An intelligent management system for thermal power plant database based on AI big model

Abstract

The present invention relates to the field of intelligent management technology, and in particular to an intelligent management system for a thermal power plant database based on an AI large model, comprising a text screening module, a synonym analysis module, a data matching coefficient analysis module, a keyword library matching module, a keyword proportion analysis module, a synonym matching module, a keyword analysis module, a keyword heat analysis module, and a management database. The system uploads text data to a thermal power plant sub-database to which the keyword group of the text data belongs by analyzing the data matching coefficient of each keyword group, obtains a target text of the search keyword by analyzing the text matching coefficients of each search phrase, obtains a heat index of each historical keyword by analyzing the number of searches of each historical keyword in each historical period, and then performs heat sorting on the thermal power plant sub-database to which it belongs, which is helpful for effective management of the thermal power plant database and improves processing efficiency and accuracy.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, and in particular to an intelligent management system for a thermal power plant database based on an AI large model. Background Art

[0002] As an important part of energy production, thermal power plants play a vital role in the power industry. With the continuous development of the power industry and the continuous expansion of the scale of thermal power plants, how to efficiently manage and operate thermal power plants has become an urgent problem to be solved. Thermal power plants involve a large amount of data, including equipment operation data, maintenance records, environmental monitoring data, etc. Database management, as a key information management method, provides thermal power plants with effective data collection, storage, analysis and management tools, which is of great significance for improving the operating efficiency of thermal power plants, optimizing resource allocation, reducing costs and improving service quality.

[0003] The patent name is a technical solution published in a Chinese patent (patent number is 201511025071.8). The solution extracts keywords from search request data, retrieves relevant recommendation word data, searches for keywords and recommendation words in the database, and converts keywords into pinyin for retrieval when no index is retrieved. It can more accurately understand the user's search intention and improve the matching degree of search results, but there are still some shortcomings, which are specifically manifested in the following aspects: First, the solution only considers extracting keywords from search request data and searching for relevant recommendation word data, but does not mention the process of extracting keywords from articles and including them in the corresponding sub-database, which may result in incomplete and inaccurate search results. The keyword extraction and inclusion of article content can better reflect the subject and quality of the article, and help improve the accuracy and relevance of search results.

[0004] Second, this solution only searches for keywords and recommended words, but does not mention the situation when the search results are not unique. When the search request corresponds to multiple possible matches, there is no appropriate strategy to display multiple results, sort multiple results, or present them to users for selection in other ways. Users may not be able to obtain all relevant information in the first time, resulting in some relevant content being ignored. Summary of the invention

[0005] In order to overcome the shortcomings of the background technology, an embodiment of the present invention provides an intelligent management system for a thermal power plant database based on an AI big model, which can effectively solve the problems involved in the above-mentioned background technology.

[0006] The purpose of the present invention can be achieved through the following technical solutions: The present invention provides an intelligent management system for thermal power plant database based on AI big model, including: a text screening module, which is used to detect the text proportion of each vocabulary in the uploaded text material, and compare it with the preset text proportion threshold, so as to screen out each high-frequency word and obtain the text proportion of each high-frequency word.

[0007] The synonym analysis module is used to match the corresponding synonym library for each high-frequency word in the text, recorded as the corresponding synonym library for each high-frequency word, and analyze the proportion of each synonym in the corresponding synonym library for each high-frequency word in the text data, recorded as the text proportion of each high-frequency synonym for each high-frequency word.

[0008] The data matching coefficient analysis module is used to obtain the data matching coefficient of each keyword group based on the text proportion of each high-frequency word and the text proportion of each high-frequency synonym.

[0009] The keyword library matching module is used to obtain the keyword group of the text data according to the data matching coefficient analysis of each keyword group, and upload the text data to the thermal power plant sub-database to which the keyword group of the text data belongs.

[0010] The keyword proportion analysis module is used to detect the number of occurrences of the input search keyword in each text material, and then analyze the proportion of each text of the search keyword.

[0011] The synonym matching module is used to match the search keyword with the synonym library corresponding to the search keyword, and detect the proportion of each search keyword synonym in the synonym library corresponding to the search keyword in each text material, which is recorded as the proportion of each synonym of the search keyword in each text.

[0012] The keyword analysis module is used to obtain the text matching coefficients of the search phrases according to the text proportions of the search keywords and the text proportions of the synonyms of the search keywords, and then obtain the target text of the search keywords.

[0013] The keyword heat analysis module is used to read the number of searches for each historical keyword in each historical period, and analyze the heat index of each historical keyword, and then sort the heat of the thermal power plant sub-database to which each historical keyword belongs.

[0014] The management database is used to store each synonym database, the thermal power plant sub-database to which each keyword group belongs, and the keyword search records input by users in each historical period.

[0015] Preferably, the specific analysis method of the text screening module is: read the uploaded text data, perform full-text scanning on the text data to obtain the total number of words in the text data, recorded as W 总 , and detect the number of occurrences of each word in the text data, recorded as ε a, where a represents the number of the ath word, a=1,2,...,b, obtain the number of words in each word, and multiply the number of words in each word by the number of times each word appears in the text data to obtain the total number of words in the text data, recorded as W a , substituting it into the formula Get the proportion of each vocabulary text ω a , and compare the text proportion of each vocabulary with the preset text proportion threshold, record the vocabulary whose text proportion is higher than the preset text proportion threshold as each high-frequency word, and select the text proportion of each high-frequency word from the text proportion of each vocabulary, and record it as the text proportion of each high-frequency word ω m , where m represents the number of the mth high-frequency word, m = 1, 2, ..., n.

[0016] Preferably, the specific analysis process of the synonym analysis module is as follows: the first step is to read each high-frequency word, and at the same time extract each synonym library from the management database, put each high-frequency word into each synonym library for retrieval, retrieve each synonym library to which each high-frequency word belongs, record it as the synonym library corresponding to each high-frequency word, and retrieve the number of occurrences of each word in the synonym library corresponding to each high-frequency word in the text data, analyze each word in the synonym library corresponding to each high-frequency word according to the method of analyzing the proportion of each word in the text, and obtain the proportion of each word in the synonym library corresponding to each high-frequency word in the text data.

[0017] In the second step, the proportion of each word in the synonym library corresponding to each high-frequency word in the text data is compared with the preset text proportion threshold, and the words in the synonym library corresponding to each high-frequency word whose proportion is higher than the preset text proportion threshold are recorded as each high-frequency synonym, and the proportion of each high-frequency synonym is screened out from the proportion of each word in the synonym library corresponding to each high-frequency word in the text data, which is recorded as the text proportion of each high-frequency synonym of each high-frequency word ω mi , where i represents the number of the i-th high-frequency synonym, i = 1, 2, ..., k.

[0018] Preferably, the specific analysis method of the data matching coefficient analysis module is: each high-frequency word in the text is combined with each high-frequency synonym of each high-frequency word to form a keyword group, recorded as each keyword group, and the proportion of each high-frequency word in the text is read respectively. m 、The proportion of each high-frequency word and each high-frequency synonym in the textω mi , substituting it into the formula Get the data matching coefficient α of each high-frequency word corresponding to the keyword group m , which is recorded as the data matching coefficient of each keyword group, where ω0 represents the reference value of the set keyword group text proportion, and φ1 represents the correction factor of the set keyword group text proportion.

[0019] Preferably, the specific analysis method of the keyword library matching module is: read the data matching coefficient of each keyword group, arrange the data matching coefficient of each keyword group in order from large to small, record the keyword group corresponding to the first data matching coefficient as the keyword group of the text material, extract the thermal power plant sub-database to which each keyword group belongs from the management database, match it with the keyword group of the text material to obtain the thermal power plant sub-database to which the keyword group of the text material belongs, and then upload the text material to the thermal power plant sub-database to which the keyword group of the text material belongs.

[0020] Preferably, the specific analysis method of the keyword proportion analysis module is: read the input search keyword, put the search keyword into each text material in the thermal power plant database for search to obtain the number of times the search keyword appears in each text material, and obtain the total number of words of the search keyword in each text material by multiplying the number of words of the search keyword and the number of times the search keyword appears in each text material in the thermal power plant database, which is recorded as W. f , where f represents the number of the f-th text material, f=1,2,...,t, and substitute it into the formula Get the proportion of search keywords in each text materialω f , recorded as the proportion of each text of the search keyword, where Indicates the total number of words in each set text data.

