CN107291697A - A kind of semantic analysis, electronic equipment, storage medium and its diagnostic system - Google Patents
A kind of semantic analysis, electronic equipment, storage medium and its diagnostic system Download PDFInfo
- Publication number
- CN107291697A CN107291697A CN201710518183.XA CN201710518183A CN107291697A CN 107291697 A CN107291697 A CN 107291697A CN 201710518183 A CN201710518183 A CN 201710518183A CN 107291697 A CN107291697 A CN 107291697A
- Authority
- CN
- China
- Prior art keywords
- module
- text
- semantic analysis
- name entity
- extraction
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic 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
- G06F16/35—Clustering; Classification
-
- 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
- G06F16/35—Clustering; Classification
- G06F16/358—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Machine Translation (AREA)
Abstract
A kind of semantic analysis of the present invention, including step Text Pretreatment, text modeling, clustering processing, visualization shows cluster result, the invention further relates to a kind of electronic equipment and computer-readable recording medium, computer program is executed by processor a kind of semantic analysis, the invention further relates to a kind of semantic analysis diagnostic system, including Text Pretreatment module, text modeling module, clustering processing module, visualize display module, safety in production unstructured data is handled by semantic analysis technology, each element category of the big data that will keep the safety in production is concluded, utilize the correlation between each key element of Association Rule Analysis, cluster finds out the potential danger factor, set up the Safety Risk in Production analysis model suitable for hidden troubles removing business datum, control Unsafe behavior, the unsafe condition of thing, the unsafe condition of machine, environmental unsafe factor, the missing of management, by the relation for coordinating man-machine thing endless tube five elementses, reaching prevents and reduces the purpose of industrial accident.
Description
Technical field
The present invention relates to safety in production field, more particularly to a kind of semantic analysis, electronic equipment, storage medium and its
Diagnostic system.
Background technology
Industrial accident hidden danger refers to not meet applicable safety production law, regulation, standard, code and safety in production pipe
The regulation of reason system, or presence may cause the people's of accident generation in production, construction and business activities because of other factorses
Unsafe acts, the unsafe condition of thing, the unsafe condition of machine, environmental unsafe factor, the missing of management.Chemical industry
A high risk industries, with HTHP, it is poisonous and harmful, work continuously, it is multi-point and wide-ranging the characteristics of, easily there is hidden danger.Such as
Fruit can not comprehensively be investigated, takes precautions against control in time to these hidden danger, it will cause occur accident, cause certain loss.Country's peace
Full production supervision management general bureau puts into effect《Temporary provisions are administered in industrial accident hidden troubles removing》, strengthen and hidden troubles removing controlled
The supervision of reason.But enterprise is during hidden troubles removing improvement is carried out, often because hidden troubles removing is not prompt enough and complete
Face, hidden danger information transmission be delayed or the corresponding precautionary measures implement not in time, Control of Hidden progress supervision is not in place, mismanagement
Deng causing occur accident, huge loss caused to people's life and property.
The content of the invention
In order to overcome the deficiencies in the prior art, an object of the present invention is to provide a kind of semantic analysis and its examined
Disconnected system, safety in production unstructured data is handled by semantic analysis technology, and each element category of the big data that will keep the safety in production is returned
Receive, using the correlation between each key element of Association Rule Analysis, cluster finds out the potential danger factor, sets up and is applied to hidden troubles removing industry
The Safety Risk in Production analysis model for data of being engaged in, control Unsafe behavior, the unsafe condition of thing, the dangerous shape of machine
State, environmental unsafe factor, the missing of management, by coordinating the relation of man-machine thing endless tube five elementses, reaching prevents and reduces
The purpose of industrial accident.
The present invention provides a kind of semantic analysis, comprises the following steps：
Text Pretreatment, is pre-processed to text data；
Text modeling, sets up text data model by the text data and is converted into vector, and the vector is passed through into spy
Sample matrix is formed after levying extraction；
Clustering processing, carries out classification processing to the sample matrix, obtains cluster result；
Visualization shows cluster result, and carrying out visualization to the cluster result shows.
