Assistant System Entity Tagging for Messaging Context
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing assistant systems in network environments lack the ability to provide seamless, context-aware information retrieval and management of named-entities within messaging conversations, requiring users to switch between applications for information lookup.
Innovation Solution
An integrated assistant system that utilizes natural-language understanding and entity resolution to identify and provide additional information for named-entities within messaging conversations, allowing users to access information without leaving the messaging app by tagging and selecting n-grams for further details from a knowledge graph.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If users switch to a search interface to look up unfamiliar terms, then information retrieval capability is improved, but conversation flow and user engagement deteriorate due to context switching
Solution Approach 1:
The patent merges the information lookup functionality directly into the messaging application interface. When users encounter unfamiliar named-entities in conversations, they can tap on the highlighted entity to view additional information from the knowledge graph without leaving the messaging context. This combines the messaging and information retrieval functions into a single integrated interface, eliminating the need to switch between applications while maintaining both conversation flow and information access capability.
2Ease of operation
If the assistant system provides additional information for named-entities, then user experience is improved, but device complexity increases due to integration requirements
Solution Approach 1:
The patent introduces an intermediary assistant system that acts as a bridge between the messaging application and the knowledge graph. The assistant system includes components that automatically recognize named-entities in messages, retrieve additional information from the knowledge graph, and present this information within the messaging interface. This intermediary layer handles the complexity of integration internally, allowing the messaging application to maintain its simplicity while still providing enhanced user experience through contextual information delivery.
3Loss of information
If the system automatically recognizes and tags named-entities in real-time, then information relevance is improved, but processing time increases
Solution Approach 1:
The patent implements preliminary action by pre-processing and indexing the knowledge graph data structure before runtime interactions. Named-entities and their associated information are organized in advance, allowing the assistant system to quickly retrieve and present relevant information when users tap on entities during conversations. This pre-preparation reduces the processing time required during real-time interactions while maintaining high information relevance.
Data Source
AI summary
In one embodiment, a method includes receiving, from a first client system associated with a first user, a message sent from the first user to a second user, where the message includes one or more n-grams, analyzing the received message to identify one or more named-entities corresponding to one or more of the n-grams, tagging one or more of the n-grams of the message with references to the one or more identified named-entities, and sending, to a second client system associated with the second user, instructions for presenting the message to the second user, where the message includes the one or more tagged n-grams corresponding to the one or more identified named-entities, where each tagged n-gram is selectable to retrieve additional information associated with the corresponding named-entity.