[0021] Preferably, the specific analysis method of the synonym matching module is: read each synonym library from the management database, and put the search keyword into each synonym library for comparison, match and obtain the synonym library to which the search keyword belongs, record it as the synonym library corresponding to the search keyword, and analyze the synonyms of each search keyword in the synonym library corresponding to the search keyword according to the method of analyzing the proportion of each text of the search keyword, obtain the proportion of each synonym of the search keyword in each text, record it as the proportion of each synonym of the search keyword in each text ω qf , where q represents the number of the qth synonym of the search keyword, q = 1, 2, ..., p.

[0022] Preferably, the specific analysis process of the keyword analysis module is as follows: In the first step, the search keyword is combined with each synonym of the search keyword to construct a search phrase, and the proportion of each text of the search keyword is read respectively. f 、The proportion of each synonym of the search keyword in each textω qf , substituting it into the formula Analyze and obtain the text matching coefficient β of the search phrase f , where ω'0 represents the set text ratio reference value, and φ2 represents the set correction factor of the search phrase text ratio.

[0023] The second step is to read the text matching coefficients of the search phrases, and sort the text matching coefficients of the search phrases in descending order, and record the text corresponding to the first matching coefficient as the target text of the keyword.

[0024] Preferably, the specific analysis process of the keyword heat analysis module is as follows: the first step is to divide the historical period according to the set time length, extract the keyword search records input by the user in each historical period from the management database, record them as each historical keyword, and extract the search times of each historical keyword in each historical period, record them as γ xs , where x represents the number of the xth historical period, x = 1, 2, ..., y, s represents the number of the sth historical keyword, s = 1, 2, ..., j, and the average number of retrievals of each historical keyword in each historical period is obtained by averaging the number of retrievals of each historical keyword, which is recorded as Substituting this into the formula Get the heat index ρ of each historical keyword s , where y represents the number of historical periods.

[0025] The second step is to read the heat index of each historical keyword, arrange the heat index of each historical keyword in order from large to small, and search the thermal power plant sub-database to which each historical keyword belongs respectively, and then sort the heat of the thermal power plant sub-database to which each historical keyword belongs according to the arrangement order of the heat index of each historical keyword. At the same time, the number of occurrences of each historical keyword in each text material in the thermal power plant sub-database to which it belongs is searched, and the text materials in the thermal power plant sub-database to which each historical keyword belongs are sorted from most to least according to the number of occurrences of each historical keyword.

[0026] Compared with the prior art, the present invention has the following beneficial effects: 1. The system obtains the data matching coefficient of each keyword group by analyzing the proportion of each high-frequency word in the text and the proportion of each high-frequency synonym of each high-frequency word, and then analyzes and obtains the keyword group of the text material, and uploads the text material to the sub-database to which the keyword group of the text material belongs, which helps to extract the key information of the text, thereby effectively managing the text content.

[0027] Second, by analyzing the proportion of each keyword text and the proportion of each keyword synonym text, we can obtain the text matching coefficient of each keyword search phrase, and then obtain the target text of the keyword, which helps users retrieve the information they need more quickly and improves the efficiency and accuracy of text processing.

[0028] 3. By analyzing the number of searches for each keyword in each historical period, we can obtain the popularity index of each keyword, and then sort the popularity of the sub-database to which each keyword belongs. This can help us understand the user's interest in different keywords, help sort the popularity of text content, and improve the exposure and attractiveness of the content. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0030] Figure 1 This is a system module connection diagram of the present invention. DETAILED DESCRIPTION

[0031] 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.

[0032] See also Figure 1 As shown, an intelligent management system for thermal power plant database based on AI big model includes text screening module, synonym analysis module, data matching coefficient analysis module, keyword library matching module, keyword proportion analysis module, synonym matching module, keyword analysis module, keyword heat analysis module and management database.

[0033] The management database is connected to the keyword proportion analysis module, the synonym analysis module, the data matching coefficient analysis module, the keyword heat analysis module, the keyword analysis module, and the synonym matching module; the data matching coefficient analysis module is connected to the synonym analysis module, the text screening module, and the keyword library matching module; the text screening module is connected to the synonym analysis module; the keyword proportion analysis module is connected to the synonym matching module and the keyword analysis module; and the synonym matching module is connected to the keyword analysis method module.

[0034] The text screening module is used to detect the text ratio of each word in the uploaded text data and compare it with the preset text ratio threshold, so as to screen out the high-frequency words and obtain the text ratio of each high-frequency word.

[0035] The specific analysis method of the text screening module is: read the uploaded text data, perform full-text scanning on the text data to obtain the total number of words in the text data, recorded as W 总 , and detect the number of occurrences of each word in the text data, recorded as ε a, where a represents the number of the ath word, a=1,2,...,b, obtain the number of words in each word, and multiply the number of words in each word by the number of times each word appears in the text data to obtain the total number of words in the text data, recorded as W a , substituting it into the formula Get the proportion of each vocabulary text ω a , and compare the text proportion of each vocabulary with the preset text proportion threshold, record the vocabulary whose text proportion is higher than the preset text proportion threshold as each high-frequency word, and select the text proportion of each high-frequency word from the text proportion of each vocabulary, and record it as the text proportion of each high-frequency word ω m , where m represents the number of the mth high-frequency word, m=1,2,...,n; by calculating the text proportion of each word and comparing it with the preset text proportion threshold, it helps to screen out high-frequency words and understand the key content of the text more quickly.

[0036] It should be noted that vocabulary is words or terms that describe concepts and entities related to thermal power plants and are used to accurately express specific meanings for data understanding and processing.

[0037] In one embodiment, "boiler" refers to a device used to burn fuel to generate steam; "steam turbine" refers to a generator set driven by steam energy; and "electricity generation" refers to the electrical energy generated by a thermal power plant per unit time.

[0038] The synonym analysis module is used to match the corresponding synonym library for each high-frequency word in the text, recorded as the corresponding synonym library for each high-frequency word, and analyze the proportion of each synonym in the corresponding synonym library for each high-frequency word in the text data, recorded as the text proportion of each high-frequency synonym for each high-frequency word.

[0039] The specific analysis process of the synonym analysis module is as follows: the first step is to read each high-frequency word, and at the same time extract each synonym library from the management database, put each high-frequency word into each synonym library for retrieval, retrieve each synonym library to which each high-frequency word belongs, record it as the synonym library corresponding to each high-frequency word, and retrieve the number of occurrences of each word in the synonym library corresponding to each high-frequency word in the text data, analyze each word in the synonym library corresponding to each high-frequency word according to the method of analyzing the proportion of each word in the text, and obtain the proportion of each word in the synonym library corresponding to each high-frequency word in the text data; extracting high-frequency words and matching them with synonym libraries helps to expand the scope of text analysis, not only can the high-frequency words in the original text be analyzed, but more relevant information can also be found through synonym libraries, thereby improving the comprehensiveness and accuracy of text analysis.

[0040] It should be noted that synonyms are words that have a certain degree of overlap in usage when describing the same or similar things. These words can be considered together during search to increase the richness of search results.

[0041] In one embodiment, "thermal power plant" is the same as "thermal power plant" and is a synonym of "thermal power plant"; "gas-fired power plant" is related to "coal-fired power plant" and refers to a power plant that uses natural gas or other fuel gases; "desulfurization and purification" is related to "flue gas desulfurization" and refers to the purification of harmful substances in flue gas after combustion.

[0042] In the second step, the proportion of each word in the synonym library corresponding to each high-frequency word in the text data is compared with the preset text proportion threshold, and the words in the synonym library corresponding to each high-frequency word whose proportion is higher than the preset text proportion threshold are recorded as each high-frequency synonym, and the proportion of each high-frequency synonym is screened out from the proportion of each word in the synonym library corresponding to each high-frequency word in the text data, which is recorded as the text proportion of each high-frequency synonym of each high-frequency word ω mi , where i represents the number of the i-th high-frequency synonym, i = 1, 2, ..., k; it can help to more systematically mine the relevant information and synonyms of high-frequency words in text materials, improve the efficiency and quality of information acquisition, and provide richer and more in-depth text information analysis.

