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 .
Response to Amendment
The Amendment filed 07/29/2026 has been entered. Claims 1-20 remain pending in the application.
Claim Rejections - 35 USC § 103
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 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 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 of this title, 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.
Claims 1-3, 6, 8-9, 13-14 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over MULLIGAN et al. (US 20210057098 A1 hereinafter Mulligan) in view of Das et al. (US 20210104307 A1 hereinafter Das), Du et al. (US 20110184977 A1) hereinafter Du and Chakrabarti (US 20150142721 A1).
As to independent claim 1, Mulligan teaches a method, comprising:
accessing resident data describing a set of services received by a resident; [patient profiles and historical data ¶79 "historical data collected from one or more data sources, one or more user profiles, a domain knowledge, feedback data, or a combination thereof"]
generating a set of fitness scores for the set of services, wherein each respective fitness score from the set of fitness scores indicates a respective suitability of a respective service for the resident; [generates scores using historical data (features) (supports machine learning ¶98) (usefulness based score ¶82) ¶94 "a ranking algorithm computes a score based on a confidence interval, using a threshold on the ranking score (when the ranking of an OMA is above that threshold, learning a value of the threshold dynamically based on historical data"]
training a machine learning model using one or more collaborative filtering techniques to generate [[residential service plans]] based at least in part on the set of fitness scores; and [training and collaborative filtering to generate action recommendations as part of new guidelines ¶4, ¶106 "actions recommendation component 520 may use collaborative filtering. The actions recommendation component 520 may be trained on historical data 522 relating to one or more patients (both clinical and nonclinical), and feedback one or more optimal medical actions from the patient from one or more domain knowledge experts 560,"]
assigning the resident to a first resident group of the plurality of resident groups, [clusters patients ¶104 " cluster patients based on named entities extracted from one or more data sources"]
updating the machine learning model based on the set of proposed services and the set of fitness scores; and [progressively refines (updates) model based on feedback and recommendations and rankings (scores) ¶27 "progressively refines the recommendation model by taking into account feedback from one or more domain knowledge experts, a machine learning operation, or a combination thereof. The feedback may include approvals, rejections, and/or rankings of previous recommendations"]
deploying the trained machine learning model. [deploy models ¶98]
Mulligan does not specifically teach residential service plans based at least in part on the set of fitness scores.
However, Das teaches residential service plans based at least in part on the set of fitness scores [system generates a care plan based on rankings (score) ¶22, ¶76, ¶5 " generating, by the personalized patient engagement engine, an intervention recommendation for the given patient based on the personalized intervention effectiveness rankings"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify the modeling disclosed by Mulligan by incorporating the residential service plans based at least in part on the set of fitness scores disclosed by Das because both techniques address the same field of health services and by incorporating Das into Mulligan improves services helping assist patient care [Das ¶3, ¶18].
Mulligan and Das does not specifically teach generating a plurality of resident groups based on resident-to-resident similarity using the one or more collaborative filtering techniques and based on a plurality of features; generating a group-to-service mapping based on service-to-service similarity measures for a plurality of services provided to residents; identifying a set of proposed services based on the first resident group and the group-to-service mapping;
However, Du teaches generating a plurality of resident groups based on resident-to-resident similarity using the one or more collaborative filtering techniques and based on a plurality of features; [Clusters (groups) based on similarity between users (residents) ¶46-48 "k-means clustering algorithm based on a similarity between users "]
generating a group-to-service mapping based on service-to-service similarity measures for a plurality of services provided to residents; [Du group to item database based on similarity ¶39, ¶30 " a user group item similarity database, configured to record a similarity between items corresponding to each user group generated based on the user grouping result."]
identifying a set of proposed services based on the first resident group and the group-to-service mapping; and [determines items (services) to recommend based on group item similarity ¶40, 74 " based on an item similarity and a user item rating in the user group to which the target user belongs, items that have a high similarity to an item with a high user rating and that the target user does not rate are selected as a set to be recommended"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligan and Das by incorporating the generating a plurality of resident groups based on resident-to-resident similarity using the one or more collaborative filtering techniques and based on a plurality of features; generating a group-to-service mapping based on service-to-service similarity measures for a plurality of services provided to residents; identifying a set of proposed services based on the first resident group and the group-to-service mapping disclosed by Du because all techniques address the same field of machine learning and by incorporating Du into Mulligan and Das improves recommendation accuracy and quality accounting for groups of preferences [Du ¶11]
Mulligan, Das and Du do not specifically teach in response to determining that a threshold percentage of features, from the resident data, match feature values associated with the first resident group;
However, Chakrabarti teaches in response to determining that a threshold percentage of features, from the resident data, match feature values associated with the first resident group; [Connects based on threshold of attributes (features) that match ¶43, ¶6 "a relationship factor is determined based on a number of characteristics of a user connected to an object that match"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligan, Das and Du by incorporating the disclosed by Chakrabarti because all techniques address the same field of machine learning and by incorporating Chakrabarti into Mulligan, Das and Du identifies the attributes that are relevant and sufficient for quality recommendations and connections [Chakrabarti ¶4].
