CN103377249A - Keyword putting method and system - Google Patents
Keyword putting method and system Download PDFInfo
- Publication number
- CN103377249A CN103377249A CN2012101295650A CN201210129565A CN103377249A CN 103377249 A CN103377249 A CN 103377249A CN 2012101295650 A CN2012101295650 A CN 2012101295650A CN 201210129565 A CN201210129565 A CN 201210129565A CN 103377249 A CN103377249 A CN 103377249A
- Authority
- CN
- China
- Prior art keywords
- keyword
- key element
- word
- dictionary
- key
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a keyword putting method which includes the following steps: S1 obtaining keywords to be put; S2 calculating the transition probability of the keywords; S3 putting the keywords with the transition probability reaching a first threshold through an SEM channel and putting the keywords with the transition probability not reaching the first threshold through an SEO channel. The invention further discloses a keyword putting system. By adopting the keyword putting method and system, the keywords suitable to be put on the electronic commerce websites can be automatically selected, the appropriate putting channels can be selected according to the transition probability of each keyword, keyword putting cost and benefit are both considered, and efficient management on keyword putting is achieved.
Description
Technical field
The present invention relates to a kind of keyword put-on method and system, particularly relate to a kind of automatic switching and discharge the search engine marketing of sub-business web site with keyword put-on method and the system of keyword.
Background technology
Society, the internet is deep among the life, and advantage the has been subject to user's such as search engine is convenient and swift with it, and quantity of information is huge favor, becomes the entrance of numerous users' online.Ecommerce has also caused businessman to stand in great numbers simultaneously, situation with keen competition in recent years fast development.E-commerce venture will show one's talent in competition, does search engine marketing well, and it is most important to allow the user accurately find out corresponding product in search engine.
In traditional search engine marketing, the keyword management mode is to be operating as the master with manpower manual, early stage at e-commerce development, and range of goods is few, and business is relatively vertical, and labor management can be satisfied business demand.But nowadays, electronic commercial company is all developing to comprehensive shopping platform, and product variety is up to hundreds thousand of, and the mode of labor management search engine keywords is unable to do what one wishes, becomes the bottleneck in the search engine marketing.
The inferior position of manpower management SEO (search engine optimization)/SEM (search engine marketing) keyword has:
1, can't find abundant keyword.Calculated in 1 minute with 1 word, 1 staff can only throw in 100,000 keywords in 1 year, and large-scale electricity merchant's keyword demand is millions of.
2, keyword is chaotic, is difficult to the formative tissue structure.Because manpower can't accurately be remembered the keyword once thrown in, also be difficult to accurately divide the kind of keyword, can cause and repeat to throw in, meaning of a word confusion is unclear.
3, be difficult to judge the value of keyword.The manual input can produce the bad word of a large amount of changing effects, causes the great wasting of resources.
For the large characteristics of electronic commercial affairs enterprise's keyword demand, need supermatic, the intelligent algorithm of a cover to ensure that SEO/SEM throws in quantity and the quality of keyword.
Summary of the invention
The technical problem to be solved in the present invention be when overcoming that the keyword demand is larger in the prior art labor management keyword cause keyword management chaotic, cause the defective of throwing in the lower keyword of transition probability easily, a kind of automatic management keyword is provided, is convenient to keyword classification, can judges keyword put-on method and system that keyword is worth.
The present invention solves above-mentioned technical matters by following technical proposals:
A kind of keyword put-on method, its characteristics are that it may further comprise the steps:
Step S
1, obtain keyword to be put;
Step S
2, calculate the transition probability of this keyword, after transition probability has represented user search this keyword, buy the probability of the commodity relevant with this keyword, transition probability can be expressed as: (buying number of times/search results pages number of clicks) * 100%;
Step S
3, keyword that transition probability is reached a first threshold throws in by the SEM channel.
Preferably, step S
3In further comprising the steps of: the keyword that conversion ratio does not reach this first threshold is thrown in by the SEO channel.Be that the higher keyword of transition probability can be thrown in by emphasis, and the SEM channel of charge can not thrown in the lower keyword of transition probability, and take free SEO as main.
Preferably, step S
1May further comprise the steps:
Step S
11, from a product database, obtain product information, and determine product category and call and the corresponding dictionary of this product category according to this product category according to this product information;
Step S
12, this product information is divided at least one key element;
Step S
13, utilize this dictionary and according to each key element product information cut word and become at least one key element keyword, and format this at least one key element keyword to unify the form of key element keyword;
Step S
14, calculate a rate of return on investment of each key element keyword, and select rate of return on investment to reach the key element keyword of a Second Threshold as this keyword.Wherein the computing formula of rate of return on investment is: ROI (rate of return on investment)=Sale (search in Website sales volume)/(Search (search in Website number of times) * CPC (average clicking cost)).Clearly, product information in not all this product database all is fit to be thrown in, the income of throwing in order to improve keyword, when selecting the key element keyword, the key element keyword that main selection rate of return on investment reaches certain setting value (Second Threshold) is thrown in the expenditure of keyword and the income that keyword brings as keyword to be put with balance.
