Method, device, terminal and storage medium for automatically processing tax refund data

Abstract

The present application relates to the field of data processing technology, and specifically to a method, device, terminal and storage medium for automatically processing tax refund data. The method includes: obtaining shipping plan information of a target user; extracting product information from the shipping plan information to obtain target product information; matching the invoice and customs declaration documents of the target product information to obtain target invoice information and target customs declaration documents; generating tax refund declaration information based on the target product information, the target invoice information and the target customs declaration documents; sending the tax refund declaration information to a tax refund system to instruct the tax refund system to perform tax refund processing, thereby improving the accuracy of automated processing of tax refund data.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, terminal and storage medium for automatically processing tax refund data. Background Art

[0002] Exporters must navigate a complex tax refund declaration process to obtain refunds. Traditionally, this process involves processing a large number of paper and electronic documents, including customs declarations, invoices, shipping plans, and bank exchange receipts. These documents come in various formats and contain vast amounts of data, requiring significant manpower to capture data, identify and match documents, and submit declarations.

[0003] In existing solutions, a large amount of manual intervention by personnel with professional knowledge is still required when processing tax refund data, resulting in low efficiency in processing tax refund data. Summary of the Invention

[0004] The embodiments of the present application provide a method, device, terminal and storage medium for automatically processing tax refund data, which can automatically extract the shipping plan information of the target user and match the corresponding invoice information and customs declaration documents, and finally automatically generate tax refund declaration information for tax refund application, thereby improving the efficiency of processing tax refund data.

[0005] A first aspect of an embodiment of the present application provides a method for automatically processing tax refund data, the method comprising:

[0006] Obtain the target user's delivery plan information;

[0007] Extracting product information from the delivery plan information to obtain target product information;

[0008] Matching the invoice and customs declaration documents of the target commodity information to obtain target invoice information and target customs declaration documents;

[0009] Generate tax refund declaration information based on the target commodity information, the target invoice information and the target customs declaration document;

[0010] The tax refund declaration information is sent to the tax refund system to instruct the tax refund system to perform tax refund processing.

[0011] In one possible implementation, matching the target commodity information with the invoice and the customs declaration document to obtain the target invoice information and the target customs declaration document includes:

[0012] Extracting the supplier name and product name from the target product information;

[0013] Performing an initial matching of the invoice and the customs declaration document based on the commodity name and the supplier name to obtain a first invoice matching result and a first customs declaration document matching result;

[0014] If the first invoice matching result and / or the first customs declaration document matching result is empty, performing product name association processing on the product name to obtain a first associated product name set;

[0015] Performing a secondary match between the invoice and the customs declaration document based on the first associated commodity name in the first associated commodity name set to obtain a second invoice matching result set and a second customs declaration document matching result set;

[0016] Extracting the first associated matching information corresponding to the second invoice matching result from the second invoice matching result set to obtain a first associated matching information set, and extracting the second associated matching information corresponding to the second customs declaration document matching result from the second customs declaration document matching result set to obtain a second associated matching information set;

[0017] According to the first associated matching information set, the target invoice information corresponding to the target commodity information is determined from the second invoice matching result set, and according to the second associated matching information set, the target customs declaration document corresponding to the target commodity information is determined from the second customs declaration document matching result set.

[0018] In one possible implementation, determining target invoice information corresponding to the target commodity information from the second invoice matching result set according to the first associated matching information set includes:

[0019] determining the number of times the invoice information in the corresponding invoice matching result is successfully associated and matched based on the first associated matching information in the first associated matching information set, to obtain a matching number set;

[0020] Extracting second invoice matching results with zero matching times from the second invoice matching result set according to the matching times set to obtain a reference invoice matching result set;

[0021] Determining a transaction party information set and a transaction time information set based on the reference invoice matching result set;

[0022] Obtaining user information corresponding to the target user to obtain target user information;

[0023] Determining a preliminary invoice matching result set based on the transaction party information set and the target user information;

[0024] Extracting k suspected target invoice information from the preliminary invoice matching result set according to the transaction time information set;

[0025] The k pieces of suspected target invoice information are verified to obtain target invoice information corresponding to the target commodity information.

[0026] In a possible implementation, verifying the k pieces of suspected target invoice information to obtain target invoice information corresponding to the target commodity information includes:

[0027] n suspected target customs declaration documents in the process of determining the target customs declaration document corresponding to the target commodity information from the second customs declaration document matching result set according to the second associated matching information set;

[0028] Verification is performed using n suspected target customs declaration documents and k suspected target invoice information, and the suspected target invoice information among the suspected target customs declaration documents and suspected target invoice information that match each other is determined as the target invoice information corresponding to the target commodity information.

[0029] In one possible implementation, extracting product information from the delivery plan information to obtain target product information includes:

[0030] Perform text recognition on the delivery plan information to obtain text recognition results;

[0031] Performing keyword extraction on the text recognition result to obtain a keyword set;

[0032] The target product information is determined according to the keyword set.

[0033] A second aspect of an embodiment of the present application provides a device for automatically processing tax refund data, the device comprising:

[0034] An acquisition unit, used to obtain the target user's delivery plan information;

[0035] an extraction unit, configured to extract commodity information from the delivery plan information to obtain target commodity information;

[0036] a matching unit, configured to match the target commodity information with an invoice and a customs declaration document to obtain target invoice information and target customs declaration documents;

[0037] A generating unit, configured to generate tax refund declaration information based on the target commodity information, the target invoice information, and the target customs declaration document;

[0038] The sending unit is used to send the tax refund declaration information to the tax refund system to instruct the tax refund system to perform tax refund processing.

