CN103778553A - Commodity attribute recommendation method and commodity attribute recommendation system - Google Patents
Commodity attribute recommendation method and commodity attribute recommendation system Download PDFInfo
- Publication number
- CN103778553A CN103778553A CN201210416964.5A CN201210416964A CN103778553A CN 103778553 A CN103778553 A CN 103778553A CN 201210416964 A CN201210416964 A CN 201210416964A CN 103778553 A CN103778553 A CN 103778553A
- Authority
- CN
- China
- Prior art keywords
- item
- sought
- item property
- much
- commodity
- 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
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present invention disclose a commodity attribute recommendation method and a commodity attribute recommendation system. The commodity attribute recommendation method comprises the steps of obtaining the search keywords of users inputted under a category path; gathering the click amount of commodities corresponding to the search keywords under the category path; calculating the weight of each commodity attribute according to the click amount of commodities respectively; selecting a hot commodity attribute according to the weight of each commodity attribute; and outputting the hot commodity attribute. The commodity attribute recommendation method and the commodity attribute recommendation system of the embodiment of the present invention enable the flexibility for determining the hot commodity attribute to be improved, and can determine the hot commodity attribute accurately to recommend to users.
Description
Technical field
The present invention relates to computer internet technical field, be specifically related to a kind of item property recommend method and system.
Background technology
While shopping on the net, user adopts the mode of the item property (such as brand, price range, Time To Market, color and size etc.) of showing in webpage clicking to carry out search commercial articles conventionally.And mode based on this search commercial articles, system can be added up user in the certain hour section click volume for the item property of showing in the time of search commercial articles, and determine much-sought-after item attribute and recommend user according to the size of click volume, so that user can search for much-sought-after item.
But in practice, item property is clicked often relevant in the display location of the page with this item property, display location is obvious, and item property more easily attracts user to click, and this just makes definite problem that has very flexible of much-sought-after item attribute; Meanwhile, item property is clicked more sparse comparatively speaking, carrys out search commercial articles because most of user can't really click attribute, will make like this click volume of statistics too small, cannot accurately determine much-sought-after item attribute and recommend user.
Summary of the invention
The embodiment of the present invention provides a kind of item property recommend method and system, the very flexible existing while determining for solving much-sought-after item attribute and cannot accurately determine much-sought-after item attribute and recommend user's problem.
The embodiment of the present invention provides a kind of item property recommend method, comprising:
Obtain the searched key word that user inputs under a certain classification path;
Add up the click volume of each commodity that described searched key word under described classification path is corresponding;
Calculate the weights of each class item property according to the click volume of described each commodity;
According to the weights of described each class item property, select much-sought-after item attribute;
Export described much-sought-after item attribute.
Correspondingly, the embodiment of the present invention also provides a kind of item property commending system, comprising:
Acquiring unit, the searched key word of inputting under a certain classification path for receiving user;
Statistic unit, for adding up the click volume of each commodity that described searched key word under described classification path is corresponding;
Computing unit, for calculating the weights of each class item property according to the click volume of described each commodity;
Choose unit, for the weights according to described each class item property, select much-sought-after item attribute;
Output unit, for exporting described much-sought-after item attribute.
In the embodiment of the present invention, detecting after the searched key word that user inputs under a certain classification path, first add up the click volume of each commodity that this searched key word under this classification path is corresponding, and calculate the weights of each class item property according to the click volume of each commodity, and then select the output of much-sought-after item attribute according to the weights of each class item property.Visible, the embodiment of the present invention is to calculate the weights of each class item property and then select much-sought-after item attribute according to the click volume of each commodity, thereby the dirigibility not only can improve much-sought-after item attribute and determine time, can also accurately determine much-sought-after item attribute and recommend user.
Accompanying drawing explanation.
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, to the accompanying drawing of required use in embodiment 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 process flow diagram of a kind of item property recommend method of providing of the embodiment of the present invention;
Fig. 2 is the process flow diagram of the another kind of item property recommend method that provides of the embodiment of the present invention;
Fig. 3 is the process flow diagram of a kind of item property commending system of providing of the embodiment of the present invention.
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.
The embodiment of the present invention provides a kind of item property recommend method and system, and the dirigibility can improve much-sought-after item attribute and determine time, can also accurately determine much-sought-after item attribute and recommend user.The item property recommend method that the embodiment of the present invention provides and system can be applied to B2B platform, B2C platform, N2C platform and independently network shopping mall and group buying websites, and the embodiment of the present invention is not construed as limiting.Below be elaborated respectively.
Refer to Fig. 1, Fig. 1 is the process flow diagram of a kind of item property recommend method of providing of the embodiment of the present invention.As shown in Figure 1, this item property recommend method can comprise the following steps.
101, obtain the searched key word that user inputs under a certain classification path.
In the embodiment of the present invention, classification path is a kind of Way guidance for search commercial articles, and searched key word is the keyword for search commercial articles.For example, " mobile phone/Samsung " can be used as a kind of classification path, and price " 2001 ~ 3000 " can be used as searched key word; Again for example, " women's dress/sweater " can be used as a kind of classification path, and " cotton textiles " can be used as searched key word.
102, add up the click volume of each commodity that this searched key word under this classification path is corresponding.
In the embodiment of the present invention, can add up the click volume of each commodity that this searched key word under this classification path in certain hour section (as a week or month) is corresponding.
For instance, the classification path that can add up in one week is " mobile phone/Samsung ", and searched key word is the click volume of each Samsung mobile phone of price " 2001 ~ 3000 ".
103, calculate the weights of each class item property according to the click volume of each commodity.
For instance, in the time that each commodity corresponding to this searched key word under this classification path are mobile phone, the item property of mobile phone can comprise color, main screen size, camera pixel etc. so.
Again for instance, in the time that each commodity corresponding to this searched key word under this classification path are clothes, the item property of clothes can comprise color, style, size etc. so.
Wherein, the weights that calculate each class item property according to the click volume of each commodity can comprise:
For each class item property, the click volume of each commodity that statistics comprises such item property is respectively as the weights of such item property.
For instance, in the time that each commodity corresponding to this searched key word under this classification path are mobile phone, for item property " main screen size=4.8 inch ", can add up the click volume of the each mobile phone that comprises item property " main screen size=4.8 inch ", as the weights of item property " main screen size=4.8 inch ".Again can item property " camera pixel=8,000,000 ", the click volume that can add up the each mobile phone that comprises item property " camera pixel=8,000,000 ", as the weights of item property " camera pixel=8,000,000 ".
104,, according to the weights of each class item property, select much-sought-after item attribute.
Wherein, each class item property can be sorted from high to low successively according to weights, and start from highest weight value one end sequentially to choose some class item property as much-sought-after item attribute.
For example, in the time that each commodity corresponding to this searched key word under this classification path are mobile phone, the weights of item property " operating system=Android " are 300 points, and item property " main screen size=4.8 inch " weights are 200 points, and item property " camera pixel=8,000,000 " weights are 150 points, can choose so item property " operating system=Android " and item property " main screen size=4.8 inch " as much-sought-after item attribute.
105, export popular item property.
In the embodiment of the present invention, can export popular item property by voice and/or page mode.
In the embodiment of the present invention, after selecting much-sought-after item attribute through above-mentioned steps 104, this much-sought-after item attribute can be shown in the page, recommend the object of much-sought-after item attribute to be reached for user.
In the embodiment of the present invention, the described item property recommend method of Fig. 1 can also comprise the following steps, that is: detecting user operates the selection of much-sought-after item attribute, and the commodity under much-sought-after item attribute are gathered and exported, thereby can recommend much-sought-after item for user, guiding user carries out much-sought-after item transaction.
In the embodiment of the present invention, when user adopts different searched key words to carry out search commercial articles under different classification paths, all can obtain different much-sought-after item attribute, thereby can realize the dirigibility of much-sought-after item attribute recommendation, personalized object.
In the described method of Fig. 1, detecting after the searched key word that user inputs under a certain classification path, first add up the click volume of each commodity that this searched key word under this classification path is corresponding, and calculate the weights of each class item property according to the click volume of each commodity, and then select much-sought-after item attribute output display according to the weights of each class item property.Visible, the described method of Fig. 1 is to calculate the weights of each class item property and then select much-sought-after item attribute according to the click volume of each commodity, thereby the dirigibility not only can improve much-sought-after item attribute and determine time, can also accurately determine much-sought-after item attribute and recommend user.
Refer to Fig. 2, Fig. 2 is the process flow diagram of the another kind of item property recommend method that provides of the embodiment of the present invention.In the described method of Fig. 2, suppose that user adopts for 1000 times searched key word nike to carry out search commercial articles in classification path.As shown in Figure 2, this item property recommend method can comprise the following steps.
201, pre-recorded user adopts the details click data of the commodity that searched key word nike searches for 1000 times in classification path.
In the embodiment of the present invention, the details click data of commodity can comprise these commodity clicked time each time.
202, obtain the searched key word nike that user inputs in classification path 1000.
