Business file intelligent processing method and device based on artificial intelligence

Abstract

The invention discloses a business file intelligent processing method and device based on artificial intelligence. The method comprises the following steps: acquiring original business data associated with a file generation request of a user; analyzing the original business data to extract key information entities and semantic relationships, and generating structured business information; based on a preset business rule and a knowledge graph, performing compliance verification and logic association analysis on the structured business information, and determining a to-be-generated target file type and clause content needing to be filled; according to the target file type, calling a corresponding pre-training text generation model, and generating a natural language text paragraph conforming to grammar and semantic rules by taking the structured service information and the clause content as input; formatting and arranging the generated text paragraphs according to a standard template of the target file to generate a complete initial file; and performing content auditing and key information verification on the initial file, executing an electronic signature process after the auditing is passed, and outputting a final file.

Description

Technical Field

[0001] This invention relates to the field of computer information processing technology, and more specifically, to a method and apparatus for intelligent processing of business documents based on artificial intelligence. Background Technology

[0002] During project execution, business personnel need to draft a large number of documents, such as contracts, payment notices, quotations, delivery notes, and final cost documents. This takes a lot of time, and since a large number of documents are written manually, errors may occur in the content.

[0003] Existing technologies include some document automation tools, such as template filling software, but they can usually only perform simple text replacement. They lack deep semantic understanding of document content, compliance judgment, and intelligent generation capabilities based on business rules, and cannot meet the high-quality, automated generation requirements of complex business documents. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method and apparatus for intelligent processing of business documents based on artificial intelligence.

[0005] According to one aspect of the present invention, an intelligent processing method for business documents based on artificial intelligence is provided, comprising: In response to a user's file generation request, retrieve the raw business data associated with the request; Natural language processing technology is used to parse raw business data to extract key information entities and semantic relationships, and generate structured business information. Based on preset business rules and knowledge graphs, compliance verification and logical association analysis are performed on structured business information to determine the type of target file to be generated and the content of the clauses to be filled in. Based on the target file type, the corresponding pre-trained text generation model is invoked, taking structured business information and clause content as input, to generate natural language text paragraphs that conform to grammatical and semantic rules. The generated text paragraphs are formatted and arranged according to the standard template of the target file to generate a complete initial file; The initial document undergoes content review and key information verification. After the review is approved, the electronic signature process is executed to output the final document.

[0006] According to another aspect of the present invention, an intelligent processing device for business documents based on artificial intelligence is provided, comprising: The acquisition module is used to respond to the user's file generation request and obtain the raw business data associated with the request; The parsing module is used to parse the raw business data using natural language processing technology to extract key information entities and semantic relationships, and generate structured business information. The analysis module is used to perform compliance verification and logical association analysis on structured business information based on preset business rules and knowledge graphs, and to determine the type of target file to be generated and the content of the clauses to be filled in. The first generation module is used to call the corresponding pre-trained text generation model according to the target file type, take structured business information and clause content as input, and generate natural language text paragraphs that conform to grammatical and semantic rules. The second generation module is used to format and arrange the generated text paragraphs according to the standard template of the target file to generate a complete initial file; The verification module is used to review the content and verify key information of the initial document, and after the review is passed, execute the electronic signature process and output the final document.

[0007] According to another aspect of the present invention, a computer-readable storage medium is provided, the storage medium storing a computer program for performing the methods described in any of the above aspects of the present invention.

[0008] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method described in any of the preceding aspects of the present invention.

[0009] Therefore, this invention, through the use of innovative technologies such as natural language processing, machine learning, and smart contracts, achieves automated document generation, semantic understanding and generation, text summarization, and smart contract management, significantly reducing the workload of business personnel in writing numerous documents during project execution. These technologies can automatically generate contracts, payment notices, quotations, delivery notes, final cost documents, etc., improving work efficiency, reducing errors, and ensuring the accuracy and consistency of document content. Simultaneously, smart contract technology provides functions such as digital signatures and audit trails, increasing the reliability and traceability of contract management. Attached Figure Description

[0010] Exemplary embodiments of the present invention can be more fully understood by referring to the following figures: Figure 1 This is a flowchart illustrating an exemplary embodiment of the intelligent processing method for business documents based on artificial intelligence provided by the present invention. Figure 2This is a schematic diagram of the structure of an intelligent business document processing device based on artificial intelligence provided in an exemplary embodiment of the present invention; Figure 3 This is the structure of an electronic device provided in an exemplary embodiment of the present invention. Detailed Implementation

[0011] Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0012] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of the invention.

[0013] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of the present invention are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0014] It should also be understood that in the embodiments of the present invention, "multiple" can refer to two or more, and "at least one" can refer to one, two or more.

[0015] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more unless explicitly defined or given contrary instructions in the context.

[0016] Furthermore, the term "and / or" in this invention is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this invention generally indicates that the preceding and following related objects have an "or" relationship.

[0017] It should also be understood that the description of the various embodiments in this invention emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0018] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0019] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0020] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, they should be considered part of the specification.

[0021] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0022] The embodiments of this invention can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate together with a wide range of other general-purpose or special-purpose computing system environments or configurations. Well-known examples of terminal devices, computing systems, environments, and / or configurations suitable for use with terminal devices, computer systems, servers, and other electronic devices include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments including any of the above systems, etc.

[0023] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are executed by remote processing devices linked through communication networks. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0024] Exemplary methods Figure 1 This is a flowchart illustrating an exemplary embodiment of the intelligent processing method for business documents based on artificial intelligence provided by the present invention. This embodiment can be applied to electronic devices, such as… Figure 1 As shown, the AI-based intelligent processing method for business documents 100 includes the following steps: Step 101: In response to the user's file generation request, obtain the original business data associated with the request; Step 102: Use natural language processing technology to parse the original business data to extract key information entities and semantic relationships, and generate structured business information; Step 103: Based on the preset business rules and knowledge graph, perform compliance verification and logical association analysis on the structured business information to determine the type of target file to be generated and the content of the clauses to be filled in. Step 104: Based on the target file type, call the corresponding pre-trained text generation model, take the structured business information and clause content as input, and generate natural language text paragraphs that conform to grammatical and semantic rules. Step 105: Format and arrange the generated text paragraphs according to the standard template of the target file to generate a complete initial file; Step 106: Review the content and verify key information of the initial document, and after the review is passed, execute the electronic signature process to output the final document.

[0025] Specifically, this invention utilizes technologies such as image processing, optical character recognition, machine learning, and computer vision to preprocess, recognize, rule-basedly determine, and stamp documents submitted by employees, achieving an intelligent and automated stamping process. Specific implementation steps: 1. Natural Language Processing (NLP) and Natural Language Generation (NLG) technologies enable computers to understand and generate natural language text through methods such as machine learning and language models. In intelligent text generation systems, NLP technology is used to parse and understand input data and requirements, including lexical analysis, syntactic analysis, and semantic analysis. By analyzing the input data, the system can extract key information and semantics, and grasp the context and grammatical rules.

[0026] In the NLG stage, the system utilizes a trained language model to generate text that conforms to grammatical and semantic rules based on the parsing and understanding results. This can be achieved through rule-based text generation, sampling-based text generation, or model-based text generation methods. The specific generation method and algorithm can be selected according to the requirements and application scenario.

[0027] In summary, through NLP and NLG technologies, intelligent text generation systems can automatically generate natural and fluent text, reducing the workload of manual writing. It can understand and process input data and generate text content that conforms to grammatical and semantic rules as required. This technology has wide applications in the automatic generation of documents such as contracts, reports, and summaries.

[0028] Forward propagation formula for RNN models: h_t = f(W_h * h_{t-1} + x_t + h) y_t = g(W_y * h_t + y) Where x_t represents the input word vector, h_t represents the hidden state, y_t represents the output word vector, W_h, x_t, and W_y are weight matrices, h and y are bias vectors, and f and g are activation functions.

[0029] 2. Semantic Understanding and Knowledge Graphs: By using semantic understanding and knowledge graph technologies, information such as project requirements, contract terms, and payment terms can be understood and analyzed, and corresponding documents can be automatically generated based on this information. This approach can better grasp business rules and context, generating more accurate documents that meet actual needs.

[0030] 3. Machine Learning and Generative Models: Using machine learning and generative models, models can be trained to learn patterns and rules for generating files from a large number of instances. By learning from sample files in a dataset, the model can generate new files that meet the requirements. This method enables more personalized and accurate file generation.

[0031] Formula for text generation using recurrent neural networks (RNNs): h_t = f(W_h * h_{t-1} + x_t + h) y_t = g(W_y * h_t + y) In the formula, h_t represents the hidden state, x_t represents the input features, W_h and W_y are weight matrices, h and y are bias vectors, and f and g are activation functions. This formula describes the forward propagation process in an RNN model used to generate text sequences.

[0032] 4. Text Summarization and Automated Extraction: Text summarization and automated extraction technologies can automatically extract key information from large amounts of text data and generate concise and accurate document summaries. This method helps business personnel quickly obtain the information they need and reduces the workload of writing lengthy documents. The specific formula is as follows: 1) Extractive summarization: Sentence extraction formula based on position weight: Score(s) = PositionWeight(p) * Similarity(s, Query) Where Score(s) represents the score of sentence s, PositionWeight(p) represents the position weight of the sentence in the text, and Similarity(s, Query) represents the similarity between sentence s and the query.

[0033] 2) Generative summarization: Sequence generation formulas based on attention mechanisms (such as the Seq2Seq model): P(y_i | y_1, ..., y_{i-1}, X) = Attention(y_{i-1}, h_i) * Softmax(W_y* h_i) Where y_i represents the i-th word of the generated summary sequence, X represents the input text data, h_i represents the hidden state of the model, Attention(y_{i-1}, h_i) represents the attention distribution, W_y is the weight matrix, and Softmax is the Softmax function.

[0034] 5. Automated Contract Generation and Smart Contract Management: Smart contract technology can automate the contract generation and management process. By adopting a smart contract platform, contract templates, rules, and conditions can be defined and integrated with relevant data sources and systems to achieve automated contract generation and management, reducing the need for manual intervention.

[0035] The expression for smart contract generation and management is: T + R + D + S; T = "Contract template content", R = "Contract rules and conditions", D = "Data integration process", S = "Contract status management process".

[0036] Therefore, this invention, through the use of innovative technologies such as natural language processing, machine learning, and smart contracts, achieves automated document generation, semantic understanding and generation, text summarization, and smart contract management, significantly reducing the workload of business personnel in writing numerous documents during project execution. These technologies can automatically generate contracts, payment notices, quotations, delivery notes, final cost documents, etc., improving work efficiency, reducing errors, and ensuring the accuracy and consistency of document content. Simultaneously, smart contract technology provides functions such as digital signatures and audit trails, increasing the reliability and traceability of contract management.

[0037] Exemplary device Figure 2 This is a schematic diagram of the structure of an intelligent business document processing device based on artificial intelligence, provided in an exemplary embodiment of the present invention. Figure 2 As shown, the device 200 includes: The acquisition module 210 is used to acquire the original business data associated with the user's file generation request in response to the user's file generation request; The parsing module 220 is used to parse the original business data using natural language processing technology to extract key information entities and semantic relationships, and generate structured business information. Analysis module 230 is used to perform compliance verification and logical association analysis on structured business information based on preset business rules and knowledge graphs, and to determine the type of target file to be generated and the content of the clauses to be filled in. The first generation module 240 is used to call the corresponding pre-trained text generation model according to the target file type, take the structured business information and clause content as input, and generate natural language text paragraphs that conform to grammatical and semantic rules. The second generation module 250 is used to format and arrange the generated text paragraphs according to the standard template of the target file to generate a complete initial file; The verification module 260 is used to review the content and verify key information of the initial document, and after the review is passed, execute the electronic signature process and output the final document.

[0038] Exemplary electronic devices Figure 3 This is the structure of an electronic device provided in an exemplary embodiment of the present invention. For example... Figure 3 As shown, the electronic device 30 includes one or more processors 31 and memory 32.

[0039] The processor 31 may be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0040] The memory 32 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 31 may execute the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above, and / or other desired functions. In one example, the electronic device may also include an input device 33 and an output device 34, these components being interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0041] In addition, the input device 33 may also include, for example, a keyboard, a mouse, etc.

[0042] The output device 34 can output various information to the outside. The output device 34 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0043] Of course, for the sake of simplicity, Figure 3Only some of the components of the electronic device relevant to the present invention are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.

[0044] Exemplary computer program products and computer-readable storage media In addition to the methods and apparatus described above, embodiments of the present invention may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of the present invention described in the "Exemplary Methods" section above.

[0045] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of the present invention. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0046] Furthermore, embodiments of the present invention may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps of the methods for information mining of historical change records according to various embodiments of the present invention as described in the "Exemplary Methods" section above.

[0047] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0048] The basic principles of the present invention have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in the present invention are merely examples and not limitations, and should not be considered as essential features of each embodiment of the present invention. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the present invention to the necessity of employing the aforementioned specific details.

[0049] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0050] The block diagrams of devices, systems, devices, and systems involved in this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, systems, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0051] The methods and systems of the present invention may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of the present invention are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, the present invention may also be implemented as a program recorded on a recording medium, the program comprising machine-readable instructions for implementing the methods according to the present invention. Thus, the present invention also covers recording media storing programs for performing the methods according to the present invention.

[0052] It should also be noted that in the systems, apparatus, and methods of the present invention, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered equivalents of the present invention. The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0053] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the invention to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A business document intelligent processing method based on artificial intelligence, characterized in that, include: In response to a user's file generation request, obtain the original business data associated with the request; The original business data is parsed using natural language processing technology to extract key information entities and semantic relationships, and to generate structured business information. Based on preset business rules and knowledge graphs, compliance verification and logical association analysis are performed on the structured business information to determine the type of target file to be generated and the content of the clauses to be filled in. Based on the target file type, the corresponding pre-trained text generation model is invoked, and the structured business information and the terms are used as input to generate natural language text paragraphs that conform to grammatical and semantic rules. The generated text paragraphs are formatted and arranged according to the standard template of the target file to generate a complete initial file; The initial document undergoes content review and key information verification. After the review is passed, the electronic signature process is executed to output the final document.

2. The method according to claim 1, characterized in that, The raw business data is parsed using natural language processing techniques, including: When the original business data is an image or scanned document, optical character recognition technology is used to convert it into original text. Lexical and syntactic analysis are performed on the original text to identify and label named entities, numerical values, dates, and key terms. By analyzing the relationships between actions, participants, and objects in the original text through semantic role annotation, an initial graph structure is constructed with the key information entities as nodes and semantic relationships as edges.

3. The method according to claim 1, characterized in that, The training and generation steps of the text generation model are based on a recurrent neural network architecture, and its forward propagation process follows the formula below: h_t = f(W_h * h_{t-1} + W_x * x_t + b_h) y_t = g(W_y * h_t + b_y) Where x_t represents the input word vector at time t, h_t represents the hidden state at time t, y_t represents the probability distribution of the output word vector at time t, W_h, W_x, and W_y are weight matrices, b_h and b_y are bias vectors, and f and g are activation functions; the model is trained on a large dataset of historical documents to learn the mapping rules from structured information to compliant document text.

4. The method according to claim 1, characterized in that, The initial file undergoes content review and key information verification, including: Using either an extractive or generative summarization model, scores are calculated based on the sentence's positional weight within the text and its similarity to core business clauses. Key sentences are then extracted from the initial document. The key sentences are automatically compared with the key information entities extracted from the original business data, and an alert is triggered if there is any inconsistency.

5. The method according to claim 4, characterized in that, The calculation formula for the extractive summarization model is as follows: Score(s) = PositionWeight(p) * Similarity(s, CoreClause) Where Score(s) represents the score of sentence s, PositionWeight(p) represents the weight of sentence position p, and Similarity(s, CoreClause) represents the semantic similarity between sentence s and the core clause; The calculation formula for the generative summarization model is as follows: P(y_i | y_1, ..., y_{i-1}, X) = Attention(y_{i-1}, h_i) * Softmax(W_y *h_i) In the formula, y_i represents the i-th word of the generated summary sequence, X represents the input text data, h_i represents the hidden state of the model, Attention(y_{i-1}, h_i) represents the attention distribution, W_y is the weight matrix, and Softmax() is the Softmax function.

6. The method according to claim 1, characterized in that, Also includes: The final document will be managed intelligently as a contract: The contract template (T), contract rules and conditions (R), data integration process (D), and contract status management process (S) are digitally encapsulated and linked, and their logical relationship is expressed as: Smart Contract = T + R + D + S.

7. A business document intelligent processing device based on artificial intelligence, characterized in that, include: The acquisition module is used to acquire the original business data associated with the user's file generation request in response to the user's request; The parsing module is used to parse the original business data using natural language processing technology to extract key information entities and semantic relationships, and generate structured business information. The analysis module is used to perform compliance verification and logical association analysis on the structured business information based on preset business rules and knowledge graphs, and to determine the type of target file to be generated and the content of the clauses to be filled in. The first generation module is used to call the corresponding pre-trained text generation model according to the target file type, and take the structured business information and the clause content as input to generate natural language text paragraphs that conform to grammatical and semantic rules. The second generation module is used to format and arrange the generated text paragraphs according to the standard template of the target file to generate a complete initial file; The verification module is used to review the content and verify key information of the initial document, and after the review is passed, execute the electronic signature process and output the final document.

8. The apparatus according to claim 7, characterized in that, The parsing module uses natural language processing technology to parse the raw business data, including: When the original business data is an image or scanned document, optical character recognition technology is used to convert it into original text. Lexical and syntactic analysis are performed on the original text to identify and label named entities, numerical values, dates, and key terms. By analyzing the relationships between actions, participants, and objects in the original text through semantic role annotation, an initial graph structure is constructed with the key information entities as nodes and semantic relationships as edges.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for performing the method described in any one of claims 1-6.

10. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1-6.

Images