Preferably, step S
13In to adopt the unified synon mode of a synonym dictionary, adopt the mode of unified capital and small letter and to adopt in the mode of replacing half double byte character one or more to format this at least one key element keyword to unify the form of key element keyword.For example synon unification: " hair dryer " and " hair-dryer "; Or, wrongly written or mispronounced characters corrigendum: " Nokia " and " the promise note is inferior "; Or the Chinese and English coupling is unified: " Dell " and modes such as " dell " are unified the form of this key element keyword.
Preferably, this dictionary is one or more in brand dictionary, generic name of the goods dictionary, unit dictionary, attribute dictionary, model dictionary and the conventional word dictionary.Conventional word dictionary is for for example having comprised all prepositions commonly used and the dictionary of auxiliary word.
Preferably, step S
12Afterwards, step S
13Before further comprising the steps of: as to adopt preposition and/or auxiliary word in the conventional word dictionary excision product information.
Preferably, this at least one key element is selected from following key element: brand key element, generic name of the goods key element, unit key element, attribute key element and model key element.
Preferably, step S
14In may further comprise the steps:
Step S
141, this unit key element of filtering, this attribute key element and this model key element the key element keyword;
Step S
142, calculate through step S
141This rate of return on investment of all the other each key element keywords after the filtering, and select rate of return on investment to reach the key element keyword of a Second Threshold as this keyword.The key element keyword of unit key elements such as " 3KG ", " 500 gram " is not worth, and usually is rejected.
Preferably, step S
1May further comprise the steps:
Step S
11, from a search history database, obtain searching key word, recorded the searching key word of user search and the search rate of each searching key word in this search history database;
Step S
12, the part in this searching key word of filtering, this part is: preposition, auxiliary word, unit, attribute and model;
Step S
13, will be through step S
12Searching key word after the filtering is as this keyword.
This search history database comprises that the user is at the word searching key word of search engine search, the searching key word searched in the website of user in ecommerce etc., this class word can the exact matching user the search custom, can obtain preferential chance of showing.
Preferably, step S
3May further comprise the steps:
Step S
31, judge whether the transition probability of each keyword reaches this first threshold, if enter step S
32If not, enter step S
33
Step S
32, this keyword is thrown in by the SEM channel;
Step S
33, judge whether the search rate of this keyword reaches one the 3rd threshold value, if enter step S
34If not, enter step S
35
Step S
34, this keyword is thrown in by the SEO channel;
Step S
35, abandon the input of this keyword.
Although be that the not high but keyword frequently searched for of some transition probabilities also has certain input and is worth, can throw in by free SEO channel.
The present invention also provides a kind of keyword jettison system, and its characteristics are that it comprises:
One keyword deriving means is used for obtaining keyword to be put;
One calculation element is for the transition probability of calculating this keyword;
One keyword delivery device is used for transition probability is reached the keyword of a first threshold by the input of SEM channel.
Preferably, this keyword delivery device also is used for conversion ratio is not reached the keyword of this first threshold by the input of SEO channel.
Preferably, this keyword deriving means comprises:
One information acquisition device is used for obtaining product information from a product database, and determines product category and call and the corresponding dictionary of this product category according to this product category according to this product information;
One key element generating apparatus is used for this product information is divided at least one key element;
All word devices are used for utilizing this dictionary and according to each key element product information being cut word becoming at least one key element keyword, and format this at least one key element keyword to unify the form of key element keyword;
One keyword generating apparatus is used for calculating a rate of return on investment of each key element keyword, and selects rate of return on investment to reach the key element keyword of a Second Threshold as this keyword.
Preferably, this is cut the word device and also is used for formaing this at least one key element keyword to unify the form of key element keyword with one or more that adopt the unified synon mode of a synonym dictionary, adopt the mode of unified capital and small letter and adopt the mode of replacing half double byte character.
Preferably, this dictionary is one or more in brand dictionary, generic name of the goods dictionary, unit dictionary, attribute dictionary, model dictionary and the conventional word dictionary.
Preferably, this cuts preposition and/or auxiliary word that the word device also is used for adopting conventional word dictionary excision product information.
Preferably, this at least one key element is selected from following key element: brand key element, generic name of the goods key element, unit key element, attribute key element and model key element.
Preferably, this keyword generating apparatus also comprises:
One filtering unit is for the key element keyword of this unit key element of filtering, this attribute key element and this model key element;
One computing unit is used for calculating this rate of return on investment of all the other each key element keywords after filtering, and selects rate of return on investment to reach the key element keyword of a Second Threshold as this keyword.
