Message Prioritization via Interaction Scoring and Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users in message sharing systems often receive a large number of messages, making it difficult to identify and focus on interesting content, as existing systems lack effective configurations to prioritize messages based on user interests.
Innovation Solution
A message recommendation system that uses interaction data and message classification to assign scores to messages, allowing for prioritization and recommendation of messages likely to be interesting to users, utilizing an asymmetric graph to represent interest data and provide personalized recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If users subscribe to many users to receive comprehensive information, then the quantity of received messages increases, but the user's ability to identify interesting messages deteriorates
Solution Approach 1:
The system uses feedback from user interactions (likes, shares, comments) to continuously refine and update message prioritization. Interaction data from multiple users is aggregated to determine which messages are most interesting, creating a feedback loop that improves recommendation accuracy over time while maintaining comprehensive message delivery.
Solution Approach 2:
The system changes the parameter of message presentation by dynamically adjusting priorities based on interaction data. Messages are re-ranked and reprioritized based on real-time interaction patterns, transforming the static message list into a dynamic, adaptive presentation that separates interesting from uninteresting content while maintaining quantity.
2Ease of operation
If users manually filter messages by keywords or authors, then the ease of selecting interesting messages improves, but the time required to review messages increases
Solution Approach 1:
The system performs preliminary action by automatically prioritizing and pre-sorting messages before the user needs to review them. Interaction data is processed in advance to determine message importance, so when the user accesses their message stream, the most interesting messages are already positioned at the top, eliminating the need for manual filtering and reducing review time.
Solution Approach 2:
The system provides self-service by automatically performing the filtering and prioritization that would otherwise require manual user intervention. The automated prioritization algorithm continuously works to identify and highlight interesting messages without user input, freeing the user from manual filtering tasks while maintaining ease of operation.
3Reliability
If the system delivers all messages to subscribers, then the completeness of information delivery improves, but the relevance of individual messages to users deteriorates
Solution Approach 1:
The system segments the message stream into prioritized sections based on relevance. By dividing the complete message set into ranked segments, the system maintains completeness of delivery while improving relevance through structured presentation. High-relevance messages are segmented into prominent positions, allowing users to quickly identify interesting content without losing any messages.
Data Source
AI summary
A system and a method are disclosed for recommending electronic messages in a message sharing system. Users can post messages to the message sharing system. These messages from posting users are received by the system and sent to receiving users that have subscribed to the posting users. The receiving users interact with the messages in various ways, such as by sharing the messages with other users. Interaction information is received for each of the electronic messages. The interaction information includes an indication of the number of interactions with the electronic message by receiving users. A score is determined for each electronic message based on the interaction information. Electronic messages are selected for being recommended to a user or a group of users based on the scores. The recommendations are then sent to the users, enabling users to better focus their attention on messages that are likely to be interesting.