Search

EP-4309102-B1 - DATA DRIVEN APPROACHES FOR PERFORMANCE-BASED PROJECT MANAGEMENT

EP4309102B1EP 4309102 B1EP4309102 B1EP 4309102B1EP-4309102-B1

Inventors

  • ZHANG, YONGQIANG
  • LIN, WEI
  • WANG, Mohan
  • SCHMARZO, William

Dates

Publication Date
20260506
Application Date
20210317

Claims (6)

  1. A computer-implemented method for facilitating project management, comprising: for input of a project comprising project data and employee data, executing feature extraction on the project data and the employee data to generate features (700); executing a self-profiling algorithm (103) configured with unsupervised machine learning on the generated features (700) to derive clusters and anomalies of the project; executing a performance monitoring process (104) on the generated features (700) to determine a probability of a key performance indicator value at a milestone; and executing a supervised machine learning model (703) on the generated features (700), the derived clusters, the derived anomalies, the probability of the key performance indicator value at the milestone to generate a predicted performance value (704) of the project; characterized in that the executing the self- profiling algorithm configured with the unsupervised machine learning on the generated features (700) to derive the clusters and the anomalies of the project comprises: a) applying a set of unsupervised machine learning model algorithms to the generated features (700) to generate an unsupervised machine learning model for each of the unsupervised machine learning algorithms; b) attaching unsupervised output form the unsupervised machine learning model to the features; and c) reiterating steps a) and b) until an exit criteria is met.
  2. The computer-implemented method of claim 1, wherein the executing the self-profiling algorithm (103) configured with the unsupervised machine learning on the generated features (700) to derive the clusters and the anomalies of the project comprises: executing the unsupervised machine learning to generate unsupervised machine learning models based on the generated features (700); executing supervised machine learning (703) on results from each of the unsupervised machine learning models to generate supervised ensembled machine learning models, each of the supervised ensemble machine learning models corresponding to each of the unsupervised machine learning models; and selecting ones of the unsupervised machine learning models as the models configured to derive the clusters and the anomalies based on an evaluation of the results of the unsupervised machine learning models against predictions generated by the supervised ensemble machine learning models.
  3. The computer-implemented method of claim 1, wherein the executing the self- profiling algorithm (103) configured with the unsupervised machine learning on the generated features (700) to derive the clusters and the anomalies of the project comprises: executing each unsupervised machine learning model algorithm from a set of unsupervised learning model algorithms on the generated features (700); determining one of the unsupervised machine learning models with an associated parameter set for the each unsupervised machine learning model algorithm that meets a selection criteria; determining an unsupervised machine learning model for deployment across the set of the unsupervised machine learning model algorithms from the one of the unsupervised machine learning models of the each unsupervised machine learning model algorithm that meets the selection criteria.
  4. The computer-implemented method of claim 3, further comprising deploying the unsupervised machine learning model for deployment; and during deployment of the unsupervised model for deployment: applying the unsupervised machine learning model for deployment to the generated features (700) to generate unsupervised output; attaching the unsupervised output to the features to get the expanded features; randomly selecting another unsupervised learning model algorithm from the set of unsupervised machine learning model algorithms; training the randomly selected unsupervised learning model algorithm on the expanded features to find another unsupervised machine learning model with another associated parameter set that meets the selection criteria; and for the another unsupervised learning model generated from the randomly selected unsupervised learning model algorithm having a better evaluation than the deployed unsupervised learning model for deployment, replacing the deployed unsupervised learning model for deployment with the another unsupervised learning model.
  5. The computer-implemented method of claim 1, wherein the executing the performance monitoring process (104) on the generated features (700) to determine the probability of a key performance indicator value at a milestone comprises: generating, from historical projects, a transition network relating a transition between a plurality of first key performance indicators in a first milestone to a plurality of second key performance indicators in a second milestone; wherein the probability of the transition is determined based on a number of times the plurality of first key performance indicators of the first milestone transitioned to the second key performance indicators in the second milestone.
  6. The computer-implemented method of claim 1, wherein the executing a performance monitoring process (104) on the generated features (700) to determine the probability of the key performance indicator value at the milestone comprises: generating a multi-tasking supervised machine learning model to predict the key performance indicator values at the milestone based on the key performance indicator values at earlier milestones; wherein the probability of the key performance indicator value is one of a category for when a classification model is used as the multi-tasking supervised machine learning model or a numerical score for when a regression model is used as the multi-tasking supervised machine learning model; and wherein the key performance indicator values at the milestone are predicted concurrently.

