Audience Analytics via User Input Pattern Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current audience analytics methods are costly and inefficient due to small sample sizes, especially with the fragmentation of audiences across multiple media platforms, and lack accurate, passive methods for collecting demographic information, leading to unreliable data and legal constraints on using personally identifiable information.
Innovation Solution
A system that uses clickstream algorithms, neural networks, Bayes classifiers, and affinity-day part algorithms to generate audience analytics by analyzing user input patterns and combining them with demographics, allowing for passive and anonymous data collection and targeted content delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional audience measurement methods (people meters, paper diaries) are used, then data collection is possible, but the expense increases and sample sizes become too small to produce statistically significant results due to audience fragmentation
Solution Approach 1:
The patent uses digital copies of viewing data from multiple sources (set-top boxes, web browsers, mobile devices) to create a comprehensive audience profile. Instead of requiring physical presence of many individuals, the system aggregates and analyzes digital copies of viewing patterns, search queries, and content interactions to derive statistically significant audience analytics without needing large manual samples
Solution Approach 2:
The system employs a universal data collection framework that works across multiple platforms and devices simultaneously. The same analytical methodology processes data from television set-top boxes, web browsers, mobile applications, and other content delivery channels, enabling the system to capture audience behavior across fragmented media landscapes with a single unified approach
2Measurement precision
If larger sample sizes are used to overcome limitations, then measurement accuracy improves, but the cost of data collection increases significantly
Solution Approach 1:
The system leverages data that content delivery systems and service providers already collect and store as part of their normal operations. Viewing logs, search histories, and interaction data are generated automatically by the systems themselves without requiring additional manual data collection infrastructure or participant compensation, thereby reducing data collection costs while maintaining measurement accuracy
Solution Approach 2:
The patent merges and aggregates data from multiple existing data sources (set-top box logs, web browsing data, mobile device interactions, and other content consumption records) into a unified audience analytics platform. By combining these pre-existing data streams, the system achieves comprehensive measurement coverage without the need to create separate expensive data collection systems for each source
3Ease of manufacture
If passive data collection methods are used to reduce cost, then data gathering becomes more affordable, but reliability of data becomes suspect due to lack of verification
Solution Approach 1:
The system incorporates feedback mechanisms where users can verify and correct their profile information, and where the system provides feedback about data accuracy and completeness. User profiles are continuously refined based on actual viewing behavior patterns, allowing the system to detect and correct inconsistencies in the data, thereby maintaining high reliability while using passive collection methods
Solution Approach 2:
The system performs preliminary actions by pre-validating data quality and completeness before analysis. Profile verification steps, data consistency checks, and quality assurance procedures are built into the data collection and processing pipeline, ensuring that only reliable data is used for analytics while maintaining cost-effective passive collection approaches
4Measurement precision
If personally identifiable information is collected to improve data accuracy, then measurement precision improves, but legal constraints limit how MSOs can utilize the information
Solution Approach 1:
The system extracts and analyzes only the necessary demographic and viewing pattern information from user data without retaining or utilizing personally identifiable information. By extracting aggregate viewing patterns, content preferences, and demographic proxies while stripping out individual identifiers, the system achieves accurate audience analytics that comply with privacy regulations and legal constraints on PII utilization
Solution Approach 2:
The system uses intermediary data representations such as anonymized user profiles, aggregated viewing patterns, and synthesized audience segments that mediate between raw personal data and analytical outputs. These intermediary structures enable precise audience measurement and targeted content delivery while maintaining privacy protection and legal compliance by preventing direct access to or misuse of personally identifiable information
Data Source
AI summary
The present invention is directed to generating audience analytics that includes providing a database containing a plurality of user input pattern profiles representing the group of users of terminal device, in which each user of the group is associated with one of the plurality of user input pattern profiles. A clickstream algorithm, tracking algorithm, neural network, Bayes classifier algorithm, or affinity-day part algorithm can be used to generate the user input pattern profiles. A user input pattern is detected based upon use of the terminal device by the current user and the user input pattern of the current user is dynamically matched with one of the user input pattern profiles contained in the database. The current user is identified based upon dynamic matching of the user input pattern generated by the current user with one of the user input pattern profiles. The present invention processes each user input pattern profile to identify a demographic type. A plurality of biometric behavior models are employed to identify a unique demographic type. Each user input pattern profile is compared against the plurality of biometric behavior models to match each user input pattern profile with one of the biometric behavior models such that each user input pattern profile is correlated with one demographic type. Audience analytics are then based upon the identified demographic types.