An intelligent financial data management system based on big data

Abstract

The present invention relates to the field of data management technology, and in particular to an intelligent financial data management system based on big data. The present invention receives uploaded invoices through a financial data receiving module, the invoice analysis module compares the identified financial data with the manually input financial data, divides the invoice into color areas based on a clustering color segmentation algorithm, and determines whether to store the invoice according to the comparison result and the chromaticity value. The financial data encryption module sets an encryption password for the invoice and the financial data of the invoice, the financial data classification unit records the number of times the financial data is viewed and the password input error rate of the financial data, and classifies the financial data. The financial data encryption adjustment unit selects a specific financial data category for secondary encryption. The present invention improves the efficiency of invoice management, ensures the accuracy and integrity of information in the financial data management system, and improves the security of financial data while ensuring the conservation of computing resources.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to an intelligent financial data management system based on big data. Background Art

[0002] With the increasing complexity of business operations and the volume of data, traditional financial data management systems are no longer able to meet the demands of modern enterprises for efficient, accurate, and real-time financial management. Existing financial data management often faces the following challenges: fragmented and difficult-to-integrate data, inefficient data processing, insufficient risk early warning capabilities, and a lack of intelligent decision support. Furthermore, the diversity and complexity of financial data complicate management, particularly in data sharing, collaboration, and real-time monitoring.

[0003] In the prior art, Chinese Patent Publication No. CN113435986A discloses a financial data management method, which belongs to the field of new material processing. The present invention includes the following steps: S1 financial data input, S2 financial data additional information marking, S3 financial data processing, S4 financial data analysis, S5 data comparison and additional marking, generating an additional marking list based on the inconsistency of the additional data, and S6 report generation. The present invention establishes financial data additional information marking during the financial data input process, so that the input financial data can be better verified with the voucher collection module and the bank bill storage module. If it is found to be false, or if the input is first and the bills and actual expenses are later, it can be better verified from the additional marking list, which can better avoid the occurrence of loopholes and better reduce financial losses.

[0004] However, in the existing technology, the quality of invoices is not evaluated comprehensively from multiple aspects, resulting in low efficiency of invoice management and low accuracy and completeness of information in the financial data management system. In addition, financial data is not classified, and different encryption methods are used for different categories of financial data, resulting in the financial data management system consuming too many computing resources or having a low level of security. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent financial data management system based on big data, which can evaluate the quality of invoices through comprehensive evaluation from multiple aspects, thereby improving the efficiency of invoice management, ensuring the accuracy and completeness of information in the financial data management system, and classifying financial data, adopting different encryption methods for different categories of financial data, thereby improving the security of the system while ensuring that the financial data management system does not consume too many computing resources.

[0006] The present invention provides an intelligent financial data management system based on big data, comprising:

[0007] A financial data receiving module, configured to receive uploaded invoices, identify the financial data in the invoices, and receive manually input financial data of the invoices;

[0008] an invoice analysis module, connected to the financial data receiving module, for comparing the identified financial data with the manually input financial data, dividing the invoice into color regions using a cluster-based color segmentation algorithm, obtaining the chromaticity values ​​of several points within each color region, and determining whether to store the invoice based on the comparison results and the chromaticity values;

[0009] A financial data storage module, connected to the invoice analysis module, for storing invoices and the financial data of the invoices;

[0010] A financial data encryption module, connected to the financial data storage module, for setting an encryption password for the invoice and the financial data of the invoice according to preset rules;

[0011] The financial data monitoring module is connected to the financial data storage module and includes a financial data classification unit and a financial data encryption adjustment unit.

[0012] The financial data classification unit is used to record the number of times the financial data is viewed and the password input error rate of the financial data, and classify the financial data according to the number of times the financial data is viewed and the password input error rate of the financial data.

[0013] The financial data encryption adjustment unit is used to select a specific financial data category and perform secondary encryption on the specific financial data category.

