CN103823803A - Keyword screening method, device and equipment - Google Patents
Keyword screening method, device and equipment Download PDFInfo
- Publication number
- CN103823803A CN103823803A CN201210464019.2A CN201210464019A CN103823803A CN 103823803 A CN103823803 A CN 103823803A CN 201210464019 A CN201210464019 A CN 201210464019A CN 103823803 A CN103823803 A CN 103823803A
- Authority
- CN
- China
- Prior art keywords
- keyword
- score
- target keyword
- retrieval
- conversion ratio
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
- G06F16/162—Delete operations
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
An embodiment of the invention discloses a keyword screening method. The keyword screening method includes steps of acquiring a user-input keyword set in logs; computing scores of target keywords according to the keyword search number included in the keyword set, the search times of the target keywords and conversion rate of the target keywords; deleting the target keywords in the keyword set if the scores of the target keywords are smaller than the first preset value. By the aid of the keyword screening method, unpopular keywords can be quickly and accurately screened, occupation of too much space in the servers is avoided, and operating efficiency is improved.
Description
Technical field
The present invention relates to computer realm, relate in particular to method, device and the equipment of keyword screening.
Background technology
Existing a lot of e-commerce website adopts analyzes log statistic keyword, and the mode of then carrying out human configuration according to statistics is collected keyword and obtained cue set.
Unexpected winner keyword refers to the keyword that user seldom searches for, can only bring little flow to website, most of flow of website is all introduced by popular keyword, therefore in order to optimize the resource of website, often need the method for human configuration collection keyword to guarantee higher precision, but workload is very big, existing to upgrade in time and to eliminate becomes the crucial word problem of unexpected winner, particularly for the e-commerce website that has mass data.
Summary of the invention
Embodiment of the present invention technical matters to be solved is, a kind of method, device and equipment of keyword screening is provided.Can automatically eliminate unexpected winner keyword.
In order to solve the problems of the technologies described above, the embodiment of the present invention provides a kind of method of screening keyword, comprising:
Gather the keyword set that at least comprises keyword retrieval quantity, keyword retrieval number of times and keyword conversion ratio of user's input in daily record;
Calculate the score of described target keyword according to the conversion ratio of the retrieval number of times of the target critical word and search quantity comprising in described keyword set, described target keyword and described target keyword;
If the score of described target keyword is less than the first prevalue, from keyword set, delete described target keyword.
Wherein, also comprise:
If when the score of described target keyword is greater than described the first prevalue and is less than the second prevalue, described target keyword is saved to observation set of words;
If when the score of described target keyword is greater than described the second prevalue, described target keyword is saved to cue set.
Wherein, the computing formula of calculating the score of described target keyword comprises:
FScore(x)=α
1*FCommdiyScore(x)+α
2*FQueryScore(x)+α
3*FHotSaleScore(x);
Wherein α
1, α
2and α
3for weight parameter, and α
1+ α
2+ α
3=1;
FScore (x) is the score of target keyword x, and FCommdiyScore (x) is correlativity score, and described correlativity score is to calculate according to the retrieval quantity of target keyword x;
FQueryScore (x) is inquiry temperature score, and described query and search number of times score is to calculate according to the retrieval number of times of target keyword x;
FHotSaleScore (x) is conversion ratio score, and described conversion ratio score is to calculate according to the conversion ratio of target keyword x.
Wherein, calculating described correlativity score according to the retrieval quantity of target keyword x comprises:
The summation of the retrieval quantity of the keyword that is top N according to the retrieval quantity of target keyword x and rank calculates;
Wherein, N is the quantity of preset keyword, and the retrieval quantity of the keyword more at most rank of this keyword is more forward.
Wherein, calculating described inquiry temperature score according to the retrieval quantity of target keyword x comprises:
According to the retrieval number of times of target keyword x and last time target keyword x inquiry temperature score calculate.
Wherein, calculating described conversion ratio score according to the retrieval quantity of target keyword x comprises:
Calculate according to the quantity N of the conversion ratio of target keyword x and preset keyword.
Correspondingly, the embodiment of the present invention also provides a kind of keyword screening plant, comprising:
Acquisition module, for gathering the keyword set that at least comprises keyword retrieval quantity, keyword retrieval number of times and keyword conversion ratio of daily record user input;
Computing module, calculates the score of described target keyword for the retrieval number of times of the target critical word and search quantity comprising according to described keyword set, described target keyword and the conversion ratio of described target keyword;
Removing module if be less than the first prevalue for the score of described target keyword, is deleted described target keyword from keyword set.
Wherein, also comprise:
Judge module, if when being greater than described the first prevalue and being less than the second prevalue for the score of described target keyword, described target keyword is saved to observation set of words, if when the score of described target keyword is greater than described the second prevalue, described target keyword is saved to cue set.
Wherein, described computing module comprises:
Acquiring unit, for obtaining the retrieval number of times of target critical word and search quantity, described target keyword and three parameters of the conversion ratio of described target keyword;
Computing unit, the retrieval number of times of the target critical word and search quantity comprising for the keyword set of obtaining according to described acquiring unit, described target keyword and the conversion ratio of described target keyword calculate the score of described target keyword;
Wherein, the computing formula that described computing unit calculates the score of described target keyword comprises:
FScore (x)=α 1*FCommdiyScore (x)+α 2*FQueryScore (x)+α 3*FHotSaleScore (x), wherein α
1, α
2and α
3for weight parameter, and α
1+ α
2+ α
3=1, FScore (x) is the score of target keyword x; FCommdiyScore (x) is correlativity score, and described correlativity score is to calculate according to the retrieval quantity of target keyword x; FQueryScore (x) is query and search number of times score, and described query and search number of times score is to calculate according to the retrieval number of times of target keyword x; FHotSaleScore (x) is conversion ratio score, and described conversion ratio score is to calculate according to the conversion ratio of target keyword x.
Correspondingly, the embodiment of the present invention also provides a kind of electronic equipment,, comprise above-mentioned any device
Implement the embodiment of the present invention, there is following beneficial effect:
Implement embodiments of the invention, by gathering the keyword set of user's input in daily record, and obtain the retrieval number of times of target critical word and search quantity, described target keyword and the conversion ratio of described target keyword and calculate the score of target keyword according to keyword set, determine whether to eliminate this target keyword by Comparison score, can eliminate accurately rapidly the keyword that becomes unexpected winner, avoid too much taking the space of server, improved the efficiency of operation.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, to the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skills, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is the schematic flow sheet of the method for a kind of keyword screening of the present invention;
Fig. 2 is the another kind of schematic flow sheet of a kind of keyword screening technique of the present invention;
Fig. 3 is the structural representation of a kind of keyword screening plant of the present invention;
Fig. 4 is another structural representation of a kind of keyword screening plant of the embodiment of the present invention;
Fig. 5 is the structural representation of computing module in Fig. 4.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, rather than whole embodiment.Based on the embodiment in the present invention, those of ordinary skills, not making the every other embodiment obtaining under creative work prerequisite, belong to the scope of protection of the invention.
Referring to Fig. 1, the schematic flow sheet of the screening technique of a kind of keyword of the present invention, the method comprises:
The keyword set that at least comprises keyword retrieval quantity, keyword retrieval number of times and keyword conversion ratio of user's input in step 101, collection daily record.
Concrete, in the daily record of server, record user's Visitor Logs, from daily record, obtain the keyword set of a period, described keyword set comprises the information such as keyword and the Search Results obtaining according to this keyword of each user's input, and described keyword retrieval quantity refers to that user inputs the quantity of the result for retrieval that a keyword obtains.
Concrete, target keyword refers to any one in the keyword of in keyword set user input, the conversion ratio of target keyword refers to the ratio of the actual conversion that the flow introduced by keyword and this keyword finally reach, such as in e-commerce website, use the number of times of target critical word and search and several ratio of concluding the transaction.According to target critical word and search quantity, these 3 parameters of the retrieval number of times of target keyword and the conversion ratio of target keyword, utilize preset formula to calculate the score of this target keyword, and target keyword is quantized.
If the score of the described target keyword of step 103 is less than the first prevalue, from described keyword set, delete described target keyword.
Concrete, in the time that the score of described target keyword is less than the first prevalue, determine that this target keyword is unexpected winner keyword, deletes this target keyword from keyword set.
Implement embodiments of the invention, by gathering the keyword set of user's input in daily record, and obtain the retrieval number of times of target critical word and search quantity, described target keyword and the conversion ratio of described target keyword and calculate the score of target keyword according to keyword set, determine whether to eliminate this target keyword by Comparison score, can eliminate accurately rapidly the keyword that becomes unexpected winner, avoid too much taking the space of server, improved the efficiency of operation.
Referring to Fig. 2, be another schematic flow sheet of a kind of keyword screening technique of the embodiment of the present invention, the method comprises:
The keyword set that at least comprises keyword retrieval quantity, keyword retrieval number of times and keyword conversion ratio of user's input in step 201, collection daily record.
Concrete, in the daily record of server, record user's Visitor Logs, from daily record, obtain the keyword set of a period, described keyword set comprises the information such as keyword and the Search Results obtaining according to this keyword of each user's input, for example keyword set comprises Li Ning, Nike, Jordon, Adidas and 5 keywords of Kuang Wei, also comprise the search information obtaining according to these 5 keywords, as the conversion ratio of the retrieval quantity of the searching times of keyword " Li Ning ", keyword " Li Ning " and keyword " Li Ning " simultaneously.
Concrete, the computing formula of the score of described target keyword comprises:
FScore (x)=α
1* FCommdiyScore (x)+α
2* FQueryScore (x)+α
3* FHotSaleScore (x), wherein α
1, α
2and α
3for weight parameter, and α
1+ α
2+ α
3=1, FScore (x) is the score of target keyword x, and FCommdiyScore (x) is correlativity score, and described correlativity score is to calculate according to the retrieval quantity of target keyword x; FQueryScore (x) is query and search number of times score, and described query and search number of times score is to calculate according to the retrieval number of times of target keyword x; FHotSaleScore (x) is conversion ratio score, and described conversion ratio score is to calculate according to the conversion ratio of target keyword x.
Further, the summation of the retrieval quantity of the keyword that described correlativity score is is top N according to the retrieval quantity of target keyword x and rank calculates, wherein, N is the quantity of preset keyword, and the retrieval quantity of the keyword more at most rank of this keyword is more forward.For example target keyword x is " Li Ning ", and the quantity of supposing preset keyword is 100, be ranked first into keyword, the retrieval quantity of its this keyword is maximum.Described query and search number of times score be according to the retrieval number of times of target keyword x and last time target keyword x inquiry temperature score calculate.Described conversion ratio score is to calculate according to the quantity of the conversion ratio of target keyword x and preset keyword.
Further concrete, FCommdiyScore (x)=BaseScore*v/ (v+m), wherein, BaseScore is the self-defining basic score in website, v is the retrieval quantity of target keyword x, and m is that rank is the summation of the retrieval quantity of the keyword of top N, wherein, N is the quantity of preset keyword, and the retrieval quantity of the keyword more at most rank of this keyword is more forward.Suppose that keyword x is for " Li Ning ", Basescore=500, N=100, m=100000, suppose that keyword " Li Ning " commodity number is 1000, be v=1000, correlativity score FCommdiyScore (the x)=500*1000 (1000+100000)=4.95 of this keyword so.
FQueryScore (x)=q+e
-aT* LastFQueryScore (x), wherein q is target keyword x retrieval number of times, a is attenuation coefficient, and T is the time interval of this calculating and last computation, generally take sky as the LastFQueryScore of unit (x) is the inquiry temperature score of target keyword x last time.The retrieval number of times of supposing keyword Li Ning is 100 times, i.e. q=100.
Attenuation coefficient a is for for for a long time there is no cold word, the uncommon word of user search and being once that the inquiry score of ageing extremely strong focus word is made attenuation processing, attenuation coefficient a can determine according to following method: be equally divided into 500 according to the inquiry temperature score of the target keyword of adding up in the schedule time, need in 100 days, decay to 1 point, by equation 500*e
-a100=1 solves the value of attenuation coefficient a.The computing formula of inquiry temperature score can be to ageing very strong focus word its score that decays, and for the keyword that is becoming at present focus, due to its retrieval number of times very high (being that q value is larger), decay factor almost can be ignored its impact, therefore can carry out attenuation processing to unexpected winner keyword accurately.
The computing formula of the conversion ratio score of target keyword comprises:
FHotSaleScore (x)=G*{1-[t (x)-1]/N}, wherein, G is the maximal value of preset conversion ratio score, t (x) is the rank order of the conversion ratio of target keyword x, N is the quantity of preset keyword, and wherein the rank of higher this keyword of the conversion ratio of keyword is more forward.
The maximal value of supposing the preset conversion ratio score in electric business website is 1000, the quantity N=100 of preset keyword, calculate the conversion ratio score FHotSaleScore (x)=1000 (1-0/100)=1000 of conversion ratio rank at the keyword of 100, the conversion ratio of the 50th keyword of conversion ratio rank must be divided into FHotSaleScore (x)=1000 (1-49/100)=510, by that analogy, the conversion ratio of the keyword of rank after 100 must be divided into negative value, for the convenience of calculating, can stipulate in this case must be divided into 0 for conversion ratio.
Whether step 203, score are greater than the second prevalue, and in the time being judged as YES, execution step 205 performs step 204 in the time being judged as NO.
Concrete, in the time that the score of target keyword is greater than the second prevalue, show that this target keyword is popular keyword, be kept in the cue set in server, in the time inputting the prefix of this target keyword next time, supplement suffix with prompting user input for user.Set after threshold value, system can automatically be collected and generate keyword dictionary, is conducive to save manpower, high efficiency operation
In the time that the score of target keyword is less than the first prevalue, show that this target keyword is unexpected winner word, deletes this target keyword from keyword set.
In the time that the score of target keyword is less than the second prevalue and is greater than the first prevalue, described target keyword is saved to observation set of words.
Implement embodiments of the invention, by gathering the keyword set of user's input in daily record, and obtain the retrieval number of times of target critical word and search quantity, described target keyword and the conversion ratio of described target keyword and calculate the score of target keyword according to keyword set, determine whether to eliminate this target keyword by Comparison score, can eliminate accurately rapidly the keyword that becomes unexpected winner, avoid too much taking the space of server, improved the efficiency of operation.
Referring to Fig. 3, be the structural representation of a kind of keyword screening plant of the embodiment of the present invention, this device comprises:
Concrete, in the daily record of server, record user's Visitor Logs, acquisition module 11 obtains the keyword set of a period from daily record, described keyword set comprises the information such as keyword and the Search Results obtaining according to this keyword of each user's input, for example keyword set comprises Li Ning, Nike, Jordon, Adidas and 5 keywords of Kuang Wei, also comprise the search information obtaining according to these 5 keywords, as the conversion ratio of the searching times of keyword " Li Ning ", the retrieval quantity that comprises keyword " Li Ning " and keyword " Li Ning " simultaneously.
Concrete, target keyword refers to any one in the keyword of in keyword set user input, the conversion ratio of target keyword refers to the ratio of the actual conversion that the flow introduced by keyword and this keyword finally reach, such as in e-commerce website, use the number of times of target critical word and search and several ratio of concluding the transaction.According to target critical word and search quantity, these 3 parameters of the retrieval number of times of target keyword and the conversion ratio of target keyword, computing module 12 utilizes preset formula to calculate the score of this target keyword, and target keyword is quantized.
Removing module 13 if be less than the first prevalue for the score of described target keyword, is deleted described target keyword from keyword set.
Concrete, removing module 13 judges when the score of described target keyword is less than the first prevalue, determines that this target keyword is unexpected winner keyword, and this target keyword is deleted from keyword set.
Implement embodiments of the invention, by gathering the keyword set of user's input in daily record, and obtain the retrieval number of times of target critical word and search quantity, described target keyword and the conversion ratio of described target keyword and calculate the score of target keyword according to keyword set, determine whether to eliminate this target keyword by Comparison score, can eliminate accurately rapidly the keyword that becomes unexpected winner, avoid too much taking the space of server, improved the efficiency of operation.
Further, referring to Fig. 4 and Fig. 5, described keyword screening plant also comprises;
Wherein, described computing module 12 comprises:
Acquiring unit 121, for obtaining the retrieval number of times of target critical word and search quantity, described target keyword and three parameters of the conversion ratio of described target keyword;
Wherein, the computing formula that described computing unit 122 calculates the score of described target keyword comprises:
FScore (x)=α 1*FCommdiyScore (x)+α 2*FQueryScore (x)+α 3*FHotSaleScore (x), wherein α
1, α
2and α
3for weight parameter, and α
1+ α
2+ α
3=1, FScore (x) is the score of target keyword x; FCommdiyScore (x) is correlativity score, and described correlativity score is to calculate according to the retrieval quantity of target keyword x; FQueryScore (x) is query and search number of times score, and described query and search number of times score is to calculate according to the retrieval number of times of target keyword x; FHotSaleScore (x) is conversion ratio score, and described conversion ratio score is to calculate according to the conversion ratio of target keyword x.
Concrete, FCommdiyScore (x)=BaseScore*v/ (v+m), wherein, BaseScore is the self-defining basic score in website, v is the retrieval quantity of target keyword x, and m comprises the summation that rank is the retrieval quantity of the keyword of top N, wherein, N is the quantity of preset keyword, and the retrieval quantity that the comprises keyword more at most rank of this keyword is more forward.Suppose that keyword x is for " Li Ning ", Basescore=500, N=100, m=100000, suppose that keyword " Li Ning " commodity number is 1000, be v=1000, correlativity score FCommdiyScore (the x)=500*1000 (1000+100000)=4.95 of this keyword so.
FQueryScore (x)=q+e
-aT* LastFQueryScore (x), wherein q is target keyword x retrieval number of times, a is attenuation coefficient, and T is the time interval of this calculating and last computation, generally take sky as the LastFQueryScore of unit (x) is the inquiry temperature score of target keyword x last time.The retrieval number of times of supposing keyword Li Ning is 100 times, i.e. q=100.
Attenuation coefficient a is for for for a long time there is no cold word, the uncommon word of user search and being once that the inquiry score of ageing extremely strong focus word is made attenuation processing, attenuation coefficient a can determine according to following method: be equally divided into 500 according to the inquiry temperature score of the target keyword of adding up in the schedule time, need in 100 days, decay to 1 point, by equation 500*e
-a100=1 solves the value of attenuation coefficient a.The computing formula of inquiry temperature score can be to ageing very strong focus word its score that decays, and for the keyword that is becoming at present focus, due to its retrieval number of times very high (being that q value is larger), decay factor almost can be ignored its impact, therefore can carry out attenuation processing to unexpected winner keyword accurately.
The computing formula of the conversion ratio score of target keyword comprises:
FHotSaleScore (x)=G*{1-[t (x)-1]/N}, wherein, G is the maximal value of preset conversion ratio score, t (x) is the rank order of the conversion ratio of target keyword x, N is the quantity of preset keyword, and wherein the rank of higher this keyword of the conversion ratio of keyword is more forward.
The maximal value of supposing the preset conversion ratio score in electric business website is 1000, the quantity N=100 of preset keyword, calculate the conversion ratio score FHotSaleScore (x)=1000 (1-0/100)=1000 of conversion ratio rank at the keyword of 100, the conversion ratio of the 50th keyword of conversion ratio rank must be divided into FHotSaleScore (x)=1000 (1-49/100)=510, by that analogy, the conversion ratio of the keyword of rank after 100 must be divided into negative value, for the convenience of calculating, can stipulate in this case must be divided into 0 for conversion ratio.
Implement embodiments of the invention, by gathering the keyword set of user's input in daily record, and the conversion ratio that obtains the retrieval number of times of target critical word and search quantity, described target keyword and comprise described target keyword according to keyword set calculates the score of target keyword, determine whether to eliminate this target keyword by Comparison score, can eliminate accurately rapidly the keyword that becomes unexpected winner, avoid too much taking the space of server, improved the efficiency of operation.
One of ordinary skill in the art will appreciate that all or part of flow process realizing in above-described embodiment method, can carry out the hardware that instruction is relevant by computer program to complete, described program can be stored in a computer read/write memory medium, this program, in the time carrying out, can comprise as the flow process of the embodiment of above-mentioned each side method.Wherein, described storage medium can be magnetic disc, CD, read-only store-memory body (Read-Only Memory, ROM) or random store-memory body (Random Access Memory, RAM) etc.
Above disclosed is only a kind of preferred embodiment of the present invention, certainly can not limit with this interest field of the present invention, one of ordinary skill in the art will appreciate that all or part of flow process that realizes above-described embodiment, and the equivalent variations of doing according to the claims in the present invention, still belong to the scope that invention is contained.
Claims (10)
1. a method for keyword screening, is characterized in that, comprising:
Gather the keyword set that at least comprises keyword retrieval quantity, keyword retrieval number of times and keyword conversion ratio of user's input in daily record;
Calculate the score of described target keyword according to the conversion ratio of the retrieval number of times of the target critical word and search quantity comprising in described keyword set, described target keyword and described target keyword;
If the score of described target keyword is less than the first prevalue, from keyword set, delete described target keyword.
2. the method for claim 1, is characterized in that, also comprises:
If when the score of described target keyword is greater than described the first prevalue and is less than the second prevalue, described target keyword is saved to observation set of words;
If when the score of described target keyword is greater than described the second prevalue, described target keyword is saved to cue set.
3. method as claimed in claim 2, is characterized in that, the computing formula of calculating the score of described target keyword comprises:
FScore(x)=α
1*FCommdiyScore(x)+α
2*FQueryScore(x)+α
3*FHotSaleScore(x);
Wherein α
1, α
2and α
3for weight parameter, and α
1+ α
2+ α
3=1;
FScore (x) is the score of target keyword x, and FCommdiyScore (x) is correlativity score, and described correlativity score is to calculate according to the retrieval quantity of target keyword x;
FQueryScore (x) is inquiry temperature score, and described query and search number of times score is to calculate according to the retrieval number of times of target keyword x;
FHotSaleScore (x) is conversion ratio score, and described conversion ratio score is to calculate according to the conversion ratio of target keyword x.
4. method as claimed in claim 3, is characterized in that, calculates described correlativity score comprise according to the retrieval quantity of target keyword x:
The summation of the retrieval quantity of the keyword that is top N according to the retrieval quantity of target keyword x and rank calculates;
Wherein, N is the quantity of preset keyword, and the retrieval quantity of the keyword more at most rank of this keyword is more forward.
5. method as claimed in claim 3, is characterized in that, calculates described inquiry temperature score comprise according to the retrieval quantity of target keyword x:
According to the retrieval number of times of target keyword x and last time target keyword x inquiry temperature score calculate.
6. method as claimed in claim 3, is characterized in that, calculates described conversion ratio score comprise according to the retrieval quantity of target keyword x:
Calculate according to the quantity N of the conversion ratio of target keyword x and preset keyword.
7. a keyword screening plant, is characterized in that, comprising:
Acquisition module, for gathering the keyword set that at least comprises keyword retrieval quantity, keyword retrieval number of times and keyword conversion ratio of daily record user input;
Computing module, calculates the score of described target keyword for the retrieval number of times of the target critical word and search quantity comprising according to described keyword set, described target keyword and the conversion ratio of described target keyword;
Removing module if be less than the first prevalue for the score of described target keyword, is deleted described target keyword from keyword set.
8. device as claimed in claim 7, is characterized in that, also comprises:
Judge module, if when being greater than described the first prevalue and being less than the second prevalue for the score of described target keyword, described target keyword is saved to observation set of words, if when the score of described target keyword is greater than described the second prevalue, described target keyword is saved to cue set.
9. device as claimed in claim 8, is characterized in that, described computing module comprises:
Acquiring unit, for obtaining the retrieval number of times of target critical word and search quantity, described target keyword and three parameters of the conversion ratio of described target keyword;
Computing unit, the retrieval number of times of the target critical word and search quantity comprising for the keyword set of obtaining according to described acquiring unit, described target keyword and the conversion ratio of described target keyword calculate the score of described target keyword;
Wherein, the computing formula that described computing unit calculates the score of described target keyword comprises:
FScore (x)=α 1*FCommdiyScore (x)+α 2*FQueryScore (x)+α 3*FHotSaleScore (x), wherein α
1, α
2and α
3for weight parameter, and α
1+ α
2+ α
3=1, FScore (x) is the score of target keyword x; FCommdiyScore (x) is correlativity score, and described correlativity score is to calculate according to the retrieval quantity of target keyword x; FQueryScore (x) is query and search number of times score, and described query and search number of times score is to calculate according to the retrieval number of times of target keyword x; FHotSaleScore (x) is conversion ratio score, and described conversion ratio score is to calculate according to the conversion ratio of target keyword x.
10. an electronic equipment, is characterized in that, comprises the device as described in claim 7-9 any one.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210464019.2A CN103823803B (en) | 2012-11-16 | 2012-11-16 | A kind of method, apparatus and equipment of keyword screening |
PCT/CN2013/086587 WO2014075572A1 (en) | 2012-11-16 | 2013-11-06 | Method and apparatus for selecting a keyword |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210464019.2A CN103823803B (en) | 2012-11-16 | 2012-11-16 | A kind of method, apparatus and equipment of keyword screening |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103823803A true CN103823803A (en) | 2014-05-28 |
CN103823803B CN103823803B (en) | 2018-12-07 |
Family
ID=50730584
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210464019.2A Active CN103823803B (en) | 2012-11-16 | 2012-11-16 | A kind of method, apparatus and equipment of keyword screening |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN103823803B (en) |
WO (1) | WO2014075572A1 (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108563713A (en) * | 2018-03-29 | 2018-09-21 | 阿里巴巴集团控股有限公司 | Keyword rule generating method and device and electronic equipment |
CN109064221A (en) * | 2018-07-20 | 2018-12-21 | 广州市丰申网络科技有限公司 | AdWords intelligence put-on method and equipment based on big data technology |
CN110347900A (en) * | 2019-07-10 | 2019-10-18 | 腾讯科技(深圳)有限公司 | A kind of importance calculation method of keyword, device, server and medium |
CN110399479A (en) * | 2018-04-20 | 2019-11-01 | 北京京东尚科信息技术有限公司 | Search for data processing method, device, electronic equipment and computer-readable medium |
CN110609952A (en) * | 2019-08-15 | 2019-12-24 | 中国平安财产保险股份有限公司 | Data acquisition method and system and computer equipment |
CN114154064A (en) * | 2021-12-01 | 2022-03-08 | 北京鸥鹭数据科技有限公司 | Commodity keyword optimization method and device |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109657116A (en) * | 2018-11-12 | 2019-04-19 | 平安科技(深圳)有限公司 | A kind of public sentiment searching method, searcher, storage medium and terminal device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7082429B2 (en) * | 2003-12-10 | 2006-07-25 | National Chiao Tung University | Method for web content filtering |
CN101158957A (en) * | 2007-10-23 | 2008-04-09 | 浙江大学 | Internet hot point topics correlativity excavation method |
CN100520782C (en) * | 2007-11-09 | 2009-07-29 | 清华大学 | News keyword abstraction method based on word frequency and multi-component grammar |
US20090210409A1 (en) * | 2007-05-01 | 2009-08-20 | Ckc Communications, Inc. Dba Connors Communications | Increasing online search engine rankings using click through data |
CN102262625A (en) * | 2009-12-24 | 2011-11-30 | 华为技术有限公司 | Method and device for extracting keywords of page |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102135967B (en) * | 2010-01-27 | 2013-06-05 | 华为技术有限公司 | Webpage keywords extracting method, device and system |
-
2012
- 2012-11-16 CN CN201210464019.2A patent/CN103823803B/en active Active
-
2013
- 2013-11-06 WO PCT/CN2013/086587 patent/WO2014075572A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7082429B2 (en) * | 2003-12-10 | 2006-07-25 | National Chiao Tung University | Method for web content filtering |
US20090210409A1 (en) * | 2007-05-01 | 2009-08-20 | Ckc Communications, Inc. Dba Connors Communications | Increasing online search engine rankings using click through data |
CN101158957A (en) * | 2007-10-23 | 2008-04-09 | 浙江大学 | Internet hot point topics correlativity excavation method |
CN100520782C (en) * | 2007-11-09 | 2009-07-29 | 清华大学 | News keyword abstraction method based on word frequency and multi-component grammar |
CN102262625A (en) * | 2009-12-24 | 2011-11-30 | 华为技术有限公司 | Method and device for extracting keywords of page |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108563713A (en) * | 2018-03-29 | 2018-09-21 | 阿里巴巴集团控股有限公司 | Keyword rule generating method and device and electronic equipment |
CN108563713B (en) * | 2018-03-29 | 2021-08-10 | 创新先进技术有限公司 | Keyword rule generation method and device and electronic equipment |
CN110399479A (en) * | 2018-04-20 | 2019-11-01 | 北京京东尚科信息技术有限公司 | Search for data processing method, device, electronic equipment and computer-readable medium |
CN109064221A (en) * | 2018-07-20 | 2018-12-21 | 广州市丰申网络科技有限公司 | AdWords intelligence put-on method and equipment based on big data technology |
CN110347900A (en) * | 2019-07-10 | 2019-10-18 | 腾讯科技(深圳)有限公司 | A kind of importance calculation method of keyword, device, server and medium |
CN110347900B (en) * | 2019-07-10 | 2022-12-27 | 腾讯科技(深圳)有限公司 | Keyword importance calculation method, device, server and medium |
CN110609952A (en) * | 2019-08-15 | 2019-12-24 | 中国平安财产保险股份有限公司 | Data acquisition method and system and computer equipment |
CN110609952B (en) * | 2019-08-15 | 2024-04-26 | 中国平安财产保险股份有限公司 | Data acquisition method, system and computer equipment |
CN114154064A (en) * | 2021-12-01 | 2022-03-08 | 北京鸥鹭数据科技有限公司 | Commodity keyword optimization method and device |
Also Published As
Publication number | Publication date |
---|---|
CN103823803B (en) | 2018-12-07 |
WO2014075572A1 (en) | 2014-05-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103823803A (en) | Keyword screening method, device and equipment | |
KR100544514B1 (en) | Method and system for determining relation between search terms in the internet search system | |
CN106874292B (en) | Topic processing method and device | |
KR102080362B1 (en) | Query expansion | |
KR101681109B1 (en) | An automatic method for classifying documents by using presentative words and similarity | |
US20100262610A1 (en) | Identifying Subject Matter Experts | |
US20130268482A1 (en) | Determining entity popularity using search queries | |
US11907659B2 (en) | Item recall method and system, electronic device and readable storage medium | |
CN103136228A (en) | Image search method and image search device | |
CN103593371A (en) | Method and device for recommending search keywords | |
CN110633330A (en) | Event discovery method, device, equipment and storage medium | |
CN102388374A (en) | Method and device for data storage | |
CN101963965A (en) | Document indexing method, data query method and server based on search engine | |
JP2009031931A (en) | Search word clustering device, method, program and recording medium | |
CN1629837A (en) | Method and apparatus for processing, browsing and classified searching of electronic document and system thereof | |
CN102521374A (en) | Intelligent data aggregation method and intelligent data aggregation system based on relational online analytical processing | |
CN110825868A (en) | Topic popularity based text pushing method, terminal device and storage medium | |
CN103688256A (en) | Method, device and system for determining video quality parameter based on comment | |
CN1503164A (en) | Information process device and program for same | |
CN108875050B (en) | Text-oriented digital evidence-obtaining analysis method and device and computer readable medium | |
CN107943937B (en) | Debtor asset monitoring method and system based on judicial public information analysis | |
CN103034709B (en) | Retrieving result reordering system and method | |
CN102200984A (en) | Search method based on compound words and search engine server | |
Abdelmgeid Amin | Using a query expansion technique to improve document retrieval | |
CN103377187A (en) | Method, device and program for paragraph segmentation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |