Patent Application
20160361653
Embodiments described herein generally relate to computers. More particularly, embodiments relate to a mechanism for recommending and selecting avatars.
Avatars are well known and widely used in various systems and software applications, such as telecommunication applications, user interface applications, computer games, etc. An avatar may refer to an animated version of a human face, an animal face, a cartoon face, etc. Avatars are often used by users who wish to preserve their privacy by not revealing their real face.
With the advancement of computer vision and processing power, facial performance driven avatar animation is feasible on mobile devices such that users may morph their facial actions on avatars. However, avatar stores for mobile applications are currently not organized to meet a user's preference. For instance, users of avatar mobile applications are typically provided the same lists of avatars. Moreover, current applications feature avatars that may not resonate with a particular user's intended audience. Specifically, a selected avatar may inadvertently offend someone due to cultural norms or come across as clueless, out of date, etc.
Embodiments are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings in which like reference numerals refer to similar elements.
In the following description, numerous specific details are set forth. However, embodiments, as described herein, may be practiced without these specific details. In other instances, well-known circuits, structures and techniques have not been shown in details in order not to obscure the understanding of this description.
Embodiments provide for selection of avatars that that effectively represent a user, and are aligned with an audience's culture, age and preferences. In such embodiments, avatar selection considers profile information of senders and/or an intended audience (e.g., demographic information, tastes, social network) for selection of the sender's avatar. In further embodiments, avatar selection may further be optimized by analysis of communication dynamics and conversation topics. In such embodiments, avatar selection is tailored according to popular trends pertinent to the conversation, as well as an analysis of users' emotional states and interpersonal dynamics. In still further embodiments, the appearance of avatars may be manipulated as a form of playful communication.
Embodiments also provide for facial driven avatar recommendation. In such embodiments, a personalized recommendation list of avatars is provided by inferring user preference from a camera input. The personalized recommendation list is generated by learning both user attributes and similarities between avatar models and facial input. Embodiments implement camera input of a user's face to analyze facial attributes (e.g., facial shape, gender, age, emotion, face shape, eyewear, hair style, etc.). In consideration of these attributes, along with a user's surrounding environment factors, a ranking score of available avatars is calculated and a recommendation list of avatar models is provided to the user. In further embodiments, the list may be periodically changed upon detecting a change in depending factors or attributes.
It is to be noted that although a human face is used as an example throughout the document for the sake of brevity, clarity, and ease of understanding, embodiments are not limited in that manner and that the term user may refer to a single person, multiple persons, other living beings (e.g., dogs, cats, plants, etc.), and even non-living objects (e.g., statues, televisions, musical instruments, etc.). Further, for example, embodiments may be applied not only to the face of a single person, but that embodiments are equally applicable to and compatible with a group of persons, not merely limited to their faces, along with their pets and/or other objects, etc. Similarly, embodiments are not limited to a single computing device or a particular type of computing device, such as a smartphone, but that any number and type of devices may be used, such as computing devices with multiple or extend displays, small screens, big screens, and even massive screens, such as store displays, magic mirrors, having the ability to depth track any number and form of persons, pets, objects, etc., may be used.
Computing device 100 may include an operating system (OS) 106 serving as an interface between hardware and/or physical resources of the computer device 100 and a user. Computing device 100 further includes one or more processors 102, memory devices 104, network devices, drivers, or the like, as well as input/output (I/O) sources 108, such as touchscreens, touch panels, touch pads, virtual or regular keyboards, virtual or regular mice, etc. It is to be noted that terms like “node”, “computing node”, “server”, “server device”, “cloud computer”, “cloud server”, “cloud server computer”, “machine”, “host machine”, “device”, “computing device”, “computer”, “computing system”, and the like, may be used interchangeably throughout this document. It is to be further noted that terms like “application”, “software application”, “program”, “software program”, “package”, and “software package” may be used interchangeably throughout this document. Similarly, terms like “job”, “input”, “request” and “message” may be used interchangeably throughout this document.
