Scientific and technological policy retrieval method

By formulating search policies, processing and text mining technologies, the problem of information not being processed centrally in the existing science and technology policy search methods has been solved, the quality and efficiency of search results have been improved, manual review has been reduced, and application effect has been improved.

CN119066152AInactive Publication Date: 2024-12-03BEIJING HUAXIA TYCO CONSULTING GROUP CO LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202411107367.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-13
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing science and technology policy search methods fail to effectively centralize the processing of the retrieved information, resulting in users requiring manual verification and information extraction, which increases the subsequent workload and reduces the application effect of the method.

Method used

Adopt a science and technology policy search method that includes clarifying search requirements, selecting databases, formulating search policies, performing search operations, collecting and processing data, conducting text mining and key marking, and improve data quality and retrieval efficiency through natural language processing and deep learning models. .

Benefits of technology

By limiting search conditions in multiple dimensions, cleaning and classified data, text mining and labeling, the quality and efficiency of search results are significantly improved, the demand for manual review and extraction is reduced, and the overall application efficiency and effect are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066152A_ABST
    Figure CN119066152A_ABST
Patent Text Reader

Abstract

The invention discloses a scientific and technological policy retrieval method, which belongs to the technical field of policy retrieval, and comprises the following steps: firstly, determining a retrieval requirement, and selecting a database needing to be retrieved; according to the method, the specific policy process for formulating the retrieval is set in the method, the retrieval conditions can be effectively subjected to multi-dimensional limitation through the process, and due to the fact that the limited content comprises multiple different directions, the retrieved data can better conform to the expectation of a retriever, and the retrieval efficiency is improved. Meanwhile, a data processing process is set in the method, the data can be effectively cleaned, some irrelevant and wrong data can be cleaned, so that the overall quality of the data is improved, key information of a text can be mined and marked, and when a retrieval result is exported, the retrieval efficiency is improved. Meanwhile, some key information can be exported, manual follow-up review and extraction are not needed, and the application efficiency and effect of the whole method are greatly improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of policy retrieval, and in particular relates to a technology policy retrieval method. Background Art

[0002] As the name suggests, science and technology policy is a policy about science and technology. It is a strategic and tactical principle that determines the direction of science and technology development and guides the entire science and technology industry. These policies are aimed at promoting scientific and technological innovation, developing science and technology industries, and improving the country's scientific and technological competitiveness. Science and technology policies usually include R&D investment, scientific and technological talent training, scientific and technological innovation system construction, scientific and technological achievement transformation, scientific and technological cooperation and exchange, etc. In order to search for science and technology policies, it is necessary to apply science and technology policy search methods.

[0003] A Chinese patent (CN114691738A) discloses a method for searching technology policies, including: obtaining a technology policy search request from a user; reading the technology policy search conditions of the user from the technology policy search request; judging whether the search conditions are the technology policy search conditions used by the system for regular background searches; if so, providing the search results of the regular background searches of the system to the user; otherwise, performing a search based on the technology policy search conditions of the user, and providing the search results to the user. The technical solution of this method sets relevant technology policy search conditions for the system in advance, and performs regular background searches, so that when receiving the user's search request, the system can provide the user with the search results of regular background searches based on the pre-set relevant search conditions, which greatly reduces the user's waiting time and ensures the validity of the user's search results. Although current science and technology policy retrieval methods can also realize the retrieval of science and technology policies, the retrieved information is generally exported directly, and the data is not centrally processed, resulting in the need for further manual verification and information extraction of the retrieved data, which greatly increases the subsequent workload. The actual application effect of the method is not good. In order to solve this problem, a science and technology policy retrieval method is urgently needed. Summary of the invention

[0004] The purpose of the present invention is to propose a science and technology policy retrieval method to solve the problem that although the current science and technology policy retrieval method can also realize the retrieval of science and technology policies, the retrieved information is generally directly exported, and the information data is not centrally processed, resulting in the need for further manual verification and information extraction of the retrieved information, which greatly increases the subsequent workload and the actual application effect of the method is not good.