[0043] The data matching coefficient analysis module is used to obtain the data matching coefficient of each keyword group based on the text proportion of each high-frequency word and the text proportion of each high-frequency synonym.

[0044] The specific analysis method of the data matching coefficient analysis module is: combine each high-frequency word in the text with each high-frequency synonym of each high-frequency word to form a keyword group, recorded as each keyword group, and read the proportion of each high-frequency word in the text ω m 、The proportion of each high-frequency word and each high-frequency synonym in the textω mi , substituting it into the formula Get the data matching coefficient α of each high-frequency word corresponding to the keyword group m , which is recorded as the data matching coefficient of each keyword group, where ω0 represents the reference value of the set keyword group text ratio, and φ1 represents the correction factor of the set keyword group text ratio; the matching degree of the evaluated keyword group is quantified, and the importance and relevance of each keyword group in the text are more intuitively understood, thereby improving the accuracy and comprehensiveness of text retrieval.

[0045] The keyword library matching module is used to obtain the keyword group of the text data according to the data matching coefficient analysis of each keyword group, and upload the text data to the thermal power plant sub-database to which the keyword group of the text data belongs.

[0046] The specific analysis method of the keyword library matching module is as follows: reading the data matching coefficient of each keyword group, arranging the data matching coefficient of each keyword group in order from large to small, recording the keyword group corresponding to the first data matching coefficient as the keyword group of the text material, extracting the thermal power plant sub-database to which each keyword group belongs from the management database, matching it with the keyword group of the text material to obtain the thermal power plant sub-database to which the keyword group of the text material belongs, and then uploading the text material to the thermal power plant sub-database to which the keyword group of the text material belongs; by analyzing the data matching coefficient, the most relevant and matching keyword group to the text material can be found, thereby improving the accuracy and effectiveness of extracting key information from the text, and at the same time, the specific field or category to which the keyword group of the text material belongs can be further refined and accurately determined, which is convenient for archiving, management and classification of the text material.

[0047] The keyword proportion analysis module is used to detect the number of occurrences of the input search keyword in each text material, and then analyze the proportion of each text of the search keyword.

[0048] The specific analysis method of the keyword proportion analysis module is as follows: read the input search keyword, put the search keyword into each text material in the thermal power plant database for retrieval to obtain the number of times the search keyword appears in each text material, and multiply the number of words of the search keyword and the number of times the search keyword appears in each text material in the thermal power plant database to obtain the total number of words of the search keyword in each text material, which is recorded as W f , where f represents the number of the f-th text material, f=1,2,...,t, and substitute it into the formula Get the proportion of search keywords in each text materialω f , recorded as the proportion of each text of the search keyword, where Indicates the total number of words in each set text material; by putting the search keywords into the text materials of the thermal power plant database for searching, and counting the number of times the search keywords appear in each text material, it is possible to quickly and accurately understand the importance and correlation of the search keywords in different texts, so as to facilitate further search keyword analysis and text mining, provide more in-depth and comprehensive information processing and utilization services, and improve the efficiency and accuracy of data processing.

[0049] It should be noted that keywords are words that identify and mark specific information in the thermal power plant database for easy retrieval and organization, and are words that have specific meanings or importance in the retrieval and management of the thermal power plant database.

[0050] In one embodiment, "thermal power plant" is the most basic keyword, which is used to indicate a power plant that generates electricity by burning coal, gas, nuclear energy and other energy sources; "coal-fired power plant" refers to a thermal power plant that uses coal as fuel; and "generator set" indicates the equipment used to generate electricity in a thermal power plant.

[0051] The synonym matching module is used to match the search keyword with the synonym library corresponding to the search keyword, and detect the proportion of each search keyword synonym in the synonym library corresponding to the search keyword in each text material, which is recorded as the proportion of each synonym of the search keyword in each text.