In one embodiment, reception and capturing logic 201 facilitates an image capturing device implemented at image sources 225 at computing device 100 to receive and capture an image associated with a user, such as a live and real-time image of the user's face. As the live image of the user's face is received and captured, the user's face and its movements and expressions may be continuously, and in real-time, detected and tracked in live video frames by detection/tracking logic 203.
The detecting and tracking of the user's face and its movements and expressions as performed by detection/tracking logic 203 may include detecting the user's face and determining various features of the face, such as positions of feature points, which may then be used to determine facial expression movements and head rigid movements. Further, based on these features, similar expression features may be accessed at and retrieved from a motion capture database, such as database 240. For more details, see U.S. patent application Ser. No. 13/977,682, filed Jun. 29, 2013, U.S. National Phase of PCT/CN2011/072603, filed Apr. 11, 2011, entitled Avatar Facial Expression Techniques, by Yangzhou Du, et al.
In some embodiments, database 240 may be used to record, store, and maintain data relating to various human facial expressions, such a smile, frown, laugh, cry, anger, happy, surprise, speak, silent, eat, drink, sing, yawn sneeze, and the like. These expressions may be recorded as sequences of frames where each frame may include multiple features, such as the following nine features: 1) distance between upper and lower lips; 2) distance between two mouth corners; 3) distance between upper lip and nose tip; 4) distance between lower lip and nose tip; 5) distance between nose-wing and nose tip; 6) distance between upper and lower eyelids; 7) distance between eyebrow tip and nose-tip; 8) distance between two eyebrow tips; and 9) distance between eyebrow tip and eyebrow middle. Database 240 may include a data source, an information storage medium, such as memory (volatile or non-volatile), disk storage, optical storage, etc.
In one embodiment, based on the features retrieved from database 240, meshing and mapping module 205 employs a three-dimensional (3D) mesh to locate various facial points and maps them to the corresponding avatar. This may involve normalizing and remapping the human face to the avatar face, copying the facial expression changes to the avatar, and then driving the avatar to perform the same facial expression changes as in the retrieved features. In embodiments, meshing and mapping module 205 may include graphics rendering features that allow the avatar to be output by a display device 230 associated with computing device 100. For example, display screen or device 230 may visually output the avatar to the user and similarly, one or more display devices, such as display device 255, associated with one or more other computing devices, such as computing device 250, may display the same simulated avatar to their respective users. Further, display device 230 may be implemented with various display(s) including (but are not limited to) liquid crystal displays (LCDs), light emitting diode (LED) displays, plasma displays, and cathode ray tube (CRT) displays.
Computing device 250 may be in communication with computing device 100 over one or more networks, such as network 270 (e.g., cloud network, the Internet, intranet, cellular network, proximity or near proximity networks, etc.). Computing device 250 may further include user interface 260, communication logic 265, and one or more software applications including avatar mechanism 110.
In embodiments, detection/tracking logic 203 may receive image data from image source 225, where the image data may be in the form of a sequence of images or frames (e.g., video frames). Image sources 225 may include an image capturing device, such as a camera. Such a device may include various components, such as (but are not limited to) an optics assembly, an image sensor, an image/video encoder, etc., that may be implemented in any combination of hardware and/or software. The optics assembly may include one or more optical devices (e.g., lenses, mirrors, etc.) to project an image within a field of view onto multiple sensor elements within the image sensor. In addition, the optics assembly may include one or more mechanisms to control the arrangement of these optical device(s). For example, such mechanisms may control focusing operations, aperture settings, exposure settings, zooming operations, shutter speed, effective focal length, etc. Embodiments, however, are not limited to these examples.
In an avatar-based system (e.g., a video chatting system), it is important to capture a user's head gestures, as well as the user's facial expressions. In embodiments, these operations may be performed by detection/tracking logic 203. In turn, these gestures and expressions may be expressed as animation parameters, where such animation parameters are transferred to meshing and mapping module 205 for rendering. In this way, the avatar system may be able to reproduce the original user's facial expression on a virtual 3D model.
In some embodiments, a practical solution for detection/tracking logic 203 may provide various features. For instance, detection/tracking logic 203 may track rigid movement due to head gestures. Such rigid movement may include (but is not limited to) translation, rotation and scaling factors. Also, detection/tracking logic 203 may track non-rigid transformation due to facial expressions, where the non-rigid transformations may include multiple facial action units (e.g., six typical facial action units). Further, detection/tracking logic 203 may be optimized in its implementation to run in real-time on one or more processors (e.g., on Intel Atom 1.6 GHz processors).
Image sources 225 may further include one or more image sensors including an array of sensor elements where these elements may be complementary metal oxide semiconductor (CMOS) sensors, charge coupled devices (CCDs), or other suitable sensor element types. These elements may generate analog intensity signals (e.g., voltages), which correspond to light incident upon the sensor. In addition, the image sensor may also include analog-to-digital converter(s) ADC(s) that convert the analog intensity signals into digitally encoded intensity values. Embodiments, however, are not limited to these examples. For example, an image sensor converts light received through optics assembly into pixel values, where each of these pixel values represents a particular light intensity at the corresponding sensor element. Although these pixel values have been described as digital, they may alternatively be analog. As described above, the image sensing device may include an image/video encoder to encode and/or compress pixel values. Various techniques, standards, and/or formats (e.g., Moving Picture Experts Group (MPEG), Joint Photographic Expert Group (JPEG), etc.) may be employed for this encoding and/or compression.
As aforementioned, image sources 225 may be any number and type of components, such as image capturing devices (e.g., one or more cameras, etc.) and image sensing devices, such as (but not limited to) context-aware sensors (e.g., temperature sensors, facial expression and feature measurement sensors working with one or more cameras, environment sensors (such as to sense background colors, lights, etc.), biometric sensors (such as to detect fingerprints, facial points or features, etc.), and the like. Computing device 100 may also include one or more software applications, such as business applications, social network websites (e.g., Facebook®, Google+®, Twitter®, etc.), business networking websites (e.g., LinkedIn®, etc.), communication applications (e.g., Skype®, Tango®, Viber®, etc.), games and other entertainment applications, etc., offering one or more user interfaces (e.g., web user interface (WUI), graphical user interface (GUI), touchscreen, etc.) to display the avatar and for the user to communicate with other users at other computing device 250, while ensuring compatibility with changing technologies, parameters, protocols, standards, etc. Communication/compatibility logic 219 may be used to facilitate dynamic communication and compatibility between various computing devices, such as computing device 100 and computing devices 250 (such as a mobile computing device, a desktop computer, a server computing device, etc.), storage devices, databases and/or data sources, such as database 240, networks, such as network 270 (e.g., cloud network, the Internet, intranet, cellular network, proximity networks, such as Bluetooth, Bluetooth low energy (BLE), Bluetooth Smart, Wi-Fi proximity, Radio Frequency Identification (RFID), Near Field Communication (NFC), Body Area Network (BAN), etc.), connectivity and location management techniques, software applications/websites, (e.g., social and/or business networking websites, such as Facebook®, LinkedIn®, Google+®, Twitter®, etc., business applications, games and other entertainment applications, etc.), programming languages, etc., while ensuring compatibility with changing technologies, parameters, protocols, standards, etc.
It is contemplated that any number and type of components 201-219 of avatar mechanism 110 may not necessarily be at a single computing device and may be allocated among or distributed between any number and type of computing devices, including computing devices 100, 250 having (but are not limited to) server computing devices, cameras, PDAs, mobile phones (e.g., smartphones, tablet computers, etc.), personal computing devices (e.g., desktop devices, laptop computers, etc.), smart televisions, servers, wearable devices, media players, any smart computing devices, and so forth. Further examples include microprocessors, graphics processors or engines, microcontrollers, application specific integrated circuits (ASICs), and so forth. Embodiments, however, are not limited to these examples.
Communication logic 265 of computing devices 250 may be similar to or the same as communication/compatibility logic 219 of computing device 100 and may be used to facilitate communication between avatar mechanism 110 at computing device 100 and one or more software applications at computing devices 250 for communication of avatars over one or more networks, such as network 270. Further, logic 265, 219 may be arranged or configured to use any one or more of communication technologies, such as wireless or wired communications and relevant protocols (e.g., Wi-Fi®, WiMAX, Ethernet, etc.), to facilitate communication over one or more networks, such as network 270 (e.g., Internet, intranet, cloud network, proximity network (e.g., Bluetooth, etc.). Database 240 may include any number and type of devices or mediums (such as data storage devices, hard drives, solid-state drives, hard disks, memory cards or devices, memory circuits, etc.) for short-time and/or long-term storage of data (e.g., patient information, customization parameters, process protocols, etc.), policies, resources, software programs or instructions, etc. Each of computing device 250 may also include a memory and/or storage medium for storing, maintaining, and/or caching of data, including avatars and other relevant information, such as facial feature points, etc.
Although one or more examples (e.g., a single human face, mobile computing device, etc.) may be discussed throughout this document for brevity, clarity, and ease of understanding, it is contemplated that embodiments are not limited to any particular number and type of users, avatars, forms of access to resources or computing devices, users, network or authentication protocols or processes, or the like. For example, embodiments are not limited to any particular network security infrastructures or protocols (e.g., single-sign-on (SSO) infrastructures and protocols) and may be compatible with any number and type of network security infrastructures and protocols, such as security assertion markup language (SAML), OAuth, Kerberos, etc.
Throughout this document, terms like “logic”, “component”, “module”, “framework”, “engine”, “point”, and the like, may be referenced interchangeably and include, by way of example, software, hardware, and/or any combination of software and hardware, such as firmware. Further, any use of a particular brand, word, term, phrase, name, and/or acronym, such as “avatar”, “avatar scale factor”, “scaling”, “animation”, “human face”, “facial feature points”, “zooming-in”, “zooming-out”, etc., should not be read to limit embodiments to software or devices that carry that label in products or in literature external to this document.
It is contemplated that any number and type of components may be added to and/or removed from avatar simulation mechanism 110 to facilitate various embodiments including adding, removing, and/or enhancing certain features. For brevity, clarity, and ease of understanding of avatar simulation mechanism 110, many of the standard and/or known components, such as those of a computing device, are not shown or discussed here. It is contemplated that embodiments, as described herein, are not limited to any particular technology, topology, system, architecture, and/or standard and are dynamic enough to adopt and adapt to any future changes.
According to one embodiment, user face and movement data acquired by detection/tracking logic 203 may be used by avatar determination mechanism 207 to select and manipulate an avatar. In other embodiment, the data may be received at avatar recommendation mechanism 209, which provides a list of multiple avatars as recommendations.
According to one embodiment, avatar determination module 300 selects an avatar based on user face and movement information received from detection/tracking logic 203, sender and recipient profile information received from profile acquisition module 305, context information received from context engine 306 and information received from content analyzer 308. In one embodiment, detection/tracking logic 203 uses data from sensor arrays to monitor facial expressions of the sender to infer emotional reactions and other expressions. Additionally, voice characteristics, and other attributes of the sender may be monitored to infer emotions. In a further embodiment, avatar determination module 300 may also receive sensory array data from the recipient device (e.g., computing device 250) to infer the emotional reactions of the recipient prior to selecting an avatar.
In one embodiment, profile acquisition module 305 acquires profile information for the sender and one or more recipients whom are to receive the avatar. In such an embodiment, profile acquisition module 305 may extract information from one or more network sources, such as social network websites (e.g., Facebook®, Google+®, Twitter®, etc.), business networking websites (e.g., LinkedIn®, etc.), communication applications (e.g., Skype®, Tango®, Viber®, etc.) and service providers (e.g., Hulu®, Netflix®, Amazon®, etc.) via network 230. In a further embodiment, avatar selection may be determined by social influences shared by the sender and one or more recipients. For instance, an avatar may be selected based on the avatar selections of people that the sender or the sender's communication partners follow on Twitter®. Context engine 306 acquires information related to the current circumstances of the user and/or message recipient. For instance, context engine 306 may determine social circumstances of a recipient (e.g., alone), a current location (e.g., home or work), user activity (e.g., exercising) for the user and recipient and. Content analyzer 308 analyzes the content of messages between a sender and a recipient to determine sentiment and interpersonal dynamics (e.g., sadness or hostility).
As discussed above, avatar determination module 300 receives information from detection/tracking logic 203, profile acquisition module 305, context engine 306 and content analyzer 308 for consideration in the selection of an avatar. According to one embodiment, avatar determination module 300 may infer intent of a sender based on information received profile acquisition module 305. For example intent of the sender (e.g., friend, flirt, professional negotiation, marriage proposal, etc.) may be inferred based on a relationship between the sender and one or more recipients within a particular application, or in other social media (friends or friends of friends on Facebook®, recently met on Tinder®, colleagues on LinkedIn®, followers on Twitter®).
In another embodiment, avatar determination module 300 may map overlap between an avatar selection of the sender with tastes of the recipient. In such an embodiment, content analyzer 308 may analyze text for key topics prior to providing the information to avatar determination module 300. Subsequently, avatar determination module 300, may match words against social network pages to identify topically relevant avatars (e.g., if someone mentions the
World Cup, avatar determination module 300 may respond with selecting an avatar of a famous soccer player). In one embodiment, analysis data received from content analyzer 308 may be used to assist communication partners in modifying avatars for teasing or negotiation. For instance, if a recipient is caught off guard by a hostile note or accusation, avatar determination module 300 may select an avatar of an unjustly accused character in a well-known film for a reply.
According to one embodiment, avatar determination module 300 uses contextual analysis received from context engine 306 as a factor in avatar selection. For example, the sender's social situation (e.g., whether the recipient is alone) may influence the appearance of the avatar. In a further embodiment, avatar determination module 300 conducts a cultural translation if there is no overlap. For example, where reference to a person as a devil in the United States means the person is a charming rascal, determination module 300 may select another option if the recipient is from a country where the term a devil would be offensive. As another example, avatar determination module 300 may select an avatar of a popular DJ in Brazil in a scenario in which a middle age blogger in the United States trying to connect with teenagers in Brazil has previously chosen Mick Jagger as an avatar.
According to one avatar determination module 300 automatically selects avatars from database 240 based on the above-described factors. In such an embodiment, database 140 includes three-dimensional (3D) models of characters provided by Intel® Pocket Avatars.
however, it is contemplated that any number of them can be performed in parallel, asynchronously, or in different orders. For brevity, clarity, and ease of understanding, many of the details discussed with reference to
Method 400 begins at block 410 with receiving sender and receiver attributes at avatar detection mechanism 207. As discussed above, the attributes may comprise live, real-time, audio-video data, including a video image of a user (e.g., sender's and/or receiver's face), via one or more image sensors at a computing device. The attributes also may include information acquired by profile acquisition module 305 and context engine 306. At block 420, the received data is analyzed as discussed above. At block 430, the sender prepares a text based message (text or voice) for transmission to one or more recipients. At block 440, avatar determination mechanism 207 analyzes the message content relative to the attributes. At block 450, an avatar is selected based on the analysis. At block 460, the avatar is rendered (e.g., at meshing and mapping module 205). At block 470, the message is made available for the recipient. At block 480, avatar determination mechanism 207 monitors the recipient reaction (e.g., via audio-video from the recipient's computing device). At block 490, a determination is made as to whether an adjustment is to be made based on the recipient's reaction. If so, control is returned to block 410 where updated attributes reflecting the recipient's reactions are received and subsequently analyzed.
As shown above, the avatar determination mechanism selects avatars that increase communication resonance by aligning profile information of a sender and an intended audience (demographic information, tastes, social network). The selection is tailored according to popular trends pertinent to a conversation, as well as an analysis of each users' emotional states and interpersonal dynamics. the avatar determination mechanism also guides users in manipulating the appearance of one another's avatars as a form of playful communication.
As discussed above, existing avatar applications do not provide suitable options that meet user preferences.
According to one embodiment, avatar recommendation module 209 is implemented to provide facial driven avatars to enable a personalized list of avatar models for a user by inferring user preference directly from camera input. In such an embodiment, avatar recommendation module 209 generates a personalized recommendation list by learning user attributes and similarities between avatar models and facial input.
According to one embodiment, the model is applied to a first appearance of a user (e.g., an unseen case), resulting in an output the current user attributes. In a further embodiment, appearance features outside of the face box may also be extracted in order to determine a scene and/or check the user's dress style. In this embodiment, a visual descriptor (e.g., Histogram of oriented Gradients (HOG)) is used for the appearance of face and environment. Each user may be described according to 14 attributes: face shape, appearance, gender, age, skin color, hair color, hair length, eyewear, makeup degree, emotion, environment, lighting and dress style.
Avatar rank module 606 receives the attribute data from user recognition module 604 and ranks available avatar models at database 240 by integrating attribute similarity scores. In one embodiment, all attributes for a current user are considered to assign a score for each avatar figure. In such an embodiment, each avatar figure has values for all attributes. Subsequently, a matching between the user and avatar figure can be decomposed as matching in terms of individual attribute. In one embodiment, the attribute score is represented by:
Scoreattribute (user, avatar)=Σi=114 wi|Suseri−Savatari|
where i denotes attribute, and |Suseri−Savatari| denotes the score difference between user and avatar figure on the i-th attribute, wi is the weight parameter of the i-th attribute.
If an avatar model is similar to the user, the output score is smaller. In one embodiment, missing attributes may be ignored by setting a corresponding weight parameter to 0. For example, if a hat occludes the user's hair, the hair related attribute weight (e.g., color and length) should be set to 0.
Method 800 begins at block 810 with capturing live videos from image sources 225 during operation of an avatar application, such as Intel® Pocket Avatars, Nito®, Mojo Masks®, etc. At block 820, a user's face is located in the video. In one embodiment, detection/tracking logic 203 detects whether an image in the video includes a face. In such an embodiment, the position of each face is represented with one bounding rectangle. Based on the face rectangle, different facial features (e.g., eye -brows, eyes, nose, mouth, hair, etc.) may be further localized. At block 830, the detected face is extracted. At block 840, user attributes from the extracted are recognized at user recognition module 604, as discussed above.
At block 850, the avatar models are ranked by integrating attribute and similarity scores. At block 860, avatar models are sorted by the similarity scores. At block 870, the sorted scores are displayed at display 230 as a list. In one embodiment, a static snapshot of each model is displayed instead of the animated model in order to save bandwidth. In such an embodiment, the user can select a snapshot to load the model to check the model's dynamic actions.
An exemplary avatar application that implements avatar recommendation module 209 may involve a user operating the avatar application on a mobile device to open an avatar store to select a model. Subsequently, recommendation module 209 recognizes the different user attributes and ranks models by the integrated scores. The tailored list is then displayed on the screen.
Computing system 900 may also include read only memory (ROM) and/or other storage device 930 coupled to bus 905 that may store static information and instructions for processor 910. Date storage device 940 may be coupled to bus 905 to store information and instructions.
Date storage device 940, such as magnetic disk or optical disc and corresponding drive may be coupled to computing system 900.
Computing system 900 may also be coupled via bus 905 to display device 950, such as a cathode ray tube (CRT), liquid crystal display (LCD) or Organic Light Emitting Diode (OLED) array, to display information to a user. User input device 960, including alphanumeric and other keys, may be coupled to bus 905 to communicate information and command selections to processor 910. Another type of user input device 960 is cursor control 970, such as a mouse, a trackball, a touchscreen, a touchpad, or cursor direction keys to communicate direction information and command selections to processor 910 and to control cursor movement on display 950. Camera and microphone arrays 990 of computer system 900 may be coupled to bus 905 to observe gestures, record audio and video and to receive and transmit visual and audio commands.
Computing system 900 may further include network interface(s) 980 to provide access to a network, such as a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a personal area network (PAN), Bluetooth, a cloud network, a mobile network (e.g., 3rd Generation (3G), etc.), an intranet, the Internet, etc. Network interface(s) 980 may include, for example, a wireless network interface having antenna 985, which may represent one or more antenna(e). Network interface(s) 980 may also include, for example, a wired network interface to communicate with remote devices via network cable 987, which may be, for example, an Ethernet cable, a coaxial cable, a fiber optic cable, a serial cable, or a parallel cable.
Network interface(s) 980 may provide access to a LAN, for example, by conforming to IEEE 802.11b and/or IEEE 802.11g standards, and/or the wireless network interface may provide access to a personal area network, for example, by conforming to Bluetooth standards. Other wireless network interfaces and/or protocols, including previous and subsequent versions of the standards, may also be supported.
In addition to, or instead of, communication via the wireless LAN standards, network interface(s) 980 may provide wireless communication using, for example, Time Division, Multiple Access (TDMA) protocols, Global Systems for Mobile Communications (GSM) protocols, Code Division, Multiple Access (CDMA) protocols, and/or any other type of wireless communications protocols.
Network interface(s) 980 may include one or more communication interfaces, such as a modem, a network interface card, or other well-known interface devices, such as those used for coupling to the Ethernet, token ring, or other types of physical wired or wireless attachments for purposes of providing a communication link to support a LAN or a WAN, for example. In this manner, the computer system may also be coupled to a number of peripheral devices, clients, control surfaces, consoles, or servers via a conventional network infrastructure, including an Intranet or the Internet, for example. It is to be appreciated that a lesser or more equipped system than the example described above may be preferred for certain implementations. Therefore, the configuration of computing system 900 may vary from implementation to implementation depending upon numerous factors, such as price constraints, performance requirements, technological improvements, or other circumstances. Examples of the electronic device or computer system 900 may include without limitation a mobile device, a personal digital assistant, a mobile computing device, a smartphone, a cellular telephone, a handset, a one-way pager, a two-way pager, a messaging device, a computer, a personal computer (PC), a desktop computer, a laptop computer, a notebook computer, a handheld computer, a tablet computer, a server, a server array or server farm, a web server, a network server, an Internet server, a work station, a mini-computer, a main frame computer, a supercomputer, a network appliance, a web appliance, a distributed computing system, multiprocessor systems, processor-based systems, consumer electronics, programmable consumer electronics, television, digital television, set top box, wireless access point, base station, subscriber station, mobile subscriber center, radio network controller, router, hub, gateway, bridge, switch, machine, or combinations thereof. Embodiments may be implemented as any or a combination of: one or more microchips or integrated circuits interconnected using a parentboard, hardwired logic, software stored by a memory device and executed by a microprocessor, firmware, an application specific integrated circuit (ASIC), and/or a field programmable gate array (FPGA). The term “logic” may include, by way of example, software or hardware and/or combinations of software and hardware. Embodiments may be provided, for example, as a computer program product which may include one or more machine-readable media having stored thereon machine-executable instructions that, when executed by one or more machines such as a computer, network of computers, or other electronic devices, may result in the one or more machines carrying out operations in accordance with embodiments described herein. A machine-readable medium may include, but is not limited to, floppy diskettes, optical disks, CD-ROMs (Compact Disc-Read Only Memories), and magneto-optical disks, ROMs, RAMs, EPROMs (Erasable Programmable Read Only Memories), EEPROMs (Electrically Erasable Programmable Read Only Memories), magnetic or optical cards, flash memory, or other type of media/machine-readable medium suitable for storing machine-executable instructions.
Moreover, embodiments may be downloaded as a computer program product, wherein the program may be transferred from a remote computer (e.g., a server) to a requesting computer (e.g., a client) by way of one or more data signals embodied in and/or modulated by a carrier wave or other propagation medium via a communication link (e.g., a modem and/or network connection).
References to “one embodiment”, “an embodiment”, “example embodiment”, “various embodiments”, etc., indicate that the embodiment(s) so described may include particular features, structures, or characteristics, but not every embodiment necessarily includes the particular features, structures, or characteristics. Further, some embodiments may have some, all, or none of the features described for other embodiments.
In the following description and claims, the term “coupled” along with its derivatives, may be used. “Coupled” is used to indicate that two or more elements co-operate or interact with each other, but they may or may not have intervening physical or electrical components between them. As used in the claims, unless otherwise specified the use of the ordinal adjectives “first”, “second”, “third”, etc., to describe a common element, merely indicate that different instances of like elements are being referred to, and are not intended to imply that the elements so described must be in a given sequence, either temporally, spatially, in ranking, or in any other manner.
