Agent-driven causal graph-based project lifecycle management system.

Abstract

It is related to a system (1) that enables the management of the life cycle of artificial intelligence projects from the idea stage to the live launch and service handover, the analysis of project requests, the performance of business value, technical suitability, architecture, safety and risk assessments through expert agents, the monitoring of agent decisions through causality graphs, the inclusion of human decisions in the process and the evaluation of the results obtained through governance mechanisms.

Description

Classification: Open 1 TARIFF AGENT-MANAGED CAUSAL GRAPHIC-BASED PROJECT LIFE CYCLE MANAGEMENT SYSTEM Technical Area 5 This invention takes artificial intelligence projects in banking institutions from the idea stage to the next level. agent-based workflow for the lifecycle from go-live to service handover It is related to a system that enables its management. Previous Technique Today, the development of artificial intelligence projects in banking institutions and Project tracking systems, task management applications, software for management purposes. development tools, test tracking systems and operations management platforms 15 These systems are used for creating project requests and assigning tasks. monitoring, managing development processes, testing procedures in specific stages such as implementation and bringing projects live It is used. However, in current systems, artificial intelligence projects are in the initial stages. The entire process, from the initial stage to live deployment, is a single structure. 20 It cannot be managed through this system. Project requests, evaluation results, technical Reviews, approval processes, and post-live usage information are available on different systems or They are kept in different record formats, therefore the decisions made during the project process It is becoming difficult to track everything holistically. Therefore, banking... 25 a new generation system to be used in project planning processes in institutions It is needed. United States patent number US20260024038A1 in the known state of the art The document describes how sector-specific solutions can be developed using Collaborative Artificial Intelligence (AI) agents. Systems aimed at generating solutions are being described. However, there are only 30 from the identification of unplanned ideas by agents, to the analysis of ideas 2 from the evaluation and prioritization of projects based on the analysis results It is not mentioned. Brief Description of the Invention The aim of this invention is to rethink the ideas behind artificial intelligence projects carried out in banking institutions. from the initial stage to its deployment in the production environment and handover to operational service. The goal is to develop a system that manages the entire life cycle. Another aim of the invention is to enable 10 people working at different stages of the project life cycle. by consolidating the decisions of specialist software agents under a common governance structure to analyze project risks more accurately, to resolve disagreements among agents to convert risk input and only provide human opinion when necessary. to apply. Detailed Description of the Invention The “Agent-Driven Causal” approach was implemented to achieve the purpose of this invention. The "Graphical-Based Project Lifecycle Management System" is shown in the attached document. and in this form; Figure 1. Schematic view of the system that is the subject of the invention. 20 The parts shown in the figure are individually numbered, and the corresponding numbers correspond to these numbers. given below: 1. System 25 2. Electronic device 3. Database 4. Server D. External server 30 3 The transition of artificial intelligence projects from concept to live implementation in banking institutions and The invention enables the management of the life cycle until the service cycle. system (1); - AI project requests created by users 5 at least one electronic device that provides an interface that allows it to be displayed (2), - project objects produced throughout the project lifecycle, by the institution policies, mission restrictions, agent evaluations, human decisions, policy-action causality graph records, risk 10 to enable the storage of scores and learning data at least one database structured (3) and - Project created by the user via electronic device (2) receiving requests, incorporating the received requests into the standard project object transformation, analysis of project information, business value and impact conducting evaluations, project prioritization 15 the execution of processes, the creation of technical plans, architecture and security assessments to be carried out, expert agents the operation, the exchange of data between agents, the agent managing the workflow structure based on human decision-making, incorporating human decision-making into the process. obtaining the necessary human approvals within the scope of different agents 20 analysis of evaluations, policy-action causality graph by creating and recording decision relationships, development, testing, user Managing acceptance testing, go-live, and service handover processes, human resources. Updating governance policies in line with feedback and 25 recording of all transaction results in the database (3) It includes at least one server (4) providing. 4 The system in question consists of (1) electronic devices (2) smartphone, tablet computer, desktop It is a device similar to a desktop or portable computer. The one in question... electronic device (2) any remote communication device in the known state of the art Using the protocol, connect to the server (4) and the established connection It is structured to facilitate data exchange. The invention's preferred option is 5. In the implemented application, the electronic device (2) server (4) and the internet as a data bus It is configured to exchange data using electronic means. device (2), artificial intelligence project requests created by users on it access and viewing of evaluation results related to project processes It is structured to provide a user interface that enables 10 users. In the system that is the subject of the invention, the database (3) in (1) is in communication with the server (4) and is configured to be managed by the server (4). The invention is preferred In the arrangement made, the database (3) is created throughout the project lifecycle project objects, information on project requirements, results of business value and impact analysis, 15 project prioritization records, technical planning information, institutional policies, mission constraints, expert agent assessments, agent decisions, human actions approval, rejection and modification decisions, generated risk scores, policy-action causality graph records, production effects, and governance learning data. It is configured for storage. 20 The server (4) in the system (1) which is the subject of the invention, any remote communication to communicate with the electronic device (2) using the protocol and the established protocol to exchange data with electronic devices (2) via communication It is being configured. The server (4) records new data into the database (3), Deletion of registered data in database (3) or database (3) 25 Modifying the registered data within and the registered data within the database (3) to manage the database (3) by operations such as updating the data is configured. Server (4), user via electronic device (2) The artificial intelligence created by [the company / organization] is configured to receive the project request. Server (4), project description, project purpose, work unit 30 regarding the received project request. information, requestor information, expected work output, data sources to be used, customer impact, regulatory information, safety requirements and other project parameters Project management systems, enterprise human resources systems, enterprise resource management systems. to receive from an external server (D) in the form of planning (ERP) systems The server (4) is configured to save the received data to the database (3). It is configured. The server (4) converts the received project request into a standard project object. It is configured to normalize in a way that will create a (project object). The server (4) finds that there is missing or inconsistent information in the created project object. It is configured to determine if it is not present. The server (4) detects missing information. If this is done, the missing information from the relevant user via the electronic device (2) 10 It is configured to request completion. The server (4) requests the completion of the missing information. Project management systems if available from corporate systems or the relevant project via an external server (D) in the form of corporate data resources It is configured to receive the data. The server (4) is completed for the project. 15. Complete the process of creating a standard project object by updating its information. It is structured as follows: Server (4), external in the form of corporate data sources. Completed or ongoing project information obtained from servers (D), project evaluation records, process logs, operational performance indicators, user feedback, customer engagement data, corporate strategic By analyzing data in the form of goals and business unit needs, the project request is still 20 to identify untapped development opportunities and AI project candidates It is structured. The server (4) is structured according to the areas of expertise on the project objects. structured work value assessment agent, technical conformity assessment agent, architectural assessment agent, safety and compliance assessment agent, risk analysis 25 to operate agents in the form of agents and project prioritization agents It is configured. The server (4) runs expert agents, between agents Sharing evaluation data, combining agent outputs, and agent-based work It is configured to manage the flow. Server (4), business value with specialist agents. assessment, technical suitability assessment, architectural assessment, 30 security and compliance assessment, risk analysis and project prioritization processes It is configured to implement. The server (4) creates the project object. 6 to conduct a business value analysis on it It is structured. The server (4) will provide the project within the scope of business value analysis. expected financial contribution, increased operational efficiency, customer experience its contribution, strategic priority, and alignment with corporate goals It is structured to analyze the value of the work performed. Server (4) 5 The server is configured to save the analysis results to the database (3). (4), to perform a business impact analysis on the project object It is being configured. The server (4) will be affected by the project within the scope of business impact analysis. systems, business units, operational processes, customer processes, technical 10 to analyze their dependencies, regulatory impacts and operational risks is configured. The server (4) provides the generated business impact analysis results data. It is configured to save to the database (3). The server (4) retrieves from the database (3) project records, resource utilization information, and capacity related to ongoing projects. plans and project dependencies project management systems or enterprise data 15 to obtain resources from an external server (D) is structured. Server (4), business value analysis results, business impact analysis by evaluating the results together with the current resource situation and project dependencies The project is structured to perform a prioritization analysis. The server (4) will submit the prioritization results to the senior management for decision. It is configured to convert to a file. The server (4) generates decision 20 to present the file to users via electronic device (2) It is configured. The server (4) only allows authorized personnel to access the generated decision file. It is configured to provide to users. The server (4), upper management or initiation, pilot program implementation, postponement as decided by the authorized decision-making board. or is configured to make the decision to reject. Server (4), expert agent 25 to determine the level of disagreement between their assessments, and conversely, the risk to generate a score and if the risk score exceeds a predetermined threshold value The server (4) is structured to initiate the human decision-making process. approval, rejection, conditional approval or modification decisions made by the agent 30 by associating them with the evaluations and including them in the project life cycle is structured. The server (4) handles the decisions made throughout the project lifecycle. 7 which institutional policy, mandate, expert agent assessment, and human decision policy-action causal graph to show that it was created based on It is configured to create. The server (4) rejects or cancels the decision given. In case of postponement, record the reason for the decision in the database (3) is being configured. Server (4), if it is decided to start the project 5 It is configured to initiate the technical planning process. Server (4), It is configured to create a backlog for the approved project. Server (4) creates user story records on the generated job list. It is structured in such a way. The server (4) uses technical data from user history records. It is configured to produce tasks. The server (4) handles technical tasks 10 It is configured to be deployed to the development cycle (sprints). Server (4), by creating development cycle plans, task dependencies, and work distribution It is structured to prepare the technical development plan. Server (4), The prepared technical plan is configured to be saved in the database (3). The server (4) will conduct an architectural suitability assessment on the prepared technical plan. It is configured to perform. Server (4), architectural suitability As part of its evaluation, the solution architecture, system integrations, and corporate to analyze architectural standards and technical dependencies It is configured. The server (4) stores the architectural evaluation results in the database. (3) is configured to save. Server (4), architectural compatibility 20 Security and compliance assessment simultaneously with the evaluation. It is configured to perform. Server (4), security and compliance As part of its assessment, data privacy requirements and access authorizations, regulatory rules, model risk requirements, information 25 to analyze security policies and institutional policies It is configured. The server (4) retrieves the institutional policies and tasks from the database (3). It is configured to receive the restrictions. The server (4) receives the institutional policies. converting into mission constraints and during the security assessment It is configured to implement task restrictions. The server (4), security and 30 to record the results of the compliance assessment in the database (3) is structured. Server (4), expert agent assessments, human decisions, 8 by analyzing project results and policy-action causality graph records together to implement governance learning, update institutional policies and to improve decision parameters to be used in subsequent project evaluations It is structured accordingly. Industrial Application of the Invention 5 The system in question (1) is an artificial intelligence developed in banking institutions. from the idea stage of their projects to going live and handing over the service centralized management of processes, different personnel involved in project processes the joint analysis of assessments from different areas of expertise and the results obtained It ensures that decisions are stored in a traceable manner. The architecture of the invention is 10 thanks to this, finance, banking and enterprise technology with intensive project processes. In their infrastructure, not only are project monitoring carried out, but the projects themselves are also implemented. prioritization, risk assessment, human decision-making processes, development, testing, living organisms Transition and post-operation management processes are carried out in an integrated manner. This invention ensures the continuity of service and 15 Fully compatible with different industrial systems, horizontally scalable and operational. From this perspective, it provides a sustainable system (1) optimization. Around these fundamental concepts, the invention is called "Agent-Driven Causal Graph-Based". 20 various applications related to Project Life Cycle Management System (1)” It is possible to develop further, and the invention cannot be limited to the examples described here. It is essentially as stated in the requests.

