Electronic Message Processing with Meta Information Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing email response management systems are limited in their ability to process incoming messages effectively, as they often rely on a narrow scope of information and are inflexible in applying processing rules, leading to unsatisfactory results due to the lack of sufficient business context and sophisticated linguistic analysis.
Innovation Solution
A method and system that access meta information to retrieve relevant fact information from pre-selected classes, allowing for the storage of this information in an electronic file associated with incoming messages, enabling more flexible and comprehensive processing rules to be applied, including business context, analytical data, and communication information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automatic processing using rule-based engine is implemented, then message processing efficiency is improved, but system complexity and maintenance cost increase
Solution Approach 1:
The system segments the complex knowledge management task into smaller, manageable rule-based processing units. Each rule handles a specific aspect of message processing (routing, categorization, response generation), making the overall system more manageable and maintainable while achieving high automation levels.
Solution Approach 2:
The patent introduces an intermediary layer between the incoming messages and the processing logic. This layer includes components that standardize message formats, extract key information, and prepare data for rule evaluation, thereby simplifying the rule-based engine's workload and reducing overall system complexity.
2Measurement precision
If sophisticated linguistic analysis is used, then message understanding accuracy is improved, but implementation difficulty and cost increase
Solution Approach 1:
The system extracts only the essential information elements from incoming messages that are necessary for processing (such as sender, recipient, subject, key entities, and action verbs). By focusing on extracting only the critical data points rather than performing comprehensive linguistic analysis, the system achieves sufficient understanding accuracy with reduced complexity.
Solution Approach 2:
The patent applies different levels of analysis to different parts of the message based on their importance. Critical fields like subject lines and key entities receive more rigorous processing, while less important fields use simpler analysis methods, optimizing the balance between accuracy and complexity.
3Speed
If limited scope information is used for processing, then processing speed is improved, but processing quality and business context sufficiency worsen
Solution Approach 1:
The system performs preliminary actions by pre-fetching and caching commonly needed information (such as customer profiles, product catalogs, and organizational charts) before message processing begins. This allows the rule-based engine to access comprehensive business context information without incurring additional processing delays during actual message handling.
Solution Approach 2:
The patent implements dynamic information retrieval where the scope of information fetched for processing adapts based on the message type and processing requirements. For simple routine messages, only essential information is retrieved to maintain speed, while complex messages trigger retrieval of additional contextual information, optimizing the balance between speed and completeness.
Data Source
AI summary
System and techniques are described for retrieving information relating to a received electronic message. Upon receipt of an incoming electronic message in a computer system, meta information stored in the computer system is accessed. The meta information identifies a first pre-selected class of a plurality of classes of stored fact information. A portion of the stored fact information that is a member of the first pre-selected class is retrieved. The retrieved portion of the stored fact information is stored in an electronic file that is associated with the incoming electronic message such that a rule for processing the incoming electronic message can be applied to the retrieved portion.