Intelligent recommendation method and device based on Internet TV platform
An Internet TV and recommendation method technology, applied in the field of intelligent recommendation methods and devices, can solve problems such as inability to recommend videos, and achieve the effect of improving user experience
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0075] figure 1 It is a flow chart of the intelligent recommendation method based on the Internet TV platform provided by Embodiment 1 of the present invention.
[0076] refer to figure 1 , the method includes the following steps:
[0077] Step S101, acquiring external data and internal data, and extracting data from the external data and internal data to obtain a basic data set;
[0078] Here, the external data includes but is not limited to, specifically, comment content, ranking data, tag data and introduction data (catalog data) of websites such as Baidu and Douban. Internal data includes, but is not limited to, specific user basic information data, user behavior data, content catalog data and user selection data. After capturing the external data, search with the internal data to find the corresponding internal data, and organize the external data into the database in the form of a dictionary to form a basic data set.
[0079] Step S102, inputting the basic data set i...
Embodiment 2
[0140] figure 2 It is a schematic diagram of an intelligent recommendation method based on an Internet TV platform provided by Embodiment 2 of the present invention.
[0141] refer to figure 2 , the external data and internal data are extracted to obtain the basic data set; the basic data set is used as the input of each algorithm in the intelligent recommendation algorithm pool to obtain the program screening set output by each algorithm; multiple program screening sets Generate programs to be selected; obtain user historical behavior information; obtain the weight corresponding to each algorithm in the intelligent recommendation algorithm pool according to user historical behavior information; sort according to weight. According to different weights, select several algorithms from the intelligent recommendation algorithm pool in turn, and grab some videos from them for sorting. The sorting process can refer to the following application scenarios.
[0142] In the subscrib...
Embodiment 3
[0160] image 3 It is a schematic diagram of an intelligent recommendation device based on an Internet TV platform provided by Embodiment 3 of the present invention.
[0161] refer to image 3 , the device consists of:
[0162] A basic data set acquisition unit 10, configured to acquire external data and internal data, and extract data from the external data and internal data to obtain a basic data set;
[0163] Program screening set acquisition unit 20, for inputting the basic data set into each algorithm in the intelligent recommendation algorithm pool to obtain multiple program screening sets;
[0164] A generation unit 30, configured to generate a plurality of selected program sets into a program to be selected set;
[0165] A historical behavior information acquisition unit 40, configured to acquire user historical behavior information;
[0166] A weight acquisition unit 50, configured to obtain the corresponding weight of each algorithm in the intelligent recommendatio...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More