Claims

9 REQUESTS 1. The transition of artificial intelligence projects from concept to live implementation in banking institutions and Enables the management of the lifecycle until the service cycle; - 5 of the AI ​​project requests created by users on it the entry and evaluation results of the project processes at least one electronic device that provides an interface that allows it to be displayed (2), - project objects produced throughout the project lifecycle, by the institution policies, mission restrictions, agent evaluations, human decisions, policy-action causality graph records, risk 10 to enable the storage of scores and governance learning data at least one database structured (3) and - Project created by the user via electronic device (2) receiving requests, incorporating the received requests into the standard project object transformation, analysis of project information, business value and impact 15 conducting evaluations, project prioritization the execution of processes, the creation of technical plans, architecture and security assessments to be carried out, expert agents execution, management of agent-based workflow structure, human decision-making obtaining the necessary human approvals as part of the inclusion in the process, 20 analyzing different agent assessments, policy-action recording decision relationships by creating a causality graph, development, testing, user acceptance testing, go-live, and service handover. managing processes, managing based on human feedback. updating policies and all transaction results within 25 days It must contain at least one server (4) that enables recording to the database (3). a characterized system (1).

2. A device such as a smartphone, tablet computer, or laptop computer. A system like the one in Claim 1, characterized by an electronic device (2) (1). 30 3. Connect to the server (4) using any remote communication protocol. to establish and exchange data with the server (4) through this established connection electronic device (2) configured to make it happen A system like the one in Claim 1 or 2, characterized (1).

4. To establish a connection with the server (4) via a data network such as the Internet. a structured electronic device (2) as in Claim 3 system (1).

5. 10 of the AI ​​project requests created by users. the entry and evaluation results of the project processes electronic device (2) configured to enable its display a system like any of the above characterized claims (1).

6. To be in communication with Server (4) and to be managed by Server (4) from the above requests characterized by the structured database (3) a system like any other (1).

7. Project objects created throughout the project lifecycle, according to project requirements. related information, business value and impact analysis results, project prioritization records, technical planning information, organizational policies, job limitations, expert agent assessments, agent decisions, human-given approval, rejection and change decisions, generated risk scores, policy-action causality graph records, production effects, and governance learning data 25 characterized by the database structured for storage (3) a system like any of the above requests (1).

8. User-generated artificial intelligence project via electronic device (2) 30 characterized by the server (4) configured to ensure the request is received a system like any of the above-mentioned requests (1). 11 9. Project description, project objective, and business unit information related to the received project request. Requestor information, expected work output, data sources to be used, customer impact, regulatory information, safety requirements and other project parameters Project management systems, enterprise human resources systems, enterprise 5 to receive from an external server (D) in the form of resource planning systems any of the above requests characterized by the configured server (4) a system like one of them (1).

10. Server (4) configured to save the received data to the database (3) 10 a system like any of the above characterized claims (1).

11. Normalize the received project request to create a standard project object. to check if there is any missing or inconsistent information within the created project object 15 characterized by the server (4) configured to determine that it is not present. a system like any of the above-mentioned requests (1).

12. If missing information is detected, the relevant information will be sent via the electronic device (2). to ask the user to complete the missing information and the missing information 20 Project management systems if available from corporate systems or via an external server (D) in the form of corporate data sources characterized by the server (4) configured to receive project data a system like any of the above requests (1).

13. Creating a standard project object by updating completed project information. characterized by the server (4) configured to complete the operation a system like any of the above requests (1).

14. From corporate data sources, existing project records, operational process 30 information and organizational goals obtained from external servers (D) 12 Information on completed or ongoing projects, project evaluation records, work Transaction logs related to processes, operational performance indicators, user feedback notifications, customer interaction data, corporate strategic goals, business unit by analyzing data in the form of needs that have not yet been converted into project requests Server (4) and 5 configured to identify artificial intelligence project candidates a system like any of the above characterized claims (1).

15. Work value structured according to areas of expertise on project objects. assessment agent, technical conformity assessment agent, architecture 10 assessment agent, safety and compliance assessment agent, risk analysis agent and structured to operate agents in the form of project prioritization agents any of the above requests characterized by the server (4) such a system (1).

16. Business value assessment, technical suitability assessment with expert agents, architectural assessment, safety and compliance assessment, risk analysis and project server (4) configured to implement prioritization operations a system like any of the above characterized claims (1). 20 17. Perform a business value analysis on the created project object and the business value Within the scope of the analysis, the expected financial contribution of the project and its operational aspects were considered. increased efficiency, contribution to customer experience, strategic priority and structured to analyze its alignment with corporate goals 25 any of the above requests characterized by the server (4) such a system (1).

18. To record the results of the business value analysis performed in the database (3). 30 of the above requests characterized by the configured server (4) a system like any other (1). 13 19. Performing a business impact analysis on the project object and conducting a business impact analysis. within the scope of the project, the systems, business units, and operations that will be affected. processes, customer processes, technical dependencies, regulatory impacts, and Server (4) and 5 configured to analyze operational risks a system like any of the above characterized claims (1).

20. To record the results of the generated business impact analysis in the database (3). 10 of the above requests characterized by the configured server (4) a system like any other (1).

21. From the database (3) project records relating to ongoing projects, resources usage information, capacity plans and project dependencies project management an external server (D) 15 in the form of systems or corporate data sources characterized by the server (4) configured to receive from it a system like any of the above requests (1).

22. Results of business value analysis, results of business impact analysis, current resource status, and By jointly evaluating project dependencies, we can perform a project prioritization analysis. 20 to implement and report the prioritization results to senior management. with the server (4) configured to convert into a decision file to be presented a system like any of the above characterized claims (1).

23. Presenting the generated decision file to users via electronic device (2). and to forward the generated decision file only to authorized users. from the above requests characterized by the configured server (4) a system like any other (1). 14 24. Launching, piloting, authorized by senior management or the decision-making board. to make a decision to proceed, postpone or reject within the scope from the above requests characterized by the configured server (4) a system like any other (1).

25. To determine the level of disagreement between expert agent assessments, In contrast, creating a risk score and the risk score exceeding a predetermined threshold structured to initiate the human decision-making process if its value exceeds any of the above requests characterized by the server (4) such a system (1). 10 26. Approvals, refusals, conditional approvals, or modification decisions made by humans. to integrate into the project lifecycle by associating with agents any of the above requests characterized by the configured server (4) a system like one of them (1). 15 27. Which institutional policy or task is reflected in the decisions made throughout the project lifecycle? the constraint is based on expert agent assessment and human decision policy-action causal graph to show that it was created to create and if the decision is to reject or postpone, the decision is 20 with server (4) configured to record the reason in the database (3) a system like any of the above characterized claims (1).

28. If a decision is made to start the project, the technical planning process will begin on 25 days. configured to initiate and create a work list for the approved project. any of the above requests characterized by the server (4) such a system (1).

29. Creating user story records on the generated task list, user 30 generating technical tasks from story recordings and developing technical tasks Characterized by the server (4) configured to participate in the cycle a system like any of the above requests (1).

30. Architectural suitability assessment of the prepared technical plan. to implement, solution 5 within the scope of architectural suitability assessment architecture, system integrations, enterprise architecture standards and technical to analyze dependencies and store architectural evaluation results in the database (3) characterized by the server (4) configured to record a system like any of the above requests (1).

31. Safety and compliance simultaneously with architectural conformity assessment. to conduct an assessment and security and compliance assessment within the scope of data privacy requirements, access authorizations, regulatory rules, model risk requirements, information security Server 15 is configured to analyze policies and institutional policies. (4) like any of the above-mentioned claims characterized by system (1).

32. Development cycle plans, task dependencies, and work distribution. by creating and preparing a technical development plan and submitting the prepared technical plan to data 20 characterized by the server (4) configured to save to the base (3) a system like any of the above requests (1).

33. To retrieve (3) institutional policies and task restrictions from the database, retrieved Transforming organizational policies into mission constraints and security assessment 25 during which time these mission restrictions are implemented and security-compliance configured to record the evaluation results in the database (3) any of the above requests characterized by the server (4) such a system (1). 16 34. Expert agent assessments, human decisions, project outcomes and policy- learning governance by analyzing action causality graph records together to implement, update institutional policies and the next project to improve the decision parameters to be used in evaluations 5 of the above requests characterized by the configured server (4). a system like any other (1). 15 25

Images