[0014] Furthermore, the invoice analysis module is used to compare the identified financial data with the manually input financial data, including:

[0015] Obtaining identified financial data of invoices and manually entered financial data;

[0016] Compare each manually input financial data with the corresponding identified financial data in turn;

[0017] If the manually input financial data is identical to the corresponding identified financial data, it is determined that the financial data is accurately identified;

[0018] If the manually input financial data is different from the corresponding identified financial data, it is determined that the financial data was not accurately identified;

[0019] If the manually input financial data does not have corresponding identified financial data, it is determined to be missing identified financial data;

[0020] The ratio of the number of inaccurately identified financial data to the number of manually input financial data is recorded as the financial identification inaccuracy rate;

[0021] The ratio of missing identified financial data to the number of manually entered financial data is recorded as the financial identification missing rate.

[0022] Furthermore, the invoice analysis module is used to divide the invoice into color regions based on a clustering-based color segmentation algorithm, and obtain the chromaticity values ​​of several points in each color region, including:

[0023] Use clustering-based color segmentation algorithm to divide the invoice into color regions;

[0024] Select any number of points in each color area;

[0025] Get the chromaticity values ​​of any points in each color area.

[0026] Furthermore, the invoice analysis module is further configured to calculate an invoice storage tendency characterization value based on the comparison result and the color value, including:

[0027] Compare the chromaticity values ​​of any number of points in each color area with the corresponding preset chromaticity value threshold;

[0028] Obtain the difference between the chromaticity value of any number of points in each color area and the corresponding preset chromaticity value threshold;

[0029] Obtaining a ratio of the absolute value of the difference to the corresponding preset chromaticity value threshold, which is recorded as a chromaticity value difference ratio;

[0030] The invoice storability tendency characterization value is obtained by weighted summing up the financial recognition inaccuracy rate, the financial recognition missing rate and the color value difference ratio.

[0031] Furthermore, the invoice analysis module determines whether to store the invoice.

[0032] If the invoice storability tendency characterization value of the invoice is less than a preset invoice storability tendency characterization value comparison threshold, determining to store the invoice;

[0033] If the invoice storability tendency characterization value of the invoice is greater than or equal to a preset invoice storability tendency characterization value comparison threshold, it is determined that the invoice is not to be stored.

[0034] Furthermore, the financial data encryption module is used to set an encryption password for the financial data according to preset rules, wherein the full name of the invoicing company in the financial data is obtained, and the first letter of the full name of the invoicing company is set as the encryption password.

[0035] Furthermore, the financial data classification unit is also used to obtain the password input error rate of the financial data, wherein the total number of password input times for the financial data and the number of incorrect password input times for the financial data are obtained, and the ratio of the number of incorrect password input times to the total number of password input times is recorded as the password input error rate.

[0036] Furthermore, the financial data classification unit is used to classify the financial data according to the number of times the financial data is viewed and the password input error rate of the financial data.

[0037] If the financial data meets the preset conditions, the financial data category is classified as high-risk financial data;

[0038] If the financial data does not meet the preset conditions, the financial data category is classified as low-risk financial data;

[0039] The preset condition is that the number of times the financial data is viewed is greater than a preset viewing number comparison threshold, and the password input error rate of the financial data is greater than a preset password input error rate comparison threshold.

[0040] Furthermore, the financial data encryption adjustment unit is used to select a high-risk financial data category and perform secondary encryption on the high-risk financial data category.

[0041] Furthermore, the financial data includes invoice number, invoice date, invoice issuing company name, invoice receiving company name, tax-exclusive amount, tax rate, tax amount, tax-inclusive amount, product description, quantity, and unit price.

[0042] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention receives uploaded invoices through a financial data receiving module, the invoice analysis module compares the identified financial data with the manually input financial data, divides the invoice into color areas based on a clustering color segmentation algorithm, and determines whether to store the invoice according to the comparison result and the chromaticity value. The financial data encryption module sets an encryption password for the invoice and the financial data of the invoice, the financial data classification unit records the number of times the financial data is viewed and the error rate of the password input of the financial data, and classifies the financial data. The financial data encryption adjustment unit selects a specific financial data category for secondary encryption. The present invention improves the efficiency of invoice management, ensures the accuracy and completeness of information in the financial data management system, and improves the security of financial data while ensuring the conservation of computing resources.

