CN108022152A - The automatic commending system of user's commodity and recommendation method based on image recognition - Google Patents
The automatic commending system of user's commodity and recommendation method based on image recognition Download PDFInfo
- Publication number
- CN108022152A CN108022152A CN201711243171.7A CN201711243171A CN108022152A CN 108022152 A CN108022152 A CN 108022152A CN 201711243171 A CN201711243171 A CN 201711243171A CN 108022152 A CN108022152 A CN 108022152A
- Authority
- CN
- China
- Prior art keywords
- user
- commercial product
- product recommending
- module
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides the automatic commending system of user's commodity based on image recognition and recommend method, which includes：User images acquisition module, for gathering user images in real time, and is sent to subscriber identification module；Subscriber identification module, for user images to be converted to user parameter information, and is sent to user type judgment module by user parameter information；User type judgment module, sends to commercial product recommending model computation module for judging the user for new user or old user, and by user parameter information；Commercial product recommending model computation module, for sending the commercial product recommending calculated information to commercial product recommending inventory generation module；Commercial product recommending inventory generation module, for commercial product recommending information to be generated commercial product recommending inventory, and is sent to terminal and is shown；Database, for real-time storage and renewal user parameter information and type of merchandise information.The present invention has the advantages that simple in structure, easy to operate and improves merchandise sales rate.
Description
Technical field
The present invention relates to commercial product recommending technical field, more particularly to a kind of user's commodity based on image recognition to recommend automatically
System and recommendation method.
Background technology
Under the overall background of " internet+", e-commerce is flourished, meanwhile, country also supports electric business energetically
Development, solves the problem of employment of many people.Currently, large quantities of electric business platforms have been emerged in large numbers, commodity amount is hundreds of millions of, to consume
Person removes to find one by one oneself desired thing and becomes impossible task, and usual electric business platform can all classify commodity
Put, or search capability is provided, but this allows people to find desired commodity or gruelling.At present, some electric business websites
Commodity in use commending system provides for customer recommends commodity interested.The commending system of these electric business platforms mainly according to
The relevant informations such as the passing data in family, the automatic commodity that may be interested in for user's displaying, such as according to the history purchaser record of user
Such as buy classification, the time buying comes for same user's Recommendations, substantially increase user and buy efficiency, enhance user's body
Test, it has also become the important component of electric business platform.
At present, commercial product recommending system is applied to electric business platform mostly, is designed primarily directed to user's shopping on the web.
It is browsed the preference that history etc. obtains user, is carried out using collaborative filtering according to being by user behavior, such as purchasing history
Commercial product recommending.And the commercial product recommending system in physical stores mainly utilizes face recognition technology, shop user's face is recorded, it is raw
Into unique ID, and record user and seek advice from product information, as user again to shop after, facilitate sales force to user recommend produce
Product.When the shortcomings that this system is that new user does not produce historical data also, any accurate commodity, i.e., existing reality can not be recommended
Body shop such as 4S shops, can not provide intelligent recommendation service to arrive shop user first.
The content of the invention
In view of the above problems, it is proposed that the present invention overcomes the above problem in order to provide one kind or solves at least in part
State the automatic commending system of user's commodity and recommendation method based on image recognition of problem.
One aspect of the present invention, there is provided a kind of automatic commending system of user's commodity based on image recognition, including：
User images acquisition module, for gathering user images in real time, and is sent to subscriber identification module；
Subscriber identification module, for user images to be converted to user parameter information, and user parameter information is sent out
Give user type judgment module；
User type judgment module, the customer parameter for will have been deposited in user parameter information and customer parameter database are believed
Breath is contrasted, and judges that the user for new user or old user, if new user, then sends user parameter information respectively
To customer parameter database and commercial product recommending model computation module, if old user, then user parameter information is sent to commodity
Recommended models computing module；
Commercial product recommending model computation module, for the commodity transferred to user parameter information and from type of merchandise database
Type information is calculated, and the commercial product recommending information calculated is sent to commercial product recommending inventory generation module；
Commercial product recommending inventory generation module, for commercial product recommending information to be generated commercial product recommending inventory, and is sent to terminal；
Terminal, the commercial product recommending inventory of reception is shown；
Customer parameter database, for real-time storage and renewal user parameter information；
Type of merchandise database, for real-time storage and renewal type of merchandise information.
Further, commercial product recommending model computation module calculates commodity using association analysis algorithm or collaborative filtering
Recommendation information.
Further, user images acquisition module gathers user images in real time using camera, and is wirelessly sent to user
Identification module.
Further, commercial product recommending inventory generation module pushes away commercial product recommending information generation commodity according to the sales volume of commodity
Inventory is recommended, and is sent to terminal.
Further, user images acquisition module is connected with subscriber identification module radio, user type judgment module point
It is not electrically connected with subscriber identification module, customer parameter database, commercial product recommending model computation module, commercial product recommending model calculates mould
Block is electrically connected with type of merchandise database, commercial product recommending inventory generation module respectively, commercial product recommending inventory generation module and terminal
Radio connects.
The second aspect of the invention, there is provided a kind of user's commodity auto recommending method based on image recognition, including
Following steps：
User images acquisition module gathers user images in real time, and is sent to subscriber identification module；
User images are converted to user parameter information by subscriber identification module, and user parameter information is sent to use
Family type judging module；
User type judgment module by the user parameter information deposited in user parameter information and customer parameter database into
Row contrast, and judge that user parameter information for new user or old user, if new user, then is respectively sent to use by the user
Family parameter database and commercial product recommending model computation module, if old user, then send user parameter information to commercial product recommending
Model computation module；
The type of merchandise that commercial product recommending model computation module is transferred to user parameter information and from type of merchandise database
Information is calculated, and the commercial product recommending information calculated is sent to commercial product recommending inventory generation module；
Commercial product recommending information is generated commercial product recommending inventory by commercial product recommending inventory generation module, and is sent to terminal；
Terminal is shown the commercial product recommending inventory of reception；
Customer parameter database real-time storage and renewal user parameter information；
Type of merchandise database real-time storage and renewal type of merchandise information.
Further, commercial product recommending model computation module calculates commodity using association analysis algorithm or collaborative filtering
Recommendation information.
Further, user images acquisition module gathers user images in real time using camera, and is wirelessly sent to user
Identification module.
Further, commercial product recommending inventory generation module pushes away commercial product recommending information generation commodity according to the sales volume of commodity
Inventory is recommended, and is sent to terminal.
Further, commercial product recommending inventory is wirelessly sent to terminal by commercial product recommending inventory generation module.
The automatic commending system of user's commodity and recommendation method provided by the invention based on image recognition, by collecting shop
The image information of user, can be embodied as the function that old and new users provides commercial product recommending, compared with prior art with following progress：
With reference to existing user information and goods purchase information, in time, easily to provide the commodity of personalization to the old and new users in shop
Recommendation service, has the advantages that simple in structure, easy to operate and improves marketing efficiency.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the embodiment of the present invention.
Brief description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this area
Technical staff will be clear understanding.Attached drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And in whole attached drawing, identical component is denoted by the same reference numerals.In the accompanying drawings：
Fig. 1 is that the device of the automatic commending system of user's commodity based on image recognition of the embodiment of the present invention connects block diagram；
The step of Fig. 2 is user's commodity auto recommending method based on image recognition of the embodiment of the present invention is schemed.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific terminology), there is the meaning identical with the general understanding of the those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have with the context of the prior art
The consistent meaning of meaning, and unless by specific definitions, otherwise will not be explained with the implication of idealization or overly formal.
Fig. 1 diagrammatically illustrates the automatic commending system of user's commodity based on image recognition of one embodiment of the invention
Device connects block diagram.Reference Fig. 1, the automatic commending system of user's commodity based on image recognition of the embodiment of the present invention, including：
User images acquisition module, for gathering user images in real time, and is sent to subscriber identification module；
Subscriber identification module, for user images to be converted to user parameter information, and user parameter information is sent out
Give user type judgment module；
User type judgment module, the customer parameter for will have been deposited in user parameter information and customer parameter database are believed
Breath is contrasted, and judges that the user for new user or old user, if new user, then sends user parameter information respectively
To customer parameter database and commercial product recommending model computation module, if old user, then user parameter information is sent to commodity
Recommended models computing module；
Commercial product recommending model computation module, for the commodity transferred to user parameter information and from type of merchandise database
Type information is calculated, and the commercial product recommending information calculated is sent to commercial product recommending inventory generation module；
Commercial product recommending inventory generation module, for commercial product recommending information to be generated commercial product recommending inventory, and is sent to terminal；
Terminal, the commercial product recommending inventory of reception is shown；
Customer parameter database, for real-time storage and renewal user parameter information；
Type of merchandise database, for real-time storage and renewal type of merchandise information.