[0005] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a method for searching science and technology policies, comprising the following steps:

[0006] S1. First clarify the search requirements;

[0007] S2. Select the database to be searched;

[0008] S3. Formulate specific search guidelines;

[0009] S4, performing a search operation;

[0010] S5. Collect and centralize the retrieved data;

[0011] S6. Process the collected data;

[0012] S7. Perform text mining on data;

[0013] S8. Mark the mined information;

[0014] S9. Export the retrieved original data and mined information.

[0015] Furthermore, the method is provided with a process for formulating specific search policies, through which the search conditions can be effectively limited in multiple dimensions. Since the limited content includes many different directions, the retrieved information can be more in line with the searcher's expectations. At the same time, a process for processing information data is provided in the method, which can effectively clean the data and clear out some irrelevant and erroneous data, thereby improving the overall quality of the data. At the same time, key information of the text can be mined and marked, so that when the search results are exported, some key information can be exported at the same time, without the need for subsequent manual review and extraction, which greatly improves the application efficiency and effect of the overall method.

[0016] As a further description of the above technical solution:

[0017] In S1, the search requirements are first clarified. The search requirements include the subject of the science and technology policy to be searched, the scope of the science and technology policy to be searched, the time range of the science and technology policy to be searched, and the implementation record of the science and technology policy to be searched.

[0018] As a further description of the above technical solution:

[0019] In S2, the database to be searched is selected, and the database is one or more of the major official policy databases, academic research institution databases, professional journal databases and CNKI databases. Selecting a suitable database can improve the accuracy and comprehensiveness of the search results.

[0020] As a further description of the above technical solution:

[0021] In S3, a specific search policy is formulated, which includes: first determining the search keywords, then using Boolean operators to combine the keywords, then setting reasonable search restrictions, and finally setting the search time range. A well-formulated search strategy can significantly improve the search efficiency and accuracy.

[0022] As a further description of the above technical solution:

[0023] In S4, a search operation is performed. During the search operation, the time is calculated and the search time is controlled to be 2-3 seconds. If it exceeds this range, the system and the network are checked.

[0024] As a further description of the above technical solution:

[0025] In S6, the collected data is processed, and the specific steps are: first, the data is centrally screened, then the data is centrally cleaned, then the data is classified and grouped, and the grouped data are numbered, using either digital or alphabetical numbers, and the order of the numbers is set according to the size of the data.

[0026] As a further description of the above technical solution:

[0027] The centralized data cleaning is mainly carried out through natural language processing and data preprocessing technology to remove irrelevant information and improve data quality.

[0028] As a further description of the above technical solution:

[0029] In S7, a deep learning model is used to extract text features and perform semantic analysis, and to perform text mining on the data.

[0030] As a further description of the above technical solution:

[0031] In S8, the mined information is marked with key points, and the marked key information is backed up and stored.

[0032] As a further description of the above technical solution:

[0033] In S9, the retrieved original data and mined information are exported, and the entire retrieval process is evaluated through artificial intelligence. The evaluation results are divided into three levels, namely excellent, good and poor.

[0034] The present invention also discloses a science and technology policy retrieval system, including a retrieval demand establishment module, the output end of the retrieval demand establishment module is connected to the retrieval database selection module, the output end of the retrieval demand establishment module is connected to the input end of the retrieval database selection module, the output end of the retrieval database selection module is connected to the input end of the retrieval policy formulation module, the output end of the retrieval policy formulation module is connected to the input end of the retrieval operation execution module, the output end of the retrieval operation execution module is connected to the input end of the retrieval data and information concentration module, the output end of the retrieval data and information concentration module is connected to the input end of the data collection processing module, and the data collection processing module The output end of the data and information text mining module is connected to the input end of the mining information key marking module, the output end of the mining information key marking module is connected to the input end of the original data retrieval and mining information export module, wherein the data collection and processing module also includes a data and information centralized screening module, the output end of the data and information centralized screening module is connected to the input end of the data collection cleaning module, the output end of the data collection cleaning module is connected to the input end of the data and information classification and grouping module, and the output end of the data and information classification and grouping module is connected to the input end of the grouped data and information numbering module.

