Scientific and technological achievement association analysis method and system based on big data and medium
Through big data methods, the data of scientific and technological achievements are encrypted and associated matching, and the correlation index is calculated, which solves the problem that traditional methods are difficult to analyze the correlation of scientific and technological achievements, and realizes efficient correlation analysis and sorting, supporting scientific research and technological innovation.
Patent Information
- Application Number
- CN202411072855.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-06
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
It is difficult for the existing technology to effectively analyze and reveal the degree and correlation between scientific and technological achievements, especially in the huge ocean of data. Traditional methods are limited by the amount of data and processing speed, making it difficult to fully and accurately realize the correlation analysis of scientific and technological achievements.
Through a big data-based method, scientific and technological achievements data sets and historical data sets are obtained and encrypted, correlation matching is performed, association matching index, authoritative validity index and reference recommendation index are calculated, and correlation status data is obtained after threshold comparison to achieve correlation Classification sorting and analysis of files.
It realizes accurate analysis of the correlation degree of scientific and technological achievements, improves data processing efficiency and analysis accuracy, and can effectively identify and sort strongly relevant scientific and technological achievements documents to help scientific research management and technological innovation.
Smart Images

Figure CN118940835A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of scientific and technological achievement correlation analysis, and specifically, to a scientific and technological achievement correlation analysis method, system and medium based on big data. Background Art
[0002] With the rapid development of science and technology, the number of scientific and technological achievements produced each year around the world has increased dramatically, including academic papers, patents, technical reports and other forms. These achievements are scattered in different fields and databases, forming a huge ocean of data. However, how to effectively mine valuable information from these data, especially the degree of correlation and correlation between scientific and technological achievements, has become an important challenge facing current scientific research management and technological innovation. Traditional analysis methods are often limited by the amount of data, processing speed and analysis capabilities, and it is difficult to fully and accurately reveal the degree of correlation between scientific and technological achievements. Therefore, how to realize the correlation analysis of scientific and technological achievements based on big data has become a problem that needs to be solved at present.
[0003] In view of the above problems, effective technical solutions are urgently needed. Summary of the invention
[0004] The purpose of this application is to provide a method, system and medium for correlation analysis of scientific and technological achievements based on big data, which can realize the correlation analysis technology of related files by calculating the correlation matching index, authoritative validity index and reference recommendation index, obtaining the correlation status data after threshold comparison.
[0005] This application also provides a method for analyzing the association of scientific and technological achievements based on big data, comprising the following steps:
[0006] Obtain information on scientific and technological achievements and historical scientific and technological achievements databases, and extract scientific and technological achievement data sets and historical scientific and technological achievements databases;
[0007] Encrypt the scientific and technological achievement data set and the historical scientific and technological achievement database according to preset encryption rules to obtain an encrypted scientific and technological achievement data set and an encrypted historical scientific and technological achievement database;
[0008] Perform correlation matching on the encrypted scientific and technological achievement data set and the encrypted historical scientific and technological achievement database to obtain correlation data of the associated files, and process the correlation data through a preset correlation matching detection model to obtain a correlation matching index;
[0009] Obtain the associated impact data of the associated files, and calculate the authoritative validity index through a preset authoritative validity index detection model;
[0010] Calculating a reference recommendation index based on the association matching index and the authoritative validity index;
[0011] Compare the reference recommendation index with a preset reference recommendation index threshold to obtain correlation status data;
[0012] The associated files are classified and sorted according to the association status data combined with the reference recommendation index, and sent to a preset client.
[0013] Optionally, in the method for analyzing the association of scientific and technological achievements based on big data described in the present application, the obtaining of scientific and technological achievement information and historical scientific and technological achievement database information, and extracting scientific and technological achievement data sets and historical scientific and technological achievement databases, specifically includes:
[0014] Obtain scientific and technological achievement information and extract scientific and technological achievement data sets, including scientific and technological achievement keywords, scientific and technological achievement paragraph layout data, and scientific and technological achievement semantic feature data;
[0015] Obtain historical scientific and technological achievements database information, and extract historical scientific and technological achievements database, including historical achievements keywords, historical achievements paragraph layout data and historical achievements semantic feature data.
[0016] Optionally, in the method for analyzing the association of scientific and technological achievements based on big data described in the present application, encrypting the scientific and technological achievement dataset and the historical scientific and technological achievement database according to a preset encryption rule to obtain an encrypted scientific and technological achievement dataset and an encrypted historical scientific and technological achievement database specifically includes:
[0017] Encrypting the scientific and technological achievement keywords, the scientific and technological achievement paragraph layout data and the scientific and technological achievement semantic feature data according to a preset encryption rule to obtain encrypted scientific and technological achievement keywords, encrypted scientific and technological achievement paragraph layout data and encrypted scientific and technological achievement semantic feature data;
[0018] The historical achievement keywords, historical achievement paragraph layout data and historical achievement semantic feature data are encrypted according to preset encryption rules to obtain encrypted historical achievement keywords, encrypted historical achievement paragraph layout data and encrypted historical achievement semantic feature data.
[0019] Optionally, in the scientific and technological achievement association analysis method based on big data described in the present application, the encrypted scientific and technological achievement data set and the encrypted historical scientific and technological achievement database are subjected to association matching to obtain association degree data of associated files, and the association degree data is processed by a preset association matching degree detection model to obtain an association matching index, specifically including:
[0020] The encrypted scientific and technological achievement keywords, encrypted scientific and technological achievement paragraph layout data, encrypted scientific and technological achievement semantic feature data and the encrypted historical achievement keywords, encrypted historical achievement paragraph layout data, encrypted historical achievement semantic feature data are matched with each other through a preset achievement correlation matching model to obtain correlation data of the associated files;
[0021] The association data includes keyword repetition data, paragraph layout similarity data and semantic similarity data;
[0022] Inputting the keyword repetition number data, paragraph layout similarity data and semantic similarity data into a preset association matching detection model for processing to obtain an association matching index;
[0023] The calculation formula of the association matching index in the association matching degree detection model is:
[0024]
[0025] Among them, G p is the correlation matching index, G c is the keyword repetition number data, D b is the paragraph layout similarity data, Y x is the semantic similarity data, and α, β, χ, and δ are the preset feature coefficients.
[0026] Optionally, in the method for analyzing the association of scientific and technological achievements based on big data described in the present application, the step of obtaining the association influence data of the associated files and calculating the authority validity index through a preset authority validity index detection model specifically includes:
[0027] Obtain the associated impact data of associated files, including the file publishing platform influence data, the author's industry impact factor and the file publishing time data;
[0028] Input the influence data of the document publishing platform, the author's industry impact factor and the document publishing time data into a preset authority validity index detection model to calculate and obtain an authority validity index;
[0029] The calculation formula of the authoritative validity index in the authoritative validity index detection model is:
[0030]
[0031] Among them, Q x is the authoritative validity index, P y The influence data of the file publishing platform is Z h is the author's industry impact factor, S c is the file release duration data, γ1, γ2, γ3, γ4, is the preset characteristic coefficient.
[0032] Optionally, in the scientific and technological achievement association analysis method based on big data described in the present application, the reference recommendation index is obtained by calculating the association matching index and the authority validity index, specifically including:
[0033] Inputting the association matching index and the authoritative validity index into a preset reference recommendation index evaluation model for processing to obtain a reference recommendation index;
[0034] The calculation formula of the reference recommendation index in the reference recommendation index evaluation model is:
[0035]
[0036] Among them, T j For reference recommendation index, G p is the correlation matching index, Q x is the authoritative validity index, and η1 and η2 are the preset characteristic coefficients.
[0037] Optionally, in the method for analyzing association of scientific and technological achievements based on big data described in the present application, comparing the reference recommendation index with a preset reference recommendation index threshold to obtain association status data specifically includes:
[0038] Compare the reference recommendation index with a preset reference recommendation index threshold to obtain correlation status data;
[0039] If the reference recommendation index is greater than a preset reference recommendation index threshold, the correlation status data is strongly correlated status data;
[0040] If the reference recommendation index is less than or equal to a preset reference recommendation index threshold, the correlation status data is weak correlation status data.
[0041] Optionally, in the method for analyzing the association of scientific and technological achievements based on big data described in the present application, the associated files are classified and sorted according to the association status data combined with the reference recommendation index, and sent to a preset client, specifically including:
[0042] Determining the association status data, and grouping according to the association status data;
[0043] If the correlation status data of the associated files is strongly correlated status data, sorting the associated files according to the reference recommendation index to obtain sequentially associated files;
[0044] The sequence association file is sent to a preset client.
[0045] In a second aspect, the present application provides a scientific and technological achievement association analysis system based on big data, the system comprising: a memory and a processor, the memory comprising a program of a scientific and technological achievement association analysis method based on big data, and the program of the scientific and technological achievement association analysis method based on big data is executed by the processor to implement the following steps:
[0046] Obtain information on scientific and technological achievements and historical scientific and technological achievements databases, and extract scientific and technological achievement data sets and historical scientific and technological achievements databases;
[0047] Encrypt the scientific and technological achievement data set and the historical scientific and technological achievement database according to preset encryption rules to obtain an encrypted scientific and technological achievement data set and an encrypted historical scientific and technological achievement database;
[0048] Perform correlation matching on the encrypted scientific and technological achievement data set and the encrypted historical scientific and technological achievement database to obtain correlation data of the associated files, and process the correlation data through a preset correlation matching detection model to obtain a correlation matching index;
[0049] Obtain the associated impact data of the associated files, and calculate the authoritative validity index through a preset authoritative validity index detection model;
[0050] Calculating a reference recommendation index based on the association matching index and the authoritative validity index;
[0051] Compare the reference recommendation index with a preset reference recommendation index threshold to obtain correlation status data;
[0052] The associated files are classified and sorted according to the association status data combined with the reference recommendation index, and sent to a preset client.
[0053] In the third aspect, the present application also provides a readable storage medium, which includes a scientific and technological achievement association analysis method program based on big data. When the scientific and technological achievement association analysis method program based on big data is executed by a processor, the steps of the scientific and technological achievement association analysis method based on big data as described in any one of the above items are implemented.
[0054] As can be seen from the above, the present application provides a method, system and medium for analyzing the association of scientific and technological achievements based on big data. The method obtains association data by matching the encrypted scientific and technological achievement data set with the encrypted historical scientific and technological achievement database, obtains the association matching index after processing the association data, and then obtains the authoritative validity index by calculating the association influence data of the associated files, obtains the reference recommendation index by calculating the association matching index and the authoritative validity index, obtains the association status data by comparing the reference recommendation index with the preset reference recommendation index threshold, classifies and sorts the associated files according to the association status data and the reference recommendation index, and sends the associated files that meet the conditions to the preset client; thereby, the association matching index, the authoritative validity index and the reference recommendation index are calculated, and the association status data is obtained after the threshold comparison, thereby realizing the association analysis technology for the associated files.
