to realize a mapping conversion calculation relationship between account book indicators and report indicators, and the calculation item is used to realize calculation and reorganization of the collection item in the report task bar and its own information;

[0104] Acquire the layout design content in the e-commerce report template, and determine the lower title bar of the target e-commerce analysis report based on the layout design content;

[0105] The target e-commerce analysis report is generated in combination with the upper title bar, the task bar and the lower title bar.

[0106] This application can detect and control e-commerce element data during its value assignment process, and can re-detect the data based on blockchain to avoid data errors. It can also automatically retrieve corresponding information and calculation relationships after receiving report generation instructions, and intelligently and automatically generate target e-commerce reports, ensuring the correctness of e-commerce report data, and giving e-commerce reports a normalized, timely, and intelligent detection and error reporting function.

[0107] See also Figure 5 As shown, some other embodiments of the present invention further provide a financial analysis system based on e-commerce, the system comprising:

[0108] Configuration module, used to obtain e-commerce account accounting method configuration request;

[0109] The data assignment module is used to input the e-commerce element data assigned by the user, and use the convolutional neural network model to control the e-commerce element data during the assignment process to generate a fully controlled e-commerce information document;

[0110] A data mapping module is used to map the document indicator information corresponding to the fully controlled e-commerce information document to the pre-set e-commerce account book, and establish a mapping conversion calculation relationship between various e-commerce report task column collection items and various e-commerce general ledger account book indicators;

[0111] A detection and proofreading module, used to detect the e-commerce information documents and the accumulated account book indicator information mapped to the e-commerce account book based on the blockchain, correct the system data errors according to the detection results, and obtain the corrected e-commerce account book information;

[0112] The report generation module is used to receive and transmit the report generation command issued by the user, obtain the corresponding e-commerce report template, retrieve the corresponding account book indicator information from the corrected e-commerce account book information according to the report generation command, map it to the e-commerce report template, and obtain the calculation relationship between the task bar information of the e-commerce report template, and calculate and generate the target e-commerce report.

[0113] See also Figure 6 As shown, an embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned e-commerce-based financial analysis method when executing the computer program.

[0114] The electronic device provided in the embodiment of the present application can be used to perform the e-commerce financial statement accounting analysis provided in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here.

[0115] An embodiment of the present invention further provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed on a computer, the computer executes the above-mentioned financial analysis method based on e-commerce.

[0116] It should be noted that the above-mentioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0117] Optionally, a readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in a dedicated integrated circuit. Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0118] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. A financial analysis method based on e-commerce, characterized in that: The financial analysis method includes: Step S 100 : Get e-commerce account accounting method configuration request; Step S 200 : Input the e-commerce element data assigned by the user, use the convolutional neural network model for training, and generate e-commerce information documents that meet the set rules; Step S 300 : Using a data mapping method, the document indicator information corresponding to the e-commerce informationized document and the accumulated account book indicator information are mapped to a pre-set e-commerce account book; Step S 400 :Based on the blockchain, the e-commerce informationization documents and the accumulated account book indicator information mapped to the e-commerce account book are detected, and the system data errors are corrected according to the detection results to obtain the corrected e-commerce account book information; Step S 500 : Receive and transmit the report analysis command issued by the user, obtain the corresponding e-commerce report template, retrieve the corresponding account book indicator information from the corrected e-commerce account book information according to the report analysis command and map it to the e-commerce report template, and obtain the calculation relationship between the task bar information of the e-commerce report template, calculate and generate the target e-commerce analysis report.

2. The financial analysis method based on e-commerce according to claim 1, characterized in that: In step S 200 The specific steps of using the convolutional neural network training model to train and generate a fully controlled e-commerce information document include: Step S 210 : Get the matrix parameters of the feature matrix; Step S 220 : Reading corresponding data in the e-commerce image data matrix from the first buffer space through the first bus according to the matrix parameters to obtain the e-commerce data matrix to be expanded, and sending the e-commerce data matrix to be expanded to the second preset buffer space through the second bus and saving it; Step S 230 : reading the e-commerce data matrix to be expanded from the second preset buffer space through the second bus, and expanding the e-commerce data matrix to be expanded according to the matrix parameters to obtain expanded data; Step S 240 : reading a preset number of unexpanded data in the e-commerce image data matrix from the first buffer space through the first bus, sending the unexpanded data to the second preset buffer space through the second bus and storing them, and updating the to-be-expanded e-commerce data matrix stored in the second preset buffer space according to the unexpanded data; Step S 250 : Return to execute the step of reading the to-be-expanded e-commerce data matrix from the second preset buffer space through the second bus, and expanding the to-be-expanded e-commerce data matrix according to the matrix parameters.

