Abstract:
Provided are an apparatus and method for generating a narrative for lifestyle recognition. The apparatus for generating a narrative for lifestyle recognition includes an input unit configured to collect basic data of narrative generation for the lifestyle recognition, a memory configured to store a program for generating a user's lifestyle narrative using the basic data, and a processor configured to execute the program, in which the processor performs a causal relationship analysis on a cause of a mind state and a result of the mind state using the lifestyle narrative.
Abstract:
Disclosed is technology for providing a proper UI/UX through various devices or services when occurrence of registered concerned context is predicted or recognized in order to predict or recognize the circumstances that require attention or emotion control with regard to a change in his/her biological information With this, a user designates his/her own biological information range or emotional state with regard to circumstances which catch his/her attention, and registers concerned context by selectively designating attributes of circumstantial elements. Further, a user registers feedback desired to be given and an external device/service desired to interface with when the occurrence of the concerned context is predicted or recognized. According to the attributes of the circumstances designated in the registered concerned context, points in time for collecting and managing UX data are automatically determined, thereby processing and managing the UX data as useful information.
Abstract:
Provided is a method of analyzing multimodal user experience data for providing a psychological stability service, the method including: receiving multimodal user experience data collected on the basis of a user device that is predetermined; analyzing an association between the collected multimodal user experience data to identify whether a user is in a stressful situation; when the stressful situation is identified, analyzing a frequency pattern of the stressful situation of the user; recognizing stress context information about the stressful situation occurring to the user on the basis of the frequency pattern of the stressful situation; and providing the user device with a preemptive psychological stability service on the basis of the stress context information corresponding to the stressful situation.
Abstract:
Provided is an apparatus for refining data and improving the performance of a behavior recognition model by reflecting time-series characteristics of a behavior. The apparatus includes: a data pre-processing unit configured to receive training data and real-time data as input, identify a missing value of sensor data, and interpolate the sensor data; a behavior recognition unit configured to, through a behavior recognition model, generate a behavior recognition classification result for the preprocessed real-time data; a data refinement unit configured to correct the behavior recognition classification result to generate a refined dataset; a learning model update unit configured to analyze a similarity of the refined dataset and, based on a result of the analysis, perform learning to generate the behavior recognition model; and an information output unit configured to express a corrected behavior recognition result to a user.
Abstract:
The present invention relates to a method and apparatus for providing an emotion-adaptive user interface (UI) on the basis of an affective computing service, in which the provided service is configured with at least one of a service operation condition, a service end condition, and an emotion-adaptive UI service type on the basis of purpose information of the service, and the detailed pattern is changed and provided on the basis of the purpose information and the usefulness information of the service.
Abstract:
Technology for a method of detecting a user hand by a user hand detecting device. The method according to an aspect of the present invention includes extracting a first mask image from a depth image in which the user hand is imaged; extracting a second mask image having a preset skin color value among regions corresponding to the first mask image in a color image in which the user hand is imaged; generating a skin color value histogram model in a color space different from a region of the color image corresponding to a color region of the second mask image; generating a skin color probability image of the different color space from the color image using the skin color value histogram model and an algorithm for detecting a skin color region; and combining the skin color probability image with the second mask image and detecting the user's hand region.
Abstract:
A method of connecting a call by a recipient terminal includes the recipient terminal receiving a call from a caller terminal, and displaying the purpose of the call, input by a caller and included in the call, on a call reception indication screen.