Prosecution Insights
Last updated: November 18, 2026
Application No. 19/051,148

COMPUTING SYSTEM AND METHOD FOR BUILDING AND EXECUTING A FORECASTING MODEL FOR CALL CENTER CAPACITY SHRINKAGE

Final Rejection §103
Filed
Feb 11, 2025
Examiner
WARNER, PHILIP N
Art Unit
3624
Tech Center
3600 — Transportation & Electronic Commerce
Assignee
Capital One Financial Corporation
OA Round
2 (Final)
39%
Grant Probability
At Risk
3-4
OA Rounds
68%
With Interview

Examiner Intelligence

Grants only 39% of cases
39%
Career Allowance Rate
47 granted / 120 resolved
-12.8% vs TC avg
Strong +28% interview lift
Without
With
+28.3%
Interview Lift
resolved cases with interview
Typical timeline
Avg Prosecution
29 currently pending
Career history
154
Total Applications
across all art units

Office Action

§103
DETAILED ACTION 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 . The following FINAL Office Action is in response to Applicant’s communication filed 06/25/2026 regarding Application 19/051,148. Status of Claim(s) Claim(s) 1-20 is/are currently pending and are rejected as follows. Response to Arguments – 101 Rejection Applicant’s arguments and amendments in regard to the previously applied 101 rejection have been fully considered and are deemed persuasive. Examiner accordingly withdraws the previously applied 101 rejection. Response to Arguments – 102/103 Rejection Applicant’s arguments in regard to the previously applied 102 and 103 rejections are rendered moot in view of the amended prior art rejection below. 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 (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. The following is a quotation of 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. Claim(s) 1-2, 4, 7-11, 13, and 16-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sciarra (WO 2025/019936 A1) in view of Qamar (US 2015/0269244 A1) Claim(s) 1, 10, and 19 – Sciarra discloses the following: at least one network interface; (Sciarra: Paragraph 258, “The server(s) 3502 each comprise a CPU 3522, a non-transitory computer-readable memory 3524, a non-volatile storage 3526, an input/output interface 3528, and may also comprise graphical processing units (“GPU”) 3530. The non-transitory computer-readable memory 3524 comprises computer-executable instructions stored thereon at runtime which, when executed by the CPU 3522, configure the server to perform a workforce optimization method. The non-volatile storage 3526 has stored on it computer-executable instructions that are loaded into the non- transitory computer-readable memory at runtime. The input/output interface 3528 allows the server to communicate with one or more external devices (e.g. via a network). The GPU 3530 may be used to control a display and may also be used to implement aspects of the method (e.g. running the machine learning models).”) at least one processor; (Sciarra: Paragraph 258, “The server(s) 3502 each comprise a CPU 3522, a non-transitory computer-readable memory 3524, a non-volatile storage 3526, an input/output interface 3528, and may also comprise graphical processing units (“GPU”) 3530. The non-transitory computer-readable memory 3524 comprises computer-executable instructions stored thereon at runtime which, when executed by the CPU 3522, configure the server to perform a workforce optimization method. The non-volatile storage 3526 has stored on it computer-executable instructions that are loaded into the non- transitory computer-readable memory at runtime. The input/output interface 3528 allows the server to communicate with one or more external devices (e.g. via a network). The GPU 3530 may be used to control a display and may also be used to implement aspects of the method (e.g. running the machine learning models).”) at least one non-transitory computer-readable medium; and (Sciarra: Paragraph 258, “The server(s) 3502 each comprise a CPU 3522, a non-transitory computer-readable memory 3524, a non-volatile storage 3526, an input/output interface 3528, and may also comprise graphical processing units (“GPU”) 3530. The non-transitory computer-readable memory 3524 comprises computer-executable instructions stored thereon at runtime which, when executed by the CPU 3522, configure the server to perform a workforce optimization method. The non-volatile storage 3526 has stored on it computer-executable instructions that are loaded into the non- transitory computer-readable memory at runtime. The input/output interface 3528 allows the server to communicate with one or more external devices (e.g. via a network). The GPU 3530 may be used to control a display and may also be used to implement aspects of the method (e.g. running the machine learning models).”) program instructions stored on the at least one non-transitory computer-readable medium that, when executed by the at least one processor, cause the computing platform to: (Sciarra: Paragraph 258, “The server(s) 3502 each comprise a CPU 3522, a non-transitory computer-readable memory 3524, a non-volatile storage 3526, an input/output interface 3528, and may also comprise graphical processing units (“GPU”) 3530. The non-transitory computer-readable memory 3524 comprises computer-executable instructions stored thereon at runtime which, when executed by the CPU 3522, configure the server to perform a workforce optimization method. The non-volatile storage 3526 has stored on it computer-executable instructions that are loaded into the non- transitory computer-readable memory at runtime. The input/output interface 3528 allows the server to communicate with one or more external devices (e.g. via a network). The GPU 3530 may be used to control a display and may also be used to implement aspects of the method (e.g. running the machine learning models).”) obtain historical data comprising (i) capacity-shrink-rate data for a call center workforce, (ii) call-volume data for the call center workforce,… (Sciarra: Paragraph 23, “In some aspects, the customer experience tool determines and stores current and historical service levels.”; Paragraph 24, “In some aspects, the workforce comprises employees of a call center.”; Paragraph 38, “In some aspects, the method further comprises using a machine learning model trained on historical employee requirements to determine the forecasted employee requirements”; Paragraph 54, “In accordance with yet another aspect of the present disclosure, there is provided a method of determining a forecast plan comprising receiving data about one or more groups, the data comprising social media data, finance data, performance data and historical data; automatically generating one or more recommendations based on machine learning models and received data; displaying the one or more recommendations for the user; receiving influence data from the user and automatically updating the recommendations based on the KPI data; receiving a selection of one or more of the one or more updated recommendations; generating a forecast plan based on a combination of the one or more selected recommendations; and outputting the forecast plan for execution.”; Paragraph 126, “The performance view may also depict an entrance score for the agent to determine their Sales and Loyalty potential (408), a number of contact the employee had for the selected month (410), survey results for the employee (412), working hours for the employee (414), an employee initial training cohort number (416), the employee tenure within company (418), sales metric used for the employee’s scorecard (420)-(424), the actual results for the selected month (426), a metric specific target for the employee (428), a percent weight for each metric to total 100% (430), a resulting percent to target performance based on actual vs. target for employee scored (432), performance score based on the percent to target result (434), the last reported result date (436), quartile results based on site, segment tenure and segment and whether the employee meets or doesn’t meet criteria (438), overall score based on three levels (site, segment tenure and segment) which identify top performers at different levels (440), payout level quartiling which is used for compensation bonus calculation (442), summary of metric results for the individual and their team (444), segment average for the same team for that metric (446), target which is set by performance experts (448), and team average for that metric (450).”; Paragraph 177, “The capacity plan may be created such that it matches the previously determined demand conditions, as the generation of the plan considers factors that influence resourcing, such as shrinkage, hiring and attrition. The system also allows the user to view the productivity factors to determine how many staff or employees may be regarding to achieve certain results. The capacity plan allows for the user to determine when certain employees should be working, and with which groups. For example, for call centres, the plan identifies where calls should be placed, after a forecasting workload is created.”) based on the obtained historical data, generate one or more training datasets for training candidate time-series models that are each configured to predict time-series forecast values of a capacity shrink rate for the call center workforce based on predicted future time-series data obtain historical data for a set of exogenous variables, the set of exogenous variables comprising (i) call volume for the call center workforce and…; (Sciarra: Paragraph 165, “The data collected (1602) may be collected over a particular period of time, and may be collected daily, monthly, weekly, quarterly or yearly. The collected data is analysed based on the type of data. Data relating to the demand of the services offered is analysed (1610), for example, the calls offered actuals, current handle times and resulting service conditions. Data relating to capacity of groups including partner groups is analysed (1612), for example performance, existing tenure mix, current shrinkage, absenteeism, occupancy, and more. Data relating to hiring is analysed (1614), for example the performance and cost of each group and partner groups. Data relating to placement and conditions is analysed (1616), this data includes existing combinations of demand and supply by the groups such that new different combinations may be made to view resulting expected conditions. The placement and condition data may comprise results, such as the forecast, from the demand and capacity analyses for the analysis.”; Paragraph 161, “The WFM tool provides a method and process of creating and executing a forecasting plan. The plan may be created and shared within the tool and to other tools within the workforce optimization system (e.g. the budgeting tool described above). The WFM tool utilizes machine learning models to conduct demand analysis. A variety of time series models may be