Preferably, this keyword deriving means comprises:
One search information acquisition device is used for obtaining searching key word from a search history database, has recorded the searching key word of user search and the search rate of each searching key word in this search history database;
One filtering device, for the part of this searching key word of filtering, this part is: preposition, auxiliary word, unit, attribute and model;
One keyword generating apparatus is used for the searching key word after this filtering device filtering as this keyword.
Preferably, this keyword delivery device comprises:
One first judgment means is used for judging whether the transition probability of each keyword reaches this first threshold, if enable one first delivery device; If not, enable one second judgment means;
This first delivery device is used for this keyword is thrown in by the SEM channel;
This second judgment means is used for judging whether the search rate of this keyword reaches one the 3rd threshold value, if enable one second delivery device; If not, abandon the input of this keyword;
This second delivery device is used for this keyword is thrown in by the SEO channel.
Positive progressive effect of the present invention is: the invention provides a kind of keyword put-on method and system, can automatically select out and be fit to the keyword that e-commerce website is thrown in, and select the input channel that is fit to according to the transition probability of each keyword, take into account cost and the keyword of keyword input and thrown in the income of bringing, realized the efficient management that keyword is thrown in.
Description of drawings
Fig. 1 is the process flow diagram of the keyword put-on method of the embodiment of the invention 1.
Fig. 2 is the structured flowchart of the keyword jettison system of the embodiment of the invention 1.
Fig. 3 is the process flow diagram of the keyword put-on method of the embodiment of the invention 2.
Fig. 4 is the structured flowchart of the keyword jettison system of the embodiment of the invention 2.
Embodiment
Provide preferred embodiment of the present invention below in conjunction with accompanying drawing, to describe technical scheme of the present invention in detail.
Embodiment 1
With reference to figure 1, the described keyword put-on method of present embodiment may further comprise the steps:
Step 102 is divided at least one key element with this product information, and this at least one key element is selected from following key element: brand key element, generic name of the goods key element, unit key element, attribute key element and model key element.
Step 103 adopts preposition and/or auxiliary word in the conventional word dictionary excision product information.
Step 104 is utilized this dictionary and according to each key element product information is cut word to become at least one key element keyword, and formats this at least one key element keyword to unify the form of key element keyword.Wherein adopt the unified synon mode of a synonym dictionary, adopt the mode of unified capital and small letter and adopt in the mode of replacing half double byte character one or more to format this at least one key element keyword to unify the form of key element keyword.
Step 105 is calculated a rate of return on investment of each key element keyword, and selects rate of return on investment to reach the key element keyword of a Second Threshold as this keyword.Specifically, the key element keyword of elder generation's this unit key element of filtering, this attribute key element and this model key element, such as the key element keyword " 5kg " of unit key element, the key element keyword " redness " of attribute key element and the key element keyword " N97 " of model key element etc., follow in this rate of return on investment of calculating all the other each key element keywords after filtering, and select rate of return on investment to reach the key element keyword of a Second Threshold as this keyword.
Step 106 is calculated the transition probability of this keyword, and transition probability is expressed as: (buying number of times/search results pages number of clicks) * 100%.
Step 107 judges whether the transition probability of this keyword reaches first threshold, if enter step 108; If not, enter step 109.
Step 108 is thrown in this keyword by the SEM channel.
Step 109 is thrown in this keyword by the SEO channel.
With reference to figure 2, introduce the described keyword jettison system of present embodiment, it comprises:
One keyword deriving means 1 is used for obtaining keyword to be put;
One calculation element 2 is for the transition probability of calculating this keyword;
One keyword delivery device 3, the keyword that is used for transition probability is reached a first threshold is by the input of SEM channel, and the keyword that conversion ratio is not reached this first threshold is thrown in by the SEO channel.
Specifically, this keyword deriving means 1 comprises:
One information acquisition device 11, be used for obtaining product information from a product database, and determine product category and call and the corresponding dictionary of this product category according to this product category according to this product information, wherein, this dictionary is one or more in brand dictionary, generic name of the goods dictionary, unit dictionary, attribute dictionary, model dictionary and the conventional word dictionary;
One key element generating apparatus 12 is used for this product information is divided at least one key element, and wherein, this at least one key element is selected from following key element: brand key element, generic name of the goods key element, unit key element, attribute key element and model key element;
All word devices 13 are used for utilizing this dictionary and according to each key element product information being cut word becoming at least one key element keyword, and format this at least one key element keyword to unify the form of key element keyword;
One keyword generating apparatus 14 is used for calculating a rate of return on investment of each key element keyword, and selects rate of return on investment to reach the key element keyword of a Second Threshold as this keyword.
