Vehicle Voice Shortcut Generation for Conditional Action Automation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle systems require users to manually execute multiple operations such as typing or clicking to set automatic instructions, leading to cumbersome settings and poor user experience, especially when dealing with complex conditions and actions.
Innovation Solution
A method that utilizes a server to recognize action and condition results from a user's speech request, generating a target shortcut instruction based on these results, allowing vehicles to execute actions when specific condition groups are satisfied, using a script and Java layer for efficient execution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If users manually type or click multiple times to set automatic instructions, then the vehicle can execute specific actions under specific conditions, but the setting process becomes cumbersome and user experience deteriorates
Solution Approach 1:
The patent replaces the mechanical interaction (typing and clicking operations) with an acoustic field interaction (voice commands). Users speak natural language instructions instead of manually navigating menus, converting the mechanical input method into a voice-based interface that reduces operational complexity while maintaining automation capability
Solution Approach 2:
The patent introduces a voice recognition server as an intermediary between the user and the vehicle's control system. The server processes natural language voice commands, interprets user intent, and translates them into executable automatic instructions, serving as a mediator that simplifies the interaction while enabling complex automated functions
2Speed
If the vehicle locally recognizes action and condition in speech requests, then response speed may be faster, but the vehicle's computational load increases and recognition efficiency may be compromised
Solution Approach 1:
The patent extracts the complex speech recognition and natural language processing functions from the vehicle's onboard system and relocates them to an external voice recognition server. This extraction removes the computational burden from the vehicle while maintaining fast and accurate recognition capabilities through cloud-based processing
Solution Approach 2:
The patent employs a universal voice recognition server that can handle multiple types of commands, conditions, and actions through a single centralized system. This multi-functional server serves various recognition tasks (action identification, condition parsing, parameter extraction) without requiring separate local processing units in each vehicle
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
The present disclosure discloses a shortcut instruction generation method and apparatus, a vehicle, and a computer-readable storage medium. The method includes: obtaining a first speech request for setting a target shortcut instruction, sending the first speech request to a server, and determining, according to an action recognition result and a condition recognition result sent by the server, a target action queue and a target condition group corresponding to the target action queue, to generate the target shortcut instruction. In this way, the vehicle of the present disclosure can complete the generation of the target shortcut instruction according to the first speech request of the user and the action recognition result and the condition recognition result determined by the server, thereby avoiding that the user needs to manually type the shortcut instruction, and improving the usage experience of the shortcut instruction. In the present disclosure, the server can be used to recognize an action and a condition in the first speech request, avoiding that the vehicle locally recognizes the first speech request, thereby reducing the load of the vehicle and ensuring the recognition efficiency of the action recognition result and the condition recognition result.