Generating text with OpenAI GPT [+Drafting Option Only]

ClaimMaster's patent drafting tools let you store and invoke helpful OpenAI GPT prompts enriched with the text from your document to generate, rewrite, and summarize text.   To do so, ClaimMaster connects to either OpenAI's or Microsoft Azure OpenAI's GPT services via Enterprise-level API.   ClaimMaster will send and receive data to/from the selected GPT service using API directly from the computer where ClaimMaster is installed, without sending data for processing to any intermediate servers.  According to OpenAI API policies and/or Azure OpenAI API policies,  the use of API ensures that your prompts (inputs), completions (outputs), and any other transmitted data will not be available to other customers and will not be used to improve GPT models.  To further enhance data privacy, you can also configure ClaimMaster with your own API key and endpoint (Azure) to connect to private models set up in OpenAI or Azure OpenAI services. If ClaimMaster is configured to access private GPT models using your API keys, those keys will be always stored in encrypted format on a machine where ClaimMaster is installed.


In any event, you are responsible for determining whether OpenAI API policies and/or Azure OpenAI API policies suit your needs, satisfy your organization's security requirements, and assume all risk for using GPT services with your confidential data. All GPT features in ClaimMaster will only transmit data to GPT after your explicit command. You control exactly what data is being sent to GPT.  It's also a good practice to always review GPT responses for factual correctness, especially if you are using GPT prompts with settings for higher response randomness/creativity.


To access GPT tools in ClaimMaster, follow these steps:



Getting Started

  • From the ClaimMaster Ribbon, click on the Patent Drafting Tools menu, then select Generate Text with GPT:





Feature Options

Once you select the feature from the menu above, the patent drafting window will come up. It will be "docked" to the left side of your Word document when it launches, unless automatic docking of patent drafting windows is disabled in Patent Drafting Preferences (i.e., the "Dock drafting windows" checkbox is unchecked). The following operations are available for this feature:



    1. Click this button to review GPT data usage policies.
    2. Use this tab to select one of the inputs from the document to enrich the stored GPT prompt template via the [INPUT] variable. The following inputs are available
      • Special inputs:
        • Text in the preview window - allows applying GPT transformations on the results produced by previous GPT requests
        • Selected text in the document
        • Surrounding word/sentence/paragraph at the cursor's current position
        • All document text
      • Part names (and optionally numbers) extracted from the document
      • Acronyms extracted from the document
      • Terms extracted from claims
      • Claim text and individual limitations
    1. Click on one of the rows in the table to select the specific [INPUT] value to be inserted into the GPT prompt
    2. Specifies the GPT prompt template, where the [INPUT] variable will be populated based on the selection from the left-side table (item 3).  You can specify any prompt you wish - for example, helpful prompt include directions for GPT to define or explain terms, add more information, summarize text portions, or draft certain section of the patent document using provided inputs.  However, do not pass sensitive data as input unless you review and are OK with GPT data usage policies.  There many different operations GPT can perform on the passed-in text, but some of the interesting things you can ask GPT to do include:
      • Explain or define a technical term
      • Re-write a text portion more eloquently
      • Write a paragraph or two explaining the state of problems with the current technology
      • Generate sample data tables for you
      • Draft a section of the application based on the passed-in subject matter, such as title, background, etc.
    1. Use the filter field to limit the list shown in the template table only to those templates that at least partially match the filter.  To remove the filter, click on the "Clear" button.
    2. Click this button to open settings for GPT prompts.
    3. If you are adding a figure to a GPT prompt (i.e., for drafting figure description, etc.), select this checkbox if you want to add red triangle annotations next to part #s in the figures. This may help GPT better identify parts in the figures. However, if you have very dense figures with many parts closely located to each other, uncheck this box to avoid accidentally overwriting parts #s in the figures with annotations. 
    4. Press this button to open a file with one or more figures (PDF, PPT, Visio, Word, JPG, PNG).  If you are providing a multi-page file, you'll be presented with a selection window where you can select one figure to include in the GPT prompt, as shown below:


    1. Press this button to remove the figure from being added to the GPT prompt.
    2. Press this button to select another page from the same file.
    3. Press this button to see the currently selected, full-sized page that will be sent to GPT as part of the prompt.
    4. Shows the preview of the final GPT prompt with the input data inserted. This will be the prompt that will be sent to GPT. You can make edits/adjustments to this prompt directly in the window. If a figure is specified, ClaimMaster will automatically attempt to extract the following information from the figures/specification and fill-in these placeholders in the template to improve GPT output accuracy:
      • [FIGURE_NUMBER] - specifies the figure #. 
      • [FIGURE_SHORT_DESC] - specifies short description of the figure that would be extracted from the specification, if available.  
      • [FIGURE_PARTS] - specifies the list of part #s extracted from the figures or  part names + numbers extracted from the Specification (item 2).
    1. Use this slider to make GPT responses more or less random/deterministic. Corresponds to the temperature setting for the GPT.  Higher values will make GPT output more random/creative, while lower values like.will make it more focused and deterministic. It's a good practice to always review GPT responses for factual correctness, especially if you are using GPT prompts with settings for higher response randomness/creativity.
    2. Press this button to open OpenAI's GPT API settings window.
    3. Press this button to send the prompt from the preview window (item 7) to GPT. As mentioned above, ClaimMaster does not automatically access OpenAI's or Azure OpenAI GPT services using API. You will only send a prompt to GPT when you press this button.



Providing additional examples/context to GTP for rewriting

To possibly improve the quality of GPT output you can also pass example output or additional context as part of GPT prompts.  Note - you need to edit the contents of this window before sending text prompts to GPT. This additional example/context text would be configured as part of the GPT template - to add example/context, switch to the "Example/Context" tab when editing a GPT prompt:





The following options are available from the Example/Context window used for specifying additional context and examples for GPT templates:

    1. This window specifies the text of the example or additional context for the GPT prompt template.
    2. Click this button to load the text into the example window (item 6) from the selection in the open Word document.
    3. Click this button to load the text into the example window (item 6) from another Word document.
    4. Click this button to load the text into the example window (item 6) using the text for the specified patent number or a publication number.
    5. Click this button to clear the example/context window.


Reviewing/editing GPT output

This tab shows the results returned by GPT service based on the provided prompt or any returned error messages, if any. You can make further text modifications to the results directly in this window.


       


The following options are available from the GPT Output window:


    1. This text field shows the results returned by GPT service based on the provided prompt or any returned error messages. You can make further text modifications to the results directly in this window 


    1. Click this button to see the differences between the text passed to GPT and the output text produced by GPT.  This is a very helpful feature to pick up on any subtle differences between GPT input and output.



    1. Press this button if you like the results produced by the specific GPT prompt. It will allow you to turn this prompt and associated instructions/example into a template prompt within ClaimMaster.


    1. Specify whether you want to insert the output of GPT for a particular section in the document (e.g., "Title", "Background", etc.)



    1. Press this button to insert the contents of the preview window (item 16) into the open Word document at the location of the cursor in the document.