As to dependent claim 2, the rejection of claim 1 is incorporated, Mulligan, Das, Du and Chakrabarti further teach wherein generating the set of fitness scores comprises generating a first fitness score for a first service of the set of services, comprising: extracting one or more features, describing the first service, from the resident data;[Das extracts features from data for models ¶51 " processes both structured and unstructured data and generates automatic features. Personalized patient engagement engine 120 extracts patient engagement semantics from CM notes using natural language processing (NLP) tools"]
transforming at least one feature of the one or more features by applying one or more preprocessing operations; and [Das NLP and feature transformation (preprocess) with feature engineering ¶81, ¶51 "natural language processing (NLP) tools. Personalized patient engagement engine 120 trains a feature transformation operator "]
generating the first fitness score based on the transformed at least one feature. [Das scores from algorithm /models that are fed features ¶46]
As to dependent claim 3, the rejection of claim 2 is incorporated, Mulligan, Das, Du and Chakrabarti further teach wherein the one or more features comprise at least one of: (i) an amount of time spent providing the first service;
(ii) one or more natural language notes relating to providing the first service; or [Das notes and NLP ¶51]
(iii) a completion status of the first service.
As to dependent claim 6, the rejection of claim 1 is incorporated, Mulligan, Das, Du and Chakrabarti further teach extracting, from the resident data, a plurality of resident attributes describing the resident; and [Das extracts features from data for models ¶51 " processes both structured and unstructured data and generates automatic features. Personalized patient engagement engine 120 extracts patient engagement semantics from CM notes using natural language processing (NLP) tools"]
training the machine learning model based further on the plurality of resident attributes. [Das trains according to parameters ¶51, ¶83]
As to independent claim 8, Mulligan teaches a method, comprising:
accessing resident data describing a resident; [patient profiles and historical data ¶79 "historical data collected from one or more data sources, one or more user profiles, a domain knowledge, feedback data, or a combination thereof"]
generating a set of predicted fitness scores for a set of services by processing the set of features using a machine learning model trained based on one or more collaborative filtering techniques; and [generates scores using historical data (features) (supports collaborative filtering ¶106 and machine learning ¶98) ¶94 "a ranking algorithm computes a score based on a confidence interval, using a threshold on the ranking score (when the ranking of an OMA is above that threshold, learning a value of the threshold dynamically based on historical data"]
implementing the residential service plan for the resident based at least in part on the set of predicted fitness scores. [adds actions for a CPG guideline (plan implemented) based on the score (threshold) ¶96 "CPG section generation component 416 may then add the optimal medical actions 420 as the additional CPG upon the ranking score exceeding the predetermined threshold."]
Mulligan does not specifically teach generating a residential service plan for the resident, comprising extracting a set of features from the resident data;
However, Das teaches generating a residential service plan for the resident, comprising [system generates a care plan ¶22, ¶76 " a care plan personalization assistant in ongoing care. The CM system recommends patient-specific goals (e.g., weight loss) and corresponding interventions for achieving those goals (e.g., self-monitoring, counseling)."]
extracting a set of features from the resident data; [extracts features from data for models ¶51 " processes both structured and unstructured data and generates automatic features. Personalized patient engagement engine 120 extracts patient engagement semantics from CM notes using natural language processing (NLP) tools"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify the modeling disclosed by Mulligan by incorporating the generating a residential service plan for the resident, comprising extracting a set of features from the resident data disclosed by Das because both techniques address the same field of health services and by incorporating Das into Mulligan improves services helping assist patient care [Das ¶3, ¶18].
