DETAILED ACTION
Acknowledgement
This final office action is in response to the amendment filed on 04/19/2026.
Status of Claims
Claims 1 and 4 have been amended.
Claims 1-8 are now pending.
Response to Arguments
Claim 4 objection is withdrawn in light of amendments.
Applicant's arguments filed on 04/19/2026 regarding the 35 U.S.C. 101 and 103 rejections of claims 1-8 have been fully considered. The Applicant argues the following:
(1) As per the 101 rejection, the Applicant argues, in summary, that the claims do not recite a mental process or a method of organizing human activity and the claims integrate the alleged abstract idea into a practical application.
The Examiner respectfully disagrees. The Examiner maintains the position that the claims are directed to both abstract groups of Mental Processes and Certain Methods of Organizing Human Activity because the claims describes a process of analyzing data with trained mathematical models to predict, recommend, and schedule a personalized coaching plan for a person/agent. Estimating and optimizing predictions using mathematical models and processes is abstract and can be practically performed in the mind and does not require a computer to perform. Recommending and scheduling a coaching plan to an agent reflects certain methods of organizing human activity as the personalized coaching plan directs/manages an agent’s personal behavior and also does not require a computer to perform. Per MPEP 2106.04(a), a claim recites a judicial exception when the judicial exception is “set forth” or “described” in the claim.
The Examiner also maintains the position that the additional elements recited in the claims and listed in Step 2A(2) does not integrate the abstract idea into a practical application because the additional elements do not improve the functioning of a computer or improve another technology. These additional elements are viewed as mere instructions to implement an abstract idea on a computer and merely indicates a field of use or technological environment in which to apply the abstract idea. Applying an abstract idea on a computer and/or generally linking the use of the abstract idea to a particular technological environment does not integrate a judicial exception into a practical application or provide an inventive concept (see MPEP 2106.05 (f) and (h)). Therefore, the 35 U.S.C. 101 rejection is maintained.
(2) As per the 103 rejections, the Applicant argues that Beaver and Pryluk whether considered individually or in combination, fail to teach or suggest the claimed invention. The Examiner's proposed combination is based on hindsight reconstruction and an overly generalized reading of both references.
The Examiner respectfully disagrees. The Examiner submits that based on the broadest reasonable interpretation (BRI) of the claims, that the combination of Beaver and Pryluk teach the recited limitations of amended claim 1 as shown in the updated claim mapping below. In summary, Beaver teaches an automated, real-time coaching system that provides personalized coaching and training to agents based on KPI targets, KPI predictions, and the analysis of agent performance. The coaching plans address specific agent activities and behaviors that would improve KPI metrics and agent performance. While Beaver teaches using machine learning models to assess agent performance improvement and predict KPI metrics, Beaver does not explicitly teach using a CATE estimator. However, Pryluk teaches using a CATE estimator to analyze impact of a treatment on a patient population. The examiner submits that both Beaver and Pryluk are directed towards analyzing the effect of treatments (e.g. coaching plan or clinical trials) to a specific population (agent or patients) using mathematical models. Furthermore, all of the claimed elements were known in the prior arts of Beaver and Pryluk and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination would have yielded predictable results to one of ordinary skill in the art at the time of the invention.
As per MPEP 2145, Applicants may argue that the examiner’s conclusion of obviousness is based on improper hindsight reasoning. However, "any judgment on obviousness is in a sense necessarily a reconstruction based on hindsight reasoning, but so long as it takes into account only knowledge which was within the level of ordinary skill in the art at the time the claimed invention was made and does not include knowledge gleaned only from applicant’s disclosure, such a reconstruction is proper." In re McLaughlin, 443 F.2d 1392, 1395, 170 USPQ 209, 212 (CCPA 1971). Therefore, the 35 U.S.C. 103 rejections are proper and have been maintained.
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 .
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 1-8 are rejected under 35 U.S.C. 101 because the claimed invention, “System and Method for Personalized Coaching Recommendation”, is directed to an abstract idea, specifically Mental Processes and Certain Methods of Organizing Human Activity, without significantly more. The claims as a whole do not include additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the abstract idea because the additional elements individually or in combination provide mere instructions to implement the abstract idea on a computer.
Step 1: Claims 1-8 are directed to a statutory category, namely a process.
Step 2A (1): Claims 1-8 are directed to an abstract idea of Mental Processes and Certain Methods of Organizing Human Activity, based on the following claim limitations: “…determining an agent personalized coaching; for each agent… retrieving …historical data, wherein said historical data includes at least one of: a) past feedback; b) Key Performance Information (KPI)s; and c) coaching training sessions; (ii) cleaning and structuring the historical data …; (iii) assessing a level of impact of a plurality of coaching-plans based on the structured historical data to predict an effective-score for each coaching-plan in the plurality of coaching-plans on the KPIs by operating a Conditional Average Treatment Effect (CATE) estimator on the coaching-plan; (iv) normalizing the effective-score of each coaching-plan and storing the normalized effective-score of each coaching-plan…; (v) automatically selecting the personalized coaching-plan by operating a recommendation model on effective-scores…; and (vi) automatically scheduling the personalized coaching plan for the agent.(claim 1); …optimize the output-predictions by adjusting the output-predictions based on aggregated learning process across multiple agents and related coaching plans (claim 2);… a model that applies a single mode across all data points to predict a KPI change, … a model that uses two separate models for treated and control groups of agents to enhance accuracy of the predicted effective-score of the coaching plan, a model that improves estimates of the CATE estimator (claim 3); wherein said recommendation model comprising evaluating each normalized effective-score of each coaching-plan in a data-storage and selecting the personalized coaching-plan having the effective-score above a preconfigured threshold. (claim 4); wherein the selected personalized coaching-plan comprising one or more coaching-plans. (claim 5); wherein said…model is trained by providing a single model xi,t to predict Y(t), whereby xi is agent properties of past feedback and KPIs, and t indicates if the agent is treated and participated in the coaching plan, wherein when t = 0 then the agent is in control group of agents and wherein when t = 1 then the agent participated in the coaching plan, and Y(t) is the KPI change. (claim 6); wherein said… model is trained by training a first model in the two separate models to predict the change in KPI after the agent participated in the coaching plan and a second model in the two separate models to predict the change in KPI when the agent didn’t participate in the coaching plan. (claim 8) ”. These claims limitations describe a process of analyzing data with trained models to predict, recommend, and schedule a personalized coaching plan for a person/agent. Analyzing data with trained models to predict an outcome (e.g. the best coaching plan for an agent) can practically be performed in the human mind with pen and paper. Training could consist of fitting a particular mathematical model/algorithm to a dataset by adjusting/tuning coefficients, weights, or parameters to provide a specific output. Recommending and scheduling a coaching plan to an agent reflects certain methods of organizing human activity as the personalized coaching plan directs/manages an agent’s personal behavior. Therefore, these limitations, under the broadest reasonable interpretation, fall within the abstract groupings of Mental Processes which include concepts performed in the human mind such as observations, evaluations, judgments, and opinions and Certain Methods of Organizing Human Activity which encompasses managing personal behavior or relationships or interactions between people including social activities, teaching, and following rules or instructions. Mental Processes include claims directed to collecting information, analyzing it, and displaying certain results of the collection and analysis even if they are claimed as being performed on a computer. The courts have found claims requiring a generic computer or nominally reciting a generic computer may still recite a mental process even though the claim limitations are not performed entirely in the human mind. Certain Methods of Organizing Human Activity can encompass the activity of a single person (e.g. a person following a set of instructions), activity that involve multiple people (e.g. a commercial interaction), and certain activity between a person and a computer (e.g. a method of anonymous loan shopping). Therefore, claims 1-8 are directed to an abstract idea and are not patent eligible.
Step 2A (2): The claims as a whole do not integrate this abstract idea into a practical application. In particular, claims 1-4 and 6-8 recite additional elements of “computerized-method; database; one or more processors; a data processor; a data-storage; …wherein the recommendation model generates and automatically schedules the personalized coaching plan for the agent within a coaching web application (claim 1); meta-learner models (claims 2); meta-learner models are at least one of (i) S-learner model; (ii) T-learner model; (iii) X-learner model; and (iv) R-learner model (claims 3, 6, and 8); data-storage (claim 4); and Extreme Gradient Boosting (XGBoost) model (claim 7) ”. These additional elements do not integrate the abstract idea into a practical application because the claims do not recite (a) an improvement to another technology or technical field and (b) an improvement to the functioning of the computer itself and (c) implementing the abstract idea with or by use of a particular machine, (d) effecting a particular transformation or reduction of an article, or (e) applying the judicial exception in some other meaningful way beyond generally linking the use of an abstract idea to a particular technological environment. These additional elements evaluated individually and in combination are viewed as computing and display devices that are used to perform the abstract process of analyzing data with trained models to predict, recommend, and schedule a personalized coaching plan for a person/agent. Limitations that recite mere instructions to implement an abstract idea on a computer or merely uses a computer as a tool to perform an abstract idea are not indicative of integration into a practical application (see MPEP 2106.05(f)). Limitations that amount to merely indicating a field of use or technological environment (e.g. computer/machine learning) in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application (see MPEP 2106.05(h)). Therefore, claims 1-8 as a whole do not include individual or a combination of additional elements that integrate the abstract idea into a practical application and thus are not patent eligible.
Step 2B: The claims as a whole do not include additional elements that are sufficient to amount to significantly more than the abstract idea. Claims 1-4 and 6-8 recite additional elements of “computerized-method; database; one or more processors; a data processor; a data-storage (claim 1); meta-learner models (claims 2); meta-learner models are at least one of (i) S-learner model; (ii) T-learner model; (iii) X-learner model; and (iv) R-learner model (claims 3, 6, and 8); data-storage (claim 4); and Extreme Gradient Boosting (XGBoost) model (claim 7) ”. These additional elements evaluated individually and in combination are viewed as mere instructions to implement an abstract idea on a computer and merely indicates a field of use or technological environment in which to apply a judicial exception. The use of trained machine learning models (e.g. meta learners and XGBoost) are considered instructions to apply or implement a model on a computer. Applying an abstract idea on a computer and/or generally linking the use of the abstract idea to a particular technological environment does not integrate a judicial exception into a practical application or provide an inventive concept (see MPEP 2106.05 (f) and (h)). Therefore, claims 1-8 as a whole do not include individual or a combination of additional elements that are sufficient to amount to significantly more than the abstract idea and thus are not patent eligible.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-6 and 8 are rejected under 35 U.S.C. 103 as being unpatentable over Beaver et al. (US 2025/0315746 A1) in view of Pryluk et al. (US 20250372212 A1).
As per claim 1 (Currently Amended), Beaver teaches a computerized-method for determining an agent personalized coaching, said computerized method comprising (Beaver e.g. One aspect provides a method for providing automated agent coaching [0005]. FIGS. 5 and 6 depict illustrative block diagrams 500-1 and 500-2 corresponding to an automated agent coaching process [0076].):
for each agent in an agents database (Beaver e.g. It should be understood that the term “agent” as discussed herein refers to either human agents or computer-driven bots, such as chatbots, unless specifically stated otherwise [0020]. FIG. 10 depicts an example apparatus 1000 configured to perform the methods described herein [0132]. Apparatus 1000 further includes a memory 1010 configured to store various types of components and data [0136]. ) :
Beaver teaches (i) retrieving by one or more processors historical data, wherein said historical data includes at least one of: a) past feedback; b) Key Performance Information (KPI)s; and c) coaching training sessions; (Beaver e.g. The automated agent performance ranking processes described herein provide techniques for analyzing historical interaction data and near real-time customer-agent interactions to develop agent performance scores based on features of a customer-agent interaction, the type or difficulty of task being performed, and generating reports regarding the performance [0020]. The automated agent performance ranking processes can also directly report on the highest and lowest performing agents on features under the agents control that have a direct statistical link to the client chosen KPI metrics [0029]. KPI metrics include, but are not limited to, customer satisfaction scores (CSAT), customer churn rate (Churn), net promoter score (NPS), and the like [0024].)
Beaver teaches (ii) cleaning and structuring the historical data by operating by the one or more processors a data processor; (Beaver e.g. For each feature under agents' control, the agents are ranked by historical performance. The rankings are reported to agent coaching applications, for example, in a highest to lowest agent rank based on historical performance [0030]. Each agent's performance for each feature on the latest interaction is compared to their own historical performance by applying an outlier detection process. If there is a significant drop in performance over any feature as determined by a threshold, an indication (e.g., an alert or report) is made to the agent coaching applications [0031]. The automated agent coaching processes described herein provide technical solutions for automatically analyzing interaction history, performance and task-specific activities between groups of relatively higher and relatively lower performing agents [0033]. FIG. 3 schematically depicts an illustrative block diagram of an automated agent performance ranking process [0012]. Step 307 includes, for example, filtering out the features from the initial plurality of features (e.g., Feature 1, Feature 2, . . . , Feature n) that the contact center agent has no control over based on a set of predefined features determined to be in control of the agent [0052]. At step 314, the automated agent performance ranking process receives a KPI metric that is chosen by a user (e.g., from step 304), a filtered set of features corresponding to those that are under an agent's control (e.g., from step 308), a list of features that are task dependent (e.g., from step 312), and historical interactions for a plurality of agents (e.g., from step 316). The historical interactions for a plurality of agents, from step 316, include customer-agent interaction data for a plurality of agents over a period of time [0057].)
Beaver teaches (iii) assessing a level of impact of a plurality of coaching-plans based on the structured historical data to predict an effective-score for each coaching-plan in the plurality of coaching-plans on the KPIs by operating machine learning models (Beaver e.g. The present disclosure provides systems, methods, and apparatuses for predicting KPIs from customer-agent interactions [0024]. The KPI prediction and improvement processes enable the prediction of a value for a KPI metric, irrespective of the presence of a post interaction survey, and can further provide suggested agent-controllable features of a customer-agent interaction that can be improved to maintain or improve a KPI metric [0024]. The present disclosure provides solutions to this problem which include training classifier models, such as a gradient boosting classifier, random forest classifier, or other machine learning-based classifiers to analyze features of a customer-agent interaction and predict a value for the desired KPI metric [0026]. The automated agent coaching processes described herein provide technical solutions for automatically analyzing interaction history, performance and task-specific activities between groups of relatively higher and relatively lower performing agents [0033]. The analysis provides insights into what types of activities or behaviors, with respect to features of a customer-agent interaction, should be addressed, for example, by comparing what high-performing agents do compared to low-performing agents [0033]. In some aspects, statistical analysis of values such as performance scores on features and corresponding tasks are determined for high and low-performing agents or groups of agents to determine whether there are statically relevant differences [0033]. The statically relevant differences can provide indication as to what activity, features, and task related to the activity or feature differ and thus require coaching [0033]. Automatic and tailored coaching provides a technical benefit of providing efficient and effective training that directly relates to improvement potential for the agent and furthermore increasing and/or maintaining a target value for a KPI metric [0034]. FIG. 1 depicts an illustrative block diagram 100 of a KPI prediction process for predicting a client chosen KPI metric is depicted [0035]. The KPI prediction process predicts a value for the KPI metric and provides an indication of one or more features that can maintain and/or improve the value of the KPI metric when the one or more features are improved (i.e. impact) [0035]. The KPI prediction process includes invoking a model 125 configured predict the value for the KPI metric based on a plurality of features that the classifier model identifies and measures from the customer-agent interaction data. More specifically, the model 125 is configured to ingest customer-agent interaction data 124, a feature set 119, and the KPI metric and target value for the KPI metric 128 [0035]. The selected model 125 generates a predicted value for the KPI metric specified by the client. The selected model 125 may be a classifier model or another type of machine learning model configured to perform as described herein [0036]. The model 125 predicts a value for the KPI metric based on a plurality of features that the classifier model 125 identifies and measures from the customer-agent interaction data [0036]. Additionally, the model 125 generates a score for each feature associated with the KPI metric. Each feature score corresponds to an agent's performance with respect to the feature during the customer-agent interaction [0036]. The model 125 then outputs the predicted value 131 for further utilization by the system executing the KPI prediction process or by another system or application, such as an agent coaching application or a performance ranking application [0036].)
Beaver teaches (iv) normalizing the effective-score of each coaching-plan and storing the normalized effective-score of each coaching-plan in a data-storage; (Beaver e.g. As described in more detail herein, the technical solutions provide techniques that dissect and analyze performance on an equal basis to derive reports that identify changes in performance of an agent, gaps in knowledge or skills of an agent, as well as ranking agents in groups based on specific tasks and skills (e.g., performance with respect to features that drive KPI metrics) [0029]. There may be instances where the feature value of the human agent feature and the chatbot agent feature, such as time in the aforementioned example, needs to be normalized in order to be compared for ranking the human agent and chatbot agent based on corresponding, but not exact same type of feature [0067]. The automated agent coaching process then compares the two groups feature by feature to generate feedback. In a similar example, at step 706, a chatbot specific feature of amount of time a chatbot spent generating a response to an input may be normalized and compared with the human agents' performance related to the amount of time the human agent spent talking [0100].)
Beaver teaches (v) automatically selecting the personalized coaching-plan by operating a recommendation model on effective-scores in the data-storage; and (Beaver e.g. The technical solutions further provide a process for identifying features of the customer-agent interaction that have a potential for improvement and providing a recommendation as to which features and the amount each of the features need to be improved to meet a target value for the KPI metric [0027]. Coaching modules may be predefined by supervisors and selected for deployment when an agent's performance corresponding to the activity, feature, or task is indicated as requiring improvement [0033]. Automatic and tailored coaching provides a technical benefit of providing efficient and effective training that directly relates to improvement potential for the agent and furthermore increasing and/or maintaining a target value for a KPI metric [0034]. For example, guidance can be sent to agent coaching applications for offline training recommendations, or for online coaching, such as pop-up reminders during an interaction to use applications or features observed to be used by high-performing groups. Deployment of the real time agent coaching may be sent to Engagement Orchestration (EO)/Channel Automation (CA) at step 560 [0088].)
Beaver teaches (vi) automatically scheduling the personalized coaching plan for the agent (Beaver e.g. Automatic and tailored coaching provides a technical benefit of providing efficient and effective training that directly relates to improvement potential for the agent and furthermore increasing and/or maintaining a target value for a KPI metric [0034]. FIGS. 5 and 6 depict illustrative block diagrams 500-1 and 500-2 corresponding to an automated agent coaching process [0076]. The automated agent coaching process may be initiated by a supervisor or by other triggers indicating that agent training is needed. In some aspects, the automated agent coaching process may concurrently run while an agent is performing interactions with a customer so that near real-time coaching can be provided when activity or behaviors corresponding to features are determined to not align with best practices [0077]. Step 550 includes deploying the generated guidance to the second group. The guidance may be deployed in near real-time or as training modules one or more agents can complete when not engaged in a customer-agent interaction [0088]. Guidance can be sent to agent coaching applications for offline training recommendations, or for online coaching such as pop-up reminders during an interaction to use applications or features observed to be used by high-performing groups [0092].), wherein the recommendation model generates and automatically schedules the personalized coaching plan for the agent within a coaching web application (Beaver e.g. Coaching modules may be predefined by supervisors and selected for deployment when an agent's performance corresponding to the activity, feature, or task is indicated as requiring improvement [0033]. The selected model 125 generates a predicted value for the KPI metric specified by the client. The model 125 predicts a value for the KPI metric based on a plurality of features that the classifier model 125 identifies and measures from the customer-agent interaction data. The model 125 then outputs the predicted value 131 for further utilization by the system executing the KPI prediction process or by another system or application, such as an agent coaching application or a performance ranking application [0036]. At step 146, coaching specific to improving features of an agent's interactions with a customer are generated such that training or refreshers that are relevant to the agents. Furthermore, tailored coaching provides a technical benefit of providing efficient and effective training that directly relates to improvement potential for the agent [0049]. The technical solutions provide techniques that dissect and analyze performance on an equal basis to derive reports that identify changes in performance of an agent, gaps in knowledge or skills of an agent, as well as ranking agents in groups based on specific tasks and skills (e.g., performance with respect to features that drive KPI metrics) [0029]. The generated reports may be provided to an agent coaching application at step 350, where customized agent coaching is automatically generated and implemented, for example, absent the need for analysis and/or direction of a supervisor 360 [0068]. The automated agent coaching process may be initiated by a supervisor or by other triggers indicating that agent training is needed. In some aspects, the automated agent coaching process may concurrently run while an agent is performing interactions with a customer so that near real-time coaching can be provided when activity or behaviors corresponding to features are determined to not align with best practices [0077].)
Beaver does not explicitly teach, however, Pryluk teaches assessing by operating a Conditional Average Treatment Effect (CATE) estimator on the treatment (e.g. coaching-plan); (Pryluk e.g. According to some embodiments, there is provided a method for identifying one or more treatment subpopulations within a patient population of a clinical study, the method including applying at least two different causal predictive models on the dataset, each causal predictive model configured to output a Conditional Average Treatment Effect (CATE) for each point in the multidimensional feature space; [0013]. According to some embodiments, the clinical study may be a real-world study. As used herein the term, “real world study” refers to the collection of Real-world data (RWD)… [0043].The method includes applying at least two different causal predictive models on the dataset. According to some embodiments, each causal predictive model configured to output a predicted Conditional Average Treatment Effect (CATE) for each point in the multidimensional feature space (real and/or hypothetic) [0050]. As used herein, the terms “Conditional Average Treatment Effect” and “CATE” refer to a difference between the expected outcomes of the two treatments conditioned on covariates, i.e. the average effect of a treatment on a sub-group, wherein the validity of the estimate is conditional on being part of this subgroup. CATE is distinct from ATE, which is the average treatment effect on an entire study population [0053].)
The Examiner submits that before the effective filing date, it would have been obvious to one of ordinary skill in the art to combine Beaver’s Automated Agent Coaching Method with Pryluk’s CATE estimator assessment method in order to providing a more accurate assessment of how different groups will respond to treatments (Pryluk e.g. [0110]).
Both Beaver and Pryluk are directed towards analyzing the effect of treatments (e.g. coaching plan or clinical trials) to a specific population (agent or patients) using mathematical models. Furthermore, all of the claimed elements were known in the prior arts of Beaver and Pryluk and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination would have yielded predictable results to one of ordinary skill in the art at the time of the invention.
As per claim 2 (Original), Beaver in view of Pryluk teach the computerized-method of claim 1, Beaver does not explicitly teach, however, Pryluk teaches wherein said CATE estimator is employing meta-learner models to optimize output-predictions of base learner models of the CATE estimator, and wherein the meta-learner models optimize the output-predictions by adjusting the output-predictions based on aggregated learning process across multiple agents and related coaching plans. (Pryluk e.g. According to some embodiments, at least one of the at least two causal predictive models is a meta-learner [0016]. The method includes applying at least two different causal predictive models on the dataset. According to some embodiments, each causal predictive model configured to output a predicted Conditional Average Treatment Effect (CATE) for each point in the multidimensional feature space (real and/or hypothetic) [0050]. As used herein, the term “causal predictive models” and “predictive causal models” may be used interchangeably and refer to machine learning (ML) models that relate independent variables (i.e. variables which can be manipulated) to dependent variables (variables that can be measured), generating predictions for the values of dependent variables given a set of values for the independent variables. According to some embodiments, the at least two predictive models may be causal forests and/or meta learners [0056]. Meta-Learners are an estimation framework that enables using any ML model as a “base learner” for learning various nuisance functions and composing an estimator for CATE using a transformation of the learned functions [0058]. Advantageously, the herein disclosed system provides improved processing capabilities to the processor thus allowing it to reliably and robustly identify patient subgroups with patient populations of a clinical study [0030].)
The Examiner submits that before the effective filing date, it would have been obvious to one of ordinary skill in the art to combine Beaver’s Automated Agent Coaching Method with Pryluk’s CATE estimator and meta-learner models in order to providing a more accurate assessment of how different groups will respond to treatments (Pryluk e.g. [0110]).
As per claim 3 (Original), Beaver in view of Pryluk teach the computerized-method of claim 2, Beaver does not explicitly teach, however, Pryluk teaches wherein said meta-learners models are at least one of: (i) S-learner model; (ii) T-learner model; (iii) X-learner model; and (iv) R-learner model, wherein the S-learner model is a model that applies a single mode across all data points to predict a KPI change, wherein the T-learner model is a model that uses two separate models for treated and control groups of agents to enhance accuracy of the predicted effective-score of the coaching plan, and wherein the X-learner model is a model that improves estimates of the CATE estimator. (Pryluk e.g. According to some embodiments, at least one of the at least two causal predictive models is a meta-learner [0016]. Meta-Learners are an estimation framework that enables using any ML model as a “base learner” for learning various nuisance functions and composing an estimator for CATE using a transformation of the learned functions. There are several common meta-learner structures, including, but not limited to [0058]: S learner: A single (hence “S”) model is trained to regress the outcomes on the features and the treatment assignment (the treatment is treated as an additional binary variable attached to X) [0059]. T learner: This approach uses base-learners to estimate the conditional expectations of the two (hence “T”) potential outcomes—{(Xi, yi); ai=0} that are used to train {circumflex over ( )}μ0(X), an estimate for E[y|a=0] and {(Xi, yi); ai=1} to train {circumflex over ( )}μ1(X). Finally, an estimate for CATE is obtained by subtracting them [0061]. X learner: This approach builds on the foundations of the T Learner and starts similarly by estimating μ 0(X) and {circumflex over ( )}μ1(X). it then uses these estimates to impute the missing potential outcomes and generate “pseudo individual effects” [0062]. DR learner: This approach constructs a doubly-robust pseudo-outcome for CATE using a sub-sample of the training data, and uses the rest of the train-set to regress this pseudo outcome on X. First, using the first subset S1 to train {circumflex over ( )}π(X), μ{circumflex over ( )}0(X), μ{circumflex over ( )}1(X)—estimates for π(X), E[y|a=0, X], E[y|a=1, X], respectively [0064].)
The Examiner submits that before the effective filing date, it would have been obvious to one of ordinary skill in the art to combine Beaver’s Automated Agent Coaching Method with Pryluk’s CATE estimator and meta-learner models in order to providing a more accurate assessment of how different groups will respond to treatments (Pryluk e.g. [0110]).
As per claim 4 (Currently Amended), Beaver in view of Pryluk teach the computerized-method of claim 1, Beaver teaches wherein said recommendation model comprising evaluating each normalized effective-score of each coaching-plan in the data-storage and selecting the personalized coaching-plan having the effective-score above a preconfigured threshold. (Beaver e.g. Each agent's performance for each feature on the latest interaction is compared to their own historical performance by applying an outlier detection process. If there is a significant drop in performance over any feature as determined by a threshold, an indication (e.g., an alert or report) is made to the agent coaching applications [0031]. FIGS. 5 and 6 depict illustrative block diagrams 500-1 and 500-2 corresponding to an automated agent coaching process [0076]. The automated agent coaching process continues with analyzing the application event streams for statistically relevant differences for one or more activities performed by a first group of the plurality of agents compared to a second group of the plurality of agents at steps 520-524,530-534, and 540-544 [0083]. Step 522 may implement a Kolmogorov-Smirnov (KS) test for determining statistical significance between the groups based on a threshold for application usage time received from step 521, optionally set by a user of the system [0085]. When the application usage time between the first group and the second group is different and exceeds a threshold for application usage time as determined by step 524, the process proceeds to step 526 where guidance corresponding coaching on use of an application is generated [0085].)
As per claim 5 (Original), Beaver in view of Pryluk teach the computerized-method of claim 4, Beaver teaches wherein the selected personalized coaching-plan comprising one or more coaching-plans (Beaver e.g. Coaching modules may be predefined by supervisors and selected for deployment when an agent's performance corresponding to the activity, feature, or task is indicated as requiring improvement [0033]. Automatic and tailored coaching provides a technical benefit of providing efficient and effective training that directly relates to improvement potential for the agent and furthermore increasing and/or maintaining a target value for a KPI metric [0034]. For example, if a low-performing group is observed not using an application or feature of an application that is used by the high-performing group, the automated agent coaching process can automatically suggest training or coaching on that application [0089]. Guidance can be sent to agent coaching applications for offline training recommendations, or for online coaching such as pop-up reminders during an interaction to use applications or features observed to be used by high-performing groups [0092].)
As per claim 6 (Original), Beaver in view of Pryluk teach the computerized-method of claim 3, Beaver in view of Pryluk teaches wherein said S-learner model is trained by providing a single model xi,t to predict Y(t), whereby xi is agent properties of past feedback and KPIs, and t indicates if the agent is treated and participated in the coaching plan, wherein when t = 0 then the agent is in control group of agents and wherein when t = 1 then the agent participated in the coaching plan, and Y(t) is the KPI change
Beaver uses a machine learning model to predict KPI based on agent performance features of different groups (Beaver e.g. The automated agent performance ranking processes described herein provide techniques for analyzing historical interaction data and near real-time customer-agent interactions to develop agent performance scores based on features of a customer-agent interaction, the type or difficulty of task being performed, and generating reports regarding the performance [0020]. The present disclosure provides solutions to this problem which include training classifier models, such as a gradient boosting classifier, random forest classifier, or other machine learning-based classifiers to analyze features of a customer-agent interaction and predict a value for the desired KPI metric [0026]. The automated agent coaching processes described herein provide technical solutions for automatically analyzing interaction history, performance and task-specific activities between groups of relatively higher and relatively lower performing agents [0033]. The KPI prediction process includes invoking a model 125 configured predict the value for the KPI metric based on a plurality of features that the classifier model identifies and measures from the customer-agent interaction data. More specifically, the model 125 is configured to ingest customer-agent interaction data 124, a feature set 119, and the KPI metric and target value for the KPI metric 128 [0035]. Additionally, the model 125 generates a score for each feature associated with the KPI metric. Each feature score corresponds to an agent's performance with respect to the feature during the customer-agent interaction [0036].)
Beaver does not explicitly teach, however, Pryluk teaches using an S-learner model… (Pryluk e.g. S learner: A single (hence “S”) model is trained to regress the outcomes on the features and the treatment assignment (the treatment is treated as an additional binary variable attached to X)
PNG
media_image1.png
36
266
media_image1.png
Greyscale
[0059].CATE is the estimated by contrasting this model's predictions for both potential outcomes:
PNG
media_image2.png
22
208
media_image2.png
Greyscale
[0060]. Where a is the treatment assignment (0 for control, 1 for treatment [0052])
The Examiner submits that before the effective filing date, it would have been obvious to one of ordinary skill in the art to combine Beaver’s Automated Agent Coaching Method with Pryluk’s CATE estimator and meta-learner models in order to providing a more accurate assessment of how different groups will respond to treatments (Pryluk e.g. [0110]).
As per claim 8 (Original), Beaver in view of Pryluk teach the computerized-method of claim 3, wherein said T-learner model is trained by training a first model in the two separate models to predict the change in KPI after the agent participated in the coaching plan and a second model in the two separate models to predict the change in KPI when the agent didn’t participate in the coaching plan. (Pryluk e.g. According to some embodiments, there is provided a method for identifying one or more treatment subpopulations within a patient population of a clinical study, by applying on a dataset obtained from the clinical study a causal ensemble model, the ensemble model integrating at least two different causal predictive models to obtain an improved CATE, also referred to herein as “eCATE” [0005]. Moreover by integrating at least two different causal predictive models into a universal ensemble algorithm, a methodological synergy between the models is unexpectedly achieved [0010]. T learner: This approach uses base-learners to estimate the conditional expectations of the two (hence “T”) potential outcomes—{(Xi, yi); ai=0} that are used to train {circumflex over ( )}μ0(X), an estimate for E[y|a=0] and {(Xi, yi); ai=1} to train {circumflex over ( )}μ1(X). Finally, an estimate for CATE is obtained by subtracting them [0061].)
The Examiner submits that before the effective filing date, it would have been obvious to one of ordinary skill in the art to combine Beaver’s Automated Agent Coaching Method with Pryluk’s CATE estimator and meta-learner models in order to providing a more accurate assessment of how different groups will respond to treatments (Pryluk e.g. [0110]).
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Beaver et al. (US 2025/0315746 A1) in view of Pryluk et al. (US 20250372212 A1) and in further view of Lin et al. (US 2025/0078133 A1).
As per claim 7 (Original), Beaver in view of Pryluk teach the computerized-method of claim 6, Beaver nor Pryluk teaches, however, Lin teaches wherein said single model is Extreme Gradient Boosting (XGBoost) model. (Lin e.g. In some embodiments, the system described herein is an online concierge system that allows users to search for and order products from different retailers [0021]. For each of the users, the online concierge system computes a conditional average treatment effect (CATE) based on an average difference of user actions responsive to viewing the content items between exploration mode and non-exploration mode. The training of the machine learning model is based on the CATE [0025]. The machine learning training module 230 trains machine learning models used by the online concierge system 140. The online concierge system 140 may use machine learning models (e.g., machine-learning sensitivity model 250) to perform functionalities described herein. Example machine learning models include...xgboost, meta learner, and double machine learning [0072].)
The Examiner submits that before the effective filing date, it would have been obvious to one of ordinary skill in the art to modify Beaver in view of Pryluk’s Automated Agent Coaching Method’s use of machine learning models to include XGBoost as taught by Lin in order to improve processing of large data sets.
Conclusion
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 nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Ayanna Minor whose telephone number is (571)272-3605. The examiner can normally be reached M-F 9am-5 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jerry O'Connor can be reached at 571-272-6787. 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.
/A.M./Examiner, Art Unit 3624
/Jerry O'Connor/Supervisory Patent Examiner,Group Art Unit 3624
Prosecution Insights