[0043] In particular, the present invention compares the identified financial data and the manually input financial data through the invoice analysis module. In actual situations, since the invoice may have low pixel values ​​due to compression of the uploaded image, and there may be incomplete invoice uploads, resulting in the presence of unrecognizable financial data in the invoice, or financial data that is easily misidentified, obtaining the financial recognition inaccuracy rate and the financial recognition missing rate can effectively make a reliable assessment of the invoice upload quality, thereby improving the efficiency of invoice management and ensuring the accuracy and completeness of information in the financial data management system.

[0044] In particular, the present invention determines whether to store the invoice based on the comparison results and chromaticity values ​​through the invoice analysis module. The chromaticity values ​​in each color area of ​​the invoice can evaluate the quality of the image. The accuracy of the chromaticity value can reflect key information such as the clarity and color reproduction of the invoice image. If the chromaticity value of the invoice image deviates significantly from the standard value, it may mean that the image has problems such as blur, stains or color distortion. By combining the chromaticity value of the invoice, the financial recognition inaccuracy rate and the financial recognition missing rate, the accuracy of the invoice quality assessment can be improved, thereby improving the efficiency of invoice management and ensuring the accuracy and completeness of information in the financial data management system.

[0045] In particular, the present invention records the number of times financial data is viewed and the password input error rate of the financial data through a financial data classification unit. In actual situations, the number of times financial data is viewed can reflect to a certain extent that the data has important value to their current work, decision-making or interests, and the password input error rate of the financial data can reflect to a certain extent the security level of the financial data. By obtaining the number of times financial data is viewed and the password input error rate of the financial data, the security and importance of the financial data can be characterized, thereby improving the security of the financial data.

[0046] In particular, the present invention performs secondary encryption on specific financial data categories through a financial data encryption adjustment unit. In actual situations, secondary encryption of all financial data requires excessive computing resources, increases the computing burden of the system, and slows down the processing speed, thereby requiring more time and resources to configure and maintain the encryption system, resulting in increased maintenance costs. By selecting high-risk financial data categories for secondary encryption, the security of financial data can be improved while ensuring the conservation of computing resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a structural diagram of an intelligent financial data management system based on big data according to an embodiment of the present invention;

[0048] Figure 2 This is a structural diagram of a financial data monitoring module according to an embodiment of the present invention;

[0049] Figure 3 This is a logic decision diagram for the invoice analysis module of an embodiment of the present invention to determine whether to store an invoice;

[0050] Figure 4 This is a logical decision diagram for classifying financial data by the financial data classification unit of an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0052] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0053] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0054] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0055] like Figures 1-4 As shown, this embodiment provides an intelligent financial data management system based on big data, and the intelligent financial data management system based on big data includes:

[0056] A financial data receiving module, configured to receive uploaded invoices, identify the financial data in the invoices, and receive manually input financial data of the invoices;

[0057] an invoice analysis module, connected to the financial data receiving module, for comparing the identified financial data with the manually input financial data, dividing the invoice into color regions using a cluster-based color segmentation algorithm, obtaining the chromaticity values ​​of several points within each color region, and determining whether to store the invoice based on the comparison results and the chromaticity values;

[0058] A financial data storage module, connected to the invoice analysis module, for storing invoices and the financial data of the invoices;

[0059] A financial data encryption module, connected to the financial data storage module, for setting an encryption password for the invoice and the financial data of the invoice according to preset rules;

[0060] The financial data monitoring module is connected to the financial data storage module and includes a financial data classification unit and a financial data encryption adjustment unit.

[0061] The financial data classification unit is used to record the number of times the financial data is viewed and the password input error rate of the financial data, and classify the financial data according to the number of times the financial data is viewed and the password input error rate of the financial data.

[0062] The financial data encryption adjustment unit is used to select a specific financial data category and perform secondary encryption on the specific financial data category.

[0063] It is understandable that the uploaded invoice can be one picture or multiple pictures, which contain financial data to be stored. In this embodiment, the manually input financial data is repeatedly checked and there is no erroneous financial data.

[0064] In this embodiment, Python is used to divide the invoice into color regions based on a clustering color segmentation algorithm, and the chromaticity values ​​of several points in each color region are obtained.