Mulligan and Das does not specifically teach generating a plurality of resident groups based on resident-to-resident similarity using the one or more collaborative filtering techniques and based on a plurality of features; generating a group-to-service mapping based on service-to-service similarity measures for a plurality of services provided to residents; identifying a set of proposed services based on the first resident group and the group-to-service mapping;
However, Du teaches generating a plurality of resident groups based on resident-to-resident similarity using the one or more collaborative filtering techniques and based on a plurality of features; [Clusters (groups) based on similarity between users (residents) ¶46-48 "k-means clustering algorithm based on a similarity between users "]
generating a group-to-service mapping based on service-to-service similarity measures for a plurality of services provided to residents; [Du group to item database based on similarity ¶39, ¶30 " a user group item similarity database, configured to record a similarity between items corresponding to each user group generated based on the user grouping result."]
identifying a set of proposed services based on the first resident group and the group-to-service mapping; and [determines items (services) to recommend based on group item similarity ¶40, 74 " based on an item similarity and a user item rating in the user group to which the target user belongs, items that have a high similarity to an item with a high user rating and that the target user does not rate are selected as a set to be recommended"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligan and Das by incorporating the generating a plurality of resident groups based on resident-to-resident similarity using the one or more collaborative filtering techniques and based on a plurality of features; generating a group-to-service mapping based on service-to-service similarity measures for a plurality of services provided to residents; identifying a set of proposed services based on the first resident group and the group-to-service mapping disclosed by Du because all techniques address the same field of machine learning and by incorporating Du into Mulligan and Das improves recommendation accuracy and quality accounting for groups of preferences [Du ¶11]
Mulligan, Das and Du do not specifically teach in response to determining that a threshold percentage of features, from the resident data, match feature values associated with the first resident group;
However, Chakrabarti teaches in response to determining that a threshold percentage of features, from the resident data, match feature values associated with the first resident group; [Connects based on threshold of attributes (features) that match ¶43, ¶6 "a relationship factor is determined based on a number of characteristics of a user connected to an object that match"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligan, Das and Du by incorporating the disclosed by Chakrabarti because all techniques address the same field of machine learning and by incorporating Chakrabarti into Mulligan, Das and Du identifies the attributes that are relevant and sufficient for quality recommendations and connections [Chakrabarti ¶4].
As to dependent claim 9, the rejection of claim 8 is incorporated, Mulligan, Das, Du and Chakrabarti further teach wherein generating the set of predicted fitness scores for the set of services comprises: assigning the resident to a first resident group, of a plurality of resident groups indicated in the machine learning model, based on the set of features; [Das groups based on similar profiles and phenotypes Fig. 8 801 ¶86 "matches the patient to a behavioral phenotype according to a similarity of the patient's interactional, contextual, and behavioral features to the prototypical cases of each phenotype (block 801). The mechanism estimates the propensity of positive behavioral responses of each of the targeted behaviors (block 802). Then, the mechanism dynamically updates the personalized intervention effectiveness rankings in context for CM and patient's decision-making based on what has been shown to lead to positive responses for individuals with similar behavioral profile (block 803)"]
identifying the set of services based on determining that the set of services is associated with the first resident group in the machine learning model; and [Das identifies interventions (services) accordingly Fig. 8 803-804 ¶86 "ranking, the mechanism recommends the most effective intervention for the patient given the goal assigned and the individual intervention effect estimation (block 804)"]
generating the set of predicted fitness scores based on historical fitness scores used to train the machine learning model. [Mulligan score based votes and updates are used ¶122-124, ¶128 "rank or re-rank the one or more useful medical actions according to a scoring criteria"]
As to dependent claim 13, the rejection of claim 8 is incorporated, Mulligan, Das, Du and Chakrabarti further teach wherein generating the set of fitness scores comprises generating a first fitness score for a first service of the set of services, comprising: extracting one or more features, describing the first service, from the resident data;[Das extracts features from data for models ¶51 " processes both structured and unstructured data and generates automatic features. Personalized patient engagement engine 120 extracts patient engagement semantics from CM notes using natural language processing (NLP) tools"]
transforming at least one feature of the one or more features by applying one or more preprocessing operations; and [Das NLP and feature transformation (preprocess) with feature engineering ¶81, ¶51 "natural language processing (NLP) tools. Personalized patient engagement engine 120 trains a feature transformation operator "]
generating the first fitness score based on the transformed at least one feature. [Das scores from algorithm /models that are fed features ¶46]
As to dependent claim 14, the rejection of claim 13 is incorporated, Mulligan, Das, Du and Chakrabarti further teach wherein the one or more features comprise at least one of: (i) an amount of time spent providing the first service;
(ii) one or more natural language notes relating to providing the first service; or [Das notes and NLP ¶51]
(iii) a completion status of the first service.
As to dependent claim 17, the rejection of claim 13 is incorporated, Mulligan, Das, Du and Chakrabarti further teach refining the machine learning model based on the first fitness score. [Mulligan input data includes a score as well ¶82]
Claims 4 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Mulligan in view of Das, Du and Chakrabarti as applied to the rejection of claim 3 and 14 above, and further in view of Brown et al. (US 11289204 B2 hereinafter Brown)
As to dependent claim 4, the combination of Mulligan, Das, Du and Chakrabarti teach all the limitations of claim 3 that is incorporated.
Mulligan, Das, Du and Chakrabarti further teach wherein transforming the at least one feature comprises generating a complexity score by processing the one or more natural language notes [Das notes and NLP ¶51], [Das scores from algorithm /models ¶46]
Mulligan, Das, Du and Chakrabarti do not specifically teach using one or more sentiment analysis models.
However, Brown teaches using one or more sentiment analysis models. [notes analyzed by sentiment analysis Col. 2-3 ln. 64-14 "determine location topics of note within unstructured data, known algorithms for named entity recognition may be used to identify entities of note, or known sentiment analysis algorithms may be used to identify a patient sentiment"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed Mulligan, Das, Du and Chakrabarti by incorporating the using one or more sentiment analysis models disclosed by Brown because all techniques address the same field of health care and by incorporating Brown into Mulligan, Das, Du and Chakrabarti improves adherence to patent care plans and help outcomes [Brown Col. 4 ln. 50-63]
As to dependent claim 15, the combination of Mulligan, Das, Du and Chakrabarti teach all the limitations of claim 14 that is incorporated.
Mulligan, Das, Du and Chakrabarti further teach wherein transforming the at least one feature comprises generating a complexity score by processing the one or more natural language notes [Das notes and NLP ¶51], [Das scores from algorithm /models ¶46]
Mulligan, Das, Du and Chakrabarti do not specifically teach using one or more sentiment analysis models.
However, Brown teaches using one or more sentiment analysis models. [notes analyzed by sentiment analysis Col. 2-3 ln. 64-14 "determine location topics of note within unstructured data, known algorithms for named entity recognition may be used to identify entities of note, or known sentiment analysis algorithms may be used to identify a patient sentiment"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligan, Das, Du and Chakrabarti by incorporating the using one or more sentiment analysis models disclosed by Brown because all techniques address the same field of health care and by incorporating Brown into Mulligan, Das, Du and Chakrabarti improves adherence to patent care plans and help outcomes [Brown Col. 4 ln. 50-63]
Claims 5 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Mulligan in view of Das, Du, Chakrabarti and Brown, as applied to the rejection of claim 4 and 15 above, and further in view of McGillin (US 20060287906 A1)
As to dependent claim 5, the combination of Mulligan, Das, Du, Chakrabarti and Brown teach all the limitations of claim 4 that is incorporated.
Mulligan, Das, Du, Chakrabarti and Brown further teach the complexity score is directly related to the first fitness score. [Das score ¶21, ¶46]
Mulligan, Das, Du, Chakrabarti and Brown do not specifically teach the amount of time is directly related to the first fitness score.
However, McGillin teaches the amount of time is directly related to the first fitness score. [ score based on time involved ¶35 "score values comprising weighted assessments of times involved in caring for a patient"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligan, Das and Brown by incorporating the amount of time is directly related to the first fitness score, and disclosed by McGillin because all techniques address the same field of health care and by incorporating McGillin into Mulligan, Das and Brown enables efficient managing decisions in real time more according to patient needs [McGillin ¶12]
As to dependent claim 16, the combination of Mulligans, Das, Du, Chakrabarti and Brown teach all the limitations of claim 15 that is incorporated.
Mulligans, Das, Du, Chakrabarti and Brown further teach the complexity score is directly related to the first fitness score. [Das score ¶21, ¶46]
Mulligans, Das, Du, Chakrabarti and Brown do not specifically teach the amount of time is directly related to the first fitness score.
However, McGillin teaches the amount of time is directly related to the first fitness score. [ score based on time involved ¶35 "score values comprising weighted assessments of times involved in caring for a patient"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligan, Das and Brown by incorporating the amount of time is directly related to the first fitness score, and disclosed by McGillin because all techniques address the same field of health care and by incorporating McGillin into Mulligans, Das, Du, Chakrabarti and Brown enables efficient managing decisions in real time more according to patient needs [McGillin ¶12]
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Mulligan in view of Das, Du and Chakrabarti as applied to the rejection of claim 6 above, and further in view of HU et al. (US 20140297317 A1 hereinafter Hu)
As to dependent claim 7, the combination of Mulligans, Das, Du and Chakrabarti teach all the limitations of claim 6 that is incorporated.
Mulligan, Das, Du and Chakrabarti further teach wherein the machine learning model is further trained based on data for a plurality of residents, comprising: extracting a respective plurality of resident attributes for each respective resident of the plurality of residents; [Das extracts features from data for models ¶51 " processes both structured and unstructured data and generates automatic features. Personalized patient engagement engine 120 extracts patient engagement semantics from CM notes using natural language processing (NLP) tools"]
Mulligans, Das, Du and Chakrabarti do not specifically teach generating a set of resident groups based on the respective pluralities of resident attributes; generating a plurality of service groups, from the set of services, based on co-occurrences of services in the data for the plurality of residents; and mapping each respective resident group of the set of resident groups to a corresponding subset of services based at least in part on the plurality of service groups.
However, Hu teaches generating a set of resident groups based on the respective pluralities of resident attributes; [groups patient events ¶16-17 "Events of a patient trace are segmented into event groups according to a temporal relationship between consecutive events."]
generating a plurality of service groups, from the set of services, based on co-occurrences of services in the data for the plurality of residents; and [co-occurrences of events include services ¶16-17 "A co-occurrence matrix is formed, where the events of the event groups are represented as both rows and columns of the co-occurrence matrix"]
mapping each respective resident group of the set of resident groups to a corresponding subset of services based at least in part on the plurality of service groups. [maps groups to a cluster of events (services) ¶16-17 " Clustering (e.g., by singular value decomposition) is performed on the co-occurrence matrix to determine event clusters. Event clusters are then used to aggregate events in patient traces such that patient traces are reduced"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligans, Das, Du and Chakrabarti by incorporating the generating a set of resident groups based on the respective pluralities of resident attributes; generating a plurality of service groups, from the set of services, based on co-occurrences of services in the data for the plurality of residents; and mapping each respective resident group of the set of resident groups to a corresponding subset of services based at least in part on the plurality of service groups disclosed by Hu because all techniques address the same field of health care and by incorporating Hu into Mulligans, Das, Du and Chakrabarti improves pattern analysis to better identify the most predictive of an outcome [Hu ¶19].
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Mulligan in view of Das, Du and Chakrabarti as applied to the rejection of claim 8 above, and further in view of Dunstan et al. (US 11114203 B1 hereinafter Dunstan)
As to dependent claim 10, the combination of Mulligans, Das, Du and Chakrabarti teach all the limitations of claim 8 that is incorporated.
Mulligan, Das, Du and Chakrabarti further teach outputting the set of predicted fitness scores to a care provider; [Mulligan outputs to providers ¶26]
receiving selection, from the care provider, of a subset of services from the set of services; and [Mulligan experts can vote (select) ¶24]
Mulligan, Das, Du and Chakrabarti do not specifically teach scheduling the subset of services for the resident.
However, Dunstan teaches scheduling the subset of services for the resident. [generates care schedule (service plans) using learning Col. 6 ln. 53-67 " ECSP server may be configured to process all of the user and caregiver data (e.g., events of the user, and schedules and preferences of the caregivers) the ECSP server receives from the user and caregivers (e.g., through the ECSP application) and coordinate a care schedule of the user between the caregivers and/or promote user engagement with the ECSP application. "]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligan, Das, Du and Chakrabarti by incorporating the scheduling the subset of services for the resident disclosed by Dunstan because all techniques address the same field of health care and by incorporating Dunstan into Mulligan, Das, Du and Chakrabarti allows the user to quickly and easily check-in with the caregivers, giving the caregivers peace of mind and improving engagement [Dunstan Col. 17 ln. 37-54].
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Mulligan in view of Das, Du, Chakrabarti and Dunstan as applied to the rejection of claim 10 above, and further in view of Schmidt et al. (US 20120232930 A1 hereinafter Schmidt)
As to dependent claim 11, the combination of Mulligan, Das, Du Chakrabarti and Dunston teach all the limitations of claim 10 that is incorporated.
Mulligan, Das, Du Chakrabarti and Dunston further teach wherein outputting the set of predicted fitness scores comprises displaying the set of services and the set of predicted fitness scores on a graphical user interface (GUI), comprising, for each respective service of the set of services: [Mulligan gui based on score ¶122 "The ranked OMAs may be displayed with the matching SECGs via a graphical user interface (“GUI”)"]
generating a visual depiction of suitability of the respective service for the resident based on the selected manner of presentation. [Mulligan displays and allows for voting in GUI ¶122 "The domain expert(s) 710 may vote on one or more dimensions of the ranked OMAs and/or the matching SECGs, as in block 718. The CPG section generation component 416 may re-rank the OMAs (e.g., updating the ranking score)"]
Mulligan, Das, Du, Chakrabarti and Dunston do not specifically teach selecting a manner of presentation based on a corresponding predicted fitness score from the set of predicted fitness scores;
However, Schmidt teaches selecting a manner of presentation based on a corresponding predicted fitness score from the set of predicted fitness scores; [selects a highlight manner according to a value (score) ¶13 "The system then determines which of the potential next clinical actions has the highest quality value and highlights on a graphical user interface a representation of the potential next clinical action having the highest quality value"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligan, Das, Du, Chakrabarti and Dunston by incorporating the selecting a manner of presentation based on a corresponding predicted fitness score from the set of predicted fitness scores by Schmidt because all techniques address the same field of health care and by incorporating Schmidt into Mulligan, Das, Du, Chakrabarti and Dunston lowers costs and finds more optimal clinical options [Schmidt ¶32]
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Mulligan in view of Das, Du and Chakrabarti as applied to the rejection of claim 8 above, and further in view of McGillin.
As to dependent claim 12, the combination of Mulligans, Das, Du and Chakrabarti teach all the limitations of claim 8 that is incorporated.
Mulligans, Das, Du and Chakrabarti further teach generating a plurality of residential service plans for a plurality of residents in a residential care facility; [Das system generates a care plan for residents ¶89, ¶76 " a care plan personalization assistant in ongoing care. The CM system recommends patient-specific goals (e.g., weight loss) and corresponding interventions for achieving those goals (e.g., self-monitoring, counseling)."]
generating an aggregate service plan based on the plurality of residential service plans; and [Mulligan enhances existing guidelines (uses past sets make new sets of actions) ¶23 "collaboratively generating one or more new/additional sections of CPGs, while also enhancing existing sections of clinical guidelines"]
Mulligans, Das, Du and Chakrabarti do not specifically teach facilitating staff allocation based on the aggregate service plan.
However, McGillin teaches facilitating staff allocation based on the aggregate service plan. [Assigns care according to staff and acuity ¶13 "A translation processor interprets determined acuity scores in real time to identify required staff competencies and compare the required staff competencies with an existing available skill mix for an entire care unit and for a single patient care assignment,"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligans, Das, Du and Chakrabarti by incorporating the facilitating staff allocation based on the aggregate service plan disclosed by McGillin because all techniques address the same field of health care and by incorporating McGillin into Mulligans, Das, Du and Chakrabarti enables efficient managing decisions in real time more according to patient needs [McGillin ¶12]
Claims 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Mulligan in view of Das, McGillin, Du and Chakrabarti.
As to independent claim 18, Mulligan teaches a system, comprising: [system ¶14]
one or more computer processors; and [processor ¶125]
one or more memories containing a program which when executed by the one or more computer processors performs an operation, the operation comprising: [CRM with memory, instructions and processor ¶125, ¶132]
accessing resident data describing a resident; [patient profiles and historical data ¶79 "historical data collected from one or more data sources, one or more user profiles, a domain knowledge, feedback data, or a combination thereof"]
generating a residential service [[plan]] for the resident, comprising: [recommended actions (examples ¶80) in a guideline (CPG) of service ¶77 " Each of the one or more of the recommended user medical actions may be selected and ranked. The one or more of the recommended user medical actions may be added, according to the selecting and ranking, as an additional CPG or as an enhancement to one or more of the matching portions of the recommended user medical actions."]
generating a set of predicted fitness scores for a set of services by processing the set of features using a machine learning model trained based on one or more collaborative filtering techniques; and [generates scores using historical data (features) (supports collaborative filtering ¶106 and machine learning ¶98) ¶94 "a ranking algorithm computes a score based on a confidence interval, using a threshold on the ranking score (when the ranking of an OMA is above that threshold, learning a value of the threshold dynamically based on historical data"]
implementing the residential service plan for the resident based at least in part on the set of predicted fitness scores, comprising, for each respective service of the set of services: [adds actions for a CPG guideline (plan implemented) based on the score (threshold) ¶96 "CPG section generation component 416 may then add the optimal medical actions 420 as the additional CPG upon the ranking score exceeding the predetermined threshold."]
selecting [[a manner of]] presentation based on a corresponding predicted fitness score from the set of predicted fitness scores; and [score is a ranking that selects which to display ¶122 "The ranked OMAs may be displayed with the matching SECGs via a graphical user interface (“GUI”)"]
Mulligan does not specifically teach residential service plans and extracting a set of features from the resident data;
However, Das teaches residential service plans [system generates a care plan ¶22, ¶76 " a care plan personalization assistant in ongoing care. The CM system recommends patient-specific goals (e.g., weight loss) and corresponding interventions for achieving those goals (e.g., self-monitoring, counseling)."]
extracting a set of features from the resident data; [extracts features from data for models ¶51 " processes both structured and unstructured data and generates automatic features. Personalized patient engagement engine 120 extracts patient engagement semantics from CM notes using natural language processing (NLP) tools"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify the modeling disclosed by Mulligan by incorporating the residential service plans and extracting a set of features from the resident data disclosed by Das because both techniques address the same field of health services and by incorporating Das into Mulligan improves services helping assist patient care [Das ¶3, ¶18]
Mulligan and Das do not specifically teach selecting a manner of presentation based on a corresponding predicted fitness score from the set of predicted fitness scores;
However, Schmidt teaches selecting a manner of presentation based on a corresponding predicted fitness score from the set of predicted fitness scores; [selects a highlight manner according to a value (score) ¶13 "The system then determines which of the potential next clinical actions has the highest quality value and highlights on a graphical user interface a representation of the potential next clinical action having the highest quality value"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligan and Das by incorporating the selecting a manner of presentation based on a corresponding predicted fitness score from the set of predicted fitness scores by Schmidt because all techniques address the same field of health care and by incorporating Schmidt into Mulligan and Das lowers costs and finds more optimal clinical options [Schmidt ¶32].
Mulligan, Das and Schmidt do not specifically teach generating a plurality of resident groups based on resident-to-resident similarity using the one or more collaborative filtering techniques and based on a plurality of features; generating a group-to-service mapping based on service-to-service similarity measures for a plurality of services provided to residents; identifying a set of proposed services based on the first resident group and the group-to-service mapping;
However, Du teaches generating a plurality of resident groups based on resident-to-resident similarity using the one or more collaborative filtering techniques and based on a plurality of features; [Clusters (groups) based on similarity between users (residents) ¶46-48 "k-means clustering algorithm based on a similarity between users "]
generating a group-to-service mapping based on service-to-service similarity measures for a plurality of services provided to residents; [Du group to item database based on similarity ¶39, ¶30 " a user group item similarity database, configured to record a similarity between items corresponding to each user group generated based on the user grouping result."]
identifying a set of proposed services based on the first resident group and the group-to-service mapping; and [determines items (services) to recommend based on group item similarity ¶40, 74 " based on an item similarity and a user item rating in the user group to which the target user belongs, items that have a high similarity to an item with a high user rating and that the target user does not rate are selected as a set to be recommended"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligan, Das and Schmidt by incorporating the generating a plurality of resident groups based on resident-to-resident similarity using the one or more collaborative filtering techniques and based on a plurality of features; generating a group-to-service mapping based on service-to-service similarity measures for a plurality of services provided to residents; identifying a set of proposed services based on the first resident group and the group-to-service mapping disclosed by Du because all techniques address the same field of machine learning and by incorporating Du into Mulligan, Das and Schmidt improves recommendation accuracy and quality accounting for groups of preferences [Du ¶11]
Mulligan, Das, Schmidt and Du do not specifically teach in response to determining that a threshold percentage of features, from the resident data, match feature values associated with the first resident group;
However, Chakrabarti teaches in response to determining that a threshold percentage of features, from the resident data, match feature values associated with the first resident group; [Connects based on threshold of attributes (features) that match ¶43, ¶6 "a relationship factor is determined based on a number of characteristics of a user connected to an object that match"]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligan, Das, Schmidt and Du by incorporating the disclosed by Chakrabarti because all techniques address the same field of machine learning and by incorporating Chakrabarti into Mulligan, Das, Schmidt and Du identifies the attributes that are relevant and sufficient for quality recommendations and connections [Chakrabarti ¶4].
As to dependent claim 19, the rejection of claim 18 is incorporated, Mulligan, Das, Schmidt, Du and Chakrabarti further teach wherein generating the set of predicted fitness scores for the set of services comprises: assigning the resident to a first resident group, of a plurality of resident groups indicated in the machine learning model, based on the set of features; [Das groups based on similar profiles and phenotypes Fig. 8 801 ¶86 "matches the patient to a behavioral phenotype according to a similarity of the patient's interactional, contextual, and behavioral features to the prototypical cases of each phenotype (block 801). The mechanism estimates the propensity of positive behavioral responses of each of the targeted behaviors (block 802). Then, the mechanism dynamically updates the personalized intervention effectiveness rankings in context for CM and patient's decision-making based on what has been shown to lead to positive responses for individuals with similar behavioral profile (block 803)"]
identifying the set of services based on determining that the set of services is associated with the first resident group in the machine learning model; and [Das identifies interventions (services) accordingly Fig. 8 803-804 ¶86 "ranking, the mechanism recommends the most effective intervention for the patient given the goal assigned and the individual intervention effect estimation (block 804)"]
generating the set of predicted fitness scores based on historical fitness scores used to train the machine learning model. [Mulligan score based votes and updates are used ¶122-124, ¶128 "rank or re-rank the one or more useful medical actions according to a scoring criteria"]
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Mulligan in view of Das, Schmidt, Du and Chakrabarti, as applied to the rejection of claim 18 above, and further in view of Dunstan.
As to dependent claim 20, the combination of Mulligan, Das, Schmidt, Du and Chakrabarti teach all the limitations of claim 18 that is incorporated.
Mulligan, Das, Schmidt, Du and Chakrabarti further teach outputting the set of predicted fitness scores to a care provider; [Mulligan outputs to providers ¶26]
receiving selection, from the care provider, of a subset of services from the set of services; and [Mulligan experts can vote (select) ¶24]
Mulligan, Das, Schmidt, Du and Chakrabarti do not specifically teach scheduling the subset of services for the resident.
However, Dunstan teaches scheduling the subset of services for the resident. [generates care schedule (service plans) using learning Col. 6 ln. 53-67 " ECSP server may be configured to process all of the user and caregiver data (e.g., events of the user, and schedules and preferences of the caregivers) the ECSP server receives from the user and caregivers (e.g., through the ECSP application) and coordinate a care schedule of the user between the caregivers and/or promote user engagement with the ECSP application. "]
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention to modify data modelling disclosed by Mulligan, Das, Schmidt, Du and Chakrabarti by incorporating the scheduling the subset of services for the resident disclosed by Dunstan because all techniques address the same field of health care and by incorporating Dunstan into Mulligan, Das, Schmidt, Du and Chakrabarti allows the user to quickly and easily check-in with the caregivers, giving the caregivers peace of mind and improving engagement [Dunstan Col. 17 ln. 37-54].
Response to Arguments
Applicant's arguments filed 07/29/2025. With respect to the 101 rejections these rejections have been withdrawn.
Applicant's arguments filed 07/29/2025. In the remark, applicant argues that:
(1) Mulligan and Das fail to teach new language including " identifying a plurality of resident groups generated based on resident-to-resident similarity using the one or more collaborative filtering techniques, wherein the resident-to-resident similarity is defined based on a plurality of features; assigning the resident to a first resident group, of the plurality of resident groups in response to determining that a threshold percentage of features, from the set of features, match feature values associated with the first resident group; and identifying the set of services based on the first resident group and a group-to-service mapping generated based on service-to- service similarity measures" as recited in amended claim 1, 8 and 18 and discussed over interview.
As to point (1), Applicant’s arguments with respect to claim 1 have been considered but are moot in view of a new ground of rejection as set forth above of Mulligan in view of Das, Du and Chakrabarti.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Applicant is required under 37 C.F.R. § 1.111(c) to consider these references fully when responding to this action.
Wu et al. (US 20220253722 A1) teaches user similarity thresholds when making recommendations (See ¶18).
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BEAU SPRATT whose telephone number is (571)272-9919. The examiner can normally be reached M-F 8:30-5 PST.
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, Jennifer Welch can be reached on 5712127212. 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.
/BEAU D SPRATT/ Primary Examiner, Art Unit 2143
Prosecution Insights