CN104615721A - Method and system for recommending communities based on returned goods related information - Google Patents
Method and system for recommending communities based on returned goods related information Download PDFInfo
- Publication number
- CN104615721A CN104615721A CN201510062406.7A CN201510062406A CN104615721A CN 104615721 A CN104615721 A CN 104615721A CN 201510062406 A CN201510062406 A CN 201510062406A CN 104615721 A CN104615721 A CN 104615721A
- Authority
- CN
- China
- Prior art keywords
- goods
- commodity
- label
- return
- given number
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and system for recommending communities based on returned goods related information. The method includes the steps of establishing a community label database, establishing a shopping behavior context system on the basis of returned goods, calculating a specific number of communities on the basis of community labels and shopping behavior contexts, and recommending a specific calculated number of communities to a user.
Description
Technical field
The present invention relates to recommending goods in electronic business, more specifically, the present invention relates to for the method and system based on return of goods related information Recommendations.
Background technology
Along with the universal of internet and the development of ecommerce, various human nature service just constantly released by shopping at network platform, such as, finds to make user the commodity wanted more quickly, shopping at network platform can the network behavior of Collection and analysis user, and then recommends dependent merchandise for user.Under the competitive environment be growing more intense, Recommendations information can effectively retain user, prevent customer loss, and improves the sale of e-commerce system.
Existing commending system adopts the large data analysis technique based on commodity, user behavior, and it can recommend suitable commodity based on the label of commodity to user, or recommends similar product according to the hobby that user's preference in the past or user are arranged.Such as, when return of goods behavior occurs user, the system of prior art, based on a series of behaviors of user before the return of goods, is its label of commodity identification, utilizes Commercial goods labels for user's Recommendations.Therefore, user after the return of goods, or does not obtain the merchandise news of subsequent recommendation, otherwise obtain be all based on return goods move ahead into recommend commodity, this is have no to associate with the behavior that user returned goods at that time substantially.System due to prior art cannot utilize return of goods related information to come for user's Recommendations, so more effectively can not improve buying rate.
Therefore, a kind of method and system that can come for user's Recommendations based on return of goods related information is needed, to improve second purchase rate further.
Summary of the invention
In the inventive solutions, carrying out the reason of returning goods according to user, be combined with the follow-up buying behavior information of the user of same return of goods behavior, is user's Recommendations, thus improves second purchase rate.
According to one embodiment of present invention, provide a kind of method based on return of goods related information Recommendations, comprising: set up Commercial goods labels database; Set up the Shopping Behaviors context system based on returning goods; The commodity of given number are calculated based on described Commercial goods labels and described Shopping Behaviors context; And by the commercial product recommending of calculated given number to user.
Preferably, the second label that described Commercial goods labels comprises the first label and is associated with described first label, described first label comprises the information of commodity, and described second label comprises described return of goods reason.
Preferably, described Shopping Behaviors context comprises the Shopping Behaviors of rear specific times of returning goods.
Preferably, the step calculating the commodity of given number the most often bought after returning goods comprises further: based on described second label, associates out described first label with the commodity of the most close given number of the commodity drawn with return goods; And based on described Shopping Behaviors context, the commodity of the given number the most often bought after calculating the return of goods.
Preferably, the commodity of described given number comprise and the commodity of the most close given number of commodity of returning goods and the commodity of given number the most often bought after returning goods.
According to another embodiment of the invention, provide a kind of system based on return of goods related information Recommendations, comprising: database, described database is used for storing commodity tag database; Return of goods system, described return of goods system is for setting up the Shopping Behaviors context system based on returning goods; Commending system, described commending system is used for the commodity calculating given number based on described Commercial goods labels and described Shopping Behaviors context, and by the commercial product recommending of calculated given number to user.
Preferably, the second label that described Commercial goods labels comprises the first label and is associated with described first label, described first label comprises the information of commodity, and described second label comprises described return of goods reason.
Preferably, described Shopping Behaviors context comprises the Shopping Behaviors of rear specific times of returning goods.