[0035] In the present invention, the method is provided with a specific policy process for formulating the search, through which the search conditions can be effectively limited in multiple dimensions. Since the limited content includes many different directions, the searched information can be more in line with the expectations of the searcher. At the same time, a processing process for the information data is provided in the method, which can effectively clean the data and clear some irrelevant and erroneous data, thereby improving the overall quality of the data. At the same time, the key information of the text can be mined and marked, so that when the search results are exported, some key information can be exported at the same time, without the need for subsequent manual review and extraction, which greatly improves the application efficiency and effect of the overall method. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flow chart of a technology policy retrieval method. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] Example 1

[0039] See also Figure 1 The present invention provides a technical solution: a method for searching science and technology policies, comprising the following steps:

[0040] S1. First, clarify the search requirements, which include the subject of the science and technology policy to be searched, the scope of the science and technology policy to be searched, the time range of the science and technology policy to be searched, and the implementation record of the science and technology policy to be searched;

[0041] S2. Select the databases to be searched, which are the official policy databases and academic research institution databases. Selecting the appropriate database can improve the accuracy and comprehensiveness of the search results.

[0042] S3. Formulate a specific search strategy, which includes: first determine the search keywords, then use Boolean operators to combine the keywords, then set reasonable search restrictions, and finally set the search time range. A good search strategy can significantly improve search efficiency and accuracy;

[0043] S4. Execute the search operation. During the search operation, calculate the time and control the search time to 2-3 seconds. If it exceeds this range, check the system and network.

[0044] S5. Collect and centralize the retrieved data;

[0045] S6. Processing the collected data, the specific steps are: firstly, centrally screening the data, then centrally cleaning the data, then classifying and grouping the data, numbering the grouped data, using digital numbers, and the order of numbers is set according to the size of the data. The data is centrally cleaned, mainly through natural language processing and data preprocessing technology, to remove irrelevant information and improve data quality;

[0046] S7. Use deep learning models to extract text features and perform semantic analysis, and conduct text mining on data;

[0047] S8, marking key points of the mined information, and backing up and storing the key marked information;

[0048] S9. The retrieved original data and mined information are exported, and the entire retrieval process is evaluated through artificial intelligence. The evaluation results are divided into three levels: excellent, good and poor.

[0049] In this embodiment, the method is provided with a specific search policy process, through which the search conditions can be effectively limited in multiple dimensions. Since the limited content includes many different directions, the searched information can better meet the expectations of the searcher.

[0050] Example 2

[0051] See also Figure 1 The present invention provides a technical solution: a method for searching science and technology policies, comprising the following steps:

[0052] S1. First, clarify the search requirements, which include the subject of the science and technology policy to be searched, the scope of the science and technology policy to be searched, the time range of the science and technology policy to be searched, and the implementation record of the science and technology policy to be searched;

[0053] S2. Select the database to be searched, which includes professional journal database and CNKI database. Selecting an appropriate database can improve the accuracy and comprehensiveness of the search results.

[0054] S3. Formulate a specific search strategy, which includes: first determine the search keywords, then use Boolean operators to combine the keywords, then set reasonable search restrictions, and finally set the search time range. A good search strategy can significantly improve search efficiency and accuracy;

[0055] S4. Execute the search operation. During the search operation, calculate the time and control the search time to 2-3 seconds. If it exceeds this range, check the system and network.

[0056] S5. Collect and centralize the retrieved data;

[0057] S6. Processing the collected data, the specific steps are: firstly, centrally screening the data, then centrally cleaning the data, then classifying and grouping the data, numbering the grouped data, using alphabetical numbers, and the order of numbers is set according to the size of the data. The data is centrally cleaned, mainly through natural language processing and data preprocessing technology, to remove irrelevant information and improve data quality;

[0058] S7. Use deep learning models to extract text features and perform semantic analysis, and conduct text mining on data;

[0059] S8, marking key points of the mined information, and backing up and storing the key marked information;

[0060] S9. The retrieved original data and mined information are exported, and the entire retrieval process is evaluated through artificial intelligence. The evaluation results are divided into three levels: excellent, good and poor.

