CN113360600A - Method and system for screening enterprise performance prediction indexes based on signal attenuation - Google Patents

Method and system for screening enterprise performance prediction indexes based on signal attenuation Download PDF

Info

Publication number
CN113360600A
CN113360600A CN202110620536.3A CN202110620536A CN113360600A CN 113360600 A CN113360600 A CN 113360600A CN 202110620536 A CN202110620536 A CN 202110620536A CN 113360600 A CN113360600 A CN 113360600A
Authority
CN
China
Prior art keywords
indexes
research
keywords
acquiring
signal attenuation
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
Application number
CN202110620536.3A
Other languages
Chinese (zh)
Inventor
周纯葆
王彦棡
王珏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Computer Network Information Center of CAS
Original Assignee
Computer Network Information Center of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Computer Network Information Center of CAS filed Critical Computer Network Information Center of CAS
Priority to CN202110620536.3A priority Critical patent/CN113360600A/en
Publication of CN113360600A publication Critical patent/CN113360600A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • G06F40/216—Parsing using statistical methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • 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
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Development Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Educational Administration (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Game Theory and Decision Science (AREA)
  • Artificial Intelligence (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides a method for screening enterprise performance prediction indexes based on signal attenuation, which is characterized in that text data signals in a research and report chart of an acquired target enterprise are subjected to attenuation processing, a text with the latest release time is given higher weight, and text data signals farther away from the current time point are given lower weight, so that the timeliness of judging indexes according to the logic association degree is ensured, and further, the screened prior indexes are ensured to have higher prediction application value.

Description

Method and system for screening enterprise performance prediction indexes based on signal attenuation
Technical Field
The invention relates to the technical field of index screening, in particular to a method and a system for screening enterprise performance prediction indexes based on signal attenuation.
Background
As time goes on and the operating range of the listed company changes, the leading indicators of the operating performance of the listed company also change, and the number of the indicators which can be purchased in the market is large in order of magnitude (hundreds of thousands, even millions). Therefore, when the leading indicators are screened from a large number of indicators, the timeliness of the screened indicators should be ensured, so that the screened linear indicators can be ensured to have a predicted application value.
Disclosure of Invention
In view of this, the embodiment of the present application provides a method and a system for screening enterprise performance prediction indicators based on signal attenuation.
In a first aspect, an embodiment of the present application provides a method for screening an enterprise performance prediction index based on signal attenuation, including:
acquiring a related research and report chart and business income of a target enterprise, and acquiring direct keywords and year information of the research and report chart from the research and report chart;
expanding the direct keywords to obtain candidate keywords; obtaining a signal attenuation word frequency according to the candidate keywords and the year information of the research and report chart;
comparing the signal attenuation word frequency with a word frequency threshold value to obtain a keyword list; screening indexes in the industry database of the target enterprise according to the keyword list, acquiring a key index list, and acquiring index values of all indexes in the key index list;
determining the correlation between the operating income and the index values of the indexes, and acquiring a related index list according to the correlation;
and performing collinearity removal on the indexes in the related index list to obtain a look-ahead index.
Optionally, the obtaining of the direct keyword from the research and report chart includes:
obtaining the character information in the research and report chart by a character recognition technology;
and aiming at the character information in the research and report chart, obtaining the keywords in the research and report chart through word segmentation, word frequency statistics and part-of-speech analysis.
Optionally, the expanding the direct keyword to obtain the candidate keyword includes:
and obtaining synonyms of the direct keywords, and taking the synonyms and the direct keywords as post-selection keywords.
Optionally, the obtaining a signal attenuation word frequency according to the candidate keyword and the year information of the research and the report includes:
and counting the word frequencies of the keywords in the research and report chart of different years, and performing weighted summation on the word frequencies of different years to obtain the signal attenuation word frequencies.
Optionally, the obtaining the signal attenuation word frequency by weighted summation of the word frequencies of different years includes: the word frequency corresponding to the year closer to the current year has a higher weight.
Optionally, the screening the indexes related to the target enterprise according to the keyword list, and obtaining the index list includes: and carrying out fuzzy matching on the keywords in the keyword list and the indexes, determining the indexes which are successfully matched as key indexes, and generating a key index list.
In a second aspect, an embodiment of the present application provides a system for screening enterprise performance prediction indicators based on signal attenuation, including:
the acquisition unit is used for acquiring relevant research and report charts and business income of the target enterprise;
the processing unit is used for acquiring direct keywords and the year information of the research and report chart from the research and report chart, expanding the direct keywords to obtain candidate keywords, and acquiring signal attenuation word frequency according to the candidate keywords and the year information of the research and report chart; comparing the signal attenuation word frequency with a word frequency threshold value to obtain a keyword list; screening indexes in an industry database to which the target enterprise belongs according to the keyword list, acquiring a key index list, and acquiring index values of all indexes in the key index list; determining the correlation between the operating income and the index values of the indexes, and acquiring a related index list according to the correlation; and performing collinearity removal on the indexes in the related index list to obtain a look-ahead index.
The embodiment of the application provides a method and a system for screening enterprise performance prediction indexes based on signal attenuation. And then newly determining the target enterprise forward-looking index according to the correlation between the macro index of the target enterprise and the index value of the industrial index and the business income. The prospective index has higher timeliness and better prediction application value.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a system for screening an enterprise performance prediction index based on signal attenuation according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for screening performance indicators of an enterprise based on signal attenuation according to an embodiment of the present invention;
FIG. 3 is a flow chart of yet another method for screening a performance prediction index of an enterprise based on signal attenuation according to an embodiment of the present application;
FIG. 4 is a diagram illustrating the results of keywords and their corresponding macro and industrial indicators obtained by attenuating the word frequency by signals;
fig. 5 is a schematic diagram of a result of a look-ahead factor obtained by performing collinearity removal on a keyword obtained by signal attenuation word frequency and a macro index and an industrial index corresponding to the keyword.
Detailed Description
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
The construction of the judgment index for judging the logic association degree between macro and industry data indexes and the marketing company operation performance needs to attenuate the text data signal, the text with the latest release time should be given higher weight, and the text data farther away from the current time point should be given lower weight, so that the judgment index of the logic association degree is guaranteed to have timeliness, and the screened prior index is guaranteed to have more predictive application value.
Therefore, the embodiment of the present invention provides a system for screening enterprise performance prediction indicators based on signal attenuation, as shown in fig. 1, including: the device comprises an acquisition unit 101, a processing unit 102, a storage unit 103 and a display unit 104. These elements may be connected to an internal bus or may be connected to each other through separate wirings.
The collecting unit 101 is used for collecting the research and report chart and the business income of the target enterprise. And stores the collected research and report charts and business income information into the storage unit 103.
The processing unit 102 is configured to obtain the direct keywords and the year information of the newspaper corresponding to each direct keyword from the newspaper graph collected by the collecting unit 101. And then expanding the acquired direct keywords to obtain candidate keywords, and obtaining signal attenuation word frequency according to the candidate keywords and the year information of the research and the newspaper corresponding to the keywords. Further, comparing the signal attenuation word frequency with a preset word frequency threshold value to obtain a keyword list, screening indexes in an industry database to which the target enterprise belongs according to the keyword list to obtain an index list, calculating index values of all the indexes in the index list, then calculating the correlation between the obtained business income of the target enterprise and all the index values in the index list, and obtaining a forward-looking index capable of predicting the enterprise performance according to the correlation.
The storage unit 103 is used for storing the research and report chart and the business income of the target enterprise, which are collected by the collection unit 101. Further, the storage unit 103 is further configured to store the prospective index determined by the processing unit 102.
In one possible example, the collecting unit 101 may send the report chart and the revenue to the processing unit 102 for processing after collecting the report chart and the revenue of the target enterprise, without storing the report chart and the revenue into the storage unit 103.
The display unit 104 is used for displaying the obtained prospective index.
The display unit 104 is further configured to receive enterprise name information input by a user and word frequency threshold information input by the user.
In the embodiment of the application, the obtained text data signals in the research and report chart of the target enterprise are attenuated, the text with the latest release time is weighted more heavily, and the text data signals farther away from the current time point are weighted less heavily, so that the timeliness of the judgment indexes according to the logic association degree is ensured, and further, the screened prior indexes are ensured to have more predictive application values.
Fig. 2 and fig. 3 are flowcharts of a method for screening enterprise operation performance prediction leading indicators according to an embodiment of the present invention, and as shown in fig. 3, the method includes the following steps:
step S301, acquiring a related newspaper research chart and business income of a target enterprise, and acquiring direct keywords and the year information of the newspaper research from the newspaper research chart;
and acquiring a report chart and business income of the target enterprise according to the acquired enterprise name of the target enterprise. The official website of the target enterprise can be searched according to the enterprise name of the target enterprise, and at least one research and report chart and business income of the target enterprise are downloaded on the official website of the target enterprise.
When the research and report chart of the target enterprise is downloaded, the selected standard is that the research and report chart with more than 10 pages is a high-quality research and report chart.
Since most of the downloaded report charts are image files, file information needs to be extracted from the downloaded report charts. Specifically, the downloaded image file may be analyzed and recognized through Optical Character Recognition (OCR), so as to obtain the text and layout information. And aiming at the character information in the research and report chart, obtaining the keywords in the research and report chart through word segmentation, word frequency statistics and part of speech analysis.
Step S302, expanding the direct keywords to obtain candidate keywords; obtaining a signal attenuation word frequency according to the candidate keywords and the year information of the research and the report;
the synonyms of the direct keywords are added into the obtained direct keywords to expand the direct keywords, and a plurality of candidate keywords are obtained.
Specifically, when the obtained direct keyword is "property", it can be known that synonyms of "property" are "property" and "land", and then the "property" is expanded according to the synonym of "property", and candidate keywords can be obtained as follows: "real estate", "real estate" and "land".
Further, word frequencies of the keywords in the research and report chart of different years are counted, and the signal attenuation word frequencies are obtained through weighted summation of the word frequencies of different years. Wherein, the word frequency corresponding to the year closer to the current year has higher weight. Generally, the signal effectiveness is higher in the time period with the closer time, and the signal strength gradually decreases as the time advances; meanwhile, the key indexes are possibly different due to the change of business of enterprises in different years, so that the information can be effectively obtained through signal attenuation.
Step S303, comparing the signal attenuation word frequency with a word frequency threshold value to obtain a keyword list; screening indexes in an industry database to which the target enterprise belongs according to the keyword list, acquiring a key index list, and acquiring index values of all indexes in the key index list;
the word frequency threshold value may be determined by the user according to the need. The indexes in the industry database comprise macro indexes and industry indexes. When the indexes in the industry database to which the target enterprise belongs are screened, the macro indexes and the industry indexes in the database can be subjected to fuzzy matching with the keywords in the keyword list. And determining the indexes successfully matched with the keywords in the keyword list as key indexes, and generating a key index list.
The indexes in the industry database comprise macro indexes and industry indexes. The obtained index value refers to time-series data stored in a database, and can be extracted through database operation.
Step S304, calculating the correlation between the business income of the target enterprise and the determined index value, and acquiring a related index list; and performing collinearity removal on the indexes in the related index list, and obtaining a prospective index according to the correlation.
Specifically, after the business income of the target enterprise and the relevance of the determined index values are determined, the key indexes in the key index list are sorted and subjected to de-collinearity according to the sequence from high relevance to low relevance, and then N key indexes with the top ranking are selected as the forward-looking indexes. Wherein, N is a natural number more than or equal to 1, and the value of N can be set according to the requirement of a user.
In one possible example, the indexes in the obtained key index list may be subjected to a de-collinearity analysis by at least one of a one-way anova method, a difference method, a stepwise regression participle, and a principal component analysis.
In the embodiment of the application, a corresponding keyword list can be obtained through word frequency calculation based on signal attenuation, the position of the keyword in the list reflects the importance degree of the keyword, and a macro index and an industry index list (namely a forward-looking index) corresponding to an enterprise with more time efficiency are obtained through fuzzy matching of the keyword, the macro index and the industry index.
In one possible embodiment, taking company a as an example, the obtained keywords of company a and the corresponding macro indicators and industry indicators of company a are shown in fig. 4 based on the word frequency calculation of signal attenuation. A look-ahead factor is obtained by performing collinearity on the obtained keyword and the corresponding macro index and industrial index, as shown in fig. 5.
Those skilled in the art will recognize that, in one or more of the examples described above, the functions described in this invention may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made on the basis of the technical solutions of the present invention should be included in the scope of the present invention.

Claims (7)

1. A method for screening enterprise performance prediction indexes based on signal attenuation is characterized by comprising the following steps:
acquiring a related research and report chart and business income of a target enterprise, and acquiring direct keywords and year information of the research and report chart from the research and report chart;
expanding the direct keywords to obtain candidate keywords; obtaining a signal attenuation word frequency according to the candidate keywords and the year information of the research and report chart;
comparing the signal attenuation word frequency with a word frequency threshold value to obtain a keyword list; screening indexes in the industry database of the target enterprise according to the keyword list, acquiring a key index list, and acquiring index values of all indexes in the key index list;
determining the correlation between the operating income and the index values of the indexes, and acquiring a related index list according to the correlation;
and performing collinearity removal on the indexes in the related index list to obtain a look-ahead index.
2. The method of claim 1, wherein said obtaining direct keywords from said research chart comprises:
obtaining the character information in the research and report chart by a character recognition technology;
and aiming at the character information in the research and report chart, obtaining the keywords in the research and report chart through word segmentation, word frequency statistics and part-of-speech analysis.
3. The method according to claim 1 or 2, wherein the expanding the direct keyword to obtain the candidate keyword comprises:
and obtaining synonyms of the direct keywords, and taking the synonyms and the direct keywords as post-selection keywords.
4. The method of claim 1, wherein said deriving a signal attenuation word frequency from said candidate keywords and year information of said study comprises:
and counting the word frequencies of the keywords in the research and report chart of different years, and performing weighted summation on the word frequencies of different years to obtain the signal attenuation word frequencies.
5. The method of claim 3, wherein the obtaining the signal-attenuated word frequency by weighted summation of the word frequencies of different years comprises: the word frequency corresponding to the year closer to the current year has a higher weight.
6. The method of claim 1, wherein the filtering the indexes related to the target enterprise according to the keyword list, and obtaining an index list comprises: and carrying out fuzzy matching on the keywords in the keyword list and the indexes, determining the indexes which are successfully matched as key indexes, and generating a key index list.
7. A system for screening performance predictors for an enterprise based on signal attenuation, comprising:
the acquisition unit is used for acquiring relevant research and report charts and business income of the target enterprise;
the processing unit is used for acquiring direct keywords and the year information of the research and report chart from the research and report chart, expanding the direct keywords to obtain candidate keywords, and acquiring signal attenuation word frequency according to the candidate keywords and the year information of the research and report chart; comparing the signal attenuation word frequency with a word frequency threshold value to obtain a keyword list; screening indexes in an industry database to which the target enterprise belongs according to the keyword list, acquiring a key index list, and acquiring index values of all indexes in the key index list; determining the correlation between the operating income and the index values of the indexes, and acquiring a related index list according to the correlation; and performing collinearity removal on the indexes in the related index list to obtain a look-ahead index.
CN202110620536.3A 2021-06-03 2021-06-03 Method and system for screening enterprise performance prediction indexes based on signal attenuation Pending CN113360600A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110620536.3A CN113360600A (en) 2021-06-03 2021-06-03 Method and system for screening enterprise performance prediction indexes based on signal attenuation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110620536.3A CN113360600A (en) 2021-06-03 2021-06-03 Method and system for screening enterprise performance prediction indexes based on signal attenuation

Publications (1)

Publication Number Publication Date
CN113360600A true CN113360600A (en) 2021-09-07

Family

ID=77531813

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110620536.3A Pending CN113360600A (en) 2021-06-03 2021-06-03 Method and system for screening enterprise performance prediction indexes based on signal attenuation

Country Status (1)

Country Link
CN (1) CN113360600A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103942189A (en) * 2014-03-19 2014-07-23 百度在线网络技术（北京）有限公司 Method and device for determining keywords of compositions
CN105718598A (en) * 2016-03-07 2016-06-29 天津大学 AT based time model construction method and network emergency early warning method
CN106599181A (en) * 2016-12-13 2017-04-26 浙江网新恒天软件有限公司 Hot news detecting method based on topic model
CN108460065A (en) * 2017-08-17 2018-08-28 腾讯科技（深圳）有限公司 Photo method for cleaning, device and terminal device
CN110728136A (en) * 2019-10-14 2020-01-24 延安大学 Multi-factor fused textrank keyword extraction algorithm
CN111476030A (en) * 2020-05-08 2020-07-31 中国科学院计算机网络信息中心 Prospective factor screening method based on deep learning

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103942189A (en) * 2014-03-19 2014-07-23 百度在线网络技术（北京）有限公司 Method and device for determining keywords of compositions
CN105718598A (en) * 2016-03-07 2016-06-29 天津大学 AT based time model construction method and network emergency early warning method
CN106599181A (en) * 2016-12-13 2017-04-26 浙江网新恒天软件有限公司 Hot news detecting method based on topic model
CN108460065A (en) * 2017-08-17 2018-08-28 腾讯科技（深圳）有限公司 Photo method for cleaning, device and terminal device
CN110728136A (en) * 2019-10-14 2020-01-24 延安大学 Multi-factor fused textrank keyword extraction algorithm
CN111476030A (en) * 2020-05-08 2020-07-31 中国科学院计算机网络信息中心 Prospective factor screening method based on deep learning

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王康等: ""多维视角下科学主题演化分析框架"", 《情报学报》 *

Similar Documents

Publication Publication Date Title
US7424421B2 (en) Word collection method and system for use in word-breaking
US8630972B2 (en) Providing context for web articles
US6389412B1 (en) Method and system for constructing integrated metadata
KR100816923B1 (en) System and method for classifying document
CN106446071B (en) Information processing apparatus and method
US8949227B2 (en) System and method for matching entities and synonym group organizer used therein
CN111125343A (en) Text analysis method and device suitable for human-sentry matching recommendation system
JP5587493B2 (en) Method and system for assigning actionable attributes to data representing personal identification
CN111767716A (en) Method and device for determining enterprise multilevel industry information and computer equipment
CN107463616B (en) Enterprise information analysis method and system
CN111723260B (en) Recommended content acquisition method and device, electronic equipment and readable storage medium
KR20070009338A (en) Image search method and apparatus considering a similarity among the images
CN111538903B (en) Method and device for determining search recommended word, electronic equipment and computer readable medium
KR101011726B1 (en) Apparatus and method for providing snippet
JP5986687B2 (en) Data separation system, data separation method, program for data separation, and recording medium for the program
KR20140081721A (en) System and method for deducting imporant keyword using textmining, and a medium having computer readable program for executing the method
KR101868936B1 (en) Keyword extracting and refining system, and method thereof
JP5592552B1 (en) Document classification survey system, document classification survey method, and document classification survey program
CN113360600A (en) Method and system for screening enterprise performance prediction indexes based on signal attenuation
JP5518665B2 (en) Patent search device, patent search method, and program
KR20090060131A (en) Methods for searching and presentation of the results in digital forensics and apparatus thereof
US7630979B2 (en) Information retrieval terminal
KR101614551B1 (en) System and method for extracting keyword using category matching
JP2010218216A (en) Similar document retrieval system, method and program
JP4192760B2 (en) Category-specific new feature word ranking method, apparatus and program, and category-specific new feature word ranking program recording computer-readable storage medium

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