Voice Command Parsing for TV Schedule Recording

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing voice recognition systems for scheduling TV program recordings struggle to accurately interpret user intentions from spoken commands, leading to difficulties in setting schedule recordings for specific programs.

Innovation Solution

An information processing system that uses voice recognition to generate character strings and performs syntax analysis to decompose spoken commands, allowing for precise search and recording of TV programs based on user intentions, such as genre, date, and program name.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If voice recognition is used to search for programs, then the ease of operation is improved, but the accuracy of interpreting user intention deteriorates

Engineering Contradiction:
Improveease of operationVSAvoidaccuracy of interpreting user intention
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent segments the user's voice input into multiple components: voice recognition results, syntax analysis results, and intention detection results. By dividing the processing into these distinct stages, the system can accurately extract the user's intent (e.g., recording action, program genre, time specifications) from the voice input, thereby improving interpretation accuracy while maintaining ease of operation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary intention detection unit that acts as a mediator between the syntax analysis unit and the program search unit. This intermediary component analyzes the semantic meaning of the voice input to determine the user's specific intention (such as whether to record, the preferred genre, or time constraints), thereby bridging the gap between raw voice recognition and accurate program selection.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If the system provides detailed program search options, then the measurement precision is improved, but the device complexity increases

Engineering Contradiction:
Improveaccuracy of program searchVSAvoiddevice complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary action by detecting the user's intention before executing the program search. The intention detection unit pre-analyzes the voice input to extract key parameters (recording intent, genre preferences, time specifications) and prepares search conditions in advance. This preliminary processing enables the system to conduct precise program searches without requiring complex real-time processing during the search execution phase.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements dynamics by making the program search process adaptive based on detected user intention. The search parameters and criteria dynamically adjust according to the user's expressed preferences (e.g., if the user mentions a specific genre or time constraint, the search automatically incorporates these factors). This dynamic adaptation allows the system to provide detailed and accurate search results without requiring a fixed complex structure for all possible search scenarios.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3518530B1Information processing apparatus, information processing method, program for scheduling the recording of a broadcast program
Publication Date: 2021.12.15 SONY GROUP CORP
  • EP3518530B1 patent drawingFigure 1
  • EP3518530B1 patent drawingFigure 2
  • EP3518530B1 patent drawingFigure 3

AI summary

The present technology relates to an information processing apparatus, an information processing method, a program, and an information processing system that enable a user to easily set the schedule recording of programs listed as search results. An information processing apparatus according to an aspect of the present technology performs a search for a recorded program and a program to be provided later to acquire a first search result in a case where a character string indicating content of an utterance of a user does not include a predetermined character string indicating the setting of the schedule recording of the program to be provided later and performs a search for the program to be provided later to acquire a second search result in a case where the character string includes the predetermined character string. In a case where a program whose schedule recording is to be set is selected from a display screen of the second search result, the information processing apparatus sets the schedule recording of the selected program without displaying a detail screen. The present technology can be applied to an apparatus that can receive a broadcast program, such as a television set.