[0061] In this embodiment, a processing process for information data is provided within the method, which can effectively clean the data and clear out some irrelevant and erroneous data, thereby improving the overall quality of the data. At the same time, it can also mine and mark the key information of the text, so that when the search results are exported, some key information can be exported at the same time, without the need for subsequent manual review and extraction, which greatly improves the application efficiency and effect of the overall method.

[0062] Example 3

[0063] See also Figure 1 The present invention provides a technical solution: a method for searching science and technology policies, comprising the following steps:

[0064] S1. First, clarify the search requirements, which include the subject of the science and technology policy to be searched, the scope of the science and technology policy to be searched, the time range of the science and technology policy to be searched, and the implementation record of the science and technology policy to be searched;

[0065] S2. Select the databases to be searched, which include major official policy databases, academic research institution databases, professional journal databases and CNKI databases. Selecting the appropriate database can improve the accuracy and comprehensiveness of the search results.

[0066] S3. Formulate a specific search strategy, which includes: first determine the search keywords, then use Boolean operators to combine the keywords, then set reasonable search restrictions, and finally set the search time range. A good search strategy can significantly improve search efficiency and accuracy;

[0067] S4. Execute the search operation. During the search operation, calculate the time and control the search time to 2-3 seconds. If it exceeds this range, check the system and network.

[0068] S5. Collect and centralize the retrieved data;

[0069] S6. Processing the collected data, the specific steps are: firstly, centrally screening the data, then centrally cleaning the data, then classifying and grouping the data, numbering the grouped data, using digital numbers, and the order of numbers is set according to the size of the data. The data is centrally cleaned, mainly through natural language processing and data preprocessing technology, to remove irrelevant information and improve data quality;

[0070] S7. Use deep learning models to extract text features and perform semantic analysis, and conduct text mining on data;

[0071] S8, marking key points of the mined information, and backing up and storing the key marked information;

[0072] S9. The retrieved original data and mined information are exported, and the entire retrieval process is evaluated through artificial intelligence. The evaluation results are divided into three levels: excellent, good and poor.

[0073] In this embodiment, the method is provided with a specific policy process for formulating the search, through which the search conditions can be effectively limited in multiple dimensions. Since the limited content includes many different directions, the searched information can be more in line with the expectations of the searcher. At the same time, a data processing process is provided in the method, which can effectively clean the data and clear some irrelevant and erroneous data, thereby improving the overall quality of the data. At the same time, the key information of the text can be mined and marked, so that when the search results are exported, some key information can be exported at the same time, without the need for subsequent manual review and extraction, which greatly improves the application efficiency and effect of the overall method.

[0074] Example 4

[0075] The present invention also discloses a science and technology policy retrieval system, including a retrieval demand establishment module, the output end of the retrieval demand establishment module is connected to the retrieval database selection module, the output end of the retrieval demand establishment module is connected to the input end of the retrieval database selection module, the output end of the retrieval database selection module is connected to the input end of the retrieval policy formulation module, the output end of the retrieval policy formulation module is connected to the input end of the retrieval operation execution module, the output end of the retrieval operation execution module is connected to the input end of the retrieval data and information concentration module, the output end of the retrieval data and information concentration module is connected to the input end of the data collection processing module, and the data collection processing module The output end of the data and information text mining module is connected to the input end of the mining information key marking module, the output end of the mining information key marking module is connected to the input end of the original data retrieval and mining information export module, wherein the data collection and processing module also includes a data and information centralized screening module, the output end of the data and information centralized screening module is connected to the input end of the data collection cleaning module, the output end of the data collection cleaning module is connected to the input end of the data and information classification and grouping module, and the output end of the data and information classification and grouping module is connected to the input end of the grouped data and information numbering module.

