Technology Name Recommendation via Concept Co-occurrence Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies and services fail to provide users with appropriate information on necessary technologies and services to solve specific issues due to their specialization in web services and difficulty in ascertaining individual user needs.
Innovation Solution
A technology name and service name generation device that includes a synonym dictionary, classification dictionary, and recommendation unit to analyze user input, extract relevant concepts, and identify necessary technology and service names based on co-occurrence scores, enabling the recommendation of suitable solutions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If a user searches for technologies and services to solve issues, then the user can find available solutions, but the user cannot ascertain what technologies and services are necessary because individual needs cannot be ascertained
Solution Approach 1:
The patent replaces manual analysis of user needs with automated natural language processing. The NLP unit automatically extracts issues from user input sentences, converting unstructured text into structured problem representations without requiring manual intervention to ascertain individual needs.
Solution Approach 2:
The system enables users to self-describe their needs through natural language input. The issue extraction unit processes user sentences autonomously, allowing users to express their requirements in their own words while the system automatically interprets and categorizes them without requiring users to navigate complex classification systems.
2Reliability
If technologies and services are painstakingly developed, then solutions are created, but the needs and solutions may not match because the kind of technologies and services that exist cannot be ascertained
Solution Approach 1:
The patent creates a universal system that handles multiple types of issues and technologies through a single platform. The classification dictionary and name list units work together to categorize and retrieve various technologies and services based on extracted issues, making the system applicable to diverse problem-solution matching scenarios.
Solution Approach 2:
The system establishes a feedback loop where user input is processed through issue extraction, matched against the classification dictionary, and returns relevant technology names and service names. This closed-loop process ensures that the information on available technologies and services is continuously aligned with actual user needs.
3Adaptability or versatility
If a classification system is used to organize technologies and services, then information can be structured, but the system cannot appropriately support a wide range of requests from users due to web service specialization
Solution Approach 1:
The patent segments the classification system into distinct functional units: the classification dictionary unit stores predefined categories, the issue extraction unit processes user input separately, and the name list unit retrieves results. This modular segmentation allows the system to handle diverse requests while maintaining manageable complexity through clear separation of concerns.
Data Source
AI summary
Information indicating what technology and service are necessary to solve issues is provided by a device including dictionaries recording words having similar meanings and concepts concept co-occurrences in which two of the concepts are combined, a classification of each of technology names and service names, and a score assigned to each of the classifications, a sentence input unit receiving a sentence representing an issue, a morpheme analysis unit performing morpheme analysis on the sentence and output morphemes, a concept conversion unit extracting a word from the morphemes and convert the extracted word to a concept, a classification identifying unit configured to sum scores of respective classifications in which a set of the extracted concepts and the concept co-occurrence match and identify the classification having a highest summed score, and a recommendation unit configured to obtain, from the name list, the technology names and service names belonging to the identified classification.