Content-recommendation method and apparatus, electronic device, and system

Patent metadata

Field	Value
Publication number	US-12159305-B2
Application number	US-201916959643-A
Country	US
Kind code	B2
Filing date	Jan 23, 2019
Priority date	Mar 7, 2018
Publication date	Dec 3, 2024
Grant date	Dec 3, 2024

Abstract

The disclosed embodiments relate to a content-recommendation method and apparatus, an electronic device, and a system. The method comprises: searching, by a recommendation system according to a determined tag, a content database for content matching the tag; and recommending, by the recommendation system, the matching content to a user corresponding to the tag. Content in the content database is determined according to first-type content acquired by an internal-operation system by means of matching and second-type content acquired by an external-operation system by means of matching.

First claim

What is claimed is:

1. A content-recommendation method, comprising:
deploying a distributed system, the distributed system including an internal-operation system residing on a first computing system and an external-operation system residing on a second different computing system, and a recommendation system communicatively coupled to both the internal-operation system and the external-operation system, the recommendation system including a content database;
determining, by the internal-operation system, a first type of content by matching corresponding tags, wherein a respective piece of content of the first type indicates user traffic associated with a corresponding piece of merchandise in the distributed system, and wherein a matching tag indicates recommendation for the piece of merchandise;
determining, by the external-operation system, a second type of content by matching the corresponding tags, wherein a respective piece of content of the second type indicates promotional information directed to a piece of merchandise;
performing, in parallel, actions including:
acquiring, by the internal-operation system of the distributed system, the first type of content by matching internal information uploaded by an operation platform, and sending the first type of content to the recommendation system;
acquiring, by the internal-operation system of the distributed system, traffic access amount to individual types of content by matching traffic-distribution policy uploaded by the operation platform, and sending the traffic access amount to the recommendation system;
acquiring, by the external-operation system of the distributed system, the second type of content by matching external information uploaded by a merchant, and sending the second type of content to the recommendation system;
acquiring, by the internal-operation system of the distributed system, a content-recommendation policy by matching internal information uploaded by the operation platform, and sending the content-recommendation policy to the recommendation system; and
processing, by the recommendation system, the first type of content and the second type of content according to the content recommendation policy by at least merging the first and second types of content a merged piece of content;

searching, by the recommendation system based on a tag, a content in the content database for a piece of merchandise information matching the tag according to the content-recommendation policy;
recommending, based on resource provisioning using at least the traffic access amount by the recommendation system, the matching piece of merchandise information to a user corresponding to the tag through electronic communication between the distribution system and a user device of the user; and
separately configuring one or more of the internal-operation system or the external-operation system based on a behavior of the user after the matching piece of merchandise information has been recommended to the user through the electronic communication.

2. The method of claim 1 , wherein the content-recommendation policy comprises a merging sub-policy; and
wherein the merging the first and second types of content comprises:
merging, by the recommendation system, the first type of content with the second type of content according to the merge sub-policy to generate the merged piece of content.

3. The method of claim 2 , wherein the content-recommendation policy comprises a sorting sub-policy; and
wherein the method further comprises: sorting, by the recommendation system according to the sorting sub-policy, the merged piece of content stored in the content database to generate a sorting order.

4. The method of claim 3 , wherein recommending the matching piece of merchandise information to the user further comprises:
sequentially recommending, by the recommendation system according to the sorting order, the matching piece of merchandise information to the user corresponding to the tag.

5. The method of claim 1 , wherein the content-recommendation policy comprises a sorting sub-policy; and
wherein the method further comprises:
sorting, by the recommendation system, the first type of content and the second type of content according to the sorting sub-policy.

6. The method of claim 1 , wherein acquiring the second type of content further comprises:
receiving, by the external-operation system, a first piece of external information uploaded by at least one merchant;
statistically integrating, by the external-operation system, the first piece of external information to obtain merchant-shared information; and
acquiring, by the external-operation system, the second type of content by matching the merchant-shared information.

7. The method of claim 1 , wherein acquiring the second type of content further comprises:
receiving, by the external-operation system, a second piece of external information uploaded by at least one merchant;
acquiring, by the external-operation system, a piece of sub-content by matching the second piece of external information; and
integrating, by the external-operation system, the piece of sub-content to obtain the second type of content.

8. The method of claim 1 , wherein after recommending, by the recommendation system, the matching piece of merchandise information to the user, the method further comprises:
monitoring, by the recommendation system, an access status of the user with respect to the recommended piece of merchandise; and
feeding, by the recommendation system, the access status back to the internal-operation system and the external-operation system.

9. A content-recommendation apparatus in a distributed system, the distributed system including an internal-operation system residing on a first computing system and an external-operation system residing on a second different computing system, wherein the content-recommendation apparatus communicatively coupled to both the internal-operation system and the external-operation system, the content-recommendation apparatus comprising:
recommendation circuitry;
matching circuitry configured to:
determine a first type of content by matching corresponding tags, wherein a respective piece of content of the first type indicates user traffic associated with a corresponding piece of merchandise in the distributed system, and wherein a matching tag indicates recommendation for the piece of merchandise; and
determine a second type of content by matching the corresponding tags, wherein a respective piece of content of the second type indicates promotional information directed to a piece of merchandise;
perform, in parallel, actions including:
acquiring, from the internal-operation system of the distributed system, the first type of content by matching internal information uploaded by an operation platform, and sending the first type of content to the recommendation circuitry;
acquiring, from the internal-operation system of the distributed system, traffic access amount to individual types of content by matching traffic-distribution policy uploaded by the operation platform, and sending the traffic access amount to the recommendation circuitry:
acquiring, from the external-operation system of the distributed system, the second type of content by matching external information uploaded by a merchant, and sending the second type of content to the recommendation circuitry; and
acquiring, by the internal-operation system of the distributed system, a content-recommendation policy by matching internal information uploaded by the operation platform, and sending the content-recommendation policy to the recommendation circuitry; and
processing, by the recommendation system, the first type of content and the secon

Assignees

• Advanced New Technologies Co Ltd

Inventors

• Zhou Zhichao
• Xiong Jun
• Zhou Feng
• Jiang Jian
• Huang Guojin
• Zheng Yan
• Feng Jian

Classifications

• G06F16/22

  Indexing; Data structures therefor; Storage structures · CPC title

• G06F16/38

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06F17/00

  Digital computing or data processing equipment or methods, specially adapted for specific functions (information retrieval, database structures or file system structures therefor G06F16/00) · CPC title

• G06Q30/0631 Primary

  Recommending goods or services · CPC title

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title