Conversation Profile Matching for Contextual Entity Suggestions

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing communication systems, such as email and instant messaging, face difficulties in discerning the logical context of conversations, especially when multiple messages and responses are involved, and participants join mid-conversation, making it hard to suggest relevant entities for association.

Innovation Solution

A server system generates conversation and entity profiles based on user-specific term weights and internal conversation structures to suggest entities that best match the conversation context, allowing for improved user experience by accurately suggesting participants, categorization entities, and maintaining logical context.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If traditional email and instant messaging systems are used for communication, then basic message transmission is achieved, but logical context of conversations cannot be discerned and entity suggestions cannot be provided

Engineering Contradiction:

Improvelogical context of conversationVSAvoiddifficulty in discerning context and suggesting entities

Core Design Contradiction:

Loss of informationVSEase of operation

Solution Approach 1:

The system pre-generates conversation profiles and entity profiles before entity suggestion is needed. Conversation profiles are created by analyzing message content, participants, and temporal patterns, while entity profiles are pre-computed for contacts, folders, and tags. When a user needs entity suggestions, the pre-computed profiles enable rapid matching without real-time computation delays, thus preserving logical context information while maintaining ease of operation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces conversation profiles and entity profiles as intermediary data structures that bridge the gap between raw conversation data and entity suggestions. These profiles serve as mediators that capture logical context (participants, topics, temporal relationships) and enable the system to suggest relevant entities without requiring complex real-time analysis of the entire conversation history.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If conversation profiles and entity profiles are generated and compared to suggest entities, then accurate entity suggestions are provided, but system complexity increases

Engineering Contradiction:

Improveaccuracy of entity suggestionVSAvoidcomplexity of profile generation and comparison system

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the entity suggestion task into distinct components: conversation profile generation, entity profile generation, and profile comparison. Each component handles a specific aspect of the suggestion process, making the overall system more manageable despite increased complexity. Conversation profiles segment temporal and contextual information, while entity profiles segment entity-specific attributes, enabling precise matching through structured comparison.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system changes parameters by representing conversations and entities as vectors with specific parameters (participants, topics, temporal patterns, message counts). This parameterization transforms unstructured conversation data into comparable formats, enabling accurate entity suggestions through mathematical operations on profile vectors while systematic parameter handling reduces operational complexity.

Inventive Principle:

Principle #35Parameter changes

3Adaptability or versatility

If users access conversations from multiple devices, then accessibility is improved, but maintaining logical context across devices becomes difficult

Engineering Contradiction:

Improveaccess to conversations from multiple devicesVSAvoidlogical context of conversation

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The conversation profile serves as a universal representation that can be accessed and utilized across multiple devices. The profile encapsulates all logical context information (participants, topics, temporal relationships) in a device-agnostic format, enabling any device to reconstruct and maintain the conversation's logical context regardless of where the user accesses it from.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS9602444B2Participant suggestion system

Publication Date: 2017.03.21 GOOGLE LLC

AI summary

A server system hosts a plurality of conversations, each having an identified set of participants. For a respective conversation, the server accesses the conversation in which a user is a participant. The server obtains a conversation profile for the conversation, the conversation profile based on information including content of the conversation and user-specific term weights for at least a plurality of terms in the content of the conversation. The server accesses a plurality of entity profiles that are based on content and/or structure in other conversations in which the user is a participant. The server compares at least a subset of the entity profiles to the conversation profile to identify a set of entities having entity profiles that best match the conversation profile, generates a suggestion for the user including a suggested entity from the identified set of entities; and sends the suggestion to the client system for display to the user.