How we can help?

Cypris Advanced Search supports Lucene query syntax, a powerful standard for creating precise and flexible queries. Below is a guide to help you build more effective searches.

Contains

By default, typing a keyword into the search bar will return results that contain that term anywhere in the relevant field.

Example:
biotech – finds results that mention “biotech” in any position.

Does Not Contain

Use NOT (capitalized) to exclude results that contain a specific term.

Example:
gene NOT therapy – finds results that include “gene” but exclude anything mentioning “therapy”.

Is (Exact Match)

Use double quotes to search for an exact match or phrase.

Example:
"carbon capture" – finds results that include the exact phrase carbon capture, in that order.

Starts With / Ends With

Use the * wildcard to match terms based on how they start or end.

Examples:

• nano* – matches terms that start with “nano” (e.g., nanotech, nanomaterials)
  
  
• *delivery – matches terms that end with “delivery” (e.g., last-mile delivery, autonomous delivery)

AND / OR

Use AND, OR, and NOT to combine or exclude terms.

Examples:

• battery AND EV – both terms must be present.
  
  
• robotics OR automation – either term can be present.
  
  
• AI NOT healthcare – includes results with AI but excludes those that mention healthcare.
  
  

Proximity Search

Find words that appear near each other, even if not right next to each other.

Use "word1 word2"~N, where N is the maximum number of words between the terms.

Example:
"robotics delivery"~5 – returns results where robotics and delivery are within five words of each other, in any order. Useful for flexible phrase searches when word order varies.

Range Query

Search for values between two numbers or dates using TO.

• Use [] for inclusive ranges
  
  
• Use {} for exclusive ranges
  
  

Examples:

• year:[2019 TO 2024] – includes 2019 and 2024
  
  
• funding:{50000 TO 100000} – includes values between 50,000 and 100,000, excluding those exact endpoints
  
  
• date:[2022-01-01 TO 2023-01-01] – finds items published between January 2022 and January 2023
  
  

Fuzzy Search

Fuzzy searches find similar spellings or terms with small differences. Add a tilde ~ at the end of a term to enable fuzzy matching.

Example:

• biotech~ – returns similar terms like biotex, biotechh, or biotek
  
  
• You can fine-tune similarity by adding a number between 0 and 1: crispr~0.8 allows fewer differences than crispr~0.5
  
  

This is helpful for catching typos or alternate spellings.

Boosting

Increase the relevance of certain terms using the caret symbol ^ and a numeric weight.

Example:

• AI^3 automation – results mentioning AI will be ranked more highly (3x) than those mentioning automation
  
  

Grouping

Use parentheses to group terms and control the logic of your search.

Examples:

• (AI OR ML) AND robotics – returns results that mention robotics along with either AI or ML
  
  
• (hydrogen NOT storage) AND fuel – filters hydrogen results that do not mention storage, but do mention fuel

‍

Use these search strategies to narrow down results, discover related technologies, and unlock faster insights within Cypris.

A powerful new foundation for custom queries—built on Lucene and designed for R&D precision.

Over the past few years, Cypris has helped innovation teams make faster, more informed decisions by centralizing critical insights across datasets like patents, academic papers, and company activity. But until now, our search experience relied on a legacy query system with limited capabilities, offering little support for advanced search features or dataset-level customization.

Today, we’re excited to introduce an upgraded Advanced Search on Cypris, a complete overhaul of our query engine and search experience, powered by the open-standard Lucene query syntax. This update introduces a more robust and flexible search foundation, unlocking new ways to query data, build complex filters, and extract precisely what you need across patents, research, and more.

Why we rebuilt our search system from the ground up

Cypris’ original query syntax, a proprietary format used internally for years, limited users’ ability to craft advanced queries or tailor searches to specific datasets. It lacked modern capabilities like proximity searches, field-level customization, or true Boolean logic. This made it difficult to build a reliable and intuitive experience for both casual users and advanced researchers.

By moving to Lucene, we’re adopting a powerful, industry-standard query language that makes it easier for developers to build advanced features—and gives users access to a far more capable and flexible search toolset.

Watch the full tutorial

Watch the tutorial below or skip to the sections below to read what's new.

What’s new in Advanced Search

1. Custom Queries by Dataset
You can now layer queries to search across datasets or tailor filters to each one. For example, you can run a broad query on drone delivery, and then add separate layers to focus on patents by a specific assignee and papers from a specific country or funding agency.