[0055] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures particularly pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0057] Figure 1 A flowchart of a method for analyzing the association of scientific and technological achievements based on big data provided in an embodiment of the present application;
[0058] Figure 2 A flowchart of obtaining a scientific and technological achievement data set and a historical scientific and technological achievement database for a scientific and technological achievement association analysis method based on big data provided in an embodiment of the present application;
[0059] Figure 3 A flowchart of obtaining an encrypted scientific and technological achievement data set and an encrypted historical scientific and technological achievement database according to a method for analyzing scientific and technological achievement associations based on big data provided in an embodiment of the present application;
[0060] Figure 4 A flow chart of obtaining a correlation matching index for a method for analyzing the correlation of scientific and technological achievements based on big data provided in an embodiment of the present application. DETAILED DESCRIPTION
[0061] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.
[0062] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0063] Please refer to Figure 1 , Figure 1 1 is a flow chart of a method for analyzing the association of scientific and technological achievements based on big data in some embodiments of the present application. The method for analyzing the association of scientific and technological achievements based on big data is used in a terminal device, such as a computer. The method for analyzing the association of scientific and technological achievements based on big data comprises the following steps:
[0064] S11. Obtain scientific and technological achievements information and historical scientific and technological achievements database information, and extract scientific and technological achievements data sets and historical scientific and technological achievements database;
[0065] S12, encrypting the scientific and technological achievement data set and the historical scientific and technological achievement database according to a preset encryption rule to obtain an encrypted scientific and technological achievement data set and an encrypted historical scientific and technological achievement database;
[0066] S13, performing correlation matching on the encrypted scientific and technological achievement data set and the encrypted historical scientific and technological achievement database to obtain correlation data of the associated files, and processing the correlation data through a preset correlation matching detection model to obtain a correlation matching index;
[0067] S14, obtaining the correlation influence data of the associated files, and calculating the authority validity index through a preset authority validity index detection model;
[0068] S15, calculating and obtaining a reference recommendation index according to the association matching index and the authority validity index;
[0069] S16, comparing the reference recommendation index with a preset reference recommendation index threshold to obtain association status data;
[0070] S17: The associated files are classified and sorted according to the association status data in combination with the reference recommendation index, and sent to a preset client.
[0071] Among them, when conducting correlation analysis of scientific and technological achievements, it is first necessary to obtain scientific and technological achievement data sets and historical scientific and technological achievement databases. Before scientific and technological achievements are announced, there are often data security issues. Therefore, in order to protect the privacy of scientific and technological achievements, it is necessary to encrypt the scientific and technological achievement data sets and historical scientific and technological achievement databases to obtain encrypted scientific and technological achievement data sets and encrypted historical scientific and technological achievement databases, and then perform correlation matching on the encrypted scientific and technological achievement data sets and the encrypted historical scientific and technological achievement database to obtain correlation data, and then calculate the correlation matching index based on the correlation data; the influence of different associated files is different, so while considering the correlation, it is also necessary to consider the influence and timeliness of the associated files, obtain the associated influence data of the associated files, calculate the authoritative validity index based on the associated influence data, and then process the association matching index and the authoritative validity index to obtain the reference recommendation index, and then obtain the correlation status data through threshold comparison, and then group and sort the associated files according to the correlation status data and the reference recommendation index, and finally send them to the preset client.
[0072] Please refer to Figure 2 , Figure 2 The flowchart of the method for analyzing the association of scientific and technological achievements based on big data provided in the embodiment of the present application is to obtain a scientific and technological achievement data set and a historical scientific and technological achievement database. According to the embodiment of the present invention, the acquisition of scientific and technological achievement information and historical scientific and technological achievement database information, and the extraction of scientific and technological achievement data sets and historical scientific and technological achievement databases specifically include:
[0073] S21. Acquire scientific and technological achievement information and extract scientific and technological achievement data sets, including scientific and technological achievement keywords, scientific and technological achievement paragraph layout data, and scientific and technological achievement semantic feature data;
[0074] S22. Obtain information of a historical scientific and technological achievement database, and extract the historical scientific and technological achievement database, including historical achievement keywords, historical achievement paragraph layout data, and historical achievement semantic feature data.
[0075] Among them, the scientific and technological achievement data set refers to the scientific and technological achievement keywords, scientific and technological achievement paragraph layout data and scientific and technological achievement semantic feature data obtained by extracting the content of scientific and technological achievements. The scientific and technological achievement paragraph layout data refers to the paragraph distribution feature data extracted according to the type of scientific and technological achievements. The scientific and technological achievement semantic feature data refers to the meaning characteristics that the sentences want to express obtained after analyzing the sentences of scientific and technological achievements; historical achievements refer to the abbreviations of historical scientific and technological achievements, that is, historical achievement keywords refer to the keywords in historical scientific and technological achievements.
[0076] Please refer to Figure 3 , Figure 3The flowchart of obtaining steel mesh matching status data of the scientific and technological achievements association analysis method based on big data provided by the embodiment of the present application is as follows. According to the embodiment of the present invention, the scientific and technological achievements dataset and the historical scientific and technological achievements database are encrypted according to the preset encryption rules to obtain the encrypted scientific and technological achievements dataset and the encrypted historical scientific and technological achievements database, specifically including:
[0077] S31, encrypting the scientific and technological achievement keywords, the scientific and technological achievement paragraph layout data and the scientific and technological achievement semantic feature data according to a preset encryption rule to obtain encrypted scientific and technological achievement keywords, encrypted scientific and technological achievement paragraph layout data and encrypted scientific and technological achievement semantic feature data;
[0078] S32. Encrypt the historical achievement keywords, historical achievement paragraph layout data and historical achievement semantic feature data according to preset encryption rules to obtain encrypted historical achievement keywords, encrypted historical achievement paragraph layout data and encrypted historical achievement semantic feature data.
[0079] Among them, in order to protect the data security and related privacy of scientific and technological achievements, the scientific and technological achievement data set needs to be encrypted when performing association analysis. In order to match the encrypted scientific and technological achievement data set with the historical scientific and technological achievement database, the historical scientific and technological achievement database needs to be encrypted in the same way. In this embodiment, the preset encryption rules for encrypting the scientific and technological achievement data set and the historical scientific and technological achievement database are the same, and the preset encryption rules are obtained and verified in advance through training.
[0080] Please refer to Figure 4 , Figure 4 The flowchart of obtaining scanning accuracy status data of the scientific and technological achievements association analysis method based on big data provided by the embodiment of the present application. According to the embodiment of the present invention, the encrypted scientific and technological achievements data set and the encrypted historical scientific and technological achievements database are matched for association to obtain the association degree data of the associated files, and the association degree data is processed by a preset association matching degree detection model to obtain the association matching index, which specifically includes:
[0081] S41, performing correlation matching on the encrypted scientific and technological achievement keywords, encrypted scientific and technological achievement paragraph layout data, encrypted scientific and technological achievement semantic feature data and the encrypted historical achievement keywords, encrypted historical achievement paragraph layout data, encrypted historical achievement semantic feature data through a preset achievement correlation matching model to obtain correlation data of the associated files;
[0082] S42, the association data includes keyword repetition data, paragraph layout similarity data and semantic similarity data;
[0083] S43, inputting the keyword repetition number data, paragraph layout similarity data and semantic similarity data into a preset association matching detection model for processing to obtain an association matching index;
[0084] The calculation formula of the association matching index in the association matching degree detection model is:
[0085]
[0086] Among them, G p is the correlation matching index, G c is the keyword repetition number data, D b is the paragraph layout similarity data, Y x is the semantic similarity data, and α, β, χ, and δ are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset scientific and technological achievement association analysis platform based on big data).
[0087] Among them, the preset achievement relevance matching model refers to a neural network model obtained after training with a large amount of historical data. Through this model, the matching correlation of the features between the scientific and technological achievements and the historical scientific and technological achievements, that is, the correlation data, can be analyzed. The correlation data includes keyword repetition data, paragraph layout similarity data and semantic similarity data. The keyword repetition data, paragraph layout similarity data and semantic similarity data are input into the preset relevance matching detection model for processing, and the correlation matching index can be obtained. The correlation matching index reflects to a certain extent the degree of correlation matching between the scientific and technological achievements and a historical scientific and technological achievement. The correlation matching detection model is a computational model obtained by training the model after obtaining a large amount of keyword repetition data, paragraph layout similarity data and semantic similarity data, and the correlation matching index can be calculated.
[0088] According to an embodiment of the present invention, the step of obtaining the associated impact data of the associated files and calculating the authority validity index by using a preset authority validity index detection model specifically includes:
[0089] Obtain the associated impact data of associated files, including the file publishing platform influence data, the author's industry impact factor and the file publishing time data;
[0090] Input the influence data of the document publishing platform, the author's industry impact factor and the document publishing time data into a preset authority validity index detection model to calculate and obtain an authority validity index;
[0091] The calculation formula of the authoritative validity index in the authoritative validity index detection model is:
[0092]
[0093] Among them, Q xis the authoritative validity index, P y The influence data of the file publishing platform is Z h is the author's industry impact factor, S c is the file release duration data, γ1, γ2, γ3, γ4, The preset characteristic coefficient
[0094] (The characteristic coefficients are obtained by querying the preset scientific and technological achievements correlation analysis platform based on big data).
[0095] Among them, when scientific and technological achievements are matched with historical scientific and technological achievements, the files that are used to compare with scientific and technological achievements and are related are called related files. The influence of related files varies because of the difference in files. Related influence data refers to the impact degree data of related files, including file publishing platform influence data, author industry impact factor and file publishing time data. File publishing platform influence data refers to the influence data of the platform that publishes the related files. The author industry impact factor refers to the influence ability data of the author of the related files in the industry. File publishing time data refers to the time from the release date of the file to the association analysis, in years. The longer the file is released, the weaker the advancement and influence of the scientific and technological achievements are, which is also an influencing factor of the influence of the related files. The file publishing platform influence data, the author industry impact factor and the file publishing time data are input into the preset authority validity index detection model to calculate the authority validity index. The authority validity index refers to the data reflecting the authority and timeliness of the related files. The authority validity index detection model is a calculation model obtained by obtaining a large amount of file publishing platform influence data, author industry impact factor and file publishing time data, and then training the model to obtain the authority validity index.
[0096] According to an embodiment of the present invention, the step of calculating the reference recommendation index based on the association matching index and the authority validity index specifically includes:
[0097] Inputting the association matching index and the authoritative validity index into a preset reference recommendation index evaluation model for processing to obtain a reference recommendation index;
[0098] The calculation formula of the reference recommendation index in the reference recommendation index evaluation model is:
[0099]
[0100] Among them, T j For reference recommendation index, G p is the correlation matching index, Q x is the authoritative validity index, and η1 and η2 are the preset characteristic coefficients.
