CN114756656A - Hydraulic engineering potential safety hazard description association rule mining method based on improved Apriori algorithm - Google Patents
Hydraulic engineering potential safety hazard description association rule mining method based on improved Apriori algorithm Download PDFInfo
- Publication number
- CN114756656A CN114756656A CN202210471547.4A CN202210471547A CN114756656A CN 114756656 A CN114756656 A CN 114756656A CN 202210471547 A CN202210471547 A CN 202210471547A CN 114756656 A CN114756656 A CN 114756656A
- Authority
- CN
- China
- Prior art keywords
- hydraulic engineering
- potential safety
- data
- item set
- safety hazard
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a hydraulic engineering potential safety hazard description association rule mining method based on an improved Apriori algorithm, which comprises the steps of firstly preprocessing a large number of hydraulic engineering potential safety hazard description texts of different categories by using Jieba word segmentation, and extracting keywords and screening parts of speech of word segmentation results by using a TextRank algorithm to obtain potential safety hazard description text keywords; then, performing Boolean matrix conversion on the keyword item set based on the unique hot code, fusing and improving an Apriori association rule, mining frequent item sets in various hidden dangers, and analyzing the association rule; and finally, mining a strong association relation between the descriptions of the hidden dangers by taking the confidence coefficient as an evaluation value, and predicting the generation trend of the hidden dangers. The method carries out data preprocessing aiming at a large amount of unstructured potential safety hazard descriptions, improves the traditional Apriori algorithm, improves the operation efficiency, can analyze the potential safety hazard descriptions of the hydraulic engineering in time, and is favorable for the prediction and the troubleshooting treatment of the potential safety hazards of the hydraulic engineering.
Description
Technical Field
The invention relates to the technical field of water conservancy engineering potential safety hazard troubleshooting, in particular to a water conservancy engineering potential safety hazard description association rule mining method based on an improved Apriori algorithm.
Background
The hydraulic engineering has multiple points and wide range, a large number of potential safety hazards exist, the potential safety hazards are often related, and the mining of the related relation among various potential safety hazards has important significance. The Apriori algorithm is used as the most classical association rule mining algorithm and has related application in the field of hydraulic engineering. However, the traditional Apriori algorithm has the technical problems of low efficiency and long time consumption for a large data set, and the unstructured text of the potential safety hazard description is difficult to accurately analyze.
In order to solve the existing problems, for example, in the water conservancy project construction quality safety supervision data mining and analysis based on association rules, such as Huangdawn and the like, the technical problems of the project are divided into 50 problem categories according to the problem description, an Apriori algorithm is adopted to carry out association rule mining on the project attributes and the problem description, the method carries out merging and classifying pretreatment on original hidden danger data, and the structural expression of the hidden danger description is realized, but the method needs manual operation when processing the original hidden danger data, consumes a large amount of time for a large amount of data, has certain subjectivity and affects the accuracy of the result; as stated, the association rule optimization algorithm based on phrase extraction is provided in 'mining of association rules of potential safety hazards in hydropower engineering construction', key phrases are extracted from a potential safety hazard text based on a phrase extraction technology, and meanwhile, a phrase metric value is used as an evaluation index to optimize the support degree in an Apriori algorithm, so that association rules among potential safety hazard attributes are mined, the method mines new words in the text through the phrase extraction technology, improves the word segmentation quality, redefines the support degree at the same time, and enables the association rule mining to be more scientific, but the phrase extraction technology adopted by the method needs a large amount of labor cost for building and maintaining a required rule base, the mined new words have certain deviation with proper nouns in the hydraulic engineering field, and meanwhile, word segmentation results without clear meanings exist, such as easy generation and no setting, and the like, and are not improved in the iteration aspect of the Apriori algorithm, the operation efficiency is low.
Therefore, it is necessary to construct an efficient mining method for the hydraulic engineering potential safety hazard description association rules, and compared with the existing method, the mining method for the hydraulic engineering potential safety hazard description association rules based on the improved Apriori algorithm has two remarkable characteristics: (1) the method comprises the steps of constructing a self-defined word bank in the hydraulic engineering field, carrying out word segmentation on hidden danger texts, carrying out part of speech screening and keyword extraction by adopting a TextRank algorithm, converting word segmentation results into Boolean matrixes based on unique heat codes, and only retaining some important keywords in the preprocessed hidden danger texts. (2) And (3) optimizing an Apriori algorithm, and screening a frequent item set of the Boolean matrix before layer-by-layer iteration. Pruning optimization is carried out in iteration, meanwhile, a data set is dynamically reduced, and the operation efficiency of association rule mining is obviously improved.