[0065] It is understandable that an encryption password is set for the invoice and the financial data of the invoice according to preset rules, wherein the invoice of each transaction and the financial data contained in the invoice use an encryption password, and by entering the encryption password, the invoice and financial data of the transaction can be viewed.

[0066] It is understandable that after the financial data and the corresponding invoices are stored in the system, the financial data can be viewed, and the system will automatically record the number of times the financial data is viewed, the number of times the password is entered correctly, and the number of times the password is entered incorrectly, where the number of times the financial data is viewed is the cumulative number of times all financial data corresponding to a single transaction is viewed.

[0067] Specifically, the invoice analysis module is used to compare the identified financial data with the manually input financial data, including:

[0068] Obtaining identified financial data of invoices and manually entered financial data;

[0069] Compare each manually input financial data with the corresponding identified financial data in turn;

[0070] If the manually input financial data is identical to the corresponding identified financial data, it is determined that the financial data is accurately identified;

[0071] If the manually input financial data is different from the corresponding identified financial data, it is determined that the financial data was not accurately identified;

[0072] If the manually input financial data does not have corresponding identified financial data, it is determined to be missing identified financial data;

[0073] The ratio of the number of inaccurately identified financial data to the number of manually input financial data is recorded as the financial identification inaccuracy rate;

[0074] The ratio of missing identified financial data to the number of manually entered financial data is recorded as the financial identification missing rate.

[0075] Specifically, the present invention compares the identified financial data and the manually input financial data through the invoice analysis module. In actual situations, since the invoice may have low pixel values ​​due to compression of the uploaded image, and there may be incomplete invoice upload, resulting in the presence of unrecognizable financial data in the invoice, or financial data that is easily misidentified, obtaining the financial recognition inaccuracy rate and the financial recognition missing rate can effectively make a reliable assessment of the invoice upload quality, thereby improving the efficiency of invoice management and ensuring the accuracy and completeness of information in the financial data management system.

[0076] Specifically, the invoice analysis module is used to divide the invoice into color regions based on the clustering color segmentation algorithm, and obtain the chromaticity values ​​of several points in each color region, including:

[0077] Use clustering-based color segmentation algorithm to divide the invoice into color regions;

[0078] Select any number of points in each color area;

[0079] Get the chromaticity values ​​of any points in each color area.

[0080] Specifically, the invoice analysis module is further used to calculate the invoice storage tendency representation value based on the comparison result and the color value, including:

[0081] Compare the chromaticity values ​​of any number of points in each color area with the corresponding preset chromaticity value threshold;

[0082] Obtain the difference between the chromaticity value of any number of points in each color area and the corresponding preset chromaticity value threshold;

[0083] Obtaining a ratio of the absolute value of the difference to the corresponding preset chromaticity value threshold, which is recorded as a chromaticity value difference ratio;

[0084] The invoice storability tendency characterization value is obtained by weighted summing up the financial recognition inaccuracy rate, the financial recognition missing rate and the color value difference ratio.

[0085] In this embodiment, the average value of the chromaticity values ​​of any number of points obtained in each color area is compared with a preset chromaticity value threshold.

[0086] In this embodiment, the preset chromaticity value threshold is measured in advance by experiments. Python is used to divide several invoices that meet the storage conditions into color areas in advance, and the chromaticity value of each color area is obtained. The average value of the chromaticity values ​​of several invoices in each color area is obtained and recorded as the preset chromaticity value threshold.

[0087] It is understandable that when performing chromaticity value comparison, the chromaticity value of the corresponding color area is compared with a preset chromaticity value threshold.

[0088] In this embodiment, the weighting coefficient of the financial recognition inaccuracy rate is 0.3, the weighting coefficient of the financial recognition missing rate is 0.3, and the weighting coefficient of the chromaticity value difference ratio is 0.4.

[0089] Specifically, the present invention determines whether to store the invoice based on the comparison results and chromaticity values ​​through the invoice analysis module. The chromaticity values ​​in each color area of ​​the invoice can evaluate the quality of the image. The accuracy of the chromaticity value can reflect key information such as the clarity and color reproduction of the invoice image. If the chromaticity value of the invoice image deviates significantly from the standard value, it may mean that the image has problems such as blur, stains or color distortion. By combining the chromaticity value of the invoice, the financial recognition inaccuracy rate and the financial recognition missing rate, the accuracy of the invoice quality assessment can be improved, thereby improving the efficiency of invoice management and ensuring the accuracy and completeness of information in the financial data management system.

[0090] Specifically, the invoice analysis module determines whether to store the invoice.

[0091] If the invoice storability tendency characterization value of the invoice is less than a preset invoice storability tendency characterization value comparison threshold, determining to store the invoice;

[0092] If the invoice storability tendency characterization value of the invoice is greater than or equal to a preset invoice storability tendency characterization value comparison threshold, it is determined that the invoice is not to be stored.

[0093] In this embodiment, the preset invoice storage tendency characterization value comparison threshold is selected within the range of [0, 0.05].

[0094] Specifically, the financial data encryption module is used to set an encryption password for the financial data according to preset rules, wherein the full name of the invoicing company in the financial data is obtained, and the first letter of the full name of the invoicing company is set as the encryption password.

[0095] It is understandable that the financial data includes the full name of the invoicing company. When you need to query the financial data related to the invoicing company, you can search for all related financial data by entering the full name of the invoicing company. After entering the encryption password, you can obtain the permission to view all related financial data. The encryption password is composed of the first letters of each character in the full name of the invoicing company.

[0096] Specifically, the financial data classification unit is also used to obtain the password input error rate of the financial data, wherein the total number of password input times for the financial data and the number of incorrect password input times for the financial data are obtained, and the ratio of the number of incorrect password input times to the total number of password input times is recorded as the password input error rate.

[0097] Specifically, the present invention records the number of times financial data is viewed and the password input error rate of the financial data through a financial data classification unit. In actual situations, the number of times financial data is viewed can reflect to a certain extent that the data has important value to their current work, decision-making or interests, and the password input error rate of the financial data can reflect to a certain extent the security level of the financial data. By obtaining the number of times financial data is viewed and the password input error rate of the financial data, the security and importance of the financial data can be characterized, thereby improving the security of the financial data.

[0098] Specifically, the financial data classification unit is used to classify the financial data according to the number of times the financial data is viewed and the password input error rate of the financial data.

[0099] If the financial data meets the preset conditions, the financial data category is classified as high-risk financial data;

[0100] If the financial data does not meet the preset conditions, the financial data category is classified as low-risk financial data;

[0101] The preset condition is that the number of times the financial data is viewed is greater than a preset viewing number comparison threshold, and the password input error rate of the financial data is greater than a preset password input error rate comparison threshold.

[0102] In this embodiment, the preset viewing times comparison threshold is selected within the range of [5 times, 10 times], and the preset financial data password input error rate comparison threshold is selected within the range of [5%, 10%].

[0103] Specifically, the financial data encryption adjustment unit is used to select a high-risk financial data category and perform secondary encryption on the high-risk financial data category.

[0104] Specifically, the present invention performs secondary encryption on specific financial data categories through a financial data encryption adjustment unit. In actual situations, secondary encryption of all financial data requires excessive computing resources, increases the computing burden of the system, and slows down the processing speed, thereby requiring more time and resources to configure and maintain the encryption system, resulting in increased maintenance costs. By selecting high-risk financial data categories for secondary encryption, the security of financial data can be improved while ensuring the conservation of computing resources.

[0105] In this embodiment, symmetrical encryption is selected for financial data in the high-risk financial data category, and the symmetrical encryption method may be AES.

[0106] Specifically, the financial data includes invoice number, invoice date, invoice issuing company name, invoice receiving company name, amount excluding tax, tax rate, tax amount, amount including tax, product description, quantity, and unit price.

[0107] The modules involved in the embodiments described in this application may be implemented in software or hardware, and may also be set in a processor.

[0108] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the devices, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based device that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0109] Obviously, the above embodiments of the present invention are merely examples for the purpose of clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Those skilled in the art will appreciate that other variations or modifications can be made based on the above description. It is not necessary and impossible to enumerate all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the claims of the present invention.

Claims

1. An intelligent financial data management system based on big data, characterized in that: include: A financial data receiving module, configured to receive uploaded invoices, identify the financial data in the invoices, and receive manually input financial data of the invoices; The invoice analysis module is connected to the financial data receiving module and is used to compare the recognized financial data with the manually input financial data, divide the invoice into color regions based on the clustering color segmentation algorithm, obtain the chromaticity values ​​of several points in each color region, and calculate the invoice storable tendency representation value based on the comparison results and the chromaticity values, including: Compare the chromaticity values ​​of any number of points in each color area with the corresponding preset chromaticity value threshold; Obtain the difference between the chromaticity value of any number of points in each color area and the corresponding preset chromaticity value threshold; Obtaining a ratio of the absolute value of the difference to the corresponding preset chromaticity value threshold, which is recorded as a chromaticity value difference ratio; The invoice storability tendency representation value is obtained by weighted summing the financial recognition inaccuracy rate, the financial recognition missing rate and the color value difference ratio; Determining whether to store the invoice according to the invoice storability representation value; A financial data storage module, connected to the invoice analysis module, for storing invoices and the financial data of the invoices; A financial data encryption module, connected to the financial data storage module, for setting an encryption password for the invoice and the financial data of the invoice according to a preset rule; the preset rule is to obtain the full name of the invoicing company in the financial data and set the first letter of the full name of the invoicing company as the encryption password; The financial data monitoring module is connected to the financial data storage module and includes a financial data classification unit and a financial data encryption adjustment unit. The financial data classification unit is used to record the number of times the financial data is viewed and the password input error rate of the financial data, and classify the financial data into a high-risk financial data category or a low-risk financial data category according to the number of times the financial data is viewed and the password input error rate of the financial data. The method of calculating the password input error rate of the financial data is to obtain the total number of password input times for the financial data and the number of incorrect password input times for the financial data, and record the ratio of the number of incorrect password input times to the total number of password input times as the password input error rate; The financial data encryption adjustment unit is used to select a high-risk financial data category and perform secondary encryption on the high-risk financial data category; The financial data includes invoice number, invoice date, invoice issuing company name, invoice receiving company name, amount excluding tax, tax rate, tax amount, amount including tax, product description, quantity, and unit price.

2. The intelligent financial data management system based on big data according to claim 1, characterized in that: The invoice analysis module is used to compare the identified financial data with the manually input financial data, including: Obtaining identified financial data of invoices and manually entered financial data; Compare each manually input financial data with the corresponding identified financial data in turn; If the manually input financial data is identical to the corresponding identified financial data, it is determined that the financial data is accurately identified; If the manually input financial data is different from the corresponding identified financial data, it is determined that the financial data was not accurately identified; If the manually input financial data does not have corresponding identified financial data, it is determined to be missing identified financial data; The ratio of the number of inaccurately identified financial data to the number of manually input financial data is recorded as the financial identification inaccuracy rate; The ratio of missing identified financial data to the number of manually entered financial data is recorded as the financial identification missing rate.

3. The intelligent financial data management system based on big data according to claim 2, characterized in that: The invoice analysis module is used to divide the invoice into color regions based on the clustering color segmentation algorithm, and obtain the chromaticity values ​​of several points in each color region, including: Use clustering-based color segmentation algorithm to divide the invoice into color regions; Select any number of points in each color area; Get the chromaticity values ​​of any points in each color area.

4. The intelligent financial data management system based on big data according to claim 1, characterized in that: The invoice analysis module determines whether to store the invoice, If the invoice storability tendency characterization value of the invoice is less than a preset invoice storability tendency characterization value comparison threshold, determining to store the invoice; If the invoice storability tendency characterization value of the invoice is greater than or equal to a preset invoice storability tendency characterization value comparison threshold, it is determined that the invoice is not to be stored.

5. The intelligent financial data management system based on big data according to claim 1, characterized in that: The financial data classification unit is used to classify the financial data according to the number of times the financial data is viewed and the password input error rate of the financial data. If the financial data meets the preset conditions, the financial data category is classified as high-risk financial data; If the financial data does not meet the preset conditions, the financial data category is classified as low-risk financial data; The preset condition is that the number of times the financial data is viewed is greater than a preset viewing number comparison threshold, and the password input error rate of the financial data is greater than a preset password input error rate comparison threshold.

Images