Preferably, described commending system is configured to further: based on described second label, associates out described first label with the commodity of the most close given number of the commodity drawn with return goods; And based on described Shopping Behaviors context, the commodity of the given number the most often bought after calculating the return of goods.
Preferably, the commodity of described given number comprise and the commodity of the most close given number of commodity of returning goods and the commodity of given number the most often bought after returning goods.
According to the detailed description below the disclosure and accompanying drawing, other object, feature and advantage will be apparent to those skilled in the art.
Accompanying drawing explanation
Accompanying drawing illustrates embodiments of the invention, and is used from instructions one and explains principle of the present invention.In the accompanying drawings:
Fig. 1 is according to an embodiment of the invention based on the schematic diagram of the system of return of goods related information Recommendations.
Fig. 2 is according to an embodiment of the invention based on the process flow diagram of the method for return of goods related information Recommendations.
Embodiment
Disclose a kind of for the method and system based on return of goods related information Recommendations according to embodiments of the invention.In the following description, for illustrative purposes, multiple detail has been set forth to provide the complete understanding to embodiments of the invention.But it is evident that for those skilled in the art, embodiments of the invention can realize when not having these details.
Term as used herein " commending system " is based upon a kind of Advanced Business intelligent platform on mass data excavation basis, to help e-commerce website to provide completely personalized decision support and information service for its customer purchase, pseudo sale personnel help user to complete purchasing process.
Term as used herein " large data ", or claim flood tide data, refer to involved data quantity huge to by current main software instrument, acquisition, management cannot being reached within reasonable time, processing and arrange the information becoming and help the more positive object of enterprise management decision-making.
Fig. 1 is according to an embodiment of the invention based on the schematic diagram of the system 100 of return of goods related information Recommendations.This system 100 comprises return of goods system 101, high-volume database 103, commending system 105 and user 107.
Return of goods system 101 is used for setting up the Shopping Behaviors context system based on returning goods, and described Shopping Behaviors context comprises the Shopping Behaviors of rear specific times of returning goods.High-volume database 103 is used for storing commodity tag library.Commercial goods labels is used for indicating the information of commodity, and the second label comprising the first label and be associated with described first label, described first label comprises the information of commodity, and described second label comprises described return of goods reason.Such as, described Commercial goods labels includes but not limited to the category, price, quality, return of goods reason etc. of commodity.Commending system 105 for calculating the commodity of given number based on described Commercial goods labels and described Shopping Behaviors context, and by the commercial product recommending of calculated given number to user 107.
Such as, commodity A mobile phone has following first kind label before added: a. mobile phone, b. quality are good, c. configuration is high, d. price is low.Commodity B mobile phone has following first kind label before added: a. mobile phone, b. signal are good, c. outward appearance is beautiful, d. battery durable is outstanding.If user there occurs reimbursement after purchase A mobile phone, and have selected following reason return of goods interface user: x. signal difference, y. battery durable are poor, z. price is high, and this type of reason belongs to the Equations of The Second Kind label of these commodity.In commending system 105, the x. signal difference in Equations of The Second Kind label and the b. signal in first kind label are as relating attribute well, and the d. battery durable in y. battery durable in Equations of The Second Kind label difference and first kind label is outstanding is as relating attribute.User return goods after, first kind label recommendations weight will be modified to a. mobile phone, b. signal is good, c. battery durable is outstanding, d. configure high.Then, through the computing of commending system 105 algorithm, the firstly in subsequent recommendation B mobile phone will be recommended.
And, commending system 105 can count in the behavior storehouse after user returns goods, after generation A mobile phone is returned goods, the buying behavior that user the most often occurs is followed successively by C mobile phone, D mobile phone, E mobile phone, B mobile phone, F mobile phone, and through comparing with first kind label, commending system 105 finally can continue to recommend user to buy C, D and F mobile phone.If user selects reason z. price high in the return of goods, z. price height and the low term correlation tag of d. price in first kind label, but owing to also having this label in former commodity, then the return of goods behavior of user will reduce the weight of this label these commodity corresponding.User have purchased C mobile phone after the return of goods, then this behavior is recorded in behavior storehouse.
Fig. 2 is according to an embodiment of the invention based on the process flow diagram of the method 200 of return of goods related information Recommendations.As shown in Figure 2, first the method 200 sets up Commercial goods labels database in step 202.Particularly, first utilize the existing Commercial goods labels in electric business website to set up an initial Commercial goods labels storehouse, this initial tag library for identifying some basic information of commodity, the information such as such as category, price height, quality, as the first label, the mark behavior of this type of label source user.Then, join in initial tag library using the return of goods reason in returning goods as Equations of The Second Kind label, the label of return of goods reason, as preset value, can associate with first kind label.Such as, the price height in first kind label associates with the price in Equations of The Second Kind label is low, and the quality height in first kind label associates with the price in Equations of The Second Kind label is low, as a basis of subsequent recommendation commodity.
Then, in step 204, method 200 sets up the Shopping Behaviors context system based on returning goods.Such as, after user's return of goods behavior each time, the Shopping Behaviors (such as, 5 times) of specific times all will be recorded among this system, simultaneously as a basis of subsequent recommendation.
Then, in step 206, method 200 calculates the commodity of given number based on return of goods reason and rear Shopping Behaviors of returning goods.Particularly, when there is return of goods behavior in user, the commodity of the given number that we the most often buy after can calculating the return of goods as follows:
A. based on Commercial goods labels: when user selects return of goods reason, we can first according to return of goods reason as Equations of The Second Kind label, associate out first kind label A, this label supplementing as first kind label, the commodity (such as, 5 commodity) of the given number the most close with the commodity of returning goods are calculated based on Commercial goods labels;
B. based on shopping context: the commodity of returning goods occur user, in the system that have recorded the rear Shopping Behaviors of the return of goods, the commodity (such as, 5 commodity) of the given number the most often bought after calculating this merchandise return.
Finally, in step 208, the commodity of the given number the most often bought after the commodity of the most close calculated given number and this merchandise return are recommended user as set by the method 200.Method 200 so far terminates.
According to technical scheme of the present invention, user not only can obtain the merchandise news of subsequent recommendation after the return of goods, and the analysis of buying behavior after reason and return of goods identical goods of can returning goods based on user, commercial product recommending is carried out in conjunction with user's behavior of returning goods, thus effectively improve the second purchase rate of user, save the time that user selects commodity, improve the viscosity of user to website.
Above-described embodiment is only the preferred embodiments of the present invention, is not limited to the present invention.It will be apparent for a person skilled in the art that without departing from the spirit and scope of the present invention, various amendment and change can be carried out to embodiments of the invention.Therefore, the invention is intended to contain all amendments within the scope of the present invention as defined by the appended claims of falling into or modification.
Claims (10)
1., based on a method for return of goods related information Recommendations, comprising:
Set up Commercial goods labels database;
Set up the Shopping Behaviors context system based on returning goods;
The commodity of given number are calculated based on described Commercial goods labels and described Shopping Behaviors context; And
By the commercial product recommending of calculated given number to user.
2. method according to claim 1, wherein, the second label that described Commercial goods labels comprises the first label and is associated with described first label, described first label comprises the information of commodity, and described second label comprises described return of goods reason.
3. method according to claim 1, wherein, described Shopping Behaviors context comprises the Shopping Behaviors of rear specific times of returning goods.
4. method according to claim 2, wherein, the step calculating the commodity of the given number the most often bought after returning goods comprises further:
Based on described second label, associate out described first label with the commodity of the most close given number of the commodity drawn with return goods; And
Based on described Shopping Behaviors context, the commodity of the given number the most often bought after calculating the return of goods.
5. method according to claim 1, wherein, the commodity that the commodity of described given number comprise the given number the most close with the commodity of returning goods and the commodity of given number the most often bought after returning goods.
6., based on a system for return of goods related information Recommendations, comprising:
Database, described database is used for storing commodity tag database;
Return of goods system, described return of goods system is for setting up the Shopping Behaviors context system based on returning goods;
Commending system, described commending system is used for the commodity calculating given number based on described Commercial goods labels and described Shopping Behaviors context, and by the commercial product recommending of calculated given number to user.
7. system according to claim 6, wherein, the second label that described Commercial goods labels comprises the first label and is associated with described first label, described first label comprises the information of commodity, and described second label comprises described return of goods reason.
8. system according to claim 6, wherein, described Shopping Behaviors context comprises the Shopping Behaviors of rear specific times of returning goods.
9. system according to claim 7, wherein, described commending system is configured to further:
Based on described second label, associate out described first label with the commodity of the most close given number of the commodity drawn with return goods; And
Based on described Shopping Behaviors context, the commodity of the given number the most often bought after calculating the return of goods.
10. system according to claim 6, wherein, the commodity that the commodity of described given number comprise the given number the most close with the commodity of returning goods and the commodity of given number the most often bought after returning goods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510062406.7A CN104615721B (en) | 2015-02-06 | 2015-02-06 | For the method and system based on return of goods related information Recommendations |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510062406.7A CN104615721B (en) | 2015-02-06 | 2015-02-06 | For the method and system based on return of goods related information Recommendations |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104615721A true CN104615721A (en) | 2015-05-13 |
| CN104615721B CN104615721B (en) | 2018-02-16 |
Family
ID=53150163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510062406.7A Active CN104615721B (en) | 2015-02-06 | 2015-02-06 | For the method and system based on return of goods related information Recommendations |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104615721B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809637A (en) * | 2015-05-18 | 2015-07-29 | 北京京东尚科信息技术有限公司 | Commodity recommending method and system realized by computer |
| CN106411908A (en) * | 2016-10-13 | 2017-02-15 | 网易乐得科技有限公司 | Recommendation method and device |
| CN108665345A (en) * | 2018-05-07 | 2018-10-16 | 北京科码先锋互联网技术股份有限公司 | Label mapping method |
| CN109426974A (en) * | 2017-08-25 | 2019-03-05 | 北京奇虎科技有限公司 | Competing product analysis method and device |
| CN110019170A (en) * | 2017-12-29 | 2019-07-16 | 北京京东尚科信息技术有限公司 | Data processing method, system, computer system and computer readable storage medium |
| CN111275450A (en) * | 2018-11-19 | 2020-06-12 | 北京京东尚科信息技术有限公司 | Method and system for processing associated preferential information after goods return |
| CN117952507A (en) * | 2024-03-26 | 2024-04-30 | 南京亿猫信息技术有限公司 | Intelligent shopping cart commodity returning identification method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254028A (en) * | 2011-07-22 | 2011-11-23 | 青岛理工大学 | Personalized commodity recommending method and system which integrate attributes and structural similarity |
| CN102760163A (en) * | 2012-06-12 | 2012-10-31 | 奇智软件（北京）有限公司 | Personalized recommendation method and device of characteristic information |
| US20130013448A1 (en) * | 2011-01-27 | 2013-01-10 | Bradley Andrew J | Behavioral filter for personalized recommendations |
| US20130173419A1 (en) * | 2011-12-30 | 2013-07-04 | Certona Corporation | Recommending repeated transactions |
| CN103544632A (en) * | 2013-07-22 | 2014-01-29 | 杭州师范大学 | Method and system for individually recommending network commodities |
-
2015
- 2015-02-06 CN CN201510062406.7A patent/CN104615721B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130013448A1 (en) * | 2011-01-27 | 2013-01-10 | Bradley Andrew J | Behavioral filter for personalized recommendations |
