AI Conversational Agent for Non-Inventory Product Procurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
E-commerce and electronic environments face challenges in providing an efficient and interactive user experience for purchasing non-inventory catalog products, particularly in initiating and managing purchase requisitions and orders through conversational interfaces.
Innovation Solution
An artificial intelligence and machine learning-based conversational agent is implemented, utilizing a conversational chatbot that enables users to interactively select products, specify quantities, and submit orders through natural language dialogue, integrating with enterprise resource planning systems and machine learning classifiers to process requests and manage order status.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a traditional e-commerce interface is used for purchasing non-inventory catalog products, then the system structure is simple, but the user experience is less interactive and engagement is reduced
Solution Approach 1:
The patent replaces traditional mechanical UI interaction (buttons, forms, menus) with an AI-based conversational system that processes natural language. The chatbot uses natural language processing to understand user intent, extract entities, and execute purchase workflows through dialogue, substituting the mechanical interaction model with an intelligent conversational model that provides more engaging user experience while handling non-inventory catalog products
Solution Approach 2:
The patent introduces an AI chatbot as an intermediary between the user and the e-commerce system. This intermediary layer processes natural language input, interprets user intent, manages conversation state, and coordinates with backend systems (product catalog, order management, payment processing). The chatbot acts as a mediator that translates human language into system commands while providing natural, interactive communication, thereby enhancing user experience without requiring changes to core system architecture
2Productivity
If manual processing of purchase requisitions is used, then the system complexity is low, but the productivity and operational efficiency are reduced
Solution Approach 1:
The patent implements self-service capabilities through the AI chatbot that automatically handles purchase requisition processing without requiring manual intervention. The system autonomously performs tasks including understanding user purchase intent, searching the product catalog, retrieving product details, calculating totals, processing orders, and providing order confirmation. This automated self-service workflow significantly improves operational efficiency by eliminating manual processing steps while the modular architecture keeps system complexity manageable through clear separation of concerns
3Ease of operation
If a conversational chatbot interface is implemented, then the user engagement is improved, but the difficulty of detecting and measuring user intent increases
Solution Approach 1:
The patent implements feedback mechanisms within the conversational workflow to clarify and confirm user intent. The chatbot uses techniques such as asking clarifying questions when intent is ambiguous, presenting options for user selection, and providing summaries of detected intent for user confirmation. This feedback loop allows the system to iteratively refine its understanding of user intent while maintaining natural conversation flow, thereby improving user engagement without being overwhelmed by intent detection complexity
Solution Approach 2:
The patent employs preliminary action by pre-defining intent categories, entity types, and conversation workflows before deployment. The system is trained on predefined schemas for purchase requisitions, product attributes, and order parameters. This preliminary structuring of possible intents and responses provides a framework that guides the NLP processing, making intent detection more manageable while still allowing flexible natural language interaction that engages users
Data Source
AI summary
In some examples, artificial intelligence and machine learning based conversational agent may include ascertaining, based on a chat conducted with a conversational chatbot, a request by a user to purchase a product, and an attribute associated with the user. An intent associated with the user to purchase the product may be generated. Further, a catalog that includes a plurality of products that match the request by the user to purchase the product may be generated. Selection of a product from the plurality of products may be received. Identification of a quantity associated with the selected product may be received. A purchase request may be generated. A purchase order associated with the selected product may be generated. Further, based on the purchase order associated with the selected product, the selected product may be procured for the user.