CN108628832B - Method and device for acquiring information keywords - Google Patents
Method and device for acquiring information keywordsDownload PDFInfo
- Publication number
- CN108628832B CN108628832BCN201810431832.7ACN201810431832ACN108628832BCN 108628832 BCN108628832 BCN 108628832BCN 201810431832 ACN201810431832 ACN 201810431832ACN 108628832 BCN108628832 BCN 108628832B
- Authority
- CN
- China
- Prior art keywords
- keyword
- keywords
- temporary
- keyword set
- coverage
- 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.)
- Active
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Translated fromChinese
Description
Technical Field
The invention relates to the technical field of communication, in particular to a method and a device for acquiring information keywords.
Background
In order to adapt to market environment changes, information work is highly emphasized by domestic and foreign mainstream operators, equipment providers and internet enterprises all the time, and decision support is provided for company strategies.
According to the analysis report of Gartner, telecommunication operators in the top 30 of the world rank all have special competitive information departments, and pay more attention to the information work, AT & T designs a professional portal to manage the information work as early as 2007; verizon also establishes a self-service model as early as 2008 to improve the information service efficiency, and releases 77 related job recruitments all the year round as 2016 for Linkin thermal information recruitment analysts; the leader of the German telecommunication market and the competitive intelligence department is also an expert of the world competitive intelligence society and the European competitive intelligence society.
The keyword is a main search basis for obtaining information materials, and how to obtain the information keyword is a main problem for information management.
Disclosure of Invention
The invention provides a method and a device for acquiring information keywords, aiming at the defects in the prior art and used for at least partially solving the problem of how to automatically acquire the information keywords.
In order to solve the technical problems, the invention adopts the following technical scheme:
the invention provides a method for acquiring information keywords, which comprises the following steps:
determining a second keyword set, wherein keywords in the second keyword set are keywords of current hotspot information;
determining a third keyword set, wherein keywords in the third keyword set are common keywords of all tracked objects;
calculating a union of the second keyword set, the third keyword set and a preset first keyword set to determine an information keyword; and the keywords in the first keyword set are individual keywords of each tracked object.
Preferably, the determining the third keyword set specifically includes:
calculating the coverage of each keyword to be selected;
determining a first temporary set according to the coverage of each keyword to be selected, a preset threshold, the first keyword set and the second keyword set;
and determining a third key word set according to the number of key words in a preset third key word set and the first temporary set.
Preferably, the calculating the coverage of each candidate keyword specifically includes:
acquiring the number of tracking objects related to each keyword to be selected and the total number of the tracking objects;
and respectively calculating the ratio of the number of the tracked objects related to each keyword to be selected to the total number of the tracked objects to obtain the coverage of each keyword to be selected.
Preferably, the determining a third keyword set according to the number of keywords in a preset third keyword set and the first temporary set specifically includes:
comparing the number of keywords in the first temporary set with the number of keywords in a preset third keyword set;
if the former is larger than or equal to the latter, sorting the keywords in the first temporary set from large to small according to coverage, and selecting a preset number of keywords in the sorting as elements of the third keyword set, wherein the preset number is the number of the keywords in the third keyword set;
if the former is smaller than the latter, the third set of keywords is the first temporary set.
Preferably, the determining a first temporary set according to the coverage of each keyword to be selected, a preset threshold, the first keyword set, and the second keyword set specifically includes:
comparing the coverage of each keyword to be selected with a preset threshold, and if the coverage of each keyword to be selected is greater than the preset threshold, taking the corresponding keyword to be selected as an element of a second temporary set;
and calculating the intersection of the second temporary set, the first keyword set and the second keyword set and negating to obtain the first temporary set.
The present invention also provides a keyword management apparatus, the apparatus comprising: the system comprises a first processing module, a second processing module and a third processing module;
the first processing module is used for determining a second keyword set, wherein keywords in the second keyword set are keywords of current hotspot information;
the second processing module is used for determining a third keyword set, wherein keywords in the third keyword set are common keywords of all tracked objects;
the third processing module is used for calculating a union of the second keyword set, the third keyword set and a preset first keyword set to determine an information intelligence keyword; and the keywords in the first keyword set are individual keywords of each tracked object.
Preferably, the second processing module is specifically configured to calculate a coverage of each keyword to be selected; determining a first temporary set according to the coverage of each keyword to be selected, a preset threshold, the first keyword set and the second keyword set; and determining a third key word set according to the number of key words in a preset third key word set and the first temporary set.
