Dynamic Prompt Builder for Digital Assistant Efficiency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Processing user requests to determine and perform actions, while providing natural and quick responses, is computationally expensive for digital assistants, leading to user discomfort if not executed efficiently.
Innovation Solution
The method involves receiving an utterance, determining a potential action, creating a prompt including the action and an example, and using this prompt to determine a response to the user request, thereby enhancing processing efficiency and user satisfaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If digital assistants process user requests using traditional methods to determine and perform actions, then they can provide responses to user requests, but the processing is computationally expensive and consumes excessive power
Solution Approach 1:
The patent segments the prompt creation process into distinct components: identifying potential actions, selecting relevant examples, and structuring the prompt. This segmentation allows the system to process only necessary information rather than handling entire request contexts, reducing computational overhead and power consumption while maintaining response efficiency
Solution Approach 2:
The system performs preliminary actions by pre-identifying potential actions and pre-selecting examples that can be reused across multiple requests. This preliminary processing creates a library of actionable components that can be quickly assembled into prompts without requiring full computational analysis for each new request, thereby improving efficiency and reducing energy use
2Ease of operation
If digital assistants process user requests quickly and naturally, then user satisfaction improves, but computational cost increases
Solution Approach 1:
The patent employs copying by selecting and reusing examples from a database of previously processed requests and their corresponding actions. Instead of analyzing every request from scratch, the system copies relevant examples that match the current request pattern, enabling quick and natural responses while reducing processing complexity and computational requirements
Solution Approach 2:
The system changes parameters by dynamically adjusting the level of detail and complexity in prompt creation based on the specific request. By varying parameters such as example selection criteria, action identification depth, and prompt structure, the system can provide natural, satisfying responses while optimizing processing complexity to avoid unnecessary computational overhead
Data Source
AI summary
Systems and processes for operating an intelligent automated assistant are provided. An example process includes receiving an utterance including a user request; in response to receiving the utterance including the user request: determining, based on the received utterance, a potential action capable of being performed by a digital assistant of the electronic device; determining, based on the received utterance and the potential action capable of being performed by the digital assistant of the electronic device, an example corresponding to the potential action; creating a prompt including the potential action, the example corresponding to the potential action, and the utterance; determining, based on the prompt, a response to the user request; and providing an output including the response to the user request.