摘要:
A method for generating a recommendation is provided. The method includes the steps of: receiving at least one of a negative and positive example from one or more other users; and determining a recommendation for a user based on at least one of the negative and positive examples. The method can further include the step of generating a user profile for the user based on previous behavior of the user, in which case the determining step can include determining the recommendation based on the negative example and the user profile. The determining step can also include the step of determining the recommendation based on both of the negative and positive examples.
摘要:
A method for inserting replacement commercials into a data stream is provided. The method including: receiving the data stream; detecting at least one commercial in the data stream; determining a characteristic of program content at least prior to the at least one commercial; and replacing the at least one commercial in the data stream with a replacement commercial which is selected based at least in part on the determining.
摘要:
A method for generating a recommendation for a user is provided. The method includes: identifying a first group of other users, the first group having a plurality of first individuals associated with user preferences and/or user profiles that are considered positive influences in generating a recommendation; and generating the recommendation for the user based on the user preferences and/or user profiles of the first individuals. The method can further include: identifying a second group of other users, the second group having a plurality of second individuals associated with user preferences and/or user profiles that are considered negative influences in generating a recommendation; where the generating of the recommendation is further based on the user preferences and/or user profiles of the second individuals.
摘要:
A method for displaying close-captioned text (116) associated with video is provided. The method including: determining a position on a portion of the video for display of the close-captioned text; detecting one or more attributes of the video surrounding the position; and adjusting one or more attributes of the close-captioned text based on the detected one or more attributes of the video. The method can further include displaying the close-captioned text in the portion of the video with the adjusted one or more attributes. The one or more attributes of the video surrounding the position can be selected from a list consisting of a brightness, a contrast, a color, and a content. The one or more attributes of the close-captioned text can be selected from a group consisting of a brightness, a contrast, a color, and a degree of transparency.
摘要:
Commercials are recommended for insertion into audio and/or video programs. A two-step linking between the user (205) and a set of commercials (260, 262, 264, 266) is provided. A preference score indicates how much the user likes each of the programs (210, 212, 214, 216, 218). This can be achieved, e.g., using a program recommender (160). A commercial classifier (170) uses the advertiser's knowledge to provide a correlation factor that indicates an effectiveness of a commercial relative to a program. An effectiveness metric (E) may be obtained for each commercial that indicates the effectiveness of the commercial relative to the specific user by summing, over each program, a product of the preference score and the correlation factor.
摘要:
Commercials (200) such as television commercials are augmented by obtaining additional information (300) regarding an advertised product or service from a remote server (182, 184, 192, 194, 195) via a computer network (180) such as the Internet. Commercials are identified and descriptive information is extracted (170). The descriptive information may indicate, e.g., the type of commercial. A user provides preferences (400, 500) regarding commercials via an interface. The preferences may indicate a desired level of detail (500) for the additional information. For commercials whose descriptive information corresponds with the user preference, the computer network is searched to located additional information, e.g., in the form of a web page or link (300). The additional information may relate to promotions, availability, and specifications of an advertised product or service.
摘要:
A method for inserting replacement commercials (7-10) into a data stream (100) is provided where the data stream has program (A, B, C) and commercial (1, 2) portions. The method including: detecting one or more of the commercial portions of the data stream; and replacing the detected one or more commercial portions with either more or less of the replacement commercial portions.
摘要:
Extracting and processing video content encoded in a rendered color space to be emulated by an ambient light source, comprising extracting dominant color information from a video signal and transforming the color information through unrendered color space using tristimulus primary matrices to form a second rendered color space for ambient distribution. Steps include quantizing the rendered color space to form an assigned color distribution, such as by reducing possible color states, or binning to form superpixels; and selecting a dominant color using a mode, mean, median, or weighted average of pixel chromaticities. A color of interest can be further analyzed to produce a true dominant color, and past video frames can guide selection of dominant colors in future frames.
摘要:
An electronic programming guide (EPG) system employing a preference engine and processing system that combines explicit rule profile, history profile, and feedback profile data to generate new predictions. Television shows are presumed to be indexed by many features. These features are extracted and counted for TV shows watched (implicit profile), and for TV shows rated by the viewer (feedback profile). These profiles are straightforward to combine with suitably greater weight being given to the feedback information. In addition, explicit profiles can make recommendations that stand alone or may be used to modify recommendations arising from either of the two sources. The modifications may take the form of additive or multiplicative changes to the existing recommendations or some other suitable mathematical form.
摘要:
A method and apparatus are disclosed for recommending items of interest to a user based on recommendations made to one or more third parties. The recommendation scores generated by a primary recommender are influenced by recommendations generated for one or more third parties, such as a friend, colleague or trendsetter. The disclosed recommender corroborates with other recommenders when recommending items of interest and adjusts a conventional recommender score based on third party recommendations. The third party recommendations may be a top-N list of recommended items for a given third party, and may optionally include a recommendation score and an indication of whether or not the third party actually selected the recommended item. A recommender evaluates the viewing or purchase habits of a user and communicates with one or more other recommenders to determine the items that are being recommended by such other recommenders.