[0039] In one possible implementation, the matching unit is specifically configured to:

[0040] Extracting the supplier name and product name from the target product information;

[0041] Performing an initial matching of the invoice and the customs declaration document based on the commodity name and the supplier name to obtain a first invoice matching result and a first customs declaration document matching result;

[0042] If the first invoice matching result and / or the first customs declaration document matching result is empty, performing product name association processing on the product name to obtain a first associated product name set;

[0043] Performing a secondary match between the invoice and the customs declaration document based on the first associated commodity name in the first associated commodity name set to obtain a second invoice matching result set and a second customs declaration document matching result set;

[0044] Extracting the first associated matching information corresponding to the second invoice matching result from the second invoice matching result set to obtain a first associated matching information set, and extracting the second associated matching information corresponding to the second customs declaration document matching result from the second customs declaration document matching result set to obtain a second associated matching information set;

[0045] According to the first associated matching information set, the target invoice information corresponding to the target commodity information is determined from the second invoice matching result set, and according to the second associated matching information set, the target customs declaration document corresponding to the target commodity information is determined from the second customs declaration document matching result set.

[0046] In one possible implementation, in determining the target invoice information corresponding to the target commodity information from the second invoice matching result set based on the first associated matching information set, the matching unit is specifically configured to:

[0047] determining the number of times the invoice information in the corresponding invoice matching result is successfully associated and matched based on the first associated matching information in the first associated matching information set, to obtain a matching number set;

[0048] Extracting second invoice matching results with zero matching times from the second invoice matching result set according to the matching times set to obtain a reference invoice matching result set;

[0049] Determining a transaction party information set and a transaction time information set based on the reference invoice matching result set;

[0050] Obtaining user information corresponding to the target user to obtain target user information;

[0051] Determining a preliminary invoice matching result set based on the transaction party information set and the target user information;

[0052] Extracting k suspected target invoice information from the preliminary invoice matching result set according to the transaction time information set;

[0053] The k pieces of suspected target invoice information are verified to obtain target invoice information corresponding to the target commodity information.

[0054] A third aspect of an embodiment of the present application provides a terminal, comprising a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions and execute the step instructions in the first aspect of the embodiment of the present application.

[0055] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, wherein the above-mentioned computer-readable storage medium stores a computer program for electronic data exchange, wherein the above-mentioned computer program enables a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application.

[0056] A fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to perform some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

[0057] Implementing the embodiments of the present application has at least the following beneficial effects:

[0058] By acquiring the target user's shipping plan information, extracting commodity information from the shipping plan information to obtain target commodity information, matching the target commodity information with invoices and customs declaration documents to obtain target invoice information and target customs declaration documents, generating tax refund declaration information based on the target commodity information, the target invoice information and the target customs declaration documents, and sending the tax refund declaration information to the tax refund system to instruct the tax refund system to perform tax refund processing, the target user's shipping plan information can be automatically extracted and the corresponding invoice information and customs declaration documents can be matched, and finally the tax refund declaration information can be automatically generated to apply for tax refund, thereby improving the efficiency of processing tax refund data. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0060] Figure 1 A flowchart of a method for automatically processing tax refund data is provided for an embodiment of the present application;

[0061] Figure 2 A schematic diagram of the structure of a terminal provided in an embodiment of the present application;

[0062] Figure 3 A schematic structural diagram of a device for automatically processing tax refund data is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0064] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0065] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0066] In order to better understand the method for automatically processing tax refund data provided by the embodiment of the present application, the existing tax refund methods are first briefly introduced below. In the existing scheme, when processing customs-related tax refunds, the traditional OCR (Optical Character Recognition) technology is mainly used to identify documents, and a simple rule matching method is used to match documents. However, the recognition accuracy of traditional OCR technology for documents in complex formats is not high, and the rule matching method lacks flexibility and cannot adapt to changing business needs. In addition, these technologies are usually difficult to handle shipping plans and exchange settlement documents in different formats, and a large amount of manual participation is required for matching and other processing, which makes the efficiency low when reimbursing documents, and the accuracy is also low.

[0067] In order to solve the above problems, the embodiment of the present application provides a method for automatically processing tax refund data, which can automatically extract the target user's shipping plan information and match the corresponding invoice information and customs declaration documents, and finally automatically generate tax refund declaration information for tax refund application, thereby improving the efficiency of processing tax refund data.

[0068] See also Figure 1 , Figure 1 The present invention provides a flow chart of a method for automatically processing tax refund data. Figure 1 As shown, the method includes:

[0069] Step 101: Obtain the target user's delivery plan information.

[0070] This can be achieved by establishing a data interface with the client system and obtaining the target user's shipping plan information from the client system through the data interface. Shipping plan information can be understood as the target user's shipping plan and shipping documents for cross-border shipments. Shipping plan information can include the name of the shipped product, information about the transaction parties, and the product shipment time. Information about the transaction parties can be understood as information about the supplier and the buyer.

[0071] Step 102: extract product information from the delivery plan information to obtain target product information.

[0072] The target product information may be determined based on the keyword set obtained by performing text recognition and keyword extraction on the delivery plan information, wherein the target product information includes the buyer's name, supplier's name, product name, product quantity, unit price, and total price.

[0073] Step 103: Match the target commodity information with the invoice and the customs declaration document to obtain the target invoice information and the target customs declaration document.

[0074] Specifically, the first invoice matching result and the first customs declaration matching result may be obtained by extracting the supplier name and product name from the target product information and matching the initial invoice and customs declaration document based on the supplier name and product name. It is understood that the first invoice matching result and the first customs declaration matching result may also be obtained by extracting the purchaser name and product name from the target product information and matching the initial invoice and customs declaration document based on the purchaser name and product name; or the first invoice matching result and the first customs declaration matching result may also be obtained by matching the initial invoice and customs declaration document based on the invoice header, issuer, etc.

[0075] If both the first invoice matching result and the first customs declaration document matching result are not empty, it indicates that the matching is successful. The invoice in the first invoice matching result can be determined as the final invoice, and the customs declaration document in the first customs declaration document matching result can be determined as the final customs declaration document, and used for subsequent generation of tax refund declaration information.

[0076] A successful match indicates that both the invoice and customs declaration document meet the requirements. In this case, both the invoice and customs declaration document will include relevant information such as the supplier name and product name. Therefore, the first invoice matching result includes invoices that include the supplier name and product name; and the first customs declaration result includes customs declaration documents that include the supplier name and product name.

[0077] If at least one of the first invoice matching result and the first customs declaration document matching result is empty (indicating that no relevant information is matched), the product names are associated to obtain a first associated product name set. A second matching is performed on the invoice and the customs declaration document based on the first associated product name in the first associated product name set to obtain a second invoice matching result set and a second customs declaration document matching result set. Based on the second invoice matching result set and the second customs declaration document matching result set, the target invoice information and target customs declaration document corresponding to the target product information are determined.

[0078] Among them, the association processing of the product name can be understood as: extracting the names of similar products from the product name, and determining the similar product name as the associated product name (that is, the first associated product name). For example, if the product name is "plastic cup", the associated product name can be "plastic beverage cup", "plastic beverage cup", "plastic water cup", "plastic tea cup", etc. This is only an example and is not specifically limited. Specifically, when describing the product name, the product name in the shipping plan provided by the user may not match the standard name. In this case, it is necessary to identify the standard name corresponding to the product name in the shipping plan in order to obtain the subsequent target customs declaration documents and target invoice information, etc., to improve accuracy.

[0079] Step 104: Generate tax refund declaration information based on the target commodity information, the target invoice information, and the target customs declaration document.

[0080] The tax refund declaration information may be generated by filling the target commodity information, the target invoice information and the target customs declaration document into corresponding positions in a preset tax refund declaration information template.

[0081] Specifically, the target commodity information, the target invoice information and the target customs declaration document may be input into a preset tax refund declaration information template, and the tax refund declaration information may be generated according to the preset tax refund declaration information template.

[0082] Step 105: Send the tax refund declaration information to the tax refund system to instruct the tax refund system to process the tax refund.

[0083] Among them, the tax refund declaration information can be transmitted to the tax refund system through a common transmission method. After the tax refund system receives the tax refund declaration information, it can perform tax refund and other related processing according to the target commodity information, target invoice information and target customs declaration documents in the tax refund declaration information.

[0084] In this example, by obtaining the target user's shipping plan information, extracting product information from the shipping plan information to obtain target product information, matching the target product information with the invoice and customs declaration documents to obtain target invoice information and target customs declaration documents, generating tax refund declaration information based on the target product information, the target invoice information and the target customs declaration documents, and sending the tax refund declaration information to the tax refund system to instruct the tax refund system to perform tax refund processing. Therefore, the target user's shipping plan information can be automatically extracted and the corresponding invoice information and customs declaration documents can be matched. Finally, the tax refund declaration information is automatically generated to apply for a tax refund, thereby improving the efficiency of processing tax refund data.

[0085] In one possible implementation, when matching invoices and customs declaration documents, there may be cases where the match fails. In existing solutions, when the match fails, manual intervention and verification are usually used to handle the problem. However, since the shipping plan information may include a large number of commodity lists, in this case, there may be a commodity name with multiple similar commodity names. In this case, manual verification takes a lot of time and is prone to errors. In order to solve the above problem, a method is provided for matching the invoice and customs declaration documents of the target commodity information to obtain the target invoice information and the target customs declaration document. When the match fails, automatic verification is performed, which improves the efficiency of the verification process, avoids errors caused by manual processing, and improves the accuracy of data processing. The method specifically includes:

[0086] A1. Extracting the supplier name and product name from the target product information;

[0087] A2. Performing an initial matching operation on the invoice and the customs declaration document based on the commodity name and the supplier name to obtain a first invoice matching result and a first customs declaration document matching result;

[0088] A3. If the first invoice matching result and / or the first customs declaration document matching result is empty, perform product name association processing on the product names to obtain a first associated product name set;

[0089] A4. Perform a secondary match between the invoice and the customs declaration document based on the first associated commodity name in the first associated commodity name set to obtain a second invoice matching result set and a second customs declaration document matching result set;

[0090] A5. Extract the first associated matching information corresponding to the second invoice matching result from the second invoice matching result set to obtain a first associated matching information set, and extract the second associated matching information corresponding to the second customs declaration document matching result from the second customs declaration document matching result set to obtain a second associated matching information set.

[0091] A6. Determine the target invoice information corresponding to the target commodity information from the second invoice matching result set based on the first associated matching information set, and determine the target customs declaration document corresponding to the target commodity information from the second customs declaration document matching result set based on the second associated matching information set.

[0092] The target product information may be extracted from text using common OCR technology to obtain the supplier name and product name.

[0093] After obtaining the supplier name and product name, a preset document matching module may be used to initially match the product name and supplier name with the invoice and customs declaration document according to a preset product name strategy and SKU (Stock Keeping Unit) strategy to obtain a first invoice matching result and a first customs declaration matching result. Specifically, the cosine similarity between the product name and supplier name and the product name and supplier name in the invoice may be calculated using the method shown in the following formula. The product name and supplier name may then be initially matched with the invoice and customs declaration document based on the cosine similarity and a preset cosine similarity threshold to obtain a first invoice matching result:

[0094]

[0095] In the formula represents the cosine similarity between the product name and the supplier name extracted from the target product information and the product name and the supplier name in the invoice; representing a vector representation corresponding to the product name extracted from the target product information and a vector representation corresponding to the supplier name extracted from the target product information; The vector representation of the product name in the invoice and the vector representation of the supplier name in the invoice; The symbol for calculating the modulus of a vector; Indicates the preset cosine similarity threshold; Indicates that the product name and the supplier name are successfully matched with the invoice for the first time, and the invoice is determined as the first invoice matching result; Indicates that if the product name and the supplier name are not matched successfully with the invoice for the first time, the next invoice will be matched.

[0096] After obtaining the first invoice matching result and the first customs declaration document matching result, if the first invoice matching result and / or the first customs declaration document matching result is empty, the product name associated with the product name is obtained to obtain a first associated product name set. The first associated product name in the first associated product name set is different from the product name, but the first associated product name and the product name point to the same item. Among them, the product name association processing of the product name can be understood as: extracting the names of similar products from the product name, and determining the similar product names as associated product names. For example, if the product name is "plastic cup", the associated product names can be "plastic beverage cup", "plastic beverage cup", "plastic water cup", "plastic tea cup", etc.

[0097] After obtaining the first associated product name set, the first associated product name and the supplier name can be matched again with the invoice and customs declaration documents according to the preset product name strategy and SKU strategy through the preset document matching module to obtain a second invoice matching result set and a second customs declaration document matching result set.

[0098] After obtaining the second invoice matching result set and the second customs declaration document matching result set, the target invoice information can be determined from the second invoice matching result set by obtaining the first associated matching information corresponding to each second invoice match in the second invoice matching result set. For example, if there is a successfully matched invoice information in the second invoice matching result set, the number of matches recorded is 1, and the first associated matching information is 1. If there is no successfully matched invoice information in the second invoice matching result set, the number of matches recorded is 0, and the first associated matching information is 0. The second associated matching information of the second customs declaration document matching result in the second customs declaration document matching result set can be obtained using the same method as that used to obtain the first associated matching information set to obtain the second associated matching information set.

[0099] After obtaining the first and second associated matching information sets, the number of successful matches in the first associated matching information set may be obtained to obtain a matching count set. Based on the matching count set, a reference invoice matching result set is determined from the second invoice matching result set. The target invoice information corresponding to the target commodity information is then determined based on the reference invoice matching result set. Specifically, the target invoice information may be determined by combining the transaction party information set and the transaction time information set in the reference invoice matching result set. The transaction party information set includes supplier information and buyer information; the transaction time information in the transaction time information set can be understood as the transaction time noted on the invoice in the reference invoice matching result set. The target customs declaration document corresponding to the target commodity information may be determined from the second customs declaration document matching result set based on the second associated matching information set using the same method used to obtain the target invoice information.

[0100] In this example, the initial invoice and customs declaration document matching is performed based on the product name and the supplier name. If the first invoice matching result and / or the first customs declaration document matching result is empty, a secondary invoice and customs declaration document matching is performed based on the first associated product name in the first associated product name set to obtain a second invoice matching result set and a second customs declaration document matching result set. The target invoice information and the target customs declaration document are respectively determined based on the second invoice matching result set and the second customs declaration document matching result set, thereby improving the accuracy of the automated processing of tax refund data.

[0101] In one possible implementation, the first associated matching information set determines the target invoice information corresponding to the target commodity information from the second invoice matching result set, including:

[0102] B1. Determine, based on the first associated matching information in the first associated matching information set, the number of times the invoice information in the corresponding invoice matching result is successfully associated and matched, to obtain a matching number set;

[0103] B2. Extracting second invoice matching results with zero matching times from the second invoice matching result set based on the matching times set to obtain a reference invoice matching result set;

[0104] B3. Determine a transaction party information set and a transaction time information set based on the reference invoice matching result set;

[0105] B4. Obtain user information corresponding to the target user to obtain target user information;

[0106] B5. Determine a preliminary invoice matching result set based on the transaction party information set and the target user information;

[0107] B6. Extracting k suspected target invoice information from the preliminary invoice matching result set based on the transaction time information set;

[0108] B7. Verify the k pieces of suspected target invoice information to obtain target invoice information corresponding to the target commodity information.

[0109] The matching count set may be obtained by obtaining the number of successful association matches in the first association matching information set. Specifically, the matching count set may be obtained by obtaining non-zero first association matching information in the first association matching information set and determining the non-zero first association matching information as the number of matches in the matching count set. For specific examples of the non-zero first association matching information, please refer to the specific examples of first association matching information in sections A1-A6.

[0110] After obtaining the matching times set, the second invoice matching result with zero matching times in the second invoice matching result set can be determined based on the matching times in the matching times set, and determined as the reference invoice matching result to obtain the reference invoice matching result set.

[0111] After obtaining the reference invoice matching result set, the invoice information in the reference invoice matching result can be extracted, and the transaction party information and transaction time information can be extracted from the invoice information. The extracted transaction party information is used as the transaction party information set, and the extracted transaction time information is used as the transaction time information set. The transaction time information here can be understood as the transaction time noted in the invoice.

[0112] The target user information can be obtained by obtaining the company name, person in charge name, etc. corresponding to the target user.

[0113] The reference invoice matching results corresponding to the target user information in the transaction party information set may be determined as preliminary invoice matching results based on the target user information, and the determined preliminary invoice matching results may be used as a preliminary invoice matching result set.

[0114] The target user information can be used to extract the transaction time associated with the target product information. Multiple target transaction times can then be determined from the transaction time information set based on the transaction time. Because the associated transaction time may be a range of transaction times, multiple target transaction times can be determined from the transaction time information set. Invoice information from these multiple target transaction times that corresponds to the time in the preliminary invoice matching result set is then determined as k suspected target invoice information.

[0115] After obtaining k suspected target invoice information, n suspected target customs declaration documents can be extracted from the second customs declaration document matching result set according to the second associated matching information set to determine the target customs declaration document corresponding to the target commodity information, and the k suspected target invoice information can be verified based on the n suspected target customs declaration documents to obtain the target invoice information corresponding to the target commodity information.

[0116] In this example, a reference invoice matching result set is obtained by obtaining the second invoice matching result with zero matching times in the second invoice matching result set. According to the transaction party information and transaction time corresponding to the reference invoice matching result of the reference invoice matching result set, as well as the target user information, k suspected target invoice information is determined in the reference invoice matching result set, and the k suspected target invoice information is verified to obtain the target invoice information corresponding to the target commodity information, thereby improving the accuracy of automated processing of tax refund data.

[0117] In a possible implementation, the k pieces of suspected target invoice information are verified to obtain target invoice information corresponding to the target commodity information, including:

[0118] C1. extracting n suspected target customs declaration documents from the second customs declaration document matching result set in the process of determining the target customs declaration document corresponding to the target commodity information based on the second associated matching information set;

[0119] C2. Use n suspected target customs declaration documents and k suspected target invoice information to perform verification processing, and determine the suspected target invoice information among the suspected target customs declaration documents and suspected target invoice information that match each other as the target invoice information corresponding to the target commodity information.

[0120] The method for determining k suspected target invoice information in the above embodiment can be used to obtain n suspected target customs declaration documents. The method for obtaining the target customs declaration documents is the same as the method for obtaining the target invoice information.

[0121] After obtaining n suspected target customs declaration documents, the n suspected target customs declaration documents and the k suspected target invoice information can be verified and processed, and the suspected target invoice information in the suspected target customs declaration documents and suspected target invoice information that match each other can be determined as the target invoice information corresponding to the corresponding target commodity information.

[0122] The text similarity between the n suspected target customs declaration documents and the k suspected target invoice information can be calculated by the following formula, thereby completing the verification process between the n suspected target customs declaration documents and the k suspected target invoice information, as shown below:

[0123]

[0124] In the formula Indicates the A suspected target customs declaration document and The text similarity between the suspected target invoice information; express The first of the suspected target customs declaration documents The text length corresponding to the suspected target customs declaration document is represented by the number of characters corresponding to the suspected target customs declaration document, and can be obtained by extracting text from the suspected target customs declaration document using a common text extraction method; express Among the suspected target invoice information The text length corresponding to the suspected target invoice information is characterized by the number of characters corresponding to the suspected target invoice information, and can be obtained by extracting the suspected target invoice information through a common text extraction method; Indicates the Among the suspected target customs declaration documents Characters and Among the suspected target invoice information The edit distance between characters; Indicates the Among the suspected target customs declaration documents Characters and Among the suspected target invoice information Add 1 to the edit distance between characters; Indicates the Among the suspected target customs declaration documents Characters and Among the suspected target invoice information Add 1 to the edit distance between characters; Indicates the Among the suspected target customs declaration documents Characters and Among the suspected target invoice information Add 1 to the edit distance between characters; Indicates the maximum value operation; Indicates the minimum value operation; Indicates the preset similarity threshold; Indicates that the similarity between the suspected target customs declaration document and the suspected target invoice information is less than the preset similarity threshold, indicating that the suspected target customs declaration document and the suspected target invoice information are not matched successfully; It indicates that the similarity between the suspected target customs declaration document and the suspected target invoice information is greater than or equal to the preset similarity threshold, indicating that the suspected target customs declaration document and the suspected target invoice information are successfully matched.

[0125] The text similarity between any suspected target customs declaration document and any suspected target invoice information can be calculated using the above formula.

[0126] In this example, n suspected target customs declaration documents are determined from the second customs declaration document matching result set based on the second associated matching information set, the n suspected target customs declaration documents and k suspected target invoice information are verified, and the suspected target invoice information in the mutually matching suspected target customs declaration documents and suspected target invoice information is determined as the target invoice information corresponding to the corresponding target commodity information, thereby improving the accuracy of automated processing of tax refund data.

[0127] In one possible implementation, extracting product information from the delivery plan information to obtain target product information includes:

[0128] D1. Perform text recognition on the delivery plan information to obtain text recognition results;

[0129] D2. Extract keywords from the text recognition results to obtain a keyword set;

[0130] D3. Determine the target product information based on the keyword set.

[0131] The text in the delivery plan information may be recognized by using a general OCR technology to obtain a text recognition result.

[0132] Keywords may be extracted from the text recognition results using a common keyword extraction technique to obtain an initial keyword set. After the initial keyword set is extracted, the keywords in the initial keyword set may be filtered to obtain a keyword set. Specifically, the filtering range may include, for example, extracting keywords such as supplier name, target product name, target product quantity, target product unit price, and target product total price from the keyword set to obtain a final usable keyword set.

[0133] The target product information may be obtained by determining keywords in the keyword set as the target product information, wherein the keywords in the keyword set may be the supplier name, target product name, target product quantity, target product unit price, and target product total price corresponding to the target product information.

[0134] In this example, text recognition technology is used to perform text recognition on the original shipping plan information to obtain text recognition results, keywords are extracted from the text recognition results to obtain a keyword set, and the keywords in the keyword set are determined as target product information to obtain target product information, thereby improving the efficiency of automated processing of tax refund data.

[0135] For the same example as above, please refer to Figure 2 , Figure 2 A schematic diagram of the structure of a terminal provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the system comprises a processor, an input device, an output device and a memory, which are connected to each other, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions, and the program includes instructions for executing the following steps;

[0136] Obtain the target user's delivery plan information;

[0137] Extracting product information from the delivery plan information to obtain target product information;

[0138] Matching the invoice and customs declaration documents of the target commodity information to obtain target invoice information and target customs declaration documents;

[0139] Generate tax refund declaration information based on the target commodity information, the target invoice information and the target customs declaration document;

[0140] The tax refund declaration information is sent to the tax refund system to instruct the tax refund system to perform tax refund processing.

[0141] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that, in order to implement the above functions, the terminal includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of the various examples described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0142] The embodiment of the present application can divide the terminal into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical functional division. In actual implementation, there may be other division methods.

[0143] In line with the above, please see Figure 3 , Figure 3 The present invention provides a schematic diagram of a device for automatically processing tax refund data. Figure 3 As shown, the device includes:

[0144] An acquisition unit 301 is used to acquire the delivery plan information of the target user;

[0145] An extraction unit 302 is configured to extract product information from the delivery plan information to obtain target product information;

[0146] A matching unit 303 is configured to match the target commodity information with an invoice and a customs declaration document to obtain target invoice information and target customs declaration documents;

[0147] A generating unit 304 is configured to generate tax refund declaration information based on the target commodity information, the target invoice information, and the target customs declaration document;

[0148] The sending unit 305 is configured to send the tax refund declaration information to the tax refund system to instruct the tax refund system to perform tax refund processing.

[0149] In a possible implementation, the matching unit 303 is specifically configured to:

[0150] Extracting the supplier name and product name from the target product information;

[0151] Performing an initial matching of the invoice and the customs declaration document based on the commodity name and the supplier name to obtain a first invoice matching result and a first customs declaration document matching result;

[0152] If the first invoice matching result and / or the first customs declaration document matching result is empty, performing product name association processing on the product name to obtain a first associated product name set;

[0153] Performing a secondary match between the invoice and the customs declaration document based on the first associated commodity name in the first associated commodity name set to obtain a second invoice matching result set and a second customs declaration document matching result set;

[0154] Extracting the first associated matching information corresponding to the second invoice matching result from the second invoice matching result set to obtain a first associated matching information set, and extracting the second associated matching information corresponding to the second customs declaration document matching result from the second customs declaration document matching result set to obtain a second associated matching information set;

[0155] According to the first associated matching information set, the target invoice information corresponding to the target commodity information is determined from the second invoice matching result set, and according to the second associated matching information set, the target customs declaration document corresponding to the target commodity information is determined from the second customs declaration document matching result set.

[0156] In one possible implementation, in determining the target invoice information corresponding to the target commodity information from the second invoice matching result set according to the first associated matching information set, the matching unit 303 is specifically configured to:

[0157] determining the number of times the invoice information in the corresponding invoice matching result is successfully associated and matched based on the first associated matching information in the first associated matching information set, to obtain a matching number set;

[0158] Extracting second invoice matching results with zero matching times from the second invoice matching result set according to the matching times set to obtain a reference invoice matching result set;

[0159] Determining a transaction party information set and a transaction time information set based on the reference invoice matching result set;

[0160] Obtaining user information corresponding to the target user to obtain target user information;

[0161] Determining a preliminary invoice matching result set based on the transaction party information set and the target user information;

[0162] Extracting k suspected target invoice information from the preliminary invoice matching result set according to the transaction time information set;

[0163] The k pieces of suspected target invoice information are verified to obtain target invoice information corresponding to the target commodity information.

[0164] In one possible implementation, in verifying the k pieces of suspected target invoice information to obtain the target invoice information corresponding to the target commodity information, the matching unit 303 is specifically configured to:

[0165] extracting n suspected target customs declaration documents from the process of determining the target customs declaration document corresponding to the target commodity information from the second customs declaration document matching result set according to the second associated matching information set;

[0166] Verification is performed using n suspected target customs declaration documents and k suspected target invoice information, and the suspected target invoice information among the suspected target customs declaration documents and suspected target invoice information that match each other is determined as the target invoice information corresponding to the target commodity information.

[0167] In a possible implementation, the extraction unit 302 is specifically configured to:

[0168] Perform text recognition on the delivery plan information to obtain text recognition results;

[0169] Performing keyword extraction on the text recognition result to obtain a keyword set;

[0170] The target product information is determined according to the keyword set.

[0171] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the methods for automatically processing tax refund data as described in the above method embodiments.

[0172] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program enables a computer to execute part or all of the steps of any one of the methods for automatically processing tax refund data as described in the above method embodiments.

[0173] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0174] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0175] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0176] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0177] In addition, the functional units in the various embodiments of the application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software program modules.

[0178] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk, or optical disk, etc., various media that can store program code.

[0179] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0180] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for automatically processing tax refund data, characterized in that: The method comprises: Obtain the target user's delivery plan information; Extracting product information from the delivery plan information to obtain target product information; Matching the invoice and customs declaration documents of the target commodity information to obtain target invoice information and target customs declaration documents; Generate tax refund declaration information based on the target commodity information, the target invoice information and the target customs declaration document; Sending the tax refund declaration information to the tax refund system to instruct the tax refund system to process the tax refund; The step of matching the target commodity information with the invoice and the customs declaration document to obtain the target invoice information and the target customs declaration document includes: Extracting the supplier name and product name from the target product information; Performing an initial matching of the invoice and the customs declaration document based on the commodity name and the supplier name to obtain a first invoice matching result and a first customs declaration document matching result; If the first invoice matching result and / or the first customs declaration document matching result is empty, performing product name association processing on the product name to obtain a first associated product name set; Performing a secondary match between the invoice and the customs declaration document based on the first associated commodity name in the first associated commodity name set to obtain a second invoice matching result set and a second customs declaration document matching result set; Extracting the first associated matching information corresponding to the second invoice matching result from the second invoice matching result set to obtain a first associated matching information set, and extracting the second associated matching information corresponding to the second customs declaration document matching result from the second customs declaration document matching result set to obtain a second associated matching information set; Determining target invoice information corresponding to the target commodity information from the second invoice matching result set based on the first associated matching information set, and determining target customs declaration documents corresponding to the target commodity information from the second customs declaration document matching result set based on the second associated matching information set; The determining, based on the first associated matching information set, target invoice information corresponding to the target commodity information from the second invoice matching result set includes: determining the number of times the invoice information in the corresponding invoice matching result is successfully associated and matched based on the first associated matching information in the first associated matching information set, to obtain a matching number set; Extracting second invoice matching results with zero matching times from the second invoice matching result set according to the matching times set to obtain a reference invoice matching result set; Determining a transaction party information set and a transaction time information set based on the reference invoice matching result set; Obtaining user information corresponding to the target user to obtain target user information; Determining a preliminary invoice matching result set based on the transaction party information set and the target user information; Extracting k suspected target invoice information from the preliminary invoice matching result set according to the transaction time information set; Verify the k suspected target invoice information to obtain the target invoice information corresponding to the target product information; The verifying process of the k pieces of suspected target invoice information to obtain target invoice information corresponding to the target commodity information includes: n suspected target customs declaration documents in the process of determining the target customs declaration document corresponding to the target commodity information from the second customs declaration document matching result set according to the second associated matching information set; Using n suspected target customs declaration documents and k suspected target invoice information to perform verification processing, determining the suspected target invoice information among the suspected target customs declaration documents and suspected target invoice information that match each other as the target invoice information corresponding to the target commodity information; The text similarity between the n suspected target customs declaration documents and the k suspected target invoice information is calculated by the following formula, thereby completing the verification process between the n suspected target customs declaration documents and the k suspected target invoice information: In the formula Indicates the A suspected target customs declaration document and The text similarity between the suspected target invoice information; express The first of the suspected target customs declaration documents The text length corresponding to the suspected target customs declaration document is represented by the number of characters corresponding to the suspected target customs declaration document, and can be obtained by extracting text from the suspected target customs declaration document using a common text extraction method; express Among the suspected target invoice information The text length corresponding to the suspected target invoice information is characterized by the number of characters corresponding to the suspected target invoice information, and can be obtained by extracting the suspected target invoice information through a common text extraction method; Indicates the Among the suspected target customs declaration documents Characters and Among the suspected target invoice information The edit distance between characters; Indicates the Among the suspected target customs declaration documents Characters and Among the suspected target invoice information Add 1 to the edit distance between characters; Indicates the Among the suspected target customs declaration documents Characters and Among the suspected target invoice information Add 1 to the edit distance between characters; Indicates the Among the suspected target customs declaration documents Characters and Among the suspected target invoice information Add 1 to the edit distance between characters; Indicates the maximum value operation; Indicates the minimum value operation; Indicates the preset similarity threshold; Indicates that the similarity between the suspected target customs declaration document and the suspected target invoice information is less than the preset similarity threshold, indicating that the suspected target customs declaration document and the suspected target invoice information are not matched successfully; It indicates that the similarity between the suspected target customs declaration document and the suspected target invoice information is greater than or equal to the preset similarity threshold, indicating that the suspected target customs declaration document and the suspected target invoice information are successfully matched.