| CN102254028A (en) * | 2011-07-22 | 2011-11-23 | 青岛理工大学 | Personalized commodity recommending method and system which integrate attributes and structural similarity |
| US20130173419A1 (en) * | 2011-12-30 | 2013-07-04 | Certona Corporation | Recommending repeated transactions |
| CN102760163A (en) * | 2012-06-12 | 2012-10-31 | 奇智软件（北京）有限公司 | Personalized recommendation method and device of characteristic information |
| CN103544632A (en) * | 2013-07-22 | 2014-01-29 | 杭州师范大学 | Method and system for individually recommending network commodities |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809637A (en) * | 2015-05-18 | 2015-07-29 | 北京京东尚科信息技术有限公司 | Commodity recommending method and system realized by computer |
| CN106411908A (en) * | 2016-10-13 | 2017-02-15 | 网易乐得科技有限公司 | Recommendation method and device |
| CN106411908B (en) * | 2016-10-13 | 2019-12-03 | 网易乐得科技有限公司 | A kind of recommended method and device |
| CN109426974A (en) * | 2017-08-25 | 2019-03-05 | 北京奇虎科技有限公司 | Competing product analysis method and device |
| CN110019170A (en) * | 2017-12-29 | 2019-07-16 | 北京京东尚科信息技术有限公司 | Data processing method, system, computer system and computer readable storage medium |
| CN108665345A (en) * | 2018-05-07 | 2018-10-16 | 北京科码先锋互联网技术股份有限公司 | Label mapping method |
| CN108665345B (en) * | 2018-05-07 | 2021-11-09 | 北京科码先锋互联网技术股份有限公司 | Label mapping method |
| CN111275450A (en) * | 2018-11-19 | 2020-06-12 | 北京京东尚科信息技术有限公司 | Method and system for processing associated preferential information after goods return |
| CN111275450B (en) * | 2018-11-19 | 2024-04-16 | 北京京东尚科信息技术有限公司 | Processing method and system of associated preferential information after commodity return |
| CN117952507A (en) * | 2024-03-26 | 2024-04-30 | 南京亿猫信息技术有限公司 | Intelligent shopping cart commodity returning identification method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104615721B (en) | 2018-02-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104615721A (en) | Method and system for recommending communities based on returned goods related information | |
| CN102629360B (en) | A kind of effective dynamic commodity recommend method and commercial product recommending system | |
| CN108960992A (en) | A kind of information recommendation method and relevant device | |
| US10783561B2 (en) | Systems and methods for optimizing targeted advertising through social media interactions | |
| CN105718184A (en) | Data processing method and apparatus | |
| CN103914492A (en) | Method for query term fusion, method for commodity information publish and method and system for searching | |
| CN110969512B (en) | Commodity recommendation method and device based on user purchasing behavior | |
| CN111310038B (en) | Information recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN107291779B (en) | Cache data management method and device | |
| CN109711917B (en) | Information pushing method and device | |
| CN104809637A (en) | Commodity recommending method and system realized by computer | |
| CN108805598A (en) | Similarity information determines method, server and computer readable storage medium | |
| CN102073737A (en) | Method and system for automatically providing real-time purchasing suggestion for network retailer | |
| CN105630836A (en) | Searching result sorting method and apparatus | |
| WO2020238363A1 (en) | Method and apparatus for pushing information, electronic commerce system and storage medium | |
| CN112132660B (en) | Commodity recommendation method, system, equipment and storage medium | |
| CN104331818A (en) | Method and system capable of controlling differential pushing of merchant service information | |
| CN104992348A (en) | Method and device for displaying information | |
| CN104021485A (en) | Commodity push method and device based on physiological index parameters | |
| CN110751537A (en) | Online and offline intelligent marketing method and device | |
| TWI552099B (en) | Recommended user method and device | |
| CN110618842B (en) | Service processing method and device, electronic equipment and storage medium | |
| US9799065B1 (en) | Associating items based at least in part on physical location information | |
| US20130339136A1 (en) | Detection of events from bursts of activity indicators | |
| KR101637986B1 (en) | System for providing the optimal products and method thereof |
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 |