17914548. METHODS AND SYSTEMS FOR SEARCHING AND RETRIEVING INFORMATION simplified abstract (Telefonaktiebolaget LM Ericsson (publ))
Contents
METHODS AND SYSTEMS FOR SEARCHING AND RETRIEVING INFORMATION
Organization Name
Telefonaktiebolaget LM Ericsson (publ)
Inventor(s)
Perepu Satheesh Kumar of Chennai (IN)
METHODS AND SYSTEMS FOR SEARCHING AND RETRIEVING INFORMATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 17914548 titled 'METHODS AND SYSTEMS FOR SEARCHING AND RETRIEVING INFORMATION
Simplified Explanation
The abstract describes a method and system for searching and retrieving information using a knowledge base. Here are the key points:
- The method involves receiving a search query from a user and using a first model to determine the category that corresponds to the query.
- Based on the query, the loss function of the first model, and the objective function of a second model, the method identifies T topics related to the query.
- The method then performs a search on a specific part of the knowledge base that is associated with the identified category and/or topics.
- Finally, the method retrieves one or more files that are associated with the identified category and/or topics.
Potential applications of this technology:
- Improved search engines: This method can enhance the accuracy and relevance of search results by utilizing a knowledge base and considering both the query category and related topics.
- Information retrieval systems: The method can be used to efficiently retrieve specific files or information from a large knowledge base based on user queries.
- Personalized recommendations: By analyzing the query category and topics, the method can provide personalized recommendations for users, such as suggesting relevant articles or documents.
Problems solved by this technology:
- Improved search accuracy: By considering the query category and related topics, the method can filter out irrelevant information and provide more accurate search results.
- Efficient information retrieval: By searching only in the relevant part of the knowledge base, the method can save time and resources in retrieving the desired information.
- Enhanced user experience: The personalized recommendations and targeted search results can improve the overall user experience by providing more relevant and useful information.
Benefits of this technology:
- Increased efficiency: By narrowing down the search to specific categories and topics, the method can save time and computational resources in retrieving information.
- Improved accuracy: The method's ability to consider both the query category and related topics can result in more accurate and relevant search results.
- Personalization: By analyzing the query category and topics, the method can provide personalized recommendations and tailored search results, enhancing the user experience.
Original Abstract Submitted
Methods and systems for searching and retrieving information. In one aspect, there is a method of retrieving information using a knowledge base. The method comprises receiving a search query entered by a user and using a first model to identify a category corresponding to the received search query. The method further comprises based on the received search query, a loss function of the first model, and an objective function of a second model, identifying T topics corresponding to the received search query, and performing a search for the received search query only on a part of the knowledge base that is associated with the identified category and/or the identified topics. The method further comprises retrieving one or more files associated with the identified category and/or the identified topics.
