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 .
DETAILED ACTION
In the amendments filed 21 August 2025:
Claim(s) 1, 14, 16 and 18 are amended
Claim(s) 1-21 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 1-21 rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Claims 1, 14, 18 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim recites a method, system and non-transitory computer-readable storage medium, which are within a statutory category or are interpreted to be within a statutory category for subject matter eligibility analysis purposes). The limitations of:
Claims 1, 14 and 18 (Claim 1 being representative)
constructing a user including a plurality of features representing demographic, medical, and activity data of the user;
identify a first set of actionable insights;
identifying from user data for a plurality of users in a vector space having dimensions that correspond to the plurality of features;
assigning a respective cluster to identify a second set of actionable insights according to respective clusters assigned;
adjusting the first set of actionable insights based on the respective cluster assigned to the digital model:
presenting a subset of the adjusted first and second set of actionable insights to the user;
enhance the quality of recommendations.
as drafted, is a process that, under the broadest reasonable interpretation, covers certain methods of organizing human activity (i.e., managing personal behavior including following rules or instructions) but for recitation of generic computer components. That is, other than reciting a computer system having one or more processors and memory, and non-transitory computer-readable medium, the claimed invention amounts to managing personal behavior or interaction between people. The Examiner notes that certain “method[s] of organizing human activity” includes a person’s interaction with a computer (see MPEP 2106.04(a)(2)(II)). If a claim limitation, under its broadest reasonable interpretation, covers managing personal behavior or interactions between people but for the recitation of generic computer components, then it falls within the “certain methods of organizing human activity” grouping of abstract ideas. Accordingly, the claims recite an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claims recite the additional elements of a computer system having one or more processors and memory, and non-transitory computer-readable medium that implements the identified abstract idea. The computer system having one or more processors and memory, and non-transitory computer-readable medium are not described by the applicant and is recited at a high-level of generality (i.e., generic computer components performing generic computer functions) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
The claims further recite the additional elements of a user interface, digital model, classifier model, and clustering models. The user interface, digital model, classifier model, and clustering models merely generally links the abstract idea to a particular technological environment or field of use. MPEP 2106.04(d)(I) indicates that generally linking an abstract idea to a particular technological environment or field of use cannot provide a practical application. Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of using a computer system having one or more processors and memory, and non-transitory computer-readable medium to perform the noted steps amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept (“significantly more”).
Also, as discussed above with respect to integration of the abstract idea into a practical application, the additional elements of a user interface, digital model, classifier model, and clustering models were determined to generally link the abstract idea to a particular technological environment or field of use. This has been re-evaluated under the “significantly more” analysis and has also been found insufficient to provide significantly more. MPEP 2106.05(A) indicates that generally linking an abstract idea to a particular technological environment or field of use cannot provide significantly more. Accordingly, even in combination, this additional element does not provide significantly more. As such the claim is not patent eligible.
Claims 2-13,15-17,19-21 are similarly rejected because they either further define/narrow the abstract idea and/or do not further limit the claim to a practical application or provide as inventive concept such that the claims are subject matter eligible even when considered individually or as an ordered combination.
Claim(s) 2 merely describe(s) what the data contains, which further defines the abstract idea. Claim(s) 2 also includes the additional element of “a database of medical records” and “wearable devices” which is analyzed the same as the “user interface” and does not provide a practical application or significantly more for the same reasons.
Claim(s) 3 merely describe(s) the digital model, which further defines the abstract idea.
Claim(s) 4 merely describe(s) what the data contains, which further defines the abstract idea. Claim(s) 4 also includes the additional element of “a first sub-classifier model” and “an activity classifier model” which is analyzed the same as the “user interface” and does not provide a practical application or significantly more for the same reasons.
Claim(s) 5 merely describe(s) applying the classifier model to the digital model, which further defines the abstract idea.
Claim(s) 6 merely describe(s) a lookup table, which further defines the abstract idea.
Claim(s) 7-8 merely describe(s) what the predefined medical conditions, which further defines the abstract idea.
Claim(s) 9 merely describe(s) what the condition vector contains, which further defines the abstract idea.
Claim(s) 10, 13 merely describe(s) the medical conditions, which further defines the abstract idea.
Claim(s) 11 merely describe(s) applying classifier model to the digital model, which further defines the abstract idea.
Claim(s) 12,15,17 merely describe(s) what the clustering model includes, which further defines the abstract idea.
