Method for automatically classifying economic subjects during invoice reimbursement through OCR (Optical Character Recognition) under big data

Abstract

The invention provides a method for automatically classifying economic subjects during OCR invoice reimbursement under big data. The method comprises the following steps: S1, uploading an electronic invoice to a financial platform; s2, the financial platform identifies data information in the electronic invoice by using an OCR identification technology; and S3, the financial platform classifies the electronic invoices according to the identified data information. According to the invention, the electronic invoices can be classified and managed according to the item names identified by using the OCR identification technology, and the security privacy of the electronic invoices is ensured in the uploading process.

Description

Technical Field

[0001] The present invention relates to the technical field of invoice reimbursement classification, and particularly to an automatic classification method for economic subjects when OCR recognizes invoices for reimbursement under big data. Background Art

[0002] With the rapid development of mobile Internet, digital electronic invoices, as a new type of bill, are increasingly favored by the market due to their convenience, quickness, and ease of verification and management. Patent Application No. 2024116613555, titled "Delivery Method, Device, Storage Medium and Server for Digital Electronic Invoices", discloses the following steps: obtaining invoicing information; verifying the integrity and correctness of the invoicing information; if the verification passes, generating a digital electronic invoice in an electronic file format according to the invoicing information; performing a signature process on the original digital electronic invoice using a private key; querying the pre-set email address of the recipient according to the invoicing information; and sending the signed digital electronic invoice to the recipient according to the email address. This can effectively prevent data tampering and forgery, thus greatly enhancing the security of digital electronic invoices. Moreover, by implementing processes such as subscription and automated processing, manual operations and interventions are reduced, making the generation, transmission, and delivery processes of digital electronic invoices more efficient and quick. However, this patent application does not classify electronic invoices, which requires a large amount of working time. Summary of the Invention

[0003] The present invention aims to at least solve the technical problems existing in the prior art, and particularly innovatively proposes an automatic classification method for economic subjects when OCR recognizes invoices for reimbursement under big data.

[0004] To achieve the above object of the present invention, the present invention provides an automatic classification method for economic subjects when OCR recognizes invoices for reimbursement under big data, including the following steps:

[0005] S1, uploading the electronic invoice to the financial platform;

[0006] S2, the financial platform uses OCR recognition technology to recognize the data information in the electronic invoice, and the data information includes one or any combination of invoice number, invoicing time, purchaser information, seller information, project name, and total amount of price and tax;

[0007] The purchaser information includes the purchaser name or / and the purchaser's unified social credit code / taxpayer identification number;

[0008] The seller information includes the seller name or / and the seller's unified social credit code / taxpayer identification number;

[0009] S3, the financial platform classifies the electronic invoice according to the recognized data information.

[0010] In a preferred embodiment of the present invention, step S1 includes the following steps:

[0011] S11, log in to the financial platform;

[0012] S12, after logging in to the financial platform, select the e-invoice to be uploaded;

[0013] S13, upload the selected e-invoice to be uploaded to the financial platform.

[0014] In a preferred embodiment of the present invention, the economic subjects in step S3 include one or any combination of office expenses, printing fees, consulting fees, handling fees, water fees, electricity fees, postal and telecommunications fees, heating fees, travel expenses, rental fees, conference fees, training fees, official reception fees, special material fees, equipment purchase fees, clothing purchase fees, special fuel fees, labor fees, entrusted business fees, trade union funds, welfare fees, official vehicle operation and maintenance fees, and other transportation expenses.

[0015] In a preferred embodiment of the present invention, step S11 includes the following steps:

[0016] S111, the uploader enters the account number and password on the login interface;

[0017] S112, after the uploader enters the account number and password on the login interface, upload the account number and password entered by the uploader on the login interface to the financial platform;

[0018] S113, after the financial platform receives the account number and password, determine whether the received account number and password exist in the financial platform:

[0019] S1131, determine whether the received account number exists in the financial platform:

[0020] If the received account number exists in the financial platform, proceed to the next step;

[0021] If the received account number does not exist in the financial platform, the uploader cannot log in to the financial platform and cannot upload e-invoices to the financial platform;

[0022] S115, search for the password stored in the financial platform with the received account number, and determine whether the received password is the same as the password stored in the financial platform:

[0023] If the received password is the same as the password stored in the financial platform, the uploader logs in to the financial platform and can upload e-invoices to the financial platform;

[0024] If the received password is not the same as the password stored in the financial platform, the uploader cannot log in to the financial platform and cannot upload e-invoices to the financial platform.

[0025] In a preferred embodiment of the present invention, the method for classifying electronic invoices by economic subjects in step S3 includes the following steps:

[0026] S31, extract the keywords in the project name; let the subject serial number τ = 1;

[0027] S32, determine whether the extracted keyword belongs to the τ-th subject:

[0028] If the extracted keyword belongs to the τ-th subject, classify the electronic invoice as the τ-th subject and put the electronic invoice into the τ-th subject set;

[0029] If the extracted keyword does not belong to the τ-th subject, then τ = τ + 1 and execute the next step;

[0030] S33, determine the relationship between τ and :

[0031] If then classify the electronic invoice as the th subject, and put the electronic invoice into the th subject set; the subject classification is completed;

[0032] If then execute step S32.

[0033] In a preferred embodiment of the present invention, step S13 includes the following steps:

[0034] S131, process the electronic invoice into a black-and-white electronic invoice;

[0035] S132, perform pixel value transformation on all pixel values in the black-and-white electronic invoice with a preset pixel value;

[0036] S133, upload the transformed electronic invoice to the financial platform;

[0037] S134, after the financial platform receives the electronic invoice, perform pixel value transformation on the received electronic invoice with the preset pixel value to obtain the black-and-white electronic invoice in step S131.

[0038] In a preferred embodiment of the present invention, step S3 also includes the following judgment:

[0039] Judgment 1: Determine whether the recognized purchaser name is the same as the preset purchaser name:

[0040] If the recognized purchaser name is the same as the preset purchaser name, then perform Judgment 2;

[0041] If the recognized purchaser name is not the same as the preset purchaser name, then prompt that the purchaser name in the electronic invoice is incorrect;

[0042] Judgment Two: Determine whether the unified social credit code / taxpayer identification number of the identified purchaser is the same as the preset unified social credit code / taxpayer identification number of the purchaser:

[0043] If the unified social credit code / taxpayer identification number of the identified purchaser is the same as the preset unified social credit code / taxpayer identification number of the purchaser, the purchaser information is completely correct;

[0044] If the unified social credit code / taxpayer identification number of the identified purchaser is different from the preset unified social credit code / taxpayer identification number of the purchaser, it is prompted that the unified social credit code / taxpayer identification number of the purchaser in the electronic invoice is incorrect.

[0045] In a preferred embodiment of the present invention, in step S3, it also includes statistical classification of economic subject expenses:

[0046] Under each subject set, it includes:

[0047] S3-1, extract the invoicing time;

[0048] After extracting the invoicing time, classify the electronic invoices by year and month;

[0049] S3-3, count the monthly expenses of each subject:

[0050]

[0051] Among them, Fee τ,ε is the expense for the τ-th subject in the ε-th month;

[0052] λ τ,η,ε is the expense (total amount of price and tax) of the η-th electronic invoice in the ε-th month of the τ-th subject;

[0053] τ ε is the number of electronic invoices in the ε-th month of the τ-th subject;

[0054] ε = 1, 2, 3,..., 12;

[0055] η = 1, 2, 3,..., τ ε ;

[0056] is the number of subjects;

[0057] S3-4, count the annual expenses of each subject:

[0058]

[0059] Among them, Fee τ is the expense for the τ-th subject;

[0060] Fee τ,ε is the expense for the τ-th subject in the ε-th month;

[0061] S3 - 5, Statistics of annual expenses:

[0062]

[0063] where Fee year is the annual expense;

[0064] Fee τ is the expense for the τ-th subject;

[0065] The method of processing the electronic invoice into a black - and - white electronic invoice in step S131 is:

[0066] Gray(i,j) = 0.299*R(i,j)+0.587*G(i,j)+0.114*B(i,j),

[0067] where Gray(i,j) is the pixel value at the pixel point (i,j);

[0068] R(i,j) is the red pixel value at the pixel point (i,j);

