Determining User Interest Through Detected Physical Indicia

In accordance with some implementations, a method for determining viewer interest is disclosed. The method is performed on a client system having one or more processors, a camera, and memory storing programs for execution. The electronic device captures analyzes captured visual data to detect physical indicia of interest associated with a user of the client system. The electronic device then determines a level of interest of the user with respect to media content being displayed in the proximity of the users based on the detected physical indicia of interest. The electronic device then sends the determined level of interest to a server system; the server system including an interest profile for the user of the client system. The electronic device then receives, from the server system, recommendations for additional media content for the user based, at least in part on, the determined level of interest.

Skip to: Description  ·  Claims  · Patent History  ·  Patent History
Description
TECHNICAL FIELD

The disclosed implementations relate to the field of displaying media content generally and in particular to using determining a user's interest in displayed media.

BACKGROUND

There are currently many avenues for users to consume media content. In addition to traditional, non-interactive avenues such traditional television, radio, or projection screens in movie theatres, new electronic devices provide additional avenues to consume media content, such as streaming content over the Internet via computers, smart phones, or tablets. Some of these additional avenues are interactive and allow users to interact with the distributors of media content. This increased interaction allows distributors or producers of media content to provide more personalized services to the consumers of the media content.

One option for producers or distributors of media content to provide personalized services is through a recommendation engine. Such engines select new media content to recommend to the user based on information known about a user. Increasing the amount of information that a recommendation engine has concerning a specific user increases the accuracy of recommendation engine to correctly recommend media content that the user will find interesting. As a result, gathering information concerning what media content a user finds interesting and what media content a user does not find interesting is important to providing a good user experience.

The new avenues for viewing media content allow additional interaction that allows media content distributors to more efficiently gather information relating to a user's interest. Generally, the user indicates interest in a piece of media content by selecting a level of interest or otherwise rating the media content. Many recommendation systems are integrated directly into media content display platforms and allow users to indicate whether or not they found a particular piece of media content interesting.

SUMMARY

In accordance with some implementations, a method for determining viewer interest is disclosed. The method is performed on a client system having one or more processors, a camera, and memory storing one or more programs for execution by the one or more processors. The client system captures visual data of a user of the client system with the camera. The client system analyzes the captured visual data to detect physical indicia of interest associated with a user of the client system. The client system then determines a level of interest of the user with respect to media content being displayed in the proximity of the users based on the detected physical indicia of interest. The client system then sends the determined level of interest to a server system which maintains an interest profile for the user of the client system. The client system then receives, from the server system, recommendations for additional media content for the user based, at least in part on, the determined level of interest.

In accordance with some implementations, a client system for determining viewer interest is disclosed. The client system has one or more processors, a camera, and memory storing one or more programs to be executed by the one or more processors. The one or more programs include instructions for capturing visual data of a user of the client system with the camera. In some implementations, the client system includes instructions for analyzing the captured visual data to detect physical indicia of interest associated with a user of the client system. The client system in some implementations may also include instructions for determining a level of interest of the user with respect to media content being displayed in the proximity of the users based on the detected physical indicia of interest. In some implementations, the client system also includes instructions for sending the determined level of interest to a server system; the server system including an interest profile for the user of the client system. In some implementations, the client system further includes instructions for receiving, from the server system, recommendations for additional media content for the user based, at least in part on, the determined level of interest.

In accordance with some implementations, a non-transitory computer readable storage medium storing one or more programs configured for execution by a client system with an associated camera is disclosed. The one or more programs also include instructions for capturing visual data of a user of the client system. The one or more programs further include instructions for analyzing the captured visual data to detect physical indicia of interest associated with a user of the client system. The one or more programs also include instructions for determining a level of interest of the user with respect to media content being displayed in the proximity of the users based on the detected physical indicia of interest. The one or more programs may also include instructions for sending the determined level of interest to a server system; the server system including an interest profile for the user of the client system. The one or more programs further include instructions for receiving, from the server system, recommendations for additional media content for the user based, at least in part on, the determined level of interest.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a block diagram illustrating a client/server environment including a client system with a display in accordance with some implementations.

FIG. 2A is a block diagram illustrating a client system in accordance with some implementations.

FIG. 2B is a block diagram of an event list received from a server system in accordance with some implementations.

FIG. 3 is a block diagram illustrating a server system in accordance with some implementations.

FIG. 4 is a flow diagram illustrating the process of using detected physical indicia of a user to determine the interest a user has in media being displayed on a display associated with a client system in accordance with some implementations.

FIG. 5A depicts an example of determining user interest through physical indicia in accordance with some implementations.

FIG. 5B depicts an example of determining user interest through physical indicia in accordance with some implementations.

FIG. 5C depicts an example of determining user interest through physical indicia in accordance with some implementations.

FIG. 6A depicts an example of determining user interest through tracking displayed objects and determining the user focus area in accordance with some implementations.

FIG. 6B depicts an example of determining user interest through tracking displayed objects and determining the user focus area in accordance with some implementations.

FIG. 6C depicts an example of determining user interest through tracking displayed objects and determining the user focus area in accordance with some implementations.

FIG. 7 is a flow diagram illustrating the process of detecting user interest based on physical indicia in accordance with some implementations.

FIG. 8 is a flow diagram illustrating the process of detecting user interest based on physical indicia in accordance with some implementations.

FIG. 9 is a flow diagram illustrating the process of detecting user interest based on physical indicia in accordance with some implementations.

Like reference numerals refer to corresponding parts throughout the drawings.

DESCRIPTION OF IMPLEMENTATIONS

In some implementations, a user of a client system views media content via the client system on either a display integrated into the client system or associated with the client system. Providers of the media content find great value in determining the user's attentiveness to the displayed media content as knowing the user's interest in media content can help media providers tailor future content or recommendations more closely to the user's interests. Accordingly, in some implementations, a user's interest in displayed media is determined by analyzing visual data of the user (such as visual data from photographs or video) for physical indicia of user interest. An advantage of such an implementation is that the user does not have to actively indicate their interest to the system.

In some implementations the client system includes the ability to detect physical indicia associated with a user. For example, the client system has access to an associated camera or a microphone. The client system then uses the camera to capture and store visual information about the user. The client system then analyzes the captured visual information for any physical indicia of interest in media content.

In some embodiments, determining physical indicia of interest includes determining the position of the eyes of the user using gaze tracking techniques. For example, the client system uses the position and orientation of each eye to determine where the user is looking relative to the display. By determining where the user is looking the client system is able to determine whether the user is focusing on the display. If the user is determined to be focusing on the display associated the client system determines on what portion of the screen the user is focusing. In some implementations, the client system then uses this information to determine a level of interest for the user associated with the media currently being displayed.

In some implementations, the physical indicia of interest determined from the visual information includes the position of a user's head. By analyzing the position of the user's head, the client system is able to estimate where the user is looking and consequently, determine whether the user is looking at the display. The client system then estimates user interest in the currently displayed media. In other implementations, the determined physical indicia of interest include the user's body lean. In other implementations the determined physical indicia of interest is a user's reaction to a visual or audio event which occurs in the media being displayed. For example, a user who physically reacts to a surprising visual or startling loud sound in a movie (e.g. by jumping or screaming) is likely more interested in the movie they are watching than a user who does not react to a loud sound in a movie.

In some implementations, an audio event includes information about a song currently playing. The information includes the beats per minute for a song (or the frequency or periodicity). The client system 102 then analyzes captured visual information to determine whether the user is moving with a periodicity (or frequency or beats per minute) that matches the periodicity of the detected song. A user moving (dancing for example) with the same frequency of a song indicates positive user engagement with the presented audio event. For example, if a song is playing alone or as part of the soundtrack of a movie users who are very engaged with the currently presented media are more likely to move in time (dance) with the music.

In some implementations, the client system sends the determined interest level to a server system for further processing, storage, and use (in a recommendation system, for example). In some implementations, the client system removes personally identifiable information before sending the interest information to the server system. In some implementations the user is able to log onto a service that tracks interest information over time and keeps an interest profile for the user.

In some implementations, the server system uses the determined interest received from the client system to increase the accuracy of recommendation systems. For example, the determined interest can be used to select specific genres, performers, or topics that the user finds interesting. In some implementations these recommendations can be presented to the user for selection. In some implementations, the client system automatically begins displaying the most highly recommended media without user interaction. In some implementations the user must select the specific media to be displayed.

FIG. 1 is a block diagram illustrating a client-server environment 100, in accordance with some implementations. The client-server environment 100 includes a client system 102 which is part of a client environment 108 and a server system 120. In some implementations, the client system 102-1 includes a display 106-1 and a camera 104-1. In some implementations, the user environment 108-2 includes a camera 104-2 and a display 106-2 associated with the client system 102-2 but not integrated into the client system 102-2. The server system 120 includes a recommendation engine 122 and a media information database 130. The communication network interface 112 may connect to any of a variety of networks, including local area networks (LAN), wide area networks (WAN), wireless networks, wired networks, the Internet, or a combination of such networks.

In accordance with some implementations, the client environment 108-1 includes a client system 102. In some implementations, the client system 102-1 includes an incorporated camera 106-1 and an incorporated display 104-1. The incorporated camera 106-1 is a camera which is included in the client system 102-1 and is able to record visual information. The incorporated display 104-1 is also included in the client system 102-1 and displays media in the vicinity of the user.

In other implementations the client environment 108-2 includes a client system 102-2, a display 104-2, which is associated with the client system 102-2 but is not integrated into the client system 102-2, and a camera 106-2, which is associated with the client system 102-2 but is not integrated into the client system 102-2. The camera 106-2 is able to capture visual data of a user in the vicinity of the media being displayed on the display 104-2 associated with client system 102-2. The associated display 104-2 is configured to display media in the vicinity of the user of the client system 102-2.

In accordance with some implementations, the client system 102 receives a list of events 114 from the server system 120. The list of events 114 received from the server system includes a list of visual or auditory events which occur during a specific piece of media. In some implementations each event in the list of events include a reference time that indicates the time at which the event occurs, a duration time for the event, and, in the case of visual events, an approximate location on the display on which the event occurs. For example, a list of a events for a movie may include the following list of events: at 11 minutes and 37 seconds a loud scream occurs and lasts for 3 seconds, at 38 minutes and 27 seconds a large explosion takes place on the left half of the screen and lasts for 15 seconds, and at 61 minutes and 10 seconds a kungfu fight occurs between two characters and lasts for 2 minutes and 17 seconds.

In accordance with some implementations, the client system 102 sends the determined interest 112 to the server system 120. The determined interest represents the client systems 102 estimation, based on physical indicia, of the level of interest of a user has in the media currently or most recently displayed in the vicinity of the user. This determined interest information may be recorded in any format suitable for gauging interest. For example, the determined interest may be represented by a numerical value between 0 and 1, where 0 represents no determined interest and 1 represents full or maximum interest. Alternatively, interest may be represented by choosing one of several distinct states. For example, interest may be represented by assigning one of three possible interest values (high interest, medium interest, or low interest) to a user and reporting this value back to the server system 120. In some implementations any variation or combination of these interest scoring systems may be used.

In accordance with some implementations, the server system 120 includes a recommendation engine 122 and a media information database 130. The recommendation engine 122 is configured to collect information concerning the interests of specific users. In some implementations, this information is collected from a plurality of sources. For example, user information can be collected by aggregating user search history data, user web navigation data, user media purchases, detected user physical indicia of interest, user self-reported interest in specific media, and any other source of user interest information. Based on the collected user interest data the recommendation engine determines specific media to recommend to the user. In some implementations, the media determined by the recommendation engine 122 automatically begins displaying on the display 104 associated with the client system 102 without waiting for user selection. In other implementations, the selected media does not begin displaying until selected by a user.

In accordance with some implementations, the media information database 130 includes specific details about specific pieces of media. For example, the media information database 130 includes the genre information, cast information, director information, event information, and other information related to specific media. The server system 120 uses this information to facilitate evaluation of potential recommendations by the recommendation engine 122. The server system 120 also uses the media information database 130 to generate a list of events 114 for a specific piece of media content being displayed on a display 104 associated with a client system 102.

FIG. 2A is a block diagram illustrating a client system 102, in accordance with some implementations. The client system 102 typically includes one or more processing units (CPU's) 202, one or more network interfaces 210, memory 212, an associated camera 106, and one or more communication buses 214 for interconnecting these components. The client system 102 includes a user interface 204. The user interface 204 includes an associated display device 104 and optionally includes an input means such as a keyboard, mouse, a touch sensitive display, or other input buttons 208. Optionally, the display device 104 includes an audio device or other information delivery device. Furthermore, some client systems use a microphone and voice recognition to supplement or replace the keyboard.

Memory 212 includes high-speed random access memory, such as DRAM, SRAM, DDR RAM or other random access solid state memory devices; and may include non-volatile memory, such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid state storage devices. Memory 212 may optionally include one or more storage devices remotely located from the CPU(s) 202. Memory 212, or alternately the non-volatile memory device(s) within memory 212, includes a non-transitory computer readable storage medium. In some implementations, memory 212 or the computer readable storage medium of memory 212 stores the following programs, modules and data structures, or a subset thereof:

    • an operating system 216 that includes procedures for handling various basic system services and for performing hardware dependent tasks;
    • a network communication module 218 that is used for connecting the client system 102 to other computers via the one or more communication network interfaces 210 (wired or wireless) and one or more communication networks, such as the Internet, other wide area networks, local area networks, metropolitan area networks, and so on;
    • a display module 220 for enabling display of media on a display 104 associated with the client system 102;
    • one or more client system 102 applications module(s) 222 for enabling the client system 102 to perform the functions offered by the client system 102, including but not limited to:
      • an image capture module 224 for using the associated camera 106 to capture visual data of a user in the vicinity of the client system 102;
      • an image analysis module 230 for analyzing the visual data captured by the camera 106 to detect physical indicia of interest of a user in the proximity of the displayed media content, including but not limited to the position of the user's eyes, the position of the user's head, the position of the user's body, and any movements made by the user;
      • an event tracking module 232 for receiving a list of events from the server system (FIG. 1, 120) and comparing the detected physical indicia of interest against the list of events received from the server system (FIG. 1, 120) to more accurately gauge the interest of the user by comparing the physical reactions of a user specific events which occur during the media;
      • an object tracking module 234 for determining the position of specific objects on the display 104 associated with the client system 102, determining the gaze position of the user by analyzing the head and eye positions of the user, determining whether, at a first time, the gaze position of the user intersects with a determined object, determining whether, at a second time, the gaze position of the user intersects a determined object, and determining whether the gaze position of the user intersects with the same object at both the first and second times; and
      • an interest determination module 236 for determining the interest a user in the vicinity of the client system 102 in media currently being displayed on the display 104 associated with the client system 102 by gathering visual information to determine physical indicia of interest and comparing the determined physical indicia of interest to a list of events received from the server system (FIG. 1, 120) or objects displayed on the display 104 associated with client system 102; and
    • a data module 240 for storing data related to the client system 102, including but not limited to:
      • visual display data 242 including data to be displayed on the display 104 associated with the client system 102, including data necessary for media to be displayed, data necessary to display a user interface to allow the user to effectively control the client system 102, and any other data needed to effectively use the associated display 104;
      • user data 244 including information concerning users of the client system 102 such as a user profile, user preferences and interests, and other information relevant to effectively providing services to the user;
      • event data 246 including data received from the server system (FIG. 1, 102) that lists audio or visual events in media which is currently displayed or will be displayed in the future on the display 104 associated with the client system 102; and
      • media data 248 including data associated with the media that is currently displayed or will be soon be displayed on the display 104 associated with the client system 102.

FIG. 2B is a block diagram of an event list 246 received from a server system (FIG. 1, 12) in accordance with some implementations. Each event list includes one or more events 250. Each event represents a specific audio or visual event that occurs during the display of a specific piece of media content.

In some implementations, an event 250 includes additional information concerning the event. In some implementations each event includes one or more of: an event ID 252, a time 254, a duration 256, an on screen location 258, and additional description 260. The time 254 included in each event 250 describes at what point relative to the beginning of the piece of media the event occurs. The time data 254 allows the client system (FIG. 1, 102) to correlate specific user indicia of interest to specific events 250. In some implementations each event 250 includes a duration that describes how long the event lasts from its start time 254. For example, a scream or surprising visual would only last a few seconds at most, while a car chase or martial arts fight scene might have a duration of a few minutes or more.

In some implementations the event data 246 further includes an on screen location 258 for visual events (such information is not necessary for audio events). The on screen location data includes coordinates indicating where on a display (FIG. 1, 104) the visual event 250 is being displayed. The client system (FIG. 1, 102) uses this information to determine whether the user is focusing on the displayed event 250. In some implementations the event data 246 further includes description information 260 that describes the event 250. In some implementations this information consists of a list of categories or descriptors which describe the event. For example, a car chase event might include categories such as car chase, BMW, high speed driving, vehicle stunts, and urban driving.

In some implementations the description information 260 includes a brief textual description of the event 250. For example the description may be “Police officers chase a suspect at high speeds through downtown Paris.” In some implementations the client system (FIG. 1, 102) uses this description information, together with gathered physical indicia information, to analyze the interest of a user more specifically. For example, the client system (FIG. 1, 102) is able to determine if a specific type or category of event is of particular interest to a user. This interest information may then be transmitted to a server system (FIG. 1, 120).

FIG. 3 is a block diagram illustrating a server system 120, in accordance with some implementations. The server system 120 typically includes one or more processing units (CPU's) 302, one or more network interfaces 304, memory 306, and one or more communication buses 308 for interconnecting these components.

Memory 306 includes high-speed random access memory, such as DRAM, SRAM, DDR RAM or other random access solid state memory devices; and may include non-volatile memory, such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid state storage devices. Memory 306 may optionally include one or more storage devices remotely located from the CPU(s) 302. Memory 306, or alternately the non-volatile memory device(s) within memory 306, includes a non-transitory computer readable storage medium. In some implementations, memory 306 or the computer readable storage medium of memory 306 stores the following programs, modules and data structures, or a subset thereof:

    • an operating system 310 that includes procedures for handling various basic system services and for performing hardware dependent tasks;
    • a network communication module 312 that is used for connecting the server system 120 to other computers via the one or more communication network interfaces 304 (wired or wireless) and one or more communication networks, such as the Internet, other wide area networks, local area networks, metropolitan area networks, and so on;
    • one or more server application module(s) 314 for enabling the server system 120 to perform the functions offered by the server system 120, including but not limited to:
      • a recommendation engine 122 for using collected user information 324 and media information database 130 to determine media of interest to a user of the client system (FIG. 2, 102) and to send a determined recommendation to the user of the client system (FIG. 2, 102);
      • a media determination module 316 for determining the media being displayed at a client system (FIG. 1, 102), wherein the media being displayed at a client system (FIG. 1, 102) is determined by receiving the identification of the media from the client system (FIG. 1, 102), analyzing the data being displayed at the display (FIG. 1, 104) associated with the client system (FIG. 1, 102), or, in the case where the media displayed at the client system (FIG. 1, 102) is being provided by the server system 120, determining the media being transmitted to the client system (FIG. 1, 102);
      • an event selection module 318 for determining a list of events to send to the client system (FIG. 1, 102) based on the media determined to be displayed on the display (FIG. 1, 104) associated with the client electronic display (FIG. 1, 102) and the information stored in the media information database 130; and
      • a data reception module 320 for receiving data from the client system (FIG. 1, 102) including interest information 326 determined by analyzing physical indicia from the user of the client system (FIG. 1, 102); and
    • one or more server data module(s) 322 for storing data related to the server system 120, including but not limited to:
      • media information database 130 including specific details about particular pieces of media, including, for example, the genre information, cast information, director information, event information, and other information related to specific media;
      • user data 324 including information concerning users of the client system (FIG. 1, 102) such as a user profile, user preferences and interests, and other information relevant to effectively providing services to the user;
      • interest data 324 including data received from the client system (FIG. 1, 102) that indicates the level of interest a user has for one or more pieces of media; and
      • media display data 328 including data for, when the server system 120 provides media data to the client system (FIG. 1, 102), displaying media content on a display.

FIG. 4 is a flow diagram illustrating the process of using detected physical indicia of a user to determine the interest a user has in media being displayed on a display (FIG. 1, 104) associated with a client system 102, in accordance with some implementations. In some implementations, the server system 120 initially sends an event list 412 to the client system 102. The event data list 246 includes information concerning visual or auditory events which occur during a specific piece of media. In some implementations each event in the list of events includes A) a reference time that indicates the time at which the event occurs, B) a duration time for the event, and, in the case of visual events, C) an approximate location on the display on which the event occurs. For example, a list of a events for a movie may include the following list of events: at 11 minutes and 37 seconds a loud scream occurs and lasts for 3 seconds, at 38 minutes and 27 seconds a large explosion takes place on the left half of the screen and lasts for 15 seconds, and at 61 minutes and 10 seconds a kungfu fight occurs between two characters and lasts for 2 minutes and 17 seconds.

In accordance with some implementations, the client system 102 receives the list of events 412 and displays media on the display (FIG. 1, 104) associated with the client system 102. The client system 102 receives visual information data 406 from an associated camera 104. In some implementations the client environment device 102 analyzes the visual information data 406 received from the camera 104 to determine whether there are any physical indicia of interest in the visual information data 406 of the user of the client system 102.

In some implementations the client system 102 also receives audio data 408 from a microphone associated with the client system 102. This audio data can then be analyzed to determine whether there are any audio indicia of interest from a user. For example, if the list of events 412 received from the server 120 includes an event which is likely to produce an auditory reaction, such as a startling or surprising character suddenly jumping onto to the screen at a tense moment. A user who is very interested in the media currently being displayed is more likely to react audibly to startling or surprisingly scary events in the media being displayed.

In some implementations the client system 102 analyzes the data received from the camera 104 and the microphone 404 to determine physical indicia of interest. For example, by analyzing the visual data received from the camera 104 to determine the position of the user's eyes and, from that information, determining the sight lines of each eye and then determine where, relative to the display, the user's gaze is focused. Based on the determined user's gaze point the client system 102 is able to estimate a user's interest in the media currently being displayed. The client system 102 is also able to estimate interest by analyzing the position of the user's head to determine generally where the user is looking, the body lean of the user, and the user's reactions to the media currently being displayed.

In some implementations, the client system 102 uses the list of events 412 received from the server system 120 to help determine a user's level of interest. The client system 102 correlates the list of events 412 with the visual data 406 to improve the ability of the client system 102 to accurately determine the user's interest in the media currently being displayed. For example, if the list of events 412 describes a large explosion at a particular point in the media, the client system 102 can specifically see whether the user has a physical reaction to the noted explosion. A user who physically reacts to specific events will be determined to be more interested in the currently displayed media than a user who does not physically react to specific events.

In accordance with some implementations, the client system transmits the determined user interest data 410 to the server system 120. The user interest data 410 includes a score or ranking representing the degree to which the user is interested in a particular piece of media. The user interest data 410 includes data identifying the media to which the interest score or ranking applies.

In accordance with some implementations the server system 120 receives the user interest data 410 and stores it for further use. In some implementations, the server system 120 uses this user interest data 410 as data for the recommendation engine (FIG. 1, 122) to more accurately predict additional media that would be of interest to a user. The user interest data 410 received from the client system 102 is obtained without having to require interaction from the user. In addition, physical indicia may indicate user interest in media to which a user is not aware or which a user would not volunteer to a recommendation engine if the information were not automatically collected. In some implementations, the received user interest data 410 is combined with other information the server system has collected about the user to make a more accurate determination regarding future recommendations. In some implementations the user is able to log into a service which has a user profile for the user already constructed. The user profile includes a more extensive record of the users previously indicated interests and other information relevant to making recommendations.

FIG. 5A depicts an example of determining user interest through physical indicia, in accordance with some implementations. In this example, the client system (FIG. 1, 102) analyzes capture visual data to determine position and rotation of a user's eyes. Based on the determined position and rotation of a user's eyes, the client system (FIG. 1, 102) determine the sight line of the eye and where that sight line intersects with a display 522 that is currently displaying media. The client system (FIG. 1, 102) maps each eye independently. In accordance with some implementations the client system (FIG. 1, 102) determines where the left eye's sight line intersects the display 522 and records the left eye gaze point (A) 504. The client system (FIG. 1, 102) determines the right eye's sight line intersects the display 522 and records the right eye gaze point (B) 506.

In accordance with some implementation the client system (FIG. 1, 102) measures the distance between the left eye gaze point (A) 504 and the right eye gaze point (B) 506. The client system (FIG. 1, 102) uses the measured distance 502 between the left and right gaze points to determine where the user's focus is located. In some implementations the client system (FIG. 1, 102) determines that the user is not focused on the displayed associated with the client system (FIG. 1, 102). For example, when the measured distance 502 between the left gaze point (504) and the right gaze point (506) is greater than a predetermined value and therefore the client system (FIG. 1, 102) is able to determine the user's focus is behind the display 522. Determining that the user's focus is behind the display 522 indicates that the user does not have high interest in the currently displayed media. In some implementations, the client system (FIG. 1, 102) determines that the user's left gaze point (504) and the right gaze point (506) do not intersect with the display (FIG. 1, 104) associated with the client system (FIG. 1, 102) and thus determines that the user is not focusing on the display (FIG. 1, 104).

FIG. 5B depicts an example of determining user interest through physical indicia, in accordance with some implementations. In this example, the client system (FIG. 1, 102) determines viewer's the left gaze point (A) 514 and the right gaze point (B) 512. In accordance with some implementations the distance between the right and left gaze points is less than a predetermined distance. When the determined distance 510 is less than a predetermined distance the client system (FIG. 1, 102) is able to determine that the user is focusing on the display 524 and to determine a focus area 508 on the display 524. The focus area 508 represents the area on the display 524 that the user is focusing on. In some implementations when the distance 510 between the left gaze point 514 and the right gaze point 512 is less than a predetermined value the client system (FIG. 1, 102) determines that the user's interest in the currently displayed media is relatively high.

FIG. 5C depicts an example of determining user interest through physical indicia, in accordance with some implementations. In this example, the client system (FIG. 1, 102) determines the left gaze point (A) 520 and the right gaze point (B) 518. In some implementations the left gaze point (A) 520 is on the right side of the right gaze point (B) 518. In this case, the client system (FIG. 1, 102) can determine that user's focus is on something in front of the screen, regardless of the distance between 516 the left gaze point 520 and the right gaze point 518. Based on this determination, the client system (FIG. 1, 102) determines that the user has relatively low interest in the currently displayed media.

In some implementations more than one user is in the vicinity of the client system (FIG. 1, 102) which is displaying media content on its associated display. In some implementations, the client system (FIG. 1, 102) will have associated profiles with each user and will measure their interest individually. This is accomplished by identifying each user, via facial recognition for example, and then tracking each individual's physical indicia of interest. In other implementations, the client system (FIG. 1, 102) does not have associated profiles associated with all the users. In this circumstance the client system (FIG. 1, 102) will identify the primary user of the client system (FIG. 1, 102) and determine the primary user's interest. The primary user may be identified by facial recognition, proximity to the client system (FIG. 1, 102), or proximity to a remote control associated with the client system (FIG. 1, 102).

In some implementations, the client system (FIG. 1, 102) does not have individual profiles for each user and cannot or has not identified a primary user. In these circumstances the client system (FIG. 1, 102) tracks the interest level for all available users and then compares the levels of interest. In accordance with a determination that all available users have comparable levels of interest, the interest levels are averaged together. In accordance with a determination that all the available users have sufficiently different levels of interest, such that no real consensus is reached, the various different levels of interest are all discarded and no level of interest is sent to the server system (FIG. 1, 120).

FIG. 6A depicts an example of determining user interest through tracking displayed objects and determining the user focus area at a first point in time, in accordance with some implementations. In this example, the client system (FIG. 1, 102) determines a list of objects that are currently displayed on the display 610-1 (objects A 604-1, B 606-1, and C 610-1). The client system (FIG. 1, 102) tracks the position of each object on the display 608-1 and determines the focus area 602-1 of a user at multiple different times. By tracking the movement of objects on the display 608-1 through time and also tracking the user's focus area through time, the client system (FIG. 1, 102) can determine whether the user's focus area is following a specific object. In some implementations determining that the user's focus area 602-1 is following a specific object through different times, indicates that the user's interest in the media is high.

In accordance with some implementations, the client system (FIG. 1, 102) determines the focus area 602-1 of the user. The client system (FIG. 1, 102) then determines whether the focus area 602-1 intersects with any of the objects currently displayed on the display 608-1. In this example, the client system (FIG. 1, 102) intersects with object A 604-1. The client system (FIG. 1, 102) stores this information for future use.

FIG. 6B depicts an example of determining user interest through tracking displayed objects and determining the user focus area at a second point in time, in accordance with some implementations. In this example, the objects are the same as those depicted in FIG. 1, but have moved between the first time and the second time. The client system (FIG. 1, 102) determines the positions of the objects on the display 608-2 and the user's focus area 602-2 at a second time. As can be seen, relative to the display at time one in FIG. 6A, object A 604-2 and object B 606-2 have moved position on the display and object C 610-1 has left the display 608-2 has left the display entirely. Further, object D 612-2 has entered the display 608-2. The client system (FIG. 1, 102) determines the position of the user focus area 602-2. In this example the user focus area has moved relative to its position at the first time as seen in FIG. 6A.

In accordance with some implementations, the client system (FIG. 1, 102) determines the position of the user focus area 602-2 and whether it intersects with any objects currently displayed. In this example the user's focus area 602-2 intersects with object A. In some implementations the client system (FIG. 1, 102) compares the focus area intersect data from the first time with the focus area intersect data from the second time to determine whether the user's focus area 602-2 has followed a specific object from the first time to the second time. In this example, the user's focus area 602-2 intersects with object A at both the first and the second time. In some implementations, the client system (FIG. 1, 102) determines that the user's interest in the displayed media is relatively high based on determining that the user's focus area has followed a specific object from the first time to the second time.

FIG. 6C depicts an example of determining user interest through tracking displayed objects and determining the user focus area at a third point in time, in accordance with some implementations. In this example, the objects are the same as those depicted in FIG. 1 but the objects have moved between the first time and the third time. The client system (FIG. 1, 102) determines the position of objects on the display 608-3 and the position of the user focus area 602-3. In this example the objects A 604-3 and B 606-3 have moved from the original positions from the first time as depicted in FIG. 6A. Object C 610-1 has left the display 608-3 and object D 612-2 has entered the display 608-3. In contrast to the example depicted in FIG. 6B, the user's focus area 602-3 has not moved relative to its position at the first time depicted in FIG. 6A. Thus, the user's focus point has not moved from the first time to the second time. In some implementations, the client system (FIG. 1, 120) determines that the user interest in the displayed media is relatively low based on the fact that the user's focus area has not changed despite movement of the displayed objects.

FIG. 7 is a flow diagram illustrating the process of detecting user interest based on physical indicia, in accordance with some implementations. Each of the operations shown in FIG. 7 may correspond to instructions stored in a computer memory or computer readable storage medium. Optional operations are indicated by dashed lines (e.g., boxes with dashed-line borders). In some implementations, the method described in FIG. 7 is performed by the client system (FIG. 1, 102).

In accordance with some implementations, the client system (FIG. 1, 102) receives, from the server system (FIG. 1, 120), a list of events (FIG. 2, 246) associated with the media being displayed in the proximity of the user of the client system (702). In some implementations, a camera (FIG. 1, 106) captures visual data of a user of a client system (FIG. 1, 102) and transmits the visual data to the client system (FIG. 1, 102). In some implementations, the client system (FIG. 1, 102) analyzes the captured visual data to detect physical indicia of interest associated with a user of the client system (706). In some implementations, analyzing the capture visual data includes determining an orientation of the user's head (708). In some implementations analyzing the captured visual data includes detecting a user's physical response to the list of events received from the user (710).

In accordance with some implementations, the client system (FIG. 1, 102) analyzing the captured visual data includes determining a first gaze point for a first eye relative to a display (712). The client system (FIG. 1, 102) further determines a second gaze point for a second eye relative to a display (714). The client system (FIG. 1, 102) further measures the distance between the first gaze point and the second gaze point (716). The client system (FIG. 1, 102) further determines a focus area of the user based on the position of the firsts gaze point, the second gaze point, and the distance between them (718).

FIG. 8 is a flow diagram illustrating the process of detecting user interest based on physical indicia, in accordance with some implementations. Each of the operations shown in FIG. 8 may correspond to instructions stored in a computer memory or computer readable storage medium. Optional operations are indicated by dashed lines (e.g., boxes with dashed-line borders). In some implementations, the method described in FIG. 8 is performed by the client system (FIG. 1, 102).

In accordance with some implementations, the client system (FIG. 1, 102) analyzing the captured visual data includes receiving a stream of media content for display in proximity to the user of a client system (804). The client system (FIG. 1, 102) further analyzes the stream of media content to determine a plurality of objects currently being displayed, each object in the plurality of objects having an associated (806). The client system (FIG. 1, 102) further determines, at a first time, a first object intersecting with the user's focus area (808). The client system (FIG. 1, 102) further determines, at a second time, a second object intersecting with the user's focus area (810). The client system (FIG. 1, 102) further includes determining whether the focus area intersects the same object at both the first time and the second time (812).

For example, the client system (FIG. 1, 102) identifies three objects on a screen, a main character, a vehicle, and a chandelier. The client system (FIG. 1, 102) tracks the location of each object while the media is being displayed. The client system (FIG. 1, 102) also tracks the visual focus area of the user. So, if the client system (FIG. 1, 102) determines that, at a first time, the user's focus area intersects with the main character object, the client system (FIG. 1, 102) and at a second time, the user's focus area still intersects with the main character object despite the object having moved, the client system (FIG. 1, 102) determines that the user's interest level in this media is relatively high. Conversely if the user's focus area remains unchanged despite the displayed objects changing position, this indicates that the user's interest level is relatively low.

FIG. 9 is a flow diagram illustrating the process of detecting user interest based on physical indicia, in accordance with some implementations. Each of the operations shown in FIG. 9 may correspond to instructions stored in a computer memory or computer readable storage medium. Optional operations are indicated by dashed lines (e.g., boxes with dashed-line borders). In some implementations, the method described in FIG. 9 is performed by the client system (FIG. 1, 102).

In accordance with some implementations, the client system (FIG. 1, 102) determines a level of interest of the user with respect to media being displayed in the proximity of a user based on the detected physical indicia of interest (902). The client system (FIG. 1, 102) sends the determined level of interest to a server system (FIG. 1, 120) including an interest profile for the user of the client system (904). The client system (FIG. 1, 102) receives, from the server system (FIG. 1, 120), recommendations for additional media content for the user based, at least in part on, the determined level of interest (906).

The foregoing description, for purpose of explanation, has been described with reference to specific implementations. However, the illustrative discussions above are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. The implementations were chosen and described in order to best explain the principles of the invention and its practical applications, to thereby enable others skilled in the art to best utilize the invention and various implementations with various modifications as are suited to the particular use contemplated.

It will also be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first contact could be termed a second contact, and, similarly, a second contact could be termed a first contact, without departing from the scope of the present implementations. The first contact and the second contact are both contacts, but they are not the same contact.

The terminology used in the description of the implementations herein is for the purpose of describing particular implementations only and is not intended to be limiting. As used in the description of the implementations and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and/or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

As used herein, the term “if” may be construed to mean “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context. Similarly, the phrase “if it is determined” or “if (a stated condition or event) is detected” may be construed to mean “upon determining” or “in response to determining” or “upon detecting (the stated condition or event)” or “in response to detecting (the stated condition or event),” depending on the context.

Claims

1. A method for determining viewer interest, comprising:

on a client system having one or more processors, a camera, and memory storing one or more programs for execution by the one or more processors:
capturing visual data of a user of the client system with the camera;
analyzing the captured visual data to detect physical indicia of interest associated with a user of the client system;
based on the detected physical indicia of interest, determining a level of interest of the user with respect to media content being displayed in proximity to the user;
generating an interest score based on the determined level of interest, wherein the interest score represents the level of interest the user has in the media content being displayed in proximity to the user;
sending the interest score to a server system; the server system including an interest profile for the user of the client system; and
receiving, from the server system, recommendations for additional media content for the user based, at least in part, on the interest score.

2. The method of claim 1, wherein detecting physical indicia of interest includes:

determining a first gaze point for a first eye relative to a display;
determining a second gaze point for a second eye relative to a display; and
measuring the distance between the first gaze point and the second gaze point.

3. The method of claim 2, wherein detecting physical indicia of interest further includes:

determining a focus area of the user based on the position of the first gaze point, the second gaze point, and the distance between them.

4. The method of claim 1, wherein detecting physical indicia of interest includes:

determining an orientation of the user's head;

5. The method of claim 1, further including:

receiving, from the server system, a list of events associated with the media being displayed in proximity to the user of the client system.

6. The method of claim 5, wherein detecting physical indicia of interest further includes:

detecting a user's physical response to the list of events received from the user.

7. The method of claim 5, wherein the list of events includes audio events and visual events.

8. The method of claim 3, wherein detecting physical indicia of interest further includes:

receiving a stream of media content for display in proximity to the user of a client system;
analyzing the stream of media content to determine a plurality of objects currently being displayed, each object in the plurality of objects having an associated location;
determining, at a first time, an first object intersecting with the focus area,
determining, at a second time, a second object intersecting with the focus area; and
determining whether the focus area intersects the same object at both the first time and the second time.

9. An electronic device for determining viewer interest, comprising:

one or more processors;
a camera,
memory storing one or more programs to be executed by the one or more processors;
the one or more programs comprising instructions for: capturing visual data of a user of the client system with a camera; analyzing the captured visual data to detect physical indicia of interest associated with a user of the client system; based on the detected physical indicia of interest, determining a level of interest of the user with respect to media content being displayed in proximity to the user; generating an interest score based on the determined level of interest, wherein the interest score represents the level of interest the user has in the media content being displayed in proximity to the user; sending the interest score to a server system; the server system including an interest profile for the user of the client system; and receiving, from the server system, recommendations for additional media content for the user based, at least in part, on the interest score.

10. The electronic device of claim 9, wherein the instructions for detecting physical indicia of interest further include instructions for:

determining a first gaze point for a first eye relative to a display;
determining a second gaze point for a second eye relative to a display; and
measuring the distance between the first gaze point and the second gaze point.

11. The electronic device of claim 10, wherein the instructions for detecting physical indicia of interest further include instructions for:

determining a focus area of the user based on the position of the first gaze point, the second gaze point, and the distance between them.

12. The electronic device of claim 9, further including instructions for:

receiving, from the server system, a list of events associated with the media being displayed in proximity to the user of the client system.

13. The electronic device of claim 12, wherein the instructions for detecting physical indicia of interest further include instructions for:

detecting a user's physical response to the list of events received from the user.

14. The electronic device of claim 11, wherein the instructions for detecting physical indicia of interest further include instructions for:

receiving a stream of media content for display in proximity to the user of a client system;
analyzing the stream of media content to determine a plurality of objects currently being displayed, each object in the plurality of objects having an associated location;
determining, at a first time, an first object intersecting with the focus area,
determining, at a second time, a second object intersecting with the focus area; and
determining whether the focus area intersects the same object at both the first time and the second time.

15. A non-transitory computer readable storage medium storing one or more programs configured for execution by an electronic device with a camera, the one or more programs comprising instructions for:

capturing visual data of a user of the client system;
analyzing the captured visual data to detect physical indicia of interest associated with a user of the client system;
based on the detected physical indicia of interest, determining a level of interest of the user with respect to media content being displayed in proximity to the user;
generating an interest score based on the determined level of interest, wherein the interest score represents the level of interest the user has in the media content being displayed in proximity to the user;
sending the interest score to a server system; the server system including an interest profile for the user of the client system; and
receiving, from the server system, recommendations for additional media content for the user based, at least in part, on the interest score.

16. The computer readable storage medium of claim 15, wherein the instructions for detecting physical indicia of interest further include instructions for:

determining a first gaze point for a first eye relative to a display;
determining a second gaze point for a second eye relative to a display; and
measuring the distance between the first gaze point and the second gaze point.

17. The computer readable storage medium of claim 16, wherein the instructions for detecting physical indicia of interest further include instructions for:

determining a focus area of the user based on the position of the first gaze point, the second gaze point, and the distance between them.

18. The computer readable storage medium of claim 15 further including instructions for:

receiving, from the server system, a list of events associated with the media being displayed in proximity to the user of the client system.

19. The computer readable storage medium of claim 18, wherein the instructions for detecting physical indicia of interest further include instructions for:

detecting a user's physical response to the list of events received from the user.

20. The computer readable storage medium of claim 17, wherein the instructions for detecting physical indicia of interest further include instructions for:

receiving a stream of media content for display in proximity to the user of a client system;
analyzing the stream of media content to determine a plurality of objects currently being displayed, each object in the plurality of objects having an associated set of coordinates;
determining, at a first time, a first object intersecting with the focus area,
determining, at a second time, a second object intersecting with the focus area; and
determining whether the first object intersecting with the focus area at the first time is the same as the second object intersecting with the focus at the second time.
Patent History
Publication number: 20140026156
Type: Application
Filed: Jul 18, 2012
Publication Date: Jan 23, 2014
Inventor: David Deephanphongs (San Francisco, CA)
Application Number: 13/552,579
Classifications
Current U.S. Class: By Passive Determination And Measurement (e.g., By Detecting Motion Or Ambient Temperature, Or By Use Of Video Camera) (725/12)
International Classification: H04N 21/258 (20110101);