Governed API Calls for Natural Language Contact Center Agents
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Natural language processing engines in contact centers often lack integration with data stored by the entity, limiting their ability to access or modify customer information, transaction history, or product data, which is necessary for tasks like account management or providing accurate responses.
Innovation Solution
Integrating a software agent in the contact center with API calling technology to access data through a governance engine, allowing the software agent to leverage NLP technology to generate responses based on data retrieved via API calls.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If natural language processing engines are used in contact centers, then automated response capability is improved, but data access capability deteriorates
Solution Approach 1:
The patent introduces an API gateway as an intermediary component between the NLP engine and external data sources. The gateway receives API calls from the NLP engine, manages authentication and authorization, and retrieves data from external systems. This mediator enables the automated NLP system to access external data without direct integration complexity
Solution Approach 2:
The NLP engine is designed with multi-functionality to handle both natural language processing tasks and API call generation. The same engine that processes user queries also formulates and sends API requests to external data sources, consolidating multiple functions into a single system component
2Measurement precision
If NLP engine is integrated with external data sources, then response accuracy is improved, but system complexity increases
Solution Approach 1:
The system is segmented into distinct functional components: the NLP engine for query processing, the API gateway for data access management, and external data sources. This segmentation allows each component to be developed, maintained, and scaled independently, reducing overall system complexity while maintaining response accuracy
Solution Approach 2:
The API gateway serves as a mediator that simplifies the integration between the NLP engine and external data sources. It handles authentication, authorization, and data retrieval, shielding the NLP engine from complex integration details and reducing system complexity
3Productivity
If API calls are used to access external data, then data retrieval capability is improved, but integration complexity increases
Solution Approach 1:
The API gateway acts as an intermediary that manages all API calls to external data sources. It centralizes authentication, authorization, and data retrieval logic, simplifying the integration process and enabling rapid data access without requiring complex point-to-point integrations
Solution Approach 2:
The system implements self-service capabilities where the NLP engine automatically generates and sends API calls based on user queries without manual intervention. The API gateway automatically manages authentication and data retrieval, enabling the system to service itself and reducing integration complexity
Data Source
AI summary
A server accesses, during a contact center engagement performed by a software agent configured to generate and output automated responses to prompts, a prompt provided by a contact center user device. The server determines, using a natural language processing engine of the software agent, to use an application programming interface call based on the prompt, the natural language processing engine comprising a generative pre-trained transformer trained to generate natural language responses to natural language prompts. The server transmits an access request representing the application programming interface call to a governance engine configured to generate data structures responsive to application programming interface calls in a format readable by the software agent. The server receives a data structure responsive to the access request from the governance engine. The server generates, using the natural language processing engine, a natural language response based on the data structure.