The click volume of each commodity that 203, the searched key word nike under the classification path 1000 in statistics certain hour section is corresponding.
Such as in one week, classification path adopts for 10000 times all users of searched key word nike to click A commodity 100 times, B commodity 80 times, C commodity 50 times.
204, calculate the weights of each class item property according to the click volume of each commodity corresponding to the searched key word nike under classification path 1000.
Such as, A commodity have item property " redness " and " middle code ", B commodity have item property " blueness " and " large code ", and C commodity have item property " blueness " and " middle code ", add up known: item property " redness " weights are 100, item property " blueness " weights are 130, and item property " middle code " weights are 150, and item property " large code " weights are 80
205,, according to the weights of each class item property, select much-sought-after item attribute.
Such as, can choose item property " blueness " and item property " middle code " as much-sought-after item attribute.
206, by much-sought-after item attribute output display.
Such as, can be by item property " blueness " and item property " middle code " output display.
To calculate the weights of each class item property and then select much-sought-after item attribute according to the click volume of each commodity in the described method of Fig. 2, thereby the dirigibility not only can improve much-sought-after item attribute and determine time, can also accurately determine much-sought-after item attribute and recommend user.
Refer to Fig. 3, Fig. 3 is the structural drawing of a kind of item property commending system of providing of the embodiment of the present invention.As shown in Figure 3, this item property commending system can comprise:
Acquiring unit 301, the searched key word of inputting under a certain classification path for receiving user;
Choose unit 304, for the weights according to described each class item property, select much-sought-after item attribute;
In the embodiment of the present invention, the also selection operation to much-sought-after item attribute for detection of user of acquiring unit 301, output unit 305 is also for gathering the commodity under described much-sought-after item attribute export.
In the embodiment of the present invention, computing unit 303, for for each class item property, is added up respectively the click volume of the each commodity that comprise such item property as the weights of such item property.
In the embodiment of the present invention, choose unit 304 for each class item property is sorted from high to low successively according to weights, and start from highest weight value one end sequentially to choose some class item property as much-sought-after item attribute.
To calculate the weights of each class item property and then select much-sought-after item attribute according to the click volume of each commodity in the described system of Fig. 3, thereby the dirigibility not only can improve much-sought-after item attribute and determine time, can also accurately determine much-sought-after item attribute and recommend user.
One of ordinary skill in the art will appreciate that all or part of step in the whole bag of tricks of above-described embodiment is can carry out the hardware that instruction is relevant by program to complete, this program can be stored in a computer-readable recording medium, storage medium can comprise: flash disk, ROM (read-only memory) (Read-Only Memory, ROM), random access device (Random Access Memory, RAM), disk or CD etc.
The item property recommend method, the system that above the embodiment of the present invention are provided are described in detail, applied specific case herein principle of the present invention and embodiment are set forth, the explanation of above embodiment is just for helping to understand method of the present invention and core concept thereof; , for one of ordinary skill in the art, according to thought of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention meanwhile.
Claims (8)
1. an item property recommend method, is characterized in that, comprising:
Obtain the searched key word that user inputs under a certain classification path;
Add up the click volume of each commodity that described searched key word under described classification path is corresponding;
Calculate the weights of each class item property according to the click volume of described each commodity;
According to the weights of described each class item property, select much-sought-after item attribute;
Export described much-sought-after item attribute.
2. method according to claim 1, is characterized in that, also comprises:
Detect the selection operation of user to described much-sought-after item attribute;
Commodity under described much-sought-after item attribute are gathered and exported.
3. method according to claim 1 and 2, is characterized in that, the weights that the click volume of the described each commodity of described foundation is calculated each class item property comprise:
For each class item property, the click volume of each commodity that statistics comprises such item property is respectively as the weights of such item property.
4. method according to claim 1 and 2, is characterized in that, the weights of each class item property described in described foundation, select much-sought-after item attribute and comprise:
Each class item property is sorted from high to low successively according to weights, and start from highest weight value one end sequentially to choose some class item property as much-sought-after item attribute.
5. an item property commending system, is characterized in that, comprising:
Acquiring unit, the searched key word of inputting under a certain classification path for receiving user;
Statistic unit, for adding up the click volume of each commodity that described searched key word under described classification path is corresponding;
Computing unit, for calculating the weights of each class item property according to the click volume of described each commodity;
Choose unit, for the weights according to described each class item property, select much-sought-after item attribute;
Output unit, for exporting described much-sought-after item attribute.
