Quantity Prediction System for Voice Interfaces
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face challenges in determining the appropriate quantity of items to purchase online, especially when using voice interfaces, as they cannot visually examine the items and may need to navigate through lengthy audio recitations of available quantities, leading to potential overestimation or underestimation.
Innovation Solution
A system and method that utilize user identifiers and item identifiers to analyze user transaction history, household size, and global transaction data to predict and recommend suitable quantities for purchase, incorporating Bayesian formulations and outlier handling to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If a drop down menu is used to display available quantities, then the person can see the available quantities, but the person may still be uncertain as to which quantity would be appropriate and will spend significant time and effort trying to ascertain the correct quantity
Solution Approach 1:
The system performs preliminary analysis of user transaction history, household size, and global transaction data before the purchase transaction occurs. This pre-computation of quantity recommendations eliminates the need for the user to spend time determining the appropriate quantity during the actual transaction, as the recommendation is already prepared and presented to the user.
2Loss of information
If all available quantities are recited via voice interface, then the person can hear the available quantities, but the person must remember the audio recitation in sufficient detail to select an appropriate quantity, making the process lengthy
Solution Approach 1:
The system extracts only the most relevant quantity information based on user-specific data (transaction history, household size) rather than presenting all available quantities. This extraction of essential information through predictive algorithms reduces the cognitive load on the user and simplifies the voice interaction process by eliminating unnecessary quantity options.
3Ease of operation
If the person cannot visually examine the item, then the person cannot assess the appropriate quantity, but using voice interface without visual display makes it even more difficult to determine the correct quantity
Solution Approach 1:
The system introduces an intermediary computational layer that processes user-specific data (transaction history, household size, item characteristics) and translates these into precise quantity recommendations. This intermediary algorithm acts as a mediator between the user's limited ability to assess quantity and the need for accurate quantity determination, providing data-driven recommendations that compensate for the lack of visual examination.
Data Source
AI summary
Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform acts of receiving a user identifier, receiving an item identifier, determining user item quantity information related to quantities of the item previously selected by the user, determining a respective household size for each user, and determining aggregate household item quantity information related to quantities of the item previously selected by an aggregate of users of the same household size. If a first threshold level of the quantity of transactions is met, a recommended quantity is based on the user item quantity information, and if not, the recommended quantity is based on the aggregate household item quantity information. The user interface of the electronic device is updated to notify the user of the recommended quantity. Other embodiments are disclosed herein.