Preferably, the second processing module is specifically configured to obtain the number of the tracked objects related to each keyword to be selected and the total number of the tracked objects; and respectively calculating the ratio of the number of the tracked objects related to each keyword to be selected to the total number of the tracked objects to obtain the coverage of each keyword to be selected.
Preferably, the second processing module is configured to compare the number of keywords in the first temporary set with a preset number of keywords in a third keyword set; when the former is larger than or equal to the latter, sorting the keywords in the first temporary set from large to small according to coverage, and selecting a preset number of keywords in the sorting as elements of the third keyword set, wherein the preset number is the number of the keywords in the third keyword set; when the former is smaller than the latter, the third set of keywords is the first temporary set.
Preferably, the third processing module is configured to compare the coverage of each keyword to be selected with a preset threshold, and when the coverage of each keyword is greater than the preset threshold, use the corresponding keyword to be selected as an element of a second temporary set, and calculate and negate an intersection of the second temporary set, the first keyword set, and the second keyword set, so as to obtain the first temporary set.
According to the invention, the information keywords can be quickly determined by calculating the union of the current hotspot information keyword set, the common keyword set of each tracked object and the individual keyword set of each tracked object, and the determined information keywords not only cover the current hotspot information, but also have pertinence, can meet the individual requirements of each user (namely the tracked object), and have the characteristics of multiple dimensionality and wide coverage.
Drawings
Fig. 1 is a flow chart of information intelligence keyword acquisition provided by the embodiment of the present invention;
FIG. 2 is a flowchart of determining a third set of keywords according to an embodiment of the present invention;
FIG. 3 is a second flowchart of determining a third keyword set according to an embodiment of the present invention;
FIG. 4 is a flow chart of determining a first temporary set according to an embodiment of the present invention;
fig. 5 is a structural diagram of a keyword management apparatus according to an embodiment of the present invention.
Detailed Description
The technical solution of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
The invention provides a method for acquiring information keywords, which is applied to an information resource system, wherein the information resource system comprises the following steps: the system comprises a material collecting device, a resource pool establishing device, an information resource pool, a tracking object database, a tracking object management device, a keyword database and a keyword management device, wherein the tracking object management device is used for updating the tracking object database, the keyword management device is used for updating the keyword database, the material collecting device respectively obtains a tracking object information material and a keyword information material through the tracking object management device and the keyword management device, and the resource pool establishing device encodes the tracking object information material and the keyword information material to obtain information and stores the information in the information resource pool.
In the embodiment of the invention, the tracked objects mainly comprise global mainstream operators and large Internet companies, and are stored in the tracked object database.
The intelligence information keywords include individual keywords and common keywords. The keywords are formed according to the extraction of the strategy and key work of the company, the keywords to be searched for information retrieval of each tracked object are common keywords, such as 5G, cloud computing, big data, the Internet of things and the like, and the common keywords are stored in a common keyword module of a keyword database. And combing and refining the keywords according to the current hot spot information of the tracked object to be the individual keywords of the tracked object, wherein the individual keywords are stored in an individual keyword module of a keyword database.
As shown in fig. 1, the method for acquiring information keywords comprises the following steps:
Specifically, the number of keywords in the second keyword set kw2 is n2, n2 is a preset value, and n2 is greater than or equal to 0. kw2 ═ kw21，kw22，kw23，…kw2n2And each keyword in the second keyword set kw2 is a keyword of the current hotspot information and can be obtained by calculating the most active selection algorithm, wherein the most active selection algorithm is the existing algorithm and is not described herein again.
Specifically, the number of the keywords in the third keyword set kw3 is n3, n3 is a preset value, and n3 is greater than or equal to 0. kw3 ═ kw31，kw32，kw33，…kw3n3And each keyword in the third keyword set kw3 is a common keyword of each tracked object, and includes a hotspot vocabulary concerned by each tracked object, for example: the internet of things, block chains, big data and the like.
A specific implementation of determining the third set of keywords kw3 is described in more detail later in connection with fig. 2.
And 103, calculating a union of the second keyword set, the third keyword set and a preset first keyword set to determine the information intelligence keyword.
Specifically, the first gateThe number of key words in the key word set kw1 is n1, n1 is a preset value, and n1 is greater than or equal to 0. The total number of the information intelligence keywords is n, n is n1+ n2+ n3, n1 is more than or equal to 0 and less than or equal to n, n2 is more than or equal to 0 and less than or equal to n, and n3 is more than or equal to 0 and less than or equal to n. kw1 ═ kw11，kw12，kw13，…kw1n1And the keywords in the first keyword set kw1 are individual keywords of each tracked object, and include the long-term attention field and hot vocabulary of each tracked object, and each keyword in the first keyword set kw1 can be set by each tracked object.
