Standard file content semantic vectorization method and device, medium and electronic equipment

By graphic and vectorizing enterprise standard files, the problems of low accuracy and lack of association relationships are solved, and efficient retrieval and utilization of standard file contents are achieved.

CN119088766APending Publication Date: 2024-12-06BEIJING SHENZHOU AEROSPACE SOFTWARE TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411138599.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

In the prior art, the accuracy rate of enterprise standard documents is not high, and there is a lack of correlation information between key elements after direct vectorization.

Method used

First graph the content of the standard file, extract key elements and association relationships, and then vectorize to generate a semantic vectorized standard file.

Benefits of technology

It improves the accuracy rate of enterprise standard documents, retains the correlation information between key elements, and enhances the relevance of content.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119088766A_ABST
    Figure CN119088766A_ABST
Patent Text Reader

Abstract

The invention discloses a standard file content semantic vectorization method and device, a medium and electronic equipment, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring a standard file to be subjected to content semantic vectorization; performing content mapping on the standard file to be subjected to content semantic vectorization to obtain a standard file subjected to mapping; and carrying out vectorization on the standard file subjected to mapping to obtain a vectorized standard file. The device comprises a standard file acquisition unit, a standard file mapping unit and a standard file vectorization unit. The medium and the electronic equipment can be used for realizing the method. The method comprises the following steps: firstly, carrying out content mapping on a standard file to be subjected to content semantic vectorization to obtain a mapped standard file; and then vectorizing the standard file subjected to mapping to obtain a vectorized standard file, so that the enterprise standard file can be ensured to have a relatively high precision ratio, and the problem that association relationship information among key elements of the enterprise standard file is lost can be avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device, medium and electronic device for semantic vectorization of standard file content. Background Art

[0002] In the prior art, there are two technical routes for processing enterprise standard documents: one is to map the content of enterprise standard documents, and the other is to directly vectorize the content of enterprise standard documents. However, the precision rate of enterprise standard documents that have only been mapped is not high; and there is a lack of correlation between the key elements of enterprise standard documents that have only been vectorized. Summary of the invention

[0003] In view of this, the present invention provides a method, device, medium and electronic device for semantic vectorization of standard file content, which first performs content graphing on the standard file to be semantically vectorized to obtain a graphed standard file; then vectorizes the graphed standard file to obtain a vectorized standard file, which can not only ensure that the enterprise standard file has a high precision rate, but also avoid the problem of missing information on the correlation relationship between key elements of the enterprise standard file, thereby being more suitable for practical use.

[0004] In order to achieve the above first objective, the technical solution of the standard file content semantic vectorization method provided by the present invention is as follows:

[0005] The standard file content semantic vectorization method provided by the present invention comprises the following steps:

[0006] Obtain the standard file to be semantically vectorized;

[0007] Performing content mapping on the standard file to be semantically vectorized to obtain a mapped standard file;

[0008] Vectorization is performed on the graphed standard file to obtain a vectorized standard file.

[0009] The standard file content semantic vectorization method provided by the present invention can also be further implemented by adopting the following technical measures.

[0010] Preferably, in the step of performing content mapping on the standard file to be semantically vectorized to obtain the mapped standard file, the mapped standard file includes a number, name, version, unit, time, preface, text, appendix and references, wherein:

[0011] The main text includes the scope, normative references, terms, principles, requirements, among which:

[0012] The requirements include clauses, tables, graphics, and formulas.

[0013] Preferably, in the step of vectorizing the graphed standard file to obtain the vectorized standard file, the vectorized standard file includes basic features and individual features, wherein:

[0014] The basic characteristics include standard number, name, version, drafting unit, release time, implementation time, category, first entity, last entity, and relationship type;

[0015] The personality basis of the personality feature is a vector object.

[0016] Preferably, performing content graphing on the standard file to be semantically vectorized to obtain the graphed standard file comprises the following steps:

[0017] Extracting the overall content information of the standard file to be semantically vectorized to obtain a graphed standard file specifically includes the following steps:

[0018] Extracting the standard file attributes to be semantically vectorized, wherein the standard file attributes to be semantically vectorized include number, name, version, unit and time;

[0019] The preface, main text, appendix and references of the standard document to be semantically vectorized are extracted.

[0020] Preferably, vectorizing the graphed standard file to obtain the vectorized standard file comprises the following steps:

[0021] Assigning entity feature attributes to the graphed standard document so that the graphed standard document is converted into a semantic vector based on entity features;

[0022] Assigning entity relationship feature attributes to the graphed standard document so that the standard entities involved in the graphed standard document are converted into semantic vectors based on entity relationship features;

[0023] A vectorized standard file is obtained according to the semantic vector based on entity features and the semantic vector based on entity relationship features.

[0024] Preferably, in the step of assigning attribute of entity feature to the graphed standard file so that the graphed standard file is converted into a semantic vector based on entity feature, the entity feature includes basic entity feature and entity individual feature, wherein:

[0025] The basic characteristics of the entity include standard number, name, version, drafting unit, release time, implementation time, category, number of neighbors, number of neighbor edges, path length, and centrality;

[0026] The entity personality characteristics include units, names, terms, formulas, cited files, and references, among which:

[0027] The individual characteristics of the unit include name, organization code, address, and legal person;

[0028] The personal characteristics of the person include name, ID number, gender, age, birthday, political status, marital status, work unit, and educational experience;

[0029] The individual characteristics of the term include the preceding collocation entity, the following collocation entity, whether it is a letter, uppercase or lowercase letters, profession, product, and system;

[0030] The individual characteristics of the formula include parameter type, parameter value range, number of parameters, operator, and whether it is a formula;

[0031] The individual characteristics of the referenced documents include standard number, name, version, drafting unit, release time, and implementation time;

[0032] The individual characteristics of the reference include the reference name, publisher, journal, author, abstract, and keywords.

[0033] Preferably, the graphed standard document entity relationship feature attributes are given so that in the step of converting the standard entities involved in the graphed standard document into semantic vectors based on entity relationship features, the entity relationship features include basic entity relationship features and entity relationship individual features, wherein:

[0034] The basic characteristics of the entity relationship include the first entity, the last entity, and the relationship type;

[0035] The entity relationship personality features include references and references, references and references, formulas and formulas, terms and terms, names and names, units and units, among which:

[0036] The individual characteristics of the relationship between units include the first unit, the last unit, the unit relationship type, and the degree of association;

[0037] The individual characteristics of the relationship between names include the first person, the last person, the type of relationship between people, and the degree of association;

[0038] The individual characteristics of the formula and formula relationship include the first formula, the last formula, the formula relationship type, and the correlation degree;

[0039] The individual characteristics of the term-to-term relationship include the preceding collocation entity, the succeeding collocation entity, the term relationship type, the correlation degree, etc.;

[0040] The individual characteristics of the referenced files and the relationship between the referenced files include the first referenced file, the last referenced file, the referenced file relationship type, and the degree of association;

[0041] The individual characteristics of the relationship between references include the first reference, the last reference, the reference relationship type, and the degree of association.

[0042] In order to achieve the above second purpose, the technical solution of the standard file content semantic vectorization device provided by the present invention is as follows:

[0043] The standard file content semantic vectorization device provided by the present invention comprises:

[0044] A standard file acquisition unit, used for acquiring a standard file to be semantically vectorized;

[0045] A standard file mapping unit, used for performing content mapping on the standard file to be semantically vectorized to obtain a mapped standard file;

[0046] The standard file vectorization unit is used to vectorize the graphed standard file to obtain a vectorized standard file.

[0047] In order to achieve the third objective above, the technical solution of the computer-readable storage medium provided by the present invention is as follows:

[0048] The computer-readable storage medium provided by the present invention stores a standard file content semantic vectorization program, and when the standard file content semantic vectorization program is executed by a processor, the steps of the standard file content semantic vectorization method provided by the present invention are implemented.

[0049] In order to achieve the fourth objective, the technical solution of the electronic device provided by the present invention is as follows:

[0050] The electronic device provided by the present invention includes a memory and a processor, wherein a standard file content semantic vectorization program is stored in the memory, and when the standard file content semantic vectorization program is executed by the processor, the steps of the standard file content semantic vectorization method provided by the present invention are implemented.

[0051] The method, device, medium and electronic device for semantic vectorization of standard documents provided by the present invention first map the enterprise standard documents and then perform semantic vectorization of the standard documents, thereby retaining the information characteristics of the association relationship between key elements, improving the precision rate of the enterprise standard, and enhancing the relevance of the content of the enterprise standard. First, the enterprise standard documents are mapped to establish the association of enterprise standard content. At present, the enterprise standard documents guide the scientific research and production of enterprises with the whole document as the unit, and it is impossible to quickly grasp the content context of the standard. By mapping the enterprise standard documents, the key elements of the enterprise standard are extracted, and the standard map is established to assist users to quickly grasp the content composition of the standard, improve the utilization efficiency of the standard, and complete the structuring of the enterprise standard documents, so that the standard guides scientific research and production with the clause as the unit; then, the enterprise standard map is vectorized to improve the precision rate of the enterprise standard. At present, the enterprise standard is retrieved based on keywords, and the query results are relatively broad, and it is up to people to identify which standard is suitable. Using the vector as the search condition, through similarity calculation, the query result is relatively accurate, and the precision rate of the enterprise standard is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0053] Figure 1 A flowchart of the steps of the method for semantic vectorization of standard file content provided by an embodiment of the present invention;

[0054] Figure 2 A flowchart of the steps of performing content mapping on a standard file to be semantically vectorized and obtaining a mapped standard file, which is involved in the method for semantic vectorization of standard file content provided in an embodiment of the present invention;

[0055] Figure 3 A flowchart of the steps of vectorizing a graphed standard file involved in the method for semantic vectorization of standard file content provided by an embodiment of the present invention to obtain a vectorized standard file;

[0056] Figure 4 A schematic diagram of the signal flow relationship between the functional modules in the standard file content semantic vectorization device provided by an embodiment of the present invention;

[0057] Figure 5 A schematic diagram of the structure of a standard file content semantic vectorization device in the hardware operating environment provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to solve the problems existing in the prior art, the present invention provides a method, device, medium and electronic device for semantic vectorization of standard file content, which firstly performs content graphing on the standard file to be semantically vectorized to obtain a graphed standard file; then vectorizes the graphed standard file to obtain a vectorized standard file, which can not only ensure that the enterprise standard file has a high precision rate, but also avoid the problem of missing information on the correlation relationship between key elements of the enterprise standard file, thereby being more suitable for practical use.

[0059] After arduous efforts, those skilled in the art have found that

[0060] (1) The enterprise standard document is graphed, but there is no graph vectorization process, resulting in a low precision rate. The enterprise standard document is processed into a standard document content graph, the key elements of the document content are extracted, the relationship between the key elements is established, and the content context of the standard document is described in the graph for easy viewing and understanding. For the retrieval of the enterprise standard document graph, only keyword search is applicable, and the query results are returned in the form of full-text matching. The query results are relatively broad and cannot be accurately located. Because there is no graph vectorization process, the precision rate is not high.

[0061] (2) Enterprise standard documents are directly vectorized without a graphing process, resulting in a lack of association between key elements. Enterprise standard documents are directly vectorized, and similarity calculations are performed on the semantic vectors formed by the key elements in the standard content. The result set with the highest similarity ranking is returned to achieve accurate positioning of the query conditions. Compared with the keyword matching method, the precision rate is greatly improved. Because the semantic vector is not capable of expressing the relationships contained in the enterprise standard content, the document content has not been processed by graphing, and the relationships contained in the key elements in the content cannot be effectively discovered, resulting in the lack of information on the association relationship between the key elements.

[0062] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the standard document content semantic vectorization method, device, medium and electronic device proposed by the present invention, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "embodiment" does not necessarily refer to the same embodiment. In addition, the features, structures, or characteristics of one or more embodiments may be combined in any suitable form.

[0063] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B. Specifically, it is understood that: A and B may be included at the same time, A may exist alone, or B may exist alone, and any of the above three situations may be met.

[0064] Standard document content semantic vectorization method

[0065] See attached Figure 1 The standard file content semantic vectorization method provided by the embodiment of the present invention includes the following steps:

[0066] Step S1: Obtain a standard file to be semantically vectorized;

[0067] Step S2: performing content mapping on the standard file to be semantically vectorized to obtain a mapped standard file;

[0068] Step S3: vectorize the graphed standard file to obtain a vectorized standard file.

[0069] The standard document semantic vectorization method provided by the present invention maps the enterprise standard document first and then performs semantic vectorization of the standard document, thereby retaining the information characteristics of the association relationship between key elements, improving the precision rate of the enterprise standard, and enhancing the relevance of the enterprise standard content. First, the enterprise standard document is mapped to establish the association of the enterprise standard content. At present, the enterprise standard document guides the scientific research and production of the enterprise in the form of the entire document, and it is impossible to quickly grasp the context of the standard content. By mapping the enterprise standard document, extracting the key elements of the enterprise standard, establishing a standard map, assisting users to quickly grasp the content composition of the standard, improving the utilization efficiency of the standard, and completing the structuring of the enterprise standard document, so that the standard guides scientific research and production in the form of clauses; then, the enterprise standard map is vectorized to improve the precision rate of the enterprise standard. At present, the enterprise standard is retrieved based on keywords, and the query results are relatively broad, and it is up to people to identify which standard is suitable. Using vectors as search conditions, through similarity calculation, the query results are relatively accurate, and the precision rate of enterprise standards is improved.

[0070] Among them, in the process of obtaining the graphed standard file by graphing the content of the standard file to be semantically vectorized, the graphed standard file includes number, name, version, unit, time, preface, text, appendix and references. Among them, the text includes scope, normative reference documents, terms, principles and requirements. Among them, the requirements include clauses, tables, graphics and formulas.

[0071] In the process of vectorizing the graphed standard file to obtain the vectorized standard file, the vectorized standard file includes basic features and individual features. The basic features include standard number, name, version, drafting unit, release time, implementation time, category, first entity, last entity, and relationship type. The individual basis of the individual features is the vector object.

[0072] Among them, see Appendix Figure 2 Step S2 performs content mapping on the standard file to be semantically vectorized, and obtaining the mapped standard file includes the following steps:

[0073] Step S21: extracting the overall content information of the standard file to be semantically vectorized to obtain a graphed standard file, which specifically includes the following steps:

[0074] Step S22: extracting standard file attributes to be vectorized for content semantics, where the standard file attributes to be vectorized for content semantics include number, name, version, unit and time;

[0075] Step S23: extracting the preface, main text, appendix and references of the standard document to be semantically vectorized.

[0076] Among them, see Appendix Figure 3 Step S3 vectorizes the graphed standard file, and obtaining the vectorized standard file includes the following steps:

[0077] Step S31: assigning attribute characteristics to the graphed standard document entity, so that the graphed standard document is converted into a semantic vector based on entity characteristics;

[0078] Step S32: assigning characteristic attributes to the entity relationships of the graphed standard document, so that the standard entities involved in the graphed standard document are converted into semantic vectors based on entity relationship characteristics;

[0079] Step S33: obtaining a vectorized standard file according to the semantic vector based on entity features and the semantic vector based on entity relationship features.

[0080] Among them, in the process of assigning attribute of entity feature to the graphed standard file so that the graphed standard file is converted into semantic vector based on entity feature, entity feature includes basic entity feature and entity personality feature. Among them, basic entity feature includes standard number, name, version, drafting unit, release time, implementation time, category, number of neighbors, number of neighbor edges, path length, and centrality. Entity personality feature includes unit, name, term, formula, cited file, and reference. Among them, the personality feature of unit includes name, organization code, address, and legal person. The personality feature of name includes name, ID number, gender, age, birthday, political status, marital status, work unit, and study experience. The personality feature of term includes preceding collocation entity, following collocation entity, whether it is a letter, uppercase and lowercase letters, major, product, and system. The personality feature of formula includes parameter type, parameter value range, number of parameters, operator, and whether it is a formula. The personality feature of reference file includes standard number, name, version, drafting unit, release time, and implementation time. The personality feature of reference includes reference name, publisher, journal, author, abstract, and keywords.

[0081] Among them, in the process of assigning characteristic attributes of the entity relationship of the graphed standard file so that the standard entities involved in the graphed standard file are converted into semantic vectors based on the entity relationship characteristics, the entity relationship characteristics include basic entity relationship characteristics and entity relationship individual characteristics. Among them, the basic entity relationship characteristics include the first entity, the last entity, and the relationship type. The individual characteristics of the entity relationship include the referenced file and the referenced file, the referenced document and the referenced document, the formula and the formula, the term and the term, the name and the name, and the unit and the unit. Among them, the individual characteristics of the relationship between units include the first unit, the last unit, the unit relationship type, and the correlation. The individual characteristics of the relationship between names include the first person, the last person, the person relationship type, and the correlation. The individual characteristics of the relationship between formulas include the first formula, the last formula, the formula relationship type, and the correlation. The individual characteristics of the relationship between terms include the first collocation entity, the second collocation entity, the term relationship type, and the correlation. The individual characteristics of the relationship between referenced files include the first referenced file, the last referenced file, the referenced file relationship type, and the correlation. The individual characteristics of the relationship between references include the first reference, the last reference, the reference relationship type, and the degree of relevance.

[0082] Standard document content semantic vectorization device

[0083] See attached Figure 4 The standard file content semantic vectorization device provided by the embodiment of the present invention includes:

[0084] A standard file acquisition unit, used for acquiring a standard file to be semantically vectorized;

[0085] A standard file mapping unit, used for mapping the content of the standard file to be semantically vectorized to obtain a mapped standard file;

[0086] The standard file vectorization unit is used to vectorize the graphed standard file to obtain a vectorized standard file.

[0087] The standard document semantic vectorization device provided by the present invention maps the enterprise standard document first and then performs semantic vectorization of the standard document, thereby retaining the information characteristics of the association relationship between key elements, improving the precision rate of the enterprise standard, and enhancing the relevance of the enterprise standard content. First, the enterprise standard document is mapped to establish the association of the enterprise standard content. At present, the enterprise standard document guides the scientific research and production of the enterprise in the form of the entire document, and it is impossible to quickly grasp the context of the standard content. By mapping the enterprise standard document, the key elements of the enterprise standard are extracted, and a standard map is established to assist users to quickly grasp the content composition of the standard, improve the utilization efficiency of the standard, and complete the structuring of the enterprise standard document, so that the standard guides scientific research and production in the form of clauses; then, the enterprise standard map is vectorized to improve the precision rate of the enterprise standard. At present, the enterprise standard is retrieved based on keywords, and the query results are relatively broad, and it is up to people to identify which standard is suitable. Using vectors as search conditions, through similarity calculation, the query results are relatively accurate, and the precision rate of enterprise standards is improved.

[0088] Computer readable storage medium

[0089] The computer-readable storage medium provided by the present invention stores a standard file content semantic vectorization program. When the standard file content semantic vectorization program is executed by a processor, the steps of the standard file content semantic vectorization method provided by the present invention are implemented.

[0090] The computer-readable storage medium and electronic device provided by the present invention map the enterprise standard file first and then perform semantic vectorization of the standard file, thereby retaining the information characteristics of the association relationship between key elements, improving the precision rate of the enterprise standard, and enhancing the relevance of the enterprise standard content. First, the enterprise standard file is mapped to establish the association of the enterprise standard content. At present, the enterprise standard file guides the scientific research and production of the enterprise in the form of the entire document, and it is impossible to quickly grasp the context of the standard content. By mapping the enterprise standard file, extracting the key elements of the enterprise standard, establishing a standard map, assisting users to quickly grasp the content composition of the standard, improving the utilization efficiency of the standard, and completing the structuring of the enterprise standard file, so that the standard guides scientific research and production in the form of clauses; then, the enterprise standard map is vectorized to improve the precision rate of the enterprise standard. At present, the enterprise standard is retrieved based on keywords, and the query results are relatively broad, and it is up to people to identify which standard is suitable. Using vectors as search conditions, through similarity calculation, the query results are relatively accurate, and the precision rate of enterprise standards is improved.

[0091] Electronic devices

[0092] The electronic device provided by the present invention includes a memory and a processor. The memory stores a standard file content semantic vectorization program. When the standard file content semantic vectorization program is executed by the processor, the steps of the standard file content semantic vectorization method provided by the present invention are implemented.

[0093] The electronic device provided by the present invention maps the enterprise standard document first and then performs semantic vectorization of the standard document, thereby retaining the information characteristics of the association relationship between key elements, improving the precision rate of the enterprise standard, and enhancing the relevance of the enterprise standard content. First, the enterprise standard document is mapped to establish the association of the enterprise standard content. At present, the enterprise standard document guides the scientific research and production of the enterprise in the form of the entire document, and it is impossible to quickly grasp the context of the standard content. By mapping the enterprise standard document, extracting the key elements of the enterprise standard, establishing a standard map, assisting users to quickly grasp the content composition of the standard, improving the utilization efficiency of the standard, and completing the structuring of the enterprise standard document, so that the standard guides scientific research and production in the form of clauses; then, the enterprise standard map is vectorized to improve the precision rate of the enterprise standard. At present, the enterprise standard is retrieved based on keywords, and the query results are relatively broad, and it is up to people to identify which standard is suitable. Using vectors as search conditions, through similarity calculation, the query results are relatively accurate, and the precision rate of enterprise standards is improved.

[0094] Reference Figure 5 , Figure 5 It is a schematic diagram of the structure of a standard file content semantic vectorization device in the hardware operating environment involved in the embodiment of the present invention.

[0095] like Figure 5 As shown, the standard file content semantic vectorization device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0096] Those skilled in the art will understand that Figure 5 The structure shown in does not constitute a limitation on the standard document content semantic vectorization device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0097] like Figure 5 As shown, the memory 1005 as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module, and a standard file content semantic vectorization program.

[0098] exist Figure 5 In the standard file content semantic vectorization device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the standard file content semantic vectorization device of the present invention can be set in the standard file content semantic vectorization device, and the standard file content semantic vectorization device calls the standard file content semantic vectorization program stored in the memory 1005 through the processor 1001, and executes the standard file content semantic vectorization method provided by the embodiment of the present invention.

[0099] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0100] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for semantic vectorization of standard file content, characterized in that: The following steps are involved: Obtain the standard file to be semantically vectorized; Performing content mapping on the standard file to be semantically vectorized to obtain a mapped standard file; Vectorization is performed on the graphed standard file to obtain a vectorized standard file.

2. The method for semantic vectorization of standard file content according to claim 1, characterized in that: In the step of performing content mapping on the standard file to be semantically vectorized to obtain a mapped standard file, the mapped standard file includes a number, name, version, unit, time, preface, text, appendix and references, wherein: The main text includes the scope, normative references, terms, principles, requirements, among which: The requirements include clauses, tables, graphics, and formulas.

3. The method for semantic vectorization of standard file content according to claim 1, characterized in that: In the step of vectorizing the graphed standard file to obtain the vectorized standard file, the vectorized standard file includes basic features and individual features, wherein: The basic characteristics include standard number, name, version, drafting unit, release time, implementation time, category, first entity, last entity, and relationship type; The personality basis of the personality feature is a vector object.

4. The method for semantic vectorization of standard file content according to claim 1, characterized in that: The content graphing is performed on the standard file to be semantically vectorized to obtain the graphed standard file, which includes the following steps: Extracting the overall content information of the standard file to be semantically vectorized to obtain a graphed standard file specifically includes the following steps: Extracting the standard file attributes to be semantically vectorized, wherein the standard file attributes to be semantically vectorized include number, name, version, unit and time; The preface, main text, appendix and references of the standard document to be semantically vectorized are extracted.

5. The method for semantic vectorization of standard file content according to claim 1, characterized in that: Vectorizing the graphed standard file to obtain the vectorized standard file includes the following steps: Assigning entity feature attributes to the graphed standard document so that the graphed standard document is converted into a semantic vector based on entity features; Assigning entity relationship feature attributes to the graphed standard document so that the standard entities involved in the graphed standard document are converted into semantic vectors based on entity relationship features; A vectorized standard file is obtained according to the semantic vector based on entity features and the semantic vector based on entity relationship features.

6. The method for semantic vectorization of standard file content according to claim 5, characterized in that: In the step of assigning attribute of entity feature to the graphed standard document so as to convert the graphed standard document into a semantic vector based on entity feature, the entity feature includes basic entity feature and individual entity feature, wherein: The basic characteristics of the entity include standard number, name, version, drafting unit, release time, implementation time, category, number of neighbors, number of neighbor edges, path length, and centrality; The entity personality characteristics include units, names, terms, formulas, cited files, and references, among which: The individual characteristics of the unit include name, organization code, address, and legal person; The personal characteristics of the person include name, ID number, gender, age, birthday, political status, marital status, work unit, and educational experience; The individual characteristics of the term include the preceding collocation entity, the following collocation entity, whether it is a letter, uppercase or lowercase letters, profession, product, and system; The individual characteristics of the formula include parameter type, parameter value range, number of parameters, operator, and whether it is a formula; The individual characteristics of the referenced documents include standard number, name, version, drafting unit, release time, and implementation time; The individual characteristics of the reference include the reference name, publisher, journal, author, abstract, and keywords.

7. The method for semantic vectorization of standard file content according to claim 5, characterized in that: In the step of assigning the graphed standard document entity relationship feature attributes so that the standard entities involved in the graphed standard document are converted into semantic vectors based on entity relationship features, the entity relationship features include basic entity relationship features and entity relationship individual features, wherein: The basic characteristics of the entity relationship include the first entity, the last entity, and the relationship type; The entity relationship personality features include references and references, references and references, formulas and formulas, terms and terms, names and names, units and units, among which: The individual characteristics of the relationship between units include the first unit, the last unit, the unit relationship type, and the degree of association; The individual characteristics of the relationship between names include the first person, the last person, the type of relationship between people, and the degree of association; The individual characteristics of the formula and formula relationship include the first formula, the last formula, the formula relationship type, and the correlation degree; The individual characteristics of the term-to-term relationship include the preceding collocation entity, the succeeding collocation entity, the term relationship type, the correlation degree, etc.; The individual characteristics of the referenced files and the relationship between the referenced files include the first referenced file, the last referenced file, the referenced file relationship type, and the degree of association; The individual characteristics of the relationship between references include the first reference, the last reference, the reference relationship type, and the degree of association.

8. A device for semantic vectorization of standard file content, characterized in that: include: A standard file acquisition unit, used for acquiring a standard file to be semantically vectorized; A standard file mapping unit, used for performing content mapping on the standard file to be semantically vectorized to obtain a mapped standard file; The standard file vectorization unit is used to vectorize the graphed standard file to obtain a vectorized standard file.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a standard file content semantic vectorization program, and when the standard file content semantic vectorization program is executed by a processor, the steps of the standard file content semantic vectorization method described in any one of claims 1-7 are implemented.

10. An electronic device, characterized in that: It includes a memory and a processor, wherein a standard file content semantic vectorization program is stored in the memory, and when the standard file content semantic vectorization program is executed by the processor, the steps of the standard file content semantic vectorization method described in any one of claims 1-7 are implemented.

Citation Information

Cited By

  • Semantic analysis method for industry standard

    CN122947748A