Further, it is described pretreatment include participle, part-of-speech tagging, name Entity recognition, discovery neologisms, date recognition,
Digital processing, the name Entity recognition is included using character labeling algorithm identification name entity, and the discovery neologisms include adopting
Neologisms are found with information cross entropy, the name entity includes people, machine, thing, ring, pipe, and the people, machine, thing, ring, pipe are respectively
Personnel, production apparatus, material, environment, management.
Further, the text modeling includes extracting text feature, and construction feature space, text feature assigns power, builds
Similarity matrix, the extraction text feature is extracts the characteristic item of the text data, and the construction feature space is to pass through
Character representation model construction feature space is set up, and the text feature, which assigns power, to be included the characteristic item being assigned using TF-IDF algorithms
Weight.
A kind of semantic analysis, the step text modeling also includes extracting keyword, extracts customizing messages, matching life
Name entity, the extraction keyword is the weight extraction keyword according to the characteristic item, and the extraction customizing messages is extraction
The name entity, the matching name entity is by the keyword and the name Entities Matching.
A kind of electronic equipment, including：Processor；Memory；And program, wherein described program is stored in the storage
In device, and it is configured to by computing device, described program includes being used to perform a kind of above-mentioned semantic analysis.
A kind of computer-readable recording medium, is stored thereon with computer program, and the computer program is held by processor
A kind of above-mentioned semantic analysis of row.
A kind of semantic analysis diagnostic system, including Text Pretreatment module, text modeling module, clustering processing module, can
Depending on changing display module, the Text Pretreatment module pre-processes to text data, and the text modeling module is by the text
Notebook data changes into vector, and by the vector by forming sample matrix after feature extraction, the clustering processing module is to institute
State sample matrix and carry out classification processing, obtain cluster result, the visualization display module carries out visual to the cluster result
Change display.
Further, the Text Pretreatment module includes word-dividing mode, part-of-speech tagging module, name Entity recognition mould
Block, find neologisms modules, date recognition module, digital signal processing module, sentence containing according to word of the word-dividing mode to text
Justice carries out cutting, and entity is named in the part of speech of the part-of-speech tagging module mark institute predicate, the name Entity recognition module identification,
The name entity includes people, machine, thing, ring, pipe, and the people, machine, thing, ring, pipe are respectively personnel, production apparatus, material, ring
Border, management, described to find neologisms module to find the neologisms of the text, the date recognition module recognizes the day of the text
Phase, the digital signal processing module is handled the digital of the text.
Further, the text modeling module includes characteristic extracting module, Feature Weighting module, construction feature spatial mode
Block, structure similarity moment array module, the characteristic extracting module extract the characteristic item of the text, the Feature Weighting module pair
The characteristic item assigns weight, and the construction feature space module builds phase by setting up character representation model construction feature space
The similarity matrix of the text is built like degree matrix module, the text modeling module also includes extracting keyword module, taken out
Take customizing messages module, matching module, the extraction keyword module is described according to the weight extraction keyword of the characteristic item
Extract customizing messages module and extract the name entity, the matching module is by the keyword and the name Entities Matching.
Further, in addition to multi dimensional analysis module and expert opinion module, the multi dimensional analysis module is according to institute
State name entity to analyze the cluster result, the expert opinion module pushes expert opinion.
Compared with prior art, the beneficial effects of the present invention are：
A kind of semantic analysis of the present invention, including step Text Pretreatment, text modeling, clustering processing, visualization are aobvious
Show cluster result, the invention further relates to a kind of electronic equipment and computer-readable recording medium, computer program is held by processor
A kind of semantic analysis of row, builds the invention further relates to a kind of semantic analysis diagnostic system, including Text Pretreatment module, text
Mould module, clustering processing module, visualization display module, safety in production unstructured data is handled by semantic analysis technology,
Each element category of the big data that will keep the safety in production is concluded, and using the correlation between each key element of Association Rule Analysis, cluster is found out potential
Risk factor, set up suitable for hidden troubles removing business datum Safety Risk in Production analysis model, control Unsafe behavior,
The unsafe condition of thing, the unsafe condition of machine, environmental unsafe factor, the missing of management, by coordinating man-machine thing endless tube
The relation of five elementses, reaching prevents and reduces the purpose of industrial accident.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, below with presently preferred embodiments of the present invention and coordinate accompanying drawing describe in detail as after.
The embodiment of the present invention is shown in detail by following examples and its accompanying drawing.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this hair
Bright schematic description and description is used to explain the present invention, does not constitute inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is a kind of semantic analysis flow chart of the invention；
Fig. 2 is a kind of semantic analysis diagnostic system structured flowchart of the invention；
Fig. 3 is entity elements schematic diagram of the invention；
Fig. 4 is entity I and II key element bubble schematic diagram of the invention；
Fig. 5 is certain chemical enterprise incipient fault data of the invention；
Fig. 6 is certain chemical enterprise incipient fault data semantic analysis bubble schematic diagram of the invention；
Fig. 7 takes place frequently phenomenon multi dimensional analysis schematic diagram for certain chemical enterprise hidden danger of the present invention.
Embodiment
Below, with reference to accompanying drawing and embodiment, the present invention is described further, it is necessary to which explanation is, not
Under the premise of afoul, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example.
The present invention provides a kind of semantic analysis, as shown in figure 1, comprising the following steps：
Text Pretreatment, is pre-processed to text data, in one embodiment, it is preferable that pretreatment includes participle, word
Property mark, name Entity recognition, find neologisms, date recognition, digital processing, participle is the implication according to word to the sentence of text
Cutting is carried out, part-of-speech tagging is the part of speech of mark word, names Entity recognition to include using character labeling algorithm identification name entity,
It was found that neologisms include finding neologisms using information cross entropy, it is preferable that name entity includes people, machine, thing, ring, pipe, people, machine,
Thing, ring, pipe are respectively personnel, production apparatus, material, environment, management.
Text modeling, sets up text data model by the text data and is converted into vector, and the vector is passed through into spy
Sample matrix is formed after levying extraction, in one embodiment, it is preferable that text modeling includes extracting text feature, and construction feature is empty
Between, text feature assigns power, builds similarity matrix, extracts text feature to extract the characteristic item of text, construction feature space is
By setting up character representation model construction feature space, character representation model represents non-structured text message with characteristic item,
It is to assign weight to characteristic item that text feature, which assigns power,；Similarity matrix is built to build the similarity moment of description text similarity degree
Battle array；In one embodiment, it is preferable that step text modeling also includes extracting keyword, extracts customizing messages, matches and name real
Body, it is the weight extraction keyword according to characteristic item to extract keyword, extracts customizing messages to extract name entity, matching name
Entity is by keyword and name Entities Matching；Preferably, extracting text feature includes extracting text using information gain method
Characteristic item, construction feature space is included by setting up vector space model construction feature space, and text feature, which assigns power, to be included using
TF-IDF algorithms assign weight to characteristic item.
Clustering processing, carries out classification processing to the sample matrix, cluster result is obtained, in one embodiment, according to text
This similar matrix carries out classification processing to text, obtains cluster result, it is preferable that clustering processing includes using K-means algorithms
Clustering processing is carried out to text.
In one embodiment, it is preferable that also include step clustering after step clustering processing and describe, clustering is retouched
State including reduction feature space dimension and determine cluster number, reduction feature space dimension includes using latent semantic analysis method
The dimension of feature space is reduced, it is determined that cluster number is according to efficiency evaluation method estimation cluster number, efficiency evaluation side
Similar degree in the class ratio approach between class of the method including weighting.
Visualization shows cluster result, in one embodiment, and the result progress visualization to clustering processing is shown, preferably
Ground, visualization shows that cluster result includes the form display cluster result of bubble diagram.
A kind of electronic equipment, including：Processor；Memory；And program, its Program is stored in memory, and
And be configured to by computing device, program includes being used to perform a kind of above-mentioned semantic analysis.
A kind of computer-readable recording medium, is stored thereon with computer program, and computer program is executed by processor
State a kind of semantic analysis.
A kind of semantic analysis diagnostic system, as shown in Fig. 2 at including Text Pretreatment module, text modeling module, cluster
Module, visualization display module are managed, in one embodiment, as shown in figure 3, such as hidden danger of the Text Pretreatment module to chemical enterprise
Data are pre-processed, and text data is changed into vector by text modeling module, and by vector by forming sample after feature extraction
This matrix, it is preferable that Text Pretreatment module includes word-dividing mode, part-of-speech tagging module, name Entity recognition module, discovery newly
Word module, date recognition module, digital signal processing module, word-dividing mode carry out cutting, word to the sentence of text according to the implication of word
Property labeling module mark the part of speech of word, name Entity recognition module identification name entity, as shown in figure 4, name entity include people,
Machine, thing, ring, pipe, people, machine, thing, ring, pipe are respectively personnel, production apparatus, material, environment, management, influence the reality of safety in production
Body I and II key element as shown in table 1, finds neologisms module to find the neologisms of text, date recognition module recognizes the day of text
Phase, digital signal processing module is handled the digital of text, it is preferable that text modeling module includes characteristic extracting module, feature
Assign power module, construction feature space module, build similarity moment array module, characteristic extracting module extracts the characteristic item of text, special
Levy tax power module and weight is assigned to characteristic item, construction feature space module is by setting up character representation model construction feature space, structure
The similarity matrix of similarity matrix module construction text is built, clustering processing module carries out clustering processing to sample matrix, preferably
Ground, text modeling module also includes extracting keyword module, extracts customizing messages module, matching module, extracts keyword module
According to the weight extraction keyword of characteristic item, such as damage, lack, come off, extract customizing messages module and extract name entity, i.e.,
People, machine, thing, ring, five entities of pipe, matching module is by keyword with naming Entities Matching.
The influence safety in production I and II element distribution table of table 1
In one embodiment, it is preferable that also including clustering describing module, clustering describing module includes reduction spy
Levy space dimensionality module and determine cluster number module, reduction feature space dimension module reduces the dimension of feature space, it is determined that
Cluster number module and pass through efficiency evaluation method estimation cluster number.
In one embodiment, as shown in figure 5, visualization display module shows influence safety in production in the form of bubble diagram
Entity I and II key element, as shown in fig. 6, after analyzing the incipient fault data of chemical enterprise, visualization display module is to cluster
The result of processing carries out visualization and shown, visualization display module shows that hidden danger takes place frequently phenomenon, and being damaged in the phenomenon that such as takes place frequently has 23
It is individual, it is preferable that visualization display module includes the result of the form display clustering processing of bubble diagram.
In one embodiment, it is preferable that also including multi dimensional analysis module and expert opinion module, as shown in fig. 7, clicking on
Bubble diagram can associate related hidden danger place, person liable, installations and facilities, and such as 23 in the phenomenon that takes place frequently are damaged with carrying out various dimensions point
Analysis, multi dimensional analysis module is analyzed the result of clustering processing according to name entity, and the damage of such as facilities and equipment accounts for 12,
Including liquid level gauge, lamp, switch, pressure gauge etc., expert opinion module pushes expert opinion, and magnitude damage occurs in such as pushing equipment facility
It is bad, installations and facilities are carried out with the suggestion of special examination.