Description

BACKGROUND Field The present disclosure is directed to project management systems, and more specifically, to the use of data driven approaches to facilitate performance-based project management. Related Art A project (or program) is any undertaking, carried out individually or collaboratively through research or design, that is carefully planned (e.g., by a project team) to achieve a particular aim. A project can have various attributes. For example, projects can be internal (e.g., product development) or external (e.g., customer solutions). Projects can also fall into different categories, such as software, service, and analytics. Projects can be in different industries, such as manufacturing, transportation, and healthcare among others. Projects vary in duration, extending from weeks to months to years. Projects can involve one-time tasks (e.g., consulting) or continuous work (e.g., consulting phases I, II, III; product development versions 1, 2, 3) Given a project, the manager or stakeholder needs to understand and analyze these project attributes listed above and plan the management and execution of the project accordingly. The manager or stakeholder can analyze each individual attribute separately, combine several attributes together manually, and gain insights based on their experience and domain knowledge. To optimize effectively, the project management includes several key components for consideration. A project can be managed as a sequence of events, which can often be a set of interrelated tasks that are executed over a fixed period of time and within certain cost range along with other limitations and risks. Before the project officially starts, the manager or stakeholder may need to estimate the performance, such as delivered profit margin. The manager or stakeholder may need to plan on the management and execution of the project to achieve the best outcome and performance. After the project starts, the manager may need to monitor the project progress and adjust the execution plan of the project as needed. SUMMARY Several limitations and restrictions of conventional systems and methods are discussed below. The example implementations described herein introduce techniques to address the following issues. At it, as a related art, Fanaei Seyedeh-Sara: "Performance Measurement, Forecasting and Optimization Models for Construction Porjects", a thesis in the Department of Building, Civil and Environmental Engineering, April 1st, 2019, XP055975778 is known, in which a performance evaluation mechanism for determined projects based on the combination of Fuzzy C-means algorithms (FCM), subtractive clustering and artificial neural networks (ANN) is stipulated. In addition, in US 2018/191867 A1, various systems, methods and devices for a cyberphysical (IoT) software application development platform based upon a model driven architecture and derivative IoT SaaS applications are disclosed. Specifically, the system may include concentrators to receive and forward time-series data from sensors while also include message decoders to receive messages comprising the times-series data and storing the messages on message queues. US 2019/138968 A1 relates to an enterprise AI and Internet-of-things platform. US 2018/060744 A1 discloses creating a predictive model utilized during a prediction problem. In a first issue with the related art, the project is manually reviewed and analyzed based on the project attributes. The understanding and analysis results are used to gain the insights of the project. Some important hidden factors in the project may not be discovered. Such review and analysis process can be time-consuming, subjective, and prone to risk. There is a need to automate the project analysis and profiling with a data-driven approach to discover the hidden factors for business insights in the project. In a second issue with the related art, the project is manually monitored through regular check-ups or milestones. The performance of the project is manually analyzed and evaluated, and some adjustments may be made to the execution plan. Such monitoring and evaluation are time-consuming, subjective, and prone to risk. There is a need to have an automated and standard process or approach to monitor and evaluate the project progress with a data-driven approach. In a third issue with the related art, the performance of the project is manually estimated based on the understanding and analytic results of some attributes of the project, some aspects of the human resources, and some constraints. However, not all attributes of the project, the human resources, and the constraints are systematically analyzed and summarized. Not all available information is utilized or used properly. Also, usually the estimate is on the final delivered performance, such as delivered profit margin, based on the available information before the project starts. Such manual estimation based on experience and domain knowledge is subjective, time