Program Recommendation System Using Group Reservation Rate Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing program recommendation systems fail to provide personalized recommendations for users, especially when popular programs are broadcast infrequently or when users have diverse preferences, leading to generic recommendations that are not tailored to individual tastes.

Innovation Solution

A program recommendation system that groups users based on specific program reservations and calculates customized reservation rate rankings by subtracting the reservation rates of a broader user group from a specific user group, allowing for the extraction of programs particularly preferred by the users within that group.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If collaborative filtering is used to group users by preference patterns, then program recommendations can be automated, but recommended programs become generic and fail to reflect individual user preferences

Engineering Contradiction:

Improveprogram recommendation automationVSAvoidpersonalization capability

Core Design Contradiction:

Extent of automationVSAdaptability or versatility

Solution Approach 1:

The patent segments users into multiple hierarchical groups (first group based on specific program reservations, second group as all users) and performs separate statistical analyses on each group. This segmentation allows the system to capture both individual preferences within the first group and general trends from the second group, then combine them to provide personalized recommendations that maintain automation.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies different statistical processing to different user groups: calculating reservation rates specifically for the first group (users who reserved a specific program) and separately for the second group (all users). This local quality approach ensures that recommendations are tailored to local group characteristics while maintaining overall system automation.

Inventive Principle:

Principle #3Local quality

2Ease of operation

If general preference programs are recommended to all users, then the system is simple to operate, but it cannot satisfy diverse individual preferences

Engineering Contradiction:

Improvesystem simplicityVSAvoidpreference customization

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent dynamically adjusts recommendation strategies based on user group characteristics. For the first group, it calculates customized reservation rate rankings that reflect individual preferences. For the second group, it calculates general reservation rates. The system dynamically combines these results, maintaining simplicity while adapting to diverse preferences through conditional logic that responds to group-specific statistics.

Inventive Principle:

Principle #15Dynamics

3Extent of automation

If user grouping is performed for popular programs viewed by most users, then recommendations can be generated automatically, but the recommendations become useless as they don't reflect individual preferences

Engineering Contradiction:

Improverecommendation generation automationVSAvoidindividual preference information

Core Design Contradiction:

Extent of automationVSLoss of information

Solution Approach 1:

The patent extracts and separates the analysis of individual preference information from general popularity data. By calculating reservation rates specifically for the first group (users who reserved a specific program) and separately for the second group (all users), the system extracts individual preference information that would otherwise be lost in aggregate statistics. This extraction preserves individual preferences while maintaining automated recommendation generation.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentEP2051509B1Program recommendation system, program view terminal, program view program, program view method, program recommendation server, program recommendation program, and program recommendation method

Publication Date: 2016.07.27 PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO LTD

Figure 1
Figure 2
Figure 3

AI summary

An object of the invention is to eliminate a program having a high general preference, and recommend a program customized to a preference of a specific user. A reserved information receiver (230) in a program recommendation server (3) receives reserved information transmitted by a program viewing terminal. A reserved information DB (235) stores the reserved information with respect to each of the users. A community reserved information statistics section (236) defines the users as a first group, based on the received reserved information, and the reserved information stored with respect to each of the users. A total user reserved information statistics section (237) defines the users as a second group including the first group. A recommended program creator (239) generates recommended information customized to the first group, based on an aggregate calculation result of the reserved information of the users belonging to the first group, and an aggregate calculation result of the reserved information of the users belonging to the second group. A recommendation transmitter (240) transmits the recommended information to the program viewing terminal. The program viewing terminal reproduces a program based on the recommended information.