3. The financial analysis method based on e-commerce according to claim 1, characterized in that: In step S 300 The data mapping method is used to map the document index information corresponding to the e-commerce informationized document and the accumulated account book index information to the pre-set e-commerce account book, specifically including: Step S 310 : Establish a business data interaction channel between the e-commerce information document system and the financial system, and verify the necessary fields of the e-commerce information documents pushed to the financial system based on the set transmission verification rules to obtain the e-commerce information documents that have been successfully verified; Step S 320 : Define the business data conversion rules between the e-commerce information document system and the financial system to meet the same business data interaction channel contains multiple mapping rule definitions, generate the mapping comparison relationship between the e-commerce information document system and the financial system according to the obtained mapping rule definitions, and maintain it according to the time series; Step S 330 : Based on the data conversion rules defined by multiple mapping rules in the same business data interaction channel, the e-commerce account book generation rules of the financial system are constructed.

4. The financial analysis method based on e-commerce according to claim 1, characterized in that: In step S 400 Among them, the use of blockchain to detect the e-commerce information documents mapped to the e-commerce account book and the accumulated account book indicator information specifically includes: Step S 410 : Enter the e-commerce information documents and account book indicator information through the blockchain node, and classify them according to the specific content reflected by the user after entering; Step S 420 : Check the information of the classified accounts for duplicate information. If the comparison is consistent, the information will be confirmed in the system and saved. If the comparison is inconsistent, a request will be sent to re-enter the information; Step S 430 : After receiving the new data information, the e-commerce financial staff will modify it and submit it to the shared database. The shared database will receive the time period information and generate the corresponding e-commerce financial bill according to the time period information; Step S 440 :Store e-commerce account book information.

5. The financial analysis method based on e-commerce according to claim 2, characterized in that: In step S 220 The step of performing data expansion on the e-commerce data matrix to be expanded according to the matrix parameters includes: Determine a sliding window according to the matrix parameters; Sliding the sliding window on the to-be-expanded e-commerce data matrix according to a preset sliding direction and a preset sliding step length; After each sliding, obtaining the storage address of the data in the sliding window in the second preset buffer space; Corresponding data is read out from the second preset buffer space according to the storage address to complete data expansion.

6. The financial analysis method based on e-commerce according to claim 3, characterized in that: In step S 320 Among them, the business data conversion rule is: establish the same data transmission interface to support multiple mapping rule definitions to process the successfully verified business data and store the business data that meets the specifications set by the financial system in the financial database.

7. The financial analysis method based on e-commerce according to claim 4, characterized in that: In step S 410 Among them, the e-commerce information documents include various orders, various sales orders, various purchase orders, various checks, various invoices, various receipts, various payment orders, various receipts, various shipping orders, various bills, various bank documents, various employee salary slips, various employee reimbursement slips and various tax bills.

8. The financial analysis method based on e-commerce according to claim 1, characterized in that: In step S 500 The process of generating the target e-commerce analysis report includes: Receive selection instructions designed for table items in the upper title bar of the target e-commerce analysis report, and establish a command and dispatch relationship between each table item selection instruction and various related e-commerce general ledger accounts; Receive a setting instruction for a task bar item in the target e-commerce analysis report; the setting instruction is used to set the task bar item as a collection item or a calculation item; the collection item is used to realize a mapping conversion calculation relationship between account book indicators and report indicators, and the calculation item is used to realize calculation and reorganization of the collection item in the report task bar and its own information; Acquire the layout design content in the e-commerce report template, and determine the lower title bar of the target e-commerce analysis report based on the layout design content; The target e-commerce analysis report is generated in combination with the upper title bar, the task bar and the lower title bar.

9. A financial analysis system based on e-commerce, characterized in that: include: Configuration module, used to obtain e-commerce account accounting configuration request; The data assignment module is used to input the e-commerce element data assigned by the user, and use the convolutional neural network model to control the e-commerce element data during the assignment process to generate a fully controlled e-commerce information document; A data mapping module is used to map the document indicator information corresponding to the fully controlled e-commerce information document to the pre-set e-commerce account book, and establish a mapping conversion calculation relationship between various e-commerce report task column collection items and various e-commerce general ledger account book indicators; A detection and proofreading module, used to detect the e-commerce information documents and the accumulated account book indicator information mapped to the e-commerce account book based on the blockchain, correct the system data errors according to the detection results, and obtain the corrected e-commerce account book information; The report generation module is used to receive and transmit the report generation command issued by the user, obtain the corresponding e-commerce report template, retrieve the corresponding account book indicator information from the corrected e-commerce account book information according to the report generation command, map it to the e-commerce report template, and obtain the calculation relationship between the task bar information of the e-commerce report template, and calculate and generate the target e-commerce report.

10. An electronic device, characterized in that: include: memory for storing computer programs, A processor, configured to implement the steps of the e-commerce-based financial analysis method as claimed in any one of claims 1 to 8 when executing the computer program.