6. system according to claim 5, is characterized in that,
Described acquiring unit, the also selection operation to described much-sought-after item attribute for detection of user;
Described output unit, also gathers and exports for the commodity under described much-sought-after item attribute.
7. according to the system described in claim 5 or 6, it is characterized in that, described computing unit, for for each class item property, is added up respectively the click volume of the each commodity that comprise such item property as the weights of such item property.
8. according to the system described in claim 5 or 6, it is characterized in that, described in choose unit for by each class item property according to weights from high to low successively sequence, and start from highest weight value one end order choose some class item property as much-sought-after item attribute.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210416964.5A CN103778553A (en) | 2012-10-26 | 2012-10-26 | Commodity attribute recommendation method and commodity attribute recommendation system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210416964.5A CN103778553A (en) | 2012-10-26 | 2012-10-26 | Commodity attribute recommendation method and commodity attribute recommendation system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103778553A true CN103778553A (en) | 2014-05-07 |
Family
ID=50570753
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210416964.5A Pending CN103778553A (en) | 2012-10-26 | 2012-10-26 | Commodity attribute recommendation method and commodity attribute recommendation system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103778553A (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104391977A (en) * | 2014-12-05 | 2015-03-04 | 北京国双科技有限公司 | Web page keyword occurrence frequency detection method and device |
CN104899766A (en) * | 2015-06-03 | 2015-09-09 | 北京京东尚科信息技术有限公司 | Method and device for selecting object attributes |
CN105023171A (en) * | 2015-06-29 | 2015-11-04 | 成都亿邻通科技有限公司 | Method for recommending group purchase to user |
WO2015196397A1 (en) * | 2014-06-25 | 2015-12-30 | 北京百付宝科技有限公司 | Method and device for data mining based on user's search behaviour |
CN105488688A (en) * | 2015-05-15 | 2016-04-13 | 广州交易猫信息技术有限公司 | Commodity information pushing method, device and system |
CN105718571A (en) * | 2016-01-20 | 2016-06-29 | 百度在线网络技术(北京)有限公司 | Information pushing method and device |
CN105976212A (en) * | 2016-05-30 | 2016-09-28 | 北京京东尚科信息技术有限公司 | Commodity displaying method and apparatus and electronic commerce platform |
CN106097035A (en) * | 2016-05-30 | 2016-11-09 | 广东美的制冷设备有限公司 | The display packing of Product Interface and device |
CN106156121A (en) * | 2015-04-07 | 2016-11-23 | 北大方正集团有限公司 | Copybook recommends method and copybook commending system |
CN107092600A (en) * | 2016-02-17 | 2017-08-25 | 阿里巴巴集团控股有限公司 | A kind of information identifying method and device |
CN107169798A (en) * | 2017-05-15 | 2017-09-15 | 广东小天才科技有限公司 | Keep method, terminal device and the computer-readable storage medium of terminal client viscosity |
WO2018090786A1 (en) * | 2016-11-18 | 2018-05-24 | 深圳市世强元件网络有限公司 | Method for accurately searching within website |
CN108665300A (en) * | 2017-04-01 | 2018-10-16 | 北京京东尚科信息技术有限公司 | A kind of method, apparatus, equipment and storage medium that data are provided |
CN109525737A (en) * | 2018-12-03 | 2019-03-26 | 商客通尚景信息技术江苏有限公司 | A kind of call Cut-in control method and system |
CN109697621A (en) * | 2017-10-23 | 2019-04-30 | 阿里巴巴集团控股有限公司 | The determination method and device of hot spot attribute, data processing method, apparatus and system |
CN112184379A (en) * | 2020-09-29 | 2021-01-05 | 浙江得油信息科技有限公司 | Oil online shopping system for vehicles and ships |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102542474A (en) * | 2010-12-07 | 2012-07-04 | 阿里巴巴集团控股有限公司 | Method for sorting inquiry results and device |
-
2012
- 2012-10-26 CN CN201210416964.5A patent/CN103778553A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102542474A (en) * | 2010-12-07 | 2012-07-04 | 阿里巴巴集团控股有限公司 | Method for sorting inquiry results and device |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015196397A1 (en) * | 2014-06-25 | 2015-12-30 | 北京百付宝科技有限公司 | Method and device for data mining based on user's search behaviour |
US10896461B2 (en) | 2014-06-25 | 2021-01-19 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for data mining based on users' search behavior |
CN104391977A (en) * | 2014-12-05 | 2015-03-04 | 北京国双科技有限公司 | Web page keyword occurrence frequency detection method and device |
CN104391977B (en) * | 2014-12-05 | 2018-04-03 | 北京国双科技有限公司 | Web Page Key Words frequency of occurrence detection method and device |
CN106156121A (en) * | 2015-04-07 | 2016-11-23 | 北大方正集团有限公司 | Copybook recommends method and copybook commending system |
CN105488688A (en) * | 2015-05-15 | 2016-04-13 | 广州交易猫信息技术有限公司 | Commodity information pushing method, device and system |
CN104899766A (en) * | 2015-06-03 | 2015-09-09 | 北京京东尚科信息技术有限公司 | Method and device for selecting object attributes |
CN105023171A (en) * | 2015-06-29 | 2015-11-04 | 成都亿邻通科技有限公司 | Method for recommending group purchase to user |
CN105718571A (en) * | 2016-01-20 | 2016-06-29 | 百度在线网络技术(北京)有限公司 | Information pushing method and device |
CN107092600A (en) * | 2016-02-17 | 2017-08-25 | 阿里巴巴集团控股有限公司 | A kind of information identifying method and device |
CN105976212B (en) * | 2016-05-30 | 2020-02-07 | 北京京东尚科信息技术有限公司 | Commodity display method and device and electronic commerce platform |
CN106097035A (en) * | 2016-05-30 | 2016-11-09 | 广东美的制冷设备有限公司 | The display packing of Product Interface and device |
CN105976212A (en) * | 2016-05-30 | 2016-09-28 | 北京京东尚科信息技术有限公司 | Commodity displaying method and apparatus and electronic commerce platform |
WO2018090786A1 (en) * | 2016-11-18 | 2018-05-24 | 深圳市世强元件网络有限公司 | Method for accurately searching within website |
CN108665300A (en) * | 2017-04-01 | 2018-10-16 | 北京京东尚科信息技术有限公司 | A kind of method, apparatus, equipment and storage medium that data are provided |
CN107169798A (en) * | 2017-05-15 | 2017-09-15 | 广东小天才科技有限公司 | Keep method, terminal device and the computer-readable storage medium of terminal client viscosity |
CN109697621A (en) * | 2017-10-23 | 2019-04-30 | 阿里巴巴集团控股有限公司 | The determination method and device of hot spot attribute, data processing method, apparatus and system |
CN109697621B (en) * | 2017-10-23 | 2023-04-07 | 阿里巴巴集团控股有限公司 | Hotspot attribute determining method and device, and data processing method, device and system |
CN109525737A (en) * | 2018-12-03 | 2019-03-26 | 商客通尚景信息技术江苏有限公司 | A kind of call Cut-in control method and system |
CN112184379A (en) * | 2020-09-29 | 2021-01-05 | 浙江得油信息科技有限公司 | Oil online shopping system for vehicles and ships |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103778553A (en) | Commodity attribute recommendation method and commodity attribute recommendation system | |
TWI787196B (en) | Method, device and system for generating business object attribute identification | |
US11010441B2 (en) | Method for accurately searching within website | |
JP5878245B2 (en) | Intelligent navigation of category system | |
TWI512653B (en) | Information providing method and apparatus, method and apparatus for determining the degree of comprehensive relevance | |
CN105718184A (en) | Data processing method and apparatus | |
US9002889B2 (en) | System and method for social data mining that learns from a dynamic taxonomy | |
WO2014015079A2 (en) | Method and apparatus of recommending clothing products | |
CN103839172B (en) | Method of Commodity Recommendation and system | |
US20180053234A1 (en) | Description information generation and presentation systems, methods, and devices | |
CN103970850B (en) | Site information recommends method and system | |
CN108205768A (en) | Database building method and data recommendation method and device, equipment and storage medium | |
CN103942712A (en) | Product similarity based e-commerce recommendation system and method thereof | |
CN104239338A (en) | Information recommendation method and information recommendation device | |
CN105138690B (en) | The method and apparatus for determining keyword | |
CN103034680B (en) | For data interactive method and the device of terminal device | |
CN104102648A (en) | User behavior data based interest recommending method and device | |
CN103646341B (en) | A kind of website provides the recommendation method and apparatus of object | |
CN104615721B (en) | For the method and system based on return of goods related information Recommendations | |
CN103020128B (en) | With the method and apparatus of data interaction with terminal device | |
CN104809637A (en) | Commodity recommending method and system realized by computer | |
CN106326318B (en) | Searching method and device | |
CN108550046A (en) | A kind of resource and market recommendation method, apparatus and electronic equipment | |
CN106570031A (en) | Service object recommending method and device | |
CN108073667A (en) | Method for generating user browsing attributes, and non-transitory computer readable medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140507 |