Wherein, this cut that word device 13 also be used for to adopt the unified synon mode of a synonym dictionary, adopts the mode of unified capital and small letter and adopt the mode of replacing half double byte character one or more format this at least one key element keyword to unify the form of key element keyword.And this cuts preposition and/or auxiliary word that word device 13 also is used for adopting conventional word dictionary excision product information.
More specifically, this keyword generating apparatus 14 also comprises:
One filtering unit 141 is for the key element keyword of this unit key element of filtering, this attribute key element and this model key element;
One computing unit 142 is used for calculating this rate of return on investment of all the other each key element keywords after filtering, and selects rate of return on investment to reach the key element keyword of a Second Threshold as this keyword.
With reference to figure 3, introduce the described keyword put-on method of present embodiment, it may further comprise the steps:
Step 101 is obtained searching key word from a search history database, recorded the searching key word of user search and the search rate of each searching key word in this search history database.
Step 103 will be through step, and the searching key word after 102 filterings is as this keyword.
Step 104 is calculated the transition probability of this keyword.
Step 105 judges whether the transition probability of each keyword reaches this first threshold, if enter step 106; If not, enter step 107.
Step 106 is thrown in this keyword by the SEM channel.
Step, 107, judge whether the search rate of this keyword reaches one the 3rd threshold value, if enter step 108; If not, enter step 109.
Step 108 is thrown in this keyword by the SEO channel.
Step 109 is abandoned the input of this keyword.
With reference to figure 4, introduce the described keyword jettison system of present embodiment, it comprises:
One keyword deriving means 1 is used for obtaining keyword to be put;
One calculation element 2 is for the transition probability of calculating this keyword;
One keyword delivery device 3, the keyword that is used for transition probability is reached a first threshold is by the input of SEM channel, and the keyword that conversion ratio is not reached this first threshold is thrown in by the SEO channel.
As different from Example 1, this keyword deriving means 1 comprises:
One search information acquisition device 11 is used for obtaining searching key word from a search history database, has recorded the searching key word of user search and the search rate of each searching key word in this search history database;
One filtering device 12, for the part of this searching key word of filtering, this part is: preposition, auxiliary word, unit, attribute and model;
One keyword generating apparatus 13 is used for the searching key word after this filtering device filtering as this keyword.
Wherein, this keyword delivery device 3 comprises:
One first judgment means 31 is used for judging whether the transition probability of each keyword reaches this first threshold, if enable one first delivery device 32; If not, enable one second judgment means 33;
This first delivery device 32 is used for this keyword is thrown in by the SEM channel;
This second judgment means 33 is used for judging whether the search rate of this keyword reaches one the 3rd threshold value, if enable one second delivery device 34; If not, abandon the input of this keyword;
This second delivery device 34 is used for this keyword is thrown in by the SEO channel.
The principle of embodiment 3 is all identical with embodiment 1 and embodiment 2, and difference is:
The source that obtains of keyword to be put had both comprised embodiment 1 described product database, also comprised embodiment 2 described search history databases.
The below further introduces technical scheme of the present invention with an application example.
At first, keyword jettison system of the present invention is by docking with electric quotient data storehouse, automatically take out all keywords that are fit to this electricity merchant and throw in and (owing to throw in keyword expense and cost are arranged, if the keyword of throwing in can not bring the sale repayment of " certain value ", then be regarded as the keyword that " improper " thrown in.The standard of " certain value " is different because of company, and for example can be first this standard being decided to be rate of return on investment is exactly the keyword of " being fit to throw in " greater than 500% keyword, that is to say, throw in keyword, per 1 yuan of cost can bring 5 yuan of sales volumes, can be regarded as to be fit to throw in).Get word source can for:
Get word source one, sell goods word: obtain electricity merchant product sold information, for example this product information is to obtain from the database that the electricity merchant provides, the keyword of guarantee input is all relevant with this electricity merchant like this, use the Chinese character participle technique, the long section of cutting Word message, obtain being fit to the product brand of input, product classification, the words such as product information, and filter out unwanted product unit information etc., cutting the word filtration mainly judges according to part of speech, the brand word, classificating word is regarded as the large valuable word of flow, product information word flow less, but conversion ratio is higher, " 3KG ", " 500 gram " this specification word is not worth, usually is rejected.The word that remains needs by subsequent analysis anticipation conversion ratio.For example: ProductName " profoundness automatically contains gold and spins fragrance elite upgrading dress liquid detergent 3kg " will be by cutting: " profoundness " (brand), " liquid detergent " (classification), " automatically ", " gold spins ", " fragrance " (product information).
Get word source two; user search word: comprise that the user is at search word and the search word of user in electric trade station of search engine; this class word can the exact matching user the search custom; preferential chance of showing can be obtained, for the search word of this class, word need be do not cut; but need to filter; for example, the user often can search some nonsensical words, need to filter out with the filter method that cut in the word front such as " 11111 ", " 2 yuan " these words.
Be guaranteed by the degree of association of automatically getting word technology, input keyword and electricity merchant product, this is because the electricity merchant provides brand, classification, product information database, based on database is got word so, guarantee that brand word, the product word thrown in all are that this electricity merchant sells, can greatly improve speed again, promote yield-power.
Then, divide the word step gained keyword of extracting, (this history user behavior data is above-mentioned user search word for example to historical user behavior data, after mainly containing user search, purchase probability, commodity category Total sales volume, the goods orders average amount, the user search amount in the search engine) (electricity merchant's user behavior data will be gathered arrangement by native system and be several data, and all data are upgraded every day to carry out data mining, the data example is as shown in table 1), can draw the transition probability of each word, the word that transition probability is high can be thrown in low conversion rate by emphasis, but the SEM channel of charge can not thrown in the word that occurrence number is many, and take free SEO as main.We can also analysis of key word corresponding product inventory status, can sell state, avoid throwing in and can not sell commodity and cause waste.
The historical user behavior data tabulation of table 1
In conjunction with the Chinese search technology, can analyze the Search Results quality of each word in the station (because technical strength is different, the quality good or not of Search Results is uneven in the electric trade station, low-quality Search Results as: search in " rice ", out former results are cream-coloured clothes, furniture, rather than rice.This low-quality Search Results and user's request gap are too far away, under the conversion ratio, are not suitable for throwing in), the word that quality is high will adopt search page for logging in page or leaf, low product detail page or the advertising campaign page or leaf of then can forwarding to of quality.
By the key word analysis technology, the quality of throwing in keyword will obtain good guarantee, shoot the arrow at the target so that throw in, and cut the waste.
Then, just begin automatically to throw in this keyword.Through the keyword of screening and analysis, will according to electricity merchant's commodity classification automatic classification, be published to search engine (for example by the docking of search engine opening API) by docking with search engine.Bibliographic structure is consistent with the electricity merchant, and (for example, electricity is discussed the commodity classification bibliographic structure, and among the SEM, which floor catalogue search engine provides, and makes things convenient for user's sort key word.Suppose, the electricity merchant corresponding SEM of one-level classification " food and drink " " input account ", the corresponding SEM of secondary classification " imported food " " popularization plan ", the electricity merchant corresponding SEM of three grades of classifications " import milk " " popularization unit ", cut the suitable input keyword that word obtains in the import milk, will render to below the popularization unit of its correspondence.The benefit of doing like this is can be in conjunction with the electricity merchant to the popularization of the large class of difference strategy, and the large class of emphasis strengthens throws in, and non-emphasis reduces to be thrown in) to manage from now on keyword more orderly.
Only for illustrating, keyword put-on method of the present invention and system are not limited to this several implementations in certain above-mentioned explanation.
Although more than described the specific embodiment of the present invention, it will be understood by those of skill in the art that these only illustrate, protection scope of the present invention is limited by appended claims.Those skilled in the art can make various changes or modifications to these embodiments under the prerequisite that does not deviate from principle of the present invention and essence, but these changes and modification all fall into protection scope of the present invention.
Claims (20)
1. keyword put-on method is characterized in that it may further comprise the steps:
Step S
1, obtain keyword to be put;
Step S
2, calculate the transition probability of this keyword;
Step S
3, keyword that transition probability is reached a first threshold throws in by the SEM channel.
2. keyword put-on method as claimed in claim 1 is characterized in that step S
3In further comprising the steps of: the keyword that conversion ratio does not reach this first threshold is thrown in by the SEO channel.
3. keyword put-on method as claimed in claim 1 is characterized in that step S
1May further comprise the steps:
Step S
11, from a product database, obtain product information, and determine product category and call and the corresponding dictionary of this product category according to this product category according to this product information;
Step S
12, this product information is divided at least one key element;
Step S
13, utilize this dictionary and according to each key element product information cut word and become at least one key element keyword, and format this at least one key element keyword to unify the form of key element keyword;
Step S
14, calculate a rate of return on investment of each key element keyword, and select rate of return on investment to reach the key element keyword of a Second Threshold as this keyword.
4. keyword put-on method as claimed in claim 3 is characterized in that step S
13In to adopt the unified synon mode of a synonym dictionary, adopt the mode of unified capital and small letter and to adopt in the mode of replacing half double byte character one or more to format this at least one key element keyword to unify the form of key element keyword.
5. keyword put-on method as claimed in claim 3 is characterized in that, this dictionary is one or more in brand dictionary, generic name of the goods dictionary, unit dictionary, attribute dictionary, model dictionary and the conventional word dictionary.
6. keyword put-on method as claimed in claim 5 is characterized in that step S
12Afterwards, step S
13Before further comprising the steps of: as to adopt preposition and/or auxiliary word in the conventional word dictionary excision product information.
7. keyword put-on method as claimed in claim 3 is characterized in that, this at least one key element is selected from following key element: brand key element, generic name of the goods key element, unit key element, attribute key element and model key element.
8. keyword put-on method as claimed in claim 7 is characterized in that step S
14In may further comprise the steps:
Step S
141, this unit key element of filtering, this attribute key element and this model key element the key element keyword;
Step S
142, calculate through step S
141This rate of return on investment of all the other each key element keywords after the filtering, and select rate of return on investment to reach the key element keyword of this Second Threshold as this keyword.
9. keyword put-on method as claimed in claim 1 is characterized in that step S
1May further comprise the steps:
Step S
11, from a search history database, obtain searching key word, recorded the searching key word of user search and the search rate of each searching key word in this search history database;
Step S
12, the part in this searching key word of filtering, this part is: preposition, auxiliary word, unit, attribute and model;
Step S
13, will be through step S
12Searching key word after the filtering is as this keyword.
10. keyword put-on method as claimed in claim 9 is characterized in that step S
3May further comprise the steps:
Step S
31, judge whether the transition probability of each keyword reaches this first threshold, if enter step S
32If not, enter step S
33
Step S
32, this keyword is thrown in by the SEM channel;
Step S
33, judge whether the search rate of this keyword reaches one the 3rd threshold value, if enter step S
34If not, enter step S
35
Step S
34, this keyword is thrown in by the SEO channel;
Step S
35, abandon the input of this keyword.
11. a keyword jettison system is characterized in that it comprises:
One keyword deriving means is used for obtaining keyword to be put;
One calculation element is for the transition probability of calculating this keyword;
One keyword delivery device is used for transition probability is reached the keyword of a first threshold by the input of SEM channel.
12. keyword jettison system as claimed in claim 11 is characterized in that, this keyword delivery device also is used for conversion ratio is not reached the keyword of this first threshold by the input of SEO channel.
13. keyword jettison system as claimed in claim 11 is characterized in that, this keyword deriving means comprises:
One information acquisition device is used for obtaining product information from a product database, and determines product category and call and the corresponding dictionary of this product category according to this product category according to this product information;
One key element generating apparatus is used for this product information is divided at least one key element;
All word devices are used for utilizing this dictionary and according to each key element product information being cut word becoming at least one key element keyword, and format this at least one key element keyword to unify the form of key element keyword;
One keyword generating apparatus is used for calculating a rate of return on investment of each key element keyword, and selects rate of return on investment to reach the key element keyword of a Second Threshold as this keyword.
14. keyword jettison system as claimed in claim 13, it is characterized in that this is cut the word device and also is used for formaing this at least one key element keyword to unify the form of key element keyword with one or more that adopt the unified synon mode of a synonym dictionary, adopt the mode of unified capital and small letter and adopt the mode of replacing half double byte character.
15. keyword jettison system as claimed in claim 13 is characterized in that, this dictionary is one or more in brand dictionary, generic name of the goods dictionary, unit dictionary, attribute dictionary, model dictionary and the conventional word dictionary.
16. keyword jettison system as claimed in claim 15 is characterized in that, this cuts preposition and/or auxiliary word that the word device also is used for adopting conventional word dictionary excision product information.
17. keyword jettison system as claimed in claim 13 is characterized in that, this at least one key element is selected from following key element: brand key element, generic name of the goods key element, unit key element, attribute key element and model key element.
18. keyword jettison system as claimed in claim 17 is characterized in that, this keyword generating apparatus also comprises:
One filtering unit is for the key element keyword of this unit key element of filtering, this attribute key element and this model key element;
One computing unit is used for calculating this rate of return on investment of all the other each key element keywords after filtering, and selects rate of return on investment to reach the key element keyword of a Second Threshold as this keyword.
19. keyword jettison system as claimed in claim 11 is characterized in that, this keyword deriving means comprises:
One search information acquisition device is used for obtaining searching key word from a search history database, has recorded the searching key word of user search and the search rate of each searching key word in this search history database;
One filtering device, for the part of this searching key word of filtering, this part is: preposition, auxiliary word, unit, attribute and model;
One keyword generating apparatus is used for the searching key word after this filtering device filtering as this keyword.
20. keyword jettison system as claimed in claim 19 is characterized in that, this keyword delivery device comprises:
One first judgment means is used for judging whether the transition probability of each keyword reaches this first threshold, if enable one first delivery device; If not, enable one second judgment means;
This first delivery device is used for this keyword is thrown in by the SEM channel;
This second judgment means is used for judging whether the search rate of this keyword reaches one the 3rd threshold value, if enable one second delivery device; If not, abandon the input of this keyword;
This second delivery device is used for this keyword is thrown in by the SEO channel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210129565.0A CN103377249B (en) | 2012-04-27 | 2012-04-27 | Keyword put-on method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210129565.0A CN103377249B (en) | 2012-04-27 | 2012-04-27 | Keyword put-on method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103377249A true CN103377249A (en) | 2013-10-30 |
| CN103377249B CN103377249B (en) | 2017-12-22 |
Family
ID=49462375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210129565.0A Active CN103377249B (en) | 2012-04-27 | 2012-04-27 | Keyword put-on method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103377249B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104298789A (en) * | 2014-11-13 | 2015-01-21 | 北京国双科技有限公司 | Keyword partition method and device |
| CN104462412A (en) * | 2014-12-11 | 2015-03-25 | 北京国双科技有限公司 | Keyword detection method and device for release of internet keywords |
| CN104700295A (en) * | 2013-12-04 | 2015-06-10 | 航天信息股份有限公司 | Invoicing system with sales analysis function |
| CN105956013A (en) * | 2016-04-21 | 2016-09-21 | 世纪禾光科技发展（北京）有限公司 | Method, device, and system for extracting website keyword |
| CN106033583A (en) * | 2016-05-18 | 2016-10-19 | 杭州算子科技有限公司 | Advertisement paid listing method and system applied to electronic commerce |
| CN106161627A (en) * | 2016-07-12 | 2016-11-23 | 百度在线网络技术（北京）有限公司 | Method and device for pushed information |
| CN106294416A (en) * | 2015-05-25 | 2017-01-04 | 阿里巴巴集团控股有限公司 | The disaggregated model method for building up of SEO dictionary, key word choosing method and device |
| CN106682039A (en) * | 2015-11-10 | 2017-05-17 | 北京国双科技有限公司 | Method and device for monitoring keyword releasing effects |
| CN106776665A (en) * | 2015-11-25 | 2017-05-31 | 北京国双科技有限公司 | The put-on method and device of keyword |
| CN108804430A (en) * | 2017-04-26 | 2018-11-13 | 广东原昇信息科技有限公司 | A kind of SEM launches data sorting system and its sorting technique |
| CN108960917A (en) * | 2018-06-29 | 2018-12-07 | 深圳市跨境邦电子商务有限公司 | Network marketing promotion method and device |
| CN109993551A (en) * | 2017-12-29 | 2019-07-09 | 北京奇虎科技有限公司 | Determine that the method, apparatus and computer readable storage medium of crowd are launched in advertisement |
| CN110544110A (en) * | 2019-07-30 | 2019-12-06 | 中至数据集团股份有限公司 | SEM keyword release abnormity monitoring method and device and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080103892A1 (en) * | 2006-10-30 | 2008-05-01 | Adchemy, Inc. | System and method for generating optimized bids for advertisement keywords |
| US20110040616A1 (en) * | 2009-08-14 | 2011-02-17 | Yahoo! Inc. | Sponsored search bid adjustment based on predicted conversion rates |
| US20110106642A1 (en) * | 2009-11-03 | 2011-05-05 | Ebay Inc. | Computer-implemented method and system for keyword bidding in a market cooperative |
| CN102129431A (en) * | 2010-01-13 | 2011-07-20 | 阿里巴巴集团控股有限公司 | Search method and system applied to online trading platform |
| CN102360484A (en) * | 2011-09-30 | 2012-02-22 | 奇智软件（北京）有限公司 | Method and apparatus for authenticity detection on sale data of group purchasing website |
-
2012
- 2012-04-27 CN CN201210129565.0A patent/CN103377249B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080103892A1 (en) * | 2006-10-30 | 2008-05-01 | Adchemy, Inc. | System and method for generating optimized bids for advertisement keywords |
| US20110040616A1 (en) * | 2009-08-14 | 2011-02-17 | Yahoo! Inc. | Sponsored search bid adjustment based on predicted conversion rates |
| US20110106642A1 (en) * | 2009-11-03 | 2011-05-05 | Ebay Inc. | Computer-implemented method and system for keyword bidding in a market cooperative |
| CN102129431A (en) * | 2010-01-13 | 2011-07-20 | 阿里巴巴集团控股有限公司 | Search method and system applied to online trading platform |
| CN102360484A (en) * | 2011-09-30 | 2012-02-22 | 奇智软件（北京）有限公司 | Method and apparatus for authenticity detection on sale data of group purchasing website |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700295A (en) * | 2013-12-04 | 2015-06-10 | 航天信息股份有限公司 | Invoicing system with sales analysis function |
| CN104298789B (en) * | 2014-11-13 | 2018-04-03 | 北京国双科技有限公司 | The division methods and device of keyword |
| CN104298789A (en) * | 2014-11-13 | 2015-01-21 | 北京国双科技有限公司 | Keyword partition method and device |
| CN104462412A (en) * | 2014-12-11 | 2015-03-25 | 北京国双科技有限公司 | Keyword detection method and device for release of internet keywords |
| CN106294416B (en) * | 2015-05-25 | 2019-10-15 | 阿里巴巴集团控股有限公司 | Disaggregated model method for building up, keyword choosing method and the device of SEO dictionary |
| CN106294416A (en) * | 2015-05-25 | 2017-01-04 | 阿里巴巴集团控股有限公司 | The disaggregated model method for building up of SEO dictionary, key word choosing method and device |
| CN106682039A (en) * | 2015-11-10 | 2017-05-17 | 北京国双科技有限公司 | Method and device for monitoring keyword releasing effects |
| CN106776665A (en) * | 2015-11-25 | 2017-05-31 | 北京国双科技有限公司 | The put-on method and device of keyword |
| CN105956013A (en) * | 2016-04-21 | 2016-09-21 | 世纪禾光科技发展（北京）有限公司 | Method, device, and system for extracting website keyword |
| CN106033583A (en) * | 2016-05-18 | 2016-10-19 | 杭州算子科技有限公司 | Advertisement paid listing method and system applied to electronic commerce |
| CN106161627A (en) * | 2016-07-12 | 2016-11-23 | 百度在线网络技术（北京）有限公司 | Method and device for pushed information |
| CN108804430A (en) * | 2017-04-26 | 2018-11-13 | 广东原昇信息科技有限公司 | A kind of SEM launches data sorting system and its sorting technique |
| CN109993551A (en) * | 2017-12-29 | 2019-07-09 | 北京奇虎科技有限公司 | Determine that the method, apparatus and computer readable storage medium of crowd are launched in advertisement |
| CN108960917A (en) * | 2018-06-29 | 2018-12-07 | 深圳市跨境邦电子商务有限公司 | Network marketing promotion method and device |
| CN108960917B (en) * | 2018-06-29 | 2022-06-03 | 深圳市跨境邦电子商务有限公司 | Network marketing promotion method and device |
| CN110544110A (en) * | 2019-07-30 | 2019-12-06 | 中至数据集团股份有限公司 | SEM keyword release abnormity monitoring method and device and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103377249B (en) | 2017-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103377249A (en) | Keyword putting method and system | |
| TWI631474B (en) | Method and device for product identification label and method for product navigation | |
| US20180165712A1 (en) | Method and apparatus for composing search phrases, distributing ads and searching product information | |
| CN103729359B (en) | A kind of method and system recommending search word | |
| CN102279851B (en) | Intelligent navigation method, device and system | |
| CN105630768B (en) | A kind of product name recognition method and device based on stacking condition random field | |
| CN103678564B (en) | Internet product research system based on data mining | |
| CN103530299B (en) | Search result generating method and device | |
| CN105824898A (en) | Label extracting method and device for network comments | |
| CN104298749A (en) | Commodity retrieval method based on image visual and textual semantic integration | |
| CN104077407B (en) | A kind of intelligent data search system and method | |
| CN104281622A (en) | Information recommending method and information recommending device in social media | |
| EP1960911A1 (en) | Advertising keyword cross-selling | |
| CN107544988B (en) | Method and device for acquiring public opinion data | |
| CN101593200A (en) | Chinese Web page classification method based on the keyword frequency analysis | |
| CN102375823A (en) | Searching result gathering display method and system | |
| CN104462336A (en) | Information pushing method and device | |
| CN103606097A (en) | Method and system based on credibility evaluation for product information recommendation | |
| AU2015252513A1 (en) | Method and system for filtering goods evaluation information | |
| CN105447186A (en) | Big data platform based user behavior analysis system | |
| CN108319376B (en) | Input association recommendation method and device for optimizing commercial word promotion | |
| CN106296368A (en) | A kind of vehicle commending system and method | |
| CN104239331A (en) | Method and device for ranking comment search engines | |
| CN105468649B (en) | Method and device for judging matching of objects to be displayed | |
| CN103177036A (en) | Method and system for label automatic extraction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20160914 Address after: East Building 11, 100195 Beijing city Haidian District xingshikou Road No. 65 west Shan creative garden district 1-4 four layer of 1-4 layer Applicant after: Beijing Jingdong Shangke Information Technology Co., Ltd. Address before: 201203 Shanghai city Pudong New Area Zu Road No. 295 Room 102 Applicant before: Niuhai Information Technology (Shanghai) Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |