Based on Predictive Engine for Resource Allocation (PERA)
To improve business operation effectiveness, companies are now looking to integrate IoT, business process management, AI, and data analytics as core tools to allocate their service delivery resource and global supply chain planning.
QRInno Development is using AI and IoT technologies to help company to improve their demand and resource forecasting capabilities in their command center. The command center will have visibility to device, people, customer support activity, and other technology resources (e.g. Intelligent Video Analytics).
At i5Lab working with NUS and Huawei, QRInno Development is using Nvidia machine-learning technology to build customers demand and resource allocation solution. The machine learning, which is a branch of artificial intelligence (AI), uses specially-designed algorithms to generate predictions based on captured data either from documents or sensing devices.
For example, the company is looking to see if it can create variables based on new sources of data, such as recruitment data, business process volume and IoT sensing data to improve demand forecasts.
Historically, companies bought expensive demand management (DM) solutions developed by business analyst(BA), and then implemented the algorithms that came prepackaged in the DM solution. These solutions were periodically tuned by manpower BAs to make sure forecast accuracy did not degrade.
Now newer demand and resource management solutions have “self-healing” machine learning and resource matching capabilities — i.e., look at historical forecasts, validate the accuracy of the forecasts, and then suggest using a different algorithm in particular situations. Using AI technology with self-healing demand and resource matching solutions is a new machine learning technology that compliment the need for smart analysts in command centers.
For large corporate customers, there are standard service level agreements such as same business day, two hour, and four hour response times. They have expensive tool they’ve built on top of a BPM solution that provides business process rules at the transaction level. A particular type of service request, for example, might need to be routed to a technician with a certain skill set. The BPM level of their solution also provides limited alerts.
To improve business system for both large company and small enterprise, Resource.AI is affordable AI as a service (AIaaS) on top of the IoT runs a Predictive Engine for Resource Allocation (PERA) engine. The PERA layer looks at the thousands of alerts generated at the transaction level and looks for larger patterns.
QRInno Development can program the PERA to detect and respond on IoT devices deviations in real time. For example, company expects to receive acknowledgements from IoT devices when they receive a service request. If company is getting a myriad of non-acknowledgements, the PERA engine knows what to look to see if the non-acknowledgements are all coming from the same IoT sensor. If so, it creates report to contact that administrators and have them correct the problem. The PERA might also detect that demand have dropped in a certain area. One of their area managers is flagged, the manager will review at historical trends, deviations from expected service levels for significant patterns. So that he can confirm demand and resource allocation.
For more information, please email us at [email protected] and [eafl id=”5374″ name=”i5Lab” text=”i5Lab”]