In the present embodiment, user images acquisition module is connected with subscriber identification module radio, user type judgment module
It is electrically connected respectively with subscriber identification module, customer parameter database, commercial product recommending model computation module, commercial product recommending model calculates
Module is electrically connected with type of merchandise database, commercial product recommending inventory generation module respectively, commercial product recommending inventory generation module and end
Hold radio connection.
User's commodity automatic commending system provided in this embodiment based on image recognition is acquired letter to user images
Breath, the user parameter information of collection is contrasted with the user parameter information deposited in customer parameter database, if user joins
The parameter information of the user is stored with number database, then is old user, is otherwise exactly new user.Divided according to existing
The user parameter information and type of merchandise information of class, commercial product recommending is provided for old and new users, has simple in structure, user
Just, the efficient and lower-cost advantage of commercial product recommending.
In one specific embodiment, commercial product recommending model computation module uses association analysis algorithm or collaborative filtering meter
Calculate commercial product recommending information.The preference degree that association analysis algorithm treats each attribute of Recommendations by calculating old and new users, it is right
Commodity are ranked up, and then carry out commercial product recommending for old and new users, and the advantages of algorithm is that calculation amount is small, advisory speed is very fast；
Collaborative filtering is divided into the collaborative filtering based on user and the collaborative filtering method based on model, the collaboration based on user
Filter algorithm, each user as the main body analyzed, for each colony, will pass through the commodity of each user in processing colony
Purchaser record, calculates the degree of association between each user of the colony and colony's other users, and then recommends him to the user
The advantages of commodity that oneself buys without purchase and with the high other users of the degree of association in colony, this algorithm is to count rapidly
The purchase preference of new user is calculated, so as to be new user's Recommendations；Collaborative filtering method based on model, i.e., based on sample
User preference information, one recommended models of training, is then predicted according to the information of real-time user preferences, calculates and recommends.
This method need by cluster etc. data processing, establish one using user as row, commodity be row HugeMatrix (huge squares
Battle array), matrix element is scoring of the user to commodity.The advantages of this algorithm is to calculate accurately, it is possible to increase is pushed away for old and new users
Recommend the accuracy rate of commodity.In other embodiment, can also be calculated using other algorithms, by those skilled in the art according to
Concrete condition makes choice, and the present invention no longer illustrates one by one, and above-described embodiment is only to provide a demonstrative example.
In one embodiment, using user's Recommendations that association analysis algorithm is 4S shops, concretely comprise the following steps：Each user
Colony has a feature, such as age bracket, area, shopping preferences, the data filled in when area is according to user's registration or user
Registration phone number location or user's ship-to determine；Each user is at least included into a user group, each user group
Body has overlapping with the user in another user group, i.e., each user has at least one feature at the same time.For example, user a is
19 years old, it is Beijing suburb, interested for Volkswagen；User b is 30 years old, areas of Beijing, interested for Benz；
User group W is the crowd between age bracket is 18 years old to 22 years old, and user group X is the crowd between 30~35 years old, user group
Body Y is the crowd of areas of Beijing, and user group Z is the crowd of Beijing suburb, and user group M is people interested in Benz
Group；Then user a can be attributed to user group W, Z, and user b can be attributed to user group X, Y and M.Then structure recommends matrix M,
Matrix M is recommended to be marked using user group as rower by row of merchandise classification, matrix element Mij represents i-th of user group to jth
The evaluation score of a merchandise classification, wherein i=1,2..u, j=1,2 ... p, u are user group's number, and p is merchandise classification number；
Using recommending matrix M to carry out commercial product recommending to new user, user group belonging to user is found out to belonging to commodity from matrix M is recommended
Merchandise classification evaluation score, select highest evaluation score corresponding to merchandise classification as recommendation merchandise classification, and from
Recommendations in the merchandise classification, the commodity of recommendation be in affiliated merchandise classification with the highest some business of the commodity association degree
Product, the degree of association can be obtained by calculation of relationship degree.
In the present embodiment, user images acquisition module gathers user images in real time using camera, and is wirelessly sent to use
Family identification module.Subscriber identification module analyzes the pixel in image, identifies and changes out user parameter information, such as uses
The age at family, gender information.Wherein, the user images of collection can be the real-time head portrait of user or certificate photograph etc..According to
The age of different user and gender information sort out the type of merchandise, user can be divided into difference according to age and gender
Colony, the common type of merchandise purchase preference of the colony is determined, in favor of being later old and new users with reference to the type of merchandise
Buy preference Recommendations.In other embodiment, user can also be classified according to region, above example is simply demonstrated
Property example.This sorting technique is fairly simple, can improve the accuracy and validity of commercial product recommending.
