DETAILED ACTION
This examination is in response to the communication filed on 12/23/2025. Claims 1-43 are currently pending, where claims 7-43 have been withdrawn and claims 1-6 are being examined.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 statement (IDS) submitted on 12/23/2023 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
The information disclosure statement filed 12/23/2023 fails to comply with 37 CFR 1.98(a)(2), which requires a legible copy of each cited foreign patent document; each non-patent literature publication or that portion which caused it to be listed; and all other information or that portion which caused it to be listed. It has been placed in the application file, but the information referred to therein has not been considered.
Election/Restrictions
Claim 7-43 are withdrawn from further consideration pursuant to 37 CFR 1.142(b) as being drawn to a nonelected invention, there being no allowable generic or linking claim. Election was made without traverse in the reply filed on 12/23/2025.
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 1-6 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea and/or mathematical algorithm without significantly more. Independent claim 1 recites “obtaining transcript data representative of spoken dialog in one or more psychotherapy sessions conducted between a patient and a therapist”, “extracting speech segment from the transcript data related to one or more of the patient or the therapist”, “applying a process to the extracted speech segments to determine weighted topic labels representative of semantic psychiatric content of the extracted speech segments” and “processing the weighted topic labels to derived a psychiatric assessment for the patient.”
The limitations of “obtaining…”, “extracting…”, “applying…”, and “processing…” as drafted, are a process that, under a broadest reasonable interpretation, covers the abstract idea of “mental processes” because they cover concepts performed in the human mind, including observation, evaluation, judgement and opinion. See MPEP 2106.04(a)(2). That is, other than reciting “a trained machine learning topic model”, nothing in the claimed elements preclude the steps from practically being performed by a person
obtaining transcript data representative of spoken dialog in one or more psychotherapy sessions conducted between a patient and a therapist (e.g., by the person receiving a paper transcript of a psychotherapy session),
extracting speech segment from the transcript data related to one or more of the patient or the therapist (e.g., by the person marking the transcript to identify the patient’s speech and the therapist’s speech),
applying process to the extracted speech segments to determine weighted topic labels representative of semantic psychiatric content of the extracted speech segments (e.g., by the person annotating the segmented speech to highlight/note specific speech which corresponds to topics relevant to assessing the patient’s mental health), and
processing the weighted topic labels to derived a psychiatric assessment for the patient (e.g., the person utilizing the weighted annotations to calculate a mental health score/assessment).
This judicial exception is not integrated into a practical application because the additional element of using “a trained machine learning topic model…” is not recited with sufficient specificity as to provide any details about how the trained model operates or how the determination of weighted topic labels is made and the plain meaning of “processing” encompasses mental observations or evaluations, e.g., an person’s mental observation of evaluation as to whether the extracted speech segments includes a topics of concern with respect to assessing mental health. Thus, the claims as a whole are directed to an abstract idea (Step 2A, prong two).
Claim 1 does not include any additional elements that are sufficient to amount to significantly more than the judicial exception because, as discussed above with respect to integration of the abstract idea into a practical application, the additional elements of a “trained machine learning topic model…” amounts to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept (Step 2B).
With respect to dependent claims 2, this claim is directed the type of assessment being made. This limitation also relates to the abstract idea of “mental processes.” That is nothing in the claimed elements preclude the steps from practically being performed by a person processing the annotated labels to performed the recited types of assessment. No additional elements are present.
With respect to dependent claims 3 and 4, these claims are directed to the type of trained machine learning model or process that is applying to determine the weighted topic labels. As discussed with respect to independent claim 1, the additional
element of a trained machine learning model amounts to no more than mere instructions to apply the exception using a generic computer component. The same analysis applies here, i.e., mere instructions to apply an exception using a conventional topic model, e.g., an LDA topic model, cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B. Step 2B = No, the claim does not provide an inventive concept (significantly more than the abstract idea).
With respect to dependent claim 5, this claim is directed the added steps of transforming the extracted speech segments into representations in a vector space and determining one or more topic similarity scores between the representations. This limitation also relates to the abstract idea of “mental processes.” That is nothing in the claimed elements preclude the steps from practically being performed by a person processing the extracted words into vector representations using simple/known equations and then determining a similarity score using known distance equations both of which can be performed using paper and pencil. No additional elements are present.
With respect to dependent claim 6, this claim is directed the diarization of the session transcript. This limitation also relates to the abstract idea of “mental processes.” That is nothing in the claimed elements preclude the steps from practically being performed by a person marking or annotating the paper transcript to indication whether each speech segment is from the therapist or patient. No additional elements are present.
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)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-3 and 5-6 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Shriberg et al. (US 2019/0385711 A1; herein “Shriberg”).
Regarding claim 1, Shriberg teaches a method for analyzing psychotherapy data, the method comprising:
obtaining transcript data representative of spoken dialog in one or more psychotherapy sessions conducted between a patient and a therapist (¶[0169] teaches “The system may provide the clinician with the dialogue between itself and the patient. This dialogue may be…a text transcript of the dialogue” and Fig. 60 and ¶[0563] teaches “…speech may be captured by the primary care provider’s organization for e-transcription and the system may provide a copy for analysis” );
extracting speech segments from the transcript data related to one or more of the patient or the therapist (¶[0169] teaches “using semantic analysis to choose segments of speech that were most important to predicting the mental state of the patient”, ¶[0034] teaches “…generating the score can comprise: (i) segmenting the NLP output, the acoustic output, and the visual output into discrete time segments…” and ¶[0278] teaches “…Assessment test administrator 2202 may distinguish the voices in any number of ways…uses acoustic models (e.g., acoustic models 2218) to distinguish the two voices…may further distinguish the patient’s voice from the clinician’s voice using acoustic models 2016, which may identify and segment out the clinician’s voice from an acoustic analysis of the clinician’s voice performed prior to the clinical encounter” );
applying a trained machine learning topic model process to the extracted speech segments to determine weighted topic labels representative of semantic psychiatric content of the extracted speech segments (¶[0016] teaches “the NLP model can be selected from the group consisting of a sentiment model, a statistical language model, a topic model….”, and ¶[0044] teaches “…extracting from the speech data one or more topics of concern of the subject using a topic model.” ); and
processing the weighted topic labels to derive a psychiatric assessment for the patient ( ¶[0034] teaches “…generating the score can comprises (i) segmenting the NLP output, the acoustic output, and the visual output into discrete time segments, (ii) assigning a weight to each discrete time segment, (iii) computing a weighted average of the NLP output, the acoustic output, and the visual output using the assigned weights”, ¶[0169] teaches “These segments may be selected because they might be highly weighted in a calculation of a binary or scaled score indicating a mental state prediction…” and ¶[0279] teaches “Throughout the conversation between the patient and the clinician, assessment test administrator 2022 assesses the mental state of the patient from the patient’s speech in the manner described herein and finalizes the assessment upon detecting the conclusion of the conversation” ).
Regarding claim 2, Shriberg teaches all of the elements of claim 1 (see detailed element mapping above). In addition, Shriberg further teaches the derived psychiatric assessment for the patient comprises one or more of: mental state of the patient (¶[0005] teaches “…provides systems and methods that can more accurately and effectively assess, screen, estimate, and/or monitor the mental state of human subjects…”), a therapy adjustment recommendation (the “OR” makes this element optional), or a trajectory of therapy for the patient (the “OR” makes this element optional ).
Regarding claim 3, Shriberg teaches all of the elements of claim 1 (see detailed element mapping above). In addition, Shriberg further teaches processing the weighted topic labels comprises applying a machine learning model to the weighted topic labels (¶[0154] teaches “This may be done by providing assessment data as inputs to machine learning algorithms…” ).
Regarding claim 5, Shriberg teaches all of the elements of claim 1 (see detailed element mapping above). In addition, Shriberg further teaches applying the topic model process to the extracted speech segments comprises:
transforming one or more of the extracted speech segments into representations in a vector space to produce one or more vectored topic label representations (Fig. 13, step 1308 and ¶[0232] teaches “In step 1308, question equivalent logic 1104 combines the evaluated metrics for each question into a respective multi-dimensional vector for each question”, ¶[0237] teaches “Examples of NLP algorithms are semantic parsing, sentiment analysis, vector-space semantics, and relation extraction” See also ¶[0288]); and
determining one or more topic similarity scores between the one or more vectored topic label representations and one or more vectored representations of learned psychotherapy topic models (Fig. 13, step 1314 and ¶[0234] teaches “In step 1314, the cosine of the angle determined in step 1312 is determined by question equivalence logic 1104 to be the measured similarity between the two questions” ).
Regarding claim 6, Shriberg teaches all of the elements of claim 1 (see detailed element mapping above). In addition, Shriberg further teaches extracting the speech segments from the transcript data related to one or more of the patient or the therapist comprises:
extracting sequential temporal segments from the transcript data according to one or more extraction models comprising: pairing of dialog exchanges between the patient and the therapist, isolated patient-only speech segments, and isolated therapist-only speech segments (¶[0278] teaches “During the conversation passively heard by assessment test administrator 2022, assessment test administrator 2202 assesses the patient’s speech and not the clinician’s speech…assessment test administrator 2202 uses acoustic models (e.g., acoustic models 2218) to distinguish the two voices…may further distinguish the patient’s voice from the clinician’s voice using language models 2214…may identify and segment out the clinician’s voice…” ).
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or non-obviousness.
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Shriberg as applied to claim 1 above, and further in view of Woldenberg (US 2021/0280315 A1; herein “Woldenberg”).
Regarding claim 4, Shriberg teaches all of the elements of claim 1 (see detailed element mapping above). However, Shriberg fails to explicitly disclose what process is implemented by the topic model. Thus, Shriberg fails to explicitly disclose applying the topic model process to the extracted speech segments comprises applying one or more of: a Latent Dirichlet Allocation (LDA) process, a Non Negative Matrix Factorization (NMF) process, a Latent Semantic Analysis (LSA) process, a Pachinko Allocation Model (PAM) process Neural Variational Document Model (NVDM) process, Wasserstein Latent Dirichlet Allocation (W-LDA) process, Embedded Topic Models (ETM) process, or a Bidirectional Adversarial Topic model (BATM) process.
Woldenberg teaches systems and methods for tracking the health of participants and generating an assessment, e.g., general health certificate, that includes, inter alia, parsing data through a pipeline of machine learning or deep learning models including “a model that derives topic features” where “the model that derives topic features comprises a Latent Dirichlet Algorithm (LDA) model” (Woldenberg, ¶[0084]). Thus, Woldenberg teaches applying the topic model process to the extracted speech segments comprises applying one or more of: a Latent Dirichlet Allocation (LDA) process, a Non Negative Matrix Factorization (NMF) process (the “OR” makes this element optional ), a Latent Semantic Analysis (LSA) process (the “OR” makes this element optional ), a Pachinko Allocation Model (PAM) process Neural Variational Document Model (NVDM) process (the “OR” makes this element optional ), Wasserstein Latent Dirichlet Allocation (W-LDA) process (the “OR” makes this element optional ), Embedded Topic Models (ETM) process (the “OR” makes this element optional ), or a Bidirectional Adversarial Topic model (BATM) process (the “OR” makes this element optional ).
Shriberg differs from the claimed invention, as defined by claim 4, in that Shriberg fails to explicitly disclose that the topic model applies an LDA process. Extracting/determining topic features using an LDS topic model is known in the art as evidenced by Woldenberg. Therefore, it would have been obvious to one having ordinary skill in the art to have utilizes an LDA topic model in the system of Shriberg to extract the topic labels/features as taught by Woldenberg as it merely constitutes the substitution of known elements to achieve the predictable results to extracting topic features from the session transcripts.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PENNY L CAUDLE whose telephone number is (703)756-1432. The examiner can normally be reached M-Th 8:00 am to 5:00 pm eastern.
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.
/PENNY L CAUDLE/Examiner, Art Unit 2657