[0076] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A technology policy retrieval method, characterized by: The steps include: S1. First clarify the search requirements; S2. Select the database to be searched; S3. Develop specific search guidelines; S4, performing a search operation; S5. Collect and centralize the retrieved data; S6. Process the collected data; S7. Perform text mining on data; S8. Mark the mined information; S9. Export the retrieved original data and mined information.

2. A technology policy retrieval method according to claim 1, characterized in that: In S1, the search requirements are first clarified. The search requirements include the subject of the science and technology policy to be searched, the scope of the science and technology policy to be searched, the time range of the science and technology policy to be searched, and the implementation record of the science and technology policy to be searched.

3. A technology policy retrieval method according to claim 1, characterized in that: In S2, the database to be searched is selected, and the database is one or more of the major official policy databases, academic research institution databases, professional journal databases and HowNet databases. Selecting an appropriate database can improve the accuracy and comprehensiveness of the search results.

4. A method for searching science and technology policies according to claim 1, characterized in that: In S3, a specific search policy is formulated, which includes: first determining the search keywords, then using Boolean operators to combine the keywords, then setting reasonable search restrictions, and finally setting the search time range. A well-formulated search strategy can significantly improve search efficiency and accuracy.

5. A technology policy retrieval method according to claim 1, characterized in that: In S4, a search operation is performed. During the search operation, the time is calculated and the search time is controlled to be 2-3 seconds. If it exceeds this range, the system and network are checked.

6. A technology policy retrieval method according to claim 1, characterized in that: In said S6, the collected data is processed, and the specific steps are: first, the data is centrally screened, then the data is centrally cleaned, then the data is classified and grouped, and the grouped data are numbered. The numbering adopts one of digital numbering and alphabetical numbering, and the order of the numbers is set according to the size of the data.

7. A technology policy retrieval method according to claim 6, characterized in that: The centralized data cleaning is mainly carried out through natural language processing and data preprocessing technology to remove irrelevant information and improve data quality.

8. A method for searching science and technology policies according to claim 1, characterized in that: In S7, a deep learning model is used to extract text features and perform semantic analysis, and to perform text mining on the data.

9. A method for searching science and technology policies according to claim 1, characterized in that: In said S8, the mined information is marked and backed up and stored. In said S9, the retrieved original data and mined information are exported, and the entire retrieval process is evaluated through artificial intelligence. The evaluation results are divided into three levels, namely excellent, good and poor.

10. A science and technology policy retrieval system, characterized in that: The system comprises a retrieval requirement establishment module, an output end of the retrieval requirement establishment module is connected to a retrieval database selection module, an output end of the retrieval requirement establishment module is connected to an input end of a retrieval database selection module, an output end of the retrieval database selection module is connected to an input end of a retrieval policy formulation module, an output end of the retrieval policy formulation module is connected to an input end of a retrieval operation execution module, an output end of the retrieval operation execution module is connected to an input end of a retrieval data collection module, an output end of the retrieval data collection module is connected to an input end of a data collection processing module, and an output end of the data collection processing module is connected to an input end of a data collection processing module. The input end of the text mining module is connected, the output end of the data text mining module is connected to the input end of the mining information key marking module, the output end of the mining information key marking module is connected to the input end of the original data retrieval and mining information export module, wherein the data collection and processing module also includes a data centralized screening module, the output end of the data centralized screening module is connected to the input end of the data centralized cleaning module, the output end of the data centralized cleaning module is connected to the input end of the data classification and grouping module, and the output end of the data classification and grouping module is connected to the input end of the grouped data numbering module.

Citation Information

Patent Citations

  • Database access method and device

    CN103577408A

  • Power grid big data analysis and mining application system

    CN108733850A

  • Scientific and technological information automatic processing method and system based on knowledge organization

    CN111221957A

  • Network request processing method and application

    CN111629056A

  • Scientific and technological policy retrieval method

    CN114691738A