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 .
Preliminary Amendment
In the preliminary amendment filed 03/20/2026, the following has occurred: claims 1-20 have been canceled and claims 21-55 have been added. Now, claims 21-55 are pending.
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 21-55 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 2A Prong One
Claims 21, 36, and 46 (claim 21 representative) recite receiving input data comprising unstructured natural language text provided by a user, the input data representing one or more words or phrases describing experiences, activities, or emotional states of the user; processing the input data to extract semantic information from the unstructured natural language text; generating, based on the extracted semantic information, one or more classification outputs indicating presence or absence of one or more health risk factors; determining, for each of the one or more health risk factors, a prediction value indicative of a likelihood that the user is experiencing the health risk factor; and identifying a health condition for the user based on the prediction values for the one or more health risk factors.
These limitations, as drafted, given the broadest reasonable interpretation, encompass managing interactions between people following rules or instructions, which is a subgrouping of Certain Methods of Organizing Human Activity. For example, the claims encompass receiving text from a user, which could be a written document or verbally spoken, extracting information from the text and determining a health risk of the user, predicting a likelihood of the user experiencing the health risk to identify a health condition of the user. This could be carried out by a doctor interacting with a patient to identify a health condition of the patient. Such manual steps encompass Certain Methods of Organizing Human Activity.
Claims 22-35, 37-45, and 47-55 incorporate the abstract idea identified above and recite additional limitations that expand on the abstract idea. For example, claims 23, 29-30, 34-35, 41, and 49 further expand on processing the text of the user to identify topics, semantics, and context. Claims 24-26, 31-33, 38-39, 43, 44-45, 50, and 53-55 further expand on the health risk factors and user condition. Claim As explained above, these manual steps encompass Certain Methods of Organizing Human Activity.
Step 2A Prong Two
This judicial exception is not integrated into a practical application because the remaining elements amount to no more than general purpose computer components programmed to perform the abstract ideas along with adding elements similar to adding the words “apply it” to the abstract idea, and generally linking the abstract idea to a particular technological environment, along with insignificant, extra-solution data gathering activity.
Claims 21-55, directly or indirectly, recite the following additional elements at a high level of generality and merely utilized as tools to implement the abstract idea and/or similar to adding the words “apply it” to the abstract idea:
Claim 21:
A data processing system for identifying health conditions responsive to health risks determined from natural language input, the data processing system comprising one or more processors configured to perform operations.
using one or more natural language processing models.
Claim 23:
The one or more natural language processing models are configured.
Claim 26:
a graphical user interface configured to display, when rendered on a client device.
Claim 27:
a mobile application executing on a computing device.
Claim 34, 35:
the one or more natural language processing models are configured.
Claim 36:
by one or more processors.
using one or more natural language processing models.
Claim 41:
using one or more natural language processing models comprises: applying a first natural language processing model…applying a second natural language processing model…applying a third natural language processing model.
Claim 44:
the one or more natural language processing models are configured.
Claim 46:
A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations.
using one or more natural language processing models.
Claim 49:
using one or more natural language processing models.
The written description discloses that the recited computer components encompass generic components including “a smartphone, laptop, personal computer (PC), or other such computing device” (see paragraph 0033) and “a single computing device, or multiple computers that operate in proximity or generally remote from each other and typically interact through a communication network” (see paragraph 0093). As set forth in the MPEP 2106.04(d) “merely including instructions to implement an abstract idea on a computer” is an example of when an abstract idea has not been integrated into a practical application.
Claims 1-13, directly or indirectly, recite the following additional elements at a high level of generality, involving no more that extra-solution data gathering and transmitting activity:
Claim 39:
transmitting the report to a computing device.
These additional elements are recited at a high degree of generality and are merely involved in insignificant extra solution transmitting of data over a generic computer network. As set forth in MPEP 2106.05(g) insignificant, extra-solution activity, such as insignificant acquisition and data transmission, is an example of when an abstract idea has not been integrated into a practical application.
Claims, recite the following additional elements at a high level of generality, generally linking the abstract idea to a particular technological environment:
Claim 22:
The one or more natural language processing models comprises a transformer-based model.
Claim 28:
the one or more natural language processing models comprise a single unified language model.
Claim 29:
the one or more natural language processing models comprise a plurality of models.
Claim 30:
the plurality of models comprise two or more of: a topic modeling model, a sentiment analysis model, or a word embedding model.
Claim 31:
applying machine learning logic trained on historical data.
Claim 37:
the one or more natural language processing models comprise a pre-trained language model.
Claim 42:
the one or more natural language processing models comprise a bidirectional encoder model.
Claim 43:
training the one or more natural language processing models on training data
Claim 48:
the one or more natural language processing models comprise at least one of: a recurrent neural network model, a convolutional neural network model, or a transformer mode.
Claim 51:
the one or more natural language processing models are trained using regularized logistic regression.
Claim 52:
the one or more natural language processing models comprise a latent Dirichlet allocation model.
Claim 53:
applying the one or more natural language processing models.
using machine learning logic.
Claim 54:
the machine learning logic comprises one or more of: a support vector machine, a neural network, or a logistic regression model.
The different types of natural language processing models, machine learning logic, and training are recited at a high level of generality. There is no indication that the combination of the types of models and training, as recited in the claims with the other recited limitations, provide any type of technical improvement or an improvement to another technical field. Rather, these recitations merely link the abstract idea to a particular technological environment.
Step 2B
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because as discussed above with respect to integration into a practical application, the additional elements are recited at a high level of generality, and the written description indicates that these elements are generic computer components. Using generic computer components to perform abstract ideas does not provide a necessary inventive concept. See Alice, 573 U.S. at 223 (“mere recitation of a generic computer cannot transform a patent-ineligible abstract idea into a patent-eligible invention.”).
Insignificant, extra solution, activity (e.g. transmitting data over a computer network) has been found to not amount to significantly more than an abstract idea (see MPEP 2106.05(g) and Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016)).
Generally linking the abstract idea to a particular technological environment (e.g. types of NLP models, training, machine learning logic) does not amount to significantly more than the abstract idea (see MPEP 2016.05(h) and Affinity Labs of Texas v. DirecTV, LLC, 838 F.3d 1253, 120 USPQ2d 1201 (Fed. Cir. 2016)).
Additionally, the aforementioned additional elements, considered in combination, do not provide an improvement to a technical field or provide a technical improvement to a technical problem. These additional elements merely carry out the abstract idea through data collection, data processing, data communication, and data storage. Therefore, whether considered alone or in combination, the additional elements do not amount to significantly more than the abstract idea.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 21, 23, 25-27, 31-37, 39-40, 43-50, and 53-54 is/are rejected under 35 U.S.C. 102(a)(1) and (a)(2) as being anticipated by Ghanbari, US Patent Application Publication No. 2014/0122109.
As per claim 21, Ghanbari teaches a data processing system for identifying health conditions responsive to health risks determined from natural language input, the data processing system comprising one or more processors configured to perform operations comprising: receiving input data comprising unstructured natural language text provided by a user, the input data representing one or more words or phrases describing experiences, activities, or emotional states of the user (see paragraph 0047; receives input data from a patient describing their symptoms (experiences) in their own words (unstructured natural language text)); processing the input data using one or more natural language processing models to extract semantic information from the unstructured natural language text (see paragraph 0045; analyzes patient responses using NLP to extract key symptoms using a semantic map from particular words and phrases to medical concepts); generating, based on the extracted semantic information, one or more classification outputs indicating presence or absence of one or more health risk factors (see paragraph 0050; produces the potential presences of a diagnoses based on how closely the symptoms match diagnostic fingerprint); determining, for each of the one or more health risk factors, a prediction value indicative of a likelihood that the user is experiencing the health risk factor (see paragraph 0050 and Figure 3D; determines a prediction value indicating the likelihood that the user is experiencing a particular condition (e.g. hypertension 32.2%)); and identifying a health condition for the user based on the prediction values for the one or more health risk factors (see paragraph 0064; example of identifying hypertension based on prediction values).
As per claim 23, Ghanbari teaches the system of claim 21 as described above. Ghanbari further teaches the one or more natural language processing models are configured to generate contextual embeddings representing semantic meaning of words in the input data (see paragraph 0045; semantic meaning identified by NLP, for example identifies the word “headache” to classify one symptom as being a headache).
As per claim 25, Ghanbari teaches the system of claim 21 as described above. Ghanbari further teaches identifying the health condition comprises: comparing each prediction value to a threshold value (see paragraphs 0015-0016; determines whether confidence level in set of diagnoses satisfies a threshold confidence level); and selecting the health condition in response to at least one prediction value exceeding its corresponding threshold value (see paragraphs 0015-0016; determines whether confidence level in set of diagnoses satisfies a threshold confidence level).
As per claim 26, Ghanbari teaches the system of claim 21 as described above. Ghanbari further teaches the operations further comprise: generating data for a graphical user interface configured to display, when rendered on a client device, a representation of the identified health condition and the prediction values for the one or more health risk factors (see paragraph 0064 and Figure 3E; shows a graphical display displaying the condition and prediction values).
As per claim 27, Ghanbari teaches the system of claim 21 as described above. Ghanbari further teaches the input data is collected through a mobile application executing on a computing device of the user (see paragraph 0037; web browser executing on a smartphone, PDA, etc.).
As per claim 28, Ghanbari teaches the system of claim 21 as described above. Ghanbari further teaches he one or more natural language processing models comprise a single unified language model that processes the input data end-to-end (see paragraph 0045; analyzes patient responses using NLP to extract key symptoms using a semantic map from particular words and phrases to medical concepts).
As per claim 31, Ghanbari teaches the system of claim 21 as described above. Ghanbari further teaches generating the one or more classification outputs comprises: applying machine learning logic trained on historical data associating natural language text with health risk factors (see paragraph 0042; model is trained on data stored in the database (historic data)); and outputting, for each health risk factor, a classification metric indicating whether the health risk factor is present (see paragraph 0050; produces the potential presences of a diagnoses based on how closely the symptoms match diagnostic fingerprint).
As per claim 32, Ghanbari teaches the system of claim 31 as described above. Ghanbari further teaches determining the prediction value for each health risk factor comprises combining the classification outputs (see Figure 3E; shows classifications combined by way of a graphical display).
As per claim 33, Ghanbari teaches the system of claim 32 as described above. Ghanbari further teaches combining the classification outputs comprises applying learned weights to the classification outputs (see paragraph 0051; each disease is represented by disease objects with evidence and weights associated with it).
As per claim 34, Ghanbari teaches the system of claim 21 as described above. Ghanbari further teaches the one or more natural language processing models are configured to identify topics referenced in the unstructured natural language text (see paragraph 0048; topics, such as symptom type, are identified in the patient text).
As per claim 35, Ghanbari teaches the system of claim 21 as described above. Ghanbari further teaches the one or more natural language processing models are configured to determine sentiment expressed in the unstructured natural language text (see paragraph 0048; sentiment, such as symptom severity, identified in the patient text).
As per claim 36, Ghanbari teaches a method for identifying health conditions responsive to health risks determined from natural language input, the method comprising: receiving, by one or more processors, input data comprising unstructured natural language text provided by a user, the input data representing one or more words or phrases describing experiences, activities, or emotional states of the user (see paragraph 0047; receives input data from a patient describing their symptoms (experiences) in their own words (unstructured natural language text)); processing, by the one or more processors, the input data using one or more natural language processing models to extract semantic information from the unstructured natural language text (see paragraph 0045; analyzes patient responses using NLP to extract key symptoms using a semantic map from particular words and phrases to medical concepts); generating, by the one or more processors and based on the extracted semantic information, one or more classification outputs indicating presence or absence of one or more health risk factors (see paragraph 0050; produces the potential presences of a diagnoses based on how closely the symptoms match diagnostic fingerprint); determining, by the one or more processors and for each of the one or more health risk factors, a prediction value indicative of a likelihood that the user is experiencing the health risk factor (see paragraph 0050 and Figure 3D; determines a prediction value indicating the likelihood that the user is experiencing a particular condition (e.g. hypertension 32.2%)); and identifying, by the one or more processors, a health condition for the user based on the prediction values for the one or more health risk factors (see paragraph 0064; example of identifying hypertension based on prediction values).
As per claim 37, Ghanbari teaches the method of claim 36 as described above. Ghanbari further teaches the one or more natural language processing models comprise a pre-trained language model (see paragraph 0042; trained model).
As per claim 39, Ghanbari teaches the method of claim 36 as described above. Ghanbari further teaches generating a report identifying the health condition; and transmitting the report to a computing device of a healthcare provider (see paragraph 0046; at the end of the process, the recorded data is provided for review by a nurse or doctor).
As per claim 40, Ghanbari teaches the method of claim 36 as described above. Ghanbari further teaches the input data comprises audio data converted to text using speech recognition (see paragraph 0048; analyzed patient data includes information from the patient speaking).
As per claim 43, Ghanbari teaches the method of claim 36 as described above. Ghanbari further teaches training the one or more natural language processing models on training data comprising natural language text labeled with health risk factors (see paragraph 0042; model is trained on data stored in the database).
As per claim 44, Ghanbari teaches the method of claim 36 as described above. Ghanbari further teaches the one or more natural language processing models are configured to process the input data without requiring explicit feature selection based on cross-validation (see paragraph 0045; analyzes patient responses using NLP; does not require explicit feature selection based on cross-validation).
As per claim 45, Ghanbari teaches the method of claim 36 as described above. Ghanbari further teaches identifying the health condition comprises determining that a combination of prediction values for multiple health risk factors indicates the health condition (see Figure 3E; shows factors combined by way of a graphical display).
As per claim 46, Ghanbari teaches a non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising: receiving input data comprising unstructured natural language text provided by a user, the input data representing one or more words or phrases describing experiences, activities, or emotional states of the user (see paragraph 0047; receives input data from a patient describing their symptoms (experiences) in their own words (unstructured natural language text)); processing the input data using one or more natural language processing models to extract semantic information from the unstructured natural language text (see paragraph 0045; analyzes patient responses using NLP to extract key symptoms using a semantic map from particular words and phrases to medical concepts); generating, based on the extracted semantic information, one or more classification outputs indicating presence or absence of one or more health risk factors (see paragraph 0050; produces the potential presences of a diagnoses based on how closely the symptoms match diagnostic fingerprint); determining, for each of the one or more health risk factors, a prediction value indicative of a likelihood that the user is experiencing the health risk factor (see paragraph 0050 and Figure 3D; determines a prediction value indicating the likelihood that the user is experiencing a particular condition (e.g. hypertension 32.2%)); and identifying a health condition for the user based on the prediction values for the one or more health risk factors (see paragraph 0064; example of identifying hypertension based on prediction values).
As per claim 47, Ghanbari teaches the medium of claim 46 as described above. Ghanbari further teaches the operations further comprise: triggering an alert in response to at least one prediction value exceeding a threshold value, the alert configured to notify one or more of: the user or a healthcare provider associated with the user (see paragraph 0016; generates an alert when the confidence level in the diagnoses satisfies a threshold).
As per claim 48, Ghanbari teaches the medium of claim 46 as described above. Ghanbari further teaches the one or more natural language processing models comprise at least one of: a recurrent neural network model, a convolutional neural network model, or a transformer model (see paragraphs 0046 and 0050; a looping neural network).
As per claim 49, Ghanbari teaches the medium of claim 46 as described above. Ghanbari further teaches processing the input data using one or more natural language processing models comprises analyzing semantic content without generating an explicit intermediate feature vector (see paragraph 0045; analyzes patient responses using NLP; does not include generating an explicit intermediate feature vector).
As per claim 50, Ghanbari teaches the medium of claim 46 as described above. Ghanbari further teaches the operations further comprise: generating, for presentation to the user, a recommendation for a therapeutic intervention based on the identified health condition (see paragraph 0060; provides a list of recommended actions, including treatment for the list of diagnoses).
As per claim 53, Ghanbari teaches the medium of claim 46 as described above. Ghanbari further teaches generating the one or more classification outputs comprises: applying the one or more natural language processing models to extract features from the input data (see paragraph 0045; analyzes patient responses using NLP to extract key symptoms using a semantic map from particular words and phrases to medical concepts); and classifying each extracted feature as indicative or not indicative of a health risk using machine learning logic (see paragraph 0050; produces the potential presences of a diagnoses based on how closely the symptoms match diagnostic fingerprint).
As per claim 54, Ghanbari teaches the medium of claim 53 as described above. Ghanbari further teaches the machine learning logic comprises one or more of: a support vector machine, a neural network, or a logistic regression model (see paragraph 0050; neural network).
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) 22 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ghanbari, US Patent Application Publication No. 2014/0122109 in view of Ambati, US Patent Application Publication No. 2018/0293462.
As per claim 22, Ghanbari teaches the system of claim 21 as described above. Ghanbari does not explicitly teach the one or more natural language processing models comprise a transformer-based language model. Ambati teaches a transformer-based language model (see paragraph 0052) for processing patient data (see paragraph 0054). It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to include a transformer-based language model in the system of Ghanbari with the motivation of improving the accuracy of the models in Ghanbari (see paragraph 0004 of Ambati).
Claim(s) 24, 29-30, 38, 41-42, 51, 55 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ghanbari, US Patent Application Publication No. 2014/0122109 in view of Wang, US Patent Application Publication No. 2018/0314689.
As per claim 24, Ghanbari teaches the system of claim 21 as described above. Ghanbari does not explicitly teach the one or more health risk factors comprise one or more of: depression risk, anxiety risk, suicidal ideation risk, self- harm risk, risk of harm from others, substance abuse risk, or eating disorder risk. Wang teaches identifying one or more health risk factors comprise one or more of: depression risk, anxiety risk, suicidal ideation risk, self- harm risk, risk of harm from others, substance abuse risk, or eating disorder risk (see paragraph 0114; interpretation model analyzes user audio information to determine user’s emotional, mental, cognitive state including happy, angry, distracted, excited, distressed, etc.). It would have been obvious to one of ordinary skill in the art at the time of the effective filing data to also assess a user’s mental state in the system of Ghanbari with the motivation of coming to a better conclusion for an appropriate course of action (see paragraph 0115 of Wang).
As per claim 29, Ghanbari teaches the system of claim 21 as described above. Ghanbari further teaches the one or more natural language processing models configured to extract different types of semantic information from the input data (see paragraph 0045; analyzes patient responses using NLP to extract key symptoms using a semantic map from particular words and phrases to medical concepts). Ghanbari does not explicitly teach the models comprise a plurality of models. Wang teaches a plurality of behavioral models for extracting semantic data from different kinds of input (see paragraph 0064). It would have been obvious to one of ordinary skill in the art at the time of the effective filing data to incorporate the multiple models of Wang in the system of Ghanbari with the motivation of addressing multiple language processing (see paragraph 0002 of Wang).
As per claim 30, Ghanbari and Wang teaches the system of claim 29 as described above. Ghanbari does not explicitly teach the plurality of models comprise two or more of: a topic modeling model, a sentiment analysis model, or a word embedding model. Wang further teaches the plurality of models comprise two or more of: a topic modeling model, a sentiment analysis model, or a word embedding model (see paragraph 0484; semantic processing model; paragraph 0335; rules models based on certain topics). It would have been obvious to one of ordinary skill in the art at the time of the effective filing data to incorporate the multiple models of Wang in the system of Ghanbari with the motivation of addressing multiple language processing (see paragraph 0002 of Wang).
As per claim 38, Ghanbari teaches the method of claim 36 as described above. Ghanbari does not explicitly teach the one or more health risk factors comprise mental health risk factors. Wang teaches one or more health risk factors comprise mental health risk factors (see paragraph 0114; interpretation model analyzes user audio information to determine user’s emotional, mental, cognitive state including happy, angry, distracted, excited, distressed, etc.). It would have been obvious to one of ordinary skill in the art at the time of the effective filing data to also assess a user’s mental state in the system of Ghanbari with the motivation of coming to a better conclusion for an appropriate course of action (see paragraph 0115 of Wang).
As per claim 41, Ghanbari teaches the method of claim 36 as described above. Ghanbari further teaches processing the input data using one or more natural language processing models comprises: applying a natural language processing model to identify topics in the unstructured natural language text (see paragraph 0048; topics, such as symptom type, are identified in the patient text); applying a natural language processing model to determine sentiment in the unstructured natural language text (see paragraph 0048; sentiment, such as symptom severity, identified in the patient text); and applying a natural language processing model to generate contextual word embeddings from the unstructured natural language text (see paragraph 0045; semantic meaning identified by NLP, for example identifies the word “headache” to classify one symptom as being a headache). Ghanbari does not explicitly teach a first, second, and third natural language processing model. Wang further teaches a first, second, and third natural language processing model (see paragraph 0120; domain-specific applications including acoustic and language model, statistical language model, object and gesture models). It would have been obvious to one of ordinary skill in the art at the time of the effective filing data to incorporate the multiple models of Wang in the system of Ghanbari with the motivation of addressing multiple language processing (see paragraph 0002 of Wang).
As per claim 42, Ghanbari teaches the method of claim 36 as described above. Ghanbari does not explicitly teach the one or more natural language processing models comprise a bidirectional encoder model. Wang further teaches one or more natural language processing models comprise a bidirectional encoder model (see paragraph 0336; bidirectional interaction model). It would have been obvious to one of ordinary skill in the art at the time of the effective filing data to incorporate the multiple models of Wang in the system of Ghanbari with the motivation of addressing multiple language processing (see paragraph 0002 of Wang).
As per claim 51, Ghanbari teaches the medium of claim 46 as described above. Ghanbari further teaches the one or more natural language processing models are trained to select natural language factors that predict health assessment scores (see paragraph 0042; model is trained on data stored in the database). Ghanbari does not explicitly teach using regularized logistic regression. Wang further teaches the models using regularized logistic regression (see paragraph 0309; may apply a combination of multiple modeling approaches including logistic regression calibration). It would have been obvious to one of ordinary skill in the art at the time of the effective filing data to incorporate the multiple models of Wang in the system of Ghanbari with the motivation of addressing multiple language processing (see paragraph 0002 of Wang).
As per claim 55, Ghanbari teaches the medium of claim 46 as described above. Ghanbari does not explicitly teach the one or more health risk factors comprise peripartum mental health risk factors. Wang further teaches one or more health risk factors comprise peripartum mental health risk factors (see paragraph 0114; interpretation model analyzes user audio information to determine user’s emotional, mental, cognitive state including happy, angry, distracted, excited, distressed, etc.). It would have been obvious to one of ordinary skill in the art at the time of the effective filing data to also assess a user’s mental state in the system of Ghanbari with the motivation of coming to a better conclusion for an appropriate course of action (see paragraph 0115 of Wang).
Claim(s) 52 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ghanbari, US Patent Application Publication No. 2014/0122109 in view of McNair, US Patent Number 10,770,184.
As per claim 52, Ghanbari teaches the medium of claim 46 as described above. Ghanbari does not explicitly teach the one or more natural language processing models comprise a latent Dirichlet allocation model configured to identify topics in the unstructured natural language text. McNair teaches one or more natural language processing models comprise a latent Dirichlet allocation model configured to identify topics in the unstructured natural language text (see column 14, lines 22-45) applied to determine a patient condition from unstructured data (see column 6, lines 11-39). It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to implement this type of natural language processing in the system of Ghanbari with the motivation of improving the decision support related to the patient’s condition (see column 1, line 63 – column 2, line 7).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Li, Chinese Publication No. CN 106682387 A, discloses modeling input word text to determine symptom descriptions.
Choksi, US Patent Application Publication No. 2019/0172586, discloses predicting patient health risks by text analysis of patient notes.
Carlson, US Patent Application Publication No. 2016/0004831, discloses natural language processing of health data.
Datla, US Patent Application Publication No. 2019/0252074, discloses automated clinical diagnosis from natural language patient symptom input.
Allen, US Patent Application Publication No. 2018/0089568, discloses semantic and syntactic analysis of natural language to provide probability of a disease.
Zillner, US Patent Application Publication No. 2013/0310653, discloses categorizing symptoms as present or absent from clinical diagnosis records.
Bagchi, US Patent Application Publication No. 2018/0025127, discloses recognizing phrases relating to clinical concepts including patient symptoms.
Reece et al., Forecasting the onset and course of mental illness with Twitter data, discloses analyzing textual data to predict mental health conditions.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to C. Luke Gilligan whose telephone number is (571)272-6770. The examiner can normally be reached Monday through Friday 9:00 - 5:00.
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, Robert Morgan can be reached at 571-272-6773. 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.
C. Luke Gilligan
Primary Examiner
Art Unit 3683
/CHRISTOPHER L GILLIGAN/ Primary Examiner, Art Unit 3683
Prosecution Insights