CA3170083A1

CA3170083A1 - Systems and methods for project and program management using artificial intelligence

Info

Publication number: CA3170083A1
Application number: CA3170083A
Authority: CA
Inventors: Muhammad Shoaib Munir
Original assignee: Mavryck Inc
Current assignee: Mavryck Inc
Priority date: 2022-08-10
Filing date: 2022-08-10
Publication date: 2022-11-07
Anticipated expiration: 2042-08-10
Also published as: CA3170083C; WO2024031191A1

Abstract

A project and program management system has one or more databases having schedule data for historical and current projects; and a server computer having an input interface and an output interface, and configured to perform artificial intelligence (AI) processing using an artificial neural network (ANN) for one or more project and program management functions at least having a critical path function for determining a critical path of a current project. The server computer is configured to obtain instructions from the input interface, access the schedule data from the one or more databases, and display results through the output interface.

Description

SYSTEMS AND METHODS FOR
PROJECT AND PROGRAM MANAGEMENT USING ARTIFICIAL INTELLGENCE
FIELD OF THE DISCLOSURE
The present disclosure relates generally to project and program management systems, and in particular to computerized methods and systems for project and program management using artificial intelligence.
BACKGROUND
Project and program management is known. While historically, project and program management is largely performed manually, computerized project and program management leverages the computational power of computer systems for managing complex projects and programs, which also expands the use of computer systems.
Conventional project and program management commonly uses critical path method (CPM) which generally includes listing all activities or tasks required to complete a project. Such activities or tasks may be categorized within a work-breakdown structure as determining the time duration that each activity or task will require to complete, determining dependencies between the activities or tasks, determining logical end points such as milestones or deliverable items, and/or the like.
Projects or programs managed using CPM do not generally have a mechanism to check whether the input parameters are correct or not. CPM assumes that resources are available and that the applicable skill and/or productivity level is at 100%, which is often not accurate. CPM
analysis does not account for limitations on resource capacity as it assumes that there will be enough capacity to complete all tasks. CPM analysis does not utilize prior knowledge of historical records for similar types of projects or programs. Further, CPM analysis does not provide a framework to predict costs, consider environmental impacts, and address worker safety issues.
With such defects, conventional computerized project and program management system usually requires frequent human intervention for ensuring the correctness of project/program monitoring and managing.
US Patent No. 9,002,721 to Hughes discloses a system for planning and executing projects, facilities creating a project model comprising tasks and dependencies, determining the complexity of the tasks and modifying the tasks to maintain complexity within pre-determined bounds. The system can facilitate designating one or more tasks to be redundant tasks, and undertaking the redundant tasks with redundant resources. In some embodiments, the system includes a module Date Recue/Date Received 2022-08-10 for evaluating task criticality and designating redundant tasks based on the task complexity and criticality.
US Patent Application Publication No. US2022/0083941 to Khanna et al.
discloses a construct computing system including a construct computing device including a processor in communication with at least one memory device. The processor is programmed to:
(i) receive construction data associated with a construction project, wherein the construction data includes schedule data, budgeting data, and drawing data, (ii) store, in the memory, the construction data, (iii) generate a schedule and a budget for the construction project based upon the construction data, (iv) receive, from a user computing device, input associated with the construction data, wherein the input includes a modification to at least one of the schedule data, the budgeting data, and the drawings, and (v) modify at least one of the schedule, the budget, and the drawings based upon the input.
US Patent Application Publication No. US2022/0060541 to Shokooh et al.
discloses systems, devices, and methods for a digital collaborative system for electric, water and gas engineering and operations. The systems, devices, and methods include an automatic and intelligent synchronization of simultaneous and parallel project or digital twin modifications between multiple users in a collaborative environment that integrates utility engineering and operation teams.
US Patent Application Publication No. U52022/0058552 to Takahashi et al.
discloses a project management system having functions of receiving one or more inputs regarding "problem information", "risk information", and "task information" (all of the problem information, risk information, and task information are "project management information"), holding the project management information in association with each piece of identification information, acquiring problem solution status information in association with problem identification information, and outputting the acquired information in association with the problem information.
US Patent Application Publication No. US2022/0092517 to Morgan et al.
discloses a method including operations of displaying a schedule interface including a first work item user interface element corresponding to a first work item, the first work item user interface element displayed to visually indicate a scheduled start date of the first work item and a scheduled end date for the first work item; receiving forecast data generated in respect of the first work item;
determining, based on the forecast data, a first forecast range in respect of the first work item; and displaying a first forecast user interface element on the schedule interface, the first forecast user interface element corresponding to the first work item and having an appearance based on the first forecast range.

2 Date Recue/Date Received 2022-08-10 US Patent Application Publication No. US2022/0101235 to Khalil discloses embodiments of a computer program product that provides systems and methods as a complete solution for management profession from initiation to closeout; complies with industry standards and requirements. Automated functionality through cloud-based server, standardized combination of database management systems with five main user interfaces with an additional (extended) two user interfaces for post project completion during warrantee and operations periods/phases. The web-based user's interfaces were set for each organizational tier and for quick and emergency responses using the GPS locations for the users, roadways and providers. On real time communication, simultaneous functionality of the integrated databases provides ultimate optimization while the unified filing system and document control solution facilitates system integrations of the management knowledge areas. Public outreach enhancement with a project specific website displays permitted information to allow public search and view projects general information including alerts and status.
SUMMARY
Embodiments disclosed herein relate to computerized systems and methods for project and program management using artificial-intelligence (Al) processing for current and past data in one or more industry clusters to provide trends, predict and avoid risks relating to factors such as scheduling, costs, liability, safety and environmental. In some embodiments disclosed herein, the Al processing also includes object detection technology, artificial neural networks, natural language processing and a k-nearest neighbour method.
According to one aspect of this disclosure, there is provided a project and program management system including one or more databases including schedule data for historical and current projects; and a server computer including an input interface and an output interface, and configured to perform Al processing using an artificial neural network (ANN) for one or more project and program management functions at least including a critical path function for determining a critical path of a current project; the server computer is configured to obtain instructions from the input interface, access the schedule data from the one or more databases, and display results through the output interface.
In some embodiments, the project and program management system is configured to operate on a cloud-based computer architecture, the server computer including a first and a second server computer of allocated scalable computing capacity; the system further including: a network storage element, a client computing device for use by a user, and a network for connecting the client computing device, the network storage element, the first server computer, and the second server computer, wherein the first server computer includes an interface to communicate with the

3 Date Recue/Date Received 2022-08-10 client computing device over the network, the first server computer includes the one or more databases, and the second server computer is configured to perform the Al processing.
In some embodiments, the one or more project and program management functions further includes an accelerator and de-risking function for identifying risky and critical tasks.
In some embodiments, the one or more databases further includes historical schedule data, and the one or more project and program management functions further includes one or more of:
a bow wave trend analyzer function for displaying bow wave trends, a critical path trend analyzer function for comparing critical paths, and a total float trend analyzer function for analyzing trends in total floats.
In some embodiments, the Al processing further includes natural language processing (NLP); and the one or more project and program management functions further includes one or more of: an early warning schedule function, a garage in garbage out (GIGO) schedule function for identifying scheduling errors, a potential claims function for identifying tasks that can cause potential claims, and a schedule risk function for identifying risky tasks.
In some embodiments, the one or more databases further includes cost data for current projects; and the one or more project and program management functions further includes one or more of: a cost savings function for identifying and recommending cost savings, and a cost risk function for identifying tasks that at risk of running over pre-determined thresholds.
In some embodiments, the Al processing further includes NLP; the one or more databases further includes cost data for current projects, and historical cost and schedule data; and the one or more project and program management functions further includes one or more of: a completion probability function for analyzing a probability of completion of the current project, a cost trend analyzer function for analyzing cost trends of the current project, an early warning cost function for providing budget warnings, and a GIGO cost function for identifying cost errors.
In some embodiments, the Al processing further includes NLP and a term frequency inverse document frequency method; and the one or more databases further includes green house gas (GHG) data; and wherein the one or more project and program management functions further includes a GHG calculation function for performing carbon footprint and GHG
calculations and recommending alternative energy sources.
In some embodiments, the project and program management system further configured to receive video monitoring input and the Al processing further includes object detection technology;
and wherein the one or more project and program management functions further includes a site monitoring function for enhancing compliance and safety of the current project.

4 Date Recue/Date Received 2022-08-10 In some embodiments, the video monitoring input includes thermal or infrared imaging;
and wherein the site monitoring function is configured to analyze the thermal or infrared imaging by interpreting colours and intensities thereof.
In some embodiments, the Al processing further includes NLP; the one or more databases further includes news events data; and the one or more project and program management functions includes a risk events analysis function for identifying current events that may impact the current project.
In some embodiments, the Al processing further includes NLP; the one or more databases further includes contractual data; and the one or more project and program management functions includes a contract analyzer function for identifying clauses with risky words in the contractual data.
In some embodiments, the Al processing further includes NLP; the one or more databases further includes report data; and the one or more project and program management functions includes a report analyzer function for identifying terms with risky words in the report data.
In some embodiments, the Al processing further includes NLP and a k-nearest neighbour (KINN) method; and the one or more project and program management functions includes a resource optimization function for optimizing the use of resources on the current project.
In some embodiments, the system is configured to provide a textual analytical description of graphics displayed.
According to one aspect of this disclosure, there is provided a method for managing a project or program including: receiving instructions for performing one or more functions for project and program management; and performing the one or more functions including the steps of: retrieving schedule data for a current project, determining a critical path of the current project using artificial intelligence (Al) processing using an artificial neural network (ANN), and displaying the critical path.
In some embodiments, the one or more functions further includes the steps of:
extracting task data inputs from the schedule data; calculating update critical paths for each update of the current project using task data inputs; and displaying the update critical paths.
In some embodiments, the one or more functions further includes the steps of:
extracting project and task data from the schedule data; compiling a list of tasks identified as completed in less than average duration; sorting the list of tasks to provide a sorted list of tasks; and displaying the sorted list of tasks.
In some embodiments, the one or more functions further includes the steps of:
retrieving news items; compiling a list of relevant news items; scoring each item in the list of relevant news items as opportunities or risks; and displaying the list of relevant news items.

5 Date Recue/Date Received 2022-08-10 In some embodiments, the one or more functions further includes the steps of:
compiling a list of relevant news items scored as risks; retrieving mitigation plans;
identifying recommended mitigation plans to address risks in the list of relevant news items scored as risks; and displaying the recommended mitigation plans.
In some embodiments, the one or more functions further includes the steps of:
extracting task data from the schedule data; identifying risky tasks from the task data and compiling a list of risky tasks; and displaying the list of risky tasks.
In some embodiments, the one or more functions further includes the steps of:
extracting task data from the schedule data; identifying unfinished tasks in the task data; retrieving historical schedule data; identifying similar tasks from the historical schedule data for all of the unfinished tasks; calculating a completion probability using Al and ANN using the similar tasks from the historical data and the unfinished tasks; and displaying the completion probability.
In some embodiments, the one or more functions further includes the steps of:
extracting task data from the schedule data; calculating total floats using Al and ANN
using the task data;
and displaying the total floats.
In some embodiments, the one or more functions further includes the steps of:
extracting task data from the schedule data; producing bow waves of tasks and their durations using the task data; and displaying the bow waves.
In some embodiments, the one or more functions further includes the steps of:
extracting a list of tasks from the schedule data; retrieving historical schedule data;
identifying and mapping tasks in the list of tasks to historical schedule data; determine if logic error is detected by analyzing the mapped list of tasks and the historical schedule data; and alerting user if logic error is detected.
In some embodiments, the one or more functions further includes the step of adding a new schedule sequence to the historical schedule data.
In some embodiments, the one or more functions further includes the steps of:
extracting tasks from the schedule data; determining if actual duration of the tasks is outside of an average duration range, wherein if the actual duration of the tasks is greater than the average duration range, an overall delay on a project is calculated and one or more available resources can be recommended; and displaying the overall delay.
In some embodiments, the one or more functions further includes the steps of:
extracting a source task and a target task for a predecessor task from the schedule data;
confirming the source task and the target task belong to a same work breakdown structure;
determining if time difference between source task and target task may result in a potential claim based on one or more relation types; compiling a list of potential claims; and display the list of potential claims.