used for forecasting, such as Seasonal Auto Regressive Integrated Moving Average (SARIMA), Multivariable, Hybrid, Adjusted SARIMA, etc., and different forecasting techniques within models may be used (e.g. linear regression, auto-regression, seasonal auto-regression, neural network based methods, etc.) . It will be appreciated that various forecasting models as well as techniques within forecasting models may be used for comparison to determine the best model and forecasting technique, as described in more detail below. [162] The models provide statistical time-series techniques that when combined with machine learning outcomes provide a more accurate forecast. The WFM tool may compare different models and apply trends from various different historical data points, resulting in numerous algorithms that support a forecast. In some embodiments, the WFM tool may compare over two dozen different models and a plurality of different trend data. The tool evaluates and recommends the best option and allows the user to use the forecast as-is, or to modify the forecast as needed to accommodate additional insights that a user may have.”; Paragraph 172, “The tool also captures ongoing new results (1636) so that any adjustments can be made at the 90, 60 or 30 day mark before the forecasted month starts. The tool automatically captures the new results or new actuals on a regular basis, such as a daily basis. This data is automatically fed into the tool. The data continues to be captured and collected before, during, and after the plans are created and finalized. For example, if the plan is created 45 days before the forecasted month, the data is still collected and captured even after the locked plan is created. It will be appreciated that this may not automatically influence the forecasted plan, in particular, if the forecasted plan is already locked and issued to the leaders. The tool also allows the primes or personnel dedicated to the task to flag exceptions days with the reasons to identify for example, a huge spike in volume, so that it can be ignored or utilized in the future fore-cast. This flagging system is also unique and is designed to improve forecast accuracy.”) based on the one or more training datasets and one or more sets of hyperparameters, train the candidate time-series models that are each configured to predict time-series forecast values of the capacity shrink rate for the call center workforce based on predicted future time-series data for the set of exogenous variables; (Sciarra: Paragraph 161, “The WFM tool provides a method and process of creating and executing a forecasting plan. The plan may be created and shared within the tool and to other tools within the workforce optimization system (e.g. the budgeting tool described above). The WFM tool utilizes machine learning models to conduct demand analysis. A variety of time series models may be used for forecasting, such as Seasonal Auto Regressive Integrated Moving Average (SARIMA), Multivariable, Hybrid, Adjusted SARIMA, etc., and different forecasting techniques within models may be used (e.g. linear regression, auto-regression, seasonal auto-regression, neural network based methods, etc.) . It will be appreciated that various forecasting models as well as techniques within forecasting models may be used for comparison to determine the best model and forecasting technique, as described in more detail below.”; Paragraph 166, “The machine learning models are used to produce a number of time series-based forecasting models that the user can review and select from (1618). The machine learning recommended forecasting model with the highest probability is also identified for the user. Users may modify or update the data based on known or created known future influences (KFIs), which allows the forecasting models to be updated. The WFM tool can adjust and learn from the updated data to improve accuracy for future models.”; Paragraph 172, “The tool also captures ongoing new results (1636) so that any adjustments can be made at the 90, 60 or 30 day mark before the forecasted month starts. The tool automatically captures the new results or new actuals on a regular basis, such as a daily basis. This data is automatically fed into the tool. The data continues to be captured and collected before, during, and after the plans are created and finalized. For example, if the plan is created 45 days before the forecasted month, the data is still collected and captured even after the locked plan is created. It will be appreciated that this may not automatically influence the forecasted plan, in particular, if the forecasted plan is already locked and issued to the leaders. The tool also allows the primes or personnel dedicated to the task to flag exceptions days with the reasons to identify for example, a huge spike in volume, so that it can be ignored or utilized in the future fore-cast. This flagging system is also unique and is designed to improve forecast accuracy.”; Paragraph 173, “Figure 16B depicts a flow of data and information for creating a plan in the WFM tool 1600. A user or forecaster may access the tool 1600 to create a forecasting plan (1638). Once the tool 1600 receives a request for a forecasting plan from the user, the tool 1600 presents various steps and parts of the plan for the user to review, select from and modify as needed for the desired forecast plan (1640). Once the selections and modification have been confirmed, the tool 1600 issues the placement plan (1642).”; Paragraph 176, “Figure 18 depicts a flow chart for the capacity analysis (1612), the staffing calculation (1622), and the capacity plan (1624). The user may select relevant metrics for the capacity analysis for the forecast (1802), such as absence, shrinkage, vacation, training, and more, and select relevant results (1804) for the forecast such as previous forecast plans, budget results, outlooks, and more. Once the system receives the selections, the capacity analysis is conducted (1806), and capacity requirements are presented to the user. It will be appreciated that the capacity requirements may indicate the number of employees ready and available each day for various tasks, such as calling customers or answering customer’s calls. The requirements may be set by the group leaders to for example a vendor to indicate how many hours of work is expected. The user or forecaster may use the values/requirements as is or make additional modifications based on previous plans and on any additional KFI they are aware of (1808). Once the final capacity version or requirement is selected by the user, a budget base plan may be selected (1810), and the language, month and other factors may also be selected for the capacity forecast plan (1812). The user may also view and modify certain metrics or factors before the plan is generated such as productivity factors and/or people factors. These factors may include productive hours, call volume, handle time, occupancy, shrinkage, headcount, new hiring, transfers, and more. The capacity plan is then created and generated based on the user’s selections. The capacity plan can be stored within the system for retrieval and use later on (1814).”; Paragraph 181, “Any modifications made by the user when generating or creating the placement plan based on, for example, budgetary spend requirements, the system will automatically readjust all impacted segments with new targets. The system can further identify and present any gaps between the plan and budget so that user may modify the plan accordingly.”) select, from the candidate time-series models, a given time-series model that is configured to be utilized to predict forecast time-series values for the capacity shrink rate for the call center workforce during a target timeframe in the future; (Sciarra: Paragraph 175, “Figure 17 depicts a flow chart for the demand analysis (1610), forecast workload (1618), and demand plan (1620). The user can view social media insights (1604), and they can select relevant metrics (1702) for the forecast from tasks completed, such as call offered, abandon rate, handle time, and more, and select relevant results (1704) for the forecast such as previous forecast plans, budget results, outlooks, and more. Once the system receives the selections, the demand analysis is conducted (1706), and a variety of machine learning predictive forecasting models are presented to the user for selection. The user may use the values/models as is or make additional modifications based on previous plans and on any additional KFI they are aware of (1708). Each model can be stored and retrieved later for additional modifications. Once the final model is selected by the user, a budget base plan may be selected (1710), and the language, month and other factors may also be selected for the demand forecast plan (1712). The demand plan is then created and generated based on the user’s selections and the machine learning model selected. The demand plan can be stored within the system for retrieval and use later on (1714). It will be appreciated that the plan may be viewed as a calendar or similar system showing the monthly level forecast or a daily level forecast. This view allows for the expected volume of work for each day to be viewed by the user, allowing for the user to identify any trends or modify the plan from what has been generated. The system further allows the user to select from recent trend factors, such as over the last 4 weeks, 6 weeks, 8 weeks, or other, to capture recent trends with more weight for the forecast plan.”; Paragraph 176, “Figure 18 depicts a flow chart for the capacity analysis (1612), the staffing calculation (1622), and the capacity plan (1624). The user may select relevant metrics for the capacity analysis for the forecast (1802), such as absence, shrinkage, vacation, training, and more, and select relevant results (1804) for the forecast such as previous forecast plans, budget results, outlooks, and more. Once the system receives the selections, the capacity analysis is conducted (1806), and capacity requirements are presented to the user. It will be appreciated that the capacity requirements may indicate the number of employees ready and available each day for various tasks, such as calling customers or answering customer’s calls. The requirements may be set by the group leaders to for example a vendor to indicate how many hours of work is expected. The user or forecaster may use the values/requirements as is or make additional modifications based on previous plans and on any additional KFI they are aware of (1808). Once the final capacity version or requirement is selected by the user, a budget base plan may be selected (1810), and the language, month and other factors may also be selected for the capacity forecast plan (1812). The user may also view and modify certain metrics or factors before the plan is generated such as productivity factors and/or people factors. These factors may include productive hours, call volume, handle time, occupancy, shrinkage, headcount, new hiring, transfers, and more. The capacity plan is then created and generated based on the user’s selections. The capacity plan can be stored within the system for retrieval and use later on (1814).”; Paragraph 177, “The capacity plan may be created such that it matches the previously determined demand conditions, as the generation of the plan considers factors that influence resourcing, such as shrinkage, hiring and attrition. The system also allows the user to view the productivity factors to determine how many staff or employees may be regarding to achieve certain results. The capacity plan allows for the user to determine when certain employees should be working, and with which groups. For example, for call centres, the plan identifies where calls should be placed, after a forecasting workload is created.”; Paragraph 181, “Any modifications made by the user when generating or creating the placement plan based on, for example, budgetary spend requirements, the system will automatically readjust all impacted segments with new targets. The system can further identify and present any gaps between the plan and budget so that user may modify the plan accordingly. [182] The forecasting plans generated by and within the WFM tool allow for a business to plan for the appropriate staffing for each segment of business, hours of operation management to match the demand, additional hiring, and increase in performance criteria. It will be appreciated that inaccurate forecasts may lead to underestimating a business’ workload which may cause employee burnout, high turnover, and negatively influenced service conditions. Similarly, overestimating the workload may lead to overstaffing and overspending. The WFM tool prevents any human errors due to data collection and calculations. It will be appreciated that any special days such as public holidays or special sales days such as Black Friday are may be treated differently within the data analysed as the data for these days may be identified as a special variable for modelling. The predictive models are able to identify these days and a special factor may be assigned to them that allows for special treatment during a model forecast. This ensures that high importance days are captured as such and allow for reasonable expected volume.”) receive, as input to the given time-series model, (i) predicted time-series data for the call volume for the call center workforce during a given target timeframe in the future and (ii) predicted time-series data for the set of agent tenure variables during the given target timeframe in the future; and (Sciarra: Paragraph 166, “The machine learning models are used to produce a number of time series-based forecasting models that the user can review and select from (1618). The machine learning recommended forecasting model with the highest probability is also identified for the user. Users may modify or update the data based on known or created known future influences (KFIs), which allows the forecasting models to be updated. The WFM tool can adjust and learn from the updated data to improve accuracy for future models.”; Paragraph 172, “The tool also captures ongoing new results (1636) so that any adjustments can be made at the 90, 60 or 30 day mark before the forecasted month starts. The tool automatically captures the new results or new actuals on a regular basis, such as a daily basis. This data is automatically fed into the tool. The data continues to be captured and collected before, during, and after the plans are created and finalized. For example, if the plan is created 45 days before the forecasted month, the data is still collected and captured even after the locked plan is created. It will be appreciated that this may not automatically influence the forecasted plan, in particular, if the forecasted plan is already locked and issued to the leaders. The tool also allows the primes or personnel dedicated to the task to flag exceptions days with the reasons to identify for example, a huge spike in volume, so that it can be ignored or utilized in the future fore-cast. This flagging system is also unique and is designed to improve forecast accuracy.”; Paragraph 17., “Figure 16B depicts a flow of data and information for creating a plan in the WFM tool 1600. A user or forecaster may access the tool 1600 to create a forecasting plan (1638). Once the tool 1600 receives a request for a forecasting plan from the user, the tool 1600 presents various steps and parts of the plan for the user to review, select from and modify as needed for the desired forecast plan (1640). Once the selections and modification have been confirmed, the tool 1600 issues the placement plan (1642).”; Paragraph 181, “Any modifications made by the user when generating or creating the placement plan based on, for example, budgetary spend requirements, the system will automatically readjust all impacted segments with new targets. The system can further identify and present any gaps between the plan and budget so that user may modify the plan accordingly.”) utilize the given time-series model to predict a sequence of forecast time-series values for the capacity shrink rate for the call center workforce during the given target timeframe in the future, wherein the predicted sequence of forecast time-series values for the capacity shrink rate is made available for use in facilitating improved workforce planning for the call center workforce. (Sciarra: Paragraph 166, “The machine learning models are used to produce a number of time series-based forecasting models that the user can review and select from (1618). The machine learning recommended forecasting model with the highest probability is also identified for the user. Users may modify or update the data based on known or created known future influences (KFIs), which allows the forecasting models to be updated. The WFM tool can adjust and learn from the updated data to improve accuracy for future models.”; Paragraph 172, “The tool also captures ongoing new results (1636) so that any adjustments can be made at the 90, 60 or 30 day mark before the forecasted month starts. The tool automatically captures the new results or new actuals on a regular basis, such as a daily basis. This data is automatically fed into the tool. The data continues to be captured and collected before, during, and after the plans are created and finalized. For example, if the plan is created 45 days before the forecasted month, the data is still collected and captured even after the locked plan is created. It will be appreciated that this may not automatically influence the forecasted plan, in particular, if the forecasted plan is already locked and issued to the leaders. The tool also allows the primes or personnel dedicated to the task to flag exceptions days with the reasons to identify for example, a huge spike in volume, so that it can be ignored or utilized in the future fore-cast. This flagging system is also unique and is designed to improve forecast accuracy.”; Paragraph 173, “Figure 16B depicts a flow of data and information for creating a plan in the WFM tool 1600. A user or forecaster may access the tool 1600 to create a forecasting plan (1638). Once the tool 1600 receives a request for a forecasting plan from the user, the tool 1600 presents various steps and parts of the plan for the user to review, select from and modify as needed for the desired forecast plan (1640). Once the selections and modification have been confirmed, the tool 1600 issues the placement plan (1642).”; Paragraph 176, “Figure 18 depicts a flow chart for the capacity analysis (1612), the staffing calculation (1622), and the capacity plan (1624). The user may select relevant metrics for the capacity analysis for the forecast (1802), such as absence, shrinkage, vacation, training, and more, and select relevant results (1804) for the forecast such as previous forecast plans, budget results, outlooks, and more. Once the system receives the selections, the capacity analysis is conducted (1806), and capacity requirements are presented to the user. It will be appreciated that the capacity requirements may indicate the number of employees ready and available each day for various tasks, such as calling customers or answering customer’s calls. The requirements may be set by the group leaders to for example a vendor to indicate how many hours of work is expected. The user or forecaster may use the values/requirements as is or make additional modifications based on previous plans and on any additional KFI they are aware of (1808). Once the final capacity version or requirement is selected by the user, a budget base plan may be selected (1810), and the language, month and other factors may also be selected for the capacity forecast plan (1812). The user may also view and modify certain metrics or factors before the plan is generated such as productivity factors and/or people factors. These factors may include productive hours, call volume, handle time, occupancy, shrinkage, headcount, new hiring, transfers, and more. The capacity plan is then created and generated based on the user’s selections. The capacity plan can be stored within the system for retrieval and use later on (1814).”; Paragraph 181, “Any modifications made by the user when generating or creating the placement plan based on, for example, budgetary spend requirements, the system will automatically readjust all impacted segments with new targets. The system can further identify and present any gaps between the plan and budget so that user may modify the plan accordingly.”; Paragraph 182, “The forecasting plans generated by and within the WFM tool allow for a business to plan for the appropriate staffing for each segment of business, hours of operation management to match the demand, additional hiring, and increase in performance criteria. It will be appreciated that inaccurate forecasts may lead to underestimating a business’ workload which may cause employee burnout, high turnover, and negatively influenced service conditions. Similarly, overestimating the workload may lead to overstaffing and overspending. The WFM tool prevents any human errors due to data collection and calculations. It will be appreciated that any special days such as public holidays or special sales days such as Black Friday are may be treated differently within the data analysed as the data for these days may be identified as a special variable for modelling. The predictive models are able to identify these days and a special factor may be assigned to them that allows for special treatment during a model forecast. This ensures that high importance days are captured as such and allow for reasonable expected volume.”) Sciarra does not explicitly disclose the following, however, in analogous art of workforce planning, Qamar discloses the following: …and (iii) agent-tenure data for the call center workforce; (Qamar: Paragraph 8, “Note that the organization data may include: tenure of the employee at the organization, compensation of the employee, satisfaction scores associated with the employee, skills of the employee, a supervisor of the employee, a colleague of the employee, interaction among employees of the organization, and/or operations information of the organization. Additionally, the performance metric may include: revenue associated with the employee, productivity of the employee, overtime worked by the employee, adherence of the employee to a schedule, attendance of the employee, a number of employees that interact with the employee, activity of the employee, and/or satisfaction scores associated with the employee.”; Paragraph 49, “We now describe embodiments of the analysis technique. FIG. 1 presents a flow chart illustrating a method 100 for analyzing employee value and retention risk, which may be performed by a computer system (such as computer system 800 in FIG. 8). During operation, the computer system accesses, at a memory location, organization data for an organization (operation 110). For example, the computer system may access the organization data of a company via a data portal using a network (such as the Internet). Note that the organization data may include human-resources data and/or operations data. In particular, the organization data may include: tenure of the employee at the organization (such as the hire date), attendance of the employee (such as how often the employee is sick or late for work), compensation of the employee, satisfaction scores associated with the employee (such as rankings provided by a customer, a manager or other employees, a trainer or coach, etc.), skills of the employee, a supervisor of the employee, a colleague of the employee, interaction among employees of the organization (such as email, telephone calls or text messages among the employees), metadata about the employee (such as educational or work experience attributes), and/or operations information of the organization (such as products or services that are fabricated or sold as a function of time).”; Paragraph 111, “We now describe embodiments of the clustering analysis technique. FIG. 10 presents a flow chart illustrating a method 1000 for identifying predictors for retention, which may be performed by a computer system (such as computer system 1300 in FIG. 13). During operation, the computer system accesses, at a memory location, retention data for individuals (operation 1010), where the retention data includes, as a function of time, retention probabilities that the individuals remain in functions in an organization (or a portion of an organization, such as a location, a department or a group) and a set of potential predictors for the retention probabilities. For example, the computer system may access the retention data of a company via a data portal using a network (such as the Internet). Note that the retention data may include human-resources data and/or operations data (and, more general, organization data of the organization). In particular, the retention data may include: tenure of the employees at the organization (such as the hire dates), job types, functions or job titles in the organization, which clients the employees work with (such as a customer account), regions or locations where the employees work, supervisors or managers of the employees, satisfaction scores associated with the employees (such as rankings provided by customers, managers or other employees, trainers or coaches, etc.), attendance of the employees (such as how often the employees are sick or late for work), compensation of the employees, skills of the employees (such as a skill set), employee attributes (such as an educational background), colleagues of the employees, interaction among employees of the organization (such as email, telephone calls or text messages among the employees), metadata about the employees (such as educational or work-experience attributes), and/or operations information of the organization (such as productivity or revenue data, e.g., products or services that are fabricated or sold as a function of time).”; Paragraph 159, “We now describe embodiments of the analysis technique. FIG. 15 presents a flow chart illustrating a method 1500 for modifying an assessment technique (such as a questionnaire), which may be performed by a computer system (such as computer system 1800 in FIG. 18). During operation, the computer system accesses, at a memory location, organization data for an organization and information specifying the assessment technique (operation 1510), where the organization data includes time samples (or longitudinal data) of a performance metric for individuals in the organization (such as a categorical factor) and features that are assessed using the assessment technique. For example, the computer system may access the organization data of a company and/or the information specifying the assessment technique via a data portal using a network (such as the Internet). Note that the organization data may include human-resources data and/or operations data (and, more general, organization data of the organization). In particular, the organization data may include: information specifying individuals (such as employee identifiers), tenure of the employees at the organization (such as the hire dates), job types, functions or job titles in the organization, which clients the employees work with (such as a customer account), regions or locations where the employees work, supervisors or managers of the employees, satisfaction scores associated with the employees (such as rankings provided by customers, managers or other employees, trainers or coaches, etc.), attendance of the employees (such as how often the employees are sick or late for work), compensation of the employees, skills of the employees (such as a skill set), employee attributes (such as an educational background, work experience, etc.), colleagues of the employees, interaction among employees of the organization (such as email, telephone calls or text messages among the employees), metadata about the employees (such as educational or work-experience attributes), assessment scores of the employees, a time of year or the season, and/or operations information of the organization (such as productivity or revenue data, e.g., products or services that are fabricated or sold as a function of time).”) …(ii) a set of agent tenure variables corresponding to agents of the call center workforce, each agent tenure variable identifying a proportion of the agents having a tenure with the call center workforce that falls within a respective agent-tenure window (Qamar: Paragraph 79, “As shown in FIGS. 3-6, the calculated employee value and flight risk may then be combined and displayed as a scatterplot so that employers can identify high-flight-risk and high-value employees. This graph may also provide a dynamic and a real-time view of the state of the employer's workforce, as well as trends among their employees.”; Paragraph 159, “We now describe embodiments of the analysis technique. FIG. 15 presents a flow chart illustrating a method 1500 for modifying an assessment technique (such as a questionnaire), which may be performed by a computer system (such as computer system 1800 in FIG. 18). During operation, the computer system accesses, at a memory location, organization data for an organization and information specifying the assessment technique (operation 1510), where the organization data includes time samples (or longitudinal data) of a performance metric for individuals in the organization (such as a categorical factor) and features that are assessed using the assessment technique. For example, the computer system may access the organization data of a company and/or the information specifying the assessment technique via a data portal using a network (such as the Internet). Note that the organization data may include human-resources data and/or operations data (and, more general, organization data of the organization). In particular, the organization data may include: information specifying individuals (such as employee identifiers), tenure of the employees at the organization (such as the hire dates), job types, functions or job titles in the organization, which clients the employees work with (such as a customer account), regions or locations where the employees work, supervisors or managers of the employees, satisfaction scores associated with the employees (such as rankings provided by customers, managers or other employees, trainers or coaches, etc.), attendance of the employees (such as how often the employees are sick or late for work), compensation of the employees, skills of the employees (such as a skill set), employee attributes (such as an educational background, work experience, etc.), colleagues of the employees, interaction among employees of the organization (such as email, telephone calls or text messages among the employees), metadata about the employees (such as educational or work-experience attributes), assessment scores of the employees, a time of year or the season, and/or operations information of the organization (such as productivity or revenue data, e.g., products or services that are fabricated or sold as a function of time).”; Paragraph 188, “In an exemplary embodiment, the random effects estimator is a weighted combination of a fixed effects estimator and a between estimator. Moreover, the analysis technique may use a panel-data technique on panel data. The panel-data technique may: include controls for site, client, and/or temporal effects; by used to model performance and improvement over time; estimate the impact of an individual leaving an organization; use a single day as the observation interval; and test hypotheses and display confidence intervals. Furthermore, the panel data may include time-series or longitudinal data with repeated observations for individuals over time. In some embodiments, the panel data is balanced (with the same number of observations for a group of individuals) and/or unbalanced (with a different number of observations for another group of individuals). Additionally, a short panel may be used (with observations on a large number of individuals over a small time interval, such as 1000 individuals over a month) and/or a long panel (with observations on a small number of individuals over a long time interval, such as ten individuals over a year).”; Paragraph 254, “In an exemplary embodiment, there are 5000 predictor types in the organization data, which may each have, on average, 50-100 values. For example, the predictor types may include dimensional information, such as: a hire date, a termination date, a location, a region, a sub-region, a client, a department, a group, tenure (equal to the difference of the termination date and the hire date), assessment data, customer satisfaction ratings (e.g., a timestamp, an average value, and a number of ratings included in the average value), textural description feedback (e.g., sentiment analysis), sales performance, average handling time, etc. In addition, permutations and combinations of the 50,000 predictor-values may result in 50 million models (with different subsets or orderings of the predictor types and values) that may need to be computed. Existing computational approaches may take 1 minute per model. Moreover, 60-100 different types of models may be generated daily, resulting in some 75 million hours of runtime daily. Consequently, in the absence of the disclosed computational technique, the overall runtime may be prohibitively long.”) Sciarra discloses a method for generating models to forecast workforce management needs and capacities based on historical and current data. Qamar discloses a method for analyzing data and trends among an existing workforce. Before the filing date of Applicant’s filed invention, one or ordinary skill in the art would have deemed it obvious to combine the methods of Sciarra with the teachings of Qamar in order to improve the allocation of resources to better meet work demands as disclosed by Qamar (Qamar: Paragraph 4, “In the absence of such employee-retention techniques, the organization may inadvertently lose talented employees, with a commensurate negative impact on profits and morale.”) Claim(s) 2, 11, and 20 – Sciarra in view of Qamar disclose the limitations of claims 1, 10, and 19 Sciarra further discloses the following: transform agent-level indications of agent tenure into historical time-series data for the set of agent tenure variables by (i) segmenting the agent-level indications of agent tenure into two or more…windows, Sciarra does not explicitly disclose the following, however, in analogous art of workforce management, Qamar teaches the following: (Sciarra: Paragraph 108, “The hierarchy system stores and updates information on employees comprising employee details, location details, employee status, segment information, hierarchy information, and system IDs. The employee details comprise a hire date, name and email of the employee, unique employee number, and the employee’s work from home status identifying if the employee works from home any days. The locations details comprise company names and locations where the employee works. The employment status comprises a current active or inactive status of employment, the employment type, and may be used to identify if the employee is on long-term leave or short-term leave. The segment information comprises a business domain hierarchy to identify where the employee belongs to in the larger organization, Line of Business (LOB)/segment, and skill types. The hierarchy information comprises report to structure leading up to the executive team along with their levels in the organization. It will be appreciated that report to structure is the hierarchy of management describing who reports to who from base employees to high up management. The system IDs comprise all system IDs that belong to the employee.”; Paragraph 126, “The performance view may also depict an entrance score for the agent to determine their Sales and Loyalty potential (408), a number of contact the employee had for the selected month (410), survey results for the employee (412), working hours for the employee (414), an employee initial training cohort number (416), the employee tenure within company (418), sales metric used for the employee’s scorecard (420)-(424), the actual results for the selected month (426), a metric specific target for the employee (428), a percent weight for each metric to total 100% (430), a resulting percent to target performance based on actual vs. target for employee scored (432), performance score based on the percent to target result (434), the last reported result date (436), quartile results based on site, segment tenure and segment and whether the employee meets or doesn’t meet criteria (438), overall score based on three levels (site, segment tenure and segment) which identify top performers at different levels (440), payout level quartiling which is used for compensation bonus calculation (442), summary of metric results for the individual and their team (444), segment average for the same team for that metric (446), target which is set by performance experts (448), and team average for that metric (450).”) Sciarra does not explicitly disclose the following, however, in analogous art of workforce planning, Qamar discloses the following: … agent-tenure… and (ii) for each of the two or more agent-tenure windows, determining a respective proportion of the agents of the call center workforce that fall within a corresponding the agent-tenure window (Qamar: Paragraph 111, “We now describe embodiments of the clustering analysis technique. FIG. 10 presents a flow chart illustrating a method 1000 for identifying predictors for retention, which may be performed by a computer system (such as computer system 1300 in FIG. 13). During operation, the computer system accesses, at a memory location, retention data for individuals (operation 1010), where the retention data includes, as a function of time, retention probabilities that the individuals remain in functions in an organization (or a portion of an organization, such as a location, a department or a group) and a set of potential predictors for the retention probabilities. For example, the computer system may access the retention data of a company via a data portal using a network (such as the Internet). Note that the retention data may include human-resources data and/or operations data (and, more general, organization data of the organization). In particular, the retention data may include: tenure of the employees at the organization (such as the hire dates), job types, functions or job titles in the organization, which clients the employees work with (such as a customer account), regions or locations where the employees work, supervisors or managers of the employees, satisfaction scores associated with the employees (such as rankings provided by customers, managers or other employees, trainers or coaches, etc.), attendance of the employees (such as how often the employees are sick or late for work), compensation of the employees, skills of the employees (such as a skill set), employee attributes (such as an educational background), colleagues of the employees, interaction among employees of the organization (such as email, telephone calls or text messages among the employees), metadata about the employees (such as educational or work-experience attributes), and/or operations information of the organization (such as productivity or revenue data, e.g., products or services that are fabricated or sold as a function of time).”; Paragraph 115, “Next, the computer system identifies the predictors for retention of the individuals based on the determined natural groupings (operation 1016). For example, the identified predictors may be associated with at least natural groupings having a centroid separation exceeding a threshold value (such as N-times the standard deviation of the retention data for either of two adjacent natural groupings, where N is an integer). In particular, the predictors may be identified based on the natural groupings calculated for different iterations of the clustering analysis for the different potential predictors (i.e., retention data for a given potential predictor may be clustered, and the operations may be repeated at least M times for a set of M potential predictors, and the resulting natural groupings may be used to identify the predictors). Thus, the centroid separation may be used to identify the potential predictors that are most useful (i.e., the predictors).”; Paragraph 118, “While the preceding discussion using a modified k-means clustering as an illustration in operation 1012, in other embodiments a wide variety of clustering techniques may be used, including: hierarchical clustering, another type of centroid-based clustering (such as k-medians clustering, k-means++ clustering, fuzzy clustering, etc.), distribution-based clustering, density-based clustering, sub-space clustering, and/or correlation clustering. Thus, the specific embodiments are used for purposes of illustration only, and one or more other clustering techniques may be used. The analysis technique may be repeated periodically or after a time interval (such as one week, a month, six months, a year, etc.).”; Paragraph 129, “For example, using the clustered Kaplan-Meier estimator curves, comparisons may be presented of the cumulative attrition impact of different supervisors on particular groups of employees. Thus, it may be founds that there may be a loss of 20 employees with supervisor A after 6 months, while the loss with supervisor B may be 150 employees. The associated financial impact of this attrition may also be presented. This analysis may be performed for the entire dataset or for one or more subsets, such as a particular location (e.g., San Francisco), department and/or job type (e.g., sales). Thus, if the supervisor of a particular natural group is switched, the median employee tenure may increase by 60% to 73 days, which may result in an annual savings of $115,175. User interface 1200 may display the cumulative impact of such counter-factual analysis. In addition, user interface 1200 may present the relative impact on attrition of particular values of a predictor (such as the supervisor) and/or may rank the values of the predictor (such as the retention performance of different supervisors).”) Sciarra discloses a method for generating models to forecast workforce management needs and capacities based on historical and current data. Qamar discloses a method for analyzing data and trends among an existing workforce. Before the filing date of Applicant’s filed invention, one or ordinary skill in the art would have deemed it obvious to combine the methods of Sciarra with the teachings of Qamar in order to improve the allocation of resources to better meet work demands as disclosed by Qamar (Qamar: Paragraph 4, “In the absence of such employee-retention techniques, the organization may inadvertently lose talented employees, with a commensurate negative impact on profits and morale.”) Claim(s) 4, and 13 – Sciarra in view of Qamar discloses the limitations of claims 1 and 10 Sciarra further discloses the following: based on an evaluation of the candidate time-series models, determine a respective measure of performance for each of the candidate time series-models; (Sciarra: Paragraph 161, “The WFM tool provides a method and process of creating and executing a forecasting plan. The plan may be created and shared within the tool and to other tools within the workforce optimization system (e.g. the budgeting tool described above). The WFM tool utilizes machine learning models to conduct demand analysis. A variety of time series models may be used for forecasting, such as Seasonal Auto Regressive Integrated Moving Average (SARIMA), Multivariable, Hybrid, Adjusted SARIMA, etc., and different forecasting techniques within models may be used (e.g. linear regression, auto-regression, seasonal auto-regression, neural network based methods, etc.) . It will be appreciated that various forecasting models as well as techniques within forecasting models may be used for comparison to determine the best model and forecasting technique, as described in more detail below.”; Paragraph 162, “The models provide statistical time-series techniques that when combined with machine learning outcomes provide a more accurate forecast. The WFM tool may compare different models and apply trends from various different historical data points, resulting in numerous algorithms that support a forecast. In some embodiments, the WFM tool may compare over two dozen different models and a plurality of different trend data. The tool evaluates and recommends the best option and allows the user to use the forecast as-is, or to modify the forecast as needed to accommodate additional insights that a user may have.”; Paragraph 164, “Figure 16A depicts an overview of the WFM tool. The tool collects data (1602) from for example, social media insights (1604), spend, performance, and business results (1606), and call flow insights (1608). The social media insights 1604 may be particular to trends in the relevant field, and may be searched by the user to determine trends based on key words and how often key words were searched by different geolocations and regions. The spending, performance, and business results 1606 comprise all of the relevant data points that are available within the system. For example, the relevant data comprises results from the automatic call distributor (ACD) telephony platform, performance data from the agent suite tool, and budget-based targets from the budget tool. The combination of data provides the user a complete set of relevant and available data to base the forecasting plan. The call flow insights 1608 comprise information from applications that track flow and direction of the voice interaction of calls at call centres. This data allows the user to use historical data for call reasoning to better understand any growing or declining trends. It will be appreciated that although call centre businesses and trends are described, other businesses and trends may be used to forecast plans.”) identify a candidate time series model that has a best measure of performance relative to other candidate time-series models; and (Sciarra: Paragraph 161, “The WFM tool provides a method and process of creating and executing a forecasting plan. The plan may be created and shared within the tool and to other tools within the workforce optimization system (e.g. the budgeting tool described above). The WFM tool utilizes machine learning models to conduct demand analysis. A variety of time series models may be used for forecasting, such as Seasonal Auto Regressive Integrated Moving Average (SARIMA), Multivariable, Hybrid, Adjusted SARIMA, etc., and different forecasting techniques within models may be used (e.g. linear regression, auto-regression, seasonal auto-regression, neural network based methods, etc.) . It will be appreciated that various forecasting models as well as techniques within forecasting models may be used for comparison to determine the best model and forecasting technique, as described in more detail below.”; Paragraph 162, “The models provide statistical time-series techniques that when combined with machine learning outcomes provide a more accurate forecast. The WFM tool may compare different models and apply trends from various different historical data points, resulting in numerous algorithms that support a forecast. In some embodiments, the WFM tool may compare over two dozen different models and a plurality of different trend data. The tool evaluates and recommends the best option and allows the user to use the forecast as-is, or to modify the forecast as needed to accommodate additional insights that a user may have.”; Paragraph 164, “Figure 16A depicts an overview of the WFM tool. The tool collects data (1602) from for example, social media insights (1604), spend, performance, and business results (1606), and call flow insights (1608). The social media insights 1604 may be particular to trends in the relevant field, and may be searched by the user to determine trends based on key words and how often key words were searched by different geolocations and regions. The spending, performance, and business results 1606 comprise all of the relevant data points that are available within the system. For example, the relevant data comprises results from the automatic call distributor (ACD) telephony platform, performance data from the agent suite tool, and budget-based targets from the budget tool. The combination of data provides the user a complete set of relevant and available data to base the forecasting plan. The call flow insights 1608 comprise information from applications that track flow and direction of the voice interaction of calls at call centres. This data allows the user to use historical data for call reasoning to better understand any growing or declining trends. It will be appreciated that although call centre businesses and trends are described, other businesses and trends may be used to forecast plans.”) select the identified candidate time-series model as the given time-series model. (Sciarra: Paragraph 161, “The WFM tool provides a method and process of creating and executing a forecasting plan. The plan may be created and shared within the tool and to other tools within the workforce optimization system (e.g. the budgeting tool described above). The WFM tool utilizes machine learning models to conduct demand analysis. A variety of time series models may be used for forecasting, such as Seasonal Auto Regressive Integrated Moving Average (SARIMA), Multivariable, Hybrid, Adjusted SARIMA, etc., and different forecasting techniques within models may be used (e.g. linear regression, auto-regression, seasonal auto-regression, neural network based methods, etc.) . It will be appreciated that various forecasting models as well as techniques within forecasting models may be used for comparison to determine the best model and forecasting technique, as described in more detail below.”; Paragraph 162, “The models provide statistical time-series techniques that when combined with machine learning outcomes provide a more accurate forecast. The WFM tool may compare different models and apply trends from various different historical data points, resulting in numerous algorithms that support a forecast. In some embodiments, the WFM tool may compare over two dozen different models and a plurality of different trend data. The tool evaluates and recommends the best option and allows the user to use the forecast as-is, or to modify the forecast as needed to accommodate additional insights that a user may have.”; Paragraph 164, “Figure 16A depicts an overview of the WFM tool. The tool collects data (1602) from for example, social media insights (1604), spend, performance, and business results (1606), and call flow insights (1608). The social media insights 1604 may be particular to trends in the relevant field, and may be searched by the user to determine trends based on key words and how often key words were searched by different geolocations and regions. The spending, performance, and business results 1606 comprise all of the relevant data points that are available within the system. For example, the relevant data comprises results from the automatic call distributor (ACD) telephony platform, performance data from the agent suite tool, and budget-based targets from the budget tool. The combination of data provides the user a complete set of relevant and available data to base the forecasting plan. The call flow insights 1608 comprise information from applications that track flow and direction of the voice interaction of calls at call centres. This data allows the user to use historical data for call reasoning to better understand any growing or declining trends. It will be appreciated that although call centre businesses and trends are described, other businesses and trends may be used to forecast plans.”) Claim(s) 7 and 16 – Sciarra in view of Qamar discloses the limitations of claims 1 and 10 Sciarra further discloses the following: wherein the set of exogenous variables further comprises one or more of (iii) agent geographic location for agents of the call center workforce, (iv) agent pay grade for the agents of the call center workforce, or (vi) team leader tenure for the agents of the call center workforce. (Sciarra: Paragraph 108, “wherein the set of exogenous variables further comprises one or more of (iii) agent geographic location for agents of the call center workforce, (iv) agent pay grade for agents of the call center workforce, or (vi) team leader tenure for agents of the call center workforce.”; Paragraph 126, “The performance view may also depict an entrance score for the agent to determine their Sales and Loyalty potential (408), a number of contact the employee had for the selected month (410), survey results for the employee (412), working hours for the employee (414), an employee initial training cohort number (416), the employee tenure within company (418), sales metric used for the employee’s scorecard (420)-(424), the actual results for the selected month (426), a metric specific target for the employee (428), a percent weight for each metric to total 100% (430), a resulting percent to target performance based on actual vs. target for employee scored (432), performance score based on the percent to target result (434), the last reported result date (436), quartile results based on site, segment tenure and segment and whether the employee meets or doesn’t meet criteria (438), overall score based on three levels (site, segment tenure and segment) which identify top performers at different levels (440), payout level quartiling which is used for compensation bonus calculation (442), summary of metric results for the individual and their team (444), segment average for the same team for that metric (446), target which is set by performance experts (448), and team average for that metric (450).”) Claim(s) 8 and 17 – Sciarra in view of Qamar discloses the limitations of claims 1 and 10 Sciarra further discloses the following: wherein the predicted time series data for the set of agent tenure variables during the given target timeframe in the future is determined base on a set of current values for the set of agent tenure variables. (Sciarra: Paragraph 108, “wherein the set of exogenous variables further comprises one or more of (iii) agent geographic location for agents of the call center workforce, (iv) agent pay grade for agents of the call center workforce, or (vi) team leader tenure for agents of the call center workforce.”; Paragraph 126, “The performance view may also depict an entrance score for the agent to determine their Sales and Loyalty potential (408), a number of contact the employee had for the selected month (410), survey results for the employee (412), working hours for the employee (414), an employee initial training cohort number (416), the employee tenure within company (418), sales metric used for the employee’s scorecard (420)-(424), the actual results for the selected month (426), a metric specific target for the employee (428), a percent weight for each metric to total 100% (430), a resulting percent to target performance based on actual vs. target for employee scored (432), performance score based on the percent to target result (434), the last reported result date (436), quartile results based on site, segment tenure and segment and whether the employee meets or doesn’t meet criteria (438), overall score based on three levels (site, segment tenure and segment) which identify top performers at different levels (440), payout level quartiling which is used for compensation bonus calculation (442), summary of metric results for the individual and their team (444), segment average for the same team for that metric (446), target which is set by performance experts (448), and team average for that metric (450).”; Paragraph 165, “The data collected (1602) may be collected over a particular period of time, and may be collected daily, monthly, weekly, quarterly or yearly. The collected data is analysed based on the type of data. Data relating to the demand of the services offered is analysed (1610), for example, the calls offered actuals, current handle times and resulting service conditions. Data relating to capacity of groups including partner groups is analysed (1612), for example performance, existing tenure mix, current shrinkage, absenteeism, occupancy, and more. Data relating to hiring is analysed (1614), for example the performance and cost of each group and partner groups. Data relating to placement and conditions is analysed (1616), this data includes existing combinations of demand and supply by the groups such that new different combinations may be made to view resulting expected conditions. The placement and condition data may comprise results, such as the forecast, from the demand and capacity analyses for the analysis.”) Claim(s) 9 and 18 – Sciarra in view of Qamar discloses the limitations of claims 1 and 10 Sciarra further discloses the following: the historical data comprising the capacity shrink rate data is obtained based on input received from a client device; and (Sciarra: Paragraph 27, “In some aspects, the virtual manager is configured to implement the one or more recommended actions in response to user input.”; Paragraph 136, “Figure 6 depicts a flow of data and information for the compensation module. A user or performance manager may access the agent suite system 500 to create an incentive program (602). Once the system 500 receives an indication from a user for creating or generating an incentive program, the system 500 may automatically request additional information from the user about the incentive program, or the user can input additional information before any prompt from the system 500 (604). For example, the user can identify qualifiers such as a minimum number of tasks to be completed and an amount for each employee to be compensated. The system 500 may determine, based on the qualifiers, how many employees would qualify for and receive the incentive, and present such information and the cost associated with the information to the user. It will be appreciated that the determination is done using the information stored in the one or more databases or systems about the employees and their performance data. The user can determine if the incentive should be implemented based on this presented data, and how often the incentive should be activated. For example, the incentive may be activated every month, or other amount of time to encourage employees, or the incentive may only be active the initial time as a type of reward for employees. The system further sets the duration period of the tasks to be completed by the user to qualify for the inventive based on a period inputted by the user. Once the incentive has been generated and activated by the system, the system further automatically generates a notification or other notice to be transmitted and presented to all employees that qualify for the incentive to indicate the results of the incentive. The notification is presented to the employees and the results are stored within the system 500 for access by the employees and the user (606). Over the period of the incentive, the employees may view their task completion statuses and view a determination, by the system, of if they are close to or have already qualified for the incentive. The employees may also view the amount of compensation to be provided if they qualify for the inventive, based on their title, rank and other criteria.”; Paragraph 205, “Figure 25 depicts an overview of the virtual manager system 2500. The system quickly updates absences, employees who are late, and system issues any employees may have based on input from one or more employees and data stored in the system. The system also provides recommended actions and can generate overtime and time-off offers to particular employees based on a work schedule, employees’ input, and performance and cost data stored in the system. The system may automatically provide recommendations for next step strategies based on absences, time off or overtime possibilities, and the performance and cost data.”; Paragraph 176, “Figure 18 depicts a flow chart for the capacity analysis (1612), the staffing calculation (1622), and the capacity plan (1624). The user may select relevant metrics for the capacity analysis for the forecast (1802), such as absence, shrinkage, vacation, training, and more, and select relevant results (1804) for the forecast such as previous forecast plans, budget results, outlooks, and more. Once the system receives the selections, the capacity analysis is conducted (1806), and capacity requirements are presented to the user. It will be appreciated that the capacity requirements may indicate the number of employees ready and available each day for various tasks, such as calling customers or answering customer’s calls. The requirements may be set by the group leaders to for example a vendor to indicate how many hours of work is expected. The user or forecaster may use the values/requirements as is or make additional modifications based on previous plans and on any additional KFI they are aware of (1808). Once the final capacity version or requirement is selected by the user, a budget base plan may be selected (1810), and the language, month and other factors may also be selected for the capacity forecast plan (1812). The user may also view and modify certain metrics or factors before the plan is generated such as productivity factors and/or people factors. These factors may include productive hours, call volume, handle time, occupancy, shrinkage, headcount, new hiring, transfers, and more. The capacity plan is then created and generated based on the user’s selections. The capacity plan can be stored within the system for retrieval and use later on (1814).”; Paragraph 205, “Figure 25 depicts an overview of the virtual manager system 2500. The system quickly updates absences, employees who are late, and system issues any employees may have based on input from one or more employees and data stored in the system. The system also provides recommended actions and can generate overtime and time-off offers to particular employees based on a work schedule, employees’ input, and performance and cost data stored in the system. The system may automatically provide recommendations for next step strategies based on absences, time off or overtime possibilities, and the performance and cost data.”) transmit the predicted sequence of forecast time-series values for the capacity shrink rate for the call center workforce during the given target timeframe in the future to the client device for display via the client device. (Sciarra: Paragraph 176, “Figure 18 depicts a flow chart for the capacity analysis (1612), the staffing calculation (1622), and the capacity plan (1624). The user may select relevant metrics for the capacity analysis for the forecast (1802), such as absence, shrinkage, vacation, training, and more, and select relevant results (1804) for the forecast such as previous forecast plans, budget results, outlooks, and more. Once the system receives the selections, the capacity analysis is conducted (1806), and capacity requirements are presented to the user. It will be appreciated that the capacity requirements may indicate the number of employees ready and available each day for various tasks, such as calling customers or answering customer’s calls. The requirements may be set by the group leaders to for example a vendor to indicate how many hours of work is expected. The user or forecaster may use the values/requirements as is or make additional modifications based on previous plans and on any additional KFI they are aware of (1808). Once the final capacity version or requirement is selected by the user, a budget base plan may be selected (1810), and the language, month and other factors may also be selected for the capacity forecast plan (1812). The user may also view and modify certain metrics or factors before the plan is generated such as productivity factors and/or people factors. These factors may include productive hours, call volume, handle time, occupancy, shrinkage, headcount, new hiring, transfers, and more. The capacity plan is then created and generated based on the user’s selections. The capacity plan can be stored within the system for retrieval and use later on (1814).”; Paragraph 177, “The capacity plan may be created such that it matches the previously determined demand conditions, as the generation of the plan considers factors that influence resourcing, such as shrinkage, hiring and attrition. The system also allows the user to view the productivity factors to determine how many