Abstract: A system and method for rapidly and scalably tracking attentiveness. The system includes means for collecting relevant data streams from a plurality of client devices while consumers view content, means for analysing the collected data with an AI-driven module that outputs one or more attentiveness metrics indicative of real attention, and means for synchronising the collected data with the attentiveness metrics. The system provides the ability to synchronise attentiveness metrics with other data streams to make accessible the reasons that drive attention. A digital advertising campaign can be optimised using an effectiveness data set that expresses evolution over time of an attentiveness parameter. An effect on the attentiveness parameter caused by an adjustment to a target audience can be predicted and evaluated against a campaign objective, which can be updated for predictions that yield a positive effect.

Abstract: A system and method for rapidly and scalably tracking user presence at a user device. The system determines if a person is at the device, i.e. in a position in which they are capable of interacting with content displayed on the device. The ability to track user presence may be linked with an ability to measure attentiveness. The system operates bymay collecting sensor data during the output of information by the user device and by mapping the sensor data to a presence parameter to obtain presence data indicative of variation of the presence parameter over time. The presence data is synchronised with contextual attribute data to generate an effectiveness data set that links evolution over time of the presence parameter with corresponding contextual attribute data obtained during the output of information.

Abstract: Disclosed herein is a method and system for collecting attentiveness information associated with a user's response to consuming a piece of media content. The attentiveness information is used to create an attentiveness-labelled behavioural data for the user's response. A computer-implemented attentiveness model may be generated by applying machine learning techniques to the a set of attentiveness-labelled behavioural data from multiple users. The system may comprise an annotation tool that facilitates human labelling of the user's response with attentiveness data. The resulting attentiveness model is therefore based on correlations indicative of attentiveness within the attentiveness-labelled behavioural data and/or physiological data that are based on real human cognition rather than a predetermined feature or combination of features.

Abstract: A system for capturing behavioural data in order to influence an interpersonal interaction. In one aspect, the system assists n the training of an entity whose role is to engage in such interpersonal interactions. In this aspect, the collected information may be used to judge performance, and/or adapt or improve approach to future interactions, In another aspect, the system may assist with a live interaction, i.e. to provide feedback in an ongoing conversation. The system comprises a wearable device having (i) a data collection device configured to capture behavioural data during the interpersonal interaction, (ii) a microphone configured to capture audio data during the interpersonal interaction, and (ill) an analysis module arranged to extract emotional state information and content data, and use that extracted data to evaluate an interaction quality metric to obtain an interaction score for the interpersonal interaction.

Abstract: A computer-implement method of predicting commercial effectiveness of a piece of media content without collecting data from potential consumers. The method comprises extracting an information-rich content-based parameter from the media content. The parameter may be a vector having a predetermined, e.g. fixed, dimensionality that is designed as an input in a performance data prediction engine. By enabling the same type of parameter to be extracted from media content of different types and durations, the technique proposed allows media content for which performance data has already been gathered to be used to predict performance data for new media content. The prediction can be done based on a comparison of the content-based parameters extracted from media content. Alternatively, machine learning techniques may be used to generate a model using known performance data, whereby the model can use the content-based parameter from new media content to predict performance data.

Abstract: A system and method for rapidly and scalably tracking attentiveness. The system includes means for collecting relevant data streams from a plurality of client devices while consumers view content, means for analysing the collected data with an AI-driven module that outputs one or more attentiveness metrics indicative of real attention, and means for synchronising the collected data with the attentiveness metrics. The system provides the ability to synchronise attentiveness metrics with other data streams to make accessible the reasons that drive attention. A digital advertising campaign can be optimised using an effectiveness data set that expresses evolution over time of an attentiveness parameter. An effect on the attentiveness parameter caused by an adjustment to a target audience can be predicted and evaluated against a campaign objective, which can be updated for predictions that yield a positive effect.