[0101] Among them, the association matching index and the authority validity index both reflect the characteristics of the associated files to a certain extent. However, in order to more comprehensively reflect the reference recommendation degree of the associated files, it is necessary to calculate the reference recommendation index through the association matching index and the authority validity index. The reference recommendation index reflects the recommendation priority of the associated files to a certain extent. The preset reference recommendation index evaluation model is a calculation model obtained by obtaining a large number of association matching indices and authority validity indices and then training the model, which can calculate the reference recommendation index.
[0102] According to an embodiment of the present invention, comparing the reference recommendation index with a preset reference recommendation index threshold to obtain the association status data specifically includes:
[0103] Compare the reference recommendation index with a preset reference recommendation index threshold to obtain correlation status data;
[0104] If the reference recommendation index is greater than a preset reference recommendation index threshold, the correlation status data is strongly correlated status data;
[0105] If the reference recommendation index is less than or equal to a preset reference recommendation index threshold, the correlation status data is weak correlation status data.
[0106] Among them, the higher the reference recommendation index is, the stronger the association degree and recommendation strength are. In order to help users better screen useful related files, the association status data is determined according to the threshold comparison, including strong correlation status data and weak correlation status data. The association status data refers to two types of status data that reflect whether the association degree is valid. In this embodiment, the reference recommendation index threshold is set to: [0, 0.3], the association status data is weak correlation status data; (0.3, 1], the association status data is strong correlation status data; when the reference recommendation index is calculated to be 0.25, the association status data is weak correlation status data.
[0107] According to an embodiment of the present invention, the associated files are classified and sorted according to the association status data in combination with the reference recommendation index, and sent to a preset client, specifically including:
[0108] Determining the association status data, and grouping according to the association status data;
[0109] If the correlation status data of the associated files is strongly correlated status data, sorting the associated files according to the reference recommendation index to obtain sequentially associated files;
[0110] The sequence association file is sent to a preset client.
[0111] Among them, after obtaining the correlation status data of the associated files, they are first grouped according to the correlation status data. In the strongly correlated status data group, the associated files are sorted according to the reference recommendation index according to the user-set rules, including from large to small or from small to large. After obtaining the sequentially associated files, the associated files are sent to the customer's preset client.
[0112] The present invention also discloses a scientific and technological achievement association analysis system based on big data, comprising a memory and a processor, wherein the memory comprises a scientific and technological achievement association analysis method program based on big data, and when the scientific and technological achievement association analysis method program based on big data is executed by the processor, the following steps are implemented:
[0113] Obtain information on scientific and technological achievements and historical scientific and technological achievements databases, and extract scientific and technological achievement data sets and historical scientific and technological achievements databases;
[0114] Encrypt the scientific and technological achievement data set and the historical scientific and technological achievement database according to preset encryption rules to obtain an encrypted scientific and technological achievement data set and an encrypted historical scientific and technological achievement database;
[0115] Perform correlation matching on the encrypted scientific and technological achievement data set and the encrypted historical scientific and technological achievement database to obtain correlation data of the associated files, and process the correlation data through a preset correlation matching detection model to obtain a correlation matching index;
[0116] Obtain the associated impact data of the associated files, and calculate the authoritative validity index through a preset authoritative validity index detection model;
[0117] Calculating a reference recommendation index based on the association matching index and the authoritative validity index;
[0118] Compare the reference recommendation index with a preset reference recommendation index threshold to obtain correlation status data;
[0119] The associated files are classified and sorted according to the association status data combined with the reference recommendation index, and sent to a preset client.
[0120] Among them, when conducting correlation analysis of scientific and technological achievements, it is first necessary to obtain scientific and technological achievement data sets and historical scientific and technological achievement databases. Before scientific and technological achievements are announced, there are often data security issues. Therefore, in order to protect the privacy of scientific and technological achievements, it is necessary to encrypt the scientific and technological achievement data sets and historical scientific and technological achievement databases to obtain encrypted scientific and technological achievement data sets and encrypted historical scientific and technological achievement databases, and then perform correlation matching on the encrypted scientific and technological achievement data sets and the encrypted historical scientific and technological achievement database to obtain correlation data, and then calculate the correlation matching index based on the correlation data; the influence of different associated files is different, so while considering the correlation, it is also necessary to consider the influence and timeliness of the associated files, obtain the associated influence data of the associated files, calculate the authoritative validity index based on the associated influence data, and then process the association matching index and the authoritative validity index to obtain the reference recommendation index, and then obtain the correlation status data through threshold comparison, and then group and sort the associated files according to the correlation status data and the reference recommendation index, and finally send them to the preset client.
[0121] According to an embodiment of the present invention, the obtaining of scientific and technological achievement information and historical scientific and technological achievement database information, and extracting scientific and technological achievement data sets and historical scientific and technological achievement databases, specifically includes:
[0122] Obtain scientific and technological achievement information and extract scientific and technological achievement data sets, including scientific and technological achievement keywords, scientific and technological achievement paragraph layout data, and scientific and technological achievement semantic feature data;
[0123] Obtain historical scientific and technological achievements database information, and extract historical scientific and technological achievements database, including historical achievements keywords, historical achievements paragraph layout data and historical achievements semantic feature data.
[0124] Among them, the scientific and technological achievement data set refers to the scientific and technological achievement keywords, scientific and technological achievement paragraph layout data and scientific and technological achievement semantic feature data obtained by extracting the content of scientific and technological achievements. The scientific and technological achievement paragraph layout data refers to the paragraph distribution feature data extracted according to the type of scientific and technological achievements. The scientific and technological achievement semantic feature data refers to the meaning characteristics that the sentences want to express obtained after analyzing the sentences of scientific and technological achievements; historical achievements refer to the abbreviations of historical scientific and technological achievements, that is, historical achievement keywords refer to the keywords in historical scientific and technological achievements.