staff or employees may be regarding to achieve certain results. The capacity plan allows for the user to determine when certain employees should be working, and with which groups. For example, for call centres, the plan identifies where calls should be placed, after a forecasting workload is created.”; Paragraph 189, “A reporting and analytics layer 2116 of the queue monitor system allows for reporting views where graphical data for interval level statistics for each metric is displayed. Reports may be pre-composed by the system based on the data received to allow for quick view of the report. An alert management layer 2118 of the queue system provides a method for users to set up particular alerts and reports to be displayed or sent to them. The alerts are automated and may be set for any service related metric. The system will trigger a notification to be sent to the user as soon as a pre-set threshold is met for the metric. This allows users to have advance notice to address changing situations.”; Paragraph 252, “As described above, machine learning models are used in both the demand side forecasting and also for supply side forecasting that is used for scheduling. The workforce planning tool as described above can make forecasting predictions a set number of days in advance (e.g. 30, 45, 60 days, etc.) that is used to schedule employees. For determining the demand side, a daily ML forecast can be run that accounts for actuals from the day before. The T1 ML forecast runs for all segment and language employee combinations using all models (in this implementation, 25 models) available and then uses RMSE for calculating the best recommended model for uniquely forecasting the daily demand (which may be broken down for each segment/language combination).”; Paragraph 255, “For identifying the best model based on a monthly call volume forecast, a plurality of models are evaluated based on the accuracy of their predictions/forecasts predicted a certain time in advance relative to the actual call volume. For example, a monthly call volume prediction may occur a minimum 60 days prior the actual forecasted month (e.g. on March 31st for June prediction) using latest three month actuals. Each of the plurality of models is run for 60 day predictions based on latest three month actuals, and produce daily forecast results which are aggregated for monthly volume. The models are tested for weighted Root Mean Squared Error (RMSE) and compared and ranked for variance to actual call volumes. The model with lowest RMSE can be automatically identified as recommended model for Call Volume forecast for each Segment and Language combination”) Claim(s) 3 and 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sciarra (WO 2025/019936 A1) in view of Qamar (US 2015/0269244 A1) and Yildirmaz (US 2016/0098664 A1) Claim(s) 3 and 12 – Sciarra in view of Qamar discloses the limitations of claims 1-2 and 10-11 Sciarra in view of Qamar does not explicitly disclose the following, however, in analogous art of workforce management, Yildirmaz discloses the following: wherein the two or more agent tenure windows comprise a first tenure window from 0 to 1 years, a second tenure window from 1 to 3 years, a third tenure window from 3 to 5 years, and a fourth tenure window of 5 years or greater. (Yildirmaz: Paragraph 57, “In the illustrative example, workforce 104 may be divided into groups 124 based on characteristics 126 about groups 124. In particular, characteristics 126 are about people 106 in workforce 104. A characteristic is an indication of a feature or quality about people 106. For example, characteristics 126 of people 106 in workforce 104 may be selected from at least one of industry, firm size, type of employment, employment status, wage by tier, amount of tenure, gender, age group, or other suitable types of characteristics for people in the workforce.”; Paragraph 109, “In the illustrative example, tenure 718 is a characteristic of the duration of time an employee has been with a particular employer. In this illustrative example, tenure 718 is selected from at least one of less than one year, one to three years, three to five years, five to ten years, or greater than ten years. Other types of tenure characteristics may also be used in workforce management environment 100 in FIG. 1.”) Sciarra discloses a method for generating models to forecast workforce management needs and capacities based on historical and current data. Qamar discloses a method for analyzing data and trends among an existing workforce. Yildirmaz discloses a method for identifying and predicting the vitality of a workforce. Before the filing date of Applicant’s filed invention, one of ordinary skill in the art would have deemed it obvious to combine the methods of Sciarra in view of Qamar with the teachings of Yildirmaz in order to better achieve business goals as it relates to a workforce as disclosed by Yildirmaz (Yildirmaz: Paragraph 7, “With the analysis of the workforce, the employer also may be able to predict the probability of success of an employee, identify when new departments or positions are needed, determine when positions may be reassigned or eliminated, identify changes in the work environment to increase job satisfaction, identify changes in the work environment to increase safety, determine when to purchase assets, optimize the organizational structure, and other suitable changes.”) Claim(s) 5-6, and 14-15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sciarra (WO 2025/019936 A1) in view of Qamar (US 2015/0269244 A1) and Birru (US 2016/0098664 A1) Claim(s) 5 and 14 – Sciarra in view of Qamar discloses the limitations of claims 1 and 10 Sciarra in view of Qamar does not explicitly disclose the following, however, in analogous art of workforce management, Birru discloses the following: wherein the different one or more sets of hyperparameters combinations are selected using grid search (Birru: Paragraph 203, “The method 1000, at step 1006, may include performing hyper-parameter tuning of the plurality of candidate forecasts. In an example embodiment, hyperparameter tuning can be performed using various techniques, including grid search, random search, or more advanced optimization algorithms like Bayesian optimization. By systematically exploring different combinations of hyperparameter values and evaluating the performance of the model using appropriate evaluation metrics, such as mean absolute error (MAE) or root mean squared error (RMSE), the optimal set of hyperparameters can be identified.”) Sciarra discloses a method for generating models to forecast workforce management needs and capacities based on historical and current data. Qamar discloses a method for analyzing data and trends among an existing workforce. Birru discloses a method for forecasting demand for a workforce. Before the effective filing date of Applicant’s invention, one of ordinary skill in the art would have deemed it obvious to combine the methods of Sciarra in view of Qamar with the teachings of Birru in order to improve the accuracy of the models for predicting workforce demands as disclosed by Birru (Birru: Paragraph 12, “This allows hospitals to assess the accuracy of forecasts and make necessary adjustments to improve future predictions. By incorporating feedback and new data, hospitals can refine their forecasting strategies and optimize resource allocation.”) Claim(s) 6 and 15 – Sciarra in view of Qamar discloses the limitations of claims 1, 4, 10, and 13 Sciarra in view of Qamar does not explicitly disclose the following, however, in analogous art of workforce management, Birru discloses the following: determine, for each of the candidate time-series models, a respective mean absolute percentage error (MAPE) value. (Birru: Paragraph 203, “The method 1000, at step 1006, may include performing hyper-parameter tuning of the plurality of candidate forecasts. In an example embodiment, hyperparameter tuning can be performed using various techniques, including grid search, random search, or more advanced optimization algorithms like Bayesian optimization. By systematically exploring different combinations of hyperparameter values and evaluating the performance of the model using appropriate evaluation metrics, such as mean absolute error (MAE) or root mean squared error (RMSE), the optimal set of hyperparameters can be identified.”) Sciarra discloses a method for generating models to forecast workforce management needs and capacities based on historical and current data. Qamar discloses a method for analyzing data and trends among an existing workforce. Birru discloses a method for forecasting demand for a workforce. Before the effective filing date of Applicant’s invention, one of ordinary skill in the art would have deemed it obvious to combine the methods of Sciarra in view of Qamar with the teachings of Birru in order to improve the accuracy of the models for predicting workforce demands as disclosed by Birru (Birru: Paragraph 12, “This allows hospitals to assess the accuracy of forecasts and make necessary adjustments to improve future predictions. By incorporating feedback and new data, hospitals can refine their forecasting strategies and optimize resource allocation.”) 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 Philip N Warner whose telephone number is (571)270-7407. The examiner can normally be reached Monday-Friday 7am-4:00pm. 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. /Philip N Warner/Examiner, Art Unit 3624 /Jerry O'Connor/Supervisory Patent Examiner,Group Art Unit 3624
Read full office action

Prosecution Timeline

Feb 11, 2025
Application Filed
Mar 25, 2026
Non-Final Rejection mailed — §103
Jun 11, 2026
Interview Requested
Jun 17, 2026
Applicant Interview (Telephonic)
Jun 25, 2026
Response Filed
Jul 11, 2026
Examiner Interview Summary
Sep 11, 2026
Final Rejection mailed — §103
Oct 20, 2026
Interview Requested

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12770085
METHODS AND SYSTEMS FOR IDENTIFYING AND ADDRESSING WORKER FATIGUE
3y 11m to grant Granted Oct 20, 2026
Patent 12770073
SYSTEM AND METHOD TO IDENTIFY JOBS TO BE DONE FOR ACHIEVING DESIRED BUSINESS OUTCOMES
2y 5m to grant Granted Oct 20, 2026
Patent 12737698
OPERATION PLAN GENERATION APPARATUS, AND OPERATION PLAN GENERATION METHOD
1y 11m to grant Granted Sep 15, 2026
Patent 12657530
METHOD AND SYSTEM FOR SYNTHESIZING CONSTRAINT BASED SMARTPHONE CUE-CARDS FOR SOCIO-TECHNICAL SYSTEM SERVICE DESIGN PROTOTYPING
2y 11m to grant Granted Jun 16, 2026
Patent 12657534
Artificial Intelligence-Powered Aggregation of Project-Related Collateral
3y 1m to grant Granted Jun 16, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

3-4
Expected OA Rounds
39%
Grant Probability
68%
With Interview (+28.3%)
Moderate
PTA Risk
Based on 120 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month