[0069] G(i,j) is the green pixel value at the pixel point (i,j);

[0070] B(i,j) is the blue pixel value at the pixel point (i,j);

[0071] Or / and the method of performing pixel value transformation on all pixel values in the black - and - white electronic invoice and a preset pixel value in step S132 is:

[0072]

[0073] where Gray′(i,j) k is the value after the k - th numerical transformation of the pixel value Gray(i,j);

[0074] Gray(i,j) k is the k - th value of the pixel value Gray(i,j);

[0075] ∧ represents the transformation symbol;

[0076] valuestring is the preset pixel value;

[0077] valuestring k represents the k - th value in the preset pixel value valuestring;

[0078] i = 1, 2, 3, ……, I;

[0079] j = 1, 2, 3, ……, J;

[0080] k = 1, 2, 3, ……, K;

[0081] I, J, and K are the three parameters of the electronic invoice, namely the number of pixels in the width and height directions and the number of bits of the pixel value.

[0082] The present invention also discloses a computer system, including:

[0083] A processor;

[0084] A memory for storing instructions executable by the processor;

[0085] Wherein, when the processor is configured to execute the executable instructions, it implements the method for automatic classification of economic subjects during OCR recognition of invoice reimbursement under big data.

[0086] The present invention also discloses a computer-readable storage medium, including:

[0087] A memory having a computer program stored thereon;

[0088] A processor for executing the program in the memory to implement the method for automatic classification of economic subjects during OCR recognition of invoice reimbursement under big data.

[0089] In summary, due to the adoption of the above technical solution, the present invention can classify and manage electronic invoices according to the item names recognized by using OCR recognition technology, and ensure the security and privacy of electronic bills during the uploading process.

[0090] The additional aspects and advantages of the present invention will be partially given in the following description, partially become apparent from the following description, or be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] The above and / or additional aspects and advantages of the present invention will become apparent and easy to understand from the description of the embodiments in conjunction with the following drawings, where:

[0092] Figure 1 is a flowchart of the present invention.

[0093] Figure 2 is a schematic diagram of the display of the electronic invoice of the present invention.

[0094] Figure 3 is a schematic diagram of the display of the electronic invoice of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0095] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0096] The present invention discloses a method for automatically classifying economic subjects when OCR recognizes invoice reimbursement under big data, such as Figure 1 As shown, the following steps are included:

[0097] S1, upload the electronic invoice to the financial platform;

[0098] S2, the financial platform uses OCR recognition technology to identify the data information in the electronic invoice, which includes one or any combination of invoice number, invoice time, buyer information, seller information, item name, and price and tax total;

[0099] The purchaser's information includes the purchaser's name and / or the purchaser's unified social credit code / taxpayer identification number;

[0100] Seller information includes seller name and / or seller unified social credit code / taxpayer identification number;

[0101] S3, the financial platform classifies the electronic invoices based on the identified data information.

[0102] In a preferred embodiment of the present invention, step S1 includes the following steps:

[0103] S11, log in to the financial platform;

[0104] S12, after logging into the financial platform, select the electronic invoice to be uploaded;

[0105] S13, uploading the selected electronic invoice to be uploaded to the financial platform.

[0106] In a preferred embodiment of the present invention, the economic items in step S3 include office expenses, printing fees, consulting fees, handling fees, water charges, electricity charges, postage and telecommunications charges, heating charges, property management fees, travel expenses, official overseas travel expenses, maintenance (care) fees, rental fees, conference fees, training fees, official reception expenses, special material fees, equipment purchase fees, clothing purchase fees, special fuel fees, labor fees, entrusted business fees, union funds, welfare fees, official vehicle operation and maintenance fees, other transportation costs, taxes and additional fees, or any combination thereof.

