CN108241652A - Keyword clustering method and device - Google Patents
Keyword clustering method and device Download PDFInfo
- Publication number
- CN108241652A CN108241652A CN201611209417.4A CN201611209417A CN108241652A CN 108241652 A CN108241652 A CN 108241652A CN 201611209417 A CN201611209417 A CN 201611209417A CN 108241652 A CN108241652 A CN 108241652A
- Authority
- CN
- China
- Prior art keywords
- keyword
- phrase
- clustering
- index value
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
Abstract
The invention discloses a kind of keyword clustering method and devices, can carry out cluster analysis to the keyword in keyword set according to the index value of multiple clustering targets of keyword each in keyword set to be clustered, obtain multiple crucial phrases；Then, it is determined that the index value of the corresponding phrase clustering target of each crucial phrase, corresponding storage is carried out by the index value of the phrase clustering target with the crucial phrase.Due to the present invention by the index value of clustering target to keyword progress cluster analysis, obtained crucial phrase has different clustering target features, can recommend more useful keyword to user according to clustering target feature.
Description
Technical field
The present invention relates to keyword clustering technical field more particularly to a kind of keyword clustering method and devices.
Background technology
Search engine marketing (SEM, Search Engine Marketing) business is a kind of marketing mode, it can be
Keyword is launched on search engine platform, user triggers keyword by search term, clicks advertising creative, and then enter advertiser
Flow or conversion are reached in website.
In order to provide more keywords to advertiser, need to classify to a large amount of keyword, then to advertiser
The keyword of a certain classification is provided for its use.The prior art classifies to keyword using keyword senses, by meaning phase
Same/similar keyword is divided into one group and is supplied to user.But present inventor, which studies, to be found：Pass through the side of keyword senses
Although formula can provide a user a large amount of keywords to the mode that keyword is classified, there is a large amount of turn in these keywords
The low keyword of rate.This also allows for the prior art and more useful keyword is precisely provided without normal direction user.
Invention content
In view of the above problems, it is proposed that the present invention overcomes the above problem in order to provide one kind or solves at least partly
State the keyword clustering method and device of problem.
A kind of keyword clustering method, including：
The index value of multiple clustering targets of each keyword in keyword set to be clustered is obtained, the clustering target is
For evaluating the evaluation index of the dispensing effect of keyword；
Cluster point carries out the keyword in the keyword set to be clustered according to the index value of the clustering target
Analysis, obtains multiple crucial phrases；
Determine the index value of the corresponding phrase clustering target of each crucial phrase, by the index value of the phrase clustering target with
The crucial phrase carries out corresponding storage.
Optionally, the index value for determining the corresponding phrase clustering target of each crucial phrase, including：
Average value/median of each clustering target of keyword in each crucial phrase is determined, by the institute of clustering target
State index value of the average value/median as the phrase clustering target of corresponding crucial phrase.
Optionally, after the index value for determining the corresponding phrase clustering target of each crucial phrase, the method is also wrapped
It includes：
According to the index value of the corresponding phrase clustering target of each crucial phrase, for the matched cluster mark of each crucial phrase distribution
Label.
Optionally, in the index value of the multiple clustering targets for obtaining each keyword in keyword set to be clustered
Before, the method further includes：
Record the index value of multiple evaluation indexes of each keyword.
Optionally, it is described to obtain pass to be clustered after the index value of the multiple evaluation indexes for recording each keyword
In keyword set before the index value of multiple clustering targets of each keyword, the method further includes：
The evaluation index needed for this cluster is determined, using the evaluation index needed for this cluster as clustering target.
A kind of keyword clustering device, including：Index obtaining unit, cluster analysis unit and storage unit,
The index obtaining unit, for obtaining multiple clustering targets of each keyword in keyword set to be clustered
Index value, the clustering target are the evaluation index for evaluating the dispensing effect of keyword；
The cluster analysis unit, for the index value according to the clustering target to the keyword set to be clustered
In keyword carry out cluster analysis, obtain multiple crucial phrases；
The storage unit, for determining the index value of the corresponding phrase clustering target of each crucial phrase, by the phrase
The index value of clustering target carries out corresponding storage with the crucial phrase.
Optionally, the storage unit is specifically used for：Determine each clustering target of keyword in each crucial phrase
Average value/median refers to the average value/median of clustering target as the phrase cluster of corresponding crucial phrase
The index value of the phrase clustering target is carried out corresponding storage by target index value with the crucial phrase.
Optionally, described device further includes：Label allocation unit, for determining each crucial phrase pair in the storage unit
It is each key according to the index value of the corresponding phrase clustering target of each crucial phrase after the index value of phrase clustering target answered
Phrase distributes matched cluster labels.
Optionally, described device further includes：Index recording unit, it is to be clustered for being obtained in the index obtaining unit
In keyword set before the index value of multiple clustering targets of each keyword, the index of multiple evaluation indexes of each keyword is recorded
Value.
Optionally, described device further includes：Evaluation index determination unit, for respectively being closed in the index recording unit records
After the index value of multiple evaluation indexes of keyword, the index obtaining unit obtains each keyword in keyword set to be clustered
Multiple clustering targets index value before, determine this cluster needed for evaluation index, by this cluster needed for evaluation index
As clustering target.
By above-mentioned technical proposal, a kind of keyword clustering method and device provided by the invention can be according to be clustered
Keyword set in each keyword multiple clustering targets index value to the keyword in keyword set carry out cluster point
Analysis, obtains multiple crucial phrases；Then, it is determined that the index value of the corresponding phrase clustering target of each crucial phrase, by the phrase
The index value of clustering target carries out corresponding storage with the crucial phrase.Due to the present invention by the index value of clustering target to closing
Keyword carries out cluster analysis, therefore obtained crucial phrase has different clustering target features, can be according to clustering target spy
It levies and recommends more useful keyword to user.
Above description is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, below the special specific embodiment for lifting the present invention.
Description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this field
Technical staff will become clear.Attached drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings：
Fig. 1 shows a kind of flow chart of keyword clustering method provided in an embodiment of the present invention；
Fig. 2 shows the flow charts of another keyword clustering method provided in an embodiment of the present invention；
Fig. 3 shows the flow chart of another keyword clustering method provided in an embodiment of the present invention；
Fig. 4 shows a kind of structure diagram of keyword clustering device provided in an embodiment of the present invention；
Fig. 5 shows the structure diagram of another keyword clustering device provided in an embodiment of the present invention；
Fig. 6 shows the structure diagram of another keyword clustering device provided in an embodiment of the present invention；
Fig. 7 shows the schematic diagram of keyword clustering principle provided in an embodiment of the present invention.
Specific embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
As shown in Figure 1, a kind of keyword clustering method provided in an embodiment of the present invention, can include：
S100, the index value for obtaining multiple clustering targets of each keyword in keyword set to be clustered.
Wherein, the clustering target can be the evaluation index for evaluating the dispensing effect of keyword, such as：The amount of showing,
Clicking rate, average clicked price, rate of return on investment etc..
Citing 1 is set in the keyword set to be clustered there are four keyword, respectively keyword a, keyword b, is closed
Keyword c and keyword d.There are two clustering targets in step S100, respectively clicking rate and rate of return on investment, then step S100
The index value of the clustering target of acquisition is as shown in table 1.
Table 1
S200, the keyword in the keyword set to be clustered is gathered according to the index value of the clustering target
Alanysis obtains multiple crucial phrases；
Wherein it is possible to it is chosen using cluster algorithms such as Mean-Shift, K-means, mixed Gauss models described poly-
The index value of class index carries out cluster analysis as feature to the keyword in the keyword set to be clustered, obtains multiple
Crucial phrase.
It is understood that the index value due to the use of clustering target carries out cluster analysis, therefore obtained after clustering
Multiple crucial phrases are by with different clustering target features, such as rate of return on investment difference.In this manner it is possible to it is pushed away according to user
Recommend the crucial phrase with better clustering target feature.
Still illustrated by taking citing 1 as an example：
By cluster analysis it is found that keyword a is close with clicking rate, the rate of return on investment of keyword b；Keyword c is with closing
Clicking rate, the rate of return on investment of keyword d is close, therefore is a crucial phrase a by keyword a and keyword b clusters, will be crucial
Word c and keyword d clusters are a crucial phrase b.
In order to facilitate the principle for understanding cluster analysis, the present invention also provides the X-Y schemes drawn according to 1 data of table, such as scheme
Shown in 7, from the cluster principle of the two dimension it can be seen from the figure that present invention.Certainly, in practical applications, since clustering target can be with
Have more, therefore can might not be indicated by way of X-Y scheme.It is understood that due to each keyword
The index value of the clustering target of keyword in group is all close, thus may determine that the corresponding phrase clustering target of each crucial phrase
Feature, such as：The corresponding phrase clustering targets of crucial phrase a have：The feature of low clicking rate high return-on-investment, crucial phrase
The corresponding phrase clustering targets of b have：The feature of high clicking rate moderate investment return rate.
S300, the index value for determining the corresponding phrase clustering target of each crucial phrase, by the finger of the phrase clustering target
Scale value carries out corresponding storage with the crucial phrase.
Specifically, the index value for determining the corresponding phrase clustering target of each crucial phrase, can include：
Average value/median of each clustering target of keyword in each crucial phrase is determined, by the institute of clustering target
State index value of the average value/median as the phrase clustering target of corresponding crucial phrase.
Due to the keyword in each crucial phrase have it is multiple, in the phrase clustering target for determining crucial phrase,
It can be using the average value/median of clustering target as the index of the phrase clustering target of corresponding crucial phrase
Value.
Specifically, step S300 determines that the index value of the corresponding phrase clustering target of each crucial phrase is corresponding with crucial phrase
The feature of phrase clustering target match.It still 1 is illustrated with citing, step S300 can be (10% and 12% by 11%
Average value), 72.5% (70% and 75% average value) be identified as crucial phrase a clicking rate index value and invest back
The index value of report rate.Equally, to crucial phrase b, the index value of corresponding phrase clustering target can also carry out same treatment, no
It repeats again.
It is, of course, also possible to using the variance/standard deviation and average value/median of clustering target together as corresponding
The index value of the phrase clustering target of crucial phrase.
A kind of keyword clustering method provided in an embodiment of the present invention, can respectively close according in keyword set to be clustered
The index value of multiple clustering targets of keyword carries out cluster analysis to the keyword in keyword set, obtains multiple keywords
Group；Then, it is determined that the index value of the corresponding phrase clustering target of each crucial phrase, by the index value of the phrase clustering target with
The crucial phrase carries out corresponding storage.Since the present invention by the index value of clustering target carries out cluster analysis to keyword,
Therefore the crucial phrase obtained has different clustering target features, can be more useful to user's recommendation according to clustering target feature
Keyword.
It, can be with after step S300 as shown in Fig. 2, another kind keyword clustering method provided in an embodiment of the present invention
Including：
S400, the index value according to the corresponding phrase clustering target of each crucial phrase are distributed matched for each crucial phrase
Cluster labels.
Wherein, cluster labels can be the mark to the index value level height of clustering target, such as：Rate of return on investment is high.
Embodiment illustrated in fig. 2 for each crucial phrase by distributing matched cluster labels so that is providing a user key
When word, directly corresponding crucial phrase can be selected to provide a user according to cluster labels.
It optionally, can be by the multiple crucial phrase, index after matched cluster labels are distributed for each crucial phrase
Value and cluster labels are uploaded in keyword database.
In an alternative embodiment of the invention, before step S100, can also include：
Record the index value of multiple evaluation indexes of each keyword.
Wherein it is possible to selectively the index value of multiple evaluation indexes of each keyword is recorded, such as：To double
The index value of the multiple evaluation indexes for the keyword launched in 11 the last week is recorded, and to the key of the dispensing of time earlier
The index value of multiple evaluation indexes of word is without record.
As shown in figure 3, another kind keyword clustering method provided in an embodiment of the present invention, can include：
S001, record each keyword multiple evaluation indexes index value, the clustering target is for evaluating keyword
Dispensing effect evaluation index；
S002, the required evaluation index of this cluster is determined, using the evaluation index needed for this cluster as clustering target.
Specifically, the evaluation index to match can be chosen according to different keyword clustering purposes as clustering target.
S100, the index value for obtaining multiple clustering targets of each keyword in keyword set to be clustered, the cluster
Index is evaluation index；
S200, the keyword in the keyword set to be clustered is gathered according to the index value of the clustering target
Alanysis obtains multiple crucial phrases；
S300, the index value for determining the corresponding phrase clustering target of each crucial phrase, by the finger of the phrase clustering target
Scale value carries out corresponding storage with the crucial phrase.
Corresponding with above method embodiment, the embodiment of the present invention additionally provides a kind of keyword clustering device.
As shown in figure 4, a kind of keyword clustering device provided in an embodiment of the present invention, can include：Index obtaining unit
100th, cluster analysis unit 200 and storage unit 300,
The index obtaining unit 100, multiple clusters for obtaining each keyword in keyword set to be clustered refer to
Target index value, the clustering target are the evaluation index for evaluating the dispensing effect of keyword；
Wherein, the clustering target can be the evaluation index for evaluating the dispensing effect of keyword, such as：The amount of showing,
Clicking rate, average clicked price, rate of return on investment etc..
The cluster analysis unit 200, for the index value according to the clustering target to the keyword to be clustered
Keyword in set carries out cluster analysis, obtains multiple crucial phrases；
Wherein it is possible to it is chosen using cluster algorithms such as Mean-Shift, K-means, mixed Gauss models described poly-
The index value of class index carries out cluster analysis as feature to the keyword in the keyword set to be clustered, obtains multiple
Crucial phrase.
It is understood that the index value due to the use of clustering target carries out cluster analysis, therefore obtained after clustering
Multiple crucial phrases are by with different clustering target features, such as rate of return on investment difference.In this manner it is possible to it is pushed away according to user
Recommend the crucial phrase with better clustering target feature.
The storage unit 300, for determining the index value of the corresponding phrase clustering target of each crucial phrase, by institute's predicate
The index value of group cluster index carries out corresponding storage with the crucial phrase.
Wherein, the storage unit 300 can be specifically used for：Determine that each cluster of keyword in each crucial phrase refers to
Target average value/median gathers the average value/median of clustering target as the phrase of corresponding crucial phrase
The index value of the phrase clustering target is carried out corresponding storage by the index value of class index with the crucial phrase.
Due to the keyword in each crucial phrase have it is multiple, in the phrase clustering target for determining crucial phrase,
The storage unit 300 can be using the average value/median of clustering target as the phrase of corresponding crucial phrase
The index value of clustering target.
It is, of course, also possible to using the variance/standard deviation and average value/median of clustering target together as corresponding
The index value of the phrase clustering target of crucial phrase.
A kind of keyword clustering device provided in an embodiment of the present invention, can respectively close according in keyword set to be clustered
The index value of multiple clustering targets of keyword carries out cluster analysis to the keyword in keyword set, obtains multiple keywords
Group；Then, it is determined that the index value of the corresponding phrase clustering target of each crucial phrase, by the index value of the phrase clustering target with
The crucial phrase carries out corresponding storage.Since the present invention by the index value of clustering target carries out cluster analysis to keyword,
Therefore the crucial phrase obtained has different clustering target features, can be more useful to user's recommendation according to clustering target feature
Keyword.
As shown in figure 5, another kind keyword clustering device provided in an embodiment of the present invention, can also include：Label distributes
Unit 400, for determine the corresponding phrase clustering target of each crucial phrase in the storage unit 300 index value after, according to
The index value of the corresponding phrase clustering target of each crucial phrase distributes matched cluster labels for each crucial phrase.
Wherein, cluster labels can be the mark to the index value level height of clustering target, such as：Rate of return on investment is high.
Embodiment illustrated in fig. 5 for each crucial phrase by distributing matched cluster labels so that is providing a user key
When word, directly corresponding crucial phrase can be selected to provide a user according to cluster labels.
Optionally, after matched cluster labels are distributed for each crucial phrase, can also by the multiple crucial phrase, refer to
Scale value and cluster labels are uploaded in keyword database.
In an alternative embodiment of the invention, the keyword clustering device that above-described embodiment provides can also include：Digit synbol
Unit is recorded, multiple clusters for obtaining each keyword in keyword set to be clustered in the index obtaining unit 100 refer to
Before target index value, the index value of multiple evaluation indexes of each keyword is recorded.
Wherein it is possible to selectively the index value of multiple evaluation indexes of each keyword is recorded, such as：To double
The index value of the multiple evaluation indexes for the keyword launched in 11 the last week is recorded, and to the key of the dispensing of time earlier
The index value of multiple evaluation indexes of word is without record.
As shown in fig. 6, a kind of keyword clustering device provided in an embodiment of the present invention, can include：Index recording unit
001st, evaluation index determination unit 002, index obtaining unit 100, cluster analysis unit 200 and storage unit 300,
Index recording unit 001, for respectively closing in obtaining keyword set to be clustered in the index obtaining unit 100
Before the index value of multiple clustering targets of keyword, the index value of multiple evaluation indexes of each keyword is recorded.
Evaluation index determination unit 002, multiple evaluations for recording each keyword in the index recording unit 001 refer to
After target index value, multiple clusters that the index obtaining unit 100 obtains each keyword in keyword set to be clustered refer to
Before target index value, the evaluation index needed for this cluster is determined, using the evaluation index needed for this cluster as clustering target.
Specifically, the evaluation index to match can be chosen according to different keyword clustering purposes as clustering target.
The index obtaining unit 100, multiple clusters for obtaining each keyword in keyword set to be clustered refer to
Target index value, the clustering target are the evaluation index for evaluating the dispensing effect of keyword；
The cluster analysis unit 200, for the index value according to the clustering target to the keyword to be clustered
Keyword in set carries out cluster analysis, obtains multiple crucial phrases；
The storage unit 300, for determining the index value of the corresponding phrase clustering target of each crucial phrase, by institute's predicate
The index value of group cluster index carries out corresponding storage with the crucial phrase.
The keyword clustering device includes processor and memory, and These parameters recording unit 001, evaluation index determine
The conducts such as unit 002, index obtaining unit 100, cluster analysis unit 200, storage unit 300 and label allocation unit 400
Program unit stores in memory, performs above procedure unit stored in memory by processor to realize corresponding work(
Energy.
Comprising kernel in processor, gone in memory to transfer corresponding program unit by kernel.Kernel can set one
Or more, by evaluation index the keyword in the keyword set to be clustered is gathered by adjusting kernel parameter
Alanysis obtains multiple crucial phrases, and the index value of phrase clustering target is carried out corresponding storage with the crucial phrase.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM), memory includes at least one deposit
Store up chip.
A kind of keyword clustering device provided by the invention, can be according to keyword each in keyword set to be clustered
The index value of multiple clustering targets carries out cluster analysis to the keyword in keyword set, obtains multiple crucial phrases；Then,
The index value of the corresponding phrase clustering target of each crucial phrase is determined, by the index value of the phrase clustering target and the key
Phrase carries out corresponding storage.Keyword progress cluster analysis is obtained by the index value of clustering target due to the present invention
Crucial phrase there is different clustering target features, can more useful key be recommended to user according to clustering target feature
Word.
Present invention also provides a kind of computer program products, first when being performed on data processing equipment, being adapted for carrying out
The program code of beginningization there are as below methods step：
The index value of multiple clustering targets of each keyword in keyword set to be clustered is obtained, the clustering target is
For evaluating the evaluation index of the dispensing effect of keyword；
Cluster point carries out the keyword in the keyword set to be clustered according to the index value of the clustering target
Analysis, obtains multiple crucial phrases；
Determine the index value of the corresponding phrase clustering target of each crucial phrase, by the index value of the phrase clustering target with
The crucial phrase carries out corresponding storage.
It should be understood by those skilled in the art that, embodiments herein can be provided as method, system or computer program
Product.Therefore, the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware can be used in the application
Apply the form of example.Moreover, the computer for wherein including computer usable program code in one or more can be used in the application
The computer program production that usable storage medium is implemented on (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application is with reference to the flow according to the method for the embodiment of the present application, equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that it can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided
The processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that the instruction performed by computer or the processor of other programmable data processing devices is generated for real
The device of function specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction generation being stored in the computer-readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps are performed on calculation machine or other programmable devices to generate computer implemented processing, so as in computer or
The instruction offer performed on other programmable devices is used to implement in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, CD-ROM read-only memory (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic tape cassette, the storage of tape magnetic rigid disk or other magnetic storage apparatus
Or any other non-transmission medium, available for storing the information that can be accessed by a computing device.It defines, calculates according to herein
Machine readable medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It these are only embodiments herein, be not limited to the application.To those skilled in the art,
The application can have various modifications and variations.All any modifications made within spirit herein and principle, equivalent replacement,
Improve etc., it should be included within the scope of claims hereof.
Claims (10)
- A kind of 1. keyword clustering method, which is characterized in that including：Obtain the index value of multiple clustering targets of each keyword in keyword set to be clustered, the clustering target be for Evaluate the evaluation index of the dispensing effect of keyword；Cluster analysis is carried out to the keyword in the keyword set to be clustered according to the index value of the clustering target, is obtained To multiple crucial phrases；Determine the index value of the corresponding phrase clustering target of each crucial phrase, by the index value of the phrase clustering target with it is described Crucial phrase carries out corresponding storage.
- 2. according to the method described in claim 1, it is characterized in that, described determine the corresponding phrase clustering target of each crucial phrase Index value, including：Average value/median of each clustering target of keyword in each crucial phrase is determined, by the described flat of clustering target Index value of the mean value/median as the phrase clustering target of corresponding crucial phrase.
- 3. method according to claim 1 or 2, which is characterized in that determine that the corresponding phrase of each crucial phrase gathers described After the index value of class index, the method further includes：According to the index value of the corresponding phrase clustering target of each crucial phrase, matched cluster labels are distributed for each crucial phrase.
- 4. according to the method described in claim 1, it is characterized in that, in each key in obtaining keyword set to be clustered Before the index value of multiple clustering targets of word, the method further includes：Record the index value of multiple evaluation indexes of each keyword.
- 5. according to the method described in claim 4, it is characterized in that, the multiple evaluation indexes for recording each keyword finger It is described to obtain in keyword set to be clustered before the index value of multiple clustering targets of each keyword after scale value, the method It further includes：The evaluation index needed for this cluster is determined, using the evaluation index needed for this cluster as clustering target.
- 6. a kind of keyword clustering device, which is characterized in that including：Index obtaining unit, cluster analysis unit and storage unit,The index obtaining unit, for obtaining the index of multiple clustering targets of each keyword in keyword set to be clustered Value, the clustering target are the evaluation index for evaluating the dispensing effect of keyword；The cluster analysis unit, for the index value according to the clustering target in the keyword set to be clustered Keyword carries out cluster analysis, obtains multiple crucial phrases；For determining the index value of the corresponding phrase clustering target of each crucial phrase, the phrase is clustered for the storage unit The index value of index carries out corresponding storage with the crucial phrase.
- 7. device according to claim 6, which is characterized in that the storage unit is specifically used for：Determine each keyword Average value/median of each clustering target of keyword in group, using the average value/median of clustering target as with its The index value of the phrase clustering target of corresponding crucial phrase, by the index value of the phrase clustering target and the crucial phrase Carry out corresponding storage.
- 8. the device described according to claim 6 or 7, which is characterized in that described device further includes：Label allocation unit, is used for It is corresponding according to each crucial phrase after the index value for determining the corresponding phrase clustering target of each crucial phrase in the storage unit The index value of phrase clustering target distributes matched cluster labels for each crucial phrase.
- 9. device according to claim 6, which is characterized in that described device further includes：Index recording unit, in institute It states index obtaining unit to obtain in keyword set to be clustered before the index value of multiple clustering targets of each keyword, record is each The index value of multiple evaluation indexes of keyword.
- 10. device according to claim 9, which is characterized in that described device further includes：Evaluation index determination unit is used After the index value in multiple evaluation indexes of each keyword of index recording unit records, the index obtaining unit obtains In keyword set to be clustered before the index value of multiple clustering targets of each keyword, determine that the evaluation needed for this cluster refers to Mark, using the evaluation index needed for this cluster as clustering target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611209417.4A CN108241652A (en) | 2016-12-23 | 2016-12-23 | Keyword clustering method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611209417.4A CN108241652A (en) | 2016-12-23 | 2016-12-23 | Keyword clustering method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108241652A true CN108241652A (en) | 2018-07-03 |
Family
ID=62704341
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611209417.4A Pending CN108241652A (en) | 2016-12-23 | 2016-12-23 | Keyword clustering method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108241652A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657070A (en) * | 2018-12-11 | 2019-04-19 | 南京大学 | A kind of construction method of terminal auxiliary SWOT index system |
| CN109949070A (en) * | 2019-01-28 | 2019-06-28 | 平安科技（深圳）有限公司 | Usage rate of the user appraisal procedure, device, computer equipment and storage medium |
| CN110597987A (en) * | 2019-08-21 | 2019-12-20 | 微梦创科网络科技（中国）有限公司 | Search recommendation method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN102298576A (en) * | 2010-06-25 | 2011-12-28 | 株式会社理光 | Method and device for generating document keywords |
| CN102339417A (en) * | 2010-07-20 | 2012-02-01 | 百度在线网络技术（北京）有限公司 | Equipment, method and system for automatically optimizing account structure |
| CN103377190A (en) * | 2012-04-11 | 2013-10-30 | 阿里巴巴集团控股有限公司 | Trading platform based supplier information searching method and device |
| CN105608600A (en) * | 2015-12-18 | 2016-05-25 | 焦点科技股份有限公司 | Method for evaluating and optimizing B2B seller performances |
| CN105868377A (en) * | 2016-03-31 | 2016-08-17 | 北京奇艺世纪科技有限公司 | Method and device for pushing information |
-
2016
- 2016-12-23 CN CN201611209417.4A patent/CN108241652A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN102298576A (en) * | 2010-06-25 | 2011-12-28 | 株式会社理光 | Method and device for generating document keywords |
| CN102339417A (en) * | 2010-07-20 | 2012-02-01 | 百度在线网络技术（北京）有限公司 | Equipment, method and system for automatically optimizing account structure |
| CN103377190A (en) * | 2012-04-11 | 2013-10-30 | 阿里巴巴集团控股有限公司 | Trading platform based supplier information searching method and device |
| CN105608600A (en) * | 2015-12-18 | 2016-05-25 | 焦点科技股份有限公司 | Method for evaluating and optimizing B2B seller performances |
| CN105868377A (en) * | 2016-03-31 | 2016-08-17 | 北京奇艺世纪科技有限公司 | Method and device for pushing information |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657070A (en) * | 2018-12-11 | 2019-04-19 | 南京大学 | A kind of construction method of terminal auxiliary SWOT index system |
| CN109657070B (en) * | 2018-12-11 | 2023-06-09 | 南京大学 | Construction method of terminal-assisted SWOT index system |
| CN109949070A (en) * | 2019-01-28 | 2019-06-28 | 平安科技（深圳）有限公司 | Usage rate of the user appraisal procedure, device, computer equipment and storage medium |
| CN109949070B (en) * | 2019-01-28 | 2024-03-26 | 平安科技（深圳）有限公司 | User viscosity evaluation method, device, computer equipment and storage medium |
| CN110597987A (en) * | 2019-08-21 | 2019-12-20 | 微梦创科网络科技（中国）有限公司 | Search recommendation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Arunachalam et al. | Understanding big data analytics capabilities in supply chain management: Unravelling the issues, challenges and implications for practice | |
| US11593458B2 (en) | System for time-efficient assignment of data to ontological classes | |
| Vercellis | Business intelligence: data mining and optimization for decision making | |
| Mugunthan | Wireless rechargeable sensor network fault modeling and stability analysis | |
| CN103246672A (en) | Method and device for performing personalized recommendation on users | |
| CN106649316A (en) | Video pushing method and device | |
| CN108241652A (en) | Keyword clustering method and device | |
| CN108734587A (en) | The recommendation method and terminal device of financial product | |
| CN105825396A (en) | Co-occurrence-based advertisement label clustering method and system | |
| Bedau et al. | Open-ended technological innovation | |
| CN106528111A (en) | Similarity measurement method for data structure job program | |
| Nandy et al. | Evaluating quantitative measures for assessing functional similarity in engineering design | |
| Selsaas et al. | AFFM: Auto feature engineering in field-aware factorization machines for predictive analytics | |
| Wang | Design of agricultural product quality and safety big data fusion model based on blockchain technology | |
| Heo | The demand for life insurance | |
| CN114119068A (en) | Intelligent analysis method and management platform for pharmacy enterprise WeChat customer group | |
| CN112330426A (en) | Product recommendation method, device and storage medium | |
| CN109558432A (en) | Data processing method and device | |
| CN108132936A (en) | Data lead-in method and device | |
| CN109886299A (en) | A kind of user draws a portrait method, apparatus, readable storage medium storing program for executing and terminal device | |
| CN110309273A (en) | Answering method and device | |
| Fergina et al. | Modelling Of Data Warehouse With Making The Trend To Make Decision In Company XYZ | |
| Shang et al. | Deep learning generic features for cross-media retrieval | |
| Mengle et al. | Mastering machine learning on Aws: advanced machine learning in Python using SageMaker, Apache Spark, and TensorFlow | |
| CN108241675A (en) | Data processing method and device |
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 | ||
| CB02 | Change of applicant information |
Address after: 100080 No. 401, 4th Floor, Haitai Building, 229 North Fourth Ring Road, Haidian District, Beijing Applicant after: BEIJING GRIDSUM TECHNOLOGY Co.,Ltd. Address before: 100086 Cuigong Hotel, 76 Zhichun Road, Shuangyushu District, Haidian District, Beijing Applicant before: BEIJING GRIDSUM TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180703 |
|
| RJ01 | Rejection of invention patent application after publication |