CN110059319A - A kind of piping lane failure analysis methods based on key words co-occurrence - Google Patents
A kind of piping lane failure analysis methods based on key words co-occurrence Download PDFInfo
- Publication number
- CN110059319A CN110059319A CN201910323713.4A CN201910323713A CN110059319A CN 110059319 A CN110059319 A CN 110059319A CN 201910323713 A CN201910323713 A CN 201910323713A CN 110059319 A CN110059319 A CN 110059319A
- Authority
- CN
- China
- Prior art keywords
- keyword
- occurrence
- words
- key words
- word
- 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.)
- Granted
Links
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
- G06F16/338—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/247—Thesauruses; Synonyms
-
- 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)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of piping lane failure analysis methods based on key words co-occurrence, comprising the following steps: step 1: building is based on universaling dictionary and covers the Custom Dictionaries of piping lane industry proper noun and technical term；Step 2: after obtaining fault message, fault message pretreatment is carried out to the fault message；Step 3: after obtaining set of words, keyword selection is carried out for the set of words；Step 4: it after carrying out word cloud visualization to keyword, forms key words co-occurrence matrix and visualizes the key words co-occurrence matrix.The present invention has found failure keyword by the means of Custom Dictionaries, word frequency statistics, and is shown by the visualization of keyword word cloud；Key words co-occurrence network is further constructed, and optimization is laid out using figure placement algorithm, to reach the analysis and intuitive displaying to fault message.
Description
Technical field
The present invention relates to a kind of piping lane failure analysis methods based on key words co-occurrence.
Background technique
Text analysis technique refers to the expression to text and its selection of characteristic item, is text mining, in information retrieval
Basic problem.The information that the computer that structureless urtext is converted into structuring can be identified and be handled by it, to build
Vertical mathematical model describes and replaces text, final to realize the purpose that effective information is excavated from a large amount of texts.Key words co-occurrence
Network analysis is also Co-word analysis, is a kind of text content analysis technology, its word in the same text subject by analysis
Or the form that noun phrase occurs jointly, disclose keyword between close and distant relation, the co-occurrence frequency is higher, illustrate two keywords it
Between correlation it is stronger.
Figure placement algorithm is the algorithm for solving the problems such as layout in extensive node connection figure is mixed and disorderly, readable poor.Power is led
Drawing placement algorithm is its classical way, and main thought is that entire topological diagram is regarded as to a physical system, is deposited between adjacent vertex
There are repulsion between gravitation, non-conterminous vertex, iterate to calculate the resultant force that vertex is subject to every time, and move vertex according to resultant force,
Whole system is finally set to reach the minimum of an energy.Guiding placement algorithm by traditional power can produce side length and vertex
The figure layout result for meeting Aesthetic Standards of distribution uniform, representative algorithm have the FR of Fruchterman et al.
(Fruchterman-Reingold) algorithm.
Effective use, the class that manager usually can not rapidly to piping lane failure is not yet received in existing piping lane fault message
The contents such as type, place are judged, the specific aim service work to piping lane, therefore the trouble hunting work of piping lane can not be effectively carried out
Make gradually to be checked it is generally necessary to employ a large amount of staff, takes time and effort, leverage working efficiency, improve enterprise
The cost of industry.
Summary of the invention
The purpose of the present invention is exactly to provide a kind of piping lane failure based on key words co-occurrence to solve the above-mentioned problems
Analysis method can analyze fault message and intuitively be shown.
The object of the present invention is achieved like this:
A kind of piping lane failure analysis methods based on key words co-occurrence of the invention, comprising the following steps:
Step 1: construct based on universaling dictionary and cover the custom words of piping lane industry proper noun and technical term
Allusion quotation；
Step 2: after obtaining fault message, fault message pretreatment, fault message pretreatment are carried out to the fault message
Include:
S2.1: fault message duplicate removal: if including Chinese information and english information in fault message, by Chinese information and English
Duplicate removal is compared in literary information, and records to the fault message after duplicate removal；
S2.2: it generates set of words: in Custom Dictionaries, the fault message after the duplicate removal recorded in S2.1 being utilized and is divided
Word algorithm is segmented and is removed stop words, will be segmented and is removed the fault message after stop words and generates set of words；
Step 3: after obtaining set of words, keyword selection is carried out for the set of words, keyword selection includes:
S3.1: word frequency statistics: for the set of words generated in S2.2, count each word in the set of words and its
Word frequency；
S3.2: synonym merge: in the set of words in S3.1 word and its word frequency carry out synonym merging, and
The word frequency of combined synonym is added；
S3.3: keyword is chosen: M before word frequency ranking is chosen in the set of words after synonym merges in S3.2
Word as keyword, wherein M is the quantity that positive integer and M are less than or equal to the keyword；
S3.4: word cloud visualization the visualization of keyword word cloud: is carried out for the keyword that S3.3 is selected；
Step 4: after carrying out word cloud visualization to keyword, key words co-occurrence matrix is formed and by the key words co-occurrence
Matrix visualization, comprising:
S4.1: initialization co-occurrence matrix: indicating the quantity of the keyword selected in S3.3 with N, constructs (N+1) * (N+1)
Key words co-occurrence matrix, and by the first trip of the key words co-occurrence matrix and first be initialized as the keyword chosen in S3.3；
S4.2: key words co-occurrence frequency statistics: by each keyword of first trip in the key words co-occurrence matrix in S4.1 point
It is not matched with first each keyword, forms keyword pair, the word collection after synonym merges in S3.2
The frequency of occurrence of keyword pair is counted in conjunction, and frequency of occurrence one-to-one correspondence geo-statistic is entered into the key words co-occurrence square in S4.1
In battle array；
S4.3: keyword the visualization of key words co-occurrence matrix: will have been counted in S4.2 to the key words co-occurrence of frequency of occurrence
Matrix is visualized；The visual mode of key words co-occurrence matrix is to form key words co-occurrence network；Key words co-occurrence network
Including several nodes, each node respectively represents the keyword chosen in a S3.3, is carried out between each node by nonoriented edge
Connection is to express the relationship between the keyword pair in S4.2, the shade and thickness of nonoriented edge and the appearance frequency of the keyword pair
It is secondary directly proportional；Each size of node is directly proportional to the node degree of the node；
Step 5: finally according to the shade and thickness of size of node and/or nonoriented edge to piping lane failure carry out by
One determines investigation.
Above-mentioned a kind of piping lane failure analysis methods based on key words co-occurrence, wherein keyword word cloud is carried out in S3.4
When visualization, the size of keyword and the word frequency of the keyword are directly proportional.
Above-mentioned a kind of piping lane failure analysis methods based on key words co-occurrence, wherein also for key words co-occurrence network
Optimization will be laid out by figure placement algorithm.
Above-mentioned a kind of piping lane failure analysis methods based on key words co-occurrence, wherein figure placement algorithm is that power guiding is calculated
Method.
Above-mentioned a kind of piping lane failure analysis methods based on key words co-occurrence, wherein power guidance algorithm is
Fruchterman-Reingold algorithm.
The present invention is based on the piping lane failure analysis methods of key words co-occurrence to pass through Custom Dictionaries, the means hair of word frequency statistics
Existing failure keyword, and be shown by the visualization of keyword word cloud；Key words co-occurrence network is further constructed, and is used
Figure placement algorithm is laid out optimization, to reach the analysis and intuitive displaying to fault message.
Detailed description of the invention
Fig. 1 is a kind of flow chart of piping lane failure analysis methods based on key words co-occurrence of the invention；
Fig. 2 is the key words co-occurrence network that key words co-occurrence matrix is formed after visualization step in S4.3 of the invention
Schematic diagram；
Fig. 3 is the schematic diagram of key words co-occurrence network of the invention after layout optimization.
Specific embodiment
Below in conjunction with attached drawing, the invention will be further described.
It please refers to Fig.1 to Fig.3, the piping lane failure analysis methods the present invention is based on key words co-occurrence is shown in figure, including
Following steps:
Step 1: construct based on universaling dictionary and cover the custom words of piping lane industry proper noun and technical term
Allusion quotation；
Step 2: after obtaining fault message, fault message pretreatment, fault message pretreatment are carried out to the fault message
Include:
S2.1: fault message duplicate removal: if including Chinese information and english information in fault message, by Chinese information and English
Duplicate removal is compared in literary information, and records to the fault message after duplicate removal；
S2.2: it generates set of words: in Custom Dictionaries, segmentation methods being utilized to the fault message after duplicate removal in S2.1
Stop words is segmented and removed, will segment and remove the fault message after stop words and generate set of words；
Step 3: after obtaining set of words, keyword selection is carried out for the set of words, keyword selection includes:
S3.1: word frequency statistics: for the set of words generated in S2.2, count each word in the set of words and its
Word frequency；
S3.2: synonym merge: in the set of words in S3.1 word and its word frequency carry out synonym merging, and
The word frequency of combined synonym is added；
S3.3: keyword is chosen: M before word frequency ranking is chosen in the set of words after synonym merges in S3.2
Word as keyword, wherein M is the quantity that positive integer and M are less than or equal to the keyword；
S3.4: the visualization of keyword word cloud: word cloud visualization is carried out for the keyword that S3.3 is selected, the pass after visualization
The size of keyword and the word frequency of the keyword are directly proportional；
Step 4: after carrying out word cloud visualization to keyword, key words co-occurrence matrix is formed and by the key words co-occurrence
Matrix visualization, comprising the following steps:
S4.1: initialization co-occurrence matrix: indicating the keyword quantity selected in S3.3 with N, building (N+1) * (N+1)
Key words co-occurrence matrix, and the first trip of the key words co-occurrence matrix is initialized as the keyword chosen in S3.3 with first；
S4.2: key words co-occurrence frequency statistics: by each keyword of first trip in the key words co-occurrence matrix in S4.1 point
It is not matched with first each keyword, forms keyword pair, in the set of words that S3.2 carries out after synonym merging
The frequency of occurrence of keyword pair is counted, and frequency of occurrence one-to-one correspondence geo-statistic is entered into the key words co-occurrence matrix in S4.1
In；
S4.3: keyword the visualization of key words co-occurrence matrix: will have been counted in S4.2 to the key words co-occurrence of frequency of occurrence
Matrix is visualized；The visual mode of key words co-occurrence matrix is to form key words co-occurrence network；Key words co-occurrence network
Including several nodes, each node respectively represents the keyword chosen in a S3.3, is carried out between each node by nonoriented edge
Connection is to express the relationship between the keyword pair in S4.2, the shade and thickness of nonoriented edge and the appearance frequency of the keyword pair
It is secondary directly proportional；Each size of node is directly proportional to the node degree of the node；Key words co-occurrence network will pass through after being formed
Fruchterman-Reingold algorithm is laid out optimization；
Finally according to the shade and thickness of the size of node and/or the nonoriented edge to piping lane failure carry out by
One determines；When determining, first all nodes can be ranked up according to size, chosen, chosen first most from big to small
Big node, such as " pipeline " in Fig. 2, then by the nonoriented edge being connect with the node according to shade and line weight into
Row sequence is chosen, get colors the most thick nonoriented edge of most deep and lines first, later to this from coarse to fine from depth to shallow
The keyword that nonoriented edge is connected into carry out breakdown judge, such as Fig. 2 in " pipeline " and " getting rusty " this keyword pair, if
Investigation finds that the keyword to non-failure point, then gradually checks remaining keyword pair according to the method described above.
The present invention has found failure keyword by the means of Custom Dictionaries, word frequency statistics, and can by keyword word cloud
It is shown depending on changing；Key words co-occurrence network is further constructed, and optimization is laid out using figure placement algorithm, failure is believed
Breath is intuitively shown, and is carried out by the shade and line weight of size of node and/or nonoriented edge to fault message
Judge and carries out subsequent investigation.
Above embodiments are used for illustrative purposes only, rather than limitation of the present invention, the technology people in relation to technical field
Member, without departing from the spirit and scope of the present invention, can also make various transformation or modification, therefore all equivalent
Technical solution also should belong to scope of the invention, should be limited by each claim.
Claims (5)
1. a kind of piping lane failure analysis methods based on key words co-occurrence, which is characterized in that the piping lane failure analysis methods packet
Include following steps:
Step 1: construct based on universaling dictionary and cover the Custom Dictionaries of piping lane industry proper noun and technical term；
Step 2: after obtaining fault message, fault message pretreatment, the fault message pretreatment are carried out to the fault message
Include:
S2.1: fault message duplicate removal: if including Chinese information and english information in the fault message, by Chinese information and English
Duplicate removal is compared in literary information, and records to the fault message after duplicate removal；
S2.2: it generates set of words: in the Custom Dictionaries, the fault message after the duplicate removal recorded in S2.1 being utilized and is divided
Word algorithm is segmented and is removed stop words, will be segmented and is removed the fault message after stop words and generates set of words；
Step 3: after obtaining the set of words, keyword selection is carried out for the set of words, the keyword chooses packet
It includes:
S3.1: for the set of words generated in S2.2, each word and its word in the set of words word frequency statistics: are counted
Frequently；
S3.2: synonym merges: in the set of words in S3.1 word and its word frequency carry out synonym merging, and pairing
And the word frequency of synonym be added；
S3.3: keyword is chosen: the word of M before word frequency ranking is chosen in the set of words after synonym merges in S3.2
Language is as keyword, and wherein M is the quantity that positive integer and M are less than or equal to the keyword；
S3.4: word cloud visualization the visualization of keyword word cloud: is carried out for the keyword that S3.3 is selected；
Step 4: after carrying out word cloud visualization to keyword, key words co-occurrence matrix is formed and by the key words co-occurrence matrix
Visualization, comprising:
S4.1: initialization co-occurrence matrix: indicating the quantity of the keyword selected in S3.3 with N, constructs the pass of (N+1) * (N+1)
Keyword co-occurrence matrix, and the first trip of the key words co-occurrence matrix is initialized as the keyword chosen in S3.3 with first；
S4.2: key words co-occurrence frequency statistics: by each keyword of first trip in the key words co-occurrence matrix in S4.1 respectively with
First each keyword is matched, formation keyword pair, in the set of words after synonym merges in S3.2
The frequency of occurrence of the keyword pair is counted, and frequency of occurrence one-to-one correspondence geo-statistic is entered into the key words co-occurrence square in S4.1
In battle array；
S4.3: keyword the visualization of key words co-occurrence matrix: will have been counted in S4.2 to the key words co-occurrence matrix of frequency of occurrence
It is visualized；The visual mode of key words co-occurrence matrix is to form key words co-occurrence network；The key words co-occurrence
Network includes several nodes, and each node respectively represents the keyword chosen in a S3.3, is led between each node
Nonoriented edge is crossed to be attached to express the relationship between the keyword pair in S4.2, the shade and thickness of the nonoriented edge with should
The frequency of occurrence of keyword pair is directly proportional；Each size of node is directly proportional to the node degree of the node；
Step 5: finally according to the shade and thickness of the size of node and/or the nonoriented edge to piping lane failure into
Row determines investigation one by one.
2. a kind of piping lane failure analysis methods based on key words co-occurrence as described in claim 1, which is characterized in that described
When carrying out the visualization of keyword word cloud in S3.4, the size of keyword and the word frequency of the keyword are directly proportional.
3. a kind of piping lane failure analysis methods based on key words co-occurrence as claimed in claim 2, which is characterized in that be directed to institute
Optimization will be also laid out by figure placement algorithm by stating key words co-occurrence network.
4. a kind of piping lane failure analysis methods based on key words co-occurrence as claimed in claim 3, which is characterized in that the figure
Placement algorithm is power guidance algorithm.
5. a kind of piping lane failure analysis methods based on key words co-occurrence as claimed in claim 4, which is characterized in that the power
Guidance algorithm is Fruchterman-Reingold algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910323713.4A CN110059319B (en) | 2019-04-22 | 2019-04-22 | Pipe gallery fault analysis method based on keyword co-occurrence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910323713.4A CN110059319B (en) | 2019-04-22 | 2019-04-22 | Pipe gallery fault analysis method based on keyword co-occurrence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110059319A true CN110059319A (en) | 2019-07-26 |
| CN110059319B CN110059319B (en) | 2022-11-18 |
Family
ID=67320030
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910323713.4A Active CN110059319B (en) | 2019-04-22 | 2019-04-22 | Pipe gallery fault analysis method based on keyword co-occurrence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110059319B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110427290A (en) * | 2019-08-09 | 2019-11-08 | 上海天诚通信技术股份有限公司 | A kind of computer room Fault Locating Method |
| CN111078864A (en) * | 2019-12-24 | 2020-04-28 | 国网山东省电力公司电力科学研究院 | Knowledge graph-based information security system |
| CN112199926A (en) * | 2020-10-16 | 2021-01-08 | 中国地质大学（武汉） | Geological report text visualization method based on text mining and natural language processing |