[0107] Among them, office expenses: used to purchase daily office supplies, stationery, etc.;

[0108] Printing fee: used to pay for the printing of documents and materials;

[0109] Consulting fees: Payments to professional organizations or individuals for consulting services;

[0110] Handling fee: the handling fee paid in the process of handling various businesses;

[0111] Water fee: used to pay for water expenses in the office;

[0112] Electricity bill: used to pay for electricity expenses in the office;

[0113] Postage and telecommunications fees: used to pay for mail, telephone, Internet and other communication expenses;

[0114] Heating fee: used to pay for heating the office space in winter;

[0115] Property management fee: used to pay for the property management fee of the office space;

[0116] Travel expenses: transportation, accommodation and other expenses incurred by staff on business trips;

[0117] Expenses for official trips abroad: Expenses incurred by staff for official trips abroad or overseas inspections and visits; Repair (maintenance) expenses: used to pay for the repair and maintenance of office facilities and equipment;

[0118] Rental fees: used to pay for the costs of renting office space, equipment, etc.;

[0119] Conference expenses: expenses for venue, equipment, catering, etc. incurred in organizing and holding a meeting;

[0120] Training fees: used to pay for staff to participate in various types of training;

[0121] Official reception expenses: expenses for various official receptions (including reception of foreign guests) in accordance with regulations;

[0122] Special material expenses: expenses for purchasing special materials required for specific work;

[0123] Equipment purchase expenses: expenses for purchasing equipment required for specific work;

[0124] Cost of purchasing bedding: used to purchase bedding required by staff;

[0125] Dedicated fuel fee: used to pay for the fuel required for a specific job;

[0126] Labor costs: fees paid to external labor providers, such as temporary labor, expert consultation, etc.;

[0127] Entrusted business fees: Entrusted business fees paid for entrusting external units to handle business;

[0128] Union funds: Expenses for union activities;

[0129] Welfare expenses: Used to pay for the welfare expenses of staff, such as holiday gifts, physical examination fees, etc.;

[0130] Operating and maintenance expenses for official vehicles: Used to pay for the operation and maintenance of official vehicles, including fuel costs, maintenance costs, insurance premiums, tolls, etc.;

[0131] Other transportation expenses: Other transportation expenses other than the operating and maintenance expenses of official vehicles, such as intracity transportation expenses, taxi fares, etc.;

[0132] Taxes and surcharges: Taxes and surcharges incurred during the purchase of goods and services;

[0133] In a preferred embodiment of the present invention, step S11 includes the following steps:

[0134] S111, the uploader enters the account number and password on the login interface;

[0135] S112, after the uploader enters the account number and password on the login interface, the account number and password entered by the uploader on the login interface are uploaded to the financial platform;

[0136] S113, after the financial platform receives the account number and password, it determines whether the received account number and password exist in the financial platform:

[0137] S1131, determine whether the received account number exists in the financial platform:

[0138] If the received account number exists in the financial platform, proceed to the next step;

[0139] If the received account number does not exist in the financial platform, the uploader cannot log in to the financial platform and cannot upload electronic invoices to the financial platform;

[0140] S115, search for the password stored in the financial platform with the received account number, and determine whether the received password is the same as the password stored in the financial platform:

[0141] If the received password is the same as the password stored in the financial platform, the uploader logs in to the financial platform and can upload electronic invoices to the financial platform;

[0142] If the received password is not the same as the password stored in the financial platform, the uploader cannot log in to the financial platform and cannot upload electronic invoices to the financial platform.

[0143] In a preferred embodiment of the present invention, the method for classifying electronic invoices by economic subjects in step S3 includes the following steps:

[0144] S31. Extract the keywords in the project name; let the subject serial number τ = 1;

[0145] S32. Determine whether the extracted keywords belong to the τ-th subject:

[0146] If the extracted keywords belong to the τ-th subject, classify the electronic invoice as the τ-th subject and put the electronic invoice into the set of the τ-th subject;

[0147] If the extracted keywords do not belong to the τ-th subject, then τ = τ + 1 and execute the next step;

[0148] S33. Determine the relationship between τ and :

[0149] If then classify the electronic invoice as the subject and put the electronic invoice into the subject set; the subject classification is completed;

[0150] If then execute step S32.

[0151] In a preferred embodiment of the present invention, step S13 includes the following steps:

[0152] S131. Process the electronic invoice as shown in Figure 2 into a black-and-white electronic invoice as shown in Figure 3 ;

[0153] S132. Perform pixel value transformation on all pixel values in the black-and-white electronic invoice with a preset pixel value;

[0154] S133. Upload the transformed electronic invoice to the financial platform;

[0155] S134. After the financial platform receives the electronic invoice, perform pixel value transformation on the received electronic invoice with a preset pixel value to obtain the black-and-white electronic invoice in step S131.

[0156] In a preferred embodiment of the present invention, the following judgment is further included in step S3:

[0157] Judgment 1: Determine whether the recognized purchaser name is the same as the preset purchaser name:

[0158] If the recognized purchaser name is the same as the preset purchaser name, then perform Judgment 2;

[0159] If the recognized purchaser name is not the same as the preset purchaser name, then prompt that the purchaser name in the electronic invoice is incorrect;

[0160] Judgment Two: Determine whether the unified social credit code / taxpayer identification number of the identified purchaser is the same as the preset unified social credit code / taxpayer identification number of the purchaser:

[0161] If the unified social credit code / taxpayer identification number of the identified purchaser is the same as the preset unified social credit code / taxpayer identification number of the purchaser, then the purchaser information is completely correct;

[0162] If the unified social credit code / taxpayer identification number of the identified purchaser is different from the preset unified social credit code / taxpayer identification number of the purchaser, then prompt that the unified social credit code / taxpayer identification number of the purchaser in the electronic invoice is incorrect.

[0163] In a preferred embodiment of the present invention, the preset pixel value in step S132 is the same as the preset pixel value in step S134.

[0164] In a preferred embodiment of the present invention, in step S3, it further includes counting the expenses classified by economic subjects:

[0165] Under each subject set, it includes:

[0166] S3-1, extract the invoicing time;

[0167] S3-2, after extracting the invoicing time, classify the electronic invoices by year and month;

[0168] S3-3, count the monthly expenses of each subject:

[0169]

[0170] Among them, Fee τ,ε is the expense for the τ-th subject in the ε-th month;

[0171] λ τ,η,ε is the expense (total amount of tax and price) of the η-th electronic invoice in the ε-th month of the τ-th subject;

[0172] τ ε is the number of electronic invoices in the ε-th month of the τ-th subject;

[0173] ε = 1, 2, 3,..., 12;

[0174] η = 1, 2, 3,..., τ ε ;

[0175] is the number of subjects;

[0176] S3-4, count the annual expenses of each subject:

[0177]

[0178] Among them, Fee τ is the expense for the τ-th subject;

[0179] Fee τ,ε is the expense for the τ-th subject in the ε-th month;

[0180] S3-5. Statistic the annual expense:

[0181]

[0182] Among them, Fee year is the annual expense;

[0183] Fee τ is the expense for the τ-th subject.

[0184] The method of processing the electronic invoice into a black-and-white electronic invoice in step S131 is as follows:

[0185] Gray(i,j) = 0.299 * R(i,j) + 0.587 * G(i,j) + 0.114 * B(i,j),

[0186] where Gray(i,j) is the pixel value at the pixel point (i,j);

[0187] R(i,j) is the red pixel value at the pixel point (i,j);

[0188] G(i,j) is the green pixel value at the pixel point (i,j);

[0189] B(i,j) is the blue pixel value at the pixel point (i,j).

[0190] In a preferred embodiment of the present invention, the method of performing pixel value transformation on all pixel values in the black-and-white electronic invoice with a preset pixel value in step S132 is as follows:

[0191]

[0192] where Gray′(i,j) k is the value after the k-th numerical transformation of the pixel value Gray(i,j);

[0193] Gray(i,j) k is the k-th value of the pixel value Gray(i,j);

[0194] ∧ represents the transformation symbol;

[0195] The valuestring is a preset pixel value; the preset pixel value is a binary value, the number of digits of which is equal to K, and the corresponding pixel value Gray(i,j) is also a binary value. K is the maximum number of digits among all pixel values in the black-and-white electronic invoice; if the number of digits of other pixel values is less than K, 0 is added in front of the pixel value to make up the deficiency.

[0196] valuestring k represents the k-th value in the preset pixel value valuestring;

[0197] i = 1, 2, 3,..., I;

[0198] j = 1, 2, 3,..., J;

[0199] k = 1, 2, 3,..., K;

[0200] I, J, and K are the three parameters of the electronic invoice, namely the number of pixels in the width and height directions and the number of digits of the pixel value.

[0201] For example, if the pixel value of a certain point in the black-and-white electronic invoice is 11010111(215), K = 8, and the preset pixel value is 11010011, then the transformed pixel value is 00000100, which can also be expressed as 100. Another example, if the pixel value of a certain point in the black-and-white electronic invoice is 1010011(123), then the transformed pixel value is 10000000.

[0202] In a preferred embodiment of the present invention, the method of performing pixel value transformation on the received electronic invoice and the preset pixel value in step S134 is as follows:

[0203]

[0204] where Gray″′(i″′,j″′) k″′ is the value after transformation of the k″′-th value in the pixel value Gray″′(i″′,j″′) in the received electronic invoice;

[0205] Gray″(i″′,j″′) k″′ is the k″′-th value in the pixel value Gray″(i″′,j″′) in the received electronic invoice;

[0206] ∧ represents the transformation symbol;

[0207] The valuestring is the preset pixel value;

[0208] valuestring k″′ represents the k″′-th value in the preset pixel value valuestring;

[0209] Gray″′(i″′,j″′) is the transformed pixel value at the pixel point (i″′,j″′) in the received electronic invoice;

[0210] Gray″(i″′,j″′) is the pixel value at the pixel point (i″′,j″′) in the received electronic invoice;

[0211] i″′ = 1, 2, 3, ……, I;

[0212] j″′ = 1, 2, 3, ……, J;

[0213] k″′ = 1, 2, 3, ……, K;

[0214] I, J, and K are the three parameters of the electronic invoice, the number of pixels in the width and height directions, and the number of bits of the pixel value, respectively.

[0215] The present invention also discloses a computer system, including:

[0216] A processor;

[0217] A memory for storing processor-executable instructions;

[0218] Wherein, when the processor is configured to execute the executable instructions, it implements the method for automatically classifying economic subjects during OCR recognition of invoice reimbursement under big data.

[0219] The present invention also discloses a computer-readable storage medium, including:

[0220] A memory having a computer program stored thereon;

[0221] A processor for executing the program in the memory to implement the method for automatically classifying economic subjects during OCR recognition of invoice reimbursement under big data.

[0222] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the claims and their equivalents.

Claims

1. A method for automatically classifying economic subjects when OCR recognizes invoice reimbursement under big data, characterized in that: The following steps are involved: S1, upload the electronic invoice to the financial platform; S2, the financial platform uses OCR recognition technology to identify the data information in the electronic invoice, which includes one or any combination of invoice number, invoice time, buyer information, seller information, item name, and price and tax total; The purchaser's information includes the purchaser's name and / or the purchaser's unified social credit code / taxpayer identification number; Seller information includes seller name and / or seller unified social credit code / taxpayer identification number; S3, the financial platform classifies the electronic invoices based on the identified data information.

2. The method for automatic classification of economic subjects when OCR recognizes invoice reimbursement under big data according to claim 1 is characterized in that: Step S1 includes the following steps: S11, log in to the financial platform; S12, after logging into the financial platform, select the electronic invoice to be uploaded; S13, uploading the selected electronic invoice to be uploaded to the financial platform.

3. The method for automatic classification of economic subjects when OCR recognizes invoice reimbursement under big data according to claim 1 is characterized in that: The economic items in step S3 include office expenses, printing fees, consulting fees, handling fees, water charges, electricity charges, postage and telecommunications charges, heating charges, travel expenses, rental fees, conference fees, training fees, official reception fees, special material fees, equipment purchase fees, clothing purchase fees, special fuel fees, labor fees, entrusted business fees, union funds, welfare fees, official vehicle operation and maintenance fees, and other transportation expenses, or any combination thereof.

4. The method for automatic classification of economic subjects when OCR recognizes invoice reimbursement under big data according to claim 1 is characterized in that: Step S11 includes the following steps: S111, the uploader enters the account number and password on the login interface; S112, after the uploader enters the account number and password on the login interface, the account number and password entered by the uploader on the login interface are uploaded to the financial platform; S113, after receiving the account number and password, the financial platform determines whether the received account number and password exist on the financial platform: S1131, determine whether the received account exists on the financial platform: If the received account number exists in the financial platform, proceed to the next step; If the received account does not exist on the financial platform, the uploader cannot log in to the financial platform and cannot upload electronic invoices to the financial platform; S115, searching the password stored in the financial platform with the received account number, and determining whether the received password is the same as the password stored in the financial platform: If the received password is the same as the password stored in the financial platform, the uploader logs in to the financial platform and can upload the electronic invoice to the financial platform; If the received password is different from the password stored in the financial platform, the uploader cannot log in to the financial platform and cannot upload electronic invoices to the financial platform.

5. The method for automatic classification of economic subjects when OCR recognizes invoice reimbursement under big data according to claim 1 is characterized in that: The method for classifying the economic subjects of the electronic invoice in step S3 includes the following steps: S31, extract keywords from the project name; set the subject number τ = 1; S32, judging whether the extracted keywords belong to the τth subject: If the extracted keyword belongs to the τth subject, the electronic invoice is classified as the τth subject and the electronic invoice is placed in the τth subject set; If the extracted keyword does not belong to the τth subject, then τ=τ+1, and proceed to the next step; S33, judge τ and The relationship between: like The electronic invoice is classified as Subject, put the electronic invoice into Subject collection; subject classification completed; like Then execute step S32.

6. The method for automatic classification of economic subjects when OCR recognizes invoice reimbursement under big data according to claim 1 is characterized in that: Step S13 includes the following steps: S131, processing the electronic invoice into a black and white electronic invoice; S132, performing pixel value conversion on all pixel values ​​of the black-and-white electronic invoice and preset pixel values; S133, uploading the transformed electronic invoice to the financial platform; S134, after the financial platform receives the electronic invoice, it performs pixel value conversion on the received electronic invoice and the preset pixel value to obtain the black and white electronic invoice in step S131.

7. The method for automatic classification of economic subjects when OCR recognizes invoice reimbursement under big data according to claim 1 is characterized in that: Step S3 also includes the following judgment: Judgment 1: Determine whether the identified buyer name is the same as the preset buyer name: If the identified purchaser name is the same as the preset purchaser name, judgment 2 is performed; If the identified buyer's name is different from the preset buyer's name, it will prompt that the buyer's name in the electronic invoice is wrong; Judgment 2: Judgment whether the identified unified social credit code / taxpayer identification number of the purchaser is the same as the preset unified social credit code / taxpayer identification number of the purchaser: If the identified unified social credit code / taxpayer identification number of the purchaser is the same as the preset unified social credit code / taxpayer identification number of the purchaser, the purchaser information is completely correct; If the identified unified social credit code / taxpayer identification number of the purchaser is different from the preset unified social credit code / taxpayer identification number of the purchaser, it will be prompted that the unified social credit code / taxpayer identification number of the purchaser in the electronic invoice is incorrect.

8. The method for automatic classification of economic subjects when OCR recognizes invoice reimbursement under big data according to claim 1 is characterized in that: In step S3, the following economic account classification expenses are also included: Each subject set includes: S3-1, extract the invoicing time; S3-2, after extracting the invoice time, classify the electronic invoice by year and month; S3-3, statistics of monthly expenses of each subject: Among them, Fee τ,ε is the expenditure cost of the τth item in the εth month; λ τ,η,ε The electronic invoice expense (total price and tax) for the ηth month in the εth account; τ ε is the number of electronic invoices in the εth month in the τth account; ε=1, 2, 3,..., 12; n = 1、2、3、……、t ε ; is the number of subjects; S3-4, statistics of annual expenditures of each subject: Among them, Fee τ is the expenditure cost of the τth item; Fee τ,ε is the expenditure cost of the τth item in the εth month; S3-5, statistics of annual expenses: Among them, Fee year The expenses for the current year; Fee τ is the expense of the τth item.

9. A computer system, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the method for automatic classification of economic subjects when OCR recognizes invoice reimbursement under big data as described in one of claims 1 to 8 when executing the executable instructions.

10. A computer-readable storage medium, characterized in that: include: a memory having a computer program stored thereon; A processor is used to execute the program in the memory to implement the method for automatically classifying economic subjects when OCR recognizes invoice reimbursement under big data as described in one of claims 1 to 8.

Images