6 Date Recue/Date Received 2022-08-10 In some embodiments, the one or more functions further includes the steps of:
receiving video monitoring data; detecting objects in the video monitoring data;
creating bounding box areas around the objects; analyzing the bounding box areas for compliance and safety issues; and display compliance and safety issues.
In some embodiments, the one or more functions further includes the step of retrieving scheduling information to determine areas and times of interest.
In some embodiments, the one or more functions further includes the step of analyzing the video monitoring data using thermal imaging.
In some embodiments, the one or more functions further includes the steps of:
retrieving a contract file; extracting clauses from the contract file; identifying identified clauses containing flagged words or language; determining if the identified clauses are likely to be positive or negative; and displaying a listing of the identified clauses.
In some embodiments, the one or more functions further includes the step of estimating liquidated damages.
In some embodiments, the one or more functions further includes the steps of:
retrieving a report file; extracting terms from the report file; identifying identified terms containing flagged words or language; determining if the identified terms are likely to be positive or negative; and displaying a listing of the identified terms.
In some embodiments, the one or more functions further includes the steps of:
retrieving a cost file; extracting a listing of tasks from the cost file; retrieving historical cost data; identifying similar tasks in the historical cost data for all unfinished tasks in the listing of tasks; calculating predicted cost trends using ANN using the similar tasks and the historical cost data; and displaying cost trend results.
In some embodiments, the one or more functions further includes the steps of:
retrieving a cost file; extracting tasks from the cost file; identifying tasks at a cost risk of running over pre-determined cost thresholds; and displaying the cost risks.
In some embodiments, the one or more functions further includes the steps of:
retrieving a cost file; extracting tasks from the cost file; determining recommendations for cost savings by analyzing the tasks; and displaying cost savings recommendations.
In some embodiments, the one or more functions further includes the steps of:
retrieving a greenhouse gas (GHG) file; extracting GHG data from the GHG file; calculate carbon footprints and scores using the GHG data; and displaying carbon footprint and scores.
In some embodiments, the one or more functions further includes the step of recommending alternative energy sources.

7 Date Recue/Date Received 2022-08-10 In some embodiments, the one or more functions further includes the step of displaying levels of emissions according to regions or assets.
In some embodiments, the one or more functions further includes the step of simulating emissions with changed attributes.
In some embodiments, the one or more functions further includes the steps of:
extracting current tasks from the schedule data; retrieving resource data; retrieving historical task data;
identifying similar tasks in the current tasks with the historical task data;
making resource recommendations for the similar tasks; and displaying the resource recommendations.
In some embodiments, the one or more functions further includes the step of allocating resources to the similar tasks that are immediately actionable.
In some embodiments, the one or more functions further includes the step of identifying a list of priority tasks.
In some embodiments, the one or more functions further includes the steps of:
retrieving a cost file; extracting tasks from the cost file; retrieving historical cost data; identifying and mapping similar tasks in the tasks to the historical cost data; comparing cost information in the similar tasks with the historical cost data to identify potential errors;
displaying the potential errors.
In some embodiments, the one or more functions further includes the steps of:
extracting tasks from the schedule data; retrieving historical task data; identifying and mapping similar tasks in the tasks to the historical task data; comparing the similar tasks with the similar historical task data; determining if estimated finish dates of the similar tasks exceed a budgeted finish date by a threshold value; and displaying similar tasks where the estimated finish dates exceed the budgeted finish date by the threshold value.
In some embodiments, the one or more functions further includes the steps of:
retrieving a cost file; extracting tasks from the cost file; retrieving historical cost data; identifying and mapping similar tasks in the task to the historical cost data; comparing the similar tasks with the historical cost data; determining if estimated costs of the similar tasks is greater than a threshold percentage; and displaying similar tasks where the estimated costs is greater than the threshold percentage.
In some embodiments, the method further includes displaying a textual analytical description of graphics displayed.
BRIEF DESCRIPTION OF THE DRAWINGS
For a more complete understanding of the disclosure, reference is made to the following description and accompanying drawings, in which:

8 Date Recue/Date Received 2022-08-10 FIG. 1 is a schematic diagram of a computerized project and program management system, according to some embodiments of the present disclosure;
FIG. 2 is a schematic diagram showing a simplified hardware structure of a computing device of the computerized project and program management system shown in FIG.
1;
FIG. 3 a schematic diagram showing a simplified software architecture of a computing device of the computerized project and program management system shown in FIG.
1;
FIG. 4 is a schematic diagram showing a functional structure of the computerized project and program management system shown in FIG. 1 implemented as a cloud-based computer system, according to an embodiment of the present disclosure;
FIG. 5A is a schematic diagram of an embodiment of an artificial neural network for calculating a critical path of a project;
FIG. 5B is a flowchart of an embodiment of a critical path method function;
FIG. 6A is a flowchart of an embodiment of a critical path trend analyzer function;
FIGs. 6B to 6D are a flowchart of an example embodiment of the critical path trend analyzer function of FIG. 6A;
FIG. 7A is a flowchart of an embodiment of an accelerator and de-risking function;
FIGs. 7B and 7C are a flowchart of an example embodiment of the accelerator and de-risking function of FIG. 7A;
FIGs. 8A and 8B are flowchart of a risk events analysis function;
FIG. 8C is a schematic diagram of an embodiment of a recommendation engine for performing risk events analysis;
FIGs. 8D to 8H are a flowchart of an example embodiment of the risk events analysis function of FIGs. 8A and 8B;
FIG. 9 is a flowchart of an embodiment of a schedule risk function;
FIG. 10A is a flowchart of an embodiment of a completion probability function;
FIG. 10B is a schematic diagram of an embodiment of an artificial neural network for performing completion probability calculations;
FIGs. 10C to 10G are a flowchart of an example embodiment of the completion probability function of FIG. 10A;
FIG. 11A is a flowchart of an embodiment of a total float trend analyzer function;
FIG. 11B is a schematic diagram of an embodiment of an artificial neural network for performing total float trend calculations;
FIGs. 11C to 11E are a flowchart of an example embodiment of the total float trend analyzer function of FIG. 11A;
FIG. 12A is a flowchart of an embodiment of a bow wave trend analyzer function;

9 Date Recue/Date Received 2022-08-10 FIGs. 12B and 12C are a flowchart of an example embodiment of the bow wave trend analyzer function of FIG. 12A;
FIGs. 13A and 13B are a flowchart of an embodiment of a schedule garbage in garbage out function;
FIGs. 13C to 13E are a flowchart of an example embodiment of the schedule garbage in garbage out function of FIGs. 13A to 13B;
FIG. 14A is a flowchart of an embodiment of a potential claims function;
FIGs. 14B to 14D are a flowchart of an example embodiment of the potential claims function of FIG. 14A;
FIG. 15A is a flowchart of an embodiment of a site monitoring function;
FIGs. 15B to 15E are a flowchart of an example embodiment of the site monitoring function of FIG. 15A;
FIG. 16A is a flowchart of an embodiment of a contract analyzer function;
FIGs. 16B to 16F are a flowchart of an example embodiment of the contract analyzer function of FIG. 16A;
FIG. 17 is a flowchart of an embodiment of a report analyzer function;
FIG. 18A is a flowchart of an embodiment of a cost trend analyzer function;
FIG. 18B is a schematic diagram of an embodiment of an artificial neural network for performing cost trend calculations;
FIG. 19 is a flowchart of an embodiment of a cost risk function;
FIG. 20 is a flowchart of an embodiment of a cost savings function;
FIG. 21A is a flowchart of an embodiment of a greenhouse gas calculation function;
FIG. 21B is a schematic diagram of an embodiment of a support vector classifier for performing greenhouse gas calculations;
FIGs. 21C to 21F are a flowchart of an example embodiment of the greenhouse gas calculation function of FIG. 21A;
FIG. 22A is a flowchart of an embodiment of a resource optimization function;
FIGs. 22B to 22F are a flowchart of an example embodiment of the resource optimization function of FIG. 22A;
FIG. 23A is a flowchart of an embodiment of a cost garbage in garbage out function;
FIGs. 23B to 23E are a flowchart of an example embodiment of the cost garbage in garbage out function of FIG. 23A;
FIG. 24A is a flowchart of an embodiment of an early warning schedule function;
FIGs. 24B to 24E are a flowchart of an example embodiment of the early warning schedule function of FIG. 24A;
Date Recue/Date Received 2022-08-10 FIG. 25A is a flowchart of an embodiment of an early warning cost function;
FIGs. 25B to 25D are a flowchart of an example embodiment of the - function of FIG. 25A;
and FIGs. 26A to 26D are examples of user interfaces of an embodiment of a project and program management system.
DETAILED DESCRIPTION
Embodiments disclosed herein relate to computerized systems and methods of project and program management. As those skilled in the art will appreciate, a project usually comprises a plurality of steps each of which may involve or otherwise require various resources. The execution of each step may be according to a schedule and may face various risks, and may be successful or failure. The plurality of steps may be interrelated in that the success or failure of the execution of a previous step may impact the execution of a subsequent step. Moreover, the failure of one or more steps may cause the project to fail. Therefore, it is critical to closely monitor the execution of the steps of a project and it may be beneficial to predict the trend of the project during the execution thereof such that the resources and/or the execution order of the steps of the project may be adaptively adjusted to lower the risk and increase the probability of success.
While project monitoring and prediction may be manually conducted, the diversified natures, types and complexities of various projects may cause a significant burden to a project administrator to manually monitor the execution of a project and may prevent the project administrator from successfully identifying the critical path and other factors that may impact the success of the project. Moreover, some complex projects may have a tight schedule and require fast prediction and adjustment to the project. However, manual project monitoring and prediction may not be able to successfully provide correct prediction and appropriate adjustment within a required short time period.
The computerized systems and methods disclosed herein utilizes artificial intelligence (Al) including object detection technologies, artificial neural networks (ANN), natural language processing (NLP), and k-nearest neighbour (KINN) methods to provide project management functions for predicting trends, predicting and avoiding risks relating to factors such as scheduling, cost, liability, safety, environmental factors, and/or the like. In some embodiments disclosed herein, factors associated with schedule-related risks such as risky tasks, critical tasks, external current events, errors, potential safety hazards, and/or the like are analyzed. In some other embodiments disclosed herein, factors associated with cost-related risks such as potential claims, contractual related factors and errors, and/or the like are analyzed. In yet some other embodiments Date Recue/Date Received 2022-08-10 disclosed herein, factors associated with greenhouse-gas (GHG) emissions such as GHG gas emissions, carbon footprint, type of assets, relevant industries and resources are analyzed. In still some other embodiments, early warnings related to scheduling and costs are provided to operators of the system.
Computing Architecture Embodiments of project and program management systems disclosed herein may be implemented on a variety of computer network architectures. Referring to FIG.
1, a computer network system for project and program management is shown and is generally identified using reference numeral 100. As shown, the computer network system 100 comprises one or more server computers 102 and a plurality of client computing devices 104 functionally interconnected by a network 108, such as the Internet, a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), and/or the like, via suitable wired and wireless networking connections.
The server computers 102 may be computing devices designed specifically for use as a server, and/or general-purpose computing devices acting as server computers while also being used by various users. Each server computer 102 may execute one or more server programs.
The client computing devices 104 may be portable and/or non-portable computing devices such as laptop computers, tablets, smartphones, Personal Digital Assistants (PDAs), desktop computers, and/or the like. Each client computing device 104 may execute one or more client application programs which sometimes may be called "apps".
Generally, the computing devices 102 and 104 have a similar hardware structure such as a hardware structure 120 shown in FIG. 2. As shown, the computing device 102/104 comprises a processing structure 122, a controlling structure 124, one or more non-transitory computer-readable memory or storage devices 126, a network interface 128, an input interface 130, and an output interface 132, functionally interconnected by a system bus 138. The computing device 102/104 may also comprise other components 134 coupled to the system bus 138.
The processing structure 122 may be one or more single-core or multiple-core computing processors (also called "central processing units" (CPUs)) such as INTEL
microprocessors (INTEL is a registered trademark of Intel Corp., Santa Clara, CA, USA), AMD
microprocessors (AMD is a registered trademark of Advanced Micro Devices Inc., Sunnyvale, CA, USA), ARM
microprocessors (ARM is a registered trademark of Arm Ltd., Cambridge, UK) manufactured by a variety of manufactures such as Qualcomm of San Diego, California, USA, under the ARM
architecture, or the like. When the processing structure 122 comprises a plurality of processors, the processors thereof may collaborate via a specialized circuit such as a specialized bus or via the system bus 138.

Date Recue/Date Received 2022-08-10 The processing structure 122 may also comprise one or more real-time processors, programmable logic controllers (PLCs), microcontroller units (MCUs), pt-controllers (UCs), specialized/customized processors and/or controllers using, for example, field-programmable gate array (FPGA) or application-specific integrated circuit (ASIC) technologies, and/or the like.
Generally, each processor of the processing structure 122 comprises necessary circuitries implemented using technologies such as electrical and/or optical hardware components for executing one or more processes as the implementation purpose and/or the use case maybe, to perform various tasks. In many embodiments, the one or more processes may be implemented as firmware and/or software stored in the memory 126 and may be executed by the one or more processors of the processing structure 122. Those skilled in the art will appreciate that, in these embodiments, the one or more processors of the processing structure 122, are usually of no use without meaningful firmware and/or software.
For example, each processor of the processing structure 122 may comprise logic gates implemented by semiconductors to perform various computations, calculations, and/or processings. Examples of logic gates include AND gate, OR gate, XOR (exclusive OR) gate, and NOT gate, each of which takes one or more inputs and generates or otherwise produces an output therefrom based on the logic implemented therein. For example, a NOT gate receives an input (for example, a high voltage, a state with electrical current, a state with an emitted light, or the like), inverts the input (for example, forming a low voltage, a state with no electrical current, a state with no light, or the like), and output the inverted input as the output.
While the inputs and outputs of the logic gates are generally physical signals and the logics or processings thereof are tangible operations with physical results (for example, outputs of physical signals), the inputs and outputs thereof are generally described using numerals (for example, numerals "0" and "1") and the operations thereof are generally described as "computing"
.. (which is how the "computer" or "computing device" is named) or "calculation" or more generally, "processing", for generating or producing the outputs from the inputs thereof.
Sophisticated combinations of logic gates in the form of a circuitry of logic gates, such as the one or more processors of the processing structure 122, may be formed using a plurality of AND, OR, XOR, and/or NOT gates. Such combinations of logic gates may be implemented using individual semiconductors, or more often be implemented as integrated circuits (ICs).
A circuitry of logic gates may be "hard-wired" circuitry which, once designed, may only perform the designed tasks. In this example, the tasks thereof are "hard-coded" in the circuitry.
With the advance of technologies, it is often that a circuitry of logic gates, such as the one or more processors of the processing structure 122, may be alternatively designed in a general manner so that it may perform various tasks according to a set of "programmed"
instructions Date Recue/Date Received 2022-08-10 implemented as firmware and/or software and stored in the memory 126. In this example, the circuitry of logic gates, such as the one or more processors of the processing structure 122, is usually of no use without meaningful firmware and/or software.
Of course, those skilled the art will appreciate that a processor may be implemented using other technologies such as analog technologies.
The controlling structure 124 comprises one or more controlling circuits, such as graphic controllers, input/output chipsets, and the like, for coordinating operations of various hardware components and modules of the computing device 102/104.
The memory 126 comprises one or more one or more non-transitory computer-readable storage devices or media accessible by the processing structure 122 and the controlling structure 124 for reading and/or storing instructions for the processing structure 122 to execute, and for reading and/or storing data, including input data and data generated by the processing structure 122 and the controlling structure 124. The memory 126 may be volatile and/or non-volatile, non-removable or removable memory such as RAM, ROM, EEPROM, solid-state memory, hard disks, .. CD, DVD, flash memory, or the like. In use, the memory 126 is generally divided into a plurality of portions for different use purposes. For example, a portion of the memory 126 (denoted as storage memory herein) may be used for long-term data storing, for example, for storing files or databases. Another portion of the memory 126 may be used as the system memory for storing data during processing (denoted as working memory herein).
The network interface 128 comprises one or more network modules for connecting to other computing devices or networks through the network 108 by using suitable wired or wireless communication technologies such as Ethernet, WI-Fl (WI-Fl is a registered trademark of "Wi-Fi Alliance, Austin, TX, USA), BLUETOOTH (BLUETOOTH is a registered trademark of Bluetooth Sig Inc., Kirkland, WA, USA), Bluetooth Low Energy (BLE), Z-Wave, Long Range (LoRa), ZIGBEE (ZIGBEE is a registered trademark of ZigBee Alliance Corp., San Ramon, CA, USA), wireless broadband communication technologies such as Global System for Mobile Communications (GSM), Code Division Multiple Access (CDMA), Universal Mobile Telecommunications System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX), CDMA2000, Long Term Evolution (LTE), 3GPP, 5G New Radio (5G NR) and/or other 5G networks, and/or the like. In some embodiments, parallel ports, serial ports, USB
connections, optical connections, or the like may also be used for connecting other computing devices or networks although they are usually considered as input/output interfaces for connecting input/output devices.
The input interface 130 comprises one or more input modules for one or more users to input data via, for example, touch-sensitive screens, touch-sensitive whiteboards, touch-pads, Date Recue/Date Received 2022-08-10 keyboards, computer nice, trackballs, microphones, scanners, cameras, and/or the like. The input interface 130 may be a physically integrated part of the computing device 102/104 (for example, the touch-pad of a laptop computer or the touch-sensitive screen of a tablet), or may be a device physically separated from but functionally coupled to, other components of the computing device 102/104 (for example, a computer mouse). The input interface 130, in some implementation, may be integrated with a display output to form a touch-sensitive screen or a touch-sensitive whiteboard.
The output interface 132 comprises one or more output modules for output data to a user.
Examples of the output modules include displays (such as monitors, LCD
displays, LED displays, projectors, and the like), speakers, printers, virtual reality (VR) headsets, augmented reality (AR) goggles, and/or the like. The output interface 132 may be a physically integrated part of the computing device 102/104 (for example, the display of a laptop computer or a tablet), or may be a device physically separate from but functionally coupled to other components of the computing device 102/104 (for example, the monitor of a desktop computer). The computing device 102/104 may also comprise other components 134 such as one or more positioning modules, temperature sensors, barometers, inertial measurement units (IMUs), and/or the like.
The system bus 138 interconnects various components 122 to 134 enabling them to transmit and receive data and control signals to and from each other.
From the computer point of view, the computing device 102/104 may comprise a plurality of modules. Herein, a "module" is a term of explanation referring to a hardware structure such as a circuitry implemented using technologies such as electrical and/or optical technologies (and with more specific examples of semiconductors) for performing defined operations or processings. A
"module" may alternatively refer to the combination of a hardware structure and a software structure, wherein the hardware structure may be implemented using technologies such as electrical and/or optical technologies (and with more specific examples of semiconductors) in a general manner for performing defined operations or processings according to the software structure in the form of a set of instructions stored in one or more non-transitory, computer-readable storage devices or media.
As a part of a device, an apparatus, a system, and/or the like, a module may be coupled to or integrated with other parts of the device, apparatus, or system such that the combination thereof forms the device, apparatus, or system. Alternatively, the module may be implemented as a standalone device or apparatus.
FIG. 3 shows a simplified software architecture 160 of the computing device 102 or 104.
The software architecture 160 comprises an application layer 162, an operating system 166, a logical input/output (I/O) interface 168, and a logical memory 172. The application layer 162, Date Recue/Date Received 2022-08-10 operating system 166, and logical I/O interface 168 are generally implemented as computer-executable instructions or code in the form of software programs or firmware programs stored in the logical memory 172 which may be executed by the processing structure 122.
Herein, a software or firmware program is a set of computer-executable instructions or code stored in one or more non-transitory computer-readable storage devices or media such as the memory 126, and may be read and executed by the processing structure 122 and/or other suitable components of the computing device 102/104 for performing one or more processes. Those skilled in the art will appreciate that a program may be implemented as either software or firmware, depending on the design purposes and requirements. Therefore, for ease of description, the terms "software" and "firmware" may be interchangeably used hereinafter.
Herein, a process has a general meaning equivalent to that of a method, and does not necessarily correspond to the concept of computing process (which is the instance of a computer program being executed). More specifically, a process herein is a defined method implemented as software or firmware programs executable by hardware components for processing data (such as data received from users, other computing devices, other components of the computing device 102/104, and/or the like). A process may comprise or use one or more functions for processing data as designed. Herein, a function is a defined sub-process or sub-method for computing, calculating, or otherwise processing input data in a defined manner and generating or otherwise producing output data.
Alternatively, a process may be implemented as one or more hardware structures having necessary electrical and/or optical components, circuits, logic gates, integrated circuit (IC) chips, and/or the like.
Referring back to FIG. 3, the application layer 162 comprises one or more application programs 164 executed by or performed by the processing structure 122 for performing various tasks.
The operating system 166 manages various hardware components of the computing device 102 or 104 via the logical I/O interface 168, manages the logical memory 172, and manages and supports the application programs 164. The operating system 166 is also in communication with other computing devices (not shown) via the network 108 to allow the application programs 164 to communicate with programs running on other computing devices. As those skilled in the art will appreciate, the operating system 166 may be any suitable operating system such as MICROSOFT WINDOWS (MICROSOFT and WINDOWS are registered trademarks of the Microsoft Corp., Redmond, WA, USA), APPLE OS X, APPLE iOS (APPLE is a registered trademark of Apple Inc., Cupertino, CA, USA), Linux, ANDROID (ANDROID is a registered trademark of Google Inc., Mountain View, CA, USA), or the like. The computing devices 102 Date Recue/Date Received 2022-08-10 and 104 of the computer network system 100 may all have the same operating system, or may have different operating systems.
The logical I/O interface 168 comprises one or more device drivers 170 for communicating with respective input and output interfaces 130 and 132 for receiving data therefrom and sending data thereto. Received data may be sent to the application layer 162 for being processed by one or more application programs 164. Data generated by the application programs 164 may be sent to the logical I/O interface 168 for outputting to various output devices (via the output interface 132).
The logical memory 172 is a logical mapping of the physical memory 126 for facilitating the application programs 164 to access. In this embodiment, the logical memory 172 comprises a storage memory area that may be mapped to a non-volatile physical memory such as hard disks, solid-state disks, flash drives, and/or the like, generally for long-term data storage therein. The logical memory 172 also comprises a working memory area that is generally mapped to high-speed, and in some implementations, volatile physical memory such as RAM, generally for application programs 164 to temporarily store data during program execution.
For example, an application program 164 may load data from the storage memory area into the working memory area, and may store data generated during its execution into the working memory area. The application program 164 may also store some data into the storage memory area as required or in response to a user's command.
In a server computer 102, the application layer 162 generally comprises one or more server-side application programs 164 which provide(s) server functions for managing network communication with client computing devices 104 and facilitating collaboration between the server computer 102 and the client computing devices 104. Herein, the term "server" may refer to a server computer 102 from a hardware point of view, or to a logical server from a software point of view, depending on the context.
As described above, the processing structure 122 is usually of no use without meaningful firmware and/or software. Similarly, while the computer network system 100 may have the potential to perform various tasks, it cannot perform any tasks and is of no use without meaningful firmware and/or software. As will be described in more detail later, the computer network system 100 described herein, as a combination of hardware and software, generally produces tangible results tied to the physical world, wherein the tangible results such as those described herein may lead to improvements to the computer and system themselves.
In some embodiments disclosed herein, the project and program management system is configured to operate on a cloud-based computer architecture, wherein the server computers 102 are virtual computing environments comprising allocated scalable computer capacity, which may be called instances. In some embodiments, each server computer 102 may be a variable Date Recue/Date Received 2022-08-10 configuration of CPU, memory, storage, and networking capacity. In some embodiments, each server computer 102 is assigned a unique intern& protocol (IP) address within the network 108.
The processing, memory, storage, and networking capacity may be provided by a single physical server computer 102 or a more complex computer architecture comprising a plurality of interconnected service, storage, and network components. The cloud-based computer architecture may be provided by a number of cloud computer service platforms such as Amazon Web Services or AWS (Amazon Web Services and AWS are registered trademarks of Amazon Web Services, Inc., a subsidiary of Amazon of Seattle, Washington, USA), Microsoft AzureTM (Azure is a trademark of Microsoft Corporation of Redmond, Washington, USA) and Google Cloud Platform or GCP.
Referring to FIG. 4, from the functionality point of view, the project and program management system 100 in an embodiment comprises a first server computer 102a, a second server computer 120b and a data storage element 184 connected via a cloud network 108. In some embodiments disclosed herein, the first server computer 102a represents the core of the project and program management system 100, the first server computer 102a comprising a front-end module 186, a back-end module 192 and one or more databases 188. In some embodiments disclosed herein, the second server computer 102b comprises a microservice 196, which handles machine learning related tasks within the system 100. In some embodiments disclosed herein, the storage element 184 is for the storage of files uploaded to the system 100.
In some embodiments disclosed herein, the front-end module 186 comprises a web application 187, which runs on an Apache server, and its codebase is written in HyperText Markup Language (HTML), Cascading Style Sheets (CSS) and JavaScript (JS). The front-end module 186 is accessible to a user of the system 100, with the HTML and CSS portions of the codebase defining the look and feel of the front-end module 186. The JS portion of the codebase defines functionality of the front-end module 186. In some embodiments disclosed herein, the functionality of the front-end module 186 comprises communication with the back-end module 192 through an application programming interface (API), such as a REST or RESTful API 193, obtaining raw data and/or resulting processed data from the back-end module 192, providing dynamic functionality, and/or performing some simple analysis and calculations on raw data from the back-end module 192. In some embodiments, the dynamic functionality comprises allowing user to provide inputs including to configure the back-end module 192, to indicate display preferences as well as performing non-computationally complex calculations, sorts, filters and groupings on data.
In some embodiments disclosed herein, the databases comprise at least a MySQL
database 189 and a MongoDB NoSQL database program 190.

Date Recue/Date Received 2022-08-10 In some embodiments disclosed herein, the back-end module 192 comprises a REST
or RESTful API 193. In some embodiments disclosed herein, the back-end module 192 comprises an Apache Tomcat server 194 with its functionality implemented in Java. The back-end module 192 is not accessible to a user of the system 100 and acts as a core of the system 100 bridging communication between all components therein. In some embodiments disclosed herein, the functionality of the back-end module 192 comprises servicing requests originating from the front-end module 186 through the REST or RESTful API 193, performing more computing-intensive calculations than the front-end module 186 (not including machine learning calculations), retrieving information from and/or writing information to the MySQL database 189 and the MongoDB NoSQL database program 190, and making requests to the microservice 196 and uploading files to the storage element 184.
In some embodiments disclosed herein, the microservice 196 comprises a Python server 197 and is a Flask application written in Python. The microservice 196 is only accessible by the Apache Tomcat server 194 of the back-end module 192. In some embodiments disclosed herein, the functionality of the microservice 196 comprises servicing requests originating from the back-end module 192, and performing most of the computational operations required by the system 100 including all machine learning, Al and ANN processing.
Project and Program Management Functions FIG. 5A is a schematic diagram of an embodiment of an ANN 500 for calculating a critical path toward project completion. The ANN 500 comprises an input layer 502 having one or more input nodes 508, 510, 512, a hidden layer 504 comprising a plurality of intermediate nodes 514, 516, 518, 520, 522, and an output layer 506, having one or more output nodes 524.
In some embodiments disclosed herein, the input nodes 508, 510, 512 are configured for receiving task data inputs comprising a list of tasks, float data, and update data. The intermediate nodes 514, 516, 518 perform calculations wherein square matrices of numerical constants are weighted and multiplied with the inputs using matrix multiplication. The hidden layer 504 further comprises the intermediate node 520 for performing a summation function that combines the results of the matrix multiplication from intermediate nodes 514, 516, 518 and the intermediate node 522 for performing a sigmoid function used as an activation function to transform results from the intermediate node 520 into a required form for output node 524, which determines or otherwise provides a critical path of the project as the output.
In some embodiments disclosed herein, one of the project management functions is a critical path method function. FIG. 5B is a flowchart showing the steps of a critical path method function 530, according to one embodiment of the present disclosure. The function 530 begins with receiving instructions (step 532). At step 534, schedule data is retrieved from one or more Date Recue/Date Received 2022-08-10 databases for current projects in one or more industry clusters. At block 536, a critical path function using Al and the ANN 500 is used to determine the critical path of the project. At step 538, the critical path is displayed.
In some embodiments disclosed herein, one of the project management functions is a critical path trend analyzer for analyzing trends of tasks in a schedule file based on historical data within a specific industry using an ANN to determine one or more critical paths towards project completion. FIG. 6A is a flowchart showing the steps of a critical path trend analyzer function 600, according to one embodiment of the present disclosure. The function 600 begins with retrieving schedule data from one or more databases for current projects in one or more industry clusters (step 602). At step 604, task data inputs are extracted from the schedule data. In some embodiments disclosed herein, the task data inputs comprise a list of tasks, float data, and update data. At step 606, the critical path function 530 is used to determine critical paths for each update of a project. At step 608, results are displayed as a bar graph relating to number of tasks and/or number of critical paths.
In some embodiments disclosed herein, the critical path trend analyzer function 600 comprises the ANN 500 described above, wherein step 602 corresponds to the functionality provided by the input layer 502, steps 604 and 606 correspond to the functionality provided by the hidden layer 504, and step 608 generally corresponds to the functionality provided by the output layer 506. In some embodiments disclosed herein, results are displayed for each update on the output layer 506, for example as a bar graph relating the number of tasks and/or the number of critical path tasks.
Referring to FIGs. 6B to 6D, a schematic illustrating an example 640 of the critical path trend analyzer function 600 is shown comprising blocks 500 and 641 to 684, wherein blocks 641 to 654 illustrate retrieving task data inputs, blocks 656 to 661 illustrate performing calculations on task data inputs based on a critical path length, and blocks 659 to 661 illustrate performing calculations for tasks based on float and update data, which is input into the ANN 500. Block 662 illustrate matrix multiplication of constants, wherein variables lw, Lw, Bl, and B2 are weights biases for the ANN 500.
In some embodiments disclosed herein, one of the project management functions is an accelerator and de-risking function for identifying and providing a list of projects that could be risky and/or critical as well as those that were completed in less time than average. For each project, details for a list of tasks may be provided to assist in making projects more efficient. FIG. 7A is a flowchart showing the steps of an accelerator and de-risking function 700, according to one embodiment of the present disclosure. The function 700 begins with retrieving schedule data from a schedule file within a database (step 702). At step 704, project and task data are extracted from Date Recue/Date Received 2022-08-10 the schedule data. At step 706, task that are completed in less time than average are identified and complied into a data structure for sorting. In some embodiments disclosed herein, the task data comprises duration, start date and finish date. At step 708, the data structure comprised of the extracted task data is sorted. At step 710, the sorted data is displayed.
In some embodiments disclosed herein, task data is initially placed in a hashmap for tasks where a duration is provided. Each hashmap entry comprises a start date, a finish date and a duration. The hashmap is then converted into a linked list and is sorted by it values in ascending or descending order according to preferences. The sorted linked list is then converted back into a hashmap. Although hashmaps and linked lists have been described above, a person of skill would understand that any other data structure such as arrays could be used. In some embodiments disclosed herein, the details of the sorted hashmap are displayed, for example, in a Gantt chart with duration on x-axis and a total float on the y-axis.
Referring to FIGs. 7B to 7C, a schematic illustrating an example 740 of the accelerator and de-risking function 700 is shown comprising blocks 741 to 762.
In some embodiments disclosed herein, one of the project management functions is a risk events analysis function, which provides listings of events that may impact scheduling and cost of a project. FIG. 8A is a flowchart showing the steps of a risk events analysis function 800, according to one embodiment of the present disclosure. The function 800 begins with retrieving news items from publically available news feeds through news API (step 802).
At step 804, NLP
technologies are used to identify relevant news items by analysing news headlines and descriptions that could impact a project based on calculations and mathematical expressions of a project and items within schedule and cost files. Duplicative items may be removed. At step 806, a sentiment analysis tool scores each news item as either positive or negative. Positive news items are characterized as opportunities and negative news items are characterized as risks. At step 808, a summary of relevant news items is displayed and users are provided with access to source news articles for further explanation on any potential risk events.
In some embodiments disclosed herein, the risk events analysis function comprises a risk logs sub-function, which further evaluates negative news items characterized as risks to evaluate potential risks to the project based on historical data. FIG. 8B is a flowchart showing the steps of a risk logs sub-function 814, according to one embodiment of the present disclosure. The sub-function 814 begins with compiling a list of negative news items or risks (step 815). At step 816, schedule and cost data for a current project are retrieved. At step 817, variances between the schedule and cost data of the current project and budgeted schedule and cost data are identified.
At step 818, reasons for variances are retrieved, if applicable. At step 819, probability of occurrence of risks is calculated using quantitative analysis, wherein the probability is presented Date Recue/Date Received 2022-08-10 as a numeric value representing likelihood or risk. At step 820, mitigation plans from historical projects are retrieved. At step 821, a recommendation engine creates a knowledge database to recommend possible measures within mitigation plans to avoid risks. At step 822, recommendations are displayed to the user. In embodiment disclosed herein, a time series graph of negative news events in relation to commodity prices over time (for example, years) is displayed. In some embodiments disclosed herein, information used by the risk logs sub-function can be updated by the user for use in future predictions.
FIG. 8C is a schematic diagram of an embodiment of a recommendation engine 826 for recommending possible measures within mitigation plans to avoid risks. The engine 826 is an ANN and comprises an input layer 827 having one or more input nodes 830, 831, 832, a hidden layer 828 comprising a plurality of intermediate nodes 833, 834, 835, 836, 837, 838 and an output layer 829, having one or more output nodes 839. In some embodiments disclosed herein, the input nodes 830, 831, 832 are configured for receiving output from the risk logs sub-function 814 and risk triggers from past historical project data such as missing activities, technical changes, reassignment of critical resource, changes in business direction, delayed decision making, weather, reprioritization of work, budget reductions, changes in project scope, stakeholder changes, and/or the like from historical projects. The intermediate nodes 833, 834, 835, 836 perform calculations with configured biases. The hidden layer 828 further comprises the intermediate nodes 837, 838 to perform an activation function and for performing a summation function that combines the results of the intermediate nodes 833, 834, 835, 836. In some embodiments disclosed herein, the risk events analysis function 800 comprises the method 826 described above.
Referring to FIGs.
8C to 8G, a schematic illustrating an example 840 of a risk events analysis function 800 is shown comprising blocks 826 to 884.
In some embodiments disclosed herein, one of the project management functions is a schedule risk function for identifying tasks within a given schedule file that are considered risky based upon historical data in industry clusters and past trends based upon the features of the various schedule items given. FIG. 9 is a flowchart showing the steps of a schedule risk function 900, according to one embodiment of the present disclosure. The function 900 begins with retrieving schedule data from one or more databases for current projects in one or more industry clusters (step 902). At step 904, a listing of tasks is extracted from the schedule data. At step 906, NLP is used to identify those tasks that may be considered risky to a project's schedule based on calculations and mathematical expressions. At step 908, a summary of relevant tasks identified by the function 900 is displayed to the user.
In some embodiments disclosed herein, one of the project management functions is a completion probability function for analyzing the probability of completion for a schedule file. In Date Recue/Date Received 2022-08-10 some embodiments disclosed herein, the completion probability function uses NLP and an ANN
method to calculate the probability of the completion for a schedule file based on the historical schedule data and detecting the patterns in the historical schedules in specific industries. FIG. 10A
is a flowchart showing the steps of a completion probability function 1000, according to one embodiment of the present disclosure. The function 1000 begins with retrieving schedule data from a schedule file (step 1002). At step 1004, project and task data is extracted from the schedule data, which may include attributes of a project within a specific industry including a project identifier (ProjectID), updates relating to the project, a lists of tasks, required resources including space, workfront availabilities and/or other events that may affect the completion of the project.
At step 1006, the function 1000 identifies unfinished tasks by checking a task's actual start and finish dates. At step 1008, historical schedule data is retrieved. NLP is used to identify similar tasks within the historical schedule data. At step 1012, project and schedule data for all similar tasks are input into an ANN to calculate a completion probability. In some embodiments disclosed herein, the ANN calculates an accuracy score. At step 1014, the completion probability is displayed.
In some embodiments disclosed herein, the completion probability is a function of time between the start and end dates wherein an estimated completion time is based on similar tasks in the historical schedule data. In some embodiments disclosed herein, the accuracy score comprises calculations directed towards the similarity of tasks and calculations directed towards the accuracy of the completion probability.
FIG. 10B is a schematic diagram of an embodiment of an ANN 1016 for calculating a completion probability. The ANN 1016 comprises an input layer 1018 having one or more input nodes 1021, 1022, 1023, a hidden layer 1019 comprising a plurality of intermediate nodes 1024, 1025, 1026, 1027, 1028, 1029, 1030, 1031, 1032 and an output layer 1020, having one or more output nodes 1033 for calculating completion probability. In some embodiments disclosed herein, the input nodes 1021, 1022, 1023 are configured for receiving task data inputs comprising a list of tasks, float data, update data, start date, finish date, and workfront availability. The hidden layer comprises a first layer of the intermediate nodes 1024, 1025, 1026, 1027 and a second layer of intermediate notes 1028, 1029, 1030, 1031, which perform calculations on variables in the intermediate nodes 1024, 1025, 1026, 1027, 1028, 1029, 1030, 1031 using numerical constants to produce numerical values, including the duration assigned by the project for all tasks to be completed and actual duration of all tasks of the project. The numerical values are provided to the intermediate node 1032 for performing a sigmoid function used as an activation function to transform results from the intermediate nodes 1024, 1025, 1026, 1027, 1028, 1029, 1030, 1031 into a required form for intermediate node 1032, which generates the completion probability in Date Recue/Date Received 2022-08-10 percentage format (calculated from duration and actual duration) for the one or more output nodes 1033 to output.
In some embodiments disclosed herein, the completion probability function 1000 comprises the ANN 1016 described above and referred to in step 1010. Referring to FIGs. 10C to 10G, a schematic illustrating an example 1040 of the completion probability function 1000 is shown comprising blocks 1042 to 1096, wherein blocks 1041 to 1054 correspond to retrieving project and schedule data, blocks 1063 to 1071 illustrate using NLP to identify similar tasks, and blocks 1016 and 1077 illustrate the ANN.
In some embodiments disclosed herein, one of the project management functions is a total float trend analyzer function for analyzing trends of tasks in a schedule file for a current project based on historical data within a specific industry cluster using an ANN. FIG.
11A is a flowchart showing the steps of a total float trend analyzer function 1100, according to one embodiment of the present disclosure. The function 1100 begins with retrieving schedule data from a schedule file (step 1102). At step 1104, task data inputs are extracted from the schedule data. In some embodiments disclosed herein, the task data inputs comprise a list of tasks, float data, and update data. At step 1106, total floats for the project are calculated for each update using ANN. At step 1108, results are displayed, for example, as a bar graph.
FIG. 11B is a schematic diagram of an embodiment of an ANN 1114 for calculating a total float trend. The ANN 1114 comprises an input layer 1116 having one or more input nodes 1120, 1122, 1124, a hidden layer 1118 comprising a plurality of intermediate nodes 1126, 1128, 1130, 1132, 1134, and an output layer 1120, having one or more output nodes 1136.
In some embodiments disclosed herein, the input nodes 1120, 1122, 1124 are configured for receiving task data inputs comprising a list of tasks, float data, and update data. The intermediate nodes 1126, 1128, 1130 perform calculations wherein square matrices of numerical constants are weighted and multiplied with the inputs using matrix multiplication. The hidden layer 1118 further comprises the intermediate node 1132 for performing a summation function that combines the results of the matrix multiplication from intermediate nodes 1126, 1128, 1130 and the intermediate node 1134 for performing a sigmoid function used as an activation function to transform results from the intermediate node 1132 into a required form for output node 1136, which provides the total float for the projects.
In some embodiments disclosed herein, the total float trend analyzer function comprises the ANN 1114 described above, wherein step 1102 corresponds to the functionality provided by the input layer 1106, steps 1104 to 1108 correspond to the functionality provided by the hidden layer 1118, and step 1110 generally corresponds to the functionality provided by the Date Recue/Date Received 2022-08-10 output layer 1120. In some embodiments disclosed herein, results are displayed for each update on the output layer 506, for example as a bar graph.
Referring to FIGs. 11C to 11E, a schematic illustrating an example 1140 of a total float trend analyzer function 1100 is shown comprising blocks 1114 and 1141 to 1184, wherein blocks 1141 to 1161 illustrate retrieving task data inputs, and block 1162 illustrate matrix multiplication of constants, wherein variables lw, Lw, B1 and B2 are weights biases for the ANN 1114.
In some embodiments disclosed herein, one of the project management functions is a bow wave trend analyzer function to display a bow wave trend for a current project based on the historic data under a specific industry cluster for illustrating how delays to tasks affect the scheduling of subsequent tasks. FIG. 12A is a flowchart showing the steps of a bow wave trend analyzer function 1200, according to one embodiment of the present disclosure. The function 1200 begins with retrieving schedule data from a particular schedule file (step 1202). At step 1204, task data is extracted from the schedule file for a number of tasks including their duration, start date and end date. At step 1206, a bow wave is produced of the tasks and their durations for indicating how delays to tasks affect the scheduling of subsequent tasks. At step 1208, results are displayed, for example as a line graph of time against the number of tasks. Referring to FIGs. 12B to 12C, a schematic illustrating an example 1240 of a bow wave trend analyzer function 1200 is shown comprising blocks 1241 to 1260.
In some embodiments disclosed herein, one of the project management functions is a garbage in garbage out (GIGO) function relating to scheduling to detect logical and duration errors within a schedule file. The schedule GIGO function uses a combination of mathematical calculations and Al methods along with NLP technologies and historical data of specific industries in libraries to detect flaws or errors in a schedule file for a project within a specific industry cluster.
In some embodiments disclosed herein, the scheduling GIGO function comprises a logic flaw method (also called a logic error method) and a duration flaw method (also called a duration error method).
In some embodiments disclosed herein, a logic error method analyzes a schedule file to detect activities that are not in a sequence of a predefined series of activities from a library. The library comprises a series of activities to be completed in a specific order.
For example, a library defining a series of activities for the development of a software application comprises brainstorming ideas, planning, designing, resource implementation, testing, deployment, and maintenance. When a sequence of activities deviates from a defined order, it may impact the overall results of a project. To identify errors that may be responsible for such a breakdown, the logic error method may use an Al model trained with historical schedule files within one or more specific industries. FIG. 13A is a flowchart showing the steps of a logic error method 1302 of a Date Recue/Date Received 2022-08-10 schedule GIGO function 1300, according to one embodiment of the present disclosure. The method 1302 begins with retrieving schedule data from a schedule file (step 1304). At step 1306, a list of tasks is extracted from the schedule file. At step 1308, historical schedule data is retrieved.
At step 1310, NLP is used to determine the similarity of determine task similarity to map activities within a current schedule file to similar activities within the library. At step 1312, the method 1302 determines if a logic error is detected using the Al model and at step 1314, a user can be alerted with an indicator along with a listing of an order of activities the logic error method has determined to be correct. At step 1316, optionally, a user can decide to accept the existing schedule identified by the logic error method 1302 and the new sequence of activities may be added to the library such that the logic error method 1302 is trained to use the new sequence for future predictions.
In some embodiments disclosed herein, a duration error method compares an actual duration of a specific activity with an average duration range for the activity determined based on learning from historical data. FIG. 13B is a flowchart showing the steps of a duration error method 1320 of a schedule GIGO function 1300, according to one embodiment of the present disclosure.
The method 1320 begins with retrieving schedule data from a schedule file (step 1322). At step 1324, schedule data is extracted from the schedule file. In some embodiments disclosed herein, the schedule data comprises task data, task duration, and updates. At step 1326, the actual duration is compared to a predefined duration range such as an average duration range.
At step 1328, if the actual duration for a task is outside the average duration range, the duration error method 1320 flags an error for the task. Where the actual duration of the task is greater than the average duration range, a resource optimization function, as described in more detail below, may recommend a list of available resources to assist in completing the specific activity and the duration error method 1320 may calculate an overall delay on the project. If the actual duration of a task is less than the average duration range, a user can be notified, and one or more resources required for the specific task can be identified as efficient and available. In some embodiments disclosed herein, where the actual duration of the specific task is less than the average duration range, potential outcomes comprising a list of tasks with associated durations are also compared to historical information to ensure quality is maintained. Optionally, a user can decide to update an average duration range for a task.
In some embodiments, the duration error method may use Al for determining the predefined duration range which is a typical duration range determined by the Al based on the historical project data and quantities/scope with rates of placement.
Referring to FIGs. 13C to 13D, a schematic illustrating an example 1340 of a schedule GIGO function 1300 is shown comprising blocks 1341 to 1388, wherein blocks 1342 to 1355 Date Recue/Date Received 2022-08-10 illustrate obtaining schedule data, blocks 1356 and 1360 to 1372 illustrate elements of the logic error method, and blocks 1357 and 1374 to 1388 illustrate elements of the duration error method.
In some embodiments disclosed herein, one of the project management functions is a potential claims function to identify and provide a list of tasks that can cause potential claims or extensions of time from interfacing tasks or parties. In some embodiments disclosed herein, the potential claims function uses NLP to determine similar previous task histories. FIG. 14A is a flowchart showing the steps of a potential claims function 1400, according to one embodiment of the present disclosure. The method 1400 begins with retrieving schedule data from a schedule file (step 1402). At step 1404, a source task and a target task are extracted from a predecessor task. At step 1406, the function 1400 checks for updates and confirms that the source task and the predecessor task belong to a common work breakdown structure (WBS). At step 1408, the function 1400 calculates based on one or more types of relations to determine whether a time difference between the source task and the target task is less than a threshold delay time such that a potential claim may result. At step 1410, if a potential claim may result, the task is added to a list of potential claims. In some embodiments disclosed herein, task details are updated with task name being source task name, task unique ID being source unique ID, x-axis being a list of update and y-axis being unique source ID, and for each identified potential claim, the entry to the list comprises the following attributes: relationship type, source task, task unique ID, relation unique ID and time difference. At step 1412, the list is displayed. Referring to FIGs. 14B to 14D, a schematic illustrating an example 1440 of a potential claims function 1400 is shown comprising blocks 1441 to 1470.
In some embodiments disclosed herein, one of the project management functions is a site monitoring function directed towards enhancing safety of equipment and people.
FIG. 15A is a flowchart showing the steps of a site monitoring function 1500, according to one embodiment of the present disclosure. The site monitoring function 1500 may help avoid and prevent compliance issues and safety incidents. The function 1500 comprises Al is used to analyze video monitoring data from a work site, such as a construction site, to identify instances of workers committing safety violations, such as the removal of protective equipment, allowing issues to be addressed prior to the potential occurrence of penalties or injuries. In some embodiments disclosed herein, the function 1500 comprises Al to analyze thermal imaging to identify instances of equipment near failure, which can prevent expensive repairs or schedule delays and/or to identify employees who are about to collapse or are unhealthy.
The function 1500 begins with receiving video monitoring data (step 1502). In some embodiments disclosed herein, the video monitoring data is provided by closed-circuit television (CCTV), drones, infrared cameras, and/or the like to capture workers and various equipment. In Date Recue/Date Received 2022-08-10 some embodiments disclosed herein, the site monitoring function uses a python opencv library for implementation. At step 1504, optionally, the function 1500 retrieves scheduling information, such as worker information including periods of work, assigned tasks and equipment used, for enhancing the efficiency of the site monitoring function 1500, including in real time, by identifying critical periods of time and locations of interest. In some embodiments disclosed herein, the function 1500 is also connected to multiple cameras that are dynamically controllable and operable with interconnected devices. At step 1506, Al is used to detect objects, such as workers and equipment, in the video monitoring data. At step 1508, the function 1500 creates one or more bounding boxes around potential objects of interest. At step 1510, the function 1500 uses Al to analyze the one or more areas defined by bounding boxes for compliance and/or safety issues, such as whether a worker is wearing safety equipment or if a worker is near collapse. At step 1512, optionally, the function 1500 analyzes the video monitoring data from thermal or infrared cameras with sensors used to interpret the colours and intensities therein to identify equipment near failure.
At step 1514, results are displayed to a user. In some embodiments disclosed herein, the results may be displayed in a report with bounding boxes coloured green indicating no potential concerns and/or red indicating potential concerns may be used along with appropriate labels to help the site monitoring function and/or user.
Referring to FIGs. 15B to 15E, a schematic illustrating an example 1540 of a site monitoring function 1500 is shown comprising blocks 1541 to 1589. As shown in FIG. 15B, the site monitoring function 1500 uses one or more imaging cameras such as closed-circuit television (CCTV), drones with cameras, thermal imaging cameras, and/or the like to capture pictures and/or live video streams of a site. The intensity of color of captured pictures and/or video streams may be analyzed for monitoring equipment operations. The video streams are also processed by drawing reference lines in each frame thereof for indicating a region of interest (R01). Workers are also detected in the video streams. The identified workers are marked with bounding boxes.
The site monitoring function 1500 then determines ROI trespassing by detecting if a bounding box passes a reference line. Then, the site monitoring function 1500 monitors the worker entering the ROI as shown in FIG. 15C. In some embodiments, the site monitoring function 1500 also uses the schedule data to command the one or more imaging cameras to move as scheduled and/or as needed.
As shown in FIG. 15C, the site monitoring function 1500 identifies the gestures, facial expression and motion of the worker entering the ROI from the captured video streams, and labels the captured video streams and/or images with a first type of classes including worker in critical region and worker in healthy or safe region based on, for example, the position of the worker (step Date Recue/Date Received 2022-08-10 1554). In this example, the site monitoring function 1500 uses the resources details from the schedule to determine the critical region.
The site monitoring function 1500 also receives from input data the information of relevant safety equipment such as safety helmet, jacket, and/or the like. By using the information of relevant safety equipment, the site monitoring function 1500 labels the captured video streams and/or images with a second type of classes such as worker wearing safety equipment and worker not wearing safety equipment (step 1555). The labeled video streams and/or images (at steps 1554 and 1555) are used for generating a file such as a xml file defining the bounding box (that is, the worker) and the labels. The generated file is then used to create a csv file.
Moreover, in order to create machine-learning model, the data (that is, the labeled video streams and/or images) is split training data for training the machine-learning model and test data for testing the trained machine-learning model in the ratio of 80 and 20.
As those skilled in the art will appreciate, the above-described site monitoring requires extensive image processing. In some embodiments as shown in FIG. 15D, the site monitoring function 1500 uses a residual neural network (ResNet) for processing the captured video streams to obtain a feature map. The site monitoring function 1500 then extracts features of the image from the feature map and uses ROI coordinates to obtain a fixed-size feature map and align it with the ROI. A fully connected (FC) layer of the ResNet processes the aligned fixed-size feature map which is used for refining or predicting localization boxes using, for example, bounding box regression, for determining the classes using, for example, a softmax method, and for determining a mask.
FIG. 15E shows the details of steps 1554 and 1555. As shown, the color intensity in the captured video streams on a machine is checked. Based on the color intensity, the site monitoring function 1500 further uses relevant sensors to detect the dimension such as the length of the machine to determine the scaling of the machine for estimating the correct measurement of the machine in the camera. The site monitoring function 1500 also uses relevant sensor outputs to calculate the stress on the machine for detecting load and stress on the machine and predicting (for example, using an Al model) if the machine has any fault or breakdown.
Based on the classes, the site monitoring function 1500 annotates the captured video stream by adding a bounding box in a first color (such as green) to worker wearing safety equipment and adding a bounding box in a second color (such as red) to worker not wearing safety equipment.
Similarly, the site monitoring function 1500 annotates the captured video stream by adding a bounding box in a first color (such as green) to worker in healthy position and adding a bounding box in a second color (such as red) to worker in critical position.

Date Recue/Date Received 2022-08-10 In some embodiments disclosed herein, one of the project management functions is a contract analyzer function for identifying clauses with risky words in a contract document using Al and NLP. FIG. 16A is a flowchart showing the steps of a contract analyzer function 1600, according to one embodiment of the present disclosure. The function 1600 begins with retrieving a contract file (step 1602). In some embodiments disclosed herein, the contract files extracted by the function 1600 are in .pdf or .docx format. At step 1604, clauses are extracted from the contract file. At step 1606, NLP analyzes one or more clauses to identify clauses within a contract file containing flagged words or language for further processing, and at step 1608, Al comprises sentiment analysis, which is used to determine if the identified clauses containing flagged words or language are likely to be positive or negative to a user. At step 1610, optionally, the function 1600 retrieves and analyzes a schedule file associated with the contract file to estimate liquidated damages in terms of dollar values where one or more schedule items are not currently being met.
At step 1612, a listing of all flagged clauses including results of an analysis by the function 1600 in are provided in tabular format.
Referring to FIGs. 16B to 16F, a schematic illustrating an example 1640 of a contract analyzer function 1600 is shown comprising blocks 1641 to 1694. The contract analyzer function 1600 parses a contract file in PDF or Microsoft WORD DOCX format (FIG. 16B) (WORD is a trademark of Microsoft Corporation of Redmond, Washington, USA). As shown in FIG. 16C, for the contract file in PDF format, the contract analyzer function 1600 extracts text of the contract file (ignoring the special symbols) and creates list of sentences from the extracted text. The list of sentences are then put into a content list. For the contract in DOCX format, the contract analyzer function 1600 extracts text of the contract file, parses paragraphs to objects, and creates list of sentences from the parsed objects. The list of sentences are then put into the content list.
As shown in FIG. 16D, the content list is then processed using a trained Al model wherein the text in the content list is preprocessed by removing punctuations, symbols, white spaces, and like, and converting characters of the text to lowercase. The processes text is tokenized using a text tokenizer for creating tokens which are converted into numbers such as integers for being processed using the trained Al model. FIG. 16E shows the detail of the Al model, which may be used to, for example, predict negative words in the sentences in the contract file along with semantic. FIG. 16F shows the detail of the processing of the content list. In this example, some characters such as tabs, white spaces, commas, and brackets are removed from each sentence, and then sentiment analysis is used to find faulty or risky words in each sentence along with sematic.
If any of such words are found, the sentence is added to contract analyzer risk dictionary.
In some embodiments disclosed herein, one of the project management functions is a report analyzer function for analyzing terms in one or more reports to identify those which pay Date Recue/Date Received 2022-08-10 present risk. Using Al and NLP. FIG. 17 is a flowchart showing the steps of a report analyzer function 1700, according to one embodiment of the present disclosure. The function 1700 begins with retrieving a report file (step 1702). In some embodiments disclosed herein, the report files extracted by the function 1700 are in PDF or DOCX format. At step 1704, terms are extracted from the report file. At step 1706, NLP analyzes one or more terms to identify terms within a report file containing flagged words or language for further processing, and at step 1708, Al comprises sentiment analysis, which is used to determine if the identified terms containing flagged words or languages are likely to be positive or negative to a user. At step 1710, a listing of all flagged terms including results of an analysis by the function 1700 in are provided in tabular format.
In some embodiments disclosed herein, one of the project management functions is a cost trend analyzer function for analyzing trends of tasks of a project and offers cost estimates based on historical data within a specific industry cluster using an ANN. FIG. 18A
is a flowchart showing the steps of a cost trend analyzer function 1800, according to one embodiment of the present disclosure. The function 1800 begins with retrieving a cost file (step 1802). At step 1804, data is extracted from the cost file, which may include a list of tasks, cost data, and update data.
At step 1806, historical cost data is retrieved. In some embodiments disclosed herein, the function 1800 checks a task's actual start and finish dates to identify tasks that are not completed. At step 1808, NLP is used to identify similar tasks within the historical cost data.
At step 1810, project and cost data for all similar tasks are input into an ANN to calculate cost trends. At step 1812, calculated cost trends are displayed.
FIG. 18B is a schematic diagram of an embodiment of an ANN 1814 for calculating a cost trend. The ANN 1814 comprises an input layer 1816 having one or more input nodes 1820, 1822, 1824, a hidden layer 1818 comprising a plurality of intermediate nodes 1826, 1828, 1830, 1832, 1834, and an output layer 1820, having one or more output nodes 1836.
In some embodiments disclosed herein, the input nodes 1820, 1822, 1824 are configured for receiving task data inputs comprising a list of tasks, float data, update data, currency, and cost file having cost data. The intermediate nodes 1826, 1828, 1830 perform calculations wherein square matrices of numerical constants are weighted and multiplied with the inputs using matrix multiplication. The hidden layer 1818 further comprises the intermediate node 1832 for performing a summation function that combines the results of the matrix multiplication from intermediate nodes 1826, 1828, 1830 and the intermediate node 1834 for performing a sigmoid function used as an activation function to transform results from the intermediate node 1832 into a required form for output node 1836.

Date Recue/Date Received 2022-08-10 In some embodiments disclosed herein, the cost-trend trend analyzer function comprises the ANN 1814 described above. In some embodiments disclosed herein, results are displayed for each update on the output layer 1820.
In some embodiments disclosed herein, one of the project management functions is a cost risk function for identifying tasks within a given cost file that at risk of running over pre-determined thresholds. FIG. 19 is a flowchart showing the steps of a cost risk function 1900, according to one embodiment of the present disclosure. The function 1900 begins with retrieving a cost file (step 1902). At step 1904, data is extracted from the cost file, which may include a list of tasks, cost data, and update data. At step 1906, an Al model is used to determine which tasks are at risk of running over pre-determined cost thresholds. At step 1908, results are displayed to a user of all tasks that are at risk of running over pre-determined thresholds.
In some embodiments disclosed herein, one of the project management functions is a cost savings function for identifying and providing a list of recommendations for cost savings based on an AI-based recommendation engine providing, based on past trends and patterns, cost savings strategies for a given cost file. FIG. 20 is a flowchart showing the steps of a cost risk function 2000, according to one embodiment of the present disclosure. The function 2000 begins with retrieving a cost file (step 2002). At step 2004, data is extracted from the cost file, which may include a list of tasks, cost data, and update data. At step 2006, an AI-based recommendation engine uses collaborative filtering for recommendation to identify and provide a list of recommendations for cost savings. At step 2008, the function 2000 displays a summary of potential cost savings to a user.
Many industries contains processes or activities that affect the environment by releasing green house gases (GHG) such as CO2, NON, SON, CH4, etc. GHGs result in increasing the temperature of the atmosphere and warming the planet's surface to a temperature above what it would otherwise be. In some embodiments disclosed herein, one of the project management functions is a GHG calculation function, which uses a combination of mathematical calculations, Al methods including deep learning, and historical GHG data to calculate and compare GHG
equivalencies or carbon footprints for projects, as well as provide recommendations for capital projects and operational assets, including those relating to an asset lifecycle. The recommendations relate to measurements of a project carbon emissions over an asset's lifecycle and also applies to operational facilities.
FIG. 21 is a flowchart showing the steps of a GHG calculation function 2100, according to one embodiment of the present disclosure. The function 2100 begins with retrieving a GHG file of a project (step 2102). At step 2104, GHG data is extracted from the GHG
file, which may include carbon emissions, carbon taxes, phases, disciplines, emission factor categories, types of Date Recue/Date Received 2022-08-10 assets, relevant industries, and resources involved. Carbon emission can be calculated with respect to emission factors, standard unit conversion factors, equipment related factors, and conversion factors. At step 2106, a support vector classifier method is used to calculate a carbon footprint or emission for a project and provide a percentage score relating to the environmental friendliness of the project or operational assets based on the GHG data. In some embodiments disclosed herein, the higher the percentage, the more green or environmentally friendly a project is or operation assets are. At step 2108, optionally, the function 2100 uses a term frequency inverse document frequency (TF-IDF) method for recommending alternative energy sources and other approaches to reduce carbon footprint or emissions. TF-IDF is used in NLP to quantify words in a document to help identify important words. The TF-IDF method can also be used over a project life cycle to achieve carbon balance to reach net zero carbon at future time/year and provide carbon savings.
The TF-IDF method can also be used to predict expected carbon taxes and suggest strategies to reduce carbon emission which will help clients reduce carbon taxes to save money. Using geographic information systems, the TF-IDF method can help locate areas with fertile land for tree planting.
At step 2110, optionally, the function 2100 uses a heatmap function for displaying to a user how various regions or assets are responsible for different levels of emissions, including regions of maximum emissions. At step 2112, results are displayed to a user including the percentage score and an interpretation thereof. In some embodiments disclosed herein, the function 2100 comprises a simulation feature 2114, which allows a user to check how changing attributes of a project affects emissions.
FIG. 21B is a schematic diagram of an embodiment of a support vector classifier method 2116 for calculating a carbon footprint and a percentage score. The method 2116 comprises an input layer 2118 having one or more input nodes 2121, 2122, 2123, a hidden layer 2119 comprising a plurality of intermediate nodes 2124, 2125, 2126, 2127, 2128, and an output layer 2120 having one or more output nodes 2129, which provides as the output a carbon footprint value, a classification of whether a project is green or not, and cost savings recommendations including taxation costs. In some embodiments disclosed herein, the input nodes 2121, 2122, 2123 are configured for receiving task data inputs comprising GHG data, including total carbon emissions, total carbon tax, phases, and/or the like. The intermediate nodes 2124, 2125, 2126, 2127 perform calculations with configured biases. The hidden layer 2119 further comprises the intermediate node 2128 for performing a summation function that combines the results of the intermediate nodes 2124, 2125, 2126, 2127. In some embodiments disclosed herein, the GHG
calculation function 2100 comprises the method 2116 described above. Referring to FIGs. 21C to Date Recue/Date Received 2022-08-10 21H, a schematic illustrating an example 2140 of a GHG calculation function 2100 is shown comprising blocks 2140 to 2189.
In some embodiments disclosed herein, one of the project management functions is a resource optimization function to assist with more efficient allocation of resources. In an embodiment, resource management is for managing the supply and demand of resources, which may comprise tools, machinery and human resources, including for reducing unnecessary overtime and the like. In some embodiment, machine learning algorithms are used to provide estimates of duration, resource requirements and budget requirements for work streams. In some embodiments disclosed herein, the resources optimization function helps optimize resources, including personnel, tools, machinery, equipment, materials, consumables, and/or the like that are necessary to complete tasks. FIG. 22A is a flowchart showing the steps of a resource optimization function 2200, according to one embodiment of the present disclosure. The function 2200 begins with retrieving schedule data (step 2202). At step 2204, the task and other data is extracted from the schedule data, which may include data relating to industries, projects and schedules. In some .. embodiments disclosed herein, the data comprises years of experience, qualifications, tasks completed, skill sets, duration to complete tasks, number of tasks completed, rate of placement, productivity factors, working conditions, calendar inputs, project details, industry details, and schedule details. At step 2206, resource data is retrieved. At step 2208, historical task data is retrieved. At step 2210, NLP is used to identify similar tasks for comparison.
At step 2212, an AI-based, k-nearest neighbor (KNN) method is used to recommend resources based on features and to allocate resources for implementing or executing tasks. In some embodiments disclosed herein, the KNN method creates classes for different kinds of resources based on their features. The features comprise: experience, skills, availability, working conditions, rates of placement, and productivity factors. The KNN method recommends resources based on these features and then allocates resources for implementing or executing activities or tasks. More specifically, the KNN
method may make recommendations relating to staffing levels, employee schedules, prioritization of tasks, and project duration estimates. At step 2214, results are displayed to a user, for example information relating to resources, recommendations, and allocations are displayed using a progress tracker or a visualizer board.
Optionally, at step 2216, a user is presented with a list of immediately actionable tasks.
Items containing these tasks from the progress tracker can be identified with subsequent tasks. A
report is presented to the user identifying the immediately actionable tasks and subsequent tasks.
The user may allocate resources from a list to tasks and initiate notifications. A user would be able to specify available resources/personnel, including their tickets, qualifications, and competencies, through an interface. This is linked with cost overruns.

Date Recue/Date Received 2022-08-10 Optionally, at step 2218, losses relating to coordination, meaning tasks waiting for resources or waiting for personnel, are displayed to users. In some embodiments disclosed herein, user simulations relating to schedules/durations and estimated finish dates taking into consideration coordination losses and work front availability are displayed.
For example, if a particular task is taking 10 days instead of baseline or planned 5 days, this information can be used in a simulation to estimate impact on a project using nodes. The system may also use past historical records. The resource optimization function 2200 uses past performance to simulate the probabilities. The simulation of step 2214 may also be used in conjunction with resource allocation in step 2212 to provide a solution for resource optimization using lean just in time (JIT), materials availability, and prediction of idle time based on resource availabilities.
Optionally, at step 2220, the resource optimization function 2200 can be used to identify what tasks are critical, providing a priority list, using historical of performance of particular resources, taking into account lean JIT methodology, rate of production with historical rates of placement, skill levels, experience levels, push and pull planning, and completion probabilities.
The function 2200 provides multitasking functionality, reduces duration of projects, and provides users with important information about resources, including resources allocation and their predicted availabilities. The KNN method is used provide information to display about and making recommendations to improve efficiency of resources, experiences, workfront availability, resource availability, and skilled worker availability. Referring to FIGs. 22B
to 22F, a schematic .. illustrating an example 2240 of a resource optimization function 2200 is shown comprising blocks 2241 to 2298.
In some embodiments disclosed herein, one of the project management functions is a cost GIGO function relating to cost information to detect errors within a cost file. More specifically, the cost GIGO function identifies cost entries that stand out having unexpected values when .. compared to similar tasks within the project management systems database.
FIG. 23A is a flowchart showing the steps of a cost GIGO function 2300, according to one embodiment of the present disclosure. The function 2300 begins with retrieving a cost file relating to a particular project within a specific industry cluster (step 2302). At step 2304, cost data is extracted from the cost file. At step 2306, historical cost data is retrieved.
At step 2308, NLP is used to identify similar tasks, at step 2310, the function 2300 compares the cost file against historical cost data contained within the identified similar tasks to identify potential errors in the cost file and produce a similarity score. In some embodiments disclosed herein, the cost file is downloaded from an AWS bucket, spreadsheet files are selected and its contents are compared using NLP to create a glossary of budget and work breakdown structure terms.
In some embodiments disclosed herein, the function 2300 may retrieve the current US
dollar exchange rate Date Recue/Date Received 2022-08-10 and note its current value relative to the historical data. At step 2312, results are displayed, for example a list of potential cost errors. Referring to FIGs. 23B to 23E, a schematic illustrating an example 2340 of the GIGO cost function 2300 is shown comprising blocks 2341 to 2382.
In some embodiments disclosed herein, one of the project management functions is an early warning schedule function for providing an early warning based on an analysis of attributes related to tasks within a schedule file, including if the estimated finish date is greater than the planned finish date by at least a threshold value. In some embodiments disclosed herein, analysis in the early warning schedule function comprises methods combined with mathematical formulas.
FIG. 24A is a flowchart showing the steps of an early warning schedule function 2400, according to one embodiment of the present disclosure. The function 2400 begins with retrieving a schedule file within a specific industry cluster (step 2402). At step 2404, schedule data is extracted from the schedule file which may include task names, start dates, finish dates, durations, update data, reasons, and records. At step 2406, historical schedule data is retrieved. At step 2408, NLP is used to identify similar tasks from other projects and extract data therefrom. At step 2410, the schedule data is compared against the historical schedule data for similar tasks in other projections. At step 2412, the function 2400 determines if an estimated finish date (calculated based on a start date, an estimated duration, and updates) is greater than a finish date by at least a threshold value. At step 2414, where the threshold value is exceeded, the function 2400 can alert a user. Optionally, a user can compare results between updates. Optionally, the function 2400 comprises a scenario planning tool which allows users to compare different schedules of a project based on particular updates to see trends between the two updates. The scenario planning tool can be configured to view and compare three or more updates wherein users can view trends across any number of updates. The details of any trend can be communicated to users according specified thresholds. In some embodiments disclosed herein, users can select colours to use for the indicator as well as to select threshold values. Users can also select variables and compare results between selected updates. The comparative approach can provide historical results under specified conditions. In some embodiments disclosed herein, users can provide reasons for changes in their data and can view previously provided reasons for similar tasks in a particular industry cluster identified using NLP technologies. Referring to FIGs. 24B to 24E, a schematic illustrating an example 2440 of the early warning schedule function 2400 is shown comprising blocks 2441 to 2477.
In some embodiments disclosed herein, one of the project management functions is an early warning cost function for providing an early warning based on an analysis of attributes related to tasks within a cost file. In particular, in some embodiments disclosed herein, the early warning cost function provides an early warning if a budget under at particular industry is greater Date Recue/Date Received 2022-08-10 than threshold values. This particular capability is based on mathematical formula combine with methods.
FIG. 25A is a flowchart showing the steps of an early warning cost function 2500, according to one embodiment of the present disclosure. The function 2500 begins with retrieving a cost file within a specific industry cluster (step 2502). At step 2504, cost data is extracted from the cost file, which may include task names, start dates, finish dates, durations, update data, reasons, and records. At step 2506, historical cost data is retrieved. At step 2508, NLP is used to identify similar tasks from other projects and extract data therefrom. At step 2510, the cost data is compared against the historical cost data for similar tasks in other projections. At step 2512, the function 2500 performs calculations to determine the amount estimated cost will be exceeded by actual cost, if applicable. At step 2514, results are displayed to a user. For example, if the cost is greater than the estimated cost by a percentage greater than a specified value, P1, the entry is indicated in a red color, and if the cost is greater than the estimated cost by a percentage greater than a specified value, P2, the entry is indicated in a yellow color.
Optionally, a user can compare results between updates. Optionally, the function 2500 comprises a scenario planning tool which allows users to compare different schedules of a project based on particular updates to see trends between the two updates. The scenario planning tool can be configured to view and compare three or more updates wherein users can view trends across any number of updates.
The details of any trend can be communicated to users according specified thresholds. In some embodiments disclosed herein, users can select colours to use for the indicator as well as to select threshold values. Users can also select variables and compare results between selected updates. The comparative approach can provide historical results under specified conditions. In some embodiments disclosed herein, users can provide reasons for changes in their data and can view previously provided reasons for similar tasks in a particular industry cluster identified using NLP
technologies. Referring to FIGs. 25B to 25D, a schematic illustrating an example 2540 of the early warning cost function 2500 is shown comprising blocks 2541 to 2572.
In some embodiments disclosed herein, a project management system comprises an interface configured to display various graph types using attributes from any of supported file types including schedule files, cost files, and contract files. In some embodiments disclosed herein, the interface can be configured to display various combinations of the available attributes, including plotting multiple different attributes on the same display and allowing users to perform basic statistical operations on the attributes. For example, plotting a count of a first attribute against a summation of a second attribute. In some embodiments disclosed herein, the interface comprises a feature which provides a textual analytical description or explanation of the graph displayed. FIGs 26A to 26D illustrate examples of user interfaces.

Date Recue/Date Received 2022-08-10 With above-described project analysis functions, a project may be closely and promptly monitored during the execution of the project. In some embodiments, the project and its schedule may be updated based on the results or outputs of above-described project analysis functions. The updated project and schedule thereof may be displayed to a user via a suitable user interface such as a display.
Although a few embodiments have been shown and described with reference to the accompanying drawings, it will be appreciated by those skilled in the art that various changes and modifications can be made to those skilled in the art that various changes and modifications can be made to these embodiments without changing or departing from their scope, intent, or functionality as defined by the appended claims. The terms and expressions used in the preceding specification have been used herein as terms of description and not of limitation, and there is no intention in the use of such terms and expressions of excluding equivalents of the features shown and described or portions thereof.

Date Recue/Date Received 2022-08-10

Claims

WHAT IS CLAIMED IS:

1. A project and program management system comprising:
one or more databases comprising schedule data for historical and current projects; and a server computer comprising an input interface and an output interface, and configured to perform artificial intelligence (AI) processing using an artificial neural network (ANN) for one or more project and program management functions at least comprising a critical path function for determining a critical path of a current project;
wherein, the server computer is configured to obtain instructions from the input interface, access the schedule data from the one or more databases, and display results through the output interface.

2. The project and program management system of claim 1 configured to operate on a cloud-based computer architecture, wherein the server computer comprises a first and a second server computer of allocated scalable computing capacity, the system further comprising:
a network storage element, a client computing device for use by a user, a network for cormecting the client computing device, the network storage element, the first server computer, and the second server computer, wherein:
the first server computer comprises an interface to communicate with the client computing device over the network, the first server computer comprises the one or more databases, and the second server computer is configured to perform the AI processing.

3. The project and program management system of claim 1 or 2, wherein the one or more project and program management functions further comprises an accelerator and de-risking function for identifying risky and critical tasks.

4. The project and program management system of claim 1 or 2, wherein:
the one or more databases further comprises historical schedule data; and the one or more project and program management functions further comprises one or more of:
a bow wave trend analyzer function for displaying bow wave trends, a critical path trend analyzer function for comparing critical paths, and a total float trend analyzer function for analyzing trends in total floats.

Date Recue/Date Received 2022-08-10

5. The project and program management system of claim 1 or 2, wherein:
the AI processing further comprises natural language processing (NLP);
and the one or more project and program management functions further comprises one or more of:
an early warning schedule function, a garage in garbage out (GIGO) schedule function for identifying scheduling errors, a potential claims function for identifying tasks that can cause potential claims, and a schedule risk function for identifying risky tasks.

6. The project and program management system of claim 1 or 2, wherein:
the one or more databases further comprises cost data for current projects;
and the one or more project and program management functions further comprises one or more of:
a cost savings function for identifying and recommending cost savings, and a cost risk function for identifying tasks that at risk of running over pre-determined thresholds.

7. The project and program management system of claim 1 or 2, wherein:
the AI processing further comprises NLP;
the one or more databases further comprises cost data for current projects, and historical cost and schedule data; and the one or more project and program management functions further comprises one or more of:
a completion probability function for analyzing a probability of completion of the current project, a cost trend analyzer function for analyzing cost trends of the current project, an early warning cost function for providing budget warnings, and a GIGO cost function for identifying cost errors.

8. The project and program management system of claim 1 or 2, wherein:
the AI processing further comprises NLP and a term frequency inverse document frequency method; and the one or more databases further comprises green house gas (GHG) data; and wherein the one or more project and program management functions further comprises a GHG calculation Date Recue/Date Received 2022-08-10 function for performing carbon footprint and GHG calculations and recommending alternative energy sources.

9. The project and program management system of claim 1 or 2, further configured to receive video monitoring input and the AI processing further comprises object detection technology; and wherein the one or more project and program management functions further comprises a site monitoring function for enhancing compliance and safety of the current project.

10. The project and program management system of claim 9, wherein the video monitoring input comprises thermal or infrared imaging; and wherein the site monitoring function is configured to analyze the thermal or infrared imaging by interpreting colours and intensities thereof.

11. The project and program management system of claim 1 or 2, wherein:
the AI processing further comprises NLP;
the one or more databases further comprises news events data; and the one or more project and program management functions comprises a risk events analysis function for identifying current events that may impact the current project.

12. The project and program management system of claim 1 or 2, wherein:
the AI processing further comprises NLP;
the one or more databases further comprises contractual data; and the one or more project and program management functions comprises a contract analyzer function for identifying clauses with risky words in the contractual data.

13. The project and program management system of claim 1 or 2, wherein the AI processing further comprises NLP;
the one or more databases further comprises report data; and the one or more project and program management functions comprises a report analyzer function for identifying terms with risky words in the report data.

14. The project and program management system of claim 1 or 2, wherein:
the AI processing further comprises NLP and a k-nearest neighbour (KNN) method; and the one or more project and program management functions comprises a resource optimization function for optimizing the use of resources on the current project.

Date Recue/Date Received 2022-08-10

15. The project and program management system of any one of claims 1 to 14, wherein the system is configured to provide a textual analytical description of graphics displayed.

16. A method for managing a project or program comprising:
receiving instructions for performing one or more functions for project and program management; and performing the one or more functions comprising the steps of:
retrieving schedule data for a current project, determining a critical path of the current project using artificial intelligence (AI) processing using an artificial neural network (ANN), and displaying the critical path.

17. The method of claim 16, wherein the one or more functions further comprises the steps of:
extracting task data inputs from the schedule data;
calculating update critical paths for each update of the current project using task data inputs;
and displaying the update critical paths.

18. The method of claim 16, wherein the one or more functions further comprises the steps of:
extracting project and task data from the schedule data;
compiling a list of tasks identified as completed in less than average duration;
sorting the list of tasks to provide a sorted list of tasks; and displaying the sorted list of tasks.

19. The method of claim 16, wherein the one or more functions further comprises the steps of:
retrieving news items;
compiling a list of relevant news items;
scoring each item in the list of relevant news items as opportunities or risks; and displaying the list of relevant news items.

20. The method of claim 19, wherein the one or more functions further comprises the steps of:
compiling a list of relevant news items scored as risks;
retrieving mitigation plans;

Date Recue/Date Received 2022-08-10 identifying recommended mitigation plans to address risks in the list of relevant news items scored as risks; and displaying the recommended mitigation plans.

21. The method of claim 16, wherein the one or more functions further comprises the steps of:
extracting task data from the schedule data;
identifying risky tasks from the task data and compiling a list of risky tasks; and displaying the list of risky tasks.

22. The method of claim 16, wherein the one or more functions further comprises the steps of:
extracting task data from the schedule data;
identifying unfinished tasks in the task data;
retrieving historical schedule data;
identifying similar tasks from the historical schedule data for all of the unfmished tasks;
calculating a completion probability using AI and ANN using the similar tasks from the historical data and the unfinished tasks; and displaying the completion probability.

23. The method of claim 16, wherein the one or more functions further comprises the steps of:
extracting task data from the schedule data;
calculating total floats using AI and ANN using the task data; and displaying the total floats.

24. The method of claim 16, wherein the one or more functions further comprises the steps of:
extracting task data from the schedule data;
producing bow waves of tasks and their durations using the task data; and displaying the bow waves.

25. The method of claim 16, wherein the one or more functions further comprises the steps of:
extracting a list of tasks from the schedule data;
retrieving historical schedule data;
identifying and mapping tasks in the list of tasks to historical schedule data;
determine if logic error is detected by analyzing the mapped list of tasks and the historical schedule data; and alerting user if logic error is detected.

Date Recue/Date Received 2022-08-10

26. The method of claim 25, wherein the one or more functions further comprises the step of adding a new schedule sequence to the historical schedule data.

27. The method of claim 16, wherein the one or more functions further comprises the steps of:
extracting tasks from the schedule data;
determining if actual duration of the tasks is outside of an average duration range, wherein if the actual duration of the tasks is greater than the average duration range, an overall delay on a project is calculated and one or more available resources can be recommended;
and displaying the overall delay.

28. The method of claim 16, wherein the one or more functions further comprises the steps of:
extracting a source task and a target task for a predecessor task from the schedule data;
confirming the source task and the target task belong to a same work breakdown structure;
determining if time difference between source task and target task may result in a potential claim based on one or more relation types;
compiling a list of potential claims; and display the list of potential claims.

29. The method of claim 16, wherein the one or more functions further comprises the steps of:
receiving video monitoring data;
detecting objects in the video monitoring data;
creating bounding box areas around the objects;
analyzing the bounding box areas for compliance and safety issues; and display compliance and safety issues.

30. The method of claim 29, wherein the one or more functions further comprises the step of retrieving scheduling information to determine areas and times of interest.

31. The method of claim 29, wherein the one or more functions further comprises the step of analyzing the video monitoring data using thermal imaging.

32. The method of claim 16, wherein the one or more functions further comprises the steps of:
retrieving a contract file;
extracting clauses from the contract file;

Date Recue/Date Received 2022-08-10 identifying identified clauses containing flagged words or language;
determining if the identified clauses are likely to be positive or negative;
and displaying a listing of the identified clauses.

33. The method of claim 32, wherein the one or more functions further comprises the step of estimating liquidated damages.

34. The method of claim 16, wherein the one or more functions further comprises the steps of:
retrieving a report flle;
extracting terms from the report file;
identifying identified terms containing flagged words or language;
determining if the identified terms are likely to be positive or negative; and displaying a listing of the identified terms.

35. The method of claim 16, wherein the one or more functions further comprises the steps of:
retrieving a cost file;
extracting a listing of tasks from the cost file;
retrieving historical cost data;
identifying similar tasks in the historical cost data for all unfinished tasks in the listing of tasks;
calculating predicted cost trends using ANN using the similar tasks and the historical cost data; and displaying cost trend results.

36. The method of claim 16, wherein the one or more functions further comprises the steps of:
retrieving a cost file;
extracting tasks from the cost flle;
identifying tasks at a cost risk of running over pre-determined cost thresholds; and displaying the cost risks.

37. The method of claim 16, wherein the one or more functions further comprises the steps of:
retrieving a cost file;
extracting tasks from the cost flle;
determining recommendations for cost savings by analyzing the tasks; and displaying cost savings recommendations.
Date Recue/Date Received 2022-08-10

38. The method of claim 16, wherein the one or more functions further comprises the steps of:
retrieving a greenhouse gas (GHG) file;
extracting GHG data from the GHG file;
calculate carbon footprints and scores using the GHG data; and displaying carbon footprint and scores.

39. The method of claim 38, wherein the one or more functions further comprises the step of recommending alternative energy sources.

40. The method of claim 38, wherein the one or more functions further comprises the step of displaying levels of emissions according to regions or assets.

41. The method of claim 38, wherein the one or more functions further comprises the step of simulating emissions with changed attributes.

42. The method of claim 16, wherein the one or more functions further comprises the steps of:
extracting current tasks from the schedule data;
retrieving resource data;
retrieving historical task data;
identifying similar tasks in the current tasks with the historical task data;
making resource recommendations for the similar tasks; and displaying the resource recommendations.

43. The method of claim 42, wherein the one or more functions further comprises the step of allocating resources to the similar tasks that are immediately actionable.

44. The method of claim 42, wherein the one or more functions further comprises the step of identifying a list of priority tasks.

45. The method of claim 16, wherein the one or more functions further comprises the steps of:
retrieving a cost file;
extracting tasks from the cost file;
retrieving historical cost data;
identifying and mapping similar tasks in the tasks to the historical cost data;

Date Recue/Date Received 2022-08-10 comparing cost information in the similar tasks with the historical cost data to identify potential errors;
displaying the potential errors.

46. The method of claim 16, wherein the one or more functions further comprises the steps of:
extracting tasks from the schedule data;
retrieving historical task data;
identifying and mapping similar tasks in the tasks to the historical task data;
comparing the similar tasks with the similar historical task data;
determining if estimated finish dates of the similar tasks exceed a budgeted finish date by a threshold value; and displaying similar tasks where the estimated fmish dates exceed the budgeted finish date by the threshold value.

47. The method of claim 16, wherein the one or more functions further comprises the steps of:
retrieving a cost file;
extracting tasks from the cost file;
retrieving historical cost data;
identifying and mapping similar tasks in the task to the historical cost data;
comparing the similar tasks with the historical cost data;
determining if estimated costs of the similar tasks is greater than a threshold percentage;
and displaying similar tasks where the estimated costs is greater than the threshold percentage.

48. The method of any one of claims 16 to 47 further comprising displaying a textual analytical description of graphics displayed.

Date Recue/Date Received 2022-08-10