Association technology text novelty search method and system based on semantic recognition

Abstract

The invention discloses an association technology text novelty retrieval method and system based on semantic recognition, and relates to the technical field of patent novelty retrieval, and the method comprises the steps: obtaining at least one to-be-retrieved technical keyword based on to-be-retrieved technical content; obtaining a key index of each to-be-retrieved technical keyword in the to-be-retrieved technical content text; obtaining an existing associated technical content set corresponding to each to-be-retrieved technical keyword, and solving a union set to obtain a total associated technical content set of the to-be-retrieved technical content; based on a technology association algorithm, respectively calculating an association index of each existing association technology in the total association technology content set and the to-be-retrieved technology content; and based on the association index of the to-be-retrieved technical content, outputting the technical text content associated with the to-be-retrieved technical content. The method has the advantages that the technical content highly related to the innovation subject can be rapidly and accurately output, and the working efficiency and the success rate of a user in the technology research and development and innovation process are greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of patent novelty search technology, and in particular to a method and system for searching related technical texts based on semantic recognition. Background Art

[0002] Intelligent knowledge search is an important part of patent search innovation. An excellent intelligent resource search system can perform intelligent technology search based on the different technical needs of different users, helping users to accurately search for relevant knowledge materials and master target knowledge and skills while searching for less content. At present, traditional search methods are generally static, divided into collaborative filtering-based search and content-based search. In recent years, deep query and enhanced query-based search have also emerged. Although many search algorithms have been proposed, due to the continuous innovation and iteration of technology, direct search of knowledge resources based on text keywords can no longer meet the daily needs of users, and accurate information cannot be obtained from a large number of resources. It is necessary to find a better solution for related technical text search. Summary of the invention

[0003] In order to solve the above technical problems, a method and system for searching related technical texts based on semantic recognition is provided. This technical solution solves the problem that the direct retrieval of knowledge resources based on text keywords can no longer meet the daily needs of users and cannot obtain accurate information from a large amount of resources.

[0004] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0005] A novelty search method for related technical texts based on semantic recognition, comprising:

[0006] Based on the technical content to be searched, obtaining at least one technical keyword to be searched;

[0007] Based on the technical keywords to be searched, search and match the existing technical content to be searched, and obtain the key index of each technical keyword to be searched in the technical content text to be searched;

[0008] Using the technical keywords to be searched to perform search and matching in the existing prior art database, obtaining all the existing related technical contents that match each technical keyword to be searched, and forming a set of existing related technical contents corresponding to each technical keyword to be searched;

[0009] The total set of existing related technical contents corresponding to all technical keywords to be searched is combined to obtain the total set of related technical contents of the technical contents to be searched;

[0010] Based on the technical association algorithm, the association index between each existing related technology in the total set of related technical content and the technical content to be retrieved is calculated respectively;

[0011] Based on the correlation index with the technical content to be retrieved, the technical text content associated with the technical content to be retrieved is output.

[0012] Preferably, the searching and matching based on the technical keywords to be searched in the existing technical content to be searched, and obtaining the key index of each technical keyword to be searched in the technical content text to be searched specifically includes:

[0013] The word segmentation technology is used to perform word segmentation processing on the technical content text to be retrieved, so as to obtain a word set of the technical content text to be retrieved;

[0014] Compare the number of occurrences of the technical keywords to be searched in the word set with the total number of words in the word set to obtain the TF value of the technical keywords to be searched in the technical content text to be searched;

[0015] According to the key indexes of all the technical keywords to be searched in the technical content text to be searched, normalization standard processing is performed to obtain the key indexes of the technical keywords to be searched in the technical content text to be searched;

[0016] The formula for the normalization standard processing is:

[0017]

[0018] Among them, G i is the key index of the i-th technical keyword to be retrieved in the technical content text to be retrieved, TF i is the TF value of the i-th technical keyword to be searched in the technical content text to be searched, and n is the total number of technical keywords to be searched.

[0019] Preferably, the method of using the to-be-searched technical keywords to search and match in the existing prior art database, obtaining all the existing related technical contents that match each to-be-searched technical keyword, and forming a set of existing related technical contents corresponding to each to-be-searched technical keyword specifically includes:

[0020] Based on the searched technical keywords and the existing prior art database, the prior art data in which the searched technical keywords appear in all content texts are recorded as the corresponding related existing technologies matched by the searched technical keywords;

[0021] All existing related technologies that match the technical keywords to be searched are obtained to form a set of existing related technology content corresponding to the technical keywords to be searched.

[0022] Preferably, the technology association algorithm specifically includes:

[0023] Based on the keyword matching algorithm, determine the initial technical relevance index of each existing related technology in the total set of existing related technical content;

[0024] Based on the reference relationship of the existing related technologies in the total set of existing related technology contents, determine the reference technology set and the referenced technology set of each existing related technology;

[0025] Based on the correlation analysis formula, the updated value of the technology correlation index of each existing related technology in the total set of existing related technology contents is calculated by combining the initial technology correlation index of each existing related technology in the total set of existing related technology contents, the referenced technology set and the referenced technology set;

[0026] Determine whether the deviation between the updated technical correlation index value of each existing related technology in the total set of existing related technical content and the initial technical correlation index of each existing related technology in the total set of existing related technical content is less than the deviation threshold value; if so, output the updated technical correlation index value of each existing related technology in the total set of existing related technical content as the correlation index between each existing related technology in the total set of related technical content and the technical content to be retrieved; if not, normalize the updated technical correlation index value of each existing related technology in the total set of existing related technical content and re-substitute it into the correlation analysis formula as the initial technical correlation index of each existing related technology in the total set of existing related technical content for calculation;

[0027] The correlation analysis formula is as follows:

[0028]

[0029] In the formula, Update the technical relevance index value of the u-th existing related technology in the total set of existing related technology contents;

[0030] is the initial technical relevance index of the u-th existing related technology in the total set of existing related technical contents;

[0031] α is the damping coefficient;

[0032] B u is the cited technology set of the uth existing related technology in the total set of existing related technology contents;

[0033] bv is the vth element in the cited technology set of the uth existing related technology in the total set of existing related technology contents;

[0034] is the initial technology relevance index of the vth element in the cited technology set of the uth existing related technology in the total set of existing related technology contents;

[0035] N v It is the total number of elements in the referenced technology set of the vth element in the referenced technology set of the uth existing related technology in the total set of existing related technology contents.

[0036] Preferably, the keyword matching algorithm specifically includes:

[0037] Obtain at least one to-be-searched technical keyword corresponding to an existing related technology in the total set of existing related technical contents, and construct a technical keyword set of the existing related technology;

[0038] The existing related technical text is segmented by using the word segmentation technology to obtain a word set of the existing related technical text;

[0039] The number of occurrences of the elements in the technical keyword set of the existing related technology in the word set of the existing related technology text is compared with the total number of words in the word set of the existing related technology text to obtain the TF value of the elements in the technical keyword set of the existing related technology in the existing related technology text;

[0040] The initial technical relevance index of the existing related technology is calculated by combining the key index of the element in the technical keyword set of the existing related technology and the TF value of the element in the technical keyword set of the existing related technology in the existing related technology text through the initial relevance formula;

[0041] The initial correlation formula is specifically:

[0042]

[0043] In the formula, a j is the jth element in the technical keyword set of existing related technologies, A u is the technical keyword set of the u-th existing related technology, G j is the key index of the jth element in the technical keyword set of the existing related technology, TF j is the TF value of the jth element in the technical keyword set of the existing related technology in the existing related technology text, and m is the total number of existing related technologies in the total set of existing related technology content.

[0044] Preferably, the calculation formula for the deviation value between the updated value of the technical correlation index of each existing related technology in the total set of existing related technology content and the initial technical correlation index of each existing related technology in the total set of existing related technology content is:

[0045]

[0046] Where P is the deviation value;

[0047] The calculation formula for normalizing the technical correlation index update value of each existing related technology in the total set of existing related technology contents is:

[0048]

[0049] in, is the updated initial technology association index of the u-th existing associated technology.

[0050] Furthermore, a novelty search system for related technical texts based on semantic recognition is proposed, which is used to implement the novelty search method for related technical texts based on semantic recognition as described above, comprising:

[0051] A keyword extraction module, wherein the keyword extraction unit is used to obtain at least one technical keyword to be retrieved based on the technical content to be retrieved;

[0052] A self-matching module, the self-matching module being electrically connected to the keyword extraction module, and the self-matching module being used to perform search and matching on the existing technical content to be searched based on the technical keyword to be searched, and to obtain a key index of each technical keyword to be searched in the technical content text to be searched;

[0053] A search module, the search module is electrically connected to the keyword extraction module, and the search module is used to use the technical keywords to be searched to perform search and matching in the existing prior art database, obtain all the existing related technical contents corresponding to each technical keyword to be searched, and form a set of existing related technical contents corresponding to each technical keyword to be searched, and calculate the union of the total set of existing related technical contents corresponding to all the technical keywords to be searched, so as to obtain the total set of related technical contents of the technical contents to be searched;

[0054] An association matching module, the association matching module is electrically connected to the keyword extraction module and the retrieval module, and is used to calculate the association index between each existing related technology in the total set of related technical content and the technical content to be retrieved based on the technical association algorithm, and output the related technical text content with the technical content to be retrieved based on the association index with the technical content to be retrieved.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] The present invention proposes a novelty search scheme for related technical texts based on semantic recognition. By performing multiple related technical searches on the relevant weights of technical keywords and the technology itself, the correlation between technical keywords and the retrieved texts, and the mutual citation relationship between the retrieved technical texts, the correlation between the retrieved related technical contents and the technology itself is effectively improved, thereby providing accurate prior art texts for the innovativeness evaluation of the technical contents, thereby improving the accuracy of users' novelty search judgments on the technical contents. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 Flow chart of the novelty search method for related technical texts based on semantic recognition proposed in this solution;

[0058] Figure 2 A flowchart of a method for determining the key index of each technical keyword to be searched in the technical content text to be searched in this solution;

[0059] Figure 3 A flowchart of a method for forming a set of existing related technical contents corresponding to the technical keywords to be searched in this solution;

[0060] Figure 4 A method flow chart of the technical association algorithm in this solution;

[0061] Figure 5 This is a method flow chart of the keyword matching algorithm in this solution;

[0062] Figure 6 This is a schematic diagram of the electronic device of the present application;

[0063] Figure 7 This is a schematic diagram of the computer-readable storage medium structure of the present application. DETAILED DESCRIPTION

[0064] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0065] Reference Figure 1 As shown, a novelty search method for related technical texts based on semantic recognition includes:

[0066] Based on the technical content to be searched, obtaining at least one technical keyword to be searched;

[0067] Based on the technical keywords to be searched, search and match the existing technical content to be searched, and obtain the key index of each technical keyword to be searched in the technical content text to be searched;

[0068] Using the technical keywords to be searched to perform search and matching in the existing prior art database, obtaining all the existing related technical contents that match each technical keyword to be searched, and forming a set of existing related technical contents corresponding to each technical keyword to be searched;

[0069] The total set of existing related technical contents corresponding to all technical keywords to be searched is combined to obtain the total set of related technical contents of the technical contents to be searched;

[0070] Based on the technical association algorithm, the association index between each existing related technology in the total set of related technical content and the technical content to be retrieved is calculated respectively;

[0071] Based on the correlation index with the technical content to be retrieved, the technical text content associated with the technical content to be retrieved is output.

[0072] The present invention is not limited to keyword analysis and retrieval at a single level, but adopts a multi-dimensional and multi-level comprehensive evaluation method. It deeply explores the intrinsic connection between technical keywords and technical entities, carefully quantifies the degree of correlation between technical keywords and retrieved texts, and carefully tracks the mutual references and correlation contexts between retrieved technical texts. Through this comprehensive and in-depth retrieval strategy, this solution greatly improves the fit between the retrieved technical content and the user's own technical field. It provides rich and accurate existing technical text resources for evaluating the innovativeness of technical content. These resources are like a beacon of wisdom, illuminating the road to technological innovation. In addition, this solution also significantly enhances the user's ability to search for new information when facing massive technical information. It can not only help users quickly locate the most relevant and valuable technical texts, but also guide users to discover potential technical breakthroughs and innovation opportunities through intelligent analysis and suggestions. Thereby, the efficiency and success rate of users in the process of technology research and development and innovation are greatly improved.

[0073] Reference Figure 2 As shown, based on the technical keywords to be searched, the existing technical content to be searched is searched and matched, and the key index of each technical keyword to be searched in the technical content text to be searched is obtained, which specifically includes:

[0074] The word segmentation technology is used to perform word segmentation processing on the technical content text to be retrieved, so as to obtain a word set of the technical content text to be retrieved;

[0075] Compare the number of occurrences of the technical keywords to be searched in the word set with the total number of words in the word set to obtain the TF value of the technical keywords to be searched in the technical content text to be searched;

[0076] According to the key indexes of all the technical keywords to be searched in the technical content text to be searched, normalization standard processing is performed to obtain the key indexes of the technical keywords to be searched in the technical content text to be searched;

[0077] The formula for normalization standard processing is:

[0078]

[0079] Among them, G i is the key index of the i-th technical keyword to be retrieved in the technical content text to be retrieved, TF i is the TF value of the i-th technical keyword to be searched in the technical content text to be searched, and n is the total number of technical keywords to be searched.

[0080] In this scheme, the correlation between technical keywords and technical content is analyzed by word frequency analysis. The more times a technical keyword appears in the technical text, the more it represents the core technical content.

[0081] Reference Figure 3 As shown, the technical keywords to be searched are used to search and match in the existing prior art database, and all the existing related technical contents corresponding to each technical keyword to be searched are obtained, and the existing related technical content set corresponding to each technical keyword to be searched is specifically composed of:

[0082] Based on the searched technical keywords and the existing prior art database, the prior art data in which the searched technical keywords appear in all content texts are recorded as the corresponding related existing technologies matched by the searched technical keywords;

[0083] All existing related technologies that match the technical keywords to be searched are obtained to form a set of existing related technology content corresponding to the technical keywords to be searched.

[0084] By directly searching, all existing technologies that may be related to the technical content to be searched can be screened out, which can ensure the completeness of the search content, thereby reducing the missed detection rate and avoiding omissions in the search.

[0085] Reference Figure 4 As shown, the technical association algorithm specifically includes:

[0086] Based on the keyword matching algorithm, determine the initial technical relevance index of each existing related technology in the total set of existing related technical content;

[0087] Based on the reference relationship of the existing related technologies in the total set of existing related technology contents, determine the reference technology set and the referenced technology set of each existing related technology;

[0088] Based on the correlation analysis formula, the updated value of the technology correlation index of each existing related technology in the total set of existing related technology contents is calculated by combining the initial technology correlation index of each existing related technology in the total set of existing related technology contents, the referenced technology set and the referenced technology set;

[0089] Determine whether the deviation between the updated technical correlation index value of each existing related technology in the total set of existing related technical content and the initial technical correlation index of each existing related technology in the total set of existing related technical content is less than the deviation threshold value; if so, output the updated technical correlation index value of each existing related technology in the total set of existing related technical content as the correlation index between each existing related technology in the total set of related technical content and the technical content to be retrieved; if not, normalize the updated technical correlation index value of each existing related technology in the total set of existing related technical content and re-substitute it into the correlation analysis formula as the initial technical correlation index of each existing related technology in the total set of existing related technical content for calculation;

[0090] The correlation analysis formula is as follows:

[0091]

[0092] In the formula, Update the technical relevance index value of the u-th existing related technology in the total set of existing related technology contents;

[0093] is the initial technical relevance index of the u-th existing related technology in the total set of existing related technical contents;

[0094] α is the damping coefficient;

[0095] B u is the cited technology set of the uth existing related technology in the total set of existing related technology contents;

[0096] bv is the vth element in the cited technology set of the uth existing related technology in the total set of existing related technology contents;

[0097] is the initial technology relevance index of the vth element in the cited technology set of the uth existing related technology in the total set of existing related technology contents;

[0098] N v It is the total number of elements in the referenced technology set of the vth element in the referenced technology set of the uth existing related technology in the total set of existing related technology contents.

[0099] The calculation formula for the deviation value between the updated value of the technical correlation index of each existing related technology in the total set of existing related technology content and the initial technical correlation index of each existing related technology in the total set of existing related technology content is:

[0100]

[0101] Where P is the deviation value;

[0102] The calculation formula for normalizing the updated value of the technical relevance index of each existing related technology in the total set of existing related technology content is:

[0103]

[0104] in, is the updated initial technology association index of the u-th existing associated technology.

[0105] Reference Figure 5 As shown in the figure, the keyword matching algorithm specifically includes:

[0106] Obtain at least one to-be-searched technical keyword corresponding to an existing related technology in the total set of existing related technical contents, and construct a technical keyword set of the existing related technology;

[0107] The existing related technical text is segmented by using the word segmentation technology to obtain a word set of the existing related technical text;

[0108] The number of occurrences of the elements in the technical keyword set of the existing related technology in the word set of the existing related technology text is compared with the total number of words in the word set of the existing related technology text to obtain the TF value of the elements in the technical keyword set of the existing related technology in the existing related technology text;

[0109] The initial technical relevance index of the existing related technology is calculated by combining the key index of the elements in the technical keyword set of the existing related technology and the TF value of the elements in the technical keyword set of the existing related technology in the existing related technology text through the initial relevance formula;

[0110] Among them, the initial correlation formula is specifically:

[0111]

[0112] In the formula, a j is the jth element in the technical keyword set of existing related technologies, A u is the technical keyword set of the u-th existing related technology, G j is the key index of the jth element in the technical keyword set of the existing related technology, TF jis the TF value of the jth element in the technical keyword set of the existing related technology in the existing related technology text, and m is the total number of existing related technologies in the total set of existing related technology content.

[0113] In this solution, the present invention gives an initial correlation index to the existing related technologies by comprehensively considering the two key dimensions of the correlation weight between the technical keywords and the technology itself and the correlation between the technical keywords and the retrieved text. This index not only intuitively reflects the direct correlation between the existing related technologies and the technologies to be retrieved, but also lays a solid foundation for subsequent in-depth mining. On this basis, the present invention cleverly combines the relevant reference relationship between the existing related technologies and draws on the core idea of ​​the PageRank algorithm to further screen and refine the more authoritative and influential technical content in the existing related technologies. This process aims to capture those technical contents that are truly meaningful for new searches. Through this series of precise and efficient multi-related technology retrieval operations, the present invention can quickly and accurately output technical content that is highly relevant to the innovation subject. This not only provides users with a shortcut to quickly locate the most relevant and valuable technical texts, but also inspires users' innovative inspiration through intelligent analysis and suggestions, guides them to discover potential technical breakthroughs and innovation opportunities, and greatly improves the work efficiency and success rate of users in the process of technology research and development and innovation.

[0114] Further, based on the same inventive concept as the above-mentioned related technical text novelty search method based on semantic recognition, this solution proposes a related technical text novelty search system based on semantic recognition, comprising:

[0115] A keyword extraction module, the keyword extraction unit is used to obtain at least one technical keyword to be retrieved based on the technical content to be retrieved;

[0116] A self-matching module, the self-matching module is electrically connected to the keyword extraction module, and the self-matching module is used to perform search and matching based on the technical keywords to be searched in the existing technical content to be searched, and obtain the key index of each technical keyword to be searched in the technical content text to be searched;

[0117] A search module, the search module is electrically connected to the keyword extraction module, and is used to use the technical keywords to be searched to perform search and matching in the existing prior art database, obtain all the existing related technical contents corresponding to each technical keyword to be searched, and form a set of existing related technical contents corresponding to each technical keyword to be searched, and calculate the union of the total set of existing related technical contents corresponding to all the technical keywords to be searched, so as to obtain the total set of related technical contents of the technical contents to be searched;

[0118] The association matching module is electrically connected to the keyword extraction module and the retrieval module. The association matching module is used to calculate the association index between each existing related technology in the total set of related technical content and the technical content to be retrieved based on the technical association algorithm, and output the related technical text content with the technical content to be retrieved based on the association index with the technical content to be retrieved.

[0119] The process of using the above system is:

[0120] Step 1: The keyword extraction module obtains at least one technical keyword to be searched based on the technical content to be searched;

[0121] Step 2: The self-matching module searches and matches the existing technical content to be searched based on the technical keywords to be searched, and obtains the key index of each technical keyword to be searched in the technical content text to be searched;

[0122] Step 3: The search module uses the technical keywords to be searched to search and match in the existing prior art database, obtains all the existing related technical contents corresponding to each technical keyword to be searched, and forms a set of existing related technical contents corresponding to each technical keyword to be searched, and calculates the union of the total set of existing related technical contents corresponding to all technical keywords to be searched, so as to obtain the total set of related technical contents of the technical contents to be searched;

[0123] Step 4: The association matching module calculates the association index between each existing related technology in the total set of related technical content and the technical content to be retrieved based on the technical association algorithm, and outputs the related technical text content with the technical content to be retrieved based on the association index with the technical content to be retrieved.

[0124] Furthermore, the method according to the embodiment of the present application can also be performed by Figure 6 The electronic device architecture shown in FIG. Figure 6 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store a method for searching related technical texts based on semantic recognition provided by the present application. The electronic device 500 may also include a user interface 508. Of course, Figure 6 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 6 One or more components of an electronic device are shown.

[0125] Figure 7Schematic diagram of a computer-readable storage medium structure provided by an embodiment of the present application. Figure 7 As shown, a computer-readable storage medium 600 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, a method for searching for related technical texts based on semantic recognition according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0126] In summary, the advantages of the present invention are that it can quickly and accurately output technical content that is highly relevant to the innovation subject, greatly improving the work efficiency and success rate of users in the process of technology research and development and innovation.

[0127] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for searching related technical texts based on semantic recognition, characterized in that: include: Based on the technical content to be searched, obtaining at least one technical keyword to be searched; Based on the technical keywords to be searched, search and match the existing technical content to be searched, and obtain the key index of each technical keyword to be searched in the technical content text to be searched; Using the technical keywords to be searched to perform search and matching in the existing prior art database, obtaining all the existing related technical contents that match each technical keyword to be searched, and forming a set of existing related technical contents corresponding to each technical keyword to be searched; The total set of existing related technical contents corresponding to all technical keywords to be searched is combined to obtain the total set of related technical contents of the technical contents to be searched; Based on the technical association algorithm, the association index between each existing related technology in the total set of related technical content and the technical content to be retrieved is calculated respectively; Based on the correlation index with the technical content to be retrieved, the technical text content associated with the technical content to be retrieved is output.

2. The method for searching related technical texts based on semantic recognition according to claim 1, characterized in that: The method of performing search and matching based on the technical keywords to be searched in the existing technical content to be searched and obtaining the key index of each technical keyword to be searched in the technical content text to be searched specifically includes: The word segmentation technology is used to perform word segmentation processing on the technical content text to be retrieved, so as to obtain a word set of the technical content text to be retrieved; Compare the number of occurrences of the technical keywords to be searched in the word set with the total number of words in the word set to obtain the TF value of the technical keywords to be searched in the technical content text to be searched; According to the key indexes of all the technical keywords to be searched in the technical content text to be searched, normalization standard processing is performed to obtain the key indexes of the technical keywords to be searched in the technical content text to be searched; The formula for the normalization standard processing is: Among them, G i is the key index of the i-th technical keyword to be retrieved in the technical content text to be retrieved, TF i is the TF value of the i-th technical keyword to be searched in the technical content text to be searched, and n is the total number of technical keywords to be searched.

3. The method for searching related technical texts based on semantic recognition according to claim 2, characterized in that: The method of using the technical keywords to be searched to search and match in the existing prior art database, obtaining all the existing related technical contents corresponding to each technical keyword to be searched, and forming a set of existing related technical contents corresponding to each technical keyword to be searched specifically includes: Based on the searched technical keywords and the existing prior art database, the prior art data in which the searched technical keywords appear in all content texts are recorded as the corresponding related existing technologies matched by the searched technical keywords; All existing related technologies that match the technical keywords to be searched are obtained to form a set of existing related technology content corresponding to the technical keywords to be searched.

4. The method for searching related technical texts based on semantic recognition according to claim 3 is characterized in that: The technical association algorithm specifically includes: Based on the keyword matching algorithm, determine the initial technical relevance index of each existing related technology in the total set of existing related technical content; Based on the reference relationship of the existing related technologies in the total set of existing related technology contents, determine the reference technology set and the referenced technology set of each existing related technology; Based on the correlation analysis formula, the updated value of the technology correlation index of each existing related technology in the total set of existing related technology contents is calculated by combining the initial technology correlation index of each existing related technology in the total set of existing related technology contents, the referenced technology set and the referenced technology set; Determine whether the deviation between the updated technical correlation index value of each existing related technology in the total set of existing related technical contents and the initial technical correlation index of each existing related technology in the total set of existing related technical contents is less than the deviation threshold value; if so, output the updated technical correlation index value of each existing related technology in the total set of existing related technical contents as the correlation index between each existing related technology in the total set of related technical contents and the technical contents to be retrieved; if not, normalize the updated technical correlation index value of each existing related technology in the total set of existing related technical contents and substitute it into the correlation analysis formula as the initial technical correlation index of each existing related technology in the total set of existing related technical contents for calculation; The correlation analysis formula is as follows: In the formula, Update the technical relevance index value of the u-th existing related technology in the total set of existing related technology contents; is the initial technical relevance index of the u-th existing related technology in the total set of existing related technical contents; α is the damping coefficient; B u is the cited technology set of the u-th existing related technology in the total set of existing related technology contents; bv is the vth element in the cited technology set of the uth existing related technology in the total set of existing related technology contents; is the initial technology relevance index of the vth element in the cited technology set of the uth existing related technology in the total set of existing related technology contents; N v It is the total number of elements in the referenced technology set of the vth element in the referenced technology set of the uth existing related technology in the total set of existing related technology contents.

5. The method for searching related technical texts based on semantic recognition according to claim 4 is characterized in that: The keyword matching algorithm specifically includes: Obtain at least one to-be-searched technical keyword corresponding to an existing related technology in the total set of existing related technical contents, and construct a technical keyword set of the existing related technology; The existing related technical text is segmented by using the word segmentation technology to obtain a word set of the existing related technical text; The number of occurrences of the elements in the technical keyword set of the existing related technology in the word set of the existing related technology text is compared with the total number of words in the word set of the existing related technology text to obtain the TF value of the elements in the technical keyword set of the existing related technology in the existing related technology text; The initial technical relevance index of the existing related technology is calculated by combining the key index of the elements in the technical keyword set of the existing related technology and the TF value of the elements in the technical keyword set of the existing related technology in the existing related technology text through the initial relevance formula; The initial correlation formula is specifically: In the formula, a j is the jth element in the technical keyword set of existing related technologies, A u is the technical keyword set of the u-th existing related technology, G j is the key index of the jth element in the technical keyword set of the existing related technology, TF j is the TF value of the jth element in the technical keyword set of the existing related technology in the existing related technology text, and m is the total number of existing related technologies in the total set of existing related technology content.

6. The method for searching related technical texts based on semantic recognition according to claim 5, characterized in that: The calculation formula for the deviation value between the updated value of the technical correlation index of each existing related technology in the total set of existing related technology content and the initial technical correlation index of each existing related technology in the total set of existing related technology content is: Where P is the deviation value; The calculation formula for normalizing the technical correlation index update value of each existing related technology in the total set of existing related technology contents is: in, is the updated initial technology association index of the u-th existing associated technology.

7. A new search system for related technical texts based on semantic recognition, characterized in that: The method for searching related technical texts based on semantic recognition as described in any one of claims 1 to 6 comprises: A keyword extraction module, wherein the keyword extraction unit is used to obtain at least one technical keyword to be retrieved based on the technical content to be retrieved; A self-matching module, the self-matching module being electrically connected to the keyword extraction module, and the self-matching module being used to perform search and matching on the existing technical content to be searched based on the technical keyword to be searched, and to obtain a key index of each technical keyword to be searched in the technical content text to be searched; A search module, the search module is electrically connected to the keyword extraction module, and the search module is used to use the technical keywords to be searched to perform search and matching in the existing prior art database, obtain all the existing related technical contents corresponding to each technical keyword to be searched, and form a set of existing related technical contents corresponding to each technical keyword to be searched, and calculate the union of the total set of existing related technical contents corresponding to all the technical keywords to be searched, so as to obtain the total set of related technical contents of the technical contents to be searched; An association matching module, the association matching module is electrically connected to the keyword extraction module and the retrieval module, and is used to calculate the association index between each existing related technology in the total set of related technical content and the technical content to be retrieved based on the technical association algorithm, and output the related technical text content with the technical content to be retrieved based on the association index with the technical content to be retrieved.

8. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method for searching related technical texts based on semantic recognition as described in any one of claims 1-6.

9. A computer-readable storage medium storing computer-readable instructions, characterized in that: When the computer-readable instructions are executed by a processor, a method for searching related technical texts based on semantic recognition as described in any one of claims 1 to 6 is implemented.

Images