User Preference Generation via Thesaurus Keyword Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in accurately generating user attribute and preference information, particularly when household electric appliances are used by multiple individuals, leading to difficulties in distinguishing the relevant user's behavior from others.
Innovation Solution
An information provision system connected to both Web and household electric appliance terminals, which collects access and manipulation history information and uses a thesaurus-based keyword mapping to generate user attribute and preference information, filtering out keywords not related to the primary user's behavior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If household electric appliance manipulation history is collected for user preference analysis, then more user behavior data is available for advertisement targeting, but it becomes difficult to distinguish the relevant user's behavior from other users who use the same appliance
Solution Approach 1:
The patent segments user behavior data by creating a relationship table that links appliance manipulation history to specific user profiles. Instead of treating all appliance usage as undifferentiated data, the system divides it into user-specific segments using thesaurus-based keyword matching to identify which user performed which actions, thereby maintaining data quantity while improving identification precision.
Solution Approach 2:
The patent introduces a thesaurus-based keyword mapping system as an intermediary between raw appliance manipulation data and user preference analysis. This intermediary layer processes and annotates the data with user-specific attributes, enabling accurate user identification without losing the volume of behavioral data collected from shared household appliances.
2Adaptability or versatility
If web terminal access history and household electric appliance manipulation history are integrated, then more comprehensive user profile can be generated, but the complexity of data processing and user identification increases
Solution Approach 1:
The patent creates a universal thesaurus-based keyword mapping system that handles both web terminal access history and household electric appliance manipulation history through the same processing mechanism. This multi-functional approach integrates diverse data sources without requiring separate complex processing pipelines for each type, thereby achieving comprehensive user profiles while controlling processing complexity.
Solution Approach 2:
The patent transforms heterogeneous data from web terminals and appliances into a unified format by applying thesaurus-based keyword mapping. This parameter transformation converts diverse data types into comparable user preference representations, enabling comprehensive profiling through standardized processing that reduces overall system complexity.
Data Source
AI summary
An information provision system includes a first history collection device, a second history collection device, and a specific-information generation device. The specific-information generation device includes a history collector that acquires first history information and second history information, and a specific-information generator that generates specific information regarding an attribute and a preference of a user, based on the first history information and the second history information. The specific-information generator disposes, on a map of a thesaurus prepared in advance, a first keyword obtained from an access history of a Web terminal, and a second keyword obtained from a manipulation history of a household electric appliance terminal, and generates first specific information, based on the second keyword having a distance smaller than a predetermined distance from a disposed position of the first keyword disposed on the map.