Disclosure of Invention
The invention aims to provide a method for mining the potential safety hazard description association rules of water conservancy projects based on an improved Apriori algorithm, solve the problems that the potential safety hazard description in the water conservancy project safety construction is difficult to structurally express and the operation efficiency of the association rule mining algorithm is low, timely mine the association rules among the potential safety hazards in the water conservancy project construction, and provide auxiliary support for prediction and troubleshooting management of the potential safety hazards of the water conservancy projects.
The invention discloses a hydraulic engineering potential safety hazard description association rule mining method based on an improved Apriori algorithm, which comprises the following steps of:
step S1, building a self-defined word bank in the hydraulic engineering field, carrying out word segmentation on the hidden danger data set by adopting jieba word segmentation, removing stop words, screening out the part of speech by a TextRank algorithm, and taking the extracted keywords as an input data set;
step S2, step S2, based on one-hot encoding, Boolean matrix conversion is carried out on the input data set obtained in step S1;
step S3, calculating the support degree of each item set by improving Apriori algorithm, and screening out item sets not less than the minimum support degree, namely frequent item sets;
step S4, performing confidence calculation on the obtained frequent item set, and screening out an association rule not less than the minimum confidence, that is, a strong association rule a ═ B, that is, when the item set a appears, the item set B also appears as much as possible.
Preferably, the step S1 specifically includes:
step S11, collecting entries in the hydraulic engineering field, constructing a self-defined word bank in the hydraulic engineering field, adopting jieba word segmentation, segmenting the hidden danger data set, and labeling the part of speech;
step S12, loading the stop word stock, eliminating words which have no definite meaning in the word segmentation result, such as word help words, adverbs, prepositions, conjunctions and the like;
and step S13, sorting the importance of the participles by adopting a TextRank algorithm, and extracting the keywords of which the parts of speech are nouns, verbs, vernouns and place names in the participles to serve as a final input data set.
Through the steps S11-S13, the hidden danger description texts which are difficult to structurally express in the data set are preprocessed.
Preferably, the step S2 specifically includes:
in step S21, the input data set D is first set to { D ═ D1,D1…,DnAnd converting the matrix into a matrix T in a DataFrame data frame form, wherein the matrix T is in the form of:
wherein n is the number of the hidden danger description data, m is the maximum word segmentation number in n pieces of data, and TijThe key word is the jth key word of the ith data, and if the key word is Null, the number is Null; diFor the ith data in the data set, i.e. the set { T }i1,Ti2,…,Tin}；
Step S22, carrying out one-hot coding on the data frame matrix T, and converting the data frame matrix T into a Boolean matrix M; let I ═ I1,I2,…,ItThe boolean matrix M is a set of all the different entries in the dataset D, the form of the boolean matrix M being:
where t is the number of all different keywords in the dataset D, MijThe Boolean value of the ith data to the jth keyword if DiComprising IjI.e. the ith piece of data contains the jth keyword, then MijIs 1(True), otherwise is 0 (False).
The chinese text preprocessed in step S1 is converted into an easily recognizable boolean matrix by step S2.
Preferably, the step S3 specifically includes:
step S31, before iteration, performing one-time traversal on the Boolean matrix obtained by conversion in the step S22, counting and summing each column in the Boolean matrix respectively, quickly mining a 1-dimensional frequent item set, and deleting a non-frequent item set;
step S32, while iterating, k-1 dimension frequent item set Lk-1Connected to form a k-dimensional candidate set denoted Ck(ii) a Let I1And I2Is Lk-1If k-2 items in the item set are identical, I1、I2Concatenating produces a set of result items, which is a set of candidate items CkOne of them;
step S33, for candidate item set CkPruning, CkIs LkA superset of (c); for Lk-1Each item set T in (1), sequentially traversing CkAnd counting each candidate based on the boolean matrix. After all traversals are finished, counting result pairs CkCutting each candidate item set, if the count is less than k, deleting the candidate item set, and simultaneously deleting all item sets containing the item set in the data set; otherwise, reserving and carrying out the next step;
step S34, calculating a support degree (support) for each of the pruned candidate sets, where the support degree formula is:
support(A＝>B)＝P(A∪B)
in the formula: A. b is a set of items consisting of any item in I, namely representing the probability that the data contains each item in the sets of items A and B;
if the support degree of the candidate item set is not less than the minimum support degree, the candidate item set is k-frequent item set, and L is addedkOtherwise, deleting the item set and deleting the item set at the same timeExcept for all sets of items in the dataset that contain the set of items. And returning to the step S32 after the screening is finished until the k-frequent item set can not be found.
