DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This Office Action is in response to correspondence filed 30 July 2024 in reference to application 18/788,677. Claims 1-20 are pending and have been examined.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1, 8, and 15 recite receiving a digital file having an image with text; parsing the text in the digital file; segmenting the text into data chunks; creating vector embeddings of the chunks; feeding a first chunk and corresponding vector embeddings into a first large language model (“LLM”), wherein the first LLM outputs a classification of the first chunk; inserting the first data chunk into a first prompt template corresponding to the classification; feeding the first prompt template into a second LLM that outputs a string with data, the data in the string being based on the first prompt template; and rendering the data in the string in a GUI.
The limitation of receiving a digital file having an image with text, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting “a non-transitory computer readable medium” in claim 8, and “a memory” and “a hardware-based processor” in claim 15, nothing in the claim element precludes the step from practically being performed in the mind. For example, but for the “by a processor” language, “receiving” in the context of this claim encompasses a person viewing a file off of a computer screen that has images with text.
The limitation of parsing the text in the digital file, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for the generic computer components, “parsing” in the context of this claim encompasses a person reading and understanding the text.
The limitation of segmenting the text into data chunks, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for the generic computer components, “segmenting” in the context of this claim encompasses a person dividing the text into sections.
The limitation of creating vector embeddings of the chunks, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for the generic computer components, “creating” in the context of this claim encompasses a person assigning numbers to represent information about the text chunk.
The limitation of feeding a first chunk and corresponding vector embeddings into a first large language model (“LLM”), wherein the first LLM outputs a classification of the first chunk, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for the generic computer components, “feeding” in the context of this claim encompasses a person using the interface of an LLM to provide a text chunk, its corresponding embedding, and a prompt to the LLM and reading the classification output by the LLM.
The limitation of inserting the first data chunk into a first prompt template corresponding to the classification, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for the generic computer components, “inserting” in the context of this claim encompasses a person writing a prompt using a template that corresponds to the classification and including the chunk.
The limitation of feeding the first prompt template into a second LLM that outputs a string with data, the data in the string being based on the first prompt template, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for the generic computer components, “feeding” in the context of this claim encompasses a person inputting the prompt into an interface of LLM and reading the string that is generated.
The limitation of rendering the data in the string in a GUI, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for the generic computer components, “rendering” in the context of this claim encompasses a person typing the string into a GUI. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claims recite an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claims only additionally recite “a non-transitory computer readable medium” in claim 8, and “a memory” and “a hardware-based processor” in claim 15. These components are recited at a high-level of generality such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of using computer components amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are not patent eligible.
Claims 2, 9, and 16 further recite identifying the text from the digital file using optical character recognition; and converting the identified text to a machine-readable format. However these steps are basic data gathering steps which is an extra-solutional activity which does not provide a practical application or amount to significantly more than the abstract idea. Therefore these claims are not patent eligible.
Claims 3, 10, and 17 further recite wherein the text is segmented into chunks based on relative locations of the text in the digital file. However a person could segment text into chunks based on locations in the text file. Similar to above, no additional limitations are recited that provide a practical application or amount to significantly more than the abstract idea itself. These claims are not patent eligible.
Claims 4, 11, and 18 further identifying a contract document type; retrieving a second prompt template corresponding to the document type; and inserting the first data chunk and corresponding vector embeddings into the second prompt template, wherein the first data chunk is fed into the first LLM using the second prompt template. However a person could “identify” by recognizing a document type, “retrieve” by finding a prompt template corresponding to type, and “insert” by writing out a prompt using the template. Similar to above, no additional limitations are recited that provide a practical application or amount to significantly more than the abstract idea itself. These claims are not patent eligible.
Claims 5, 12, and 19 further converting the string to a JavaScript Object Notation (“JSON”) object; and sending the JSON object to an enterprise resource planning application. However a person could “convert” by writing a JSON object, and “send” by entering the statement into an application interface. Similar to above, no additional limitations are recited that provide a practical application or amount to significantly more than the abstract idea itself. These claims are not patent eligible.
Claims 6, 13, and 20 further recite wherein the classification of the first chunk is one of a Section B clause or a mandatory government clause. However a person can perform the recited steps recited above including these classifications. Similar to above, no additional limitations are recited that provide a practical application or amount to significantly more than the abstract idea itself. These claims are not patent eligible.
Claims 7 and 14 further recite wherein rendering the data in the string in the GUI includes displaying a list of line-items identified in the contract document. However a person can type line-items into a GUI. Similar to above, no additional limitations are recited that provide a practical application or amount to significantly more than the abstract idea itself. These claims are not patent eligible.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-4, 6-11, 13-18 and 20 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Padmashali et al. (US PAP 2025/0148020).
Consider claim 1, Padmashali teaches A method for parsing a contract document (abstract), comprising:
receiving a digital file having an image with text (0045-47, inputting document, 0049, OCR, which indicates image including text);
parsing the text in the digital file (0049, OCR, converting to machine readable format);
segmenting the text into data chunks (0050, segmenting text into meaningful groupings);
creating vector embeddings of the chunks (0057, vector generation for segmented text);
feeding a first chunk and corresponding vector embeddings into a first large language model (“LLM”), wherein the first LLM outputs a classification of the first chunk (0054-55, using machine learning such as OpenAI, an LLM, to identify paragraph types or categories, which would require the vectors in 0057);
inserting the first data chunk into a first prompt template corresponding to the classification (0080, prompts customized for each category and task, using prompts 0081-102);
feeding the first prompt template into a second LLM that outputs a string with data, the data in the string being based on the first prompt template (0081-102, feeding prompts to LLMs and chunks to generate strings, see for example 0097-0102 shows string outputs); and
rendering the data in the string in a GUI (figure 9, 0185-86, displaying key summary points in GUI).
Consider claim 2, Padmashali teaches the method of claim 1, wherein parsing the text comprises:
identifying the text from the digital file using optical character recognition (0049, OCR); and
converting the identified text to a machine-readable format (0049, converting to machine readable format).
Consider claim 3, Padmashali teaches the method of claim 1, wherein the text is segmented into chunks based on relative locations of the text in the digital file (0051, segments may be divided based on formatting or location within document).
Consider claim 4, Padmashali teaches the method of claim 1, further comprising:
identifying a contract document type (0047, detecting document type, such a real estate contract or NDA);
retrieving a second prompt template corresponding to the document type (0080, prompts customized for each category and task in including document categories); and
inserting the first data chunk and corresponding vector embeddings into the second prompt template, wherein the first data chunk is fed into the first LLM using the second prompt template (0054-55, using machine learning such as OpenAI, an LLM, to identify paragraph types or categories, which require a prompt).
Consider claim 6, Padmashali teaches The method of claim 1, wherein the classification of the first chunk is one of a Section B clause or a mandatory government clause (0047, document may be real estate agreement, 0054 classifying chunks of the document, real estate agreements are known to have government mandated disclosures (lead paint, etc.). Also, see figure 9, where state law is explicitly extracted).
Consider claim 7, Padmashali teaches the method of claim 1, wherein rendering the data in the string in the GUI includes displaying a list of line-items identified in the contract document (figure 9, list of line items in right column).
Consider claim 8, Padmashali teaches a non-transitory, computer-readable medium containing instructions that, when executed by a hardware-based processor, causes the processor to perform stages for providing a GUI for representing tunnels and stretched networks in a virtual entity pathway virtualization (0396, CRM, 00331-34, memory, processors), the stages comprising:
receiving a digital file having an image with text (0045-47, inputting document, 0049, OCR, which indicates image including text);
parsing the text in the digital file (0049, OCR, converting to machine readable format);
segmenting the text into data chunks (0050, segmenting text into meaningful groupings);
creating vector embeddings of the chunks (0057, vector generation for segmented text);
feeding a first chunk and corresponding vector embeddings into a first large language model (“LLM”), wherein the first LLM outputs a classification of the first chunk (0054-55, using machine learning such as OpenAI, an LLM, to identify paragraph types or categories, which would require the vectors in 0057);
inserting the first data chunk into a first prompt template corresponding to the classification (0080, prompts customized for each category and task, using prompts 0081-102);
feeding the first prompt template into a second LLM that outputs a string with data, the data in the string being based on the first prompt template (0081-102, feeding prompts to LLMs and chunks to generate strings, see for example 0097-0102 shows string outputs); and
rendering the data in the string in a GUI (figure 9, 0185-86, displaying key summary points in GUI).
Claim 9 contains similar limitations as claim 2 and is therefore rejected for the same reasons.
Claim 10 contains similar limitations as claim 3 and is therefore rejected for the same reasons.
Claim 11 contains similar limitations as claim 4 and is therefore rejected for the same reasons.
Claim 13 contains similar limitations as claim 6 and is therefore rejected for the same reasons.
Claim 14 contains similar limitations as claim 7 and is therefore rejected for the same reasons.
Consider claim 15, Padmashali teaches a system for parsing a contract document (abstract), comprising:
a memory storage including a non-transitory, computer-readable medium comprising instructions (00331-34, memory); and
a hardware-based processor that executes the instructions to carry out stages comprising: (00331-34, processors), the stages comprising:
receiving a digital file having an image with text (0045-47, inputting document, 0049, OCR, which indicates image including text);
parsing the text in the digital file (0049, OCR, converting to machine readable format);
segmenting the text into data chunks (0050, segmenting text into meaningful groupings);
creating vector embeddings of the chunks (0057, vector generation for segmented text);
feeding a first chunk and corresponding vector embeddings into a first large language model (“LLM”), wherein the first LLM outputs a classification of the first chunk (0054-55, using machine learning such as OpenAI, an LLM, to identify paragraph types or categories, which would require the vectors in 0057);
inserting the first data chunk into a first prompt template corresponding to the classification (0080, prompts customized for each category and task, using prompts 0081-102);
feeding the first prompt template into a second LLM that outputs a string with data, the data in the string being based on the first prompt template (0081-102, feeding prompts to LLMs and chunks to generate strings, see for example 0097-0102 shows string outputs); and
rendering the data in the string in a GUI (figure 9, 0185-86, displaying key summary points in GUI).
Claim 16 contains similar limitations as claim 2 and is therefore rejected for the same reasons.
Claim 17 contains similar limitations as claim 3 and is therefore rejected for the same reasons.
Claim 18 contains similar limitations as claim 4 and is therefore rejected for the same reasons.
Claim 20 contains similar limitations as claim 6 and is therefore rejected for the same reasons.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 5, 12, and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Padmashali in view of Ahmad et al. (US PAP 20205/0217799).
Consider claim 5, Padmashali teaches the method of claim 1, further comprising:
converting the string to a JavaScript Object Notation (“JSON”) object (0134, generating JSON statements from key points in documents); but does not specifically teach
sending the JSON object to an enterprise resource planning application.
In the same field machine learning, Ahmad teaches ending the JSON object to an enterprise resource planning application (0139 JSON may be sent to enterprise resource planning systems).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to send JSON to ERP applications as taught by Ahmad in the system of Padmashali in order to streamline processing of document data (Ahmad 0139).
Claim 12 contains similar limitations as claim 5 and is therefore rejected for the same reasons.
Claim 19 contains similar limitations as claim 5 and is therefore rejected for the same reasons.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Pidilla et al. (US PAP 2025/0191480) and Sinha et al. (US PAP 2025/0156639) teach similar methods of document analysis.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DOUGLAS C GODBOLD whose telephone number is (571)270-1451. The examiner can normally be reached 6:30am-5pm Monday-Thursday.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Flanders can be reached at (571)272-7516. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
DOUGLAS GODBOLD
Examiner
Art Unit 2655
/DOUGLAS GODBOLD/ Primary Examiner, Art Unit 2655