Navigating the All Datasets tab introduces a new level of complexity—and power—by allowing users to apply dataset-specific logic within a single, unified query workflow. While querying multiple datasets simultaneously might seem straightforward, the underlying differences in schema, metadata, and available fields between our proprietary datasets make this a deeply technical challenge. Patents, for example, include claims, application numbers, and multiple date fields (filed, granted, updated), while academic papers use DOIs, have different structural conventions, and emphasize different metadata. In the past, we sidestepped this complexity by translating general queries like ((drone_allText)) into dataset-specific logic under the hood. Now, instead of obscuring that logic, we allow users to opt in to it. The builder provides progressive layers of customization: start with intuitive keyword searches across all fields, then move into the advanced builder for field-specific targeting, fuzzy logic, and term boosting, and finally, tailor query logic by dataset—such as specifying different countries of interest for papers vs. patents. This approach preserves flexibility while giving users full control, and with tools like our real-time Live Analysis and “Your Query” panel, we make it easy to understand how every decision affects the results.

Note that all fields includes claims, title, abstract, author/inventor, and organization/assignee/applicant.

2. More Fields to Query
We’re exposing deeper fields across datasets—giving you explicit control over the dimensions of your search. For the first time, users can now search academic papers by DOI, a critical identifier previously unsupported on the platform. You can also query by:

• Author or inventor names
  
  
• Organizations or assignees
  
  
• Countries, journals, funding agencies, and more

3. Full Boolean Support
Advanced Search now leverages powerful Boolean logic—AND, OR, NOT, and grouping—enabling more precise control over search logic and improving performance and accuracy.

4. Lucene Syntax Features
Use built-in Lucene features to create expressive, complex searches:

• Proximity searches to find terms near each other
  
  
• Fuzzy searches for flexible matching
  
  
• Exact phrase matching
  
  
• Boosting to prioritize results (e.g., prioritize results mentioning AI 3x more than others)
  
  
• Prefix/Postfix queries to match phrases that start or end a certain way
  
  
• Range queries for fields like date, funding amounts, or numerical values

For a guide to Lucene Syntax, view this article here.

A more powerful user experience

Our new search interface is built to help you tap into these capabilities without needing to know the syntax from the start. You’ll find:

• A Query Builder to guide you through complex searches
  
  
• A Help Video to onboard users to Lucene-style searches
  
  
• Inline examples and tips for writing queries using grouping, boosting, and more

Built for precision, speed, and customization

With Lucene as our foundation, search results are now not only more flexible but also faster and more accurate. Semantic search continues to offer natural-language ease of use, while Boolean search gives power users the performance and structure they need to uncover insights with greater specificity.

Whether you’re an innovation analyst drilling into AI patents or a business development lead scanning academic papers from Chilean researchers—Advanced Search is built to help you get to the signal, faster.

Available now to all users

Advanced Search is live and available across the Cypris platform today. If you’re already using Cypris, you’ll find the new search interface in your dashboard, complete with updated syntax documentation and walkthroughs.

We’re excited to see what you’ll build, discover, and analyze with this new capability. This is just the beginning—we’ll continue expanding the fields, syntax features, and customization options as we push the boundaries of what intelligent search can do for R&D.

We’ve rebuilt the Cypris search experience from the ground up—introducing Advanced Search, powered by Lucene. This upgrade gives you full control over how you search patents, academic papers, and company activity. With support for Boolean logic, proximity queries, fuzzy matching, and field-level filtering, Advanced Search enables both simple and highly customized queries tailored to each dataset. Whether you're scanning for keywords or constructing complex filters, this new foundation is built for speed, precision, and flexibility.

Watch the video below to learn how to use the new interface, explore example queries, and make the most of this powerful search upgrade.

To read about the new changes, view this article here.

For a guide to Lucene Syntax, view this article here.

Users have the ability to save individual datasets that are not attached to the original search query. 

How to Save a Search

Start by performing a technology search.

When the search results populate, the save button will be in the top right corner.

After clicking the Save Search button, users will be prompted to either select, All Datasets or Select Datasets. By selecting datasets, users will have the option to select which datasets they would like to be saved. 

Once the search is saved, it will be accessible from the Saved Searches section on the the Homepage.

Saved Searches will also be accessible from the Saved Searches tab in the dashboard view.

Flagged Data Collections will give users the ability to gather data points from multiple Saved Searches and store them in one place. 

Cypris’s Flagged Data Collections will give allow users to flag the following data points:

• Patents
• Research Papers
• Organizations

To Flag any data, click on the three vertical docs on the content you'd like to flag. Select "Add to Collection" to add to existing Collections or "+Create New Collection".

