Emotional State Indicators via Interval-Based Group Aggregation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to effectively bridge the emotional gap between on-site and online audiences at real-world events, as emotions and interactions are not bidirectionally transmitted, and individual user data sets are too large to process and compare without context, leading to incomplete emotional representation.
Innovation Solution
A computer-implemented method aggregates user-specific data from various sensors to derive emotion data, smoothing outliers and transforming it into a common format for near-real-time communication between different user groups, using predefined rules and thresholds to control emotional state indicators across different locations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If individual user data from multiple sensors is collected to represent emotions, then the completeness of emotional representation is improved, but the data processing complexity and time delay increase
Solution Approach 1:
The patent segments the emotional state representation into discrete categories (positive, negative, neutral) rather than processing raw sensor data directly. This segmentation simplifies the processing complexity while maintaining accurate emotional representation by mapping complex sensor inputs to standardized emotional states.
Solution Approach 2:
The patent introduces an intermediary processing layer that aggregates sensor data from multiple sources (chat messages, emojis, audio, video) into unified emotional state indicators. This intermediary layer mediates between the complex raw data and the simplified emotional representation, reducing processing complexity while preserving accuracy.
2Speed
If real-time emotion aggregation is implemented to enable near-real-time communication, then the responsiveness is improved, but the computational resources and processing time increase
Solution Approach 1:
The patent applies partial action by aggregating emotions at strategic intervals rather than continuously processing all sensor data in real-time. This selective aggregation maintains responsiveness for near-real-time communication while reducing overall computational resource consumption by processing data only when necessary.
Solution Approach 2:
The patent changes the parameter of emotion aggregation from continuous to interval-based processing. By adjusting the aggregation time interval, the system achieves near-real-time responsiveness when needed while reducing computational resources during periods when real-time processing is not critical.
3Quantity of substance
If emotional data from diverse sensor sources is integrated, then the comprehensiveness of emotion capture is improved, but the data standardization and comparability decrease
Solution Approach 1:
The patent implements universality by creating a unified emotional state indicator format that can represent emotions from multiple sensor sources (chat, emojis, audio, video) in a consistent manner. This universal format enables easy comparison and integration of data from diverse sources while maintaining their individual characteristics.
Solution Approach 2:
The patent standardizes diverse sensor data by transforming it into a common parameter space of emotional states (positive, negative, neutral). This parameter transformation enables direct comparison and integration of data from different sensor types while preserving the essential emotional information from each source.
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
Computer-implemented method and system (100) is provided for quantifying emotional states of users (1, 2, 3) of a first group (10) of users to determine control instructions for transmitting emotional state indicators associated with the first group (10) to a second group (20) of users. A stream (11) of user events is received for each of the users (1, 2, 3) of the first group (10) and the events are buffered with their respective timestamps in a user event data structure (110). Each user event corresponds to a user action of a particular action type. After sorting (120), the user events (11f) are aggregated (130) during a current aggregation time interval into corresponding user specific action vectors (12). A transformation function (140) is applied to the user specific action vectors to obtain respective user specific emotion vectors (13). A current emotion score vector (14) is computed (150) for each user (1, 2, 3) of the first group (10) as quantification of the respective emotional states. A total current emotion score matrix (15) is derived (160) for all users (1, 2, 3), and control instructions (16) are computed (170) based on the current emotion score matrix values in accordance with predefined control rules.