Shovel Speech-to-Text Failure Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing shovel management systems face challenges in accurately expressing and handling failures, discomfort, or issues by operators, as the degree of these issues is not accurately conveyed in speech data, making it difficult to provide appropriate methods for resolution.
Innovation Solution
A shovel management system that includes a management apparatus capable of converting speech data into text, extracting relevant failure information from a database, and displaying handling methods on a display device, allowing for effective communication and resolution of operational issues.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If operators transmit failure information as speech data, then the system can capture operator input, but the degree of failure and discomfort is not accurately conveyed
Solution Approach 1:
The patent introduces speech recognition technology as an intermediary between the operator's speech input and the failure information database. The speech recognition unit converts speech data into text data, which then serves as a query to extract relevant failure information. This intermediary process bridges the gap between easy speech input and accurate failure description by automatically translating spoken words into structured information that can be matched with the database.
2Reliability
If the system stores comprehensive failure information in a database, then accurate failure handling can be provided, but the system complexity increases
Solution Approach 1:
The patent implements a self-service system where the shovel's own controller manages failure information locally. The controller stores failure information in an onboard storage unit and automatically queries and extracts relevant information when failures occur, without requiring external server connections. This self-service approach provides reliable failure handling while reducing system complexity by eliminating the need for complex network infrastructure and external database management.
Solution Approach 2:
The system performs preliminary action by pre-storing failure information and handling methods in the shovel's local database before failures occur. When a failure happens, the system immediately queries the pre-stored information based on speech input and displays relevant handling methods. This preliminary preparation ensures rapid response to failures without requiring real-time external database access, thereby reducing system complexity while maintaining reliability.
3Measurement precision
If speech data is converted to text and matched with failure information, then accurate failure handling is achieved, but the time to process and display information increases
Solution Approach 1:
The patent applies partial action by extracting only the most relevant failure information that matches the speech input, rather than processing or displaying all available database entries. The extraction unit identifies and retrieves specific failure records that correspond to the detected issue, filtering out unnecessary information. This selective extraction reduces processing time while maintaining accurate failure matching by focusing only on relevant data.
Data Source
AI summary
A shovel management includes a shovel, and a management apparatus configured to manage the shovel. The management apparatus includes a memory configured to store one or more pieces of failure information about a failure, and a hardware processor coupled to the memory and configured to convert speech data acquired from the shovel into text data, extract, from the memory, failure information whose content is similar to the text data, and cause a display device of the shovel to display information indicating a method of handling the failure included in the extracted failure information.