When flagging data, you can create a “Collection” and title each collection in relation to the type of data that you are flagging.

Where Flagged Data is Stored

All flagged data is accessible on the main home screen of the platform at the very bottom. You can create a “Collection” and add each flagged data to a specific collection.

While looking at a specific Flagged Data Collection, it’s important to note that the data will be separated on the sidebar.

AI Insights Across Flagged Data

We’ve added to our platform the unique feature of running AI insights across your flagged data.

For example, in the screenshot below, there are two patents are saved to the flagged data collection. Users can use AI Insights to summarize the latest activity.

Flagged Data Collections can also be added into Projects. Learn more about Projects here.

We’re thrilled to announce a significant enhancement to the Cypris platform: the expansion of our global patent dataset.

Previously, our patent coverage was primarily U.S.-focused, with limited access to global full-text data. Now, Cypris provides full-text coverage across 165M patent records from over 150 patent offices worldwide, updated daily. This includes:

• Global claims, enabling a more comprehensive understanding of patent scopes.
• Patent families, offering insights into related filings across jurisdictions.
• Forward and backward citations, supporting detailed analysis of patent influence and innovation trends.

This enhancement elevates our patent dataset to match the capabilities of leading enterprise-grade global patent search platforms, empowering your team with a cutting-edge solution for R&D and innovation research.

Why We Built This Feature

Patent data serves as a powerful indicator of global innovation within a specific domain. It provides valuable insights into who is active in a market, their unique strategies, and the progression of research in a field. While it doesn't offer the full picture, it remains a critical piece of the puzzle. Our mission is to equip R&D teams and innovators with the most comprehensive and up-to-date patent dataset available. This feature is designed to deliver maximum coverage and frequent updates, ensuring our users stay informed and never miss a key development when leveraging patent data to address their most pressing research questions.

User Needs Addressed

• Access to global patent data with daily updates.
• The ability to conduct more in-depth analyses with robust citation tracking.
• Improved usability and visibility of patent details through an intuitive interface.

How It Works

AI Insights Integration
The expanded dataset directly integrates with our AI Insights tool, enabling users to uncover trends across industries, explore relationships between patents, and leverage citation analysis for actionable insights.

Enhanced Patent Summary Card
The updated card provides:

• Comprehensive claims data (beyond U.S. coverage).
• Legal and citation information for deeper analysis.
• A clear presentation of the patent’s core features and status.

New UI Enhancements

• Patent Cards: A refreshed design for quick reference.
• Patent Summary View (Side Panel): Streamlined access to key details.
• Patent Pages (Full Display View): A detailed view with backward and forward citations, global claims, CPC codes, and more.

Improved Search Functionality
The default search now includes titles, abstracts, and global claims for faster and more relevant results. Coming in Q1, we’re expanding Advanced Search capabilities to help you build more complex queries using the new dataset.

‍

The Cypris platform offers multiple ways to conduct searches, allowing users to efficiently navigate through patents, research, and market insights. Below are the different types of searches available and how to use them effectively.

Semantic Search

Semantic search allows users to input natural language queries to retrieve relevant results. This search method is particularly useful when looking for insights beyond exact keyword matches.

For example, searching for "sodium-ion battery applications" will return patents, research papers, and company insights related to this topic. 

Semantic Search | Current Limitations

Currently, our semantic search does not effectively support queries that combine an inventor’s name or organization name with keywords, such as "patents filed by John Doe" or "patents filed by Amazon."

Avoid This:

Instead, Try This:

We’re actively working on improving this capability, with an enhanced search experience expected to launch in Q2.

In the meantime, we recommend searching for the inventor or organization name separately and then using keyword filters to refine your results. 

Semantic Search | Keyword Search

Keyword search allows users to enter specific terms related to their area of interest. Using a string of keywords can refine results effectively.

Example: "biodegradable packaging materials"

This method is useful for finding precise information related to specific terms in patents, research articles, and market reports.

Semantic Search | Patent ID Search

Our platform now supports flexible patent ID searches without formatting restrictions. You no longer need to manually remove spaces, commas, or slashes.

Examples of accepted formats:

• Official format: US 11,704,006 B1 or US 2017/0330365 A1
• Flexible format: US 11,704,006 or 11,704,006

The system automatically recognizes and processes these variations to provide accurate results.

Boolean Search

The most effective way to perform precise and efficient searches.

Boolean search enables users to build precise queries using Boolean operators to refine search results. The key operators are:

• AND – Narrows results by including all specified terms (e.g., "AI AND drug discovery").
• OR – Broadens results by including at least one of the specified terms (e.g., "bioplastics OR biodegradable polymers").
• NOT – Excludes specific terms from results (e.g., "gene therapy NOT CRISPR").
• Quotation Marks ("") – Searches for exact phrases (e.g., "electric vehicle battery").
• Parentheses () – Groups terms for complex searches (e.g., "((AI OR machine learning) AND drug discovery)".

To create a Boolean search:

1. Click on the search bar and input keywords using Boolean operators.

1. Once the query is complete, click “in boolean search” to execute the search.
2. After running the query, you can save it by selecting the Save Search button in the top right corner.

Advanced Search

Advanced search provides a more refined and customizable search experience, allowing users to construct detailed queries visually.

How to Use Advanced Search

The Advanced Search functionality is perfect for users who need a high level of control over their queries, allowing for deeper analysis and more precise results. By leveraging these search capabilities, users can efficiently navigate the Cypris platform and uncover insights tailored to their specific research needs.

Read our in-depth guide here.

For a video walkthrough, check out the tutorial below.

‍

‍

Cypris Monitoring has been fully redesigned to give R&D and innovation teams faster, smarter, and more actionable insights. Powered by advanced large language models (LLMs), Monitoring doesn’t just deliver updates—it interprets them, surfacing key insights and emerging trends so you can focus on what matters most.

What’s New in Monitoring

1. The New AI-Generated Monitoring Report

• Spreadsheets are no longer needed; updates are organized in a clear, structured format.

• The latest Monitoring Report uses advanced LLMs to read the data for you, surfacing key insights and emerging trends automatically, so you can skip the noise and get straight to what matters.

• Flag items directly into collections without manual steps like noting patent numbers or re-entering data.
  
  
• Access updates via email links or dashboard; review and flag relevant items instantly.
  
  
• Includes full AI-enhanced summaries of key trends and updates.
  
  
• Reports are refreshed every few weeks (based on user cadence) and automatically save previous updates, creating a running log.
  
  
• Patent-focused cards highlight key changes: “patent expansion” shows new jurisdictions, “assignee transfer” shows ownership changes between companies.

2. Redesigned Update Emails

• Redesigned emails with structured, visually engaging layouts.
  
  
• Attention-grabbing summary paragraph of recent activity.
  
  
• Highlights three key trends, with one trend previewed in email and a CTA to view the rest in-platform.
  
  
• Categorized, filterable updates for all tracked datasets.
  
  
• “View updates in-platform” CTA links to interactive pages with sorting, filters, and engagement tracking.

3. Simplified & Intuitive Setup

• Smart recipient suggestions include company colleagues, frequent contacts, and shared project members.
  
  
• Faster setup flow: choose monitoring type (keyword, patent, paper, organization), select saved searches or collections, and preview emails.
  
  
• Customize title, send date, and stop date with ease.

4. Improved Discoverability‍

• The Monitoring button now appears on every search results page.
  
  
• It also shows which queries are currently monitored with an indication so users don’t duplicate their monitors.
  
  
• External recipients can be easily added to email updates, enhancing collaboration.

5. Reduced Data Overload

• “Only send if new results exist” toggle prevents duplicate notifications.
  
  
• Only newly published patents, papers, new entrants, and news trigger alerts.
  
  
• Future updates will enable automatic tracking of entire corporate hierarchies.

6. Critical Alerts for Key Events

• Four new patent tracking alerts in addition to legal status changes: expiration risk, assignee transfers, patent family expansions, and forward citations

• Track forward citations of your own papers to monitor competitor activity in real time.

Bonus Update: A Fresh Look for Navigation

Alongside these Monitoring improvements, we’ve refreshed the Cypris side navigation bar with a new blue design. It’s a cleaner, modernized look that makes it easier to find your way around the platform while keeping your research flow uninterrupted.

With these updates, Cypris Monitoring becomes more than just alerts. It’s your central hub for staying ahead of competitors, discovering emerging technologies, and acting on insights with confidence.

The Impact

With these updates, Cypris Monitoring becomes more than just alerts—it’s a central hub for competitive intelligence. Users can:

• Stay ahead of emerging competitors and technologies
  
  
• Spot trends faster with AI-enhanced summaries
  
  
• Reduce noise with smarter alerts
  
  

Have questions or want help getting started? Reach out to your Cypris team directly.

‍

We’re excited to announce the launch of AI Reports for Patents, our newest feature designed to uncover unique and valuable insights from the patent dataset. With this feature, you can build downloadable reports tailored to common patent-focused research objectives, such as a Commercialization Report, Citations Impact Analysis, Technology Clustering Report, White Space Anlaysis & more. 

Additionally, you can create custom report templates (or custom prompts) by defining your objective and selecting the specific data points you’d like to analyze. Custom prompts can be saved to dashboards for easy access and future use.

We believe this feature will transform how users conduct research on Cypris. AI Reports allows users to run in-depth queries, analyze the accuracy of raw results, and use that data to create highly detailed, targeted reports. This process not only enhances users' confidence in the information provided by the AI model but also enables them to focus the AI on a defined pool of data.

This is just the beginning for AI Reports. In the future, we plan on extending the feature to our other datasets like Research Papers, Market News, and Organizations, but for now, we trust and hope you can find value for your patent-focused research initiatives. 

Why We Built This Feature

One of our most popular product offerings over the last year has been our Research Briefs, created by Cypris analysts. Time is proving to be one of the more valuable commodities for R&D teams, and traditional dashboard products have led them to spend more time on research and less time on development. This is a misstep on the vendor's part and is slowing down critical R&D initiatives.

Research Briefs have been well-received because they give valuable time back to researchers. With AI Reports, we set out to bring that same value to our self-service dashboard.

We chose to start with patents due to the high volume of patent-related work our analysts have spent time on. We then analyzed the most common patent report types users were manually building to determine which ones to include as suggested prompts. Each suggested prompt reflects the optimal report structure, informed by our findings and close collaboration with users during testing.

Additionally, we wanted to provide agility in the feature by allowing users to create and save custom prompts, by simply adding an objective and descriptive formatting. 

User Needs Addressed

• Automatically generate reports using the following suggested prompts: 
  • Patent Commercialization Reports
    • Evaluates a patent's commercial potential, highlighting sectors or companies where the technology could be monetized through licensing.
  • Citation Impact Analysis
    • Analyze a patent's impact based on its forward (cited by) and backward (cites to) citations.
  • Technology Clustering
    • Examines where patents can be grouped according to applicable technology sectors.
  • White Space Analysis
    • A white space analysis that identifies gaps in the patent landscape, highlights innovation opportunities and provides actionable recommendations supported by data insights.
  • Patent Portfolio Analysis & Impact Assessment
    • A comprehensive analysis on the selected patents, their owners, and their possible impact on the market.
  • Design custom report prompts by describing an objective and source formatting. Save prompts in your dashboard for quick future use. 
  • Suggest edits to the report using the ‘Regenerate’ text box. 
  • Download reports to PDF.

How AI Reports Work

1. Run any type of search (semantic, boolean, or organization).

2. Navigate to a patent in the results 
   1. If on an organization page go to their patents tab.
3. If you’d like to build a report on 1 patent, select the AI Report Blue Icon to open the report builder. 

4. If you’d like to build a report on multiple patents, checkbox the group of patents and select AI Report in the bottom pop-up bar.
5. Choose a suggested prompt or Design your own prompt.
6. Once you get back your results, download to PDF or choose to regenerate the report with added comments. 

How We Built This Feature

This feature is powered by ‘retrieval augmented generation’ or ‘RAG’. 

Explained simply, RAG is an AI technique that focuses the answers you get from language models by combining external contextual knowledge with text generation. When you ask a question, a RAG model searches through a focused set of documents (or ‘context’) to find the most relevant information. It then uses this information to generate a response, effectively blending up-to-date data with its language skills. This means you get more accurate and context-aware answers, making the AI's responses more accurate and reliable.

‍

Cypris RAG Context for This Feature

For this feature, we’re primarily looking at the selected group of patent documents as the initial context to build the analysis, and depending on the report type retrieve answers from the Cypris database in addition to external providers. 

Depending on the chosen report type we’re analyzing a different breadth of context from the patent document. For example, the citations impact analysis primarily looks at the patent’s forward and backward citation data. 

In ‘Design Your Own Prompt’ the user can specify the context to be either the Metadata or Full Text. 

For AI Reports case, Metadata includes: Title, Abstract, Assignee, Country, Publication Date, and Inventor. And Full Text includes Claims and Citations + all Metadata. 

Finally, certain prompts are restricted by a maximum amount of ‘Input Context’. For example, when doing a Citation Impact Analysis, it can only be done on a maximum of 20 patents due to the breadth of input context.