Patent Application 18317623 - SYSTEMS AND METHODS FOR PROVIDING USER

Title: SYSTEMS AND METHODS FOR PROVIDING USER INTERFACES TO CONVERSE WITH A CORPUS OF ELECTRONIC DOCUMENTS VIA A LARGE LANGUAGE MODEL
Application Information

Invention Title: SYSTEMS AND METHODS FOR PROVIDING USER INTERFACES TO CONVERSE WITH A CORPUS OF ELECTRONIC DOCUMENTS VIA A LARGE LANGUAGE MODEL
Application Number: 18317623
Submission Date: 2025-05-15T00:00:00.000Z
Effective Filing Date: 2023-05-15T00:00:00.000Z
Filing Date: 2023-05-15T00:00:00.000Z
National Class: 704
National Sub-Class: 009000
Examiner Employee Number: 99230
Art Unit: 2654
Tech Center: 2600
Rejection Summary

102 Rejections: 0
103 Rejections: 2
Cited Patents

No patents were cited in this rejection.
Office Action Text



    DETAILED ACTION
This office action is in response to Applicant’s submission filed on 5/15/2023. Claims 1-20 are pending in the application. As such, claims 1-20 have been examined.
	
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 .

Information Disclosure Statement
The information disclosure statements (IDS) were submitted on 6/08/2023, 10/09/2023, 12/09/2023, and 6/05/2024.  The submission is in compliance with the provisions of 37 CFR 1.97.  Accordingly, the information disclosure statement is being considered by the examiner.

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.


Claims 1-8, 10, 11-18, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Mukherjee et al. (US 20240354436 A1; hereinafter referred to as Mukherjee) in view of Russell et al. (US 20240296295 A1; hereinafter referred to as Russell).
Regarding claim 1, Mukherjee teaches: a system configured for providing user interfaces to converse with a corpus of electronic documents via a large language model, wherein the large language model has been trained on at least a million documents, wherein the large language model includes a neural network using over a billion parameters and/or weights ([0121] the system may swap the LLM 130 using other LLMs (e.g., switching between GPT-3 to GPT-4) for generating answers based on user queries. GPT3 was trained on 45TB of text data and has about 175 billion parameters.), the system comprising: one or more hardware processors configured by machine-readable instructions to: effectuate a presentation of a first user interface, the first user interface being configured to obtain entry of user input from a user ([0009] various embodiments rely on detection of user inputs via graphical user interfaces, calculation of updates to displayed electronic data based on those user inputs,) to: (i) select one or more documents to be provided as input to a large language model for a particular conversation between the user and the one or more documents, wherein the one or more documents form the corpus of electronic documents ([0077] the document prompt module 110 is configured to generate a prompt to a language model, such as LLM 130a. As described in further detail below, the document prompt module 110 may generate such a prompt based on data provided by the user interface module 104 (e.g., a user input or a user query) and/or other modules (e.g., one or more document portions that are more relevant or similar to the user query identified by the document search module 106) of the document search system 102),
(ii) enter queries regarding the one or more documents that have been selected ([0078] The document source 120 is configured to store data and/or documents that may be queried by the user 150 and/or various aspects of the document search system 102, where the stored data and/or documents may be obtained by the document search system 102), 
and (iii) navigate between a set of different portions of the first user interface ([0013] the interactive and dynamic user interfaces described herein are enabled by innovations in efficient interactions between the user interfaces and underlying systems and components), wherein the set of different portions includes: (a) a first portion configured to select, by the user, an individual conversation from a set of conversations, wherein the set of conversations includes the particular conversation ([0066] Context may include all or part of a conversation history from one or more sessions with the user (e.g., a sequence of user prompts and/or user selections (e.g., via a point and click interface or other graphical user interface). Thus, context may include one or more of: previous analyses performed by the system, previous prompts provided by the user, previous conversation of the user with the language model, a role of the user, a context associated with a user input, a user question, or a user query, and/or other contextual information. Different sessions can indicate different conversations.), (b) a second portion configured to enter, by the user, an individual query and present, to the user, an individual reply to the individual query ([0102] In various examples, a user query may be a natural language query, and the document search system 102 is expected to return a natural language output responsive to the natural language query), and (d) the fourth portion configured to present, to the user, the individual document as either (1) selected in the third portion or (2) determined to be relevant to the individual reply ([0148] the user interface 700 further shows a button 710 and a button 706 under the message portion 716. The button 710, if pressed by the user 150, may allow the user 150 to preview documents based on which the LLM 130 answers a user query from the user 150. The user 150 may press the button 706 to view a graphical representation of an output from the LLM 130);
responsive to selection of the individual conversation, provide the individual query as a prompt to the large language model ([0013] the system (and related processes, functionality, and interactive graphical user interfaces), can advantageously generate a prompt for the LLMs using a user query and portions of a set of documents that are more relevant or bear similarity to the user query);
obtain the individual reply from the large language model, wherein the individual reply is presented in the second portion of the first user interface ([0150] FIG. 8 shows an example user interface 800 that may receive a user query from the user 150 and provide an answer in response to the user query);
determine the individual document from the one or more documents that is relevant to the individual reply ([0087] the document search module 106 may execute a similarity search between the query vector and the plurality of vectors to identify one or more documents portions that are more relevant or similar to the user input from the user 150);
and present the individual document in the fourth portion of the first user interface ([0153] Although not illustrated in the user interface 800, other document tiles and/or document contents that may be similar to the user query from the user 150 and/or utilized by the LLM 130 to provide the answer in the message portion 806 may also be displayed through the user interface 800. In various implementations, the user interface 800 may display n most similar portions of a set of documents for the user 150 to preview, where n being any positive integer).
Mukherjee does not explicitly, but Russell discloses: (c) a third portion configured to select, by the user, an individual document from the one or more documents for presentation in a fourth portion ([0090] receiving a selection of the source identifier; and in response to receiving the selection, causing a display of the source document positioned to show the asserted quote).
 Mukherjee and Russell are considered analogous in the field of large language models. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Mukherjee to combine the teachings of Russell because doing so would reduce the generation of inaccurate information by the LLM and provide an interface for viewing the relevant information from a document (Russell [0003] the output from the LLM is parsed to identify asserted quotes from within the output. A query is then performed against the source document to determine if the identified quotes are actually supported by the document. Visual indicia may then be included with the output of the LLM to indicate the reliability of the output from the LLM. Links to the portions of the source document may also be provided adjacent the verified quotes to provide direct access to the corresponding portion of the source document. By implementing such improvements in prompt generation and output verification, the overall likelihood of hallucinations is reduced).

Regarding claim 2, Mukherjee in view of Russell teaches: the system of claim 1. Mukherjee further teaches: wherein the second portion is specific to the individual conversation from the set of conversations that has been selected through the first portion of the first user interface ([0046] The system may generate a prompt for a LLM for responding to a user query further based on a context associated with the user query or a user that submitted the user query. Context may include any information associated with a user, user session, or some other characteristics. For example, context may include all or part of a conversation history from one or more sessions with the user).

Regarding claim 3, Mukherjee in view of Russell teaches: the system of claim 1. Russell further teaches: wherein the second portion presents modifications to the corpus of electronic documents ([0023] As depicted, the AV application 112 includes a prompt generator 202, an LLM interface 204, and a postprocessor 206. A user may use a productivity application 110 to create, read, and/or edit a source document 222. The source document 222 may be any corpus of data, such as a word processing document, web page, or other types of documents).
Mukherjee and Russell are considered analogous in the field of large language models. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Mukherjee to combine the teachings of Russell because doing so would for users to see if changes were made to a source document and let the system reuse past data if no changes were made (Russell [0080] where the interrogation request is to generate a summary or the document, that summary will not change unless the document changes. Accordingly, rather than having to expend computing resources to reprocess the summarization prompt by the LLM, the summarization results that have been verified may be stored or cached with the corresponding supporting document).

Regarding claim 4, Mukherjee in view of Russell teaches: the system of claim 1. Mukherjee further teaches: wherein the second portion indicates whether the individual query was scoped to a subset of the corpus of electronic documents ([0041] Based on the query vector and the plurality of vectors generated from vectorizing portions (e.g., text chunks) of the set of documents permissioned to the user, the system may execute a similarity search between the query vector and the plurality of vectors to identify one or more documents portions that are more relevant or similar to the user query).

Regarding claim 5, Mukherjee in view of Russell teaches: the system of claim 1. Mukherjee further teaches: wherein the large language model is modeled such that the individual reply is limited in scope to one or more statements that have support in the corpus of electronic documents ([0034] the system can enable natural language searching and response, utilizing the LLM, with references to a large set of documents, without being constrained by a size limit on a prompt for the LLM. rather than providing response that may be generic or prone to hallucination, the LLM may output focused, specific, or on the point responses based on particular information sources not only permissioned to the user but more relevant to the user query).

Regarding claim 6, Mukherjee in view of Russell teaches: the system of claim 1. Mukherjee further teaches: wherein the large language model is based on Generative Pre-trained Transformer 3 (GPT3) ([0121] the system may swap the LLM 130 using other LLMs (e.g., switching between GPT-3 to GPT-4) for generating answers based on user queries.).

Regarding claim 7, Mukherjee in view of Russell teaches: the system of claim 1. Mukherjee further teaches: wherein the large language model is derived from Generative Pre-trained Transformer 3 (GPT3) or a successor of Generative Pre-trained Transformer 3 (GPT3) ([0121] the system may swap the LLM 130 using other LLMs (e.g., switching between GPT-3 to GPT-4) for generating answers based on user queries). 

Regarding claim 8, Mukherjee in view of Russell teaches: the system of claim 1. Mukherjee further teaches: wherein the individual reply is formatted for presentation based on the individual query ([0056] the system may employ an LLM, via providing an input (e.g., a user query) to, and receiving an output (e.g., an answer to the user query) from, the LLM. The output from the LLM may be parsed and/or a format of the output may be updated to be usable for various aspects of the system).

Regarding claim 10, Mukherjee in view of Russell teaches: the system of claim 1. Mukherjee further teaches: wherein at least some parts of the first portion, the second portion, the third portion, and the fourth portion are presented to the user at the same time ([0048] interact with the system through a user interface (e.g., a graphical user interface (“GUI”) or other types of user interfaces), and receive a user query for a LLM or provide output from the LLM. In various implementations, in addition to providing the output from the LLM, the system may provide through the user interface the portions of a set of documents similar to the user query for a user to preview such that the user may have a better understanding about the basis of the output from the LLM. Also see Fig. 7 and 8.).

Regarding claim 11, it recites similar limitations as claim 1 and therefore is rejected similarly.

Regarding claim 12, it recites similar limitations as claim 2 and therefore is rejected similarly.

Regarding claim 13, it recites similar limitations as claim 3 and therefore is rejected similarly.

Regarding claim 14, it recites similar limitations as claim 4 and therefore is rejected similarly.

Regarding claim 15, it recites similar limitations as claim 5 and therefore is rejected similarly.

Regarding claim 16, it recites similar limitations as claim 6 and therefore is rejected similarly.

Regarding claim 17, it recites similar limitations as claim 7 and therefore is rejected similarly.

Regarding claim 18, it recites similar limitations as claim 8 and therefore is rejected similarly.

Regarding claim 20, it recites similar limitations as claim 10 and therefore is rejected similarly.

Claims 9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Mukherjee in view of Russell and in further view of Dang et al. (US 20240070489 A1; hereinafter referred to as Dang).
Regarding claim 9, Mukherjee in view of Russell teaches: the system of claim 1. Mukherjee in view of Russell does not explicitly, but Dang teaches: wherein a segment in the individual document that is relevant to the individual reply is emphasized in the fourth portion of the first user interface ([0055] Such a representation can enable a client device to find and highlight (e.g., make bold) an answer within a display of the text document or a portion thereof. In some implementations, the display can link to the full-text document and only include a portion of the document near the answer (as represented by start, length, or end offsets)). 
Mukherjee, Russell, and Dang are considered analogous in the field of text processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Mukherjee and Russell to combine the teachings of Dang because doing so would provide better responses to user queries and improve the UI experience (Dang [0059] client device can provide user interface (UI) elements (e.g., thumbs up, thumbs down) to allow a user to provide an explicitly positive or negative interaction. The client device can transmit data representing these interactions back to the server, which can then use the data to improve the mapping of queries to questions or the underlying question-answer generating model (discussed in FIG. 3)).

Regarding claim 19, it recites similar limitations as claim 9 and therefore is rejected similarly.
	

Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Andreica et al. (US 20190005138 A1) – discloses searching a corpus of online documents in order to respond and answer a user query.
He et al. (US 20240362286 A1) – discloses using an LLM to search a set of electronic documents and retrieve relevant summarization results.

Any inquiry concerning this communication or earlier communications from the examiner should be directed to Nathan Tengbumroong whose telephone number is (703)756-1725. The examiner can normally be reached Monday - Friday, 11:30 am - 8:00 pm EST.
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, Hai Phan can be reached at 571-272-6338. 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.





/NATHAN TENGBUMROONG/Examiner, Art Unit 2654                       

/HAI PHAN/Supervisory Patent Examiner, Art Unit 2654