[0052] The specific analysis method of the synonym matching module is as follows: read each synonym library from the management database, put the search keyword into each synonym library for comparison, match and obtain the synonym library to which the search keyword belongs, record it as the synonym library corresponding to the search keyword, and analyze the synonyms of each search keyword in the synonym library corresponding to the search keyword according to the method of analyzing the proportion of each text of the search keyword, obtain the proportion of each synonym of each search keyword in each text, record it as the proportion of each synonym of the search keyword in each text ω qf , where q represents the number of the qth synonym of the search keyword, q = 1, 2, ..., p; analyzing the proportion of each synonym of each search keyword in each text is conducive to in-depth exploration of the semantic association and usage scenarios of the search keywords, and improving the accuracy and efficiency of information retrieval.

[0053] The keyword analysis module is used to obtain the text matching coefficients of the search phrases according to the text proportions of the search keywords and the text proportions of the synonyms of the search keywords, and then obtain the target text of the search keywords.

[0054] The specific analysis process of the keyword analysis module is as follows: In the first step, the search keyword is combined with each synonym of the search keyword to construct a search phrase, and the proportion of each text of the search keyword is read respectively. f 、The proportion of each synonym of the search keyword in each textω qf , substituting it into the formula Analyze and obtain the text matching coefficient β of the search phrase f , where ω'0 represents the set text ratio reference value, and φ2 represents the set correction factor of the search phrase text ratio; by analyzing the text matching coefficients of the search phrases, the matching degree of the search phrases in each text can be quantitatively evaluated to help find the required information more quickly. At the same time, through the set text ratio reference value and the correction factor of the search phrase text ratio, the search results can be adjusted and optimized to ensure that the search results are more accurate and meet the needs, thereby improving the search efficiency.

[0055] The second step is to read the text matching coefficients of each search phrase, and sort the text matching coefficients of each search phrase in descending order, and record the text corresponding to the first matching coefficient as the target text of the keyword; this helps to directly find the most matching text, reduce the time of browsing and filtering in search results, and improve the convenience and speed of information search.

[0056] The keyword heat analysis module is used to read the number of searches for each historical keyword in each historical period, and analyze the heat index of each historical keyword, and then sort the heat of the thermal power plant sub-database to which each historical keyword belongs.

[0057] The specific analysis process of the keyword heat analysis module is as follows: In the first step, the historical period is divided according to the set time length, and the keyword search records input by users in each historical period are extracted from the management database, which are recorded as each historical keyword, and the search times of each historical keyword in each historical period are extracted, which are recorded as γ xs , where x represents the number of the xth historical period, x = 1, 2, ..., y, s represents the number of the sth historical keyword, s = 1, 2, ..., j, and the average number of retrievals of each historical keyword in each historical period is obtained by averaging the number of retrievals of each historical keyword, which is recorded as Substituting this into the formula Get the heat index ρ of each historical keyword s , where y represents the number of historical cycles; it helps to analyze and understand the users’ search results for specific historical keywords in different time periods, and helps to evaluate the importance and attention of each historical keyword.

[0058] The second step is to read the heat index of each historical keyword, arrange the heat index of each historical keyword in order from large to small, and search the thermal power plant sub-database to which each historical keyword belongs respectively, and then sort the heat of the thermal power plant sub-database to which each historical keyword belongs according to the arrangement order of the heat index of each historical keyword. At the same time, the number of occurrences of each historical keyword in each text material in the thermal power plant sub-database to which it belongs is searched, and the text materials in the thermal power plant sub-database to which each historical keyword belongs are sorted from most to least according to the number of occurrences of each historical keyword. The heat situation of each historical keyword can be quickly and accurately understood, and the degree of user attention to each historical keyword can be understood more intuitively, so as to optimize search results and content display.

[0059] The management database is used to store each synonym database, the thermal power plant sub-database to which each keyword group belongs, and the keyword search records input by users in each historical period.

[0060] This system obtains the data matching coefficient of each keyword group by analyzing the proportion of each high-frequency word in the text and the proportion of each high-frequency synonym of each high-frequency word, and then analyzes and obtains the keyword group of the text data, and uploads the text data to the thermal power plant sub-database to which the keyword group of the text data belongs. By analyzing the proportion of each text of the retrieval keyword and the proportion of each text of each synonym of the retrieval keyword, the text matching coefficient of each retrieval phrase is obtained, and then the target text of the retrieval keyword is obtained. By analyzing the number of searches for each historical keyword in each historical period, the popularity index of each historical keyword is obtained, and then the thermal power plant sub-database to which each historical keyword belongs is ranked by popularity, which improves the efficiency and accuracy of text processing and helps to effectively manage text content.

[0061] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations on the present invention. A person skilled in the art may make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention and they are still covered by the protection scope of the present invention.

Claims

1. An intelligent management system for thermal power plant database based on AI big model, characterized in that: The system specifically includes the following modules: The text screening module is used to detect the text proportion of each word in the uploaded text data and compare it with the preset text proportion threshold, so as to screen out each high-frequency word and obtain the text proportion of each high-frequency word; The synonym analysis module is used to match the corresponding synonym library for each high-frequency word in the text, recorded as the corresponding synonym library for each high-frequency word, and analyze the proportion of each synonym in the corresponding synonym library for each high-frequency word in the text data, recorded as the text proportion of each high-frequency synonym for each high-frequency word; The data matching coefficient analysis module is used to obtain the data matching coefficient of each keyword group according to the text proportion of each high-frequency word and the text proportion of each high-frequency synonym of each high-frequency word; The keyword library matching module is used to obtain the keyword group of the text data according to the data matching coefficient of each keyword group, and upload the text data to the thermal power plant sub-database to which the keyword group of the text data belongs; The keyword proportion analysis module is used to detect the number of occurrences of the input search keyword in each text document, and then analyze the proportion of each text of the search keyword; The synonym matching module is used to match the search keyword with the synonym library corresponding to the search keyword, and detect the proportion of each synonym of the search keyword in the synonym library corresponding to the search keyword in each text material, which is recorded as the proportion of each synonym of the search keyword in each text; The keyword analysis module is used to obtain the text matching coefficients of the search phrases according to the text proportions of the search keywords and the text proportions of the synonyms of the search keywords, and then obtain the target text of the search keywords; The keyword heat analysis module is used to read the number of searches for each historical keyword in each historical period, and analyze the heat index of each historical keyword, and then perform heat ranking on the thermal power plant sub-database to which each historical keyword belongs; Management database, used to store each synonym database, each keyword group to which the thermal power plant sub-database belongs, and each historical period user input keyword search record; in Indicates The number of high-frequency synonyms, ; The specific analysis method of the data matching coefficient analysis module is: Combine each high-frequency word in the text with its high-frequency synonyms to form a keyword group, record it as each keyword group, and read the proportion of each high-frequency word in the text separately , the proportion of each high-frequency word and each high-frequency synonym in the text , substituting it into the formula Get the data matching coefficient of each high-frequency word corresponding to the keyword group , which is recorded as the data matching coefficient of each keyword group, where Indicates the reference value of the set keyword group text ratio. Indicates the correction factor of the set keyword group text ratio; in Indicates The number of synonyms of the search keyword, ; The specific analysis process of the keyword analysis module is as follows: The first step is to combine the search keyword with its synonyms to construct a search phrase, and read the proportion of each text of the search keyword separately. , The proportion of each synonym of the search keyword in each text , substituting it into the formula Analyze and obtain the text matching coefficients of the search phrases ,in Indicates the set text ratio reference value. Indicates the correction factor of the set search phrase text ratio; The second step is to read the text matching coefficients of the search phrases, and sort the text matching coefficients of the search phrases in descending order, and record the text corresponding to the first matching coefficient as the target text of the keyword; The specific analysis process of the keyword heat analysis module is as follows: The first step is to divide the historical period into the set time period, extract the keyword search records entered by the user in each historical period from the management database, record them as historical keywords, and extract the search times of each historical keyword in each historical period, record them as ,in Indicates The number of the historical period, , Indicates The number of historical keywords, , by taking the average of the search times of each historical keyword in each historical period, we can get the average search times of each historical keyword in the period, which is recorded as , substituting it into the formula Get the heat index of each historical keyword ,in Indicates the number of historical periods; The second step is to read the heat index of each historical keyword, arrange the heat index of each historical keyword in order from large to small, and search the thermal power plant sub-database to which each historical keyword belongs respectively, and then sort the heat of the thermal power plant sub-database to which each historical keyword belongs according to the arrangement order of the heat index of each historical keyword. At the same time, the number of occurrences of each historical keyword in each text material in the thermal power plant sub-database to which it belongs is searched, and the text materials in the thermal power plant sub-database to which each historical keyword belongs are sorted from most to least according to the number of occurrences of each historical keyword.

