CN113641893A - Preference recommendation method based on user portrait deep analysis technology - Google Patents
Preference recommendation method based on user portrait deep analysis technology Download PDFInfo
- Publication number
- CN113641893A CN113641893A CN202110799023.3A CN202110799023A CN113641893A CN 113641893 A CN113641893 A CN 113641893A CN 202110799023 A CN202110799023 A CN 202110799023A CN 113641893 A CN113641893 A CN 113641893A
- Authority
- CN
- China
- Prior art keywords
- user
- browsed
- information
- image information
- product
- 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
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000005516 engineering process Methods 0.000 title claims abstract description 12
- 230000002596 correlated effect Effects 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
Images
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 a preference recommendation method based on a user portrait deep analysis technology, which comprises the following steps: acquiring user information and image information browsed by a user through big data acquisition; classifying the user information according to the times and the similarity of the image information browsed by the user; pushing the associated product information to the classified user information for the user to select; the user performs intention selection on the pushed associated product information and moves the selected product to the alternative area; the invention can accurately find the product preferred by the user in time through the image information browsed by the user.
Description
Technical Field
The invention relates to the technical field of portrait analysis, in particular to a favorite recommendation method based on a user portrait deep analysis technology.
Background
With the rapid development of the internet and the mobile communication technology, the live internet video broadcast can release contents such as electronic commerce commodities on the internet on site, and the interactive effect of the electronic commerce commodities is enhanced by utilizing the characteristics of intuition, rapidness, good expression form, rich contents, strong interactivity, unlimited regions, divisible audiences and the like of the internet.
At present, when related products are purchased on the internet, the background database generally does not classify the products according to the image information of the products browsed by the user, so that the related products cannot be pushed to the user timely and accurately, and inconvenience is brought to the user.
Disclosure of Invention
The invention aims to provide a preference recommendation method based on a user portrait deep analysis technology so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a preference recommendation method based on a user portrait deep analysis technology comprises the following steps:
acquiring user information and image information browsed by a user through big data acquisition;
classifying the user information according to the times and the similarity of the image information browsed by the user;
pushing the associated product information to the classified user information for the user to select;
the user performs intention selection on the pushed associated product information and moves the selected product to the alternative area; the product to be selected is finally determined in the alternative area.
As a further scheme of the invention: the classification of the user information according to the times and the similarity of the image information browsed by the user specifically comprises the following steps:
if the times and the time of the image information browsed by the user do not meet the preset requirements and the image information browsed by the user does not have a mutual relation, judging that the user is an unintentional user;
if the times and the time of the image information browsed by the user reach preset requirements and the image information browsed by the user can find a mutual relation, judging that the user is a potential user;
and if the times and the time of the image information browsed by the user reach preset requirements and the image information browsed by the user is similar products, judging that the user is a target user.
As a further scheme of the invention: if the user judges that the target user exists, the browsed product information is tracked, the associated information among the browsed product information is searched, and specific products with the associated information are pushed to the target user through the database;
and if the selection time of the target user exceeds the expected time, automatically inquiring the satisfaction point and the dissatisfaction point among the products browsed by the target user, and pushing the specific products from the target user in the database.
As a further scheme of the invention: pushing the associated product information to the classified user information for the user to select specifically:
if the user is judged to be the user without intention, pushing related products of the previously browsed product information from the database to the database;
and if the user is judged to be a potential user, finding out common points of the correlated products from the browsed image information, and pushing the products with the characteristics from the database.
As a further scheme of the invention: the final determination of the product to be selected in the alternative area is specifically:
the common product information features are abstracted from the viewed product information and compared to the products in the candidate area and displayed in a ranking for selection by the customer.
Compared with the prior art, the invention has the beneficial effects that: the invention classifies the users according to the product information browsed by the users, and pushes related products to the users aiming at the user information of different classifications, thereby enabling the users to find the corresponding products in time, and the invention can find the products favored by the users in time and accurately through the image information browsed by the users.
Description of the invention
FIG. 1 is a schematic diagram of a preference recommendation method based on a deep parsing technique of a user profile.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, in an embodiment of the present invention, a preference recommendation method based on a deep parsing technique of a user portrait includes the following steps:
acquiring user information and image information browsed by a user through big data acquisition;
classifying the user information according to the times and the similarity of the image information browsed by the user;
pushing the associated product information to the classified user information for the user to select;
the user performs intention selection on the pushed associated product information and moves the selected product to the alternative area; the product to be selected is finally determined in the alternative area.
The classification of the user information according to the times and the similarity of the image information browsed by the user specifically comprises the following steps:
if the times and the time of the image information browsed by the user do not meet the preset requirements and the image information browsed by the user does not have a mutual relation, judging that the user is an unintentional user;
if the times and the time of the image information browsed by the user reach preset requirements and the image information browsed by the user can find a mutual relation, judging that the user is a potential user;
and if the times and the time of the image information browsed by the user reach preset requirements and the image information browsed by the user is similar products, judging that the user is a target user.
If the user judges that the target user exists, the browsed product information is tracked, the associated information among the browsed product information is searched, and specific products with the associated information are pushed to the target user through the database;
and if the selection time of the target user exceeds the expected time, automatically inquiring the satisfaction point and the dissatisfaction point among the products browsed by the target user, and pushing the specific products from the target user in the database.
Pushing the associated product information to the classified user information for the user to select specifically:
if the user is judged to be the user without intention, pushing related products of the previously browsed product information from the database to the database;
and if the user is judged to be a potential user, finding out common points of the correlated products from the browsed image information, and pushing the products with the characteristics from the database.
The final determination of the product to be selected in the alternative area is specifically:
the common product information features are abstracted from the viewed product information and compared to the products in the candidate area and displayed in a ranking for selection by the customer.
When the system is used, user information and image information browsed by a user are acquired through big data acquisition;
classifying the user information according to the times and the similarity of the image information browsed by the user;
the classification of the user information according to the times and the similarity of the image information browsed by the user specifically comprises the following steps:
if the times and the time of the image information browsed by the user do not meet the preset requirements and the image information browsed by the user does not have a mutual relation, judging that the user is an unintentional user;
if the times and the time of the image information browsed by the user reach preset requirements and the image information browsed by the user can find a mutual relation, judging that the user is a potential user;
and if the times and the time of the image information browsed by the user reach preset requirements and the image information browsed by the user is similar products, judging that the user is a target user.
If the user judges that the target user exists, the browsed product information is tracked, the associated information among the browsed product information is searched, and specific products with the associated information are pushed to the target user through the database;
and if the selection time of the target user exceeds the expected time, automatically inquiring the satisfaction point and the dissatisfaction point among the products browsed by the target user, and pushing the specific products from the target user in the database.
Pushing the associated product information to the classified user information for the user to select;
pushing the associated product information to the classified user information for the user to select specifically:
if the user is judged to be the user without intention, pushing related products of the previously browsed product information from the database to the database;
and if the user is judged to be a potential user, finding out common points of the correlated products from the browsed image information, and pushing the products with the characteristics from the database.
The user performs intention selection on the pushed associated product information and moves the selected product to the alternative area;
the product to be selected is finally determined in the alternative area.
The final determination of the product to be selected in the alternative area is specifically:
the common product information features are abstracted from the viewed product information and compared to the products in the candidate area and displayed in a ranking for selection by the customer.
Although the present description is described in terms of embodiments, not every embodiment includes only a single embodiment, and such description is for clarity only, and those skilled in the art should be able to integrate the description as a whole, and the embodiments can be appropriately combined to form other embodiments as will be understood by those skilled in the art.
Therefore, the above description is only a preferred embodiment of the present application, and is not intended to limit the scope of the present application; all changes which come within the meaning and range of equivalency of the claims are to be embraced within their scope.
Claims (5)
1. The preference recommendation method based on the user portrait deep analysis technology is characterized by comprising the following steps of:
acquiring user information and image information browsed by a user through big data acquisition;
classifying the user information according to the times and the similarity of the image information browsed by the user;
pushing the associated product information to the classified user information for the user to select;
the user performs intention selection on the pushed associated product information and moves the selected product to the alternative area;
the product to be selected is finally determined in the alternative area.
2. The preference recommendation method based on the user portrait deep analysis technology as claimed in claim 1, wherein the classifying the user information according to the number of times and the similarity of the image information browsed by the user is specifically:
if the times and the time of the image information browsed by the user do not meet the preset requirements and the image information browsed by the user does not have a mutual relation, judging that the user is an unintentional user;
if the times and the time of the image information browsed by the user reach preset requirements and the image information browsed by the user can find a mutual relation, judging that the user is a potential user;
and if the times and the time of the image information browsed by the user reach preset requirements and the image information browsed by the user is similar products, judging that the user is a target user.
3. The preference recommendation method based on the user portrait deep analysis technology as claimed in claim 2, wherein if the user determines that the target user is a user, the browsed product information is tracked, the associated information between the browsed product information is searched, and the specific product with the associated information is pushed to the target user through the database;
and if the selection time of the target user exceeds the expected time, automatically inquiring the satisfaction point and the dissatisfaction point among the products browsed by the target user, and pushing the specific products from the target user in the database.
4. The method of claim 2, wherein pushing the associated product information to the classified user information for user selection specifically comprises:
if the user is judged to be the user without intention, pushing related products of the previously browsed product information from the database to the database;
and if the user is judged to be a potential user, finding out common points of the correlated products from the browsed image information, and pushing the products with the characteristics from the database.
5. The preference recommendation method based on the user portrait deep parsing technology as claimed in claim 1, wherein the final determination of the product to be selected in the candidate area is:
the common product information features are abstracted from the viewed product information and compared to the products in the candidate area and displayed in a ranking for selection by the customer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110799023.3A CN113641893A (en) | 2021-07-15 | 2021-07-15 | Preference recommendation method based on user portrait deep analysis technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110799023.3A CN113641893A (en) | 2021-07-15 | 2021-07-15 | Preference recommendation method based on user portrait deep analysis technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113641893A true CN113641893A (en) | 2021-11-12 |
Family
ID=78417351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110799023.3A Pending CN113641893A (en) | 2021-07-15 | 2021-07-15 | Preference recommendation method based on user portrait deep analysis technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113641893A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617540A (en) * | 2013-10-17 | 2014-03-05 | 浙江大学 | E-commerce recommendation method of tracking user interest changes |
| CN103841122A (en) * | 2012-11-20 | 2014-06-04 | 阿里巴巴集团控股有限公司 | Target-object information recommending method, server and client |
| CN105894332A (en) * | 2016-04-22 | 2016-08-24 | 深圳市永兴元科技有限公司 | Commodity recommendation method, device and system based on user behavior analysis |
| CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Merchandise news method for pushing, device, storage medium and server |
| CN109598588A (en) * | 2018-12-04 | 2019-04-09 | 广州拓飞商贸有限公司 | A kind of online merchandise display method based on big data analysis |
| CN110046968A (en) * | 2019-04-23 | 2019-07-23 | 佛山远钧智慧科技有限公司 | A kind of intelligent recommendation system for purchase based on trade in commodities |
| CN112465591A (en) * | 2020-05-10 | 2021-03-09 | 石伟 | User portrait analysis method, system and platform based on electronic commerce big data |
-
2021
- 2021-07-15 CN CN202110799023.3A patent/CN113641893A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103841122A (en) * | 2012-11-20 | 2014-06-04 | 阿里巴巴集团控股有限公司 | Target-object information recommending method, server and client |
| CN103617540A (en) * | 2013-10-17 | 2014-03-05 | 浙江大学 | E-commerce recommendation method of tracking user interest changes |
| CN105894332A (en) * | 2016-04-22 | 2016-08-24 | 深圳市永兴元科技有限公司 | Commodity recommendation method, device and system based on user behavior analysis |
| CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Merchandise news method for pushing, device, storage medium and server |
| CN109598588A (en) * | 2018-12-04 | 2019-04-09 | 广州拓飞商贸有限公司 | A kind of online merchandise display method based on big data analysis |
| CN110046968A (en) * | 2019-04-23 | 2019-07-23 | 佛山远钧智慧科技有限公司 | A kind of intelligent recommendation system for purchase based on trade in commodities |
| CN112465591A (en) * | 2020-05-10 | 2021-03-09 | 石伟 | User portrait analysis method, system and platform based on electronic commerce big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9075875B1 (en) | System and method for recommending television programs based on user search queries | |
| CN1316826C (en) | Method and apparatus for generating recommendations based on user preferences and environmental characteristics | |
| CN106878405B (en) | Method and device for adjusting push items | |
| CN109033149B (en) | Information recommendation method and device, server and storage medium | |
| US9043828B1 (en) | Placing sponsored-content based on images in video content | |
| CN104462573A (en) | Method and device for displaying video retrieval results | |
| CN105653572A (en) | Resource processing method and apparatus | |
| CN105792010A (en) | Television shopping method and device based on image content analysis and picture index | |
| US8346604B2 (en) | Facilitating bidding on images | |
| US20170213248A1 (en) | Placing sponsored-content associated with an image | |
| CN104602128A (en) | Video processing method and device | |
| CN101668176A (en) | Multimedia content-on-demand and sharing method based on social interaction graph | |
| KR101404596B1 (en) | System and method for providing video service based on image data | |
| CN104462336A (en) | Information pushing method and device | |
| CN105721944A (en) | News information recommendation method for smart television | |
| CN106126544B (en) | Internet content delivery method and device | |
| CN106682049B (en) | Topic display system and topic display method | |
| CN105827690A (en) | Information push method according to user preferences and information push server thereof | |
| CN105916032A (en) | Video recommendation method and video recommendation terminal equipment | |
| CN110598098A (en) | Information recommendation method and device and information recommendation device | |
| CN111310046A (en) | Object recommendation method and device | |
| CN115187301A (en) | Advertisement instant implanting method, system and device based on user portrait | |
| CN104581224A (en) | Play content switching method and device and terminal | |
| JP6369979B2 (en) | Data processing apparatus, data processing system, data display apparatus, data processing method, display method, and program | |
| CN109919805A (en) | Information-pushing method, user equipment, storage medium and device |
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 |