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 .
Status of Amendments
Claims 1-16 and 18-23 are currently pending in this case and have been examined and addressed below. This communication is a Final Rejection in response to the Amendment to the Claims and Remarks filed on 01/26/2026.
Claims 1, 6, 8, 11-12, 15, 18- 19 are amended claims.
Claims 2-3, 7, 9, 13-14, 16, and 20 are original claims.
Claims 21-23 are new claims.
Claims 4-5, 10, and 17 have been cancelled and will not be considered at this time.
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 1-3, 6-9, 11-16, and 18-23 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to a judicial exception (i.e. an abstract idea) without significantly more.
Step 1 – Statutory Categories of Invention:
Claims 1, 8, and 15 are drawn to method, a system, and an article of
manufacture, which are statutory categories of invention.
Step 2A – Judicial Exception Analysis, Prong 1:
Independent claims 1 recites a method comprising obtaining an original dataset to generate a synthetic doctor-patient conversation, the original dataset including data as textual dialogue associated with each of a plurality of individual doctor-patient conversations; constructing input data by performing a named entity recognition operation on the textual dialogue of the original dataset that captures and categorizes named medical entities present in the textual dialogue; generating prepared input data by arranging the input data in an annotated turn-by-turn conversation format using an input data preparation algorithm having various control parameters comprising at least a topics control parameter, an entities control parameter, a speaker control parameter, a remaining turns control parameter, and a context control parameter, wherein each the control parameters of the input data preparation algorithm is associated with a data field containing at least one value, and, for each conversation turn, the data field for the context control parameter comprises a concatenated dialogue of all preceding conversation turns, with an exception of a first conversation turn where the data field for the context control parameter is an empty string; executing a conversation generation control algorithm having control parameters, which are at least partially the same as the control parameters of the input data preparation algorithm, the executing the conversation generation control algorithm including:(a)randomly selecting a disease from a medical knowledge graph and capturing a plurality of symptoms that are mapped to the selected disease; and,(b) constructing a data field for the topics control parameter of the conversation generation control algorithm using the plurality of symptoms,(c) setting a speaker as a value in a value field for the speaker control parameter of the conversation generation control algorithm, wherein an initial speaker among a doctor and a patient is assigned at the first conversation turn and then the value of the value field for the speaker control parameter is alternated between the doctor and the patient for successive conversation turns, (d) setting a number of remaining turns in the value field of the remaining turns control parameter of the conversation generation control algorithm to a positive integer greater than 1,(e) injecting entities, as values into a data field of the entities control parameter of the conversation generation control algorithm at each conversation turn according to probability rules, the injecting including injecting the entities based on a lower probability of occurrence at the first conversation turn and injecting the entities based on different probabilities at subsequent conversation turns based on a presence or an absence of entities in a previous conversation turn,(f) setting context in a data field of the context control parameter of the conversation generation control algorithm for each conversation turn to a concatenation of dialogue from all preceding conversation turns, with an exception of the first conversation turn where the data field is an empty string, and, when a token length for the data field of the context control parameter exceeds a predetermined maximum allowable token length, recursively removing earlier conversation turns one by one from a beginning of context until the token length no longer exceeds the predetermined maximum allowable token length,{g)_causing the trained machine learning model to generate a conversation turn of the turn-by-turn synthetic doctor-patient conversation; the plurality of symptoms, the injected entities, the speaker, the context, and the number of remaining turns,(h) decrementing the number of the remaining turns by 1 after generation of each conversation turn, and(i) repeating (e) to (h) until the number of the remaining turns reaches zero and outputting generated turn-by-turn synthetic doctor-patient conversation, wherein the generated turn-by-turn synthetic doctor-patient conversation.
Independent claim 8 recites a system comprising obtaining an original dataset to generate a synthetic doctor-patient conversation, the original dataset including data as textual dialogue associated with each of a plurality of individual doctor-patient conversations; constructing input data by performing a named entity recognition operation on the textual dialogue of the original dataset that captures and categorizes named medical entities present in the textual dialogue; generating prepared input data by arranging the input data in an annotated turn-by-turn conversation format using an input data preparation algorithm having various control parameters comprising at least a topics control parameter, an entities control parameter, a speaker control parameter, a remaining turns control parameter, and a context control parameter, wherein each the control parameters of the input data preparation algorithm is associated with a data field containing at least one value, and, for each conversation turn, the data field for the context control parameter comprises a concatenated dialogue of all preceding conversation turns, with an exception of a first conversation turn where the data field for the context control parameter is an empty string; executing a conversation generation control algorithm having control parameters, which are at least partially the same as the control parameters of the input data preparation algorithm, the executing the conversation generation control algorithm including:(a)randomly selecting a disease from a medical knowledge graph and capturing a plurality of symptoms that are mapped to the selected disease; and,(b) constructing a data field for the topics control parameter of the conversation generation control algorithm using the plurality of symptoms,(c) setting a speaker as a value in a value field for the speaker control parameter of the conversation generation control algorithm, wherein an initial speaker among a doctor and a patient is assigned at the first conversation turn and then the value of the value field for the speaker control parameter is alternated between the doctor and the patient for successive conversation turns, (d) setting a number of remaining turns in the value field of the remaining turns control parameter of the conversation generation control algorithm to a positive integer greater than 1,(e) injecting entities, as values into a data field of the entities control parameter of the conversation generation control algorithm at each conversation turn according to probability rules, the injecting including injecting the entities based on a lower probability of occurrence at the first conversation turn and injecting the entities based on different probabilities at subsequent conversation turns based on a presence or an absence of entities in a previous conversation turn,(f) setting context in a data field of the context control parameter of the conversation generation control algorithm for each conversation turn to a concatenation of dialogue from all preceding conversation turns, with an exception of the first conversation turn where the data field is an empty string, and, when a token length for the data field of the context control parameter exceeds a predetermined maximum allowable token length, recursively removing earlier conversation turns one by one from a beginning of context until the token length no longer exceeds the predetermined maximum allowable token length,{g)_causing the trained machine learning model to generate a conversation turn of the turn-by-turn synthetic doctor-patient conversation; the plurality of symptoms, the injected entities, the speaker, the context, and the number of remaining turns,(h) decrementing the number of the remaining turns by 1 after generation of each conversation turn, and(i) repeating (e) to (h) until the number of the remaining turns reaches zero and outputting generated turn-by-turn synthetic doctor-patient conversation, wherein the generated turn-by-turn synthetic doctor-patient conversation.
Independent claim 15 recites an article of manufacture comprising obtaining an original dataset to generate a synthetic doctor-patient conversation, the original dataset including data as textual dialogue associated with each of a plurality of individual doctor-patient conversations; constructing input data by performing a named entity recognition operation on the textual dialogue of the original dataset that captures and categorizes named medical entities present in the textual dialogue; generating prepared input data by arranging the input data in an annotated turn-by-turn conversation format using an input data preparation algorithm having various control parameters comprising at least a topics control parameter, an entities control parameter, a speaker control parameter, a remaining turns control parameter, and a context control parameter, wherein each the control parameters of the input data preparation algorithm is associated with a data field containing at least one value, and, for each conversation turn, the data field for the context control parameter comprises a concatenated dialogue of all preceding conversation turns, with an exception of a first conversation turn where the data field for the context control parameter is an empty string; executing a conversation generation control algorithm having control parameters, which are at least partially the same as the control parameters of the input data preparation algorithm, the executing the conversation generation control algorithm including:(a)randomly selecting a disease from a medical knowledge graph and capturing a plurality of symptoms that are mapped to the selected disease; and,(b) constructing a data field for the topics control parameter of the conversation generation control algorithm using the plurality of symptoms,(c) setting a speaker as a value in a value field for the speaker control parameter of the conversation generation control algorithm, wherein an initial speaker among a doctor and a patient is assigned at the first conversation turn and then the value of the value field for the speaker control parameter is alternated between the doctor and the patient for successive conversation turns, (d) setting a number of remaining turns in the value field of the remaining turns control parameter of the conversation generation control algorithm to a positive integer greater than 1,(e) injecting entities, as values into a data field of the entities control parameter of the conversation generation control algorithm at each conversation turn according to probability rules, the injecting including injecting the entities based on a lower probability of occurrence at the first conversation turn and injecting the entities based on different probabilities at subsequent conversation turns based on a presence or an absence of entities in a previous conversation turn,(f) setting context in a data field of the context control parameter of the conversation generation control algorithm for each conversation turn to a concatenation of dialogue from all preceding conversation turns, with an exception of the first conversation turn where the data field is an empty string, and, when a token length for the data field of the context control parameter exceeds a predetermined maximum allowable token length, recursively removing earlier conversation turns one by one from a beginning of context until the token length no longer exceeds the predetermined maximum allowable token length,{g)_causing the trained machine learning model to generate a conversation turn of the turn-by-turn synthetic doctor-patient conversation; the plurality of symptoms, the injected entities, the speaker, the context, and the number of remaining turns,(h) decrementing the number of the remaining turns by 1 after generation of each conversation turn, and(i) repeating (e) to (h) until the number of the remaining turns reaches zero and outputting generated turn-by-turn synthetic doctor-patient conversation, wherein the generated turn-by-turn synthetic doctor-patient conversation.
These steps amount to certain methods of organizing human activity which
includes functions relating to managing personal behavior or relationships or
interactions between people (including social activities, teaching, and following rules or
instructions) (MPEP § 2106.04(a)(2)(II)(C) citing the abstract idea grouping for methods
of organizing human activity for managing personal behavior or relationships or
interactions between people – also note MPEP § 2106.04(a)(2)(II) stating certain activity
between a person and a computer may fall within the “certain methods of organizing
human activity” grouping).
Step 2A – Judicial Exception Analysis, Prong 2:
This judicial exception is not integrated into a practical application because the
additional elements within the claims only amount to instructions to implement the
judicial exception using a computer [MPEP 2106.05(f)].
Claim 1 recites computer-implemented. Claims 8 and 16 recite one or more data
processors and one or more non-transitory computer readable storage media.
These elements are recited at a high-level of generality such that it amounts to
mere instructions to apply the exception because this is an example of applying the
abstract idea by use of general-purpose computer which does not integrate the abstract
idea into a practical application.
Claims 1, 8, and 15 recite for training a machine learning model, a named entity
recognition operation, using an input data preparation algorithm having various control
parameters; training the machine learning model using the prepared input data; a
conversation generation control algorithm having various control parameters, machine
learning model, and conversation generation control algorithm as tools to apply data to
an algorithm and report the results (MPEP § 2106.05(f)(2) see case involving a
commonplace business method or mathematical algorithm being applied on a general-
purpose computer within the “Other examples.. i.”) amounting to instruction to
implement the abstract idea using a general-purpose computer. Alice Corp. Pty. Ltd. V.
CLS Bank Int’l, 134 S. Ct. 2347, 1357 (2014).
The above claims, as a whole, are therefore directed to an abstract idea.
Step 2B – Additional Elements that Amount to Significantly More:
The present claims do not include additional elements that are sufficient to
amount to more than the abstract idea because the additional elements or combination
of elements amount to no more than a recitation of instructions to implement the
abstract idea on a computer.
Claim 1 recites computer-implemented. Claims 8 and 16 recite one or more data
processors and one or more non-transitory computer readable storage media.
Thus, taken alone, the additional elements do not amount to significantly more
than the above-identified judicial exception. Looking at the limitations as an ordered
combination adds nothing that is not already present when looking at the elements
taken individually. Their collective functions merely provide conventional computer
implementation.
Claims 1, 8, and 15 recite for training a machine learning model, a named entity
recognition operation, using an input data preparation algorithm having various control
parameters; training the machine learning model using the prepared input data; a
conversation generation control algorithm having various control parameters, machine
learning model, and conversation generation control algorithm as tools to apply data to
an algorithm and report the results (MPEP § 2106.05(f)(2) see case involving a
commonplace business method or mathematical algorithm being applied on a general-
purpose computer within the “Other examples.. i.”) amounting to instruction to
implement the abstract idea using a general-purpose computer. Alice Corp. Pty. Ltd. V.
CLS Bank Int’l, 134 S. Ct. 2347, 1357 (2014).
For the reasons stated, these claims are consequently rejected under 35 U.S.C.
§ 101.
Analysis of Dependent Claims
Dependent claim(s) 2, 9, and 16 recite(s) wherein the named medical
entities are selected from the group consisting of biomedical information,
personal identifying information, personal health information, and combinations
thereof.
Dependent claim(s) 11 and 18 recite(s) wherein the control parameters further include a conversation turn length control parameter and the annotated turn-by-turn conversation format of the prepared input data is: [TOPICS] <symptom values> [ENTITIES] <entity values> [SPEAKER] <doctor/patient> [TURN LENGTH] <length of the turn>[REMAINING_TURNS] <number of turns left> [CONTEXT] <previous
dialogues if available>.
Dependent claim 21 recites injecting the entities with a probability of occurrence of less than 15% for the first conversation turn, injecting the entities with a probability of occurrence of at least 50% for the subsequent conversation turns in which the previous conversation turn includes no entities, and injecting the entities with a probability of occurrence of at least 30% for the subsequent conversation turns in which the previous conversation turn includes at least one entity.
Dependent claim 22 recites wherein the medical knowledge graph comprises a structured data representation of diseases and their associated symptoms, treatments, and relationships.
Dependent claim 23 recites wherein the generated turn-by- turn synthetic doctor-patient conversation comprises annotated turn-by-turn dialogues, each of the annotated turn-by-turn dialogues including values for topics, entities, speaker, remaining turns, and context.
Each of these steps of the preceding dependent claims 2, 9, 11, 16, 18, and 21-23 only serve to further limit or specify the features of independent claims 1, 8, and 15
accordingly, and hence are nonetheless directed towards fundamentally the same abstract idea as the independent claim and utilize the additional elements analyzed
below in the expected manner.
Dependent claim(s) 3 recite(s) wherein constructing the input data further
comprises: post-processing the named medical entities to remove any tagging
anomalies resulting from the named entity recognition operation; and performing
an additional medical named entity recognition operation on the post- processed
named medical entities using at least one model trained on a biomedical corpus.
The named entity recognition operation and performing an additional medical
named entity recognition operation on the post- processed named medical
entities using at least one model trained on a biomedical corpus are recited as
tools to apply data to an algorithm and report the results (MPEP § 2106.05(f)(2)
see case involving a commonplace business method or mathematical algorithm
being applied on a general-purpose computer within the “Other examples.. i.”)
amounting to instruction to implement the abstract idea using a general-purpose computer. Alice Corp. Pty. Ltd. V. CLS Bank Int’l, 134 S. Ct. 2347, 1357 (2014).
Dependent claim(s) 6, 12, and 19 recite(s) wherein training the machine
learning model includes multistage finetuning of the machine learning model, the
multistage finetuning comprising: first-fold finetuning using a medical question
answering dataset; following first-fold finetuning, second-fold finetuning guided by
the input data preparation algorithm and the control parameters thereof and
using a dataset including data in the form of textual dialogue associated with
each of a plurality of individual non-medical specific conversations; and following
second-fold finetuning, final-fold finetuning guided by the input data preparation
algorithm and the control parameters thereof and using a dataset including data
in the form of textual dialogue associated with each of a plurality of individual
medical-specific conversations, wherein the symptoms/topics control parameter
of the input data preparation algorithm is composed of keywords previously
derived from a dataset including data in the form of textual dialogue associated with each of a plurality of individual non-medical conversations. This limitation is
recited as tools to apply data to an algorithm and report the results (MPEP §
2106.05(f)(2) see case involving a commonplace business method or
mathematical algorithm being applied on a general-purpose computer within the
“Other examples.. i.”) amounting to instruction to implement the abstract idea
using a general-purpose computer. Alice Corp. Pty. Ltd. V. CLS Bank Int’l, 134 S.
Ct. 2347, 1357 (2014).
Dependent claim(s) 7 and 13 recite(s) comprising evaluating performance
of the trained machine learning model by analyzing the generated turn-by-turn
synthetic doctor-patient conversation using a metric selected from the group
consisting of recall- oriented understudy for gisting evaluation, n-gram diversity
score, unique n-gram count, and combinations thereof. The trained machine
learning model is recited as a tool to apply data to an algorithm and report the
results (MPEP § 2106.05(f)(2) see case involving a commonplace business
method or mathematical algorithm being applied on a general-purpose computer
within the “Other examples.. i.”) amounting to instruction to implement the
abstract idea using a general-purpose computer. Alice Corp. Pty. Ltd. V. CLS
Bank Int’l, 134 S. Ct. 2347, 1357 (2014).
Dependent claim(s) 14 and 20 recite(s) wherein the machine learning
model has a transformer- encoder-decoder architecture. This limitation is recited
as a tool to apply data to an algorithm and report the results (MPEP §
2106.05(f)(2) see case involving a commonplace business method or
mathematical algorithm being applied on a general-purpose computer within the “Other examples.. i.”) amounting to instruction to implement the abstract idea
using a general-purpose computer. Alice Corp. Pty. Ltd. V. CLS Bank Int’l, 134 S.
Ct. 2347, 1357 (2014).
Subject Matter Free of the Prior Art
The following is an examiner’s statement of subject matter free of the prior art:
The ordered combination of the limitations in independent claims 1 (being representative), 8, and 15: the executing the conversation generation control algorithm comprising:(a)randomly selecting a disease from a medical knowledge graph and capturing a plurality of symptoms that are mapped to the selected disease; and, (b) constructing a data field for the topics control parameter of the conversation generation control algorithm using the plurality of symptoms,(c) setting a speaker as a value in a value field for the speaker control parameter of the conversation generation control algorithm, wherein an initial speaker among a doctor and a patient is assigned at the first conversation turn and then the value of the value field for the speaker control parameter is alternated between the doctor and the patient for successive conversation turns,(d) setting a number of remaining turns in the value field of the remaining turns control parameter of the conversation generation control algorithm to a positive integer greater than 1,(e) injecting entities, as values into a data field of the entities control parameter of the conversation generation control algorithm at each conversation turn according to probability rules, the injecting comprising injecting the entities based on a lower probability of occurrence at the first conversation turn and injecting the entities based on different probabilities at subsequent conversation turns based on a presence or an absence of entities in a previous conversation turn,(f) setting context in a data field of the context control parameter of the conversation generation control algorithm for each conversation turn to a concatenation of dialogue from all preceding conversation turns, with an exception of the first conversation turn where the data field is an empty string, and, when a token length for the data field of the context control parameter exceeds a predetermined maximum allowable token length, recursively removing earlier conversation turns one by one from a beginning of context until the token length no longer exceeds the predetermined maximum allowable token length, {g)_causing the trained machine learning model to generate a conversation turn of the turn-by-turn synthetic doctor-patient conversation by inputting, to the machine learning model, the plurality of symptoms the injected entities, the speaker, the context, and the number of remaining turns; (h) decrementing the number of the remaining turns by 1 after generation of each conversation turn, and(i) repeating (e) to (h) until the number of the remaining turns reaches zero and outputting generated turn-by-turn synthetic doctor-patient conversation, wherein the generated turn-by-turn synthetic doctor-patient conversation is used to train at least one downstream machine learning model for at least one from among natural language understanding, automatic speech recognition, and entity extraction.
The most remarkable prior art of record as follows:
Tang (Terminology-aware Medical Dialogue Generation) teaching on obtaining medical dialogues and employ BART (encoder-decoder structure) as the base model.
Wang (US 20210082585 A1) teaching on generating medical records from a doctor-patient dialogue
Varshney (Knowledge graph assisted end-to-end medical dialog generation) teaching on medical specific knowledge graphs that contain disease, symptom, and laboratory tests.
Erdenee (US 20230077528 A1) teaching on a training method of a conversation model including identifying a first context, identifying a first response set corresponding to the first context based on a first model, identifying a response subset selected from the first response set based on a gold response corresponding to the first context and training a second model based on the first context information and the response subset.
Gunasekara (US 20230079879 A1) teaching on automatic generation of conversations.
While Tang teaches on obtaining medical dialogues and employ BART (encoder-decoder structure) as the base model, Wang teaches on generating medical records from a doctor-patient dialogue, Varshney teaches on medical specific knowledge graphs that contain disease, symptom, and laboratory tests, Erdenee teaches on a training method of a conversation model including identifying a first context, identifying a first response set corresponding to the first context based on a first model, identifying a response subset selected from the first response set based on a gold response corresponding to the first context and training a second model based on the first context information and the response subset, and Gunasekara teaching on automatic generation of conversations, none of the cited prior teaches, individually or in combination, the ordered combination of the executing the conversation generation control algorithm comprising:(a)randomly selecting a disease from a medical knowledge graph and capturing a plurality of symptoms that are mapped to the selected disease; and, (b) constructing a data field for the topics control parameter of the conversation generation control algorithm using the plurality of symptoms,(c) setting a speaker as a value in a value field for the speaker control parameter of the conversation generation control algorithm, wherein an initial speaker among a doctor and a patient is assigned at the first conversation turn and then the value of the value field for the speaker control parameter is alternated between the doctor and the patient for successive conversation turns,(d) setting a number of remaining turns in the value field of the remaining turns control parameter of the conversation generation control algorithm to a positive integer greater than 1,(e) injecting entities, as values into a data field of the entities control parameter of the conversation generation control algorithm at each conversation turn according to probability rules, the injecting comprising injecting the entities based on a lower probability of occurrence at the first conversation turn and injecting the entities based on different probabilities at subsequent conversation turns based on a presence or an absence of entities in a previous conversation turn,(f) setting context in a data field of the context control parameter of the conversation generation control algorithm for each conversation turn to a concatenation of dialogue from all preceding conversation turns, with an exception of the first conversation turn where the data field is an empty string, and, when a token length for the data field of the context control parameter exceeds a predetermined maximum allowable token length, recursively removing earlier conversation turns one by one from a beginning of context until the token length no longer exceeds the predetermined maximum allowable token length, {g)_causing the trained machine learning model to generate a conversation turn of the turn-by-turn synthetic doctor-patient conversation by inputting, to the machine learning model, the plurality of symptoms the injected entities, the speaker, the context, and the number of remaining turns; (h) decrementing the number of the remaining turns by 1 after generation of each conversation turn, and(i) repeating (e) to (h) until the number of the remaining turns reaches zero and outputting generated turn-by-turn synthetic doctor-patient conversation, wherein the generated turn-by-turn synthetic doctor-patient conversation is used to train at least one downstream machine learning model for at least one from among natural.
Therefore, Claims 1-3, 6-9, 11-16, and 18-23 are free of the prior art.
Response to Arguments
Applicant's arguments, see pgs. 15-21 “101 Rejections” filed 01/26/2026 have been fully considered but they are not persuasive.
Applicant argues that the amended claims addresses and solves a recognized problem in AI/ ML (lack of labeled, privacy safe training data), resulting in an explicit technical improvement in AI/ ML models.
Applicant argues that the claims are not directed to a judicial exception, nor does it preempt any abstract idea. Examiner respectfully disagrees. The claimed invention comprises obtaining an original dataset to generate a synthetic doctor-patient conversation, the original dataset including data as textual dialogue associated with each of a plurality of individual doctor-patient conversations; constructing input data by performing a named entity recognition operation on the textual dialogue of the original dataset that captures and categorizes named medical entities present in the textual dialogue; generating prepared input data by arranging the input data in an annotated turn-by-turn conversation format using an input data preparation algorithm having various control parameters comprising at least a topics control parameter, an entities control parameter, a speaker control parameter, a remaining turns control parameter, and a context control parameter, wherein each the control parameters of the input data preparation algorithm is associated with a data field containing at least one value, and, for each conversation turn, the data field for the context control parameter comprises a concatenated dialogue of all preceding conversation turns, with an exception of a first conversation turn where the data field for the context control parameter is an empty string; executing a conversation generation control algorithm having control parameters, which are at least partially the same as the control parameters of the input data preparation algorithm, the executing the conversation generation control algorithm including:(a)randomly selecting a disease from a medical knowledge graph and capturing a plurality of symptoms that are mapped to the selected disease; and,(b) constructing a data field for the topics control parameter of the conversation generation control algorithm using the plurality of symptoms,(c) setting a speaker as a value in a value field for the speaker control parameter of the conversation generation control algorithm, wherein an initial speaker among a doctor and a patient is assigned at the first conversation turn and then the value of the value field for the speaker control parameter is alternated between the doctor and the patient for successive conversation turns, (d) setting a number of remaining turns in the value field of the remaining turns control parameter of the conversation generation control algorithm to a positive integer greater than 1,(e) injecting entities, as values into a data field of the entities control parameter of the conversation generation control algorithm at each conversation turn according to probability rules, the injecting including injecting the entities based on a lower probability of occurrence at the first conversation turn and injecting the entities based on different probabilities at subsequent conversation turns based on a presence or an absence of entities in a previous conversation turn,(f) setting context in a data field of the context control parameter of the conversation generation control algorithm for each conversation turn to a concatenation of dialogue from all preceding conversation turns, with an exception of the first conversation turn where the data field is an empty string, and, when a token length for the data field of the context control parameter exceeds a predetermined maximum allowable token length, recursively removing earlier conversation turns one by one from a beginning of context until the token length no longer exceeds the predetermined maximum allowable token length,{g)_causing the trained machine learning model to generate a conversation turn of the turn-by-turn synthetic doctor-patient conversation; the plurality of symptoms, the injected entities, the speaker, the context, and the number of remaining turns,(h) decrementing the number of the remaining turns by 1 after generation of each conversation turn, and(i) repeating (e) to (h) until the number of the remaining turns reaches zero and outputting generated turn-by-turn synthetic doctor-patient conversation, wherein the generated turn-by-turn synthetic doctor-patient conversation. These steps amount to certain methods of organizing human activity which includes functions relating to managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions) (MPEP § 2106.04(a)(2)(II)(C) citing the abstract idea grouping for methods of organizing human activity for managing personal behavior or relationships or interactions between people – also note MPEP § 2106.04(a)(2)(II) stating certain activity between a person and a computer may fall within the “certain methods of organizing human activity” grouping).
Applicant’s arguments, see pgs. 19-20 “103 Rejections”, filed 01/26/2026, with respect to Claims 1-3, 6-9, 11-16, and 18-23, have been fully considered and are persuasive. The rejection of the claims has been withdrawn.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Patricia K Edouard whose telephone number is (571)272-6084. The examiner can normally be reached Monday - Friday 7:30 AM - 5:00 PM.
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, Peter H Choi can be reached at 469-295-9171. 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.
/P.K.E./ Examiner, Art Unit 3681
/PETER H CHOI/ Supervisory Patent Examiner, Art Unit 3681
Prosecution Insights