The set of the finally determined information intelligence keywords is kw, kw-kw 1-kw 2-kw 3.
It can be seen fromstep 101 andstep 103 that, by calculating the union of the current hot spot information keyword set, the common keyword set of each tracked object, and the individual keyword set of each tracked object, the invention can quickly determine the information keywords, and the determined information keywords not only cover the current hot spot information, but also have pertinence, can meet the individual requirements of each user (i.e. tracked object), and has the characteristics of multiple dimensions and wide coverage.
Further, as shown in fig. 2, the determining the third keyword set (i.e. step 102) specifically includes the following steps:
Specifically, the number T1 of the tracked objects related to each candidate keyword is obtainediAnd the total number T of the tracked objects, and respectively calculating the ratio of the number of the tracked objects related to each keyword to be selected to the total number of the tracked objects so as to obtain the coverage q of each keyword to be selectediI.e. qi＝T1iand/T, wherein i represents a key to be selected.
The tracking object related to each candidate keyword refers to a tracking object which focuses on the candidate keyword, that is, a tracking object which selects the candidate keyword as a common keyword and/or an individual keyword.
Specifically, the process of determining the first temporary set temp1kw is described in detail later with reference to fig. 4.
Specifically, the keywords in the first temporary set temp1kw may be final information intelligence keywords, i.e., the third set of keywords kw3 is the same as the first temporary set temp1 kw. The keywords in the first temporary set temp1kw may be different from the final information intelligence keywords, i.e. the range of the first temporary set temp1kw is larger than the range of the third set kw 3.
The scheme of how to determine the third set of keywords kw3 is described in detail later with reference to fig. 3.
As can be seen fromstep
The process of determining the third set of keywords kw3 (i.e., step 203) is described in detail below with reference to fig. 3. As shown in fig. 3, the process of determining the third keyword set kw3 includes the following steps:
Specifically, assuming that the number of keywords in the first temporary set temp1kw is n ', n ' is compared with the number n3 of keywords in the third set kw3, and if n ' > n3, it indicates that the number of keywords in the first temporary set temp1kw is greater than the required number of keywords in the third set kw3, at this time, a more suitable keyword needs to be further selected from the first temporary set temp1kw and placed in the third set kw3 (i.e.,step 302 and step 303 are executed); if n' is less than or equal to n3, it means that the number of keywords in the first temporary set temp1kw is less than or equal to the required number of keywords in the third keyword set kw3, at this time, all the keywords in the first temporary set temp1kw are placed in the third keyword set kw3 (i.e.,step 304 is executed).
Specifically, n' keywords in the first temporary set temp1kw are arranged according to the coverage qiSorting from big to small, wherein the coverage of each keyword qiCalculated instep 201.
Specifically, the preset number is the number n3 of keywords in the third keyword set, that is, in the coverage ranking, the first n3 keywords are selected to form the third keyword set kw 3.
Specifically, if the number n' of keywords in the first temporary set temp1kw does not reach the number of keywords required by the third set kw3, the entire first temporary set temp1kw is used as the third set kw 3.
As can be seen fromsteps 301 to 303, by filtering the keywords in the first temporary set temp1kw, the information intelligence keywords (i.e. the third keyword set kw3) thus selected have a larger coverage and a wider coverage.
The process of determining the first temporary set temp1kw (i.e., step 202) is described in detail below with reference to fig. 4. As shown in fig. 3, the process of determining the first temporary set temp1kw includes the following steps:
Specifically, a threshold Q is preset, and the coverage Q of each keyword to be selected is determinediRespectively compared with a threshold value Q if the coverage of the key word to be selectedDegree q ofi>Q, if the keyword to be selected is qualified, putting the keyword to be selected into the second temporary set temp2kw (i.e. executing step 402); if the coverage of the key word to be selected is qiAnd if the value is less than or equal to Q, the keyword to be selected is not qualified, and the keyword to be selected is discarded.
In particular, the first temporary set
In this way, the same keys in the second temporary set temp2kw, the first key set kw1 and the second key set kw2 may be excluded. Keyword duplication within the third set of keywords kw3 is avoided when subsequently determining the third set of keywords kw3 from the first temporary set temp1 kw.
Based on the same technical concept, an embodiment of the present invention further provides a keyword management apparatus, as shown in fig. 5, the keyword management apparatus includes: afirst processing module 51, asecond processing module 52 and athird processing module 53.
Thefirst processing module 51 is configured to determine a second keyword set, where keywords in the second keyword set are keywords of current hotspot information.
Thesecond processing module 52 is configured to determine a third keyword set, where the keywords in the third keyword set are common keywords of each tracked object.
Thethird processing module 53 is configured to calculate a union of the second keyword set, the third keyword set, and a preset first keyword set to determine an information intelligence keyword; and the keywords in the first keyword set are individual keywords of each tracked object.
Preferably, thesecond processing module 52 is specifically configured to calculate a coverage of each keyword to be selected; determining a first temporary set according to the coverage of each keyword to be selected, a preset threshold, the first keyword set and the second keyword set; and determining a third key word set according to the number of key words in a preset third key word set and the first temporary set.
Preferably, thesecond processing module 52 is specifically configured to obtain the number of the tracked objects related to each keyword to be selected, and the total number of the tracked objects; and respectively calculating the ratio of the number of the tracked objects related to each keyword to be selected to the total number of the tracked objects to obtain the coverage of each keyword to be selected.
Preferably, thesecond processing module 52 is configured to compare the number of keywords in the first temporary set with the number of keywords in a preset third keyword set; when the former is larger than or equal to the latter, sorting the keywords in the first temporary set from large to small according to coverage, and selecting a preset number of keywords in the sorting as elements of the third keyword set, wherein the preset number is the number of the keywords in the third keyword set; when the former is smaller than the latter, the third set of keywords is the first temporary set.
Preferably, thethird processing module 53 is configured to compare the coverage of each keyword to be selected with a preset threshold, and when the coverage of each keyword is greater than the preset threshold, use the corresponding keyword to be selected as an element of the second temporary set, and calculate and negate an intersection of the second temporary set, the first keyword set, and the second keyword set, so as to obtain the first temporary set.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.
Claims (6)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810431832.7ACN108628832B (en) | 2018-05-08 | 2018-05-08 | Method and device for acquiring information keywords |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810431832.7ACN108628832B (en) | 2018-05-08 | 2018-05-08 | Method and device for acquiring information keywords |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108628832A CN108628832A (en) | 2018-10-09 |
| CN108628832Btrue CN108628832B (en) | 2022-03-18 |
Family
ID=63695891
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810431832.7AActiveCN108628832B (en) | 2018-05-08 | 2018-05-08 | Method and device for acquiring information keywords |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108628832B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111651657B (en)* | 2020-06-04 | 2024-05-24 | 深圳前海微众银行股份有限公司 | Information monitoring method, device, equipment and computer readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103425677A (en)* | 2012-05-18 | 2013-12-04 | 阿里巴巴集团控股有限公司 | Method for determining classified models of keywords and method and device for classifying keywords |
| CN103530398A (en)* | 2013-10-23 | 2014-01-22 | 合山市科学技术情报研究所 | Information collecting, processing and retrieving system |
| CN103744873A (en)* | 2013-12-18 | 2014-04-23 | 天脉聚源(北京)传媒科技有限公司 | Method, device and browser for displaying hotspot keyword |
| CN104035997A (en)* | 2014-06-13 | 2014-09-10 | 淮阴工学院 | Scientific and technical information acquisition and pushing method based on text classification and image deep mining |
| CN104679787A (en)* | 2013-11-27 | 2015-06-03 | 华为技术有限公司 | Interest information statistical method and device |
| CN106126588A (en)* | 2016-06-17 | 2016-11-16 | 广州视源电子科技股份有限公司 | Method and device for providing related words |
| CN106227735A (en)* | 2016-07-11 | 2016-12-14 | 苏州天梯卓越传媒有限公司 | A kind of word cloud Topic Selection for Publishing Industry and system |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7181438B1 (en)* | 1999-07-21 | 2007-02-20 | Alberti Anemometer, Llc | Database access system |
| CN100405371C (en)* | 2006-07-25 | 2008-07-23 | 北京搜狗科技发展有限公司 | Method and system for abstracting new word |
| CN101296128A (en)* | 2007-04-24 | 2008-10-29 | 北京大学 | A method for monitoring abnormal state of Internet information |
| CN101520878A (en)* | 2009-04-03 | 2009-09-02 | 华为技术有限公司 | Method, device and system for pushing advertisements to users |
| CN102110269A (en)* | 2011-02-25 | 2011-06-29 | 中兴通讯股份有限公司 | Advertisement releasing method and system |
| CN103714413A (en)* | 2013-11-21 | 2014-04-09 | 清华大学 | System and method for constructing quality model based on position information |
| CN104965893A (en)* | 2015-06-18 | 2015-10-07 | 山东师范大学 | Big data advertisement delivery method |
| CN107786595A (en)* | 2016-08-26 | 2018-03-09 | 阿里巴巴集团控股有限公司 | The processing method of keyword, apparatus and system in distributed memory system |
| CN106453423B (en)* | 2016-12-08 | 2019-10-01 | 黑龙江大学 | A kind of filtration system and method for the spam based on user individual setting |
| CN107341199B (en)* | 2017-06-21 | 2020-05-22 | 北京林业大学 | Recommendation method based on document information commonality mode |
- 2018
- 2018-05-08CNCN201810431832.7Apatent/CN108628832B/enactiveActive
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103425677A (en)* | 2012-05-18 | 2013-12-04 | 阿里巴巴集团控股有限公司 | Method for determining classified models of keywords and method and device for classifying keywords |
| CN103530398A (en)* | 2013-10-23 | 2014-01-22 | 合山市科学技术情报研究所 | Information collecting, processing and retrieving system |
| CN104679787A (en)* | 2013-11-27 | 2015-06-03 | 华为技术有限公司 | Interest information statistical method and device |
| CN103744873A (en)* | 2013-12-18 | 2014-04-23 | 天脉聚源(北京)传媒科技有限公司 | Method, device and browser for displaying hotspot keyword |
| CN104035997A (en)* | 2014-06-13 | 2014-09-10 | 淮阴工学院 | Scientific and technical information acquisition and pushing method based on text classification and image deep mining |
| CN106126588A (en)* | 2016-06-17 | 2016-11-16 | 广州视源电子科技股份有限公司 | Method and device for providing related words |
| CN106227735A (en)* | 2016-07-11 | 2016-12-14 | 苏州天梯卓越传媒有限公司 | A kind of word cloud Topic Selection for Publishing Industry and system |
Non-Patent Citations (1)
| Title |
|---|
| 基于关键词相关度的Deep_Web爬虫爬行策略;田野等;《计算机工程》;20080805;第34卷(第15期);220-222* |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108628832A (en) | 2018-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111782965B (en) | Intended to recommend methods, devices, equipment and storage media | |
| US10621493B2 (en) | Multiple record linkage algorithm selector | |
| Ciceri et al. | Crowdsourcing for top-k query processing over uncertain data | |
| US10185771B2 (en) | Method and system for scheduling web crawlers according to keyword search | |
| US20120215795A1 (en) | System and Method For Intelligent Job Hunt | |
| CN103838857B (en) | Automatic service combination system and method based on semantics | |
| CN119003840B (en) | Government service recommendation method and system based on user behavior analysis | |
| RU2339078C2 (en) | Designation of web-pages for identification of geographical positions | |
| CN104615734B (en) | A kind of community management service big data processing system and its processing method | |
| CN109726734A (en) | A target platform automatic identification system based on radiation source reconnaissance information | |
| CN110442614B (en) | Metadata searching method and device, electronic equipment and storage medium | |
| CN115858598A (en) | Enterprise big data-based target information screening and matching method and related equipment | |
| CN111177481A (en) | User identifier mapping method and device | |
| CN111159559A (en) | Method for constructing recommendation engine according to user requirements and user behaviors | |
| CN107067033A (en) | The local route repair method of machine learning model | |
| CN108628832B (en) | Method and device for acquiring information keywords | |
| CN103646035B (en) | A kind of information search method based on heuristic | |
| CN112734382A (en) | Talent recruitment system capable of quickly matching related job seekers according to enterprise requirements | |
| CN118536957A (en) | Talent post matching method and device based on model screening, medium and equipment | |
| CN107577690B (en) | Recommendation method and recommendation device for mass information data | |
| CN114297341B (en) | Public opinion popularity determination method, device, equipment and storage medium | |
| JP2008187612A (en) | Traffic analysis model construction method, apparatus, construction program, and storage medium thereof | |
| CN111858733A (en) | A method and system for government affairs information comparison based on Internet multi-source heterogeneous data | |
| US20120054117A1 (en) | Identifying an individual in response to a query seeking to locate personnel with particular experience | |
| CN111125336A (en) | Information prompting method, device, equipment and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |