Intelligent business archive management method and system

Abstract

The invention discloses an intelligent business archive management method and system, and the method comprises the steps: reading a contract file in a business archive, coding the contract file, configuring a project file and a financial file corresponding to the contract file according to the code of the contract file, carrying out the standardized coding of the files, and forming a standard coding data set; reading the standard coded data set, obtaining file information, and generating business archive early warning information according to the file information; standardized coding is carried out through identification information, and a standard coding data set is formed to carry out unified management of business archives; meanwhile, an index file is created, the standard coded data set is dynamically updated, and real-time updating of business archives is achieved on the basis of unified management; a natural language technology is adopted to realize quick and accurate search of the business archives, early warning information is generated for specific problems of files in the business archives and prompted in time, and whole-process intelligent management of the business archives of various types of associated files is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of file management, and more particularly, to an intelligent business file management method and system. Background Art

[0002] During the current business activities, there is cooperation and communication among multiple departments, and each department has its own work habits and file management methods. In addition to contract files, there are differences in formats and classifications of project files, financial files, etc. in different departments. Different business departments lack unified standards in aspects such as file formats, classifications, and numbers, which makes it easy to cause confusion during the sorting and archiving by the file management department, affecting the retrieval efficiency and utilization effect of files.

[0003] When it comes to the management of business files involving multiple types of files, the existing technologies often cannot adopt a unified business file standard for business file management, making it difficult to find files; when searching for relevant file content, the file index is incomplete, resulting in difficult retrieval, backward file search methods, low search efficiency, and there are also situations where files are not updated in a timely manner and file problem reminders cannot be made. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent business file management method and system to solve the above problems existing in the prior art.

[0005] Specifically, this application is as follows:

[0006] An intelligent business file management method, characterized by including the following steps:

[0007] Step 1: Read the contract files in the business files and encode the contract files;

[0008] Step 2: Configure the project files and financial files corresponding to the contract files through the encoding of the contract files;

[0009] Step 3: Perform standardized encoding on the files to form a standard encoding data set;

[0010] Step 4: Read the standard encoding data set to obtain file information;

[0011] Step 5: Generate business file warning information according to the file information.

[0012] The said Step 1: Read the contract files in the business files and encode the contract files includes: scanning the contract files through optical character recognition technology, identifying the text information of the contract files, and encoding the text information to form a first encoding data set S1.

[0013] The first encoded data set S1 is represented as:

[0014] S1 = {ID, T1, P1, M1, D1}

[0015] Wherein, ID represents a unique identifier, including the contract name and number; T1 represents a time attribute, including the signing date and the contract term; P1 represents a spatial attribute, including the contract-related project and the project location; M1 represents an asset attribute, including the contract transaction price; D1 represents a contract content set, including contract terms.

[0016] Step two: Through the encoding of the contract file, configuring the project file and the financial file corresponding to the contract file includes:

[0017] Read the encoded data of the contract file, find the related project file through the encoded data, and encode the project file to form a second encoded data set S2;

[0018] Read the encoded data of the contract file, find the related financial file through the encoded data, and encode the financial file to form a third encoded data set S3.

[0019] The second encoded data set S2 is represented as:

[0020] S2 = {ID, T2, P2, M2, D2}

[0021] Wherein, ID represents a unique identifier, including the contract name and number; T2 represents a time attribute, including the project start time and the project end time; P2 represents a spatial attribute, including the project scope; M2 represents an asset attribute, including the project budget; D2 represents a project file content set, including project plans, project execution, and project monitoring;

[0022] The third encoded data set S3 is represented as:

[0023] S3 = {ID, T3, P3, M3, D3}

[0024] Wherein, ID represents a unique identifier, including the contract name and number; T2 represents a time attribute, including the actual fund usage time; P2 represents a spatial attribute, including the fund usage location; M2 represents an asset attribute, including financial statements; D2 represents a financial file content set, including profitability analysis, operational capacity analysis, and financial decision-making;

[0025] Step three: Perform standardized encoding on the files to form a standard encoded data set, including:

[0026] Based on the first encoded data set S1, the second encoded data set S2, and the third encoded data set S3, set a unique identifier ID for the contract document and the associated project documents and financial documents. Obtain the time attribute T, space attribute P, asset attribute M, and document content set D of the document through the unique identifier ID, and form a standard encoded data set S, where S = {ID, T, P, M, D}.

[0027] After standardizing the encoding of the documents, it also includes creating an index file and dynamically updating the standard encoded data set S:

[0028] Set up a dedicated encoded index file data set. In the index file, list the ID code, file name, file type, main content summary, and associated file ID code information of each file. When a new file is generated or the association relationship between files changes, update the mapping relationship in the index file in a timely manner and record it in the standard encoded data set S.

[0029] Step four: Read the standard encoded data set to obtain file information, including: In the standard encoded data set S, read the unique identifier ID of the contract document to search for the content of the associated files, automatically display other files associated with the unique identifier ID, read the text using natural language technology, and obtain the file content according to the requirements.

[0030] Step five: Generate business archive warning information according to the file information, including:

[0031] According to the obtained file content, set warning conditions for the file regarding integrity, accuracy, security, compliance, and timeliness, and give a warning prompt when an abnormal situation occurs.

[0032] This application also provides an intelligent business archive management system, which is characterized by being used to implement the above-mentioned intelligent business archive management method. The system includes: a reading module, a configuration module, an encoding module, a processing module, and a warning module;

[0033] The reading module reads the contract documents in the business archive and encodes the contract documents; the configuration module configures the corresponding project documents and financial documents of the contract documents through the encoding of the contract documents; the encoding module performs standardized encoding on the documents to form a standard encoded data set; the processing module reads the standard encoded data set to obtain file information; the warning module generates business archive warning information according to the file information.

[0034] Compared with the prior art, the embodiments of the present invention achieve the following beneficial effects:

[0035] The present application provides an intelligent business archive management method and system. By standardizing the coding of contract documents, project documents, and financial documents involved in the business activities through identification information, a standard coding data set is formed for unified management of business archives. At the same time, an index file is created to dynamically update the standard coding data set, and real-time update of business archives is achieved on the basis of unified management. The natural language technology is used to quickly and accurately search for business archives, generate warning information for specific problems in the documents of business archives and timely remind, so as to realize the whole-process intelligent management of business archives of multiple types of associated documents. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 FIG. is a schematic flowchart of an intelligent business archive management method provided by an embodiment of the present invention;

[0037] Figure 2 FIG. is a schematic diagram of an intelligent business archive management system provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] The present invention will be described in detail below with reference to the accompanying drawings.

[0039] Embodiment 1

[0040] The present invention provides an intelligent business archive management method. The schematic flowchart of the method is as Figure 1 shown, and includes the following steps:

[0041] Step 1: Read the contract documents in the business archives and encode the contract documents; Step 2: Configure the corresponding project documents and financial documents of the contract documents through the encoding of the contract documents; Step 3: Perform standardized encoding on the documents to form a standard coding data set; Step 4: Read the standard coding data set to obtain file information; Step 5: Generate business archive warning information according to the file information.

[0042] The said Step 1: Read the contract documents in the business archives and encode the contract documents includes: Scanning the contract documents through optical character recognition technology, identifying the text information of the contract documents, and encoding the text information to form a first coding data set S1.

[0043] Specifically, the text information includes contract name, contract number, signing date, contract term, contract-related project, project location, contract transaction price, contract terms;

[0044] The first coding data set S1 is expressed as:

[0045] S1 = {ID, T1, P1, M1, D1}

[0046] Among them, ID represents a unique identifier, including the contract name and number; T1 represents the time attribute, including the signing date and contract term; P1 represents the spatial attribute, including the contract-related project and project location; M1 represents the asset attribute, including the contract transaction price; D1 represents the contract content set, including contract terms.

[0047] Step 2: Configuring the project file and financial file corresponding to the contract file through the encoding of the contract file includes:

[0048] Reading the encoding data of the contract file, searching for the related project file through the encoding data, and encoding the project file to form a second encoding data set S2;

[0049] The second encoding data set S2 is expressed as:

[0050] S2 = {ID, T2, P2, M2, D2}

[0051] Among them, ID represents a unique identifier, including the contract name and number; T2 represents the time attribute, including the project start time and project end time; P2 represents the spatial attribute, including the project scope; M2 represents the asset attribute, including the project budget; D2 represents the project file content set, including the project plan, project execution, and project monitoring;

[0052] Reading the encoding data of the contract file, searching for the related financial file through the encoding data, and encoding the financial file to form a third encoding data set S3;

[0053] The third encoding data set S3 is expressed as:

[0054] S3 = {ID, T3, P3, M3, D3}

[0055] Among them, ID represents a unique identifier, including the contract name and number; T2 represents the time attribute, including the actual fund usage time; P2 represents the spatial attribute, including the fund usage location; M2 represents the asset attribute, including the financial statements; D2 represents the financial file content set, including profitability analysis, operation ability analysis, and financial decision-making;

[0056] Specifically, the relevant project file can be found through the contract-related project in the spatial attribute P1 in the encoding information; the relevant financial file can be found through the contract-related project in the spatial attribute P1 and the contract transaction price in the asset attribute M1;

[0057] Step 3: Perform standardized encoding on the documents to form a standard encoding dataset, including: Based on the first encoding dataset S1, the second encoding dataset S2, and the third encoding dataset S3, set a unique identifier ID for the contract document and the associated project documents and financial documents. Obtain the time attribute T, space attribute P, asset attribute M, and document content set D of the documents through the unique identifier ID, and form the standard encoding dataset S, where S = {ID, T, P, M, D}.

[0058] Specifically, the contract document, all the project documents and financial documents associated with the contract document adopt a common ID encoding. In the encoding dataset S, for a contract named "Intelligent Factory Upgrade Project", the ID encoding of all documents can use "ZNGCxxxx-" as the unique identifier, where "xxxx" represents the contract number, and these documents can be quickly identified as belonging to this specific project.

[0059] After performing standardized encoding on the documents, it also includes creating an index file and dynamically updating the standard encoding dataset S:

[0060] Set up a special encoding index file dataset. In the index file, list the ID encoding, file name, file type, main content summary, and associated file ID encoding information of each document. When a new document is generated or the association relationship between documents changes, update the mapping relationship in the index file in a timely manner and record it in the standard encoding dataset S.

[0061] Specifically, when a new supplementary agreement is signed and the ID encoding is obtained, add the encoding information of the supplementary agreement to the index file, and update the association relationship between the contract document and other related documents associated with it, and record it in the standard encoding dataset under this ID encoding, so as to facilitate seeing how each document is interconnected through encoding.

[0062] Step 4: Read the standard encoding dataset to obtain document information, including: In the standard encoding dataset S, read the unique identifier ID of the contract document to find the content of the associated documents, automatically display other documents associated with the unique identifier ID, and use natural language technology to read the text and obtain the document content according to requirements.

[0063] Specifically, when viewing the contract document of the intelligent factory upgrade project and reading the ID as "ZNGCxxxx-", through the ID in the standard encoding dataset, display the links to the project documents and financial documents related to this contract on the interface, which is convenient for users to quickly navigate to the relevant documents. At the same time, the system also supports users to retrieve by entering the ID or part of the ID to find a group of documents associated with it;

[0064] Specifically, when using natural language technology for text reading, the text in the standard coding dataset S is first preprocessed, including Chinese word segmentation and part-of-speech tagging. Among them, the BIO tagging method is used to tag the labels in natural language to obtain the natural language problem text annotation sequence. The skip-gram model is selected to convert the natural language problem into word vectors. Each word needs to be predicted and adjusted k times when it is used as the center word to achieve a more accurate representation, which is expressed as:

[0065] P t = P(Sup(w k )|w t ), k = (t±1, t±2……)

[0066] Among them, P t is the probability, which represents the probability that each word appears as a context word given the center word t. w t is the center vocabulary, Sup(w k ) is the context vocabulary of the center word, and k is the window size. Through training iterations, P t is maximized;

[0067] The objective function is:

[0068]

[0069] Among them, L represents the loss, and S represents the standard coding dataset;

[0070] The method of machine learning is used for named entity recognition work to identify entity information such as signing date, contract term, contract-related project, project location, contract transaction price, contract terms, address, contact information, contract subject matter, liability for breach of contract, etc. in the document, and assist in judging the type of natural language problem. A convolutional neural network and / or a recurrent neural network is used to classify the text to obtain the required text content; for example, to find the start time and transaction price of the project with the ID code "ZNGCxxxx-", through natural language technology, the specific content of the project start time and transaction price in the contract can be found in the standard coding dataset;

[0071] Step five: Generating business file warning information according to the file information includes: setting warning conditions for the file regarding integrity, accuracy, security, compliance, and timeliness according to the obtained file content, and giving a warning prompt when an abnormal situation occurs.

[0072] Specifically, the warning information for the file includes:

[0073] Warning condition for integrity: The file is missing key pages, reports, or attachments; Set warning information: The file "unique identifier ID" is missing key pages, reports, or attachments. Please supplement them in time.

[0074] Warning conditions for accuracy: The terms do not conform to the company's policies or laws and regulations, or the data or information is inaccurate; Set warning information: The terms of the document with "unique identification ID" do not conform to the company's policies or laws and regulations. Please review it in time. The data or information is inaccurate. Please correct it in time.

[0075] Warning conditions for security: The document has been accessed or tampered with without authorization; Set warning information: The document with "unique identification ID" has been accessed or tampered with without authorization. Please check it immediately.

[0076] Warning conditions for compliance: The document is not filed or stored as required; Warning information: The document with "unique identification ID" is not filed or stored as required. Please handle it in time;

[0077] Warning conditions for timeliness: The document or the stage tasks or reports in the document are about to expire or have expired; Warning information: The document with "unique identification ID" is about to expire. Please renew or handle it in time.

[0078] This application also provides an intelligent business archive management system for implementing the above-mentioned intelligent business archive management method, as Figure 2 shown. The system includes: a reading module, a configuration module, an encoding module, a processing module, and a warning module;

[0079] The reading module reads the contract documents in the business archive and encodes the contract documents; The configuration module configures the project documents and financial documents corresponding to the contract documents through the encoding of the contract documents; The encoding module performs standardized encoding on the documents to form a standard encoding data set; The processing module reads the standard encoding data set to obtain file information; The warning module generates business archive warning information according to the file information.

