TABLE OF CONTENTS

• Introduction to Sophia Search
• Getting Started 
• Results Review
• Limitations and Considerations

Introduction to Sophia Search

Sophia Search is an AI-powered patent semantic search that uses natural language and advanced neural embeddings. Sophia search combines a new generation of natural language search based on embeddings, with an AI-powered extraction of features disclosed in user's input and patent fulltext.

This semantic search engine aims to provide better results with new embedding-based technology that ensures significantly higher recall and precision.

If you're interested in the AI capabilities for text analysis, particularly in leveraging AI to read patents and identify which elements or features have already been disclosed, you can refer to article Sophia Search: AI-powered Text Analysis & Disclosure Reveal  
Please note that this search tool offers Pre-filtering options through the Advanced Search form, allowing users to narrow down results before launching the analysis. For further details, refer to the above-mentioned article. 

For full details on how your information is processed, with or without third-party intervention, please refer to the disclaimer document: AI tools in Orbit Intelligence: Usage disclaimer

Getting Started 

Sophia Search is found under the Menu tab, listed among the various searches options in Orbit Intelligence. 

To access semantic mode, go to the main interface and enter your text in the search box. 

A character counter appears in the bottom-right corner of the text area to help you stay within the optimal length.

• Optimal text size: between 500 and 3,000 characters.
• Minimum requirement: text must be at least 100 characters.
• Beyond 3,000 characters your remaining text will be truncated and ignored

Be aware that the semantic mode functionality, as described here, is available without usage limits. 

Note: Non-English text is sent to a third-party service for automated translation. We kindly advise you to input English text, and preferably the most self-explicit about the invention (like an executive abstract).

Before running your search, set the maximum number of results at the bottom of the page. The default setting is 50 results.

Results Review

The hitlist displays the results along with a Semantic Match relevance column. Each label represents a range of relevance scores, indicating how closely the result matches your query:

• Perfect: 99-100% match
• Excellent: 97-98.99% match
• Good: 96-96.99% match 
• Moderate: 95-95.99% match
• Weak: 92-94.99% match
• 0-91.99% is considered as no match

Results are sorted by their matching score, calculated from embeddings generated from the user's input, and compared with the families' embeddings.

Percentages here disclosed are inherent to embeddings technology, and should not be compared with the Relevancy scores used in other search modes within Orbit Intelligence.

By hovering over a label, you can view its details and the corresponding numerical relevance score.

Limitations and Considerations

The following points highlight some technical constraints and behaviors to keep in mind when using Sophia Search.

Input Text Size
Only the first 3,000 characters of the input text are used for the search. A character counter is available on the Sophia Search page.

Representative Member
One embedding is computed per FAMPAT family using a specific algorithm to select the “computational” member. This may differ from your representative member chosen as defined in your settings. In other words, search may not align with the user’s representative member.