Claim(s) 16 merely describe(s) resolving a conflict between data, which further defines the abstract idea.
Claim(s) 19 merely describe(s) training the clustering model, which further defines the abstract idea.
Claim(s) 20 merely describe(s) the actionable insights, which further defines the abstract idea.
Claim(s) 21 merely describe(s) instructions prior to presenting the actionable insights, which further defines the abstract idea.
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 Examiner notes that the rejection will reference the translated documents (attached) corresponding to any foreign documents recited in the rejection.
Claims 1-10,12-15,17-20 is/are rejected under pre-AIA 35 U.S.C. 103(a) as being unpatentable over Boussios et al (US Publication No. 20220148695) in view of BOTTINGER et al (US Publication No.20170228507) in view of Srivastava et al (US Publication No. 20200075167) in view of Valdes et al (US Publication No. 20210313071).
Regarding Claim 1
Boussious teaches a method for managing data, comprising:
at a computer system having one or more processors and memory [Boussious at Para. 0064 teaches the general purpose computer is configured as a server computer, with sufficient processors, memory, storage and communication connections]:
constructing a digital model of a user including a plurality of features representing demographic, medical, and activity data of the user [Boussious at Para. 0072 teaches The example in FIG. 7 illustrates data for patient records pertinent to tracking and determining their health care outcomes as described herein. Other data sets, such as those providing demographic information, insurance information, provider information, and relationships among patient and providers, can be stored in other database structures using conventional techniques; Boussios at Para. 0177 teaches In response to a user selected the graphical element 2144, the computer system is instructed to access current data values for the given patient for medically modifiable factors such as the patient's weight, body mass index (BMI), physical activity level, diabetes control and smoking];
applying a classifier model to the digital model to identify a first set of actionable insights [Boussios at Para. 0126 teaches patients that have “insights” associated with them (such as a classifier, after processing their data, identified a risk of an event occurring)];
presenting a subset of the adjusted first and second set of actionable insights to the user on a user interface [Boussios at Para. 0130 teaches alternatively, the menu in FIG. 11 or 13 or other interface can illustrate “insights” about a risk factor or the outcome score];
Boussious does not teach identifying one or more clustering models generated from user data for a plurality of users in a vector space having dimensions that correspond to the plurality of features;
assigning the digital model to a respective cluster within each of the one or more clustering models to identify a second set of actionable insights according to respective clusters assigned to the digital model within the one or more clustering models;
adjusting the first set of actionable insights based on the respective cluster assigned to the digital model:
and apply both the classifier model and the one or more clustering models to the digital model to enhance the quality of recommendations.
BOTTINGER teaches identifying one or more clustering models generated from user data for a plurality of users in a vector space having dimensions that correspond to the plurality of features [BOTTINGER at Para. 0039 teaches after the data sets are arranged into several clusters, the process 200 continues by determining a medical diagnosis for a particular patient based on a relationship between that patient's data set and a particular one of the clusters (step 230). As described above, clusters are groups of data sets that have similar characteristics. Thus, data sets in a cluster represent patients that have a similar disease progression. If information is known about some of the patients in a particular cluster, that information might also be applicable to other patients of that cluster. For example, some patients in a particular cluster may have been previously diagnosed with a particular disease, and thus, their data set represents the progression of that disease over a period of time (characteristics interpreted as features)];
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine classifier models of Boussios with the clustering models of BOTTINGER with the motivation to provide improved medical diagnoses of current and future patients, provide more accurate predictions of patient outcome, and improve the overall quality of clinical care.
Boussios/BOTTINGER do not teach assigning the digital model to a respective cluster within each of the one or more clustering models to identify a second set of actionable insights according to respective clusters assigned to the digital model within the one or more clustering models;
adjusting the first set of actionable insights based on the respective cluster assigned to the digital model:
and apply both the classifier model and the one or more clustering models to the digital model to enhance the quality of recommendations.
Srivastava teaches assigning the digital model to a respective cluster within each of the one or more clustering models to identify a second set of actionable insights according to respective clusters assigned to the digital model within the one or more clustering models [Srivastava at Para. 0005 teaches a method includes associating a person's activities up to a current time point with one of a plurality of clusters of activity proportions for the current time point and associating the person's activities up to the current time point with a sub-cluster in the cluster of activity proportions for the current time point. A determination is then made that the sub-cluster is associated with poor sleep and a recommendation of at least one activity to increase the likelihood of good sleep is made];
adjusting the first set of actionable insights based on the respective cluster assigned to the digital model [Srivastava at Para. 0204 teaches as a user's behaviour is updated throughout the day, the distance simply needs to be recalculated and the selected recommendation dynamically updated]:
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Boussios, BOTTINGER with the insight of Srivastava with the motivation to improve sleep quality.
Boussios/BOTTINGER/Srivastava do not teach and apply both the classifier model and the one or more clustering models to the digital model to enhance the quality of recommendations.
Valdes teaches and apply both the classifier model and the one or more clustering models to the digital model to enhance the quality of recommendations [Valdes at Para. 0025 teaches in some examples, the score for an action, and/or each sub-score associated with the action, may be weighted based on machine learning by the system, user interaction with actions along the user's healthcare decision tree, user preferences, user demographics, average scores of actions or healthcare decision trees users with similar healthcare decision trees, hashing, statistical measures, regressions, classifiers, clusterings, Bayesian methods, types of relationships between the users, any combination thereof, and/or other mathematical calculations. Scores and/or weights may be updated regularly at a scheduled time and/or updated responsive to changes in a healthcare decision tree of the user or other user in the system, other change in data in the system, and/or other factor; Valdes at Para. 0026 teaches in one example, a set of linked actions may include a doctor visit, a prescription ordered by the doctor, a test ordered by the doctor, lab result(s) from the test, and/or other actions linked to the doctor visit. In another example, a set of linked actions may comprise actions associated with a condition that the user has, including recommended exercise actions as part of a treatment for the condition, a set of weight recordings obtained at specific time intervals, a set of symptom data related to the condition that are obtained at specific time intervals, and/or other data related to the condition and recommended treatment (interpret to combine )].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Boussios, BOTTINGER, Srivastava with the application of Valdes with the motivation to enable an improved and effective analysis and recommendation of health care actions from complicated, large data sets related to users, health care, pharmacy, insurance, providers, and other medical data related to managing user health care.
Regarding Claim 2
Boussios/BOTTINGER/Srivastava/Valdes /Valdes teach the method of claim 1,
Boussios/BOTTINGER/Srivastava/Valdes /Valdes further teach wherein the demographic, medical, and activity data of the user includes a subset of:
user-specified medical characteristics of the user [Boussios at Para. 0038 teaches the demographic information can include, for example, age, gender, race, family history, social history, and other information for the patient. If personally identified information authorized and stored, such information can include a name, an address and various contact information (interpreted as user-specified medical characteristics)];
historical medical data of the user, retrieved from a database of medical records of a medical institution [Boussios at Para. 0036 teaches More particularly, health care information can include, but is not limited to, information recorded for patients by a health care provider. Examples of health care providers include, but are not limited to, individuals, such as a physician, a therapist, a nurse, or support staff, and organizations, such a hospital or other facility employing health care providers (hospital interpreted as medical institution); Boussios at Para. 0041 teaches Such health care information generally includes both structured and unstructured data. Structured data generally is data that has a specified data model or other organization, whereas unstructured data generally does not. By way of example, structured data can include database records, attribute-value pairs, and the like, whereas unstructured data can be either textual data, such as free text, documents, reports of results, published and unpublished literature, and the like, or non-textual data, such as image data of which DICOM data is an example.];
activity data from one or more wearable devices worn by the user [Srivastava at Para. 0038 teaches Wearable devices provide the first hope of solving the problems associated with PSG and HST because they can be used to study sleep and physical activity for longer periods of time and outside the laboratory or hospital];
biomarker data measured by one or more laboratory tests of bodily fluids from the user [Boussios at Para. 0036 teaches health care information can include information from entities other than health care providers but who are otherwise involved in health care, such as insurers, laboratories, supply providers and the like, which may store information about claims, diagnostic tests, laboratory work, supplies and vendors. Health care information can include information reported by patients and/or their caregivers];
and changes over time in the user-specified medical characteristics, the historical medical data, the activity data, and the biomarker data [Boussios at Para. 0039 teaches Such data can be stored as a history of interactions with the health care provider and may have multiple instances of a type of data over time, such as vital signs and lab results. Such data typically includes information, typically representing symptoms, diagnoses, procedures and medications, which is typically coded according to a standard, such as ICD-9, ICD-10, CPT, SNOMED, LOINC, COSTAR, and RxNorm coding systems (interpret to combine with activity of BOTTINGER)].
Regarding Claim 3
Boussios/BOTTINGER/Srivastava/Valdes teach the method of claim 1,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein the digital model has a predefined data structure in which the plurality of features is organized to be used as inputs to the classifier model and the one or more clustering models [Boussios at Para. 0053 teaches the computer system can include a data processing module 120 that performs various processing on the patient data 106 stored in the data storage 102, so as to convert patient data into additional data and features 122. Such additional data and features can be used, for example, by the classifiers 104, or other components of the computer system. The data processing module 120 also can be implemented using a general-purpose computer such as described in FIG. 6 and programmed to perform such processing].
Regarding Claim 4
Boussios/BOTTINGER/Srivastava/Valdes teach the method of claim 1,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein the classifier model includes one or both of:
a plurality of first sub-classifier models, wherein each first sub-classifier model is configured to determine respective condition data of a plurality of predefined medical conditions [Boussios at Para. 0047 teaches after training, a trained classifier 104 applied to patient data 106 for a patient determines a likelihood that the patient has a condition corresponding to the classifier, indicated as categorization data 110 in FIG. 1. For each classifier, the health care information data storage 102 can store categorization data 110 over time for each patient, indicating whether the patient is likely in the category represented by the classifier];
and an activity classifier model that is configured to determine an activity style and an activity level of the user [Srivastava at Para. 0076 teaches Traditional prediction models applied to raw accelerometer data (e.g. logistic regression) suffer from at least 2 key limitations: (i) They are not robust enough to learn useful patterns from noisy raw accelerometer output. As a result, existing methods for classification and analysis of physical activity rely on extracting higher-level features that can be fed into prediction models [W. Wu, S. Dasgupta, E. E. Ramirez, C. Peterson, and G. J. Norman, “Classification accuracies of physical activities using smartphone motion sensors,” Journal of medical Internet research, vol. 14, no. 5, 2012].].
Regarding Claim 5
Boussios/BOTTINGER/Srivastava/Valdes teach the method of claim 1,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein applying the classifier model to the digital model to identify the first set of actionable insights further comprises:
generating a condition vector having a plurality of probability values corresponding to a plurality of predefined medical conditions [Boussios at Para. 0090 teaches the health care information system also can provide information about risks associated with a patient. For example, for each category, known risks can have an associated data field for which the value, a probability, is determined using an associated classifier. The classifier uses a predictive model to determine a probability or risk that a patient will experience a particular condition or event given that patient's current data];
and determining the first set of actionable insights based on the plurality of probability values corresponding to the plurality of predefined medical conditions [Srivastava at Para. 0091 teaches after one or more classifiers are trained, the trained classifiers are applied 306 to the health care information stored for patients. For each patient, each classifier returns a probability that the patient meets criteria for a particular category. A classifier also can return other values and probabilities associated with those values, such as a likelihood of improving with a particular treatment and a likelihood of experiencing a future event or outcome].
Regarding Claim 6
Boussios/BOTTINGER/Srivastava/Valdes teach the method of claim 5,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein a lookup table associates a plurality of probability ranges of the plurality of predefined medical conditions with a plurality of predefined actionable insights, the method further comprising:
identifying a subset of the plurality of probability ranges for a subset of predefined medical conditions [Boussios at Para. 0091 teaches After one or more classifiers are trained, the trained classifiers are applied 306 to the health care information stored for patients. For each patient, each classifier returns a probability that the patient meets criteria for a particular category. A classifier also can return other values and probabilities associated with those values, such as a likelihood of improving with a particular treatment and a likelihood of experiencing a future event or outcome. If such values exceed a threshold, a notification can be generated and transmitted to a health care provider, or a patient or other individual. The probabilities computed by each classifier for a patient are stored 308 for the patient (interpreted as having a probability range)];
and based on the subset of probability ranges for the subset of predefined medical conditions, checking the lookup table to identify the first set of actionable insights from the plurality of predefined actionable insights [Boussios at Para. 0146 teaches the set of selected input features can be stored in a data structure in a library for use for multiple entities and multiple models. For each of the selected input features, the library also can store one or more respective different data values to be used in analyzing localized models for entities. The set of selected input features or the explainable factors further can correspond to actions which can be performed with respect to the given entity, such as a particular treatment or behavior change for a patient (library interpreted as a lookup table)].
Regarding Claim 7
Boussios/BOTTINGER/Srivastava/Valdes teach the method of claim 5,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein the plurality of predefined medical conditions includes a first medical condition corresponding to a first probability value, and the method further comprises comparing the first probability value to a first threshold to determine the first set of actionable insights [Boussios at Para. 0090 teaches the classifier uses a predictive model to determine a probability or risk that a patient will experience a particular condition or event given that patient's current data].
Regarding Claim 8
Boussios/BOTTINGER/Srivastava/Valdes teach the method of claim 7,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein the plurality of predefined medical conditions includes a second medical condition corresponding to a second probability value [Boussios at Para. 0090 teaches the health care information system also can provide information about risks associated with a patient. For example, for each category, known risks can have an associated data field for which the value, a probability, is determined using an associated classifier. The classifier uses a predictive model to determine a probability or risk that a patient will experience a particular condition or event given that patient's current data. Data about such risks also can be presented as part of the graphical user interface. Such risks also may be directly related to, i.e., a function of, some patient data or a factor score or outcome score for the patient; Boussios at Para. 0134 teaches condition scores in FIGS. 16 and 17 can be computed for any group of patients, where the group can be defined using any filtering or searching criteria applied to the patient data. For example, patients can be grouped according to one or more conditions, physicians, treatments, demographic information or any other data in the patient data 102],
and the method further comprises comparing the second probability value to a second threshold to adjust the first set of actionable insights determined based on the first probability value of the first medical condition [Boussios at Para. 0100 teaches the algorithm can vary, for example, by condition, by time point and by user group or by other categorization of the data. By determining a unified condition specific health score at each time point, patient outcome scores can be directly compared from one time point to another, allowing a more standard metric for reporting of outcome scores for each condition].
Regarding Claim 9
Boussios/BOTTINGER/Srivastava/Valdes teach the method of claim 7,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein the condition vector includes an activity level, and the method further comprises: based on the activity level, adjusting the first set of actionable insights determined based on the first probability value of the first medical condition [Srivastava at Para. 0193 teaches note, The value of t will change continuously, and the RAHAR output will as well. This will lead to the recommendations dynamically updating].
Regarding Claim 10
Boussios/BOTTINGER/Srivastava/Valdes teach the method of claim 5,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein: the plurality of predefined medical conditions include one or more of: asthma, heart disease, stroke, diabetes, arthritis, cancer, obesity, Alzheimer's disease, substance abuse, influenza, HIV, Zoonotic disease, tuberculosis, chronic kidney disease, or mental illness [Boussios at Para. 0057 teaches in some implementations, the data in a field can be represented in the temporal matrix as a transition in state occurring at a point in time. For example, a patient may have a diagnosis of diabetes. While a diagnostic code may arise in the patient data record at a point in time, this characteristic of the patient for the purposes of creating the temporal matrix for deep learning analysis can be represented as a first state (non-diabetic), which transitions to a second state (diabetic) at the point in time corresponding to the diagnosis].
Regarding Claim 12
Boussios/BOTTINGER/Srivastava/Valdes teach the method of claim 1,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein the one or more clustering models includes a single clustering model corresponding to two or more clusters, each of which corresponds to one or more cluster recommendations [Srivasta at Para. 0219 teaches two activity signals belonging to the same cluster, but different sub-clusters, indicates that the signals followed similar behaviours between T0 and T50, and different behaviours between T50 and T100. Assume both of these activity signals were also predicted to have poor sleep, i.e. they received a recommendation. The signals that belong to a sub-cluster with a good-to-bad ratio greater than 2, are in the same cluster as a behaviour recipe. This suggests that they exhibit similar behaviour to the recommendation, so it naturally concludes that they followed, or adhered, to the recommendation].
Regarding Claim 13
Boussios/BOTTINGER/Srivastava/Valdes teach the method of claim 12,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein:
each of the two or more clusters corresponds to a respective one of a plurality of predefined medical conditions [BOTTINGER at Para. 0039 teaches after the data sets are arranged into several clusters, the process 200 continues by determining a medical diagnosis for a particular patient based on a relationship between that patient's data set and a particular one of the clusters (step 230)];
and the plurality of predefined medical conditions include one or more of: asthma, heart disease, stroke, diabetes, arthritis, cancer, obesity, Alzheimer's disease, substance abuse, influenza, HIV, Zoonotic disease, tuberculosis, chronic kidney disease, and mental illness [Boussios at Para. 0057 (see Claim 10 for explanation)].
Regarding Claim 14
Boussios teaches a computer system, comprising:
one or more processors [Boussios at Para. 0064 (see Claim 1 for explanation)];
and memory storing one or more programs for execution by the one or more processors, the one or more programs further comprising instructions for [Boussios at Para. 0064 (see Claim 1 for explanation)]:
constructing a digital model of a user including a plurality of features representing demographic, medical, and activity data of the user [Boussios at Para. 0072, 0177 (see Claim 1 for explanation)];
applying a classifier model to the digital model to identify a first set of actionable insights [Boussios at Para. 0126 (see Claim 1 for explanation)];
presenting a subset of the adjusted first and second set of actionable insights to the user on a user interface [Boussios at Para. 0130 (see Claim 1 for explanation)];
Boussios does not teach identifying one or more clustering models generated from user data for a plurality of users in a vector space having dimensions that correspond to the plurality of features;
assigning the digital model to a respective cluster within each of the one or more clustering models to identify a second set of actionable insights according to respective clusters assigned to the digital model within the one or more clustering models;
adjusting the first set of actionable insights based on the respective cluster assigned to the digital model;
and apply both the classifier model and the one or more clustering models to the digital model to enhance the quality of recommendations.
BOTTINGER teaches identifying one or more clustering models generated from user data for a plurality of users in a vector space having dimensions that correspond to the plurality of features [BOTTINGER at Para. 0039 (see Claim 1 for explanation)];
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine classifier models of Boussios with the clustering models of BOTTINGER with the motivation to provide improved medical diagnoses of current and future patients, provide more accurate predictions of patient outcome, and improve the overall quality of clinical care
Boussios/BOTTINGER do not teach assigning the digital model to a respective cluster within each of the one or more clustering models to identify a second set of actionable insights according to respective clusters assigned to the digital model within the one or more clustering models;
adjusting the first set of actionable insights based on the respective cluster assigned to the digital model;
and apply both the classifier model and the one or more clustering models to the digital model to enhance the quality of recommendations.
Srivastava teaches assigning the digital model to a respective cluster within each of the one or more clustering models to identify a second set of actionable insights according to respective clusters assigned to the digital model within the one or more clustering models [Srivastava at Para. 0005 (see Claim 1 for explanation)];
adjusting the first set of actionable insights based on the respective cluster assigned to the digital model [Srivastava at Para. 0204 (see Claim 1 for explanation)];
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Boussios, BOTTINGER with the insight of Srivastava with the motivation to improve sleep quality.
Boussios/BOTTINGER/Srivastava do not teach and apply both the classifier model and the one or more clustering models to the digital model to enhance the quality of recommendations.
Valdes teaches and apply both the classifier model and the one or more clustering models to the digital model to enhance the quality of recommendations [Valdes at Para. 0025-0026 (see Claim 1 for explanation)].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Boussios, BOTTINGER, Srivastava with the application of Valdes with the motivation to enable an improved and effective analysis and recommendation of health care actions from complicated, large data sets related to users, health care, pharmacy, insurance, providers, and other medical data related to managing user health care.
Regarding Claim 15
Boussios/BOTTINGER/Srivastava/Valdes teach the computer system of claim 14,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein each of the one or more clustering models corresponds to two or more clusters, each of which corresponds to one or more cluster recommendations, and the one or more programs further comprise instructions for:
determining the one or more cluster recommendations for each of the respective clusters assigned to the digital model within the one or more clustering models [Srivastava at Para. 0230 teaches once the closet recipe sub-cluster has been identified, the centroid of the closest recipe sub-cluster is used to make an activity recommendation];
and consolidating the one or more cluster recommendations for each of the clusters assigned to the digital model to identify the second set of actionable insights [Srivastava at Para. 0230].
Regarding Claim 17
Boussios/BOTTINGER/Srivastava/Valdes teach the computer system of claim 14,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein each of the one or more clustering models corresponds to two or more clusters, each of which corresponds to one or more cluster recommendations, and the one or more programs further comprise instructions for:
determining the one or more cluster recommendations for each of the respective clusters assigned to the digital model within the one or more clustering models [Srivastava at Para. 0230 teaches once the closet recipe sub-cluster has been identified, the centroid of the closest recipe sub-cluster is used to make an activity recommendation];
and consolidating the one or more cluster recommendations for each of the clusters assigned to the digital model to identify the second set of actionable insights [Srivastava at Para. 0230].
Regarding Claim 18
Boussios teaches a non-transitory computer-readable storage medium, storing one or more programs configured for execution by one or more processors, the one or more programs further comprising instructions for [Boussios at Para. 0064 (see Claim 1 for explanation)]:
constructing a digital model of a user including a plurality of features representing demographic, medical, and activity data of the user [Boussios at Para. 0072, 0177 (see Claim 1 for explanation)];
applying a classifier model to the digital model to identify a first set of actionable insights [Boussios at Para. 0126 (see Claim 1 for explanation)];
presenting a subset of the adjusted first and second set of actionable insights to the user on a user interface [Boussios at Para. 0130 (see Claim 1 for explanation)];
Boussios does not teach identifying one or more clustering models generated from user data for a plurality of users in a vector space having dimensions that correspond to the plurality of features;
assigning the digital model to a respective cluster within each of the one or more clustering models to identify a second set of actionable insights according to respective clusters assigned to the digital model within the one or more clustering models;
adjusting the first set of actionable insights based on the respective cluster assigned to the digital model;
and apply both the classifier model and the one or more clustering models to the digital model to enhance the quality of recommendations.
BOTTINGER teaches identifying one or more clustering models generated from user data for a plurality of users in a vector space having dimensions that correspond to the plurality of features [BOTTINGER at Para. 0039 (see Claim 1 for explanation)];
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine classifier models of Boussios with the clustering models of BOTTINGER with the motivation to provide improved medical diagnoses of current and future patients, provide more accurate predictions of patient outcome, and improve the overall quality of clinical care
Boussios/BOTTINGER do not teach assigning the digital model to a respective cluster within each of the one or more clustering models to identify a second set of actionable insights according to respective clusters assigned to the digital model within the one or more clustering models;
adjusting the first set of actionable insights based on the respective cluster assigned to the digital model;
and apply both the classifier model and the one or more clustering models to the digital model to enhance the quality of recommendations.
Srivastava teaches assigning the digital model to a respective cluster within each of the one or more clustering models to identify a second set of actionable insights according to respective clusters assigned to the digital model within the one or more clustering models [Srivastava at Para. 0005 (see Claim 1 for explanation)];
adjusting the first set of actionable insights based on the respective cluster assigned to the digital model [Srivastava at Para. 0204 (see Claim 1 for explanation)];
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Boussios, BOTTINGER with the insight of Srivastava with the motivation to improve sleep quality.
Boussios/BOTTINGER/Srivastava do not teach and apply both the classifier model and the one or more clustering models to the digital model to enhance the quality of recommendations.
Valdes teaches and apply both the classifier model and the one or more clustering models to the digital model to enhance the quality of recommendations [Valdes at Para. 0025-0026 (see Claim 1 for explanation)].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Boussios, BOTTINGER, Srivastava with the application of Valdes with the motivation to enable an improved and effective analysis and recommendation of health care actions from complicated, large data sets related to users, health care, pharmacy, insurance, providers, and other medical data related to managing user health care.
Regarding Claim 19
Boussios/BOTTINGER/Srivastava/Valdes teach the non-transitory computer-readable storage medium of claim 18,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein the one or more programs further comprise instructions for:
training the classifier model using first user data and corresponding ground truth [Boussios at Para. 0047 teaches the health care information system can include a training process that implements machine learning techniques to train the classifiers 104 given training data 108, including data for a set of patients];
and training the one or more clustering models using the first user data without the corresponding ground truth [Boussios at Para. 0048 teaches a classifier 104 can be built using any of family of algorithms described as supervised classification or machine learning or econometrics algorithms, which perform functions such as classification, prediction, regression or clustering. With such algorithms, a computer generates a model based on examples provided in a training set. Any supervised classification or machine learning model can be used as a classifier, such as support vector machines, conditional random fields, random forest, logistic regression, decision tree, maximum entropy, artificial neural networks, genetic algorithms, or other classifier or predictive model, or combination of such models, for which parameters of a function can be trained by minimizing errors using a set of training examples (trained examples interpreted as ground truth)].
