LLM Graph Matching for Complex B2B Resolution Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing artificial intelligence-based systems in marketing and sales fail to generate results quickly and do not make certain types of decisions that assist businesses, particularly in complex B2B environments where organizational structures and power dynamics influence decision-making, leading to inefficiencies and incomplete information capture.
Innovation Solution
A processing system that utilizes graph structure data and large language models to generate resolution data by associating entities and propositions, allowing for the automated selection of Customer Value Propositions (CVPs) that match the goals of market participants, even in the presence of conflicting interests, and predicts market size and traction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If existing artificial intelligence-based systems are used for marketing and sales decisions, then some business decisions can be made, but the results are not generated quickly enough and certain types of decisions cannot be made
Solution Approach 1:
The system segments the decision-making process into multiple specialized components: a graph structure module for organizing market participant relationships, a goal matching module for aligning CVPs with participant objectives, and a resolution generation module for producing actionable decisions. This segmentation allows each component to process specific aspects efficiently, overall improving speed and decision-making capability.
Solution Approach 2:
The patent introduces an intermediary processing layer that receives input data, processes it through graph structure analysis and goal matching algorithms, and generates resolved decisions. This intermediary layer acts as a mediator between raw data and final decisions, enabling faster and more comprehensive decision-making by pre-processing and structuring information before decision generation.
2Adaptability or versatility
If existing artificial intelligence-based systems are used, then some marketing decisions can be made, but they do not capture complex organizational structures and power dynamics
Solution Approach 1:
The system adds a dimensional layer by representing market participants and their relationships as a graph structure with multiple dimensions: entities (people, organizations), propositions (goals, objectives), and relationships (associations, influences). This graphical representation captures complex organizational structures and power dynamics that traditional linear AI models cannot process, preventing information loss while maintaining adaptability.
3Loss of time
If automated selection of Customer Value Propositions is implemented, then time and effort for reaching optimal sales outcomes is reduced, but the system must handle conflicting interests and complex dynamics
Solution Approach 1:
The system performs preliminary action by pre-processing market participant data into graph structures and pre-identifying goal associations before the actual CVP selection process. This preliminary organization of information allows the automated system to quickly match CVPs with participant goals without encountering conflicting interests as unexpected complications, thereby reducing time while managing complexity through advance preparation.
Data Source
AI summary
The disclosures are directed to processing systems and methods that apply artificial intelligence-based processes to match an input to one of multiple options. In one example, a processor receives input data and, based on inputting the input data to a large language model (LLM), generates graph data that associates each of multiple propositions to one or more entities. Further, based on inputting the graph data to a trained artificial intelligence (AI) model, the processor generates query data characterizing one or more queries. In addition, based on inputting the graph data and the query data to the same or different LLM, the processor generates matching data charactering associations between the multiple propositions and the one or more queries. The processor may then receive a query request, and can match the query request to at least one of the multiple propositions based on the matching data.