Through the steps 2 and S31, before iteration, the support degree calculation of each keyword is not needed, each column in the Boolean matrix is directly counted and summed, the 1-dimensional frequent item set is rapidly mined, and the non-frequent item set is deleted; a large amount of data sets are rapidly screened based on the Boolean matrix, so that the data sets are greatly reduced, and the iterative operation efficiency under the condition of large data sets in the initial iteration stage is improved. In iteration, k-1 dimensional frequent item set Lk-1Connecting to form k-dimensional candidate set CkFor Lk-1Each item set T in (1), sequentially traversing CkAnd counting each candidate based on the boolean matrix. After traversing is finished, counting result pairs CkIs clipped, if the count is less than k, the candidate item is deleted, and all item sets in the data set containing the item set are deleted. Optimizing a pruning link through step S32, and enabling the time complexity to be O (n)2) And the integral iterative operation efficiency is improved by reducing the operation speed to O (n).
The conventional Apriori algorithm searches through the L-dimension subset of each candidate item againk-1This increases the computation time, affecting the algorithm efficiency. The improved Apriori algorithm mainly comprises the steps of rapidly mining a frequent item set before iteration, carrying out pruning optimization in the iteration, and dynamically reducing a data set, so that the operation efficiency of the algorithm is remarkably improved.
Compared with the prior art, the invention has the beneficial effects that:
(1) according to the method, the user-defined word bank in the hydraulic engineering field is constructed, the TextRank algorithm is adopted for keyword extraction and part-of-speech filtering, and automatic word segmentation is performed through a machine, so that preprocessing of hidden danger description texts which are difficult to express structurally is realized, and the problems that labor cost is high and hydraulic engineering field terms cannot be identified in the prior art are solved.
(2) According to the invention, before iteration, a large number of data sets are rapidly screened based on the Boolean matrixTherefore, the data set is greatly reduced, and the iterative operation efficiency under the condition of a large data set at the initial stage of iteration is improved; in iteration, the time complexity is changed from O (n) by optimizing a pruning link2) And the integral iterative operation efficiency is improved by reducing the operation speed to O (n).
(3) According to the invention, by improving the algorithm before and during iteration, the operation efficiency of the Apriori algorithm is greatly improved, and the problem of lower operation efficiency of the algorithm under the condition of a huge data set in the prior art is solved.
Drawings
FIG. 1 is an overall work flow diagram of the present invention.
Detailed Description
The technical solution of the present invention is described in detail with reference to the following examples, but the scope of the present invention is not limited to the examples.
Example 1
As shown in fig. 1, the method of the present invention specifically includes the following steps:
step S1, a user-defined word bank in the hydraulic engineering field is built, a jieba word is adopted to carry out word segmentation on the hidden danger data set and remove stop words, the part of speech is screened through a TextRank algorithm, and the extracted keywords are used as an input data set, and the specific steps are as follows:
step S11, collecting items of hydraulic engineering hidden danger description sentences 1917 as sample data sets, collecting 7480 items of entries in the hydraulic engineering field, constructing a self-defined word bank in the hydraulic engineering field, adopting jieba word segmentation, segmenting the sample data, and labeling the part of speech, wherein part of the sample data sets are shown in Table 1.
Some entries are as follows: the system comprises a hidden lamp, a ground resistance value, a hidden layer, a hidden pipe, a hidden culvert, a hidden hinge, a hidden room, a hidden beam, a hidden furnace slice, a safety exit lamp outlet, a safety island, a safety valve debugging record, a safety precaution facility, a safety management, a safety grounding, a safety alarm system and the like.
TABLE 1
Step S12, loading the stop word library, and removing words such as "@", "a", "and", etc., which are usually not definite, such as adverb, preposition, and conjunctive words, from the word segmentation result.
And step S13, sorting the importance of the participle by adopting a TextRank algorithm, and extracting the keywords of which the parts of speech are noun (n), verb (v), vernoun (vn) and place name (ns) in the participle.
The final segmentation result as shown in Table 2 is obtained as the input data set through steps S11-S13.
TABLE 2 word segmentation results
Step S2, performing boolean matrix encoding on the input data set obtained in step S1, that is, for each piece of data, if the corresponding item set in the data set is included, the entry set is marked as 1(True), otherwise, the entry set is 0(False), and the specific steps are as follows:
step S21, first, convert the input data set into 1917 × 20 matrix in DataFrame data frame form, where the number of rows is 1917, i.e., number of hidden danger description data, the number of columns is 20, i.e., number of most participles in 1917 data, the jth word in the jth row is the jth keyword of the ith data, if it is Null, and the DataFrame data frame is as shown in table 3.
Table 3DataFrame data box
Step S22, performing unique one-hot encoding on the DataFrame data frame, and converting the DataFrame data frame into a boolean matrix, where the matrix is 1917 × 1139, where the row number is 1917, i.e., the number of hidden danger description data, and the column number is 1139, i.e., the number of all different keywords in the data set, if the i pieces of data include the jth keyword, the value of the jth column in the ith row is 1(True), otherwise, the value is 0 (False). The encoded boolean matrix is shown in table 4.
TABLE 4 Boolean matrix results
Step S3, calculating the support degree of each item set by improving Apriori algorithm, and screening out an item set not less than the minimum support degree as a frequent item set, where the data amount is 1917, and the threshold of the minimum support degree is set to 0.01. The frequent item sets with a length of 3 or more were selected and the results are shown in Table 5.
TABLE 5 frequent itemset results
Through the reflection of frequent item set result, potential safety hazard often appears in places such as the workshop of blending station maintenance, grit processing factory electricity distribution room in the hydraulic engineering safety work progress that this data set corresponds, and the hidden danger problem such as scaffold frame dense mesh drops, cable insulation is ageing, job site personnel wear comparatively frequently appears.
And step S4, performing confidence calculation on the obtained frequent item set, and screening out association rules not less than the minimum confidence, namely strong association rules. Further association rule mining is performed on the frequent item set obtained in step S3 using association _ rules () function, and mining is performed with the confidence as an evaluation value. The lowest confidence is set to 0.8. The strong association rule results are shown in table 6. The confidence of 1 is an absolute association.
Table 6 strong association rule results
Through strong association rule result reflection, in the hydraulic engineering safety work process that this data set corresponds, the hidden danger problem that the dense mesh net of scaffold frame often appears droing, and the personnel of job site often appear wearing relevant problem, and the mix station is the place that the hidden danger is comparatively frequent to take place in the repair shop.
In this embodiment, the beneficial effects of the present invention are specifically shown in: (1) for 1917 pieces of data adopted in this embodiment, automatic word segmentation is realized through machine codes, and word segmentation results are shown in table 2, whereas the phrase extraction technology in the prior art generates words without definite meanings and parts of speech, such as "easily caused", "not required", and "not set", because a custom word stock in the hydraulic engineering field is not introduced and part of speech filtering is not performed, so that the word segmentation quality is reduced, and the accuracy of association rule mining is affected. (2) Based on 1917 pieces of data adopted in the embodiment, the code test is performed through the PyCharm, 0.1587965 seconds are needed for the traditional Apriori algorithm, and 0.0328939 seconds are needed for the improved Apriori algorithm provided by the invention, so that the operation efficiency of the algorithm is greatly improved.
Claims (4)
1. The hydraulic engineering potential safety hazard description association rule mining method based on the improved Apriori algorithm is characterized by comprising the following steps of:
step S1, building a self-defined word bank in the hydraulic engineering field, carrying out word segmentation on the hidden danger data set by adopting jieba word segmentation, removing stop words, screening out the part of speech by a TextRank algorithm, and taking the extracted keywords as an input data set;
step S2, performing Boolean matrix conversion on the input data set obtained in the step S1 based on the one-hot code;
step S3, calculating the support degree of each item set by improving Apriori algorithm, and screening out frequent item sets not less than the minimum support degree;
and step S4, performing confidence calculation on the obtained frequent item set, and screening out a strong association rule not less than the minimum confidence.
2. The hydraulic engineering potential safety hazard description association rule mining method based on the improved Apriori algorithm as claimed in claim 1, wherein the step S1 specifically includes:
step S11, collecting entries in the hydraulic engineering field, constructing a self-defined word bank in the hydraulic engineering field, adopting jieba word segmentation, segmenting the hidden danger data set, and labeling the part of speech;
step S12, loading a stop word bank, and eliminating words which usually have no definite meaning per se, such as mood auxiliary words, adverbs, prepositions, conjunctions and the like in the word segmentation result;
and step S13, sorting the importance of the participles by adopting a TextRank algorithm, and extracting the keywords of which the parts of speech are nouns, verbs, vernouns and place names in the participles to serve as a final input data set.
3. The hydraulic engineering potential safety hazard description association rule mining method based on the improved Apriori algorithm as claimed in claim 2, wherein the step S2 specifically includes:
in step S21, the input data set D is first set to { D ═ D1,D1…,DnAnd converting the matrix into a matrix T in a DataFrame data frame form, wherein the matrix T is in the form of:
wherein n is the number of the hidden danger description data, m is the maximum word segmentation number in n pieces of data, and TijThe j key word of the ith data is Null if the j key word is Null; diFor the ith data in the data set, i.e. the set { T }i1,Ti2,…,Tin}；
Step S22, carrying out one-hot coding on the data frame matrix T, and converting the data frame matrix T into a Boolean matrix M; if I is ═ I1,I2,…,ItThe boolean matrix M is a set of all the different entries in the dataset D, the form of the boolean matrix M being:
where t is the number of all different keywords in the dataset D, MijBoolean value for the ith data to the jth keyword, if DiComprising IjThat is, the ith data contains the jth keyword, then MijIs 1(True), otherwise is 0 (False).
4. The hydraulic engineering potential safety hazard description association rule mining method based on the improved Apriori algorithm as claimed in claim 3, wherein the step S3 specifically comprises:
step S31, before iteration, performing one-time traversal on the Boolean matrix obtained by conversion in the step S22, counting and summing each column in the Boolean matrix respectively, quickly mining a 1-dimensional frequent item set, and deleting a non-frequent item set;
step S32, while iterating, k-1 dimension frequent item set Lk-1Connected to form a k-dimensional candidate set denoted Ck(ii) a Let I1And I2Is Lk-1If k-2 items in the item set are the same, I1、I2Concatenating produces a set of result items, which is a set of candidate items CkOne of them;
step S33, for candidate item set CkPruning, CkIs LkA superset of (c); for Lk-1Each item set T in (1), sequentially traversing CkAnd counting each candidate based on the boolean matrix. After traversing is finished, counting result pairs CkCutting each candidate item set, if the count is less than k, deleting the candidate item set, and simultaneously deleting all item sets containing the item set in the data set; otherwise, reserving and carrying out the next step;
step S34, calculating a support degree (support) for each of the pruned candidate sets, where the support degree formula is:
support(A＝>B)＝P(A∪B)
in the formula: A. b is a set of items consisting of any item in I, namely representing the probability that the data contains each item in the sets of items A and B;
if the support degree of the candidate item set is not less than the minimum support degree, the candidate item set is a k-dimensional frequent item set, and L is addedkOtherwise, deleting the item set and deleting all item sets containing the item set in the data set. And returning to the step S32 after the screening is finished until the k-dimensional frequent item set cannot be found.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210471547.4A CN114756656A (en) | 2022-04-29 | 2022-04-29 | Hydraulic engineering potential safety hazard description association rule mining method based on improved Apriori algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210471547.4A CN114756656A (en) | 2022-04-29 | 2022-04-29 | Hydraulic engineering potential safety hazard description association rule mining method based on improved Apriori algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114756656A true CN114756656A (en) | 2022-07-15 |