In the present embodiment, commercial product recommending information is generated commodity by commercial product recommending inventory generation module according to the sales volume of commodity
Recommend inventory, and be sent to terminal.Commercial product recommending model computation module is calculated using association analysis algorithm or collaborative filtering
Go out commercial product recommending information and be sent to commercial product recommending inventory generation module afterwards, commercial product recommending inventory generation module will be according to the commodity
Recommendation information is ranked up commodity, in order to which sales force recommends user according to the ranking results, is recommended with improving
The accuracy of commodity, and save the time.In the present embodiment, commercial product recommending inventory generation module is according to the sales volumes of commodity by commodity
Recommendation information generates commercial product recommending inventory, and sales volume is a parameter easy to obtain, count and validity is strong, by sales volume most
High commodity make number one, and recommend the commodity to user first, can further improve accurate rate and the sale of commercial product recommending
Rate.In the present embodiment, commercial product recommending inventory is wirelessly sent to terminal by commercial product recommending inventory generation module, for example passes through 3G/4G
Network or wifi network etc. wirelessly carry out the transmission of data, save the complexity of cable connection, simplify structure, than
More convenient, saving space and cost.Terminal in the present embodiment is mobile phone either tablet computer or computer, by sales force
Make choice as the case may be, more convenient sales force carries out commercial product recommending to user.
In the present embodiment, user images acquisition module carries out collection user images, and transmitting wirelessly in real time using camera
To subscriber identification module.User images are gathered in real time using camera, cost and enhancing user experience can be reduced.
Fig. 2 diagrammatically illustrates user's commodity auto recommending method based on image recognition of one embodiment of the invention
Block diagram.With reference to Fig. 2, user's commodity auto recommending method based on image recognition of the embodiment of the present invention, comprises the following steps：
S1, user images acquisition module gather user images, and are sent to subscriber identification module in real time；
User images are converted to user parameter information by S2, subscriber identification module, and user parameter information is sent
Give user type judgment module；
The user parameter information that S3, user type judgment module will have been deposited in user parameter information and customer parameter database
Contrasted, and judge that user parameter information for new user or old user, if new user, is then respectively sent to by the user
Customer parameter database and commercial product recommending model computation module, user parameter information if old user, then sent to commodity and pushed away
Recommend model computation module；
The commodity class that S4, commercial product recommending model computation module are transferred to user parameter information and from type of merchandise database
Type information is calculated, and the commercial product recommending information calculated is sent to commercial product recommending inventory generation module；
S5, commercial product recommending inventory generation module by commercial product recommending information generate commercial product recommending inventory, and be sent to terminal into
Row display；
S6, database real-time storage and renewal user parameter information and type of merchandise information.
User's commodity auto recommending method based on image recognition in the present embodiment is simple, workable, can be rapid
Commercial product recommending effectively is provided for old and new users, has the advantages that to save time and cost.
In one specific embodiment, commercial product recommending model computation module uses association analysis algorithm or collaborative filtering meter
Calculate commercial product recommending information.Association analysis algorithm or collaborative filtering are fairly simple, and result of calculation is more accurate, and calculate speed
Degree is fast, can quickly calculate the preference degree of user, recommends personalized commercial in time, efficiently for old and new users easy to salesman.
In the present embodiment, user images acquisition module gathers user images in real time using camera, and is wirelessly sent to use
Family identification module.The popularity rate of camera is higher, and cost is relatively low, maintenance work easy to use and follow-up.User images are adopted
Collection module by wireless transmission as wifi network either 3G/4G networks or other user images are wirelessly sent to use
Family identification module, reduces cable connection complexity, more cost-effective and space.In the present embodiment, subscriber identification module is led to
User parameter information, including the age of user, gender, appearance etc. are changed out in the identifications such as the pixel crossed in user images, coordinate
Information.Age, gender information's division colony in the present embodiment by user, as the female user between 20-30 Sui was bought
Car category etc., make the recommendation of commodity more accurate, be conducive to improve commodity and sell rate.In other embodiment, it can also adopt
With other user parameter informations, such as region dividing user groups, above example is only demonstrative example, by this area
Technical staff makes choice as the case may be.