[0080] In the specification provided here, a large number of specific details are described. However, it can be understood that the embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures, and technologies are not shown in detail so as not to obscure the understanding of this specification.

[0081] In addition, those skilled in the art can understand that although some embodiments herein include certain features included in other embodiments rather than other features, the combination of the features of different embodiments means that it is within the scope of the present invention and forms different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination.

Claims

1. An intelligent business archive management method, characterized in that: The following steps are involved: Step 1: Read the contract document in the business file and encode the contract document; Step 2: By coding the contract document, configure the project document and financial document corresponding to the contract document; Step 3: Standardize the encoding of the files to form a standard encoding data set; Step 4: Read the standard coding data set to obtain file information; Step 5: Generate business archive warning information based on the file information.

2. The intelligent business archive management method according to claim 1, characterized in that: The step 1: reading the contract document in the business file and encoding the contract document includes: scanning the contract document by optical character recognition technology, identifying the text information of the contract document, encoding the text information, and forming a first coded data set S1.

3. The intelligent business archive management method according to claim 2, characterized in that: The first encoded data set S1 is expressed as: S1={ID,T1,P1,M1,D1} Among them, ID represents a unique identifier, including the contract name and number; T1 represents time attributes, including the signing date and the contract period; P1 represents space attributes, including contract-related projects and project locations; M1 represents asset attributes, including the contract transaction price; D1 represents the contract content set, including contract terms.

4. The intelligent business archive management method according to claim 1, characterized in that: The second step: configuring the project file and the financial file corresponding to the contract file through the coding of the contract file includes: Read the coded data of the contract document, search for the project file related thereto through the coded data, and encode the project file to form a second coded data set S2; The coding data of the contract document is read, the financial documents related thereto are searched through the coding data, and the financial documents are encoded to form a third coding data set S3.

5. The intelligent business archive management method according to claim 4, characterized in that: The second encoded data set S2 is expressed as: S2={ID,T2,P2,M2,D2} Among them, ID represents a unique identifier, including the contract name and number; T2 represents time attributes, including the project start time and project end time; P2 represents space attributes, including the project scope; M2 represents asset attributes, including the project budget; D2 represents the project file content set, including project planning, project execution, and project monitoring; The third encoded data set S3 is represented as: S3={ID,T3,P3,M3,D3} Among them, ID represents a unique identifier, including the contract name and number; T2 represents time attributes, including the actual time of fund use; P2 represents space attributes, including the location of fund use; M2 represents asset attributes, including financial statements; D2 represents the content set of financial documents, including profitability analysis, operational capability analysis, and financial decision-making.

6. The intelligent business archive management method according to claim 1, characterized in that: The step three: performing standardized encoding on the file to form a standard encoding data set includes: According to the first coding data set S1, the second coding data set S2 and the third coding data set S3, a unique identification ID is set for the contract document and the associated project documents and financial documents. The time attribute T, spatial attribute P, asset attribute M and file content set D of the file are obtained through the unique identification ID to form a standard coding data set S, where S = ID, T, P, M, D}.

7. An intelligent business archive management method according to claim 6, characterized in that: After the standardized encoding of the file, the process also includes creating an index file and dynamically updating the standard encoding data set S: Set up a special coding index file data set. In the index file, list the ID code, file name, file type, main content summary and related file ID code information of each file. When a new file is generated or the relationship between files changes, update the mapping relationship in the index file in time and record it in the standard coding data set S.

8. The intelligent business archive management method according to claim 1, characterized in that: The step four: reading the standard coding data set and obtaining file information includes: in the standard coding data set S, reading the unique identification ID of the contract file to search for related file content, automatically displaying other files associated with the unique identification ID, using natural language technology to read the text, and obtaining file content as required.

9. The intelligent business archive management method according to claim 1, characterized in that: The step 5: generating business archive warning information according to the file information includes: According to the acquired file content, set warning conditions regarding the file's completeness, accuracy, security, compliance and timeliness, and issue warning prompts when abnormal situations occur.

10. An intelligent business archive management system, characterized in that: Used to implement an intelligent business archive management method as described in any one of claims 1 to 9, the system includes: a reading module, a configuration module, an encoding module, a processing module and an early warning module; The reading module reads the contract file in the business archive and encodes the contract file; the configuration module configures the project file and the financial file corresponding to the contract file through the encoding of the contract file; the encoding module performs standardized encoding on the file to form a standard encoding data set; the processing module reads the standard encoding data set to obtain file information; the early warning module generates business archive early warning information based on the file information.

Images