Abstract: Techniques for projecting household-level viewing events are described herein. Population data may be accessed including classes of a plurality of demographic attributes for households in a market. Representative household units (RHUs) may be generated, and the RHUs may be assigned a class for each of the demographic attributes and a quota based on the demographic attributes of a plurality of panelist households. Each of the panelist households may be assigned to one of the RHUs based on at least one panelist classes matching the classes for respective demographic attributes of the RHU, and the number of matching panelist households assigned to each of the RHU may be based on the quota. Panelist viewing data representing viewing events associated with the panelist household may be accessed. A report may be generated with the classes of the RHUs and the panelist viewing data of the assigned panelist households.

Abstract: A method includes receiving audio data from a microphone of a device associated with a user. The audio data includes audio received by the microphone from a first source and from a second source. The audio data is correlated with a first audio signature and a second audio signature. Then, based on the correlation of the audio data with the first audio signature, first content broadcast from the first source is identified. Second content broadcast from the second source is also identified based on the correlation of the audio data with the second audio signature. It is then determined that the device is closer to the first source than the second source based on audio qualities and/or temporal aspects of the audio data. The first content is associated with the user based on the determination that the device is closer to the first source.

Abstract: Techniques for projecting household-level viewing events are described herein. Population data may be accessed including classes of a plurality of demographic attributes for households in a market. Representative household units (RHUs) may be generated, and the RHUs may be assigned a class for each of the demographic attributes and a quota based on the demographic attributes of a plurality of panelist households. Each of the panelist households may be assigned to one of the RHUs based on at least one panelist classes matching the classes for respective demographic attributes of the RHU, and the number of matching panelist households assigned to each of the RHU may be based on the quota. Panelist viewing data representing viewing events associated with the panelist household may be accessed. A report may be generated with the classes of the RHUs and the panelist viewing data of the assigned panelist households.

Abstract: A method includes receiving audio data from a microphone of a device associated with a user. The audio data includes audio received by the microphone from a first source and from a second source. The audio data is correlated with a first audio signature and a second audio signature. Then, based on the correlation of the audio data with the first audio signature, first content broadcast from the first source is identified. Second content broadcast from the second source is also identified based on the correlation of the audio data with the second audio signature. It is then determined that the device is closer to the first source than the second source based on audio qualities and/or temporal aspects of the audio data. The first content is associated with the user based on the determination that the device is closer to the first source.

Abstract: Geographic identifiers and television network affiliate data may be received. A primary local affiliate station for each of the plurality of national television networks may be determined for each geographic identifier. The geographic identifiers that have the same primary local affiliate for each of the plurality of national television networks may be grouped together to form a first plurality of markets. The markets from the first plurality of markets that have the same primary local affiliate for a first subset of the plurality of national television networks may be merged together, resulting in a second, smaller plurality of markets. Each of the geographic identifiers may be assigned to a market from the second plurality of markets, and a report indicating the second plurality of markets may be output.

Abstract: Predict whether active viewability is taking place and/or the likelihood that active viewability will be taking place in the future is described. Historical viewing data may be obtained. One or more probability distribution functions may be generated based on the historical viewing data. One or more survival curves may be determined based on the one or more probability distribution functions. Current viewing data may be obtained. Whether viewability is active in at least one of a current time or a specified future time may be predicted based on the one or more probability distribution functions and the current viewing data. Alternatively, this prediction may be performed via a machine learning model trained on the historical viewing data. Whether to perform a function may be determined based on the prediction.

Abstract: Techniques for projecting household-level viewing events are described herein. Population data may be accessed including classes of a plurality of demographic attributes for households in a market. Representative household units (RHUs) may be generated, and the RHUs may be assigned a class for each of the demographic attributes and a quota based on the demographic attributes of a plurality of panelist households. Each of the panelist households may be assigned to one of the RHUs based on at least one panelist classes matching the classes for respective demographic attributes of the RHU, and the number of matching panelist households assigned to each of the RHU may be based on the quota. Panelist viewing data representing viewing events associated with the panelist household may be accessed. A report may be generated with the classes of the RHUs and the panelist viewing data of the assigned panelist households.

Abstract: A method includes receiving audio data from a microphone of a device associated with a user. The audio data includes audio received by the microphone from a first source and from a second source. The audio data is correlated with a first audio signature and a second audio signature. Then, based on the correlation of the audio data with the first audio signature, first content broadcast from the first source is identified. Second content broadcast from the second source is also identified based on the correlation of the audio data with the second audio signature. It is then determined that the device is closer to the first source than the second source based on audio qualities and/or temporal aspects of the audio data. The first content is associated with the user based on the determination that the device is closer to the first source.

Abstract: A computer system may include at least one processor and at least one memory storing instructions that, when executed, cause the at least one processor to perform a process. The process may include receiving audio data from a user device, and accessing content data including at least one audio signature associated with video content. The process may also include correlating the audio data with the at least one audio signature and identifying recognized video content based on the correlation of the audio data with the at least one audio. The process may also include receiving tuning data including content being presented on a display component. The process may further include correlating the recognized video content with the tuning data, determining viewed video content based on the correlation of the recognized video content with the tuning data, and storing the viewed video content in a user array.

Abstract: A computer system may include at least one processor and at least one memory storing instructions that, when executed, cause the at least one processor to perform a process. The process may include receiving audio data from a user device, and accessing content data including at least one audio signature associated with video content. The process may also include correlating the audio data with the at least one audio signature and identifying recognized video content based on the correlation of the audio data with the at least one audio. The process may also include receiving tuning data including content being presented on a display component. The process may further include correlating the recognized video content with the tuning data, determining viewed video content based on the correlation of the recognized video content with the tuning data, and storing the viewed video content in a user array.