Regarding Claim 20
Boussios/BOTTINGER/Srivastava/Valdes teach the non-transitory computer-readable storage medium of claim 18,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein each of the first and second sets of actionable insights is one of: a medication with a dosage, an activity with an activity level, a food recipe, or a dietary supplemental with a suggested usage [Boussios at Para. 0148 teaches the actionable factors can be medically modifiable factors. A medically modifiable factor is a factor, such as a treatment, intervention or other factor that can be acted upon with respect to a patient, under direction of a health care provider. Typically, such a factor can be a treatment, such as a dosage of a medication, and an expected change in patient data due to the treatment, such as a measured laboratory result].
Claims 11 rejected under pre-AIA 35 U.S.C. 103(a) as being unpatentable over Boussios, BOTTINGER, Srivastava, Valdes as applied to claim 1,14,18 above, and further in view of Allen et al (US Publication No. 20180096103).
Regarding Claim 11
Boussios/BOTTINGER/Srivastava/Valdes teach the method of claim 1,
Boussios/BOTTINGER/Srivastava/Valdes further teach wherein applying the classifier model to the digital model to identify the first set of actionable insight comprises:
generating, by the classifier model, an action vector having a plurality of recommendation scores corresponding to a plurality of predefined actionable insights [Boussios at Para. 0139 teaches similarly, a classifier may be able to classify precisely an input into a category, but may not provide information about what data most contributed to such a classification, or what actions could be taken to change such a classification for that input];
Boussios/BOTTINGER/Srivastava/Valdes do not teach ranking the plurality of recommendation scores corresponding to the plurality of predefined actionable insights;
and selecting the first set of actionable insights having a highest recommendation score in the plurality of predefined actionable insights.
Allen teaches ranking the plurality of recommendation scores corresponding to the plurality of predefined actionable insights [Allen at Para. 0087 teaches the healthcare cognitive system 300 processes the evidence in accordance with various cognitive logic algorithms to generate a confidence score for each candidate treatment recommendation indicating a confidence that the corresponding candidate treatment recommendation is valid for the patient 302. The candidate treatment recommendations may then be ranked according to their confidence scores and presented to the user 306 as a ranked listing of treatment recommendations 328. In some cases, only a highest ranked, or final answer, is returned as the treatment recommendation 328];
and selecting the first set of actionable insights having a highest recommendation score in the plurality of predefined actionable insights [Allen at Para. 0087].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Boussios, BOTTINGER, Srivastava with the ranking of Allen with the motivation to improve accuracy, system performance, machine learning, and confidence of the QA pipeline.
Claims 16 rejected under pre-AIA 35 U.S.C. 103(a) as being unpatentable over Boussios, BOTTINGER, Srivastava, Valdes as applied to claim 1,14,18 above, and further in view of Forestier et al (“Towards Conflict Resolution in Collaborative Clustering.”).
Regarding Claim 16
Boussios/BOTTINGER/Srivastava/Valdes teach the computer system of claim 15,
Boussios/BOTTINGER/Srivastava/Valdes do not teach wherein consolidating two or more cluster recommendations for each of the clusters assigned further comprises: resolving a conflict between (i) a first cluster recommendation of a first cluster of a first clustering model and (ii) a second cluster recommendation of a second cluster of a second clustering model.
Forestier teaches wherein consolidating two or more cluster recommendations for each of the clusters assigned further comprises: resolving a conflict between (i) a first cluster recommendation of a first cluster of a first clustering model and (ii) a second cluster recommendation of a second cluster of a second clustering model [Forestier at Pages 4-5 teaches 1) Worst conflict choice (WCC): This first approach consists in choosing the worst conflict, i.e. the one having the highest conflict importance (7). This approach assumes that the resolution of the most important conflict between a pair of results will increase the global agreement between all the methods. This assumption is supported by the intuition that the resolution of an important conflict should increase significantly the similarity of a pair of solutions].
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of Boussios, BOTTINGER, Srivastava and Valdes with the consolidation of Forestier with the motivation to improve the way the collaboration is processed
Claims 21 rejected under pre-AIA 35 U.S.C. 103(a) as being unpatentable over Boussios, BOTTINGER, Srivastava, Valdes as applied to claim 1,14,18 above, and further in view of Heller et al (US Publication No. 20050043965).
Regarding Claim 21
Boussios/BOTTINGER/Srivastava/Valdes teach the non-transitory computer-readable storage medium of claim 18,
Boussios/BOTTINGER/Srivastava/Valdes do not teach wherein the one or more programs further comprise instructions for, prior to presenting the subset of the first and second sets of actionable insights:
identifying an inconsistency or a conflict between (i) one of the first set of acti