2. The method for automatically processing tax refund data according to claim 1, characterized in that: The extracting commodity information from the delivery plan information to obtain target commodity information includes: Perform text recognition on the delivery plan information to obtain text recognition results; Performing keyword extraction on the text recognition result to obtain a keyword set; The target product information is determined according to the keyword set.

3. A device for automatically processing tax refund data, characterized in that: The device comprises: An acquisition unit, used to obtain the target user's delivery plan information; an extraction unit, configured to extract commodity information from the delivery plan information to obtain target commodity information; a matching unit, configured to match the target commodity information with an invoice and a customs declaration document to obtain target invoice information and target customs declaration documents; A generating unit, configured to generate tax refund declaration information based on the target commodity information, the target invoice information, and the target customs declaration document; The sending unit is used to send the tax refund declaration information to the tax refund system to instruct the tax refund system to process the tax refund; the matching unit is specifically used to: Extracting the supplier name and product name from the target product information; Performing an initial matching of the invoice and the customs declaration document based on the commodity name and the supplier name to obtain a first invoice matching result and a first customs declaration document matching result; If the first invoice matching result and / or the first customs declaration document matching result is empty, performing product name association processing on the product name to obtain a first associated product name set; Performing a secondary match between the invoice and the customs declaration document based on the first associated commodity name in the first associated commodity name set to obtain a second invoice matching result set and a second customs declaration document matching result set; Extracting the first associated matching information corresponding to the second invoice matching result from the second invoice matching result set to obtain a first associated matching information set, and extracting the second associated matching information corresponding to the second customs declaration document matching result from the second customs declaration document matching result set to obtain a second associated matching information set; Determining target invoice information corresponding to the target commodity information from the second invoice matching result set based on the first associated matching information set, and determining target customs declaration documents corresponding to the target commodity information from the second customs declaration document matching result set based on the second associated matching information set; In determining the target invoice information corresponding to the target commodity information from the second invoice matching result set based on the first associated matching information set, the matching unit is specifically configured to: determining the number of times the invoice information in the corresponding invoice matching result is successfully associated and matched based on the first associated matching information in the first associated matching information set, to obtain a matching number set; Extracting second invoice matching results with zero matching times from the second invoice matching result set according to the matching times set to obtain a reference invoice matching result set; Determining a transaction party information set and a transaction time information set based on the reference invoice matching result set; Obtaining user information corresponding to the target user to obtain target user information; Determining a preliminary invoice matching result set based on the transaction party information set and the target user information; Extracting k suspected target invoice information from the preliminary invoice matching result set according to the transaction time information set; Verify the k suspected target invoice information to obtain the target invoice information corresponding to the target product information; In the aspect of verifying the k pieces of suspected target invoice information to obtain the target invoice information corresponding to the target commodity information, the matching unit is specifically configured to: n suspected target customs declaration documents in the process of determining the target customs declaration document corresponding to the target commodity information from the second customs declaration document matching result set according to the second associated matching information set; Using n suspected target customs declaration documents and k suspected target invoice information to perform verification processing, determining the suspected target invoice information among the suspected target customs declaration documents and suspected target invoice information that match each other as the target invoice information corresponding to the target commodity information; The text similarity between the n suspected target customs declaration documents and the k suspected target invoice information is calculated by the following formula, thereby completing the verification process between the n suspected target customs declaration documents and the k suspected target invoice information: In the formula Indicates the A suspected target customs declaration document and The text similarity between the suspected target invoice information; express The first of the suspected target customs declaration documents The text length corresponding to the suspected target customs declaration document is represented by the number of characters corresponding to the suspected target customs declaration document, and can be obtained by extracting text from the suspected target customs declaration document using a common text extraction method; express Among the suspected target invoice information The text length corresponding to the suspected target invoice information is characterized by the number of characters corresponding to the suspected target invoice information, and can be obtained by extracting the suspected target invoice information through a common text extraction method; Indicates the Among the suspected target customs declaration documents Characters and Among the suspected target invoice information The edit distance between characters; Indicates the Among the suspected target customs declaration documents Characters and Among the suspected target invoice information Add 1 to the edit distance between characters; Indicates the Among the suspected target customs declaration documents Characters and Among the suspected target invoice information Add 1 to the edit distance between characters; Indicates the Among the suspected target customs declaration documents Characters and Among the suspected target invoice information Add 1 to the edit distance between characters; Indicates the maximum value operation; Indicates the minimum value operation; Indicates the preset similarity threshold; Indicates that the similarity between the suspected target customs declaration document and the suspected target invoice information is less than the preset similarity threshold, indicating that the suspected target customs declaration document and the suspected target invoice information are not matched successfully; It indicates that the similarity between the suspected target customs declaration document and the suspected target invoice information is greater than or equal to the preset similarity threshold, indicating that the suspected target customs declaration document and the suspected target invoice information are successfully matched.

4. A terminal, characterized in that: The method comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method for automatically processing tax refund data according to any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor, the processor executes the method for automatically processing tax refund data according to any one of claims 1 to 2.

Images