[0125] According to an embodiment of the present invention, encrypting the scientific and technological achievement data set and the historical scientific and technological achievement database according to a preset encryption rule to obtain an encrypted scientific and technological achievement data set and an encrypted historical scientific and technological achievement database specifically includes:
[0126] Encrypting the scientific and technological achievement keywords, the scientific and technological achievement paragraph layout data and the scientific and technological achievement semantic feature data according to a preset encryption rule to obtain encrypted scientific and technological achievement keywords, encrypted scientific and technological achievement paragraph layout data and encrypted scientific and technological achievement semantic feature data;
[0127] The historical achievement keywords, historical achievement paragraph layout data and historical achievement semantic feature data are encrypted according to preset encryption rules to obtain encrypted historical achievement keywords, encrypted historical achievement paragraph layout data and encrypted historical achievement semantic feature data.
[0128] Among them, in order to protect the data security and related privacy of scientific and technological achievements, the scientific and technological achievement data set needs to be encrypted when performing association analysis. In order to match the encrypted scientific and technological achievement data set with the historical scientific and technological achievement database, the historical scientific and technological achievement database needs to be encrypted in the same way. In this embodiment, the preset encryption rules for encrypting the scientific and technological achievement data set and the historical scientific and technological achievement database are the same, and the preset encryption rules are obtained and verified in advance through training.
[0129] According to an embodiment of the present invention, the encrypted scientific and technological achievement data set and the encrypted historical scientific and technological achievement database are subjected to correlation matching to obtain correlation data of the associated files, and the correlation data is processed by a preset correlation matching detection model to obtain a correlation matching index, specifically including:
[0130] The encrypted scientific and technological achievement keywords, encrypted scientific and technological achievement paragraph layout data, encrypted scientific and technological achievement semantic feature data and the encrypted historical achievement keywords, encrypted historical achievement paragraph layout data, encrypted historical achievement semantic feature data are matched with each other through a preset achievement correlation matching model to obtain correlation data of the associated files;
[0131] The association data includes keyword repetition data, paragraph layout similarity data and semantic similarity data;
[0132] Inputting the keyword repetition number data, paragraph layout similarity data and semantic similarity data into a preset association matching detection model for processing to obtain an association matching index;
[0133] The calculation formula of the association matching index in the association matching degree detection model is:
[0134]
[0135] Among them, G p is the correlation matching index, G c is the keyword repetition number data, D b is the paragraph layout similarity data, Y x is the semantic similarity data, and α, β, χ, and δ are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset scientific and technological achievement association analysis platform based on big data).
[0136] Among them, the preset achievement relevance matching model refers to a neural network model obtained after training with a large amount of historical data. Through this model, the matching correlation of the features between the scientific and technological achievements and the historical scientific and technological achievements, that is, the correlation data, can be analyzed. The correlation data includes keyword repetition data, paragraph layout similarity data and semantic similarity data. The keyword repetition data, paragraph layout similarity data and semantic similarity data are input into the preset relevance matching detection model for processing, and the correlation matching index can be obtained. The correlation matching index reflects to a certain extent the degree of correlation matching between the scientific and technological achievements and a historical scientific and technological achievement. The correlation matching detection model is a computational model obtained by training the model after obtaining a large amount of keyword repetition data, paragraph layout similarity data and semantic similarity data, and the correlation matching index can be calculated.
[0137] According to an embodiment of the present invention, the step of obtaining the associated impact data of the associated files and calculating the authority validity index by using a preset authority validity index detection model specifically includes:
[0138] Obtain the associated impact data of associated files, including the file publishing platform influence data, the author's industry impact factor and the file publishing time data;
[0139] Input the influence data of the document publishing platform, the author's industry impact factor and the document publishing time data into a preset authority validity index detection model to calculate and obtain an authority validity index;
[0140] The calculation formula of the authoritative validity index in the authoritative validity index detection model is:
[0141]
[0142] Among them, Q x is the authoritative validity index, P y The influence data of the file publishing platform is Z h is the author's industry impact factor, S c is the file release duration data, γ1, γ2, γ3, γ4, The preset characteristic coefficient
[0143] (The characteristic coefficients are obtained by querying the preset scientific and technological achievements correlation analysis platform based on big data).
[0144] Among them, when scientific and technological achievements are matched with historical scientific and technological achievements, the files that are used to compare with scientific and technological achievements and are related are called related files. The influence of related files varies because of the difference in files. Related influence data refers to the impact degree data of related files, including file publishing platform influence data, author industry impact factor and file publishing time data. File publishing platform influence data refers to the influence data of the platform that publishes the related files. The author industry impact factor refers to the influence ability data of the author of the related files in the industry. File publishing time data refers to the time from the release date of the file to the association analysis, in years. The longer the file is released, the weaker the advancement and influence of the scientific and technological achievements are, which is also an influencing factor of the influence of the related files. The file publishing platform influence data, the author industry impact factor and the file publishing time data are input into the preset authority validity index detection model to calculate the authority validity index. The authority validity index refers to the data reflecting the authority and timeliness of the related files. The authority validity index detection model is a calculation model obtained by obtaining a large amount of file publishing platform influence data, author industry impact factor and file publishing time data, and then training the model to obtain the authority validity index.
[0145] According to an embodiment of the present invention, the step of calculating the reference recommendation index based on the association matching index and the authority validity index specifically includes:
[0146] Inputting the association matching index and the authoritative validity index into a preset reference recommendation index evaluation model for processing to obtain a reference recommendation index;
[0147] The calculation formula of the reference recommendation index in the reference recommendation index evaluation model is:
[0148]
[0149] Among them, T j For reference recommendation index, G p is the correlation matching index, Q x is the authoritative validity index, and η1 and η2 are the preset characteristic coefficients.
[0150] Among them, the association matching index and the authority validity index both reflect the characteristics of the associated files to a certain extent. However, in order to more comprehensively reflect the reference recommendation degree of the associated files, it is necessary to calculate the reference recommendation index through the association matching index and the authority validity index. The reference recommendation index reflects the recommendation priority of the associated files to a certain extent. The preset reference recommendation index evaluation model is a calculation model obtained by obtaining a large number of association matching indices and authority validity indices and then training the model, which can calculate the reference recommendation index.
[0151] According to an embodiment of the present invention, comparing the reference recommendation index with a preset reference recommendation index threshold to obtain the association status data specifically includes:
[0152] Compare the reference recommendation index with a preset reference recommendation index threshold to obtain correlation status data;
[0153] If the reference recommendation index is greater than a preset reference recommendation index threshold, the correlation status data is strongly correlated status data;
[0154] If the reference recommendation index is less than or equal to a preset reference recommendation index threshold, the correlation status data is weak correlation status data.
[0155] Among them, the higher the reference recommendation index is, the stronger the association degree and recommendation strength are. In order to help users better screen useful related files, the association status data is determined according to the threshold comparison, including strong correlation status data and weak correlation status data. The association status data refers to two types of status data that reflect whether the association degree is valid. In this embodiment, the reference recommendation index threshold is set to: [0, 0.3], the association status data is weak correlation status data; (0.3, 1], the association status data is strong correlation status data; when the reference recommendation index is calculated to be 0.25, the association status data is weak correlation status data.
[0156] According to an embodiment of the present invention, the associated files are classified and sorted according to the association status data in combination with the reference recommendation index, and sent to a preset client, specifically including:
[0157] Determining the association status data, and grouping according to the association status data;
[0158] If the correlation status data of the associated files is strongly correlated status data, sorting the associated files according to the reference recommendation index to obtain sequentially associated files;
[0159] The sequence association file is sent to a preset client.
[0160] Among them, after obtaining the correlation status data of the associated files, they are first grouped according to the correlation status data. In the strongly correlated status data group, the associated files are sorted according to the reference recommendation index according to the user-set rules, including from large to small or from small to large. After obtaining the sequentially associated files, the associated files are sent to the customer's preset client.
[0161] The third aspect of the present invention provides a readable storage medium, which includes a scientific and technological achievement association analysis method program based on big data. When the scientific and technological achievement association analysis method program based on big data is executed by a processor, the steps of the scientific and technological achievement association analysis method based on big data as described in any one of the above items are implemented.
[0162] The invention discloses a method, system and medium for analyzing the association of scientific and technological achievements based on big data. The method obtains association data by matching an encrypted scientific and technological achievement data set with an encrypted historical scientific and technological achievement database, obtains an association matching index after processing the association data, calculates an authoritative validity index through the association influence data of the associated files, obtains a reference recommendation index by calculating the association matching index and the authoritative validity index, obtains association status data by comparing the reference recommendation index with a preset reference recommendation index threshold, classifies and sorts the associated files according to the association status data and the reference recommendation index, and sends the associated files that meet the conditions to a preset client. Thus, the association matching index, the authoritative validity index and the reference recommendation index are calculated, and the association status data is obtained after comparing the thresholds, thereby realizing the association analysis technology for the associated files.
[0163] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
[0164] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0165] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0166] Those skilled in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.
[0167] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.
Claims
1. A method for correlation analysis of scientific and technological achievements based on big data, characterized in that: include: Obtain information on scientific and technological achievements and historical scientific and technological achievements databases, and extract scientific and technological achievement data sets and historical scientific and technological achievements databases; Encrypt the scientific and technological achievement data set and the historical scientific and technological achievement database according to preset encryption rules to obtain an encrypted scientific and technological achievement data set and an encrypted historical scientific and technological achievement database; Perform correlation matching on the encrypted scientific and technological achievement data set and the encrypted historical scientific and technological achievement database to obtain correlation data of the associated files, and process the correlation data through a preset correlation matching detection model to obtain a correlation matching index; Obtain the associated impact data of the associated files, and calculate the authoritative validity index through a preset authoritative validity index detection model; Calculating a reference recommendation index based on the association matching index and the authoritative validity index; Compare the reference recommendation index with a preset reference recommendation index threshold to obtain correlation status data; The associated files are classified and sorted according to the association status data combined with the reference recommendation index, and sent to a preset client.
2. The method for analyzing the association of scientific and technological achievements based on big data according to claim 1 is characterized in that: The obtaining of scientific and technological achievement information and historical scientific and technological achievement database information, and extracting scientific and technological achievement data sets and historical scientific and technological achievement databases, specifically includes: Obtain scientific and technological achievement information and extract scientific and technological achievement data sets, including scientific and technological achievement keywords, scientific and technological achievement paragraph layout data, and scientific and technological achievement semantic feature data; Obtain historical scientific and technological achievements database information, and extract historical scientific and technological achievements database, including historical achievements keywords, historical achievements paragraph layout data and historical achievements semantic feature data.
3. According to the method for analyzing the association of scientific and technological achievements based on big data according to claim 2, it is characterized in that: The step of encrypting the scientific and technological achievement data set and the historical scientific and technological achievement database according to the preset encryption rules to obtain the encrypted scientific and technological achievement data set and the encrypted historical scientific and technological achievement database specifically includes: Encrypting the scientific and technological achievement keywords, the scientific and technological achievement paragraph layout data and the scientific and technological achievement semantic feature data according to a preset encryption rule to obtain encrypted scientific and technological achievement keywords, encrypted scientific and technological achievement paragraph layout data and encrypted scientific and technological achievement semantic feature data; The historical achievement keywords, historical achievement paragraph layout data and historical achievement semantic feature data are encrypted according to preset encryption rules to obtain encrypted historical achievement keywords, encrypted historical achievement paragraph layout data and encrypted historical achievement semantic feature data.
4. According to the method for correlation analysis of scientific and technological achievements based on big data according to claim 3, it is characterized in that: The encrypted scientific and technological achievement data set and the encrypted historical scientific and technological achievement database are subjected to correlation matching to obtain correlation data of the associated files, and the correlation data is processed by a preset correlation matching detection model to obtain a correlation matching index, specifically including: The encrypted scientific and technological achievement keywords, encrypted scientific and technological achievement paragraph layout data, encrypted scientific and technological achievement semantic feature data and the encrypted historical achievement keywords, encrypted historical achievement paragraph layout data, encrypted historical achievement semantic feature data are matched with each other through a preset achievement correlation matching model to obtain correlation data of the associated files; The association data includes keyword repetition data, paragraph layout similarity data and semantic similarity data; Inputting the keyword repetition number data, paragraph layout similarity data and semantic similarity data into a preset association matching detection model for processing to obtain an association matching index; The calculation formula of the association matching index in the association matching degree detection model is: Among them, G p is the correlation matching index, G c is the keyword repetition number data, D b is the paragraph layout similarity data, Y x is the semantic similarity data, and α, β, χ, and δ are the preset feature coefficients.
5. The method for analyzing the association of scientific and technological achievements based on big data according to claim 4 is characterized in that: The step of obtaining the associated impact data of the associated files and calculating the authority validity index using a preset authority validity index detection model specifically includes: Obtain the associated impact data of associated files, including the file publishing platform influence data, the author's industry impact factor and the file publishing time data; Input the influence data of the document publishing platform, the author's industry impact factor and the document publishing time data into a preset authority validity index detection model to calculate and obtain an authority validity index; The calculation formula of the authoritative validity index in the authoritative validity index detection model is: Among them, Q x is the authoritative validity index, P y The influence data of the file publishing platform is Z h is the author's industry impact factor, S c is the file release duration data, γ1, γ2, γ3, γ4, is the preset characteristic coefficient.
6. The method for analyzing the association of scientific and technological achievements based on big data according to claim 5 is characterized in that: The step of calculating the reference recommendation index according to the association matching index and the authority validity index specifically includes: Inputting the association matching index and the authoritative validity index into a preset reference recommendation index evaluation model for processing to obtain a reference recommendation index; The calculation formula of the reference recommendation index in the reference recommendation index evaluation model is: Among them, T j G is the reference recommendation index. p is the correlation matching index, Q x is the authoritative validity index, and η1 and η2 are the preset characteristic coefficients.
7. The method for analyzing the association of scientific and technological achievements based on big data according to claim 6 is characterized in that: The comparing the reference recommendation index with a preset reference recommendation index threshold to obtain the association status data specifically includes: Compare the reference recommendation index with a preset reference recommendation index threshold to obtain correlation status data; If the reference recommendation index is greater than a preset reference recommendation index threshold, the correlation status data is strongly correlated status data; If the reference recommendation index is less than or equal to a preset reference recommendation index threshold, the correlation status data is weak correlation status data.
8. The method for analyzing the association of scientific and technological achievements based on big data according to claim 7 is characterized in that: The associated files are classified and sorted according to the association status data combined with the reference recommendation index, and sent to a preset client, specifically including: Determining the association status data, and grouping according to the association status data; If the correlation status data of the associated files is strongly correlated status data, sorting the associated files according to the reference recommendation index to obtain sequentially associated files; The sequence association file is sent to a preset client.
9. A scientific and technological achievement correlation analysis system based on big data, characterized in that: The invention comprises a memory and a processor, wherein the memory comprises a method program for analyzing the association of scientific and technological achievements based on big data, and when the method program for analyzing the association of scientific and technological achievements based on big data is executed by the processor, the following steps are implemented: Obtain information on scientific and technological achievements and historical scientific and technological achievements databases, and extract scientific and technological achievement data sets and historical scientific and technological achievements databases; Encrypt the scientific and technological achievement data set and the historical scientific and technological achievement database according to preset encryption rules to obtain an encrypted scientific and technological achievement data set and an encrypted historical scientific and technological achievement database; Perform correlation matching on the encrypted scientific and technological achievement data set and the encrypted historical scientific and technological achievement database to obtain correlation data of the associated files, and process the correlation data through a preset correlation matching detection model to obtain a correlation matching index; Obtain the associated impact data of the associated files, and calculate the authoritative validity index through a preset authoritative validity index detection model; Calculating a reference recommendation index based on the association matching index and the authoritative validity index; Compare the reference recommendation index with a preset reference recommendation index threshold to obtain correlation status data; The associated files are classified and sorted according to the association status data combined with the reference recommendation index, and sent to a preset client.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a method program for analyzing the association of scientific and technological achievements based on big data. When the method program for analyzing the association of scientific and technological achievements based on big data is executed by a processor, the steps of the method for analyzing the association of scientific and technological achievements based on big data as described in any one of claims 1 to 8 are implemented.
