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 is response to application filed 06/18/2025.
Status of the claims
Claims 1-21 are currently pending for examination.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 07/08/2025 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 1-21 are rejected under 35 U.S.C. 103 as being unpatentable over Bell et al. (US 20240406166, hereafter Bell) in view of Hudetz et al. (US 20240370479, hereafter Hudetz).
Regarding claim 1, Bell discloses: A test and measurement instrument, comprising: one or more memories (Bell [0182]); a generative artificial intelligence (AI) model having access to the one or more memories (Bell [0184]);
a display;
user controls to allow a user to provide inputs (Bell [0184]); and
one or more processors configured to execute that code that causes the one or more processors to (Bell [0182]):
access an application programming interface (API) of an AI assistant for the generative AI model to allow the user to interact with the AI assistant (Bell [0170; 0180; 0181] discloses: a user prompt is received at an API with instructions to retrieve snippets and then present them to an AI component responsive to a user prompt);
receive one or more user inputs through one or more of the API or a user interface, the user inputs comprising a prompt (Bell [0170; 180;0181] discloses: a user prompt is received at an API with instructions to retrieve snippets and then present them to an AI component responsive to a user prompt);
access a master vector database using the prompt to retrieve a list of master candidates (Bell [0164] discloses: a set of candidate portions are identified and ranked in terms of relevance to the medical condition relative to each other and the top X number of candidate portions are selected for retrieval;[0157] discloses: vectors in a vector database; [0197] discloses: portions of the electronic document containing the candidate document vectors);
Bell didn’t disclose, but Hudetz discloses: compare the prompt to the list of master candidates to identify selected ones of the master candidates (Hudetz [0215] discloses: retrieves a set of candidate document vectors that are semantically similar to the search vector from a document index of contextualized embeddings for the electronic document. For example, the search manager 124 may perform a semantic search on the document index 730 of document vectors 726 stored in the database 708, and retrieve a set of candidate document vectors 718 that are semantically similar to the search vector);
send the selected ones of the master candidates to a vector database (Hudetz [0211] discloses: stores the document index with the document vectors in a database. For example, the search manager 124 may store the document index 730 with the document vectors 726 in a database 708 );
receive specific candidates from the vector database (Hudetz [0194] discloses: use the search vector to search the database 708 to produce search results 146. The search manager 124 may generate a NLG request with the search query 144 and some or all of the candidate document vectors 718 from the search results 146) ;
send the prompt and the specific candidates to the generative AI model (Hudetz [0134; 0159] discloses: The search manager 124 may prepare a prompt with both the search query 144 and some or all of the search results 146 (e.g., the top k sections) from the electronic document 706, and send it to the generative AI model 728);
receive a response from the generative AI model (Hudetz [0159] discloses: The generative AI model 728 uses a large language module (LLM) to assist in summarizing the search results 146 to produce an Abstractive summary 148. The generative AI may provide an Abstractive summary 148 of the search results 146 relevant to a given search query 144); and
display the response on the display (Hudetz [0134] discloses: the search results 146 in a graphical user interface (GUI) of a client device).
Bell and Hudetz are analogous art because they are in the same field of endeavor, for an artificial intelligence (AI) platform to search a document collection. It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Bell, to include the teaching of Hudetz, in order to implement various artificial intelligence (AI) techniques to improve searching for information in one or more electronic documents managed by an electronic document management system. The suggestion/motivation to combine is to improve searching for information from a document corpus of electronic documents.
Regarding claim 2, Bell as modified discloses: The test and measurement instrument as claimed in claim 1, wherein the code that causes the one or more processors to access the master vector database comprises code that causes the one or more processors to access the master vector database based upon explicit information (Bell [0275] discloses: the user identifier is checked against the access control lists to determine what data the user is authorized to access; [0068] discloses: client device such as accelerometers, gyroscopes, other sensors/devices for sensing and measuring various environmental conditions).
Regarding claim 3 Bell as modified discloses: The test and measurement instrument as claimed in claim 2, wherein the explicit information comprises at least one of information from a query of the test and measurement instrument, information from the prompt, licenses associated with the test and measurement instrument, and user context information (Bell [0275] discloses: the user identifier is checked against the access control lists to determine what data the user is authorized to access; [0068] discloses: client device such as accelerometers, gyroscopes, other sensors/devices for sensing and measuring various environmental conditions).
Regarding claim 4, Bell as modified discloses: The test and measurement instrument as claimed in claim 1, wherein the code that causes one or more processors to access the master vector database comprises code that causes the one or more processors to access the master vector database based upon implicit information (Bell query vector database in response to natural language inputs).
Regarding claim 5, Bell as modified discloses: The test and measurement instrument as claimed in claim 4, wherein the implicit information comprises at least one of instruments connected to the test and measurement instrument, input/output usages, and features of the test and measurement instrument (Bell [0069] discloses: input/output devices).
Regarding claim 6, Bell as modified discloses: The test and measurement instrument as claimed in claim 1, wherein the code that causes the one or more processors to identify specific candidates comprises code that causes the one or more processors to identify specific candidates based upon characteristics of the user, the characteristics including one or more of user security clearance, user system access privileges, user license status, user role, and user location (Bell [0130; 0131] discloses: user access token to authenticate).
Regarding claim 7, Bell as modified discloses: The test and measurement instrument as claimed in claim 1, wherein the code that causes the one or more processors to identify specific candidates comprises code that causes the one or more processors to identify specific candidates based upon external factors, the external factors including one or more of an instrument being used, applicable regulations, software applications being used, and licenses relating to the software applications (Bell [0132] discloses: The authentication request tool may include the following parameters: name, description, base URL, and/or input parameters (e.g., specifiable by the agent). For example, an example authentication request tool may have an order identifier as an input parameter).
Regarding claim 8, Bell as modified discloses: The test and measurement instrument as claimed in claim 1, wherein at least one of the master vector database and the generative AI model reside locally to the test and measurement instrument (Hudetz [0085] discloses: a generative AI locally on the server device 102).
Regarding claim 9, Bell as modified discloses: The test and measurement instrument as claimed in claim 1, wherein the one or more processors are further configured to identify and package knowledge sets for sale (Hudetz [0117] discloses: The RNN learning algorithms are primarily leveraged when using time-series data to make predictions about future outcomes, such as stock market predictions or sales forecasting).
Regarding claim 10, Bell as modified discloses: The test and measurement instrument as claimed in claim 1, wherein the one or more processors are further configured to execute code to cause the one or more processors to meter usage of knowledge sets for billing (Hudetz [0044] discloses: identifying payment terms or terms of conditions) .
Regarding claim 11, Bell as modified discloses: The test and measurement instrument as claimed in claim 1, wherein the one or more processors are further configured to execute code that causes the one or more processors to use the prompt and the specific candidates in retrieval augmented generation to update the model (Bell [0161] discloses: implementing a retrieval-augmented generative (RAG) approach to identify relevant portions of EHR text, e.g., relevant portions of unstructured clinical notes. A RAG approach proves to be more efficient and effective than providing the model with larger context windows and then feeding the retrieved documents into a model to generate an analysis and response).
Regarding claim 12, Garg discloses: A method of identifying and selecting knowledge sets for use with a generative AI model, comprising:
accessing an application programming interface (API) of an AI assistant for the generative AI model to allow a user to interact with the AI assistant(Bell [0170; 0180; 0181] discloses: a user prompt is received at an API with instructions to retrieve snippets and then present them to an AI component responsive to a user prompt);
receiving one or more user inputs through one or more of the API or a user interface, the user inputs comprising a prompt (Bell [0170; 180;0181] discloses: a user prompt is received at an API with instructions to retrieve snippets and then present them to an AI component responsive to a user prompt);
accessing a master vector database using the prompt to retrieve a list of master candidates (Bell [0164] discloses: a set of candidate portions are identified and ranked in terms of relevance to the medical condition relative to each other and the top X number of candidate portions are selected for retrieval;[0157] discloses: vectors in a vector database; [0197] discloses: portions of the electronic document containing the candidate document vectors);
Bell didn’t disclose, but Hudetz discloses: comparing the prompt to the list of master candidates to select ones of the master candidates (Hudetz [0215] discloses: retrieves a set of candidate document vectors that are semantically similar to the search vector from a document index of contextualized embeddings for the electronic document. For example, the search manager 124 may perform a semantic search on the document index 730 of document vectors 726 stored in the database 708, and retrieve a set of candidate document vectors 718 that are semantically similar to the search vector);
sending the select ones of the master candidates and the prompt to a vector database(Hudetz [0211] discloses: stores the document index with the document vectors in a database. For example, the search manager 124 may store the document index 730 with the document vectors 726 in a database 708 );
receiving specific candidates from the vector database(Hudetz [0194] discloses: use the search vector to search the database 708 to produce search results 146. The search manager 124 may generate a NLG request with the search query 144 and some or all of the candidate document vectors 718 from the search results 146) ;
sending the prompt and the specific candidates to the generative AI model (Hudetz [0159] discloses: The generative AI model 728 uses a large language module (LLM) to assist in summarizing the search results 146 to produce an Abstractive summary 148. The generative AI may provide an Abstractive summary 148 of the search results 146 relevant to a given search query 144); receiving a response from the generative AI model; and displaying the response on a display for the user (Hudetz [0134] discloses: the search results 146 in a graphical user interface (GUI) of a client device).
Bell and Hudetz are analogous art because they are in the same field of endeavor, for an artificial intelligence (AI) platform to search a document collection. It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Bell, to include the teaching of Hudetz, in order to implement various artificial intelligence (AI) techniques to improve searching for information in one or more electronic documents managed by an electronic document management system. The suggestion/motivation to combine is to to improve searching for information from a document corpus of electronic documents.
Regarding claim 13, Bell as modified discloses: The method as claimed in claim 12, wherein accessing the master vector database comprises accessing the master vector database based upon explicit information (Bell [0275] discloses: the user identifier is checked against the access control lists to determine what data the user is authorized to access; [0068] discloses: client device such as accelerometers, gyroscopes, other sensors/devices for sensing and measuring various environmental conditions).
Regarding claim 14, Bell as modified discloses: The method as claimed in claim 13, wherein the explicit information comprises at least one of information from a query of a test and measurement instrument, information from the prompt, licenses associated with the test and measurement instrument, and user context information (Bell [0275] discloses: the user identifier is checked against the access control lists to determine what data the user is authorized to access; [0068] discloses: client device such as accelerometers, gyroscopes, other sensors/devices for sensing and measuring various environmental conditions).
Regarding claim 15, Bell as modified discloses: The method as claimed in claim 12, wherein accessing the master vector database comprises accessing the master vector database based upon implicit information (Bell query vector database in response to natural language inputs).
Regarding claim 16, Bell as modified discloses: The method as claimed in claim 15, wherein the implicit information comprises at least one of instruments connected to a test and measurement instrument, input/output usages, and features of the test and measurement instrument (Bell [0069] discloses: input/output devices).
Regarding claim 17, Bell as modified discloses: The method as claimed in claim 12, identifying specific candidates comprises identifying specific candidates based upon characteristics of the user, the characteristics including one or more of user security clearance, user system access privileges, user license status, user role, and user location (Bell [0130; 0131] discloses: user access token to authenticate).
Regarding claim 18, Bell as modified discloses: The method as claimed in claim 12, wherein identifying specific candidates comprises identifying specific candidates based upon external factors, the external factors including one or more of an instrument being used, applicable regulations, software applications being used, and licenses relating to the software applications (Bell [0132] discloses: The authentication request tool may include the following parameters: name, description, base URL, and/or input parameters (e.g., specifiable by the agent). For example, an example authentication request tool may have an order identifier as an input parameter).
Regarding claim 19, Bell as modified discloses: The method as claimed in claim 12, further comprising identifying and packaging knowledge sets for sale (Hudetz [0117] discloses: The RNN learning algorithms are primarily leveraged when using time-series data to make predictions about future outcomes, such as stock market predictions or sales forecasting).
Regarding claim 20, Bell as modified discloses: The method as claimed in claim 12, further comprising metering usage of knowledge sets for billing (Hudetz [0044] discloses: identifying payment terms or terms of conditions) .
Regarding claim 21, Bell as modified discloses: The method as claimed in claim 12, further comprising using the prompt and the specific candidates in retrieval augmented generation to update the generative AI model (Bell [0161] discloses: implementing a retrieval-augmented generative (RAG) approach to identify relevant portions of EHR text, e.g., relevant portions of unstructured clinical notes. A RAG approach proves to be more efficient and effective than providing the model with larger context windows and then feeding the retrieved documents into a model to generate an analysis and response).
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CINDY NGUYEN whose telephone number is (571)272-4025. The examiner can normally be reached M-F 8:00-4:30.
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, Bhatia Ajay can be reached at 571-272-3906. 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.
/CINDY NGUYEN/Examiner, Art Unit 2156
Prosecution Insights