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 .
Claim Objections
Claim 9 is objected to because of the following informalities:
“an medical history” should be --a medical history--.
Appropriate correction is required.
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) 1-6 and 9-17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chintagunta et al. (PGPUB 20240029714), hereinafter referenced as Chinagunta in view of Henandez (PGPUB 2021/0409544).
Regarding claims 1 and 9, Chintagunta discloses a method for artificially intelligent medical history interview evaluation, comprising:
a capture device configured to capture information a medical history evaluation interview between a patient and a medical provider (audio input; p. 0216);
an evaluation device having at least one processor and memory storing non-transitory executable instructions that (processor and memory; p. 0207-0208), when executed by the processor controlling:
receiving captured data of a medical history evaluation interview between a patient and a medical provider (medical professional and patient conversations including the history taking portion of the dialog by gathering the patient’s history of present illness; p. 0031-0032, 0038);
transcribing audio of the captured data into transcribed text (converting digital speech signal to a text; p. 0203-0204);
segmenting the transcribed text into segmented lines according to a speaker of the transcribed text within the audio (separates turns using a token; p. 0176);
generating a plurality of prompts, each prompt corresponding to one of a plurality of interview analysis variables (labels such as medical conversation, history, health plan, empathy, etc.; p. 0029-0037), to control a large language model (LLM) to analyze each of the segmented lines in context of the transcribed text (discretizes medical dialog processing into several smaller dialogue processing into several smaller dialogue understanding tasks, dynamically constructs few shot prompts for those tasks and uses GPT-3 or GPT-4; p. 0030, 0177 and extracts medical entities from the conversation one provider and one patient at a time and uses those extractions as additional contextual input and uses prompt chaining and in context examples p. 0178-0182);
transmitting the plurality of prompts to the LLM (constructs prompts supplied to GPT-3 or GPT-4 including dynamically constructed few shot prompts; p. 0177)
receiving LLM responses from the LLM for each of the plurality of prompts (GPT generated outputs from the multiple dialog understanding prompting tasks are subsequently used in processing; p. 0177, 0188), but does not specifically teach analyzing the LLM responses with respect to a scoring rubric and generating a detail report defining performance of the medical provider during interaction between the patient and the medical provider.
Hernandez discloses a method determining which person spoke each word and generates separate customer transcripts comprising:
analyzing the LLM responses with respect to a scoring rubric (evaluates a transcript information under multiple predefined performance criteria and generates separate scores; p. 0029-0031); and
generating a detail report defining performance of the medical provider during interaction between the patient and the medical provider (generates an evaluation of the representative’s performance, gives individual scores and a total score, identifies positive/negative language and specific behavioral occurrences; p. 0019, 0031), to assist with evaluating speech.
Therefore, it would have been obvious to one of ordinary skill of the art, before the effective filing date of the claimed invention, to modify the method as described above, to provide an objective and detailed evaluation of the professional’s performance during the interaction and identify aspects of the professional’s communication that warrant improvement.
Regarding claims 2 and 13, Chintagunta discloses a method comprising the plurality of interview analysis variables each defining analysis parameters for the LLM (labels such as medical conversation, history, health plan, empathy, etc.; p. 0029-0037).
Regarding claim 3, Chintagunta discloses a method further comprising transmitting one or more settings, respectively defined for each of the plurality of interview analysis variables, to the LLM to configure the LLM to analyze the segmented line in context with the transcribed text (converting digital speech signal to a text and separate turns; p. 0176, 0203-0204).
Regarding claims 4 and 15, Chintagunta discloses a method wherein transmitting the prompts to the LLM includes transmitting at least two of the prompts in parallel to at least two different instances of the LLM (parallel corpus with pairs of dialog turn; p. 0107).
Regarding claims 5 and 16, Chintagunta discloses a method the generating a plurality of prompts comprises generating a prompt for a binary analysis of one or more of the plurality of interview analysis variables (Table 3).
Regarding claims 6 and 17, Chintagunta discloses a method the generating a plurality of prompts comprises generating a prompt for a scaled analysis of one or more of the plurality of interview analysis variables (scale; p. 0030, 0126, Table 5).
Regarding claim 10, Chintagunta discloses a method wherein the patient is a virtual patient, and the capture device is a component of a virtual training device (virtual services; p. 0038).
Regarding claim 11, Chintagunta discloses a method wherein the LLM operating on a processing device, or a group of processing devices, of the evaluation device (p. 0102, 0208, 0221).
Regarding claim 12, interpreted and rejected for similar reasons as set forth above. In addition, Hernandez discloses a method wherein the LLM is executed remotely from the evaluation device (customer and representative communicating through separate telecommunications devices over a communication network such cellular networks, Internet; p. 0022).
Regarding claim 14, Chintagunta discloses a method the non-transitory executable instructions further comprising non-transitory executable instructions that, when executed by the processor operate to control the evaluation device to transmit one or more settings, respectively defined for each of the plurality of interview analysis variables, to the LLM to configure the LLM to analyze the segmented line in context with the transcribed text (converting digital speech signal to a text and separates turns; p. 0176, 0203-0204).
Claim(s) 7 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chintagunta in view of Hernandez and in further view of Krabach et al. (PGPUB 2025/0077795), hereinafter referenced as Krabach.
Regarding claims 7 and 18, Chintagunta in view of Hernandez disclose a method as described above, but does not specifically teach a method the generating a prompt for a scaled analysis comprises:
generating a first scaled-response prompt including the segmented line;
generating a second scaled-response prompt associated with the first scaled-response prompt querying the LLM to provide an example of a low-scoring end of a scale;
generating a third scaled-response prompt associated with the first and second scaled-response prompts querying the LLM to provide an example of a high-scoring end of the scale; and
generating a fourth scaled-response prompt associated with the first, second, and third scaled-response prompts querying the LLM to provide a rating on a given scale.
Krabach discloses a method comprising:
generating a first scaled-response prompt including the segmented line (scale of 1 to 5; p. 0015-0020, 0024, 0038-0043);
generating a second scaled-response prompt associated with the first scaled-response prompt querying the LLM to provide an example of a low-scoring end of a scale (multiple prompts forming an interaction history; p. 0015);
generating a third scaled-response prompt associated with the first and second scaled-response prompts querying the LLM to provide an example of a high-scoring end of the scale (previous prompts can provide context to subsequent prompts; p. 0015, 0041, 0047-0048); and
generating a fourth scaled-response prompt associated with the first, second, and third scaled-response prompts querying the LLM to provide a rating on a given scale (the system evaluates characteristics and generates numerical classifications; p. 0015-0020, 0024, 0038-0043), to provide a standardized and quantifiable assessment.
Therefore, it would have been obvious to one of ordinary skill of the art, before the effective filing date of the claimed invention, to modify the method as described above, to assist with satisfying a predetermined evaluation characteristic.
Claim(s) 8 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chintagunta in view of Hernandez and Krabach and in further view of Krishnamurthy et al. (PGPUB 2025/0111237), hereinafter referenced as Krishnamurthy.
Regarding claims 8 and 19, it is interpreted and rejected for similar reasons as set forth above, however, the prior art cited fails to teach the claims in combination wherein the rating is a cosine similarity analysis between LLM responses associated with the first, second, and third scaled-response prompts.
Krishnamurthy discloses a method comprising rating is a cosine similarity analysis between LLM responses associated with the first, second, and third scaled-response prompts (p. 0036), to provide a quantitative measure of sematic similarity and dissimilarity.
Therefore, it would have been obvious to one of ordinary skill of the art, before the effective filing date of the claimed invention, to modify the method as described above, to thereby facilitate objective evaluation and comparison of the responses.
Claim(s) 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chintagunta in view of Hernandez and in further view of Correia Gracio et al. (PGPUB 2018/0165979), hereinafter referenced as Correia Gracio.
Regarding claim 20, it is interpreted and rejected for similar reasons as set forth above, but does not specifically teach a method comprising receiving captured data of a debriefing dialog for a scenario-based medical simulation.
Correia Gracio discloses a method comprising receiving captured data of a debriefing dialog for a scenario-based medical simulation (p. 0032-0035, 0042), to provide an objective assessment.
Therefore, it would have been obvious to one of ordinary skill of the art, before the effective filing date of the claimed invention, to modify the method as described above, to identify areas of performance warranting discussion or improvement during debriefing.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. This information has been detailed in the PTO 892 attached (Notice of References Cited).
Sorkey et al. discloses medical transcription with dynamic language models.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JAKIEDA R JACKSON whose telephone number is (571)272-7619. The examiner can normally be reached Mon - Fri 6:30a-2:30p.
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, Daniel Washburn can be reached at 571.272.5551. 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.
/JAKIEDA R JACKSON/Primary Examiner, Art Unit 2657
Prosecution Insights