Cognitive Assistant Personalizing Recommendations via User State

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional cognitive assistants primarily rely on general recommendations based on user data from various sources, lacking personalization and failing to effectively utilize user emotions, habits, and preferences to suggest activities or places tailored to the user's current cognitive state.

Innovation Solution

A system that captures user data from multiple sources, including wearables and personal information systems, to determine the user's cognitive state and preferences, correlating this data to provide personalized recommendations for activities and places based on learned habits, tastes, and customs, using a cloud computing environment to process and rank user interests.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If conventional cognitive assistants use general recommendations based on user data, then the system is simpler to operate, but the recommendations lack personalization and relevance to user's current cognitive state

Engineering Contradiction:

Improveease of operationVSAvoidpersonalization capability

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The system automatically captures user data from multiple sources, determines cognitive state, correlates data to identify habits and preferences, and generates personalized recommendations without requiring constant manual input or configuration from the user. The assistant serves itself by continuously learning and adapting to user patterns.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system incorporates feedback loops where user interactions and data from multiple sources continuously refine the cognitive state model and preference correlations, enabling increasingly accurate personalized recommendations over time while maintaining ease of use.

Inventive Principle:

Principle #23Feedback

2Adaptability or versatility

If the system captures and processes data from multiple sources to determine cognitive state, then the personalization and relevance of recommendations improve, but the device complexity increases

Engineering Contradiction:

Improvepersonalization capabilityVSAvoiddevice complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system uses a multi-functional approach where a single cognitive assistant platform integrates data capture from diverse sources (wearables, mobile devices, cloud services), cognitive state determination, preference correlation, and recommendation generation, eliminating the need for separate specialized systems.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system introduces an intermediary processing layer that standardizes and correlates data from multiple heterogeneous sources into a unified cognitive state model, simplifying the complexity of integrating multiple data sources while maintaining high personalization capability.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Ease of operation

If the system automatically learns user interests and customs without manual input, then the ease of operation improves, but the measurement precision of user preferences may deteriorate

Engineering Contradiction:

Improveease of operationVSAvoidprecision of user preference detection

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system continuously monitors and learns from user behavior patterns across multiple data sources, maintaining an ever-updating profile of preferences and cognitive state. This continuous learning process improves measurement precision over time while requiring no manual input from the user.

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The system replaces manual preference declaration mechanisms with automated computational analysis of behavioral data patterns, using algorithms to infer preferences from observed actions, context, and cognitive state indicators rather than requiring explicit user input.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11681895B2Cognitive assistant with recommendation capability

Publication Date: 2023.06.20 KYNDRYL INC

AI summary

Cognitive assistants which use feedback to highlight relevant points of interest to a user so that recommendations can be provided to the user based upon learned knowledge of the users preferences, tastes and customs are provided. For this purpose a computer-implemented method includes capturing user data of a user from a plurality of sensors, determining a cognitive state of the user from the captured data, correlating the user data to the cognitive state of the user, and making recommendations to the user based on the correlation of the user data and the determined cognitive state of the user.