Family
ID=82333842
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210471547.4A Pending CN114756656A (en) | 2022-04-29 | 2022-04-29 | Hydraulic engineering potential safety hazard description association rule mining method based on improved Apriori algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114756656A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115794801A (en) * | 2022-12-23 | 2023-03-14 | 东南大学 | Data analysis method for mining chain relation of automatic driving accident cause |
| CN117314154A (en) * | 2023-09-14 | 2023-12-29 | 甘肃电通电力工程设计咨询有限公司 | Construction site intelligent monitoring system and method based on Beidou positioning |
| CN118013955A (en) * | 2024-04-08 | 2024-05-10 | 中国标准化研究院 | Standard information updating method based on association algorithm |
| CN118427181A (en) * | 2024-04-03 | 2024-08-02 | 云启智慧科技有限公司 | Data management system for formulating data standard based on knowledge management |
-
2022
- 2022-04-29 CN CN202210471547.4A patent/CN114756656A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115794801A (en) * | 2022-12-23 | 2023-03-14 | 东南大学 | Data analysis method for mining chain relation of automatic driving accident cause |
| CN115794801B (en) * | 2022-12-23 | 2023-08-15 | 东南大学 | Data analysis method for mining cause chain relation of automatic driving accidents |
| CN117314154A (en) * | 2023-09-14 | 2023-12-29 | 甘肃电通电力工程设计咨询有限公司 | Construction site intelligent monitoring system and method based on Beidou positioning |
| CN117314154B (en) * | 2023-09-14 | 2024-06-04 | 甘肃电通电力工程设计咨询有限公司 | Construction site intelligent monitoring system and method based on Beidou positioning |
| CN118427181A (en) * | 2024-04-03 | 2024-08-02 | 云启智慧科技有限公司 | Data management system for formulating data standard based on knowledge management |
| CN118013955A (en) * | 2024-04-08 | 2024-05-10 | 中国标准化研究院 | Standard information updating method based on association algorithm |
| CN118013955B (en) * | 2024-04-08 | 2024-07-26 | 中国标准化研究院 | Standard information updating method based on association algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114756656A (en) | Hydraulic engineering potential safety hazard description association rule mining method based on improved Apriori algorithm | |
| CN106649260B (en) | Product characteristic structure tree construction method based on comment text mining | |
| CN110502361B (en) | Fine granularity defect positioning method for bug report | |
| CN110825877A (en) | Semantic similarity analysis method based on text clustering | |
| CN104392006A (en) | Event query processing method and device | |
| CN109189820B (en) | Coal mine safety accident ontology concept extraction method | |
| Chi et al. | Establish a patent risk prediction model for emerging technologies using deep learning and data augmentation | |
| CN113157903A (en) | Multi-field-oriented electric power word stock construction method | |
| CN115545671A (en) | Method and system for structured processing of laws and regulations | |
| CN115794798A (en) | Market supervision informationized standard management and dynamic maintenance system and method | |
| CN114265935A (en) | Science and technology project establishment management auxiliary decision-making method and system based on text mining | |
| Kogilavani et al. | Clustering based optimal summary generation using genetic algorithm | |
| CN117827882B (en) | Deep learning-based financial database SQL quality scoring method, system, equipment and storable medium | |
| CN118193716A (en) | Self-updating legal case recommendation system based on large model and rule reasoning | |
| CN109471934B (en) | Financial risk clue mining method based on Internet | |
| CN111062574A (en) | Method for measuring similarity of manufacturing process | |
| CN112329432B (en) | Power distribution network voltage out-of-limit problem correlation analysis method based on improved Apriori | |
| CN113449508A (en) | Internet public opinion correlation deduction prediction analysis method based on event chain | |
| Firdhous | Automating legal research through data mining | |
| CN116738979A (en) | Power grid data searching method and system based on core data identification and electronic equipment | |
| Misu et al. | An exploratory study on interface similarities in code clones | |
| CN116304726A (en) | Material similarity analysis method based on semantic library and knowledge graph | |
| CN114239553A (en) | Log auditing method, device, equipment and medium based on artificial intelligence | |
| CN112488593A (en) | Auxiliary bid evaluation system and method for bidding | |
| CN113064978A (en) | Project construction period rationality judgment method and device based on feature word matching |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |