Back to results
US 11,893,603 B1Granted
Interactive, personalized advertising
AssigneeAmazon Technologies, Inc.
InventorsGregory Michael Hart, Ian W. Freed
Life of this patent
Estimating the term…
Abstract
Techniques for selecting and providing highly targeted, interactive advertisements in a personalized manner. These advertisements may be audio-only advertisements, video-only advertisements, or advertisements that include both audio and video. As described below, advertisements may be selected and/or generated for a particular user based on an array of factors, including the user's interactions with multiple different client devices (e.g., a tablet computing device, a voice-controlled device, a television etc.), as well as additional behavior of the user. In some instances, the client devices may include a voice-controlled device that the user interacts with via voice commands and that provides audible content for output to the user.
Claims22
A method comprising:
- under control of one or more remote computing systems configured with executable instructions,
- receiving, via a communication network, first media content from a first device in an environment that includes a user and a second device, wherein the first device is a voice-controlled device, the second device includes a display, and the first media content represents first speech captured by the first device;
- performing speech recognition on the first media content to identify an item that is referenced in the first speech;
- determining a first location associated with the first device;
- determining a second location associated with the second device;
- determining that a first format of first previous media content to which a first user response was received is an audio-content format, the first user response received from the first device;
- determining that a second format of second previous media content to which a second user response was received is a video-content format, the second user response received from the second device;
- receiving second media content from the first device, based at least in part on sound associated with a program being output by a third device;
- analyzing the second media content to identify the program;
- selecting at least one of third media content or fourth media content to output based at least on part on the program and the item;
- selecting, based at least in part on the first location, the determining that the first format of the first previous media content to which the first user response was received is the audio-content format, and the first user response including a first online purchase request associated with a first previous item identified by the first previous media content, the first device to receive the third media content in the audio-content format;
- selecting, based at least in part on the second location, the determining that the second format of the second previous media content to which the second user response was received is the video-content format, and the second user response including a second online purchase request associated with a second previous item identified by the second previous media content, the second device to receive the fourth media content in the video-content format;
- sending, via the communication network, to the first device and based at least in part on the selecting the first device, the third media content in the audio-content format;
- sending, via the communication network, to the second device and based at least in part on the selecting the second device, the fourth media content in the video-content format;
- receiving, via the communication network and from the first device, fifth media content in the audio-content format representing second speech;
- determining that at least a portion of the fifth media content in the audio-content format corresponds to a predefined phrase;
- and
- based at least in part on the determining that the at least the portion of the fifth media content corresponds to the predefined phrase, determining a request to acquire the item.
15 more elements
A system comprising:
- one or more processors;
- and
- one or more computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
- performing speech recognition on first media content to identify an item referenced in the first media content;
- determining a first location of a first device being a voice-controlled device;
- determining a second location of a second device including a display;
- determining that a first format of first previous media content to which a first user response was received is an audio-content format, the first user response received from the first device;
- determining that a second format of second previous media content to which a second user response was received is a video-content format, the second user response received from the second device;
- receiving second media content from the first device, based at least in part on sound associated with a program being output by a third device;
- analyzing the second media content to identify the program;
- selecting at least one of third media content or fourth media content to output based at least on part on the program and the item;
- selecting, based at least in part on the first location, the determining that the first format of the first previous media content to which the first user response was received is the audio-content format, and the first user response including a first online purchase request associated with a first previous item identified by the first previous media content, the first device to receive the third media content in the audio-content format;
- selecting, based at least in part on the second location, the determining that the second format of the second previous media content to which the second user response was received is the video-content format, and the second user response including a second online purchase request associated with a second previous item identified by the second previous media content, the second device to receive the fourth media content in the video-content format;
- sending, to the first device and based at least in part on the selecting the first device, the third media content in the audio-content format;
- sending, to the second device, and based at least in part on the selecting the second device, the fourth media content in the video-content format;
- and
- receiving, from the first device, fifth media content including a request identifying the item.
14 more elements
A method comprising:
- storing data indicative of activity of a user across client devices including a voice-controlled device configured to accept voice commands from the user;
- receiving first media content identifying an item, based at least in part on the activity;
- determining a first location of a first device being the voice-controlled device;
- determining a second location of a second device being a mobile computing device that includes a display;
- determining that a first format of first previous media content to which a first user response was received is an audio-content format, the first user response received from the first device;
- determining that a second format of second previous media content to which a second user response was received is a video-content format, the second user response received from the second device;
- receiving second media content from the first device, based at least in part on sound associated with a program being output by a third device;
- analyzing the second media content to identify the program;
- selecting at least one of third media content or fourth media content to output based at least on part on the program and the item;
- selecting, by one or more remote computing systems, and based at least in part on the first location, the determining that the first format of the first previous media content to which the first user response was received is the audio-content format, and the first user response including a first online purchase request associated with a first previous item identified by the first previous media content, the first device to receive the third media content in the audio-content format;
- selecting, by the one or more remote computing systems, and based at least in part on the second location, the determining that the second format of the second previous media content to which the second user response was received is the video-content format, and the second user response including a second online purchase request associated with a second previous item identified by the second previous media content, the second device to receive the fourth media content in the video-content format;
- sending, to the first device and based at least in part on the selecting the first device, the third media content in the audio-content format;
- sending, to the second device and based at least in part on the selecting the second device, the fourth media content in the video-content format;
- receiving, from the first device, fifth media content in the audio-content format corresponding to a response to the third media content, the response including a first request received from the user;
- performing speech recognition on the fifth media content to identify the item being referenced in the first request;
- and
- sending a second request to the first device, the second request comprising a request to authorize acquisition of the item.
14 more elements
Dependencies are inferred from the claim text.