In the present embodiment, commercial product recommending information is generated commodity by commercial product recommending inventory generation module according to the sales volume of commodity
Recommend inventory, and be sent to terminal.In other embodiment, other commodity parameter information such as prices, evaluation etc. can also be used
Parameter is ranked up the commodity in commercial product recommending information, and then generates commercial product recommending inventory, and is sent to terminal, the side of transmission
Formula for wifi network either 3G/4G networks either other wirelessly terminal can be computer, mobile phone or notebook electricity
Brain or other removable or immovable terminals, in order to sales force according to the ranking results to old and new users into doing business
Product are recommended, and can improve the sales rate of commodity, while save the time.
The automatic commending system of user's commodity and recommendation method provided by the invention based on image recognition are based on existing use
Family information and its type of merchandise information of purchase establish user parameter information, user's type of merchandise information database, to new user
Information be acquired after stored and updated, the commodity of old and new users are calculated easy to the data in subsequent calls database
Preference degree is simultaneously ranked up, and ranking results are shown in terminal, checked easy to sales force and be old and new users recommend
Commodity.There is simple in structure, easy to operate, Intelligent Service and cost-effective.
For embodiment of the method, in order to be briefly described, therefore it is all expressed as to a series of combination of actions, but this area
Technical staff should know, the embodiment of the present invention and from the limitation of described sequence of movement, because implementing according to the present invention
Example, some steps can use other orders or be carried out at the same time.Secondly, those skilled in the art should also know, specification
Described in embodiment belong to preferred embodiment, necessary to the involved action not necessarily embodiment of the present invention.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
The present invention is described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that：It still may be used
To modify to the technical solution described in foregoing embodiments, or equivalent substitution is carried out to which part technical characteristic；
And these modification or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical solution spirit and
Scope.
Claims (10)
- A kind of 1. automatic commending system of user's commodity based on image recognition, it is characterised in that including：User images acquisition module, for gathering user images in real time, and is sent to subscriber identification module；Subscriber identification module, for user images to be converted to user parameter information, and user parameter information is sent to User type judgment module；User type judgment module, for the user parameter information that will deposit in user parameter information and customer parameter database into Row contrast, and judge that user parameter information for new user or old user, if new user, then is respectively sent to use by the user Family parameter database and commercial product recommending model computation module, if old user, then send user parameter information to commercial product recommending Model computation module；Commercial product recommending model computation module, for the type of merchandise transferred to user parameter information and from type of merchandise database Information is calculated, and the commercial product recommending information calculated is sent to commercial product recommending inventory generation module；Commercial product recommending inventory generation module, for commercial product recommending information to be generated commercial product recommending inventory, and is sent to terminal；Terminal, the commercial product recommending inventory of reception is shown；Customer parameter database, for real-time storage and renewal user parameter information；Type of merchandise database, for real-time storage and renewal type of merchandise information.
- 2. user's commodity automatic commending system according to claim 1 based on image recognition, it is characterised in that commodity push away Recommend model computation module and calculate commercial product recommending information using association analysis algorithm or collaborative filtering.
- 3. user's commodity automatic commending system according to claim 2 based on image recognition, it is characterised in that Yong Hutu As acquisition module using camera gathers user images in real time, and it is wirelessly sent to subscriber identification module.
- 4. user's commodity automatic commending system according to claim 3 based on image recognition, it is characterised in that commodity push away Recommend inventory generation module and commercial product recommending information is generated by commercial product recommending inventory according to the sales volume of commodity, and be sent to terminal.
- 5. the newly automatic commending system of user's commodity based on image recognition according to claim 4, it is characterised in that user Image capture module is connected with subscriber identification module radio, user type judgment module respectively with subscriber identification module, user Parameter database, commercial product recommending model computation module be electrically connected, commercial product recommending model computation module respectively with type of merchandise data Storehouse, commercial product recommending inventory generation module are electrically connected, and commercial product recommending inventory generation module is electrically connected with terminal wireless.
- 6. a kind of user's commodity auto recommending method based on image recognition, it is characterised in that comprise the following steps：User images acquisition module gathers user images in real time, and is sent to subscriber identification module；User images are converted to user parameter information by subscriber identification module, and user parameter information is sent to user class Type judgment module；User type judgment module carries out the user parameter information deposited in user parameter information and customer parameter database pair Than, and the user is judged for new user or old user, if new user, then user parameter information is respectively sent to user's ginseng Number database and commercial product recommending model computation module, if old user, then send user parameter information to commercial product recommending model Computing module；The type of merchandise information that commercial product recommending model computation module is transferred to user parameter information and from type of merchandise database Calculated, and the commercial product recommending information calculated is sent to commercial product recommending inventory generation module；Commercial product recommending information is generated commercial product recommending inventory by commercial product recommending inventory generation module, and is sent to terminal；Terminal is shown the commercial product recommending inventory of reception；Customer parameter database real-time storage and renewal user parameter information；Type of merchandise database real-time storage and renewal type of merchandise information.