A kind of semantic analysis of the present invention, including step Text Pretreatment, text modeling, clustering processing, visualization are aobvious
Show cluster result, the invention further relates to a kind of electronic equipment and computer-readable recording medium, computer program is held by processor
A kind of semantic analysis of row, builds the invention further relates to a kind of semantic analysis diagnostic system, including Text Pretreatment module, text
Mould module, clustering processing module, visualization display module, safety in production unstructured data is handled by semantic analysis technology,
Each element category of the big data that will keep the safety in production is concluded, and using the correlation between each key element of Association Rule Analysis, cluster is found out potential
Risk factor, set up suitable for hidden troubles removing business datum Safety Risk in Production analysis model, control Unsafe behavior,
The unsafe condition of thing, the unsafe condition of machine, environmental unsafe factor, the missing of management, by coordinating man-machine thing endless tube
The relation of five elementses, reaching prevents and reduces the purpose of industrial accident.
More than, only presently preferred embodiments of the present invention not makees any formal limitation to the present invention；All one's own professions
The those of ordinary skill of industry can swimmingly implement the present invention shown in by specification accompanying drawing and above；But, it is all that to be familiar with sheet special
Without departing from the scope of the present invention, that is made using disclosed above technology contents is a little by the technical staff of industry
The equivalent variations of variation, modification and evolution, are the equivalent embodiment of the present invention；Meanwhile, all substantial technologicals according to the present invention
Variation, modification and evolution of any equivalent variations made to above example etc., still fall within technical scheme
Within protection domain.
Claims (10)
1. a kind of semantic analysis, it is characterised in that comprise the following steps：
Text Pretreatment, is pre-processed to text data；
Text modeling, sets up text data model by the text data and is converted into vector, and the vector is taken out by feature
Sample matrix is formed after taking；
Clustering processing, carries out classification processing to the sample matrix, obtains cluster result；
Visualization shows cluster result, and carrying out visualization to the cluster result shows.
2. a kind of semantic analysis as claimed in claim 1, it is characterised in that：The pretreatment includes participle, part of speech mark
Note, name Entity recognition, discovery neologisms, date recognition, digital processing, the name Entity recognition include calculating using character labeling
Method identification name entity, the discovery neologisms include finding neologisms using information cross entropy, the name entity include people, machine,
Thing, ring, pipe, the people, machine, thing, ring, pipe are respectively personnel, production apparatus, material, environment, management.
3. a kind of semantic analysis as claimed in claim 1, it is characterised in that：The text modeling includes extracting text spy
Levy, construction feature space, text feature assigns power, build similarity matrix, the extraction text feature is the extraction textual data
According to characteristic item, the construction feature space is that, by setting up character representation model construction feature space, the text feature is assigned
Power includes assigning weight to the characteristic item using TF-IDF algorithms.
4. a kind of semantic analysis as claimed in claim 3, it is characterised in that：The step text modeling also includes extracting
Keyword, extraction customizing messages, matching name entity, the extraction keyword are the weight extraction key according to the characteristic item
Word, the extraction customizing messages is extracts the name entity, and the matching name entity is by the keyword and the life
Name Entities Matching.
5. a kind of electronic equipment, it is characterised in that including：Processor；Memory；And program, wherein described program is stored in
In the memory, and it is configured to by computing device, described program includes being used for perform claim requirement 1-4 any one
Described method.
6. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that：The computer program quilt
Method of the computing device as described in claim 1-4 any one.
7. a kind of semantic analysis diagnostic system, it is characterised in that：At Text Pretreatment module, text modeling module, cluster
Module, visualization display module are managed, the Text Pretreatment module is pre-processed to text data, the text modeling module
The text data is changed into vector, and by the vector by forming sample matrix, the clustering processing after feature extraction
Module carries out classification processing to the sample matrix, obtains cluster result, the visualization display module is to the cluster result
Visualization is carried out to show.
8. a kind of semantic analysis diagnostic system as claimed in claim 7, it is characterised in that：The Text Pretreatment module includes
Word-dividing mode, part-of-speech tagging module, name Entity recognition module, discovery neologisms module, date recognition module, digital processing mould
Block, the word-dividing mode carries out cutting to the sentence of text according to the implication of word, the part-of-speech tagging module mark institute predicate
Part of speech, name Entity recognition module identification name entity, the name entity includes people, machine, thing, ring, pipe, the people,
Machine, thing, ring, pipe are respectively personnel, production apparatus, material, environment, management, and the discovery neologisms module is the discovery text
Neologisms, the date recognition module recognizes the date of the text, and the digital signal processing module enters to the numeral of the text
Row processing.
9. a kind of semantic analysis diagnostic system as claimed in claim 8, it is characterised in that：The text modeling module includes spy
Levy extraction module, Feature Weighting module, construction feature space module, structure similarity moment array module, the characteristic extracting module
The characteristic item of the text is extracted, the Feature Weighting module assigns weight, the construction feature space module to the characteristic item
By setting up character representation model construction feature space, the similarity matrix of text described in similarity matrix module construction is built,
The text modeling module also includes extracting keyword module, extracts customizing messages module, matching module, the extraction keyword
Module is according to the weight extraction keyword of the characteristic item, and the extraction customizing messages module extracts the name entity, described
Matching module is by the keyword and the name Entities Matching.
10. a kind of semantic analysis diagnostic system as claimed in claim 8, it is characterised in that：Also include multi dimensional analysis module
With expert opinion module, the multi dimensional analysis module is analyzed the cluster result according to the name entity, described
Expert opinion module pushes expert opinion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710518183.XA CN107291697A (en) | 2017-06-29 | 2017-06-29 | A kind of semantic analysis, electronic equipment, storage medium and its diagnostic system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710518183.XA CN107291697A (en) | 2017-06-29 | 2017-06-29 | A kind of semantic analysis, electronic equipment, storage medium and its diagnostic system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107291697A true CN107291697A (en) | 2017-10-24 |
Family
ID=60098591
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710518183.XA Pending CN107291697A (en) | 2017-06-29 | 2017-06-29 | A kind of semantic analysis, electronic equipment, storage medium and its diagnostic system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107291697A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107918644A (en) * | 2017-10-31 | 2018-04-17 | 北京锐思爱特咨询股份有限公司 | News subject under discussion analysis method and implementation system in reputation Governance framework |
| CN107943965A (en) * | 2017-11-27 | 2018-04-20 | 福建中金在线信息科技有限公司 | Similar article search method and device |
| CN108227564A (en) * | 2017-12-12 | 2018-06-29 | 深圳和而泰数据资源与云技术有限公司 | A kind of information processing method, terminal and computer-readable medium |
| CN109241295A (en) * | 2018-08-31 | 2019-01-18 | 北京天广汇通科技有限公司 | A kind of extracting method of special entity relationship in unstructured data |
| CN109657056A (en) * | 2018-11-14 | 2019-04-19 | 金色熊猫有限公司 | Target sample acquisition methods, device, storage medium and electronic equipment |
| CN109995605A (en) * | 2018-01-02 | 2019-07-09 | 中国移动通信有限公司研究院 | A kind of method for recognizing flux and device and computer readable storage medium |
| CN110532298A (en) * | 2019-08-07 | 2019-12-03 | 北京交通大学 | More attribute railway accident reason weight analysis methods |
