18482756. SEARCHABLE INDEX simplified abstract (GOOGLE LLC)
Contents
SEARCHABLE INDEX
Organization Name
Inventor(s)
Jeremiah Harmsen of Zurich (CH)
Tushar Deepak Chandra of Los Altos CA (US)
Marcus Fontoura of Bellevue WA (US)
SEARCHABLE INDEX - A simplified explanation of the abstract
This abstract first appeared for US patent application 18482756 titled 'SEARCHABLE INDEX
Simplified Explanation
The patent application describes a system and techniques for generating entries for a searchable index based on rules generated by machine-learned models. These index entries include tokens correlated with an outcome and an outcome probability. The system can identify a subset of tokens based on the characteristics of an event and search the index for outcomes and their respective probabilities that match the subset of tokens.
- The patent application is about generating entries for a searchable index using machine-learned models.
- The index entries include tokens, outcomes, and outcome probabilities.
- The system can identify a subset of tokens based on the characteristics of an event.
- The index can be searched for outcomes and probabilities that match the subset of tokens.
Potential applications of this technology:
- Search engines can use this technology to improve the accuracy and relevance of search results.
- Recommendation systems can utilize this technology to provide personalized recommendations based on user preferences and characteristics.
- Fraud detection systems can benefit from this technology by identifying patterns and tokens associated with fraudulent activities.
Problems solved by this technology:
- This technology solves the problem of accurately indexing and retrieving information based on specific tokens and their correlations with outcomes.
- It addresses the challenge of efficiently searching for outcomes and probabilities that match a subset of tokens.
- It helps in identifying relevant information and patterns based on the characteristics of an event.
Benefits of this technology:
- Improved search accuracy and relevance.
- Enhanced recommendation systems leading to better user experiences.
- More effective fraud detection and prevention.
- Efficient indexing and retrieval of information based on specific tokens.
Original Abstract Submitted
Systems and techniques are disclosed for generating entries for a searchable index based on rules generated by one or more machine-learned models. The index entries can include one or more tokens correlated with an outcome and an outcome probability. A subset of tokens can be identified based on the characteristics of an event. The index may be searched for outcomes and their respective probabilities that correspond to tokens that are similar to or match the subset of tokens based on the event.