Abstract: Disclosed herein is a method and system for collecting attentiveness information associated with a user's response to consuming a piece of media content. The attentiveness information is used to create an attentiveness-labelled behavioural data for the user's response. A computer-implemented attentiveness model may be generated by applying machine learning techniques to the a set of attentiveness-labelled behavioural data from multiple users. The system may comprise an annotation tool that facilitates human labelling of the user's response with attentiveness data. The resulting attentiveness model is therefore based on correlations indicative of attentiveness within the attentiveness-labelled behavioural data and/or physiological data that are based on real human cognition rather than a predetermined feature or combination of features.

Abstract: Disclosed herein is a method and system for collecting attentiveness information associated with a user's response to consuming a piece of media content. The attentiveness information is used to create an attentiveness-labelled behavioural data for the user's response. A computer-implemented attentiveness model may be generated by applying machine learning techniques to the a set of attentiveness-labelled behavioural data from multiple users. The system may comprise an annotation tool that facilitates human labelling of the user's response with attentiveness data. The resulting attentiveness model is therefore based on correlations indicative of attentiveness within the attentiveness-labelled behavioural data and/or physiological data that are based on real human cognition rather than a predetermined feature or combination of features.

Abstract: Embodiments of the present method comprise activating a data recording component on the computing device to receive information relating to the environment of the computer user and executing a quality check module in the computing device operative to analyse the environment of the computer user. The quality check module performs the steps of: assessing a received signal from the data recording component against a predetermined quality metric to ascertain if an informational content of the received signal meets a predetermined minimum quality to permit computer user behavioural data to be collected therefrom, determining and executing a responsive action where the received signal does not satisfy the quality metric, and initiating a computer user behavioural data collection process to computer user collect behavioural data during the interaction between the computer user and the computing device where the received signal satisfies the quality metric.

Abstract: Disclosed herein is a method and system for collecting attentiveness information associated with a user's response to consuming a piece of media content. The attentiveness information is used to create an attentiveness-labelled behavioural data for the user's response. A computer-implemented attentiveness model may be generated by applying machine learning techniques to the a set of attentiveness-labelled behavioural data from multiple users. The system may comprise an annotation tool that facilitates human labelling of the user's response with attentiveness data. The resulting attentiveness model is therefore based on correlations indicative of attentiveness within the attentiveness-labelled behavioural data and/or physiological data that are based on real human cognition rather than a predetermined feature or combination of features.

Abstract: A computer-implemented system in which information is obtained form a user using an automated (i.e. non-human, computerised) interface that is arranged to dynamically adapt questioning based on received feedback from the user. The automated interface may comprise: (i) an agent for extracting information (e.g. meaning, sentiment, etc.) from feedback information from the user and using it to determine a direction for further questioning, and (ii) an agent for controlling the manner in which the further questioning is expressed to the user. The interface may be embodiment as a feedback collection manager communicatively connected over a network with a client device to receive the feedback information, wherein the feedback collection manager comprises: an AI-based topic generator module configured to generate a queiy topic; and an automated interactive question generator for directing an interactive information exchange with the client device using the generated queiy topic.

Abstract: Disclosed herein is a method and system for collecting attentiveness information associated with a user's response to consuming a piece of media content. The attentiveness information is used to create an attentiveness-labelled behavioural data for the user's response. A computer-implemented attentiveness model may be generated by applying machine learning techniques to the a set of attentiveness-labelled behavioural data from multiple users. The system may comprise an annotation tool that facilitates human labelling of the user's response with attentiveness data. The resulting attentiveness model is therefore based on correlations indicative of attentiveness within the attentiveness-labelled behavioural data and/or physiological data that are based on real human cognition rather than a predetermined feature or combination of features.

Abstract: A method of initiating and controlling computer user behavioural data (e.g., emotional state information) collection and processing within the structure of a video ad response provides an analysis of video ad effectiveness as a result of interaction with the computer user. A behavioural data collection and processing module is caused to nut by the execution of a Video Ad Standard Template (VAST) compliant video ad response in a video player. The data collection and processing module may be obtained by calling a resource identifier contained in the video ad response, or by providing an executable application within the served video ad response itself. In more particular methods according to the invention, processing of collected data is managed so as to improve the efficiency of media playback at the client computer and communications with remote servers.

Abstract: Embodiments of the invention provide analytics in regard to behavioural data for improved computer-resource utilization, more particularly, in connection with a computer-implemented method of using behavioural data collected for a user (and in particular emotional response data obtained from facial images of the user) to generate or otherwise control ad inventory or ad display on the fly.

Abstract: Disclosed herein is a method and system for collecting attentiveness information associated with a user's response to consuming a piece of media content. The attentiveness information is used to create an attentiveness-labelled behavioural data for the user's response. A computer-implemented attentiveness model may be generated by applying machine learning techniques to the a set of attentiveness-labelled behavioural data from multiple users. The system may comprise an annotation tool that facilitates human labelling of the user's response with attentiveness data. The resulting attentiveness model is therefore based on correlations indicative of attentiveness within the attentiveness-labelled behavioural data and/or physiological data that are based on real human cognition rather than a predetermined feature or combination of features.

Abstract: Embodiments of the invention provide a computer-implemented method of collecting computer user behavioral data during an interaction between a computer user and web-based content accessible via a computing device. A behavioral data collection activation script is provided, which may be provided within executable code of a webpage or media player executable on a webpage. The script runs during loading of the webpage or media player or upon execution of a specific operation or action within the webpage or media player. The script triggers activation of a data recording component on the computing device via a browser-based application programming interface (API), and triggers initiation of a behavioral data collection application on the computing device, which receives information from the data recording component as an input.

Abstract: Embodiments of the invention comprise advanced techniques for automated analysis and benchmarking of media based on behavioral data, including emotional state information, collected for a plurality of computer users exposed to that media. According to embodiments, a comparative analysis can be performed relative to other media content, in which case a rapid objective assessment tool can be provided. Alternatively or additionally, the comparative analysis can be relative to the media under test itself, in which case the technique can provide immediate feedback, e.g., on whether the media has had the intended impact on its target audience. Comparative analysis can further assist to identify audience sectors where an impact (positive or negative) is observed.

Abstract: A method of initiating and controlling computer user behavioural data (e.g., emotional state information) collection and processing within the structure of a video ad response provides an analysis of video ad effectiveness as a result of interaction with the computer user. A behavioural data collection and processing module is caused to nut by the execution of a Video Ad Standard Template (VAST) compliant video ad response in a video player. The data collection and processing module may be obtained by calling a resource identifier contained in the video ad response, or by providing an executable application within the served video ad response itself. In more particular methods according to the invention, processing of collected data is managed so as to improve the efficiency of media playback at the client computer and communications with remote servers.

Abstract: A method of initiating and controlling computer user behavioural data (e.g., emotional state information) collection and processing within the structure of a video ad response provides an analysis of video ad effectiveness as a result of interaction with the computer user. A behavioural data collection and processing module is caused to run by the execution of a Video Ad Standard Template (VAST) compliant video ad response in a video player. The data collection and processing module may be obtained by calling a resource identifier contained in the video ad response, or by providing an executable application within the served video ad response itself. In more particular methods according to the invention, processing of collected data is managed so as to improve the efficiency of media playback at the client computer and communications with remote servers.

Abstract: A computer-implement method of predicting commercial effectiveness of a piece of media content without collecting data from potential consumers. The method comprises extracting an information-rich content-based parameter from the media content. The parameter may be a vector having a predetermined, e.g. fixed, dimensionality that is designed as an input in a performance data prediction engine. By enabling the same type of parameter to be extracted from media content of different types and durations, the technique proposed allows media content for which performance data has already been gathered to be used to predict performance data for media content. The prediction can be done based on a comparison of the content-based parameters extracted from media content. Alternatively, machine learning techniques may be used to generate a model using known performance data, whereby the model can use the content-based parameter from new media content to predict performance data.