CN106909629A - A kind of personalized recommendation cheats the method and system of position label - Google Patents
A kind of personalized recommendation cheats the method and system of position label Download PDFInfo
- Publication number
- CN106909629A CN106909629A CN201710057487.0A CN201710057487A CN106909629A CN 106909629 A CN106909629 A CN 106909629A CN 201710057487 A CN201710057487 A CN 201710057487A CN 106909629 A CN106909629 A CN 106909629A
- Authority
- CN
- China
- Prior art keywords
- user
- label
- commodity
- unit
- preference
- 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
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of method that personalized recommendation cheats position label, it is characterised in that comprise the following steps：Collect user and browse information and client's navigation patterns；Information and client's navigation patterns are browsed according to user, the weighted value of user preference label is calculated；Judge whether to reach the condition that hole position label is recommended in displaying before loading next screen Commodity Flow every time；Show hole position label if the condition of displaying hole position label is reached.A kind of method and system of personalized recommendation hole position label of the present invention are by collecting, calculating, judge that user browses information, personalized recommends user hole position label, can be during user checks Commodity Flow, the point of interest of real-time capture user, and during user turns over screen, select suitable position polymerization displaying user's current interest point, it is easy to what user can either be in good time during browsing to focus on oneself merchandise news interested, the enjoyment strolled in Commodity Flow will not be lost again, improve the consumption experience of user.
Description
Technical field
The present invention relates to a kind of method and system for recommending to cheat position label, more particularly to a kind of personalized recommendation hole position mark
The method and system of label.
Background technology
Current e-commerce platform App ends would generally show commodity collection in the form of Commodity Flow, this be also mobile phone in itself
What feature was determined, the major way of existing goods stream displaying includes (but being not limited to)：
(1) be polymerized all classification brands of whole station, and according to certain collocation mode, such as each classification continuously occupies three holes
Position, the strategy of similar classification brand mixing displaying is arranged in order, etc. between classification according to certain sortord；
(2) certain top classification, such as men's clothing women's dress house electrical equipment etc. are focused on, class commercial fine classifying type now is various,
So showing the commodity queue of single classification in a Commodity Flow, collocation mode is similar to (1)；
(3) guess that you like commodity queue, classification interested, brand or commodity according to user recommend similar business
Product queue.
Commodity Flow is turned over easily because its feature under user, and the commodity of screen displaying are limited, so, often can be mixed using classification
The mode of row shows commodity queue, so allows user to try one's best the different commodity of many discoveries inside little space.
But shortcoming is it is also obvious that user thinks lateral comparison but when oneself classification interested, brand, commodity are run into
Seem especially troublesome, user has to jump out current commodity stream, finds more similar in removal search or subdivision classification, operates
Extremely inconvenience.
The content of the invention
The invention aims to overcome the shortcomings of above-mentioned background technology, there is provided a kind of personalized recommendation hole position label
Method and system, can be during user checks Commodity Flow, the point of interest of real-time capture user, and turns over screen in user
During, suitable position polymerization displaying user's current interest point is selected, it is easy to user to be fitted during browsing
When focus on oneself merchandise news interested, the enjoyment strolled in Commodity Flow will not be lost again.
The method that a kind of personalized recommendation that the present invention is provided cheats position label, comprises the following steps：
S1：Collect user and browse information and client's navigation patterns；
S2：Information and client's navigation patterns are browsed according to user, the weighted value of user preference label is calculated；
S3：Judge whether to reach the condition that hole position label is recommended in displaying before loading next screen Commodity Flow every time；
S4：Show hole position label if the condition of displaying hole position label is reached, otherwise return to S1.
The system that a kind of personalized recommendation that the present invention is provided cheats position label, it includes：
User information collection unit, information and client's navigation patterns are browsed for collecting user；
The weighted value computing unit of user preference label, for browsing information and client's navigation patterns, meter according to user
Calculate the weighted value of user preference label；
Judge whether that reaching displaying recommends hole position tag unit, for judging whether before loading next screen Commodity Flow every time
Reach the condition that hole position label is recommended in displaying；
Displaying hole position tag unit, for user's displaying hole position label of the condition to reaching displaying hole position label.
Beneficial effect：A kind of method and system of personalized recommendation hole position label of the present invention are used by collecting, calculating, judge
Family browses information, and personalized recommends user hole position label, can in real time be caught during user checks Commodity Flow
The point of interest of user is caught, and during user turns over screen, selects suitable position polymerization displaying user's current interest point, be easy to
User can either be in good time during browsing focus on oneself merchandise news interested, will not lose in Commodity Flow again
The enjoyment strolled, improves the consumption experience of user.
Brief description of the drawings
A kind of flow chart of the method for personalized recommendation hole position label that Fig. 1 is provided for embodiments of the invention；
A kind of function structure chart of the system of personalized recommendation hole position label that Fig. 2 is provided for embodiments of the invention.
Fig. 3 is realized for a kind of the overall of method and system of personalized recommendation hole position label that embodiments of the invention are provided
Flow chart.
Specific embodiment
Below in conjunction with the accompanying drawings and embodiment the present invention will be described in detail, the description of this part is only exemplary and explains
Property, there should not be any restriction effect to protection scope of the present invention.
As shown in figure 1, embodiment of the present invention provides a kind of flow chart of the method for personalized recommendation hole position label, including
The following steps：
As shown in figure 1, in 110, systematic collection user browses information and client's navigation patterns, specifically, the visitor
Family browses the attribute of classification of the information including user preference, brand, commodity and commodity；The user browsing behavior includes receiving
Tibetan, extra bus；
As shown in figure 1, in 120, the system browses information and client's navigation patterns according to user's, calculates user inclined
The weighted value of good label, the computational methods of the weighted value of the user preference label are：By Score, (user's history browses row
For) * HW+Score (the current navigation patterns of user) * CW are calculated；
Wherein, HW is historical scores weight, and CW is present score weight, draws and currently browse the classification score that commodity bring
Change；The behavior of user other non-present commodity does phase according to Score (user's history navigation patterns) * AW (AW is forgetting factor)
The target of the decay answered, wherein forgetting factor is that the classification not browsed more than 10 times can decay to zero, namely from the inclined of user
Removed in good queue；Collection, extra bus computing mode are similar, and simply CW therein can be different, and the CW preset values for browsing are
0.1, it is 0.5 to collect, and extra bus is 0.6, and percentage contribution of the different behaviors to preference-score is represented respectively；When label is cheated in Commodity Flow
After the displaying of position, then the classification that will show according to the mode of Score (user's history navigation patterns) * 0.5, brand, attribute are obtained
Divide the decay for doing 50%.
As shown in figure 1, in 130, the system judges whether that reaching displaying recommends before loading next screen Commodity Flow every time
The condition of position label is cheated, the condition of the displaying recommendation hole position label includes：
(1) whether the weighted score of user preference label has more than 0.5 threshold values, when user has collection or extra bus,
Because of default-weight>=0.5, so can directly meet condition, but navigation patterns need continuously to accumulate more than 5 times and could expire
Foot, the rest may be inferred for other logics；
(2) whether the fatigue phase is belonged to, after label recommendations hole position shows, used as the fatigue phase, period is follow-up continuous two screen
Satisfaction (1) condition is set still not show；
(3) user preference classification, brand, commodity and item property quantity judges, the exhibition strategy according to label, it is necessary to
10 labels of displaying, and including at least preference classification or mixing brand, attribute tags, if the number of tags of active user's preference
Amount is less than 10, even if meet (1) (2) condition will not still show.
As shown in figure 1, in 130, the system shows hole position label if the condition of displaying hole position label is reached, otherwise
110 are returned to, the methods of exhibiting of described hole position label is：
(1) for preferably 5 Top commodity of each classification, then 3- is randomly selected from the Top commodity of each classification successively
4 commodity are fitted into commodity queue；
(2) the Top1 brands for extracting each class preference now are sequentially loaded into commodity queue；
(3) the Top1 attributes for extracting each class preference now are sequentially loaded into commodity queue.
As shown in Fig. 2 the system that a kind of personalized recommendation cheats position label, it includes user information collection unit 210, user
The weighted value computing unit 220 of preference label, judge whether to reach displaying and recommend hole position tag unit 230, displaying hole position label
Unit 240.
The user information collection unit 210, browses information and client's navigation patterns, specifically, such as collecting user
Shown in Fig. 3, the user information collection unit 210 includes the receipts of the attribute of classification, brand, commodity and the commodity of user preference
Collection unit 211 and user browsing behavior collector unit 212, the user browsing behavior collector unit 212 include that user collects row
It is unit 2121 and user's extra bus behavior unit 2122；
The weighted value computing unit 220 of described user preference label, for according to user browse information and client is clear
Look at behavior, the weighted value of user preference label is calculated specifically, as shown in figure 3, the weighted value meter of the user preference label
Calculating unit 220 includes historical scores weight calculation unit 221 and present score weighted score computing unit 222, and the history is obtained
Point weight calculation unit 221 browses information to user's history and carries out score weight calculation, and the present score weighted score is calculated
Unit 222 currently browses information to user and carries out score weight calculation.
Described judges whether that reaching displaying recommends hole position tag unit 230, in loading next screen Commodity Flow every time
Before judge whether to reach the condition that hole position label is recommended in displaying, specifically, as shown in figure 3, described judge whether that reaching displaying pushes away
Recommending hole position tag unit 230 includes weighted value judging unit 231, the and of human fatigue phase judging unit 232 of user preference label
User preference quantity judging unit 233, the information of browsing sequentially pass through the user preference label weighted value judging unit 231,
Human fatigue phase judging unit 232 and user preference quantity judging unit 233, three units are by then reaching hole position label
It is required that, the weighted value judging unit 231 of the user preference label is used to judge whether the weighted score of user preference label has
Threshold values more than 0.5, when user has collection or extra bus, because of default-weight>=0.5, so can directly meet condition, but
It is that navigation patterns need continuously to accumulate more than 5 times and could meet, the rest may be inferred for other logics；The human fatigue phase judging unit
232 are used to judge whether user belongs to the fatigue phase, and after label recommendations hole position shows, follow-up continuous two screen is used as fatigue phase, phase
Even if between meet user preference label the Rule of judgment of weighted value judging unit will not still show；The user preference quantity is sentenced
Disconnected unit 233 is used to judge user preference classification, brand, commodity and item property quantity, according to the exhibition strategy of label, needs
Show 10 labels, and including at least preference classification or mixing brand, attribute tags, if the label of active user's preference
Lazy weight 10, though meet user preference label weighted value judging unit and human fatigue phase judging unit condition still
Will not show.
Displaying hole position tag unit 240, for user's displaying hole position mark of the condition to reaching displaying hole position label
Sign, specifically, as shown in figure 3, displaying hole position tag unit 240 includes classification tag unit 241, brand label unit
242nd, attribute tags unit 243；The classification tag unit 241 is used to be directed to preferably 5 Top commodity of each classification, Ran Houyi
3-4 commodity are randomly selected in the secondary Top commodity from each classification to be fitted into commodity queue；The brand label unit 242 is used
In the Top1 brands for extracting each class preference now are sequentially loaded into commodity queue；The attribute tags unit 243 is used to extract
The Top1 attributes of each class preference now are sequentially loaded into commodity queue.
A kind of method and system of personalized recommendation hole position label of the present invention are by collecting, calculating, judge that user browses letter
Breath, personalized recommends user hole position label, can during user checks Commodity Flow, real-time capture user's
Point of interest, and during user turns over screen, suitable position polymerization displaying user's current interest point is selected, it is easy to user clear
Can either be in good time during looking at focus on oneself merchandise news interested, the pleasure strolled in Commodity Flow will not be lost again
Interest, improves the consumption experience of user.
Obviously, those skilled in the art can carry out various changes and modification without deviating from essence of the invention to the present invention
God and scope.So, if these modifications of the invention and modification belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising these changes and modification.
Claims (10)
1. a kind of method that personalized recommendation cheats position label, it is characterised in that comprise the following steps：
S1：Collect user and browse information and client's navigation patterns；
S2：Information and client's navigation patterns are browsed according to user, the weighted value of user preference label is calculated；
S3：Judge whether to reach the condition that hole position label is recommended in displaying before loading next screen Commodity Flow every time；
S4：Show hole position label if the condition of displaying hole position label is reached, otherwise return to S1.
2. the method that a kind of personalized recommendation as claimed in claim 1 cheats position label, it is characterised in that：The client browses letter
Breath includes the attribute of classification, brand, commodity and the commodity of user preference；The user browsing behavior includes collection, extra bus.
3. the method that a kind of personalized recommendation as claimed in claim 1 cheats position label, it is characterised in that：The user preference mark
The computational methods of the weighted value of label are：By Score (user's history navigation patterns) * HW+Score (the current navigation patterns of user) *
CW is calculated；
Wherein, HW is historical scores weight, and CW is present score weight, draws and currently browses the classification score change that commodity bring
Change；The behavior of user other non-present commodity is done accordingly according to Score (user's history navigation patterns) * AW (AW is forgetting factor)
Decay, the target of wherein forgetting factor is that the classification not browsed more than 10 times can decay to zero, namely from the preference of user
Removed in queue；Collection, extra bus computing mode are similar, and simply CW therein can be different, and the CW preset values for browsing are
0.1, it is 0.5 to collect, and extra bus is 0.6, and percentage contribution of the different behaviors to preference-score is represented respectively；When label is cheated in Commodity Flow
After the displaying of position, then the classification that will show according to the mode of Score (user's history navigation patterns) * 0.5, brand, attribute are obtained
Divide the decay for doing 50%.
4. the method that a kind of personalized recommendation as claimed in claim 1 cheats position label, it is characterised in that：Hole is recommended in the displaying
The condition of position label includes：
(1) whether the weighted score of user preference label has more than 0.5 threshold values, when user has collection or extra bus, Yin Mo
Recognize weight>=0.5, so can directly meet condition, but navigation patterns need continuously to accumulate more than 5 times and could meet, its
The rest may be inferred for his logic；
(2) whether the fatigue phase is belonged to, after label recommendations hole position shows, follow-up continuous two screen is used as the fatigue phase, even if period is full
Foot (1) condition will not still show；
(3) user preference classification, brand, commodity and item property quantity judge that the exhibition strategy according to label is, it is necessary to show
10 labels, and including at least preference classification or mixing brand, attribute tags, if the number of labels of active user's preference is not
10, foot, even if meet (1) (2) condition will not still show.
5. the method that a kind of personalized recommendation as claimed in claim 1 cheats position label, it is characterised in that：Described hole position label
Methods of exhibiting be：
(1) for preferably 5 Top commodity of each classification, 3-4 is then randomly selected from the Top commodity of each classification successively
Commodity are fitted into commodity queue；
(2) the Top1 brands for extracting each class preference now are sequentially loaded into commodity queue；
(3) the Top1 attributes for extracting each class preference now are sequentially loaded into commodity queue.
6. a kind of method that personalized recommendation cheats position label, it is characterised in that it includes：
User information collection unit, information and client's navigation patterns are browsed for collecting user；
The weighted value computing unit of user preference label, for browsing information and client's navigation patterns according to user, calculates
The weighted value of user preference label；
Judge whether that reaching displaying recommends hole position tag unit, for judging whether to reach before loading next screen Commodity Flow every time
The condition of hole position label is recommended in displaying；
Displaying hole position tag unit, for user's displaying hole position label of the condition to reaching displaying hole position label.
7. the system that a kind of personalized recommendation as claimed in claim 6 cheats position label, it is characterised in that：The user profile is received
Collection unit includes the collector unit of the attribute of classification, brand, commodity and the commodity of user preference；User browsing behavior is collected single
Unit, the user browsing behavior collector unit includes that user collects behavior unit and user's extra bus behavior unit.
8. the system that a kind of personalized recommendation as claimed in claim 6 cheats position label, it is characterised in that：The user preference mark
The weighted value computing unit of label includes historical scores weight calculation unit and present score weighted score computing unit, the history
Score weight calculation unit browses information to user's history and carries out score weight calculation, and the present score weighted score calculates single
Unit currently browses information to user carries out score weight calculation.
9. the system that a kind of personalized recommendation as claimed in claim 6 cheats position label, it is characterised in that：It is described to judge whether to reach
Recommend weighted value judging unit of the hole position tag unit including user preference label, human fatigue phase judging unit and use to displaying
Family preference quantity judging unit, the information of browsing sequentially passes through weighted value judging unit, the human fatigue of the user preference label
Phase judging unit and user preference quantity judging unit, three units are by then reaching the requirement of hole position label, the user
The weighted value judging unit of preference label is used to judge whether the weighted score of user preference label has more than 0.5 threshold values, when
When user has collection or extra bus, because of default-weight>=0.5, so can directly meet condition, but navigation patterns need to connect
Continuous accumulation could meet for more than 5 times, and the rest may be inferred for other logics；Whether the human fatigue phase judging unit is used for judging user
Belong to the fatigue phase, after label recommendations hole position shows, follow-up continuous two screen is used as the fatigue phase, even if period meets user preference mark
The Rule of judgment of the weighted value judging unit of label will not still show；The user preference quantity judging unit is used to judge that user is inclined
Good classification, brand, commodity and item property quantity, the exhibition strategy according to label is, it is necessary to show 10 labels, and at least wrap
Classification containing preference or mixing brand, attribute tags, if the number of labels of active user's preference is less than 10, even if meet using
The weighted value judging unit of family preference label and the condition of human fatigue phase judging unit will not still show.
10. the system that a kind of personalized recommendation as claimed in claim 6 cheats position label, it is characterised in that：Displaying hole position
Tag unit includes classification tag unit, brand label unit, attribute tags unit；The classification tag unit is used for for every
Preferably 5 Top commodity of individual classification, then randomly select 3-4 commodity and load commodity team from the Top commodity of each classification successively
In row；The Top1 brands that the brand label unit is used to extract each class preference now are sequentially loaded into commodity queue；It is described
The Top1 attributes that attribute tags unit is used to extract each class preference now are sequentially loaded into commodity queue.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710057487.0A CN106909629B (en) | 2017-01-26 | 2017-01-26 | Method and system for individually recommending pit bit labels |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710057487.0A CN106909629B (en) | 2017-01-26 | 2017-01-26 | Method and system for individually recommending pit bit labels |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106909629A true CN106909629A (en) | 2017-06-30 |
| CN106909629B CN106909629B (en) | 2020-05-19 |
Family
ID=59207535
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710057487.0A Active CN106909629B (en) | 2017-01-26 | 2017-01-26 | Method and system for individually recommending pit bit labels |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106909629B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416003A (en) * | 2018-02-27 | 2018-08-17 | 百度在线网络技术（北京）有限公司 | A kind of picture classification method and device, terminal, storage medium |
| CN108460631A (en) * | 2018-02-13 | 2018-08-28 | 口口相传(北京)网络技术有限公司 | The mixing method for pushing and device of diversification information |
| CN108804491A (en) * | 2018-03-27 | 2018-11-13 | 优视科技新加坡有限公司 | item recommendation method, device, computing device and storage medium |
| CN109389440A (en) * | 2017-08-02 | 2019-02-26 | 阿里巴巴集团控股有限公司 | The method, apparatus and electronic equipment of data object information are provided |
| CN109582857A (en) * | 2018-10-15 | 2019-04-05 | 深圳壹账通智能科技有限公司 | Based on big data information-pushing method, device, computer equipment and storage medium |
| CN110188297A (en) * | 2019-05-21 | 2019-08-30 | 掌阅科技股份有限公司 | Resource information methods of exhibiting calculates equipment and computer storage medium |
| CN111882400A (en) * | 2020-07-31 | 2020-11-03 | 平安国际融资租赁有限公司 | Behavior recognition analysis method and device, computer equipment and readable storage medium |
| CN112035735A (en) * | 2020-07-28 | 2020-12-04 | 康艾艺 | Short video-based commodity recommendation method, device and system |
| CN113129093A (en) * | 2021-03-15 | 2021-07-16 | 特斯联科技集团有限公司 | Recommendation method and device for recommending commodities based on user data of smart community |
| CN113298594A (en) * | 2020-07-16 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Data pushing method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279224A (en) * | 2015-09-09 | 2016-01-27 | 百度在线网络技术（北京）有限公司 | Information push method and device |
| CN105574216A (en) * | 2016-03-07 | 2016-05-11 | 达而观信息科技（上海）有限公司 | Personalized recommendation method and system based on probability model and user behavior analysis |
| CN105787055A (en) * | 2016-02-26 | 2016-07-20 | 合网络技术（北京）有限公司 | Information recommendation method and device |
| CN105989004A (en) * | 2015-01-27 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Information releasing pretreatment method and device |
-
2017
- 2017-01-26 CN CN201710057487.0A patent/CN106909629B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989004A (en) * | 2015-01-27 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Information releasing pretreatment method and device |
| CN105279224A (en) * | 2015-09-09 | 2016-01-27 | 百度在线网络技术（北京）有限公司 | Information push method and device |
| CN105787055A (en) * | 2016-02-26 | 2016-07-20 | 合网络技术（北京）有限公司 | Information recommendation method and device |
| CN105574216A (en) * | 2016-03-07 | 2016-05-11 | 达而观信息科技（上海）有限公司 | Personalized recommendation method and system based on probability model and user behavior analysis |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389440A (en) * | 2017-08-02 | 2019-02-26 | 阿里巴巴集团控股有限公司 | The method, apparatus and electronic equipment of data object information are provided |
| CN109389440B (en) * | 2017-08-02 | 2022-05-24 | 阿里巴巴集团控股有限公司 | Method and device for providing data object information and electronic equipment |
| CN108460631A (en) * | 2018-02-13 | 2018-08-28 | 口口相传(北京)网络技术有限公司 | The mixing method for pushing and device of diversification information |
| CN108416003A (en) * | 2018-02-27 | 2018-08-17 | 百度在线网络技术（北京）有限公司 | A kind of picture classification method and device, terminal, storage medium |
| CN108804491A (en) * | 2018-03-27 | 2018-11-13 | 优视科技新加坡有限公司 | item recommendation method, device, computing device and storage medium |
| CN109582857A (en) * | 2018-10-15 | 2019-04-05 | 深圳壹账通智能科技有限公司 | Based on big data information-pushing method, device, computer equipment and storage medium |
| CN110188297A (en) * | 2019-05-21 | 2019-08-30 | 掌阅科技股份有限公司 | Resource information methods of exhibiting calculates equipment and computer storage medium |
| CN110188297B (en) * | 2019-05-21 | 2021-08-13 | 掌阅科技股份有限公司 | Resource information display method, computing device and computer storage medium |
| CN113298594A (en) * | 2020-07-16 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Data pushing method and device, electronic equipment and storage medium |
| CN112035735A (en) * | 2020-07-28 | 2020-12-04 | 康艾艺 | Short video-based commodity recommendation method, device and system |
| CN111882400A (en) * | 2020-07-31 | 2020-11-03 | 平安国际融资租赁有限公司 | Behavior recognition analysis method and device, computer equipment and readable storage medium |
| CN113129093A (en) * | 2021-03-15 | 2021-07-16 | 特斯联科技集团有限公司 | Recommendation method and device for recommending commodities based on user data of smart community |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106909629B (en) | 2020-05-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106909629A (en) | A kind of personalized recommendation cheats the method and system of position label | |
| CN110569432B (en) | Commodity sequence calculating method, commodity sequence calculating device, computer equipment and storage medium | |
| CN206179117U (en) | Intelligence display system | |
| CN105283896B (en) | Marketing system and marketing method | |
| CN107590675B (en) | User shopping behavior identification method based on big data, storage device and mobile terminal | |
| CN111815419B (en) | Recommendation method and device for virtual commodity in game and electronic equipment | |
| JP4861965B2 (en) | Information distribution system | |
| US20080215427A1 (en) | Product information provider system and method | |
| US20150019346A1 (en) | Information provision device | |
| CN107798560A (en) | A kind of retail shop's individual character advertisement intelligent method for pushing and system | |
| JP5002441B2 (en) | Marketing data analysis method, marketing data analysis system, data analysis server device, and program | |
| CN110706014A (en) | Shopping mall store recommendation method, device and system | |
| CN107481052A (en) | A kind of transmitting advertisement information method and terminal | |
| JP2018049393A (en) | Health care device, health care system, and health care method | |
| CN109165847A (en) | A kind of item recommendation method based on recommender system, device and equipment | |
| CN108876430A (en) | A kind of advertisement sending method based on crowd characteristic, electronic equipment and storage medium | |
| CN111027351B (en) | Off-line commodity recommendation method and device and electronic equipment | |
| CA2796493C (en) | Identifying evaluation information device, method and computer readable medium | |
| CN110807691B (en) | Cross-commodity-class commodity recommendation method and device | |
| WO2015159409A1 (en) | Information delivery device and information delivery method | |
| JP2018156150A (en) | Information processing device, information processing method, terminal, information processing system and program | |
| US11521244B2 (en) | Information processing device, information processing method, and information processing program | |
| JP5318443B2 (en) | Health guidance support system and program | |
| JP2014050591A (en) | Information processing system, and control method | |
| Herstein et al. | Household income and the perceived importance of discount store image components |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |