CN109657070A - A kind of construction method of terminal auxiliary SWOT index system - Google Patents
A kind of construction method of terminal auxiliary SWOT index system Download PDFInfo
- Publication number
- CN109657070A CN109657070A CN201811515374.1A CN201811515374A CN109657070A CN 109657070 A CN109657070 A CN 109657070A CN 201811515374 A CN201811515374 A CN 201811515374A CN 109657070 A CN109657070 A CN 109657070A
- Authority
- CN
- China
- Prior art keywords
- keyword
- word
- text data
- speech
- index system
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 18
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 238000013507 mapping Methods 0.000 claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims description 21
- 238000000034 method Methods 0.000 claims description 20
- 239000012141 concentrate Substances 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 241001269238 Data Species 0.000 claims description 5
- 238000003064 k means clustering Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000007423 decrease Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to field of storage in termination set, specially a kind of terminal auxiliarySWOTThe construction method of index system comprising: stepS100, based on terminal to the keyword extraction of text data set;StepS200, keyword clustering andSWOTIndex system mapping;And stepS300, generate the suggestion of index system weight.Keyword automatically extracting and clustering, and effectively saves expert's human resources, and avoid to a certain extentSWOTThe influence of human interference factor during system construction.
Description
Technical field
The present invention relates to field of storage in termination set, specially a kind of construction method of terminal auxiliary SWOT index system.
Background technique
SWOT analysis method (wherein Strengths: internal advantages factor, Weakness: internal weak tendency factor,
Opportunities: external chance factor, Threats: outside threat factor) be a kind of classics Competitive Intelligence Analysis tool,
It is proposed in 1971 Nian Qi " corporate strategy concept " book by the K.J. Theresa Andrews of Harvard Business School.This method it is main in
Appearance is to carry out widely investigation around analysis target to collect with information, is then analyzed the information being collected into, judges shadow
Ring the external opportunity and outside threat of target, the four aspect factor of internal advantages and disadvantage that target is implemented.SWOT analysis method was both
Simple preliminary analysis can be carried out, the general overview of analysis target is qualitatively understood, while the strategy of target also may be implemented
Strategy is formed, implementation or control decision.
Due to SWOT analysis method from analysis target population, can clearly list influence target implement advantage,
Disadvantage, chance and deterrent, and be subject to comprehensive analysis, the complicated factor that will affect target implementation is clear, and policymaker can be with
Clearly risk and opportunity that may be present in master goal implementation, to improve the accuracy of decision.Therefore SWOT analysis side
Method has become modern government department, enterprise in management and analysis tool the most commonly used in decision, is widely used
With research.
Need to design a kind of construction method of new terminal auxiliary SWOT index system based on above-mentioned technical problem.
Summary of the invention
The object of the present invention is to provide a kind of construction methods of terminal auxiliary SWOT index system.
In order to solve the above-mentioned technical problems, the present invention provides a kind of terminal auxiliary SWOT index system construction method,
Include:
Step S100, to the keyword extraction of text data set;
Step S200, keyword clustering and the mapping of SWOT index system;And
Step S300 generates the suggestion of index system weight.
Further, include: to the method for the keyword extraction of text data set in the step S100
Step S101, stop words filtering after carrying out Chinese word segmentation to the text data set of acquisition, select shape by accumulation
At deactivated vocabulary, filter text data in stop words;
Step S102, specific word filtering, scans for word by search engine, for search result less than threshold value
Word judges that it, for specific word, then filters specific word;
Step S103, keyword extraction carry out keyword extraction by improved TF/IDF algorithm.
Further, the improved TF/IDF algorithm are as follows:
Formula 1
2 W of formulai=W | TF/IDF (wi) > η;
3 W=∪ W of formulai;
Formula 4
In formula, TF/IDF (wi) be word w in text data marked as i TF/IDF weight;TF(wi) it is word w in label
For the frequency occurred in the text data of i;N is the text data number that text data set includes;D is the text data comprising word w
Number;
It is described by improved TF/IDF algorithm carry out keyword extraction method include:
The TF/IDF weight that text data concentrates the keyword for including in each text data is calculated by formula 1;
It is ranked up by size according to the TF/IDF weight of keyword in each text data;
Extract the keyword set Wi that keyword of the weight greater than threshold value η forms the text data marked as i, all texts
The keyword W set that the Wi set of data summarizes for text data set;
It is matched two-by-two for the keyword in W set, ratio calculated C;
TF in formula 4sum(Wa) refer to that the frequency that certain keyword a occurs in W set adds up and TFsum(Wb) refer to certain keyword
The frequency that b occurs in W set adds up and G (Wa) refer to the retrieval page results that keyword a is obtained in a search engine
Number;G(Wb) refer to the retrieval page number of results that keyword b is obtained in a search engine;Ratio C is a pair of of keyword a and b
TFsumThe ratio of value and the product of G value, and sorting by the result of ratio to the keyword in W set, and show in order with
Keyword is corrected.
Further, keyword clustering and the method for SWOT index system mapping include: in the step S200
Step S201 realizes the first subseries to keyword according to List of Chinese Classification, compares Chinese Classification theme
Vocabulary classifies the keyword extracted in current text data set, establishes initial keyword classification structure;
Step S202, after preliminary classification, the remaining key that classification can not be corresponded in List of Chinese Classification
Word, distance metric of the nearly adopted degree as word and word according to word, gathers remaining keyword using K_MEANS clustering method
Class;
Step S203 assists cluster to complete and then the keyword classification after cluster is showed and corrected in terminal;
Step S204, after the iteration to keyword clustering and to the keyword classification amendment after cluster, root
According to the classification information of the part of speech after cluster, part of speech is mapped to accordingly index, i.e.,
Establish the index system of SWOT analysis.
Further, the method that the suggestion of index system weight is generated in the step S300 includes: selection influence index system
The factor of weight judgement;
The factor of influence index system weight judgement includes:
The word amount for the keyword that part of speech includes: the pass for being included by each part of speech generated during analysis of key term clustering
Keyword quantity, to judge the mapped generation index weights of the part of speech, i.e. its corresponding index power of the more part of speech of keyword quantity
It is again bigger;
The word frequency for the keyword that part of speech includes: all keywords to include in part of speech concentrate the frequency occurred in text data
It is secondary accumulative and;And
The timeliness for the keyword that part of speech includes: word frequency statistics of the keyword for including for a part of speech on time dimension
Show the degree that the keyword is concerned on time dimension.
Further, the method for index system weight suggestion is generated in the step S300 further include: be based on influence index body
It is the generation formula of the factor building index system weight suggestion of weight judgement, i.e.,
In formula, R (W) is the corresponding index weights suggestion of a part of speech;Keyword of the i from 1 to k to include in the part of speech
Number, successively calculates keywords all in such;J is the text data for including some word w in the part of speech from 1 to d, successively
All text datas comprising word w are calculated;Traversal includes the text data of word w, calculates separately j-th and includes word w
Time attenuation function;TF(wj) it is the frequency that word w occurs in text data j;e-μ(t-tc)For time attenuation function;μ is to decline
Subtract constant;T is the time that this article notebook data occurs;Tc is current time;
R (W) the weight recommended value for calculating each part of speech generates index weights suggestion later.
The invention has the advantages that the present invention is based on terminals to the keyword extraction of text data set, and will be crucial
Term clustering and the mapping of SWOT index system;And the suggestion of index system weight is generated, realize automatically extracting and gathering for keyword
Class.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 is the flow chart of the construction method of terminal auxiliary SWOT index system according to the present invention.
Specific embodiment
In conjunction with the accompanying drawings, the present invention is further explained in detail.These attached drawings are simplified schematic diagram, only with
Illustration illustrates basic structure of the invention, therefore it only shows the composition relevant to the invention.