- 7. user's commodity auto recommending method according to claim 6 based on image recognition, it is characterised in that commodity push away Recommend model computation module and calculate commercial product recommending information using association analysis algorithm or collaborative filtering.
- 8. user's commodity auto recommending method according to claim 7 based on image recognition, it is characterised in that Yong Hutu As acquisition module using camera gathers user images in real time, and it is wirelessly sent to subscriber identification module.
- 9. user's commodity auto recommending method according to claim 8 based on image recognition, it is characterised in that commodity push away Recommend inventory generation module and commercial product recommending information is generated by commercial product recommending inventory according to the sales volume of commodity, and be sent to terminal.
- 10. user's commodity auto recommending method according to claim 9 based on image recognition, it is characterised in that commodity Recommend inventory generation module that commercial product recommending inventory is wirelessly sent to terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711243171.7A CN108022152A (en) | 2017-11-30 | 2017-11-30 | The automatic commending system of user's commodity and recommendation method based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711243171.7A CN108022152A (en) | 2017-11-30 | 2017-11-30 | The automatic commending system of user's commodity and recommendation method based on image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108022152A true CN108022152A (en) | 2018-05-11 |
Family
ID=62077736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711243171.7A Pending CN108022152A (en) | 2017-11-30 | 2017-11-30 | The automatic commending system of user's commodity and recommendation method based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108022152A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876526A (en) * | 2018-06-06 | 2018-11-23 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device and computer readable storage medium |
| CN108985853A (en) * | 2018-07-27 | 2018-12-11 | 优信拍（北京）信息科技有限公司 | A kind of promotion method of transaction, apparatus and system |
| CN109034973A (en) * | 2018-07-25 | 2018-12-18 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device, system and computer readable storage medium |
| CN109034980A (en) * | 2018-08-23 | 2018-12-18 | 深圳码隆科技有限公司 | A kind of collocation Method of Commodity Recommendation, device and user terminal |
| CN109191261A (en) * | 2018-09-19 | 2019-01-11 | 北京京东金融科技控股有限公司 | A kind of Method of Commodity Recommendation and system |
| CN109636453A (en) * | 2018-12-05 | 2019-04-16 | 安徽师范大学 | A kind of airport Personalized service method improving CNNs |
| CN109816441A (en) * | 2018-12-29 | 2019-05-28 | 江苏云天励飞技术有限公司 | Tactful method for pushing, system and relevant apparatus |
| CN110443686A (en) * | 2019-08-07 | 2019-11-12 | 陈乐乐 | Commercial product recommending system and method based on rubbish identification |
| CN110570254A (en) * | 2019-09-12 | 2019-12-13 | 名创优品（横琴）企业管理有限公司 | Commodity structure control method and system based on face recognition data |
| CN110634040A (en) * | 2018-06-22 | 2019-12-31 | 北京京东尚科信息技术有限公司 | Information recommendation method and device |
| CN111027351A (en) * | 2018-10-10 | 2020-04-17 | 深圳云天励飞技术有限公司 | Offline commodity recommendation method and device and electronic equipment |
| CN111028029A (en) * | 2018-10-10 | 2020-04-17 | 深圳云天励飞技术有限公司 | Offline commodity recommendation method and device and electronic equipment |
| CN111311379A (en) * | 2020-04-01 | 2020-06-19 | 南京奥拓电子科技有限公司 | Information interaction method and device for intelligent goods shelf, intelligent goods shelf and storage medium |
| CN111639274A (en) * | 2020-06-01 | 2020-09-08 | 重庆锐云科技有限公司 | Online commodity intelligent sorting method and device, computer equipment and storage medium |
| CN112215653A (en) * | 2020-10-12 | 2021-01-12 | 珠海格力电器股份有限公司 | Commodity recommendation method, commodity recommendation device, server and storage medium |
| CN112287213A (en) * | 2020-10-21 | 2021-01-29 | 重庆电子工程职业学院 | Information analysis method based on big data |
| CN112686737A (en) * | 2021-01-14 | 2021-04-20 | 北京国联视讯信息技术股份有限公司 | Electronic commerce information recommendation method and system |
| CN113807911A (en) * | 2020-06-16 | 2021-12-17 | 丰田自动车株式会社 | Shopping assistance device, shopping assistance system, shopping assistance method, and storage medium storing shopping assistance program |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930457A (en) * | 2012-10-24 | 2013-02-13 | 深圳市万凯达科技有限公司 | Method and system for implementing application recommendation based on facial image characteristics |
| CN104732413A (en) * | 2013-12-20 | 2015-06-24 | 中国科学院声学研究所 | Intelligent individuation video advertisement pushing method and system |
| CN105243358A (en) * | 2015-09-15 | 2016-01-13 | 上海卓悠网络科技有限公司 | Face detection-based shopping recommendation system and method |
| CN105681901A (en) * | 2016-01-19 | 2016-06-15 | 天脉聚源(北京)传媒科技有限公司 | Program recommending method and device |
| CN107274242A (en) * | 2016-04-08 | 2017-10-20 | 上海旭薇物联网科技有限公司 | A kind of Method of Commodity Recommendation based on association analysis algorithm |
-
2017
- 2017-11-30 CN CN201711243171.7A patent/CN108022152A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930457A (en) * | 2012-10-24 | 2013-02-13 | 深圳市万凯达科技有限公司 | Method and system for implementing application recommendation based on facial image characteristics |
| CN104732413A (en) * | 2013-12-20 | 2015-06-24 | 中国科学院声学研究所 | Intelligent individuation video advertisement pushing method and system |
| CN105243358A (en) * | 2015-09-15 | 2016-01-13 | 上海卓悠网络科技有限公司 | Face detection-based shopping recommendation system and method |
| CN105681901A (en) * | 2016-01-19 | 2016-06-15 | 天脉聚源(北京)传媒科技有限公司 | Program recommending method and device |
| CN107274242A (en) * | 2016-04-08 | 2017-10-20 | 上海旭薇物联网科技有限公司 | A kind of Method of Commodity Recommendation based on association analysis algorithm |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876526A (en) * | 2018-06-06 | 2018-11-23 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device and computer readable storage medium |
| CN108876526B (en) * | 2018-06-06 | 2021-11-02 | 北京京东尚科信息技术有限公司 | Commodity recommendation method and device and computer-readable storage medium |
| EP3779841A4 (en) * | 2018-06-06 | 2022-01-12 | Beijing Jingdong Shangke Information Technology Co., Ltd. | Method, apparatus and system for sending information, and computer-readable storage medium |
| US11734725B2 (en) | 2018-06-06 | 2023-08-22 | Beijing Jingdong Shangke Information Technology Co, Ltd. | Information sending method, apparatus and system, and computer-readable storage medium |
| WO2019233258A1 (en) * | 2018-06-06 | 2019-12-12 | 北京京东尚科信息技术有限公司 | Method, apparatus and system for sending information, and computer-readable storage medium |
| CN110634040A (en) * | 2018-06-22 | 2019-12-31 | 北京京东尚科信息技术有限公司 | Information recommendation method and device |
| CN109034973B (en) * | 2018-07-25 | 2021-03-30 | 北京京东尚科信息技术有限公司 | Commodity recommendation method, commodity recommendation device, commodity recommendation system and computer-readable storage medium |
| WO2020020137A1 (en) * | 2018-07-25 | 2020-01-30 | 北京京东尚科信息技术有限公司 | Commodity recommendation method, apparatus and system, and computer readable storage medium |
| CN109034973A (en) * | 2018-07-25 | 2018-12-18 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device, system and computer readable storage medium |
| CN108985853A (en) * | 2018-07-27 | 2018-12-11 | 优信拍（北京）信息科技有限公司 | A kind of promotion method of transaction, apparatus and system |
| CN109034980A (en) * | 2018-08-23 | 2018-12-18 | 深圳码隆科技有限公司 | A kind of collocation Method of Commodity Recommendation, device and user terminal |
| CN109034980B (en) * | 2018-08-23 | 2021-12-28 | 深圳码隆科技有限公司 | Collocation commodity recommendation method and device and user terminal |
| CN109191261A (en) * | 2018-09-19 | 2019-01-11 | 北京京东金融科技控股有限公司 | A kind of Method of Commodity Recommendation and system |
| CN111027351B (en) * | 2018-10-10 | 2023-10-13 | 深圳云天励飞技术有限公司 | Off-line commodity recommendation method and device and electronic equipment |
| CN111028029B (en) * | 2018-10-10 | 2023-09-01 | 深圳云天励飞技术有限公司 | Off-line commodity recommendation method and device and electronic equipment |
| CN111028029A (en) * | 2018-10-10 | 2020-04-17 | 深圳云天励飞技术有限公司 | Offline commodity recommendation method and device and electronic equipment |
| CN111027351A (en) * | 2018-10-10 | 2020-04-17 | 深圳云天励飞技术有限公司 | Offline commodity recommendation method and device and electronic equipment |
| CN109636453A (en) * | 2018-12-05 | 2019-04-16 | 安徽师范大学 | A kind of airport Personalized service method improving CNNs |
| CN109816441B (en) * | 2018-12-29 | 2021-05-11 | 江苏云天励飞技术有限公司 | Policy pushing method, system and related device |
| CN109816441A (en) * | 2018-12-29 | 2019-05-28 | 江苏云天励飞技术有限公司 | Tactful method for pushing, system and relevant apparatus |
| CN110443686A (en) * | 2019-08-07 | 2019-11-12 | 陈乐乐 | Commercial product recommending system and method based on rubbish identification |
| CN110570254A (en) * | 2019-09-12 | 2019-12-13 | 名创优品（横琴）企业管理有限公司 | Commodity structure control method and system based on face recognition data |
| CN111311379A (en) * | 2020-04-01 | 2020-06-19 | 南京奥拓电子科技有限公司 | Information interaction method and device for intelligent goods shelf, intelligent goods shelf and storage medium |
| CN111639274B (en) * | 2020-06-01 | 2023-05-09 | 重庆锐云科技有限公司 | Online commodity intelligent sorting method, device, computer equipment and storage medium |
| CN111639274A (en) * | 2020-06-01 | 2020-09-08 | 重庆锐云科技有限公司 | Online commodity intelligent sorting method and device, computer equipment and storage medium |
| CN113807911A (en) * | 2020-06-16 | 2021-12-17 | 丰田自动车株式会社 | Shopping assistance device, shopping assistance system, shopping assistance method, and storage medium storing shopping assistance program |
| CN112215653A (en) * | 2020-10-12 | 2021-01-12 | 珠海格力电器股份有限公司 | Commodity recommendation method, commodity recommendation device, server and storage medium |
| CN112287213A (en) * | 2020-10-21 | 2021-01-29 | 重庆电子工程职业学院 | Information analysis method based on big data |
| CN112686737A (en) * | 2021-01-14 | 2021-04-20 | 北京国联视讯信息技术股份有限公司 | Electronic commerce information recommendation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108022152A (en) | The automatic commending system of user's commodity and recommendation method based on image recognition | |
| CN108876526B (en) | Commodity recommendation method and device and computer-readable storage medium | |
| Yan et al. | Data mining of customer choice behavior in internet of things within relationship network | |
| CN209690978U (en) | User data acquisition device | |
| KR101712591B1 (en) | Personalized Advertisement Service System Using Sensitiveness-Based User Characteristic Analysis | |
| CN106462825A (en) | Data mesh platform | |
| CN109447713A (en) | A kind of recommended method and device of knowledge based map | |
| KR102227552B1 (en) | System for providing context awareness algorithm based restaurant sorting personalized service using review category | |
| CN107862566A (en) | A kind of Method of Commodity Recommendation and system | |
| CN108961005A (en) | Information-pushing method, device, electronic equipment and medium | |
| CN109064265A (en) | Purchase vehicle recommended method and system based on the network platform | |
| CN108805598A (en) | Similarity information determines method, server and computer readable storage medium | |
| KR102052344B1 (en) | Method and apparatus for measuring influence in social network | |
| CN111949887A (en) | Item recommendation method and device and computer-readable storage medium | |
| KR101707660B1 (en) | An e-commerce system based on interest category using related keywords | |
| US11587028B2 (en) | Computer system for optimizing garment inventory of retailer based on shapes of users | |
| CN104981829A (en) | Method for generating and identifying preferred image id code, and method for providing information using same | |
| CN110599281A (en) | Method and device for determining target shop | |
| TWI629654B (en) | Wisdom door city welcome product recommendation system and method thereof | |
| KR102442988B1 (en) | A taste network generation system based on user experience using CNN learning | |
| CN110020918A (en) | A kind of recommendation information generation method and system | |
| KR102576123B1 (en) | Product marketing linkage system and method | |
| KR20210112258A (en) | Method and apparatus for providing personalized recommendation service for offline purchase | |
| CN114399352A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| KR102099631B1 (en) | Hybrid recommendation apparatus and method, storage media storing the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180511 |