Amdocs has been granted a patent for a machine learning system that evaluates customer service agents in a retail store. The system identifies the presence of a customer and processes information associated with the customer to determine an expected outcome of an interaction. After the interaction, the actual outcome is determined and the agent is evaluated based on the comparison of the actual and expected outcomes. The evaluation result can be used to assign the agent to future customers. GlobalData’s report on Amdocs gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Amdocs, Hybrid cloud mgmt was a key innovation area identified from patents. Amdocs's grant share as of September 2023 was 81%. Grant share is based on the ratio of number of grants to total number of patents.
Evaluation of customer service agents using machine learning
A recently granted patent (Publication Number: US11775865B1) describes a method and system for optimizing customer-agent interactions in a physical retail store using machine learning. The patent outlines a computer-readable medium that stores executable code for performing the method.
The method involves collecting training data from logs of prior interactions between specified customers and agents in the retail store. This data is then used to train a machine learning model to predict the expected outcome of interactions between different combinations of customers and agents. The expected outcome is a monetary value, such as a positive value for customer purchases, a negative value for customer refunds, or zero for no customer action.
The presence of a customer in the retail store is identified, potentially using a facial recognition algorithm. The system then determines the available agents who can assist the customer and processes information about the customer and agent using the machine learning model to determine the expected outcome of their interaction. Based on these expected outcomes, one agent is selected to assist the customer, and the agent is notified to begin interacting with the customer.
During the interaction, the system records the interaction based on input to a point of sale system. After the interaction, the actual outcome is determined from the recorded interaction. The agent is then evaluated by comparing the actual outcome with the expected outcome determined by the machine learning model. The result of this evaluation is used to assign the agent to future customers.
The patent also mentions additional features, such as training the machine learning model using data from a customer relationship management system or publicly available data. The information associated with the customer may include an identifier. The agent's evaluation can be based on multiple customer interactions over time, with the results of the evaluations combined. The output of the machine learning model may also include the expected time required for each agent to serve the customer.
Overall, this patented method and system aim to optimize customer-agent interactions in a physical retail store by using machine learning to predict outcomes and assign agents based on those predictions.
To know more about GlobalData’s detailed insights on Amdocs, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