2. According to claim 1, a thermal power plant database intelligent management system based on AI large model is characterized in that: The specific analysis method of the text screening module is: Read the uploaded text data, scan the full text of the text data to get the total number of words in the full text of the text data, recorded as , and detect the number of occurrences of each word in the text data, recorded as ,in Indicates The number of the word, , get the number of words in each word, and multiply the number of words in each word by the number of times each word appears in the text data to get the total number of words in the text data, recorded as , substituting it into the formula Get the proportion of each vocabulary text The text proportion of each word is compared with the preset text proportion threshold, and the words with text proportion higher than the preset text proportion threshold are recorded as high-frequency words, and the text proportion of each high-frequency word is selected from the text proportion of each word, and recorded as the text proportion of each high-frequency word ,in Indicates The number of high frequency words, .

3. According to claim 2, a thermal power plant database intelligent management system based on AI large model is characterized in that: The specific analysis process of the synonym analysis module is as follows: The first step is to read each high-frequency word, and extract each synonym library from the management database at the same time, put each high-frequency word into each synonym library for retrieval, retrieve each synonym library to which each high-frequency word belongs, record it as the synonym library corresponding to each high-frequency word, and retrieve the number of occurrences of each word in the synonym library corresponding to each high-frequency word in the text data, analyze each word in the synonym library corresponding to each high-frequency word according to the method of analyzing the proportion of each word in the text, and obtain the proportion of each word in the synonym library corresponding to each high-frequency word in the text data; In the second step, the proportion of each word in the synonym library corresponding to each high-frequency word in the text data is compared with the preset text proportion threshold, and the words in the synonym library corresponding to each high-frequency word whose proportion is higher than the preset text proportion threshold are recorded as each high-frequency synonym, and the proportion of each high-frequency synonym is selected from the proportion of each word in the synonym library corresponding to each high-frequency word in the text data, which is recorded as the text proportion of each high-frequency synonym of each high-frequency word. .

4. According to claim 1, a thermal power plant database intelligent management system based on AI large model is characterized in that: The specific analysis method of the keyword library matching module is: Read the data matching coefficient of each keyword group, arrange the data matching coefficient of each keyword group in descending order, record the keyword group corresponding to the first data matching coefficient as the keyword group of the text data, extract the thermal power plant sub-database to which each keyword group belongs from the management database, match it with the keyword group of the text data to obtain the thermal power plant sub-database to which the keyword group of the text data belongs, and then upload the text data to the thermal power plant sub-database to which the keyword group of the text data belongs.

5. According to claim 1, a thermal power plant database intelligent management system based on AI large model is characterized in that: The specific analysis method of the keyword proportion analysis module is as follows: Read the input search keyword, put the search keyword into each text material in the thermal power plant database for search to obtain the number of times the search keyword appears in each text material, and multiply the number of words of the search keyword and the number of times the search keyword appears in each text material in the thermal power plant database to obtain the total number of words of the search keyword in each text material, recorded as ,in Indicates The number of the text document. , substituting it into the formula Get the proportion of search keywords in each text document , recorded as the proportion of each text of the search keyword, where Indicates the total number of words in each set text data.

6. According to claim 5, a thermal power plant database intelligent management system based on AI large model is characterized in that: The specific analysis method of the synonym matching module is: Read each synonym library from the management database, and put the search keyword into each synonym library for comparison, match the synonym library to which the search keyword belongs, record it as the synonym library corresponding to the search keyword, and analyze the synonyms of each search keyword in the synonym library corresponding to the search keyword according to the method of analyzing the proportion of each text of the search keyword, and obtain the proportion of each synonym of each search keyword in each text, record it as the proportion of each synonym of the search keyword in each text .

Images