CN104615721B - For the method and system based on return of goods related information Recommendations - Google Patents
For the method and system based on return of goods related information Recommendations Download PDFInfo
- Publication number
- CN104615721B CN104615721B CN201510062406.7A CN201510062406A CN104615721B CN 104615721 B CN104615721 B CN 104615721B CN 201510062406 A CN201510062406 A CN 201510062406A CN 104615721 B CN104615721 B CN 104615721B
- Authority
- CN
- China
- Prior art keywords
- goods
- commodity
- return
- label
- certain 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.)
- Active
Links
- 230000006399 behavior Effects 0.000 claims abstract description 46
- 241000394635 Acetomicrobium mobile Species 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000002860 competitive Effects 0.000 description 1
- 230000001419 dependent Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006011 modification reaction Methods 0.000 description 1
- 230000000717 retained Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
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
Abstract
The invention discloses for the method and system based on return of goods related information Recommendations.Methods described includes：Establish Commercial goods labelses database；Establish the Shopping Behaviors context system based on the return of goods；Certain number of commodity are calculated based on the Commercial goods labelses and the Shopping Behaviors context；And by the certain number of commercial product recommending calculated to user.
Description
Technical field
The present invention relates to recommending goods in electronic business, and more particularly, the present invention relate to based on return of goods related information
The method and system of Recommendations.
Background technology
With the development of popularization and the ecommerce of internet, shopping at network platform is just constantly releasing various hommization clothes
Business, for example, in order that user more quickly finds desired commodity, the network row of user can be collected and analyzed to shopping at network platform
For, and then recommend dependent merchandise for user.Under the competitive environment being growing more intense, Recommendations information can be effectively retained user,
Customer loss is prevented, and improves the sale of e-commerce system.
Existing commending system uses the big data analytical technology based on commodity, user behavior, and it can be based on commodity
Label recommends suitable commodity, or the hobby set according to the conventional preference of user or user to recommend similar production to user
Product.For example, when return of goods behavior occurs for user, a series of behaviors of the system of prior art based on user before the return of goods, are business
Product identify its label, are user's Recommendations using Commercial goods labelses.Therefore, user is after the return of goods, otherwise do not pushed away subsequently
The merchandise news recommended, otherwise the obtained return of goods that are all based on move ahead as the commodity of recommendation, this behavior base returned goods with user at that time
Originally it is to have no to associate.Because the system of prior art can not be using return of goods related information come for user's Recommendations, so can not
More effectively improve buying rate.
Therefore, it is necessary to which a kind of can be based on return of goods related information come the method and system for user's Recommendations, to enter
One step improves second purchase rate.
The content of the invention
In the inventive solutions, the reasons why being returned goods according to user, it is combined with the user of same return of goods behavior
Follow-up buying behavior information, be user's Recommendations, so as to improve second purchase rate.
According to one embodiment of present invention, there is provided a kind of method based on return of goods related information Recommendations, including：
Establish Commercial goods labelses database；Establish the Shopping Behaviors context system based on the return of goods；Based on the Commercial goods labelses and the purchase
Thing behavior context calculates certain number of commodity；And by the certain number of commercial product recommending calculated to user.
Preferably, the Commercial goods labelses include the first label and second label associated with first label, described
First label includes the information of commodity, and second label includes the return of goods reason.
Preferably, the Shopping Behaviors context includes the Shopping Behaviors of specific times after returning goods.
Preferably, the step of calculating the certain number of commodity most often bought after returning goods further comprises：Based on described
Two labels, the most similar certain number of commodity of the commodity for associating out first label to draw and return goods；And based on institute
Shopping Behaviors context is stated, calculates the certain number of commodity most often bought after returning goods.
Preferably, the certain number of commodity include the most similar certain number of commodity of commodity and the return of goods with the return of goods
The certain number of commodity most often bought afterwards.
According to another embodiment of the invention, there is provided a kind of system based on return of goods related information Recommendations, bag
Include：Database, the database are used to store Commercial goods labelses database；Return of goods system, the return of goods system are based on for foundation
The Shopping Behaviors context system of the return of goods；Commending system, the commending system are used to be based on the Commercial goods labelses and the shopping
Behavior context calculates certain number of commodity, and by the certain number of commercial product recommending calculated to user.