Embodiment 1
Fig. 1 is the flow chart of the construction method of terminal auxiliary SWOT index system according to the present invention.
As shown in Figure 1, present embodiments providing a kind of construction method of terminal auxiliary SWOT index system, comprising:
Step S100, based on terminal to the keyword extraction of text data set;
Step S200, keyword clustering and the mapping of SWOT index system;And
Step S300 generates the suggestion of index system weight;
In this embodiment, terminal can be, but not limited to assist using computer with the building to SWOT index system;
Automatically extracting and clustering for keyword, effectively saves expert's human resources, and avoids SWOT system structure to a certain extent
The influence of human interference factor during building.
In the present embodiment, the step S100 includes: based on method of the terminal to the keyword extraction of text data set
Step S101, stop words filtering to be formed after carrying out Chinese word segmentation to the text data set of terminal acquisition by accumulating to select
Vocabulary is deactivated, filters the stop words in text data, the stop words is usually auxiliary words of mood, function word and numeral-classifier compound etc.;Step
Rapid S102, specific word filtering, scans for word by search engine, and the word of threshold value is less than for search result, judges that it is
Then specific word filters specific word, the specific word is generally the very strong specific word of the directive property such as place name, name;It is different from
Stop words, specific word is difficult to be filtered by customization vocabulary, in relevant research work, many practical word categorical reasonings
Realize the classification of specific word, whether grammatical term for the character is place name, name etc., but this infers that there are certain unreliabilities;Make
With search engine, such as Google, Baidu, to judge specific word;Such as Google can show the knot of search when searching for every time
Fruit number scans for that less searched page number can be obtained using specific word, therefore for search result less than certain threshold value
Word, it can be determined that it is specific word, is filtered;The retrieval specific word of Google can be by the algorithm of Google come automatic complete
At;Step S103, keyword extraction carry out keyword extraction by improved TF/IDF algorithm;TF/IDF algorithm is current master
The keyword extraction algorithm of stream, TF (Term Frequency: word frequency) refer to time that some word occurs in some text
Number, IDF (Inverse Document Frequency: inverse document frequency).
It is in the present embodiment, required to be accomplished that the keyword extracted in the set towards entire text data set,
Traditional TF/IDF algorithm be extract the keyword in the document for some document, therefore to traditional TF/IDF algorithm into
Row improves;The improved TF/IDF algorithm are as follows:
Formula 1
2 W of formulai=W | TF/IDF (wi) > η;
3 W=∪ W of formulai;
Formula 4
In formula, TF/IDF (wi) be word w in text data marked as i TF/IDF weight;TF(wi) it is word w in label
For the frequency occurred in the text data of i;N is the text data number that text data set includes;D is the text data comprising word w
Number;
The method for carrying out keyword extraction by improved TF/IDF algorithm includes: to calculate textual data by formula 1
According to the TF/IDF weight for concentrating the keyword for including in each text data;According to the TF/IDF power of keyword in each text data
Value is ranked up by size;Extract the keyword set that keyword of the weight greater than threshold value η forms the text data marked as i
Wi, the keyword W set that the Wi set of all text datas summarizes for text data set;Two-by-two for the keyword in W set
Pairing, ratio calculated C;WF in formula 4sum(Wa) refer to that the frequency that certain keyword a occurs in W set adds up and WFsum(Wb) refer to
The frequency that certain keyword b occurs in W set adds up and G (Wa) refer to the retrieved page that keyword a is obtained in a search engine
Face number of results;G(Wb) refer to the retrieval page number of results that keyword b is obtained in a search engine;Ratio C is a pair of of keyword
The TF of a and bsumValue and G value (G value and TFsumThe form of expression it is the same, refer to what a pair of of keyword obtained in a search engine
Retrieve page number of results) product ratio, and sort, and show in order to the keyword in W set by the result of ratio
Show to be corrected to keyword.
In the present embodiment, keyword clustering and the method for SWOT index system mapping include: step in the step S200
Rapid S201 realizes the first subseries to keyword according to List of Chinese Classification, compares List of Chinese Classification, will work as
Preceding text data concentrates the keyword extracted to classify, and establishes initial keyword classification structure;Step S202, for first
After step classification, the remaining keyword that classification can not be corresponded in List of Chinese Classification, the nearly adopted degree conduct according to word
The distance metric of word and word clusters remaining keyword using K MEANS clustering method;Step S203 is assisted in terminal
Cluster is completed and then the keyword classification after cluster is showed and corrected, and the modified method can be, but not limited to pass through
Manually it is modified;Step S204, after the iteration of keyword clustering and to the keyword classification amendment after cluster,
According to the classification information of the part of speech after cluster, part of speech is mapped to accordingly index, that is, establishes the index system of SWOT analysis.
In the present embodiment, the step S300, the method for generating the suggestion of index system weight includes: selection influence index
The factor of system weight judgement;Each index is different for the support for analyzing result in index system, i.e., some indexs are
Principal element, and some indexs are then secondary cause, the present embodiment is by three influence index system weights judgements because usually
Generate weight suggestion;The factor of influence index system weight judgement includes:
The word amount for the keyword that part of speech includes: the pass for being included by each part of speech generated during analysis of key term clustering
Keyword quantity, to judge the mapped generation index weights of the part of speech, i.e. its corresponding index power of the more part of speech of keyword quantity
It is again bigger;
The word frequency for the keyword that part of speech includes: other than keyword quantity, the keyword word frequency that part of speech is included is also
The weight judgment basis of the index of part of speech mapping, all keywords for including in the keyword word frequency that part of speech the includes i.e. part of speech
Concentrate the frequency that occurs accumulative in text data and;
The timeliness for the keyword that part of speech includes: the frequency that keyword occurs in some period passes through data of increasing income
Collected text data set all has time attribute, and the word in text data is also attached with the time attribute of this article notebook data,
In analysis and the time attribute for not investigating word when extracting keyword, and the keyword that a part of speech includes is in time dimension
On word frequency statistics show the degree that the keyword is concerned on time dimension, i.e. the timeliness of the part of speech keyword that includes
Property be also judge its correspond to index weights element.
In the present embodiment, the step S300, the method for generating the suggestion of index system weight further include: referred to based on influence
The generation formula of the factor building index system weight suggestion of mark system weight judgement, i.e.,
In formula, R (W) is the corresponding index weights suggestion of a part of speech;Keyword of the i from 1 to k to include in the part of speech
Number, successively calculates keywords all in such;J is the text data for including some word w in the part of speech from 1 to d, successively
All text datas comprising word w are calculated;Traversal includes the text data of word w, calculates separately j-th and includes word w
Time attenuation function;TF(wj) it is the frequency that word w occurs in text data j;e-μ(t-tc)For time attenuation function;μ is to decline
Subtract constant;T is the time that this article notebook data occurs;Tc is current time;R (W) the weight recommended value for calculating each part of speech is raw later
At index weights suggestion.
In conclusion the present invention is by the keyword extraction to text data set, with keyword clustering and SWOT index body
System's mapping, ultimately produces index system weight suggestion, realizes automatically extracting and clustering for keyword, effectively save expert people
Power resource, and the influence of human interference factor during SWOT system construction is avoided to a certain extent;And the present invention is also
It can be effectively saved the workload of intelligence analysis personnel, and SWOT index system establishment mistake can be reduced to a certain extent
Disturbing factor in journey, this also has promote meaning for the application of SWOT analysis.
By first time iteration to obtain the relevant keyword of SWOT analysis target and be clustered to keyword, second
Crucial part of speech is mapped to the evaluation index of SWOT by the target of secondary iteration, last part, after the generation of SWOT evaluation index,
The suggestion of SWOT index weights is generated by algorithm.
Taking the above-mentioned ideal embodiment according to the present invention as inspiration, through the above description, relevant staff is complete
Various changes and amendments can be carried out without departing from the scope of the technological thought of the present invention' entirely.The technology of this invention
Property range is not limited to the contents of the specification, it is necessary to which the technical scope thereof is determined according to the scope of the claim.
Claims (6)
1. a kind of construction method of terminal auxiliary SWOT index system characterized by comprising
Step S100, to the keyword extraction of text data set;
Step S200, keyword clustering and the mapping of SWOT index system;And
Step S300 generates the suggestion of index system weight.
2. construction method as described in claim 1, which is characterized in that
Include: to the method for the keyword extraction of text data set in the step S100
Step S101, stop words filtering after carrying out Chinese word segmentation to the text data set of acquisition, to be formed by accumulating to select
Vocabulary is deactivated, the stop words in text data is filtered;
Step S102, specific word filtering, scans for word by search engine, and the word of threshold value is less than for search result, is sentenced
It break as specific word, then filters specific word;
Step S103, keyword extraction carry out keyword extraction by improved TF/IDF algorithm.
3. construction method as claimed in claim 2, which is characterized in that
The improved TF/IDF algorithm are as follows:
Formula 1
2 W of formulai=W | TF/IDF (wi) > η;
3 W=∪ W of formulai;
Formula 4
In formula, TF/IDF (wi) be word w in text data marked as i TF/IDF weight;TF(wi) it is word w marked as i's
The frequency occurred in text data;N is the text data number that text data set includes;D is the text data number comprising word w;
It is described by improved TF/IDF algorithm carry out keyword extraction method include:
The TF/IDF weight that text data concentrates the keyword for including in each text data is calculated by formula 1;
It is ranked up by size according to the TF/IDF weight of keyword in each text data;
Extract the keyword set W that keyword of the weight greater than threshold value η forms the text data marked as ii, all text datas
WiThe keyword W set that set summarizes for text data set;
It is matched two-by-two for the keyword in W set, ratio calculated C;
TF in formula 4sum(Wa) refer to that the frequency that certain keyword a occurs in W set adds up and TFsum(Wb) refer to certain keyword b in W
The frequency occurred in set adds up and G (Wa) refer to the retrieval page number of results that keyword a is obtained in a search engine;G
(Wb) refer to the retrieval page number of results that keyword b is obtained in a search engine;Ratio C is the TF of a pair of of keyword a and bsum
The ratio of value and the product of G value, and sort by the result of ratio to the keyword in W set, and shown in order to pass
Keyword is corrected.
4. construction method as claimed in claim 3, which is characterized in that
The step S200, keyword clustering and SWOT index system mapping method include:
Step S201 realizes the first subseries to keyword according to List of Chinese Classification, compares Chinese Classification descriptor
Table classifies the keyword extracted in current text data set, establishes initial keyword classification structure;
Step S202, after preliminary classification, the remaining keyword that classification can not be corresponded in List of Chinese Classification, according to
Distance metric according to the nearly adopted degree of word as word and word, clusters remaining keyword using K_MEANS clustering method;
Step S203 assists cluster to complete and then the keyword classification after cluster is showed and corrected in terminal;
Step S204, after the iteration to keyword clustering and to the keyword classification amendment after cluster, according to poly-
Part of speech is mapped to accordingly index, i.e., by the classification information of the part of speech after class
Establish the index system of SWOT analysis.
5. construction method as claimed in claim 4, which is characterized in that
In the step S300 generate the suggestion of index system weight method include: select influence index system weight judgement because
Element;
The factor of influence index system weight judgement includes:
The word amount for the keyword that part of speech includes: the keyword for being included by each part of speech generated during analysis of key term clustering
Quantity, to judge the mapped generation index weights of the part of speech, i.e. its corresponding index weights of the more part of speech of keyword quantity more
Greatly;
The word frequency for the keyword that part of speech includes: all keywords to include in part of speech concentrate the frequency occurred tired in text data
Meter and;
The timeliness for the keyword that part of speech includes: word frequency statistics of the keyword for including for a part of speech on time dimension are shown
The degree that the keyword is concerned on time dimension out.
6. construction method as claimed in claim 5, which is characterized in that
The method of index system weight suggestion is generated in the step S300 further include: based on the judgement of influence index system weight
Factor constructs the generation formula of index system weight suggestion, i.e.,
In formula, R (W) is the corresponding index weights suggestion of a part of speech;I is the keyword number for including in the part of speech from 1 to k, according to
It is secondary that keywords all in such are calculated;J is the text data for including some word w in the part of speech from 1 to d, successively to packet
All text datas of the w containing the word are calculated;Traversal include word w text data, calculate separately j-th comprising word w when
Between attenuation function;TF(wj) it is the frequency that word w occurs in text data j;e-μ(t-tc)For time attenuation function;μ is that decaying is normal
Number;T is the time that this article notebook data occurs;Tc is current time;
R (W) the weight recommended value for calculating each part of speech generates index weights suggestion later.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811515374.1A CN109657070B (en) | 2018-12-11 | 2018-12-11 | Construction method of terminal-assisted SWOT index system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811515374.1A CN109657070B (en) | 2018-12-11 | 2018-12-11 | Construction method of terminal-assisted SWOT index system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109657070A true CN109657070A (en) | 2019-04-19 |
CN109657070B CN109657070B (en) | 2023-06-09 |
Family
ID=66113770
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811515374.1A Active CN109657070B (en) | 2018-12-11 | 2018-12-11 | Construction method of terminal-assisted SWOT index system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109657070B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110532357A (en) * | 2019-09-04 | 2019-12-03 | 深圳前海微众银行股份有限公司 | Generation method, device, equipment and the readable storage medium storing program for executing of ESG score-system |
CN110991785A (en) * | 2019-10-11 | 2020-04-10 | 平安科技(深圳)有限公司 | Text-based index extraction method and device, computer equipment and storage medium |
CN111767401A (en) * | 2020-07-02 | 2020-10-13 | 中国标准化研究院 | NQI index automatic generation method |
CN112508376A (en) * | 2020-11-30 | 2021-03-16 | 中国科学院深圳先进技术研究院 | Index system construction method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101593200A (en) * | 2009-06-19 | 2009-12-02 | 淮海工学院 | Chinese Web page classification method based on the keyword frequency analysis |
CN104008143A (en) * | 2014-05-09 | 2014-08-27 | 启秀科技(北京)有限公司 | Vocational ability index system establishment method based on data mining |
CN107958344A (en) * | 2017-12-13 | 2018-04-24 | 国网陕西省电力公司经济技术研究院 | A kind of power distribution network Development Strategy Analysis method based on AHP and SWOT |
CN108062306A (en) * | 2017-12-29 | 2018-05-22 | 国信优易数据有限公司 | A kind of index system establishment system and method for business environment evaluation |
CN108241652A (en) * | 2016-12-23 | 2018-07-03 | 北京国双科技有限公司 | Keyword clustering method and device |
-
2018
- 2018-12-11 CN CN201811515374.1A patent/CN109657070B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101593200A (en) * | 2009-06-19 | 2009-12-02 | 淮海工学院 | Chinese Web page classification method based on the keyword frequency analysis |
CN104008143A (en) * | 2014-05-09 | 2014-08-27 | 启秀科技(北京)有限公司 | Vocational ability index system establishment method based on data mining |
CN108241652A (en) * | 2016-12-23 | 2018-07-03 | 北京国双科技有限公司 | Keyword clustering method and device |
CN107958344A (en) * | 2017-12-13 | 2018-04-24 | 国网陕西省电力公司经济技术研究院 | A kind of power distribution network Development Strategy Analysis method based on AHP and SWOT |
CN108062306A (en) * | 2017-12-29 | 2018-05-22 | 国信优易数据有限公司 | A kind of index system establishment system and method for business environment evaluation |
Non-Patent Citations (2)
Title |
---|
CHAIMAE OUCHICHA等: "Cluster validity index: Comparative study and a new validity index with high performance", 《LOPAL "18: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON LEARNING AND OPTIMIZATION ALGORITHMS: THEORY AND APPLICATIONS》 * |
黄敏: "长三角地区潜在战略性主导产...评价及筛选——以江苏省为例", 《时代金融》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110532357A (en) * | 2019-09-04 | 2019-12-03 | 深圳前海微众银行股份有限公司 | Generation method, device, equipment and the readable storage medium storing program for executing of ESG score-system |
CN110532357B (en) * | 2019-09-04 | 2024-03-12 | 深圳前海微众银行股份有限公司 | ESG scoring system generation method, device, equipment and readable storage medium |
CN110991785A (en) * | 2019-10-11 | 2020-04-10 | 平安科技(深圳)有限公司 | Text-based index extraction method and device, computer equipment and storage medium |
WO2021068798A1 (en) * | 2019-10-11 | 2021-04-15 | 平安科技(深圳)有限公司 | Index extraction method and device based on text, computer apparatus, and storage medium |
CN110991785B (en) * | 2019-10-11 | 2023-07-25 | 平安科技(深圳)有限公司 | Index extraction method and device based on text, computer equipment and storage medium |
CN111767401A (en) * | 2020-07-02 | 2020-10-13 | 中国标准化研究院 | NQI index automatic generation method |
CN111767401B (en) * | 2020-07-02 | 2023-04-28 | 中国标准化研究院 | NQI index automatic generation method |
CN112508376A (en) * | 2020-11-30 | 2021-03-16 | 中国科学院深圳先进技术研究院 | Index system construction method |
Also Published As
Publication number | Publication date |
---|---|
CN109657070B (en) | 2023-06-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109657070A (en) | A kind of construction method of terminal auxiliary SWOT index system | |
US10565233B2 (en) | Suffix tree similarity measure for document clustering | |
CN103605665B (en) | Keyword based evaluation expert intelligent search and recommendation method | |
CN107220295A (en) | A kind of people's contradiction reconciles case retrieval and mediation strategy recommends method | |
CN108121829A (en) | The domain knowledge collection of illustrative plates automated construction method of software-oriented defect | |
CN103577462B (en) | A kind of Document Classification Method and device | |
CN108829658A (en) | The method and device of new word discovery | |
CN103942340A (en) | Microblog user interest recognizing method based on text mining | |
US20140280242A1 (en) | Method and apparatus for acquiring hot topics | |
CN110019689A (en) | Position matching process and position matching system | |
CN104615734B (en) | A kind of community management service big data processing system and its processing method | |
CN107967290A (en) | A kind of knowledge mapping network establishing method and system, medium based on magnanimity scientific research data | |
CN105787097A (en) | Distributed index establishment method and system based on text clustering | |
Wick et al. | A unified approach for schema matching, coreference and canonicalization | |
CN110569273A (en) | Patent retrieval system and method based on relevance sorting | |
Barrio et al. | Sampling strategies for information extraction over the deep web | |
Bougouin et al. | Keyphrase annotation with graph co-ranking | |
Liang et al. | Clustering web services for automatic categorization | |
CN109526027A (en) | A kind of cell capacity optimization method, device, equipment and computer storage medium | |
CN113094514A (en) | Water affair data intelligent discovery method based on domain knowledge graph | |
Guan et al. | Research and design of internet public opinion analysis system | |
Jin et al. | Tise: A temporal search engine for web contents | |
CN110083686A (en) | A kind of algorithm design of patent auto recommending method | |
Hamdi et al. | Machine learning vs deterministic rule-based system for document stream segmentation | |
CN115147081B (en) | Policy matching method, system and storage medium based on artificial intelligence |
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 |