| CN111275574A (en) * | 2020-01-16 | 2020-06-12 | 国家电网有限公司 | Semantic analysis-based electric power accident risk early warning method and system |
| CN111291562A (en) * | 2020-01-17 | 2020-06-16 | 中国石油集团安全环保技术研究院有限公司 | Intelligent semantic recognition method based on HSE |
| CN111680516A (en) * | 2020-06-04 | 2020-09-18 | 宁波浙大联科科技有限公司 | PDM system product design requirement information semantic analysis and extraction method and system |
| CN112364627A (en) * | 2020-10-23 | 2021-02-12 | 北京建筑大学 | Safety production accident analysis method and device based on text mining, electronic equipment and storage medium |
| CN112613729A (en) * | 2020-12-19 | 2021-04-06 | 前海飞算科技(深圳)有限公司 | Default risk big data visualization method and device and storage medium |
| CN113449509A (en) * | 2021-08-05 | 2021-09-28 | 湖南特能博世科技有限公司 | Text analysis method and device and computer equipment |
| CN115630161A (en) * | 2022-12-20 | 2023-01-20 | 航天神舟智慧系统技术有限公司 | Intelligent analysis and diagnosis method and system for hidden danger big data |
| CN117807404A (en) * | 2024-02-29 | 2024-04-02 | 智广海联(天津)大数据技术有限公司 | AI-based intelligent duplicate removal analysis method and device for studying and judging event |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100017390A1 (en) * | 2008-07-16 | 2010-01-21 | Kabushiki Kaisha Toshiba | Apparatus, method and program product for presenting next search keyword |
| CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
| CN104133916A (en) * | 2014-08-14 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | Search result information organizational method and device |
| CN104408033A (en) * | 2014-11-25 | 2015-03-11 | 中国人民解放军国防科学技术大学 | Text message extracting method and system |
-
2017
- 2017-06-29 CN CN201710518183.XA patent/CN107291697A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100017390A1 (en) * | 2008-07-16 | 2010-01-21 | Kabushiki Kaisha Toshiba | Apparatus, method and program product for presenting next search keyword |
| CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
| CN104133916A (en) * | 2014-08-14 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | Search result information organizational method and device |
| CN104408033A (en) * | 2014-11-25 | 2015-03-11 | 中国人民解放军国防科学技术大学 | Text message extracting method and system |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107918644B (en) * | 2017-10-31 | 2020-12-08 | 北京锐思爱特咨询股份有限公司 | News topic analysis method and implementation system in reputation management framework |
| CN107918644A (en) * | 2017-10-31 | 2018-04-17 | 北京锐思爱特咨询股份有限公司 | News subject under discussion analysis method and implementation system in reputation Governance framework |
| CN107943965A (en) * | 2017-11-27 | 2018-04-20 | 福建中金在线信息科技有限公司 | Similar article search method and device |
| CN108227564B (en) * | 2017-12-12 | 2020-07-21 | 深圳和而泰数据资源与云技术有限公司 | Information processing method, terminal and computer readable medium |
| CN108227564A (en) * | 2017-12-12 | 2018-06-29 | 深圳和而泰数据资源与云技术有限公司 | A kind of information processing method, terminal and computer-readable medium |
| CN109995605B (en) * | 2018-01-02 | 2021-04-13 | 中国移动通信有限公司研究院 | Flow identification method and device and computer readable storage medium |
| CN109995605A (en) * | 2018-01-02 | 2019-07-09 | 中国移动通信有限公司研究院 | A kind of method for recognizing flux and device and computer readable storage medium |
| CN109241295A (en) * | 2018-08-31 | 2019-01-18 | 北京天广汇通科技有限公司 | A kind of extracting method of special entity relationship in unstructured data |
| CN109241295B (en) * | 2018-08-31 | 2021-12-24 | 北京天广汇通科技有限公司 | Method for extracting specific entity relation in unstructured data |
| CN109657056A (en) * | 2018-11-14 | 2019-04-19 | 金色熊猫有限公司 | Target sample acquisition methods, device, storage medium and electronic equipment |
| CN110532298A (en) * | 2019-08-07 | 2019-12-03 | 北京交通大学 | More attribute railway accident reason weight analysis methods |
| CN111275574A (en) * | 2020-01-16 | 2020-06-12 | 国家电网有限公司 | Semantic analysis-based electric power accident risk early warning method and system |
| CN111291562A (en) * | 2020-01-17 | 2020-06-16 | 中国石油集团安全环保技术研究院有限公司 | Intelligent semantic recognition method based on HSE |
| CN111291562B (en) * | 2020-01-17 | 2024-05-03 | 中国石油天然气集团有限公司 | Intelligent semantic recognition method based on HSE |
| CN111680516A (en) * | 2020-06-04 | 2020-09-18 | 宁波浙大联科科技有限公司 | PDM system product design requirement information semantic analysis and extraction method and system |
| CN112364627B (en) * | 2020-10-23 | 2023-07-25 | 北京建筑大学 | Text mining-based safety production accident analysis method and device, electronic equipment and storage medium |
| CN112364627A (en) * | 2020-10-23 | 2021-02-12 | 北京建筑大学 | Safety production accident analysis method and device based on text mining, electronic equipment and storage medium |
| CN112613729A (en) * | 2020-12-19 | 2021-04-06 | 前海飞算科技(深圳)有限公司 | Default risk big data visualization method and device and storage medium |
| CN113449509A (en) * | 2021-08-05 | 2021-09-28 | 湖南特能博世科技有限公司 | Text analysis method and device and computer equipment |
| CN115630161A (en) * | 2022-12-20 | 2023-01-20 | 航天神舟智慧系统技术有限公司 | Intelligent analysis and diagnosis method and system for hidden danger big data |
| CN117807404A (en) * | 2024-02-29 | 2024-04-02 | 智广海联(天津)大数据技术有限公司 | AI-based intelligent duplicate removal analysis method and device for studying and judging event |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107291697A (en) | A kind of semantic analysis, electronic equipment, storage medium and its diagnostic system | |
| CN107066446B (en) | Logic rule embedded cyclic neural network text emotion analysis method | |
| JPWO2012132388A1 (en) | Text analysis apparatus, problem behavior extraction method, and problem behavior extraction program | |
| Hecking et al. | Can topic models be used in research evaluations? Reproducibility, validity, and reliability when compared with semantic maps | |
| CN114416939A (en) | Intelligent question and answer method, device, equipment and storage medium | |
| CN115210705A (en) | Vector embedding model for relational tables with invalid or equivalent values | |
| CN116719683A (en) | Abnormality detection method, abnormality detection device, electronic apparatus, and storage medium | |
| Dey | Growing importance of machine learning in compliance and regulatory reporting | |
| Khritankov et al. | Discovering text reuse in large collections of documents: A study of theses in history sciences | |
| CN116383406A (en) | Enterprise portrait generation method, computer device and computer readable storage medium | |
| Schirmer et al. | A new dataset for topic-based paragraph classification in genocide-related court transcripts | |
| Najeeb | Towards a deep leaning-based approach for hadith classification | |
| Al-Obeidat et al. | Twitter sentiment analysis to understand students' perceptions about online learning during the Covid'19 | |
| Hamad et al. | Sentiment analysis of restaurant reviews in social media using naïve bayes | |
| CN114492437A (en) | Keyword recognition method and device, electronic equipment and storage medium | |
| Lai et al. | An unsupervised approach to discover media frames | |
| CN114547321A (en) | Knowledge graph-based answer generation method and device and electronic equipment | |
| Hettiarachchi et al. | SPARCL: An improved approach for matching Sinhalese words and names in record clustering and linkage | |
| Lin et al. | Design and implementation of intelligent scoring system for handwritten short answer based on deep learning | |
| CN112287215A (en) | Intelligent employment recommendation method and device | |
| WO2014188555A1 (en) | Text processing device and text processing method | |
| De et al. | Unsupervised clustering technique to harness ideas from an Ideas Portal | |
| Ding et al. | Handwritten and printed text distinction by using stroke thickness features | |
| Kamada et al. | Recommendation system of grants-in-aid for researchers by using jsps keyword | |
| Modarresi et al. | Generalized variable conversion using k-means clustering and web scraping |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171024 |
|
| RJ01 | Rejection of invention patent application after publication |