Preferably, the Commercial goods labelses include the first label and second label associated with first label, described
First label includes the information of commodity, and second label includes the return of goods reason.
Preferably, the Shopping Behaviors context includes the Shopping Behaviors of specific times after returning goods.
Preferably, the commending system is further configured to：Based on second label, first label is associated out
With the most similar certain number of commodity of the commodity for drawing and returning goods；And based on the Shopping Behaviors context, calculate and move back
The certain number of commodity most often bought after goods.
Preferably, the certain number of commodity include the most similar certain number of commodity of commodity and the return of goods with the return of goods
The certain number of commodity most often bought afterwards.
According to the detailed description below the disclosure and accompanying drawing, mesh other to those skilled in the art
, feature and advantage will be apparent.
Brief description of the drawings
Accompanying drawing illustrates embodiments of the invention, and for explaining principle of the invention together with specification.In the accompanying drawings：
Fig. 1 is the schematic diagram of the system according to an embodiment of the invention based on return of goods related information Recommendations.
Fig. 2 is the flow chart of the method according to an embodiment of the invention based on return of goods related information Recommendations.
Embodiment
Disclose according to an embodiment of the invention and a kind of be used for the method and system based on return of goods related information Recommendations.
In the following description, for illustrative purposes, multiple details are elaborated to provide comprehensive reason to embodiments of the invention
Solution.However, for those skilled in the art it is readily apparent that embodiments of the invention can be in the case of without these details
Lower realization.
Term " commending system " as used herein is built upon a kind of Advanced Business intelligence on the basis of mass data is excavated
Energy platform, to help e-commerce website to provide complete personalized decision support and information service, simulation as its customer purchase
Sales force helps user to complete purchasing process.
Term " big data " as used herein, or flood tide data, refer to that involved data quantity is huge and arrive
It can not reach acquisition within the reasonable time by current main software instrument, manage, handle and arrange as enterprise operation is helped
The information of the more positive purpose of decision-making.
Fig. 1 is the schematic diagram of the system 100 according to an embodiment of the invention based on return of goods related information Recommendations.Should
System 100 includes return of goods system 101, high-volume database 103, commending system 105 and user 107.
Return of goods system 101 is used for establishing the Shopping Behaviors context system based on the return of goods, the Shopping Behaviors context bag
Include the Shopping Behaviors of specific times after returning goods.High-volume database 103 is used for storing Commercial goods labelses storehouse.Commercial goods labelses are used for indicating business
The information of product, including the first label and second label associated with first label, first label include commodity
Information, second label include the return of goods reason.For example, the Commercial goods labelses include but is not limited to the category of commodity, valency
Lattice, quality, return of goods reason etc..Commending system 105 is used to calculate based on the Commercial goods labelses and the Shopping Behaviors context
Certain number of commodity, and by the certain number of commercial product recommending calculated to user 107.
For example, commodity A mobile phones have following first kind label before restocking：A. mobile phone, b. mass are good, c. configurations are high,
D. price is low.Commodity B mobile phones have following first kind label before restocking：A. mobile phone, b. signals are good, c. outward appearances are beautiful, d.
Battery durable is outstanding.If user, there occurs reimbursement, and have selected in return of goods interface user following after A mobile phones are bought
Reason：X. signal difference, y. battery durables are poor, z. prices are high, and such reason belongs to the second class label of the commodity.In commending system
In 105, the x. signal differences in the second class label and the b. signals in first kind label are the second class label as relating attribute well
In y. battery durables difference and first kind label in d. battery durables it is outstanding be as relating attribute.After user returns goods,
The weight of first kind label recommendations will be modified to that a. mobile phones, b. signals are good, c. battery durables are outstanding, d. configurations are high.Then, pass through
Cross the computing of the algorithm of commending system 105, it will the first in subsequent recommendation to recommend B mobile phones.
Moreover, commending system 105 can count in the behavior storehouse after user returns goods, after A mobile phones occur and return goods, use
The buying behavior that family occurs most frequently is followed successively by C mobile phones, D mobile phones, E mobile phones, B mobile phones, F mobile phones, and passes through and first kind label
It is compared, commending system 105 finally may proceed to recommended user and buy C, D and F mobile phone.If user selects reason in the return of goods
Z. price is high, the high term correlation tag low with the d. prices in first kind label of z. prices, but due to also having this in former commodity
Label, the then return of goods behavior of user will reduce the weight that the label corresponds to this commodity.User have purchased C mobile phones after the return of goods,
Then this behavior is recorded in behavior storehouse.
Fig. 2 is the flow chart of the method 200 according to an embodiment of the invention based on return of goods related information Recommendations.Such as
Shown in Fig. 2, this method 200 establishes Commercial goods labelses database in step 202 first.Specifically, it is existing first with electric business website
Commercial goods labelses establish an initial Commercial goods labelses storehouse, this initial tag library is used for some the basic letters for identifying commodity
Breath, such as the information such as category, price height, quality, as the first label, the mark behavior of such label source user.Then,
It is added to the return of goods reason in the return of goods as the second class label in initial tag library, the label of return of goods reason is as default
Value, can be associated with first kind label.For example, price in first kind label it is high it is low with the price in the second class label enter
Row is associated, and the quality height in first kind label is low with the price in the second class label to be associated, as subsequent recommendation commodity
One basis.
Then, in step 204, method 200 establishes the Shopping Behaviors context system based on the return of goods.For example, user is every
Among the Shopping Behaviors (for example, 5 times) of specific times all will recorded this system after return of goods behavior once, while as follow-up
The basis recommended.
Then, in step 206, method 200 is certain number of to calculate based on Shopping Behaviors after return of goods reason and the return of goods
Commodity.Specifically, when return of goods behavior occurs for user, the certain number of business most often bought after the return of goods can be calculated as below in we
Product：
A. Commercial goods labelses are based on：When user selects return of goods reason, we can be first according to return of goods reason as the second category
Label, associate out first kind label A, supplement of this label as first kind label, and the commodity with returning goods are calculated based on Commercial goods labelses
Most similar certain number of commodity (for example, 5 commodity)；
B. based on shopping context：The commodity that user returns goods, in the system of Shopping Behaviors after have recorded the return of goods, calculate
Go out after the merchandise return the certain number of commodity (for example, 5 commodity) most often bought.
Finally, in step 208, this method 200 is by the most similar certain number of commodity calculated and the merchandise return
The certain number of commodity most often bought afterwards recommend user as set.Method 200 so far terminates.
Technique according to the invention scheme, user can not only obtain the merchandise news of subsequent recommendation after the return of goods, and
Commodity can be carried out with reference to the behavior of user's return of goods based on the analysis of buying behavior after user's return of goods reason and identical commodity of returning goods
Recommend, so as to effectively increase the second purchase rate of user, save the time that user selects commodity, improve user to website
Viscosity.
Above-described embodiment is only the preferred embodiments of the present invention, is not intended to limit the invention.To those skilled in the art
It is readily apparent that without departing from the spirit and scope of the present invention, various repair can be carried out to embodiments of the invention
Change and change.Therefore, the invention is intended to cover to fall into all within the scope of the present invention as defined by the appended claims and repair
Change or modification.
Claims (8)
1. a kind of method based on return of goods related information Recommendations, including：
Establish Commercial goods labelses database；Wherein, the Commercial goods labelses include the first label and associated with first label
Second label, first label include the information of commodity, and second label includes the return of goods reason；
Establish the Shopping Behaviors context system based on the return of goods；
Certain number of commodity are calculated based on the Commercial goods labelses and the Shopping Behaviors context；And
By the certain number of commercial product recommending calculated to user.
2. according to the method for claim 1, wherein, the Shopping Behaviors context includes the shopping of specific times after returning goods
Behavior.
3. according to the method for claim 1, wherein, calculate return goods after most often buy certain number of commodity the step of enter
One step includes：
Based on second label, the most similar certain number of business of the commodity for associating out first label to draw and return goods
Product；And
Based on the Shopping Behaviors context, the certain number of commodity most often bought after returning goods are calculated.
4. according to the method for claim 1, wherein, the certain number of commodity include most similar with the commodity of the return of goods
Certain number of commodity and the certain number of commodity most often bought afterwards of returning goods.
5. a kind of system based on return of goods related information Recommendations, including：
Database, the database are used to store Commercial goods labelses database；Wherein, the Commercial goods labelses include the first label and with
The second associated label of first label, first label include the information of commodity, and second label includes described
Return of goods reason；
Return of goods system, the return of goods system are used to establish the Shopping Behaviors context system based on the return of goods；
Commending system, the commending system are used to calculate certain number based on the Commercial goods labelses and the Shopping Behaviors context
Purpose commodity, and by the certain number of commercial product recommending calculated to user.
6. system according to claim 5, wherein, the Shopping Behaviors context includes the shopping of specific times after returning goods
Behavior.
7. system according to claim 5, wherein, the commending system is further configured to：
Based on second label, the most similar certain number of business of the commodity for associating out first label to draw and return goods
Product；And
Based on the Shopping Behaviors context, the certain number of commodity most often bought after returning goods are calculated.
8. system according to claim 5, wherein, the certain number of commodity include most similar with the commodity of the return of goods
Certain number of commodity and the certain number of commodity most often bought afterwards of 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 CN104615721A (en) | 2015-05-13 |
| CN104615721B true 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) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809637B (en) * | 2015-05-18 | 2021-07-20 | 北京京东尚科信息技术有限公司 | Computer-implemented commodity recommendation method and system |
| 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 |
| 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 |
Citations (4)
| 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 |
| CN103544632A (en) * | 2013-07-22 | 2014-01-29 | 杭州师范大学 | Method and system for individually recommending network commodities |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130173419A1 (en) * | 2011-12-30 | 2013-07-04 | Certona Corporation | Recommending repeated transactions |
-
2015
- 2015-02-06 CN CN201510062406.7A patent/CN104615721B/en active Active
Patent Citations (4)
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104615721A (en) | 2015-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110222272B (en) | Potential customer mining and recommending method | |
| CN104615721B (en) | For the method and system based on return of goods related information Recommendations | |
| CN102629360B (en) | A kind of effective dynamic commodity recommend method and commercial product recommending system | |
| CN105718184A (en) | Data processing method and apparatus | |
| CN108960992A (en) | A kind of information recommendation method and relevant device | |
| CN106708821A (en) | User personalized shopping behavior-based commodity recommendation method | |
| CN108960719B (en) | Method and device for selecting products and computer readable storage medium | |
| CN104239338A (en) | Information recommendation method and information recommendation device | |
| CN103970850B (en) | Site information recommends method and system | |
| WO2016150354A1 (en) | Method and system for classifying users of e-commerce platform | |
| EP3528142A1 (en) | Method for accurately searching within website | |
| CN104820863A (en) | Consumer portrait generation method and device | |
| CN105976229A (en) | Collaborative filtering algorithm based on user and project mixing | |
| CN105761099A (en) | Business information recommendation system and method based on behavior data of multi-business channel | |
| CN112837118B (en) | Commodity recommendation method and device for enterprise users | |
| CN106096998A (en) | The price data statistical decision of a kind of electricity business's platform analyzes method | |
| CN107679103B (en) | Attribute analysis method and system for entity | |
| CN103778553A (en) | Commodity attribute recommendation method and commodity attribute recommendation system | |
| CN107403345A (en) | Best-selling product Forecasting Methodology and system, storage medium and electric terminal | |
| CN109087177A (en) | To the method, apparatus and computer readable storage medium of target user's Recommendations | |
| US8793201B1 (en) | System and method for seeding rule-based machine learning models | |
| CN109840796B (en) | Decision factor analysis device and decision factor analysis method | |
| CN102073737A (en) | Method and system for automatically providing real-time purchasing suggestion for network retailer | |
| CN111310038B (en) | Information recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN104408648A (en) | Method and device for choosing items |
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 |