Abstract: Techniques for projecting household-level viewing events are described herein. Population data may be accessed including classes of a plurality of demographic attributes for households in a market. Representative household units (RHUs) may be generated, and the RHUs may be assigned a class for each of the demographic attributes and a quota based on the demographic attributes of a plurality of panelist households. Each of the panelist households may be assigned to one of the RHUs based on at least one panelist classes matching the classes for respective demographic attributes of the RHU, and the number of matching panelist households assigned to each of the RHU may be based on the quota. Panelist viewing data representing viewing events associated with the panelist household may be accessed. A report may be generated with the classes of the RHUs and the panelist viewing data of the assigned panelist households.

Abstract: Techniques for projecting household-level viewing events are described herein. Population data may be accessed including classes of a plurality of demographic attributes for households in a market. Representative household units (RHUs) may be generated, and the RHUs may be assigned a class for each of the demographic attributes and a quota based on the demographic attributes of a plurality of panelist households. Each of the panelist households may be assigned to one of the RHUs based on at least one panelist classes matching the classes for respective demographic attributes of the RHU, and the number of matching panelist households assigned to each of the RHU may be based on the quota. Panelist viewing data representing viewing events associated with the panelist household may be accessed. A report may be generated with the classes of the RHUs and the panelist viewing data of the assigned panelist households.

Abstract: Content reaction evaluation and display systems and methods. Through the present invention, a user can easily identify how content changes impact content reactions. The present invention preferably includes a content presentation region, which allows a user to experience the content, and a content reaction display region, which allows a user to view content reactions as the content is experienced. A preferred embodiment of the present invention uses content reactions collected from set-top box event data, viewership logs, and other such data to generate the content reaction display. A preferred embodiment of the present invention also analyzes content reaction data to determine content ratings, content market share, and other such data and can present such data to the user along with the content reaction information.

Abstract: A method of creating new content based on previously experienced content and content ratings, in which content attributes are obtained and analyzed against set-top box events collected as the content is experienced. Analysis includes determining effects of various content attributes on content ratings, content attribute order on content ratings, and determining a preferred content attribute set and content attribute presentation order. Also taught is a system and method of predicting future events given a proposed dataset, in which past events are monitored and correlated with a proposed dataset sharing at least one attribute with, and having a substantially similar structure to, the past events, and the results of the correlation are reported as a prediction of future events.

Abstract: A system and method for dynamically determining the demographic identity of an individual operating a set-top box, is disclosed which may include monitoring set top-box events for a plurality of set-top boxes, correlating set-top box events with demographic characteristics, applying with a computer inverse demographic matrix calculation techniques to determine probabilities for demographic characteristic and set-top box event dataset correlations without knowing individual-specific demographic information pertaining to the set-top box event dataset, ascribing demographic characteristic probabilities to each set-top box over time based on observed set-top box events and their relationship to such inverse demographic matrix probabilities, evaluating such ascribed demographic characteristic probabilities over time through statistical analysis, fining probabilities ascribed to demographic characteristics to statistically determine the most likely set of constant dataset possibilities for each set-top box, and fit

Abstract: The invention concerns a computerized method of invalidating set-top box events. The method may include monitoring set-top box events, storing the set-top box events in a first array, calculating a first trend in the first array of set-top box events, invalidating the set-top box events which are one or more statistical outliers from the first trend, storing the invalidated set-top box events in a second array, and calculating a second trend in the second array of invaidated set-top box events, wherein invalidated set-top box events are revalidated and new set-top box event categories to be ignored are identified based on the second trend.

Abstract: A system and method for using inverse mathematical principles in the analysis of compatible datasets so that correlations and trends within and between said datasets can be uncovered. The present invention is tailored to the analysis of datasets that are extremely large; result from passive, privacy-secure, or anonymous, data collection; and are relatively unbiased. Correlations and trends uncovered by such analysis can be further examined by data mining and prediction portions of the present invention, which uncover and make use of interrelated rules that determine data structures. An embodiment directed toward analysis of television viewership and marketing data that does this while still respecting privacy concerns is disclosed.

Abstract: The invention concerns a method of determining the effect of content attributes on content ratings. The method may include obtaining content attributes, recording set-top box events as content is experienced without knowing individual-specific demographic information, correlating set-top box events to content attributes, and analyzing the correlations of set-top box events to content attributes over time to estimate the effect of content attributes on content ratings.

Abstract: Content reaction evaluation and display systems and methods. Through the present invention, a user can easily identify how content changes impact content reactions. The present invention preferably includes a content presentation region, which allows a user to experience the content, and a content reaction display region, which allows a user to view content reactions as the content is experienced. A preferred embodiment of the present invention uses content reactions collected from set-top box event data, viewership logs, and other such data to generate the content reaction display. A preferred embodiment of the present invention also analyzes content reaction data to determine content ratings, content market share, and other such data and can present such data to the user along with the content reaction information.

Abstract: A system and method for using inverse mathematical principles in the analysis of compatible datasets so that correlations and trends within and between said datasets can be uncovered. The present invention is tailored to the analysis of datasets that are extremely large; result from passive, privacy-secure, or anonymous, data collection; and are relatively unbiased. Correlations and trends uncovered by such analysis can be further examined by data mining and prediction portions of the present invention, which uncover and make use of interrelated rules that determine data structures. An embodiment directed toward analysis of television viewership and marketing data that does this while still respecting privacy concerns is disclosed. In a preferred embodiment, a satellite, internet, cable, or other content provider can provide a viewer with a set-top box which may be specially instrumented to allow monitoring, recording, and transmission of set-top box events.