| CN115796172A (en) * | 2023-02-08 | 2023-03-14 | 广东粤港澳大湾区硬科技创新研究院 | Fault case recommendation method, device and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100145939A1 (en) * | 2008-12-05 | 2010-06-10 | Yahoo! Inc. | Determining related keywords based on lifestream feeds |
| CN103744951A (en) * | 2014-01-02 | 2014-04-23 | 上海大学 | Method for ordering significance of keywords in text |
| CN104766250A (en) * | 2015-04-30 | 2015-07-08 | 上海化学工业区公共管廊有限公司 | Risk factor weight value calculation method for pipe of pipe gallery |
| CN105677833A (en) * | 2016-01-06 | 2016-06-15 | 云南电网有限责任公司电力科学研究院 | Method for extracting circuit breaker fault characteristic information on basis of text mining technology |
| CN108304382A (en) * | 2018-01-25 | 2018-07-20 | 山东大学 | Mass analysis method based on manufacturing process text data digging and system |
| CN109240258A (en) * | 2018-07-09 | 2019-01-18 | 上海万行信息科技有限公司 | Vehicle failure intelligent auxiliary diagnosis method and system based on term vector |
-
2019
- 2019-04-22 CN CN201910323713.4A patent/CN110059319B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100145939A1 (en) * | 2008-12-05 | 2010-06-10 | Yahoo! Inc. | Determining related keywords based on lifestream feeds |
| CN103744951A (en) * | 2014-01-02 | 2014-04-23 | 上海大学 | Method for ordering significance of keywords in text |
| CN104766250A (en) * | 2015-04-30 | 2015-07-08 | 上海化学工业区公共管廊有限公司 | Risk factor weight value calculation method for pipe of pipe gallery |
| CN105677833A (en) * | 2016-01-06 | 2016-06-15 | 云南电网有限责任公司电力科学研究院 | Method for extracting circuit breaker fault characteristic information on basis of text mining technology |
| CN108304382A (en) * | 2018-01-25 | 2018-07-20 | 山东大学 | Mass analysis method based on manufacturing process text data digging and system |
| CN109240258A (en) * | 2018-07-09 | 2019-01-18 | 上海万行信息科技有限公司 | Vehicle failure intelligent auxiliary diagnosis method and system based on term vector |
Non-Patent Citations (3)
| Title |
|---|
| JIAWEN DENG: ""Text Classification with Keywords and Co-occurred Words in Two-stream Neural Network"", 《2018 5TH IEEE INTERNATIONAL CONFERENCE ON CLOUD COMPUTING AND INTELLIGENCE SYSTEMS (CCIS)》 * |
| 丁志浩等: ""公共管廊管道的风险评价方法研究"", 《石油化工自动化》 * |
| 马慧芳等: ""基于加权超图随机游走的文献关键词提取算法"", 《电子学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110427290A (en) * | 2019-08-09 | 2019-11-08 | 上海天诚通信技术股份有限公司 | A kind of computer room Fault Locating Method |
| CN111078864A (en) * | 2019-12-24 | 2020-04-28 | 国网山东省电力公司电力科学研究院 | Knowledge graph-based information security system |
| CN112199926A (en) * | 2020-10-16 | 2021-01-08 | 中国地质大学（武汉） | Geological report text visualization method based on text mining and natural language processing |
| CN112199926B (en) * | 2020-10-16 | 2024-05-10 | 中国地质大学（武汉） | Geological report text visualization method based on text mining and natural language processing |
| CN115796172A (en) * | 2023-02-08 | 2023-03-14 | 广东粤港澳大湾区硬科技创新研究院 | Fault case recommendation method, device and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110059319B (en) | 2022-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110059319A (en) | A kind of piping lane failure analysis methods based on key words co-occurrence | |
| Zhang et al. | Sentiment analysis of Chinese micro-blog text based on extended sentiment dictionary | |
| CN102722709B (en) | Method and device for identifying garbage pictures | |
| CN106503148B (en) | A kind of table entity link method based on multiple knowledge base | |
| CN109871451A (en) | A kind of Relation extraction method and system incorporating dynamic term vector | |
| CN105389341B (en) | A kind of service calls repeat the text cluster and analysis method of incoming call work order | |
| CN107566376A (en) | One kind threatens information generation method, apparatus and system | |
| Einasto et al. | Sdss dr7 superclusters-morphology | |
| CN107273350A (en) | A kind of information processing method and its device for realizing intelligent answer | |
| CN108133045A (en) | Keyword extracting method and system, keyword extraction model generating method and system | |
| CN106599029A (en) | Chinese short text clustering method | |
| CN110362678A (en) | A kind of method and apparatus automatically extracting Chinese text keyword | |
| CN103699525A (en) | Method and device for automatically generating abstract on basis of multi-dimensional characteristics of text | |
| CN107239512B (en) | A kind of microblogging comment spam recognition methods of combination comment relational network figure | |
| CN105653518A (en) | Specific group discovery and expansion method based on microblog data | |
| CN105630884A (en) | Geographic position discovery method for microblog hot event | |
| CN108763212A (en) | A kind of address information extraction method and device | |
| CN110287329A (en) | A kind of electric business classification attribute excavation method based on commodity text classification | |
| CN104408033A (en) | Text message extracting method and system | |
| Alian et al. | Arabic semantic similarity approaches-review | |
| CN106445911A (en) | Anaphora resolution method and system based on microscopic topic structure | |
| CN104281565A (en) | Semantic dictionary constructing method and device | |
| Lu et al. | A semi-automatic approach to detect structural components from CAD drawings for constructing as-is BIM objects | |
| CN102779119A (en) | Method and device for extracting keywords | |
| Claster et al. | Unsupervised artificial neural nets for modeling movie sentiment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |