Voice Purchase System Using Confidence Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
As computing devices become smaller and more portable, traditional input methods like keyboards and touchscreens become less feasible, leading to a need for more intuitive and efficient interaction methods, particularly in devices like head-mountable displays and mobile phones where other input modalities are limited.
Innovation Solution
A hybrid human and computer-automated response system that processes voice requests to facilitate product or service purchases, using automated responses when confident and human assistance when necessary, with image recognition to aid in identifying target products or services.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If speech-based interfaces are used for interaction, then ease of operation is improved, but device complexity increases due to the need for hybrid automated and human response systems
Solution Approach 1:
The system segments the response handling into automated response components and human guide components. The computing system automatically processes speech inputs and determines confidence levels, while human guides handle complex or low-confidence scenarios. This segmentation allows the system to maintain simplicity for routine operations while providing complex human assistance only when needed.
Solution Approach 2:
The system implements self-service through automated speech processing and confidence level determination. The computing system autonomously evaluates speech inputs, identifies purchase requests, determines target products or services, and executes purchases when confidence levels are sufficient. This self-service capability reduces the need for human intervention in routine transactions.
2Productivity
If automated response system is used, then productivity is improved, but reliability decreases when confidence level is insufficient
Solution Approach 1:
The system uses feedback through confidence level determination to dynamically adjust its operation mode. When the automated system's confidence level is high, it proceeds with automated purchase execution. When confidence is low, the system feedback-indicates the need for human guide intervention. This feedback mechanism ensures high productivity for clear, unambiguous requests while maintaining reliability by involving human guides for uncertain cases.
3Measurement precision
If image recognition is integrated, then measurement precision is improved for product identification, but device complexity increases
Solution Approach 1:
The system merges speech-based product identification with image recognition capabilities. The computing system can process speech inputs to identify products or services, and when additional precision is needed, it integrates image analysis of product packaging, labels, or barcodes. This merging of multiple identification methods enhances measurement precision for product identification while sharing computational resources across different input modalities.
Data Source
AI summary
Methods are described herein related to enabling users to purchase a product or service by providing a voice request and/or an image. An example method may involve: (a) receiving, by a hybrid response system (“HRS”), a first speech-segment message that comprises a speech segment and is associated with a user-account, (b) the HRS determining that the speech segment indicates a purchase request, (c) the HRS determining a target product/service based on at least the purchase request, (d) the HRS determining a confidence level associated with a purchase of the target product/service, (e) if the confidence level is greater than or equal to a threshold level, then the HRS sending a purchase order, via the associated user-account, for the target product or service, otherwise, the HRS sending the purchase request and the target product/service to at least one guide computing system to facilitate a response to the purchase request.