Rakuten Symphony has developed a prioritized list of the top 25 AI initiatives for communications service providers and divided them into five categories. Rakuten Site Manager Process Mining is one of the top priorities for the Network Site Management and Roll Out category.
Building out a cell site is a complex endeavor with highly detailed processes, critical dependencies, multiple vendors, deadlines, equipment and more. Managing the build out and ongoing operation of these sites is a great challenge for an AI initiative we call process mining that is built into our Rakuten Site Manager software.
Rakuten Site Manager provides full network lifecycle services such as network design, planning, deployment and network operations. The software provides end-to-end visibility and automation into all site-related tasks. It reduces manual processes through an option to bulk upload site data and assigns appropriate roles to initiate activities on the site. Without the process mining model, Rakuten Site Manager users manually access the application to individually check the status of work orders or tasks, including initiation and potential delays.
However, with Rakuten Site Manager’s AI capability, users can gain a detailed overview of the site project’s performance, pinpoint areas for improvement, and make informed decisions to ensure the project is completed successfully and on time. It aims to guarantee a 100% completion rate within the designated timeframe, with proactive notifications about program progress and timely resolution of any issues that arise during implementation.
The process flow in Rakuten Site Manager involves identifying all of the required tasks and grouping them into one or multiple work orders. In the software, a combination of tasks defines a milestone which has a set start and end date. However, milestone deadlines are often missed due to various factors such as vendor delays, contractor issues, or adverse weather conditions.
By training on the data collected from daily operations, the process mining model can determine which task or milestone deadlines are likely to be missed and by how much.
This information can be combined with other data to generate a summarized insight for the end user, including:
The output from process mining predictions is stored in a central online analytical processing (OLAP) database and can be utilized for ongoing training by the Rakuten AI for Telecom Assistance knowledge base. This will support any inquiries received from Rakuten Site Manager end users.
The Process Mining feature provides a number of benefits to mobile operators who are looking to streamline their site lifecycle management.