The following clauses and/or examples pertain to further embodiments or examples. Specifics in the examples may be used anywhere in one or more embodiments. The various features of the different embodiments or examples may be variously combined with some features included and others excluded to suit a variety of different applications. Examples may include subject matter such as a method, means for performing acts of the method, at least one machine-readable medium including instructions that, when performed by a machine cause the machine to performs acts of the method, or of an apparatus or system for facilitating hybrid communication according to embodiments and examples described herein.
Some embodiments pertain to Example 1 that includes an apparatus to facilitate dynamic selection of avatars. The apparatus includes reception and capturing logic to capture, in real-time, an image of a user, detection/tracking logic to determine facial features of the user based on the user image and an avatar selection module to facilitate selection of an avatar based on the user facial feature.
Example 2 includes the subject matter of Example 1, wherein the avatar selection module includes a profile acquisition module to acquire profile information for user and one or more recipients, a context engine to acquire information related to current circumstances of the user and the one or more recipients, a content analyzer to analyze content of a message between the user and the one or more recipients to determine sentiment and interpersonal dynamics and an avatar determination module to select an avatar based on the profile information, information acquired by the context engine and the sentiment and interpersonal dynamics determined by the content analyzer.
Example 3 includes the subject matter of Example 2,wherein the profile acquisition module extracts information from one or more social network sources.
Example 4 includes the subject matter of Example 3,wherein the avatar determination module infers intent of the user based on the information from one or more social network sources as a factor in selecting the avatar.
Example 5 includes the subject matter of Example 4, wherein the avatar determination module selects the avatar based on social influences shared by the sender and one or more recipients.
Example 6 includes the subject matter of Example 2, wherein the avatar determination module matches words in text from the content analyzer against the social network sources to select a topically relevant avatar.
Example 7 includes the subject matter of Example 2, wherein the avatar determination module selects the avatar based on a social situation of a recipient.
Example 8 includes the subject matter of Example 2, wherein the avatar determination module receives image data or text data from the one or more recipients and selects the avatar based on perceived emotional reactions of the one or more recipients.
Example 9 includes the subject matter of Example 1, wherein the avatar selection module comprises a user recognition module to recognize user attributes based on the user facial features, a ranking module to receive user attribute data and rank available avatar models based on attribute similarity scores and an avatar recommendation module to recommend an avatar based on the ranked available avatar models.
Example 10 includes the subject matter of Example 9, wherein the all attributes for the user are considered to assign an attribute similarity score to each available avatar model.
Example 11 includes the subject matter of Example 9, wherein the avatar recommendation module generates a list of the ranked available avatar models for display.
Some embodiments pertain to Example 12 that includes a method to facilitate dynamic selection of avatars, comprising acquiring attributes, analyzing the attributes and facilitating selection of an avatar based on the user attributes.
Example 13 includes the subject matter of Example 12, wherein the attributes include at least one of profile information for a user and one or more recipients, information related to current circumstances of the user and the one or more recipients, facial attributes of a user.
Example 14 includes the subject matter of Example 13, further comprising analyzing content of a message between the user and the one or more recipients to determine sentiment and interpersonal dynamics and selecting an avatar based on the attributes and the content of the message.
Example 15 includes the subject matter of Example 14, further comprising monitoring facial attributes of the one or more recipients, receiving text data from the one or more recipients and selecting an updated avatar based on the facial attributes text data from the one or more recipients.
Example 16 includes the subject matter of Example 12, wherein analyzing the user attributes comprises recognizing user facial attributes.
Example 17 includes the subject matter of Example 16, further comprising assigning an attribute similarity score to each available avatar model, ranking the available avatar models based on attribute similarity scores and recommending an avatar based on the ranked available avatar models.
Example 18 includes the subject matter of Example 17, wherein the all attributes for the user are considered to assign an attribute similarity score to each available avatar model. Example 19 includes the subject matter of Example 17, further comprising generating a list of the ranked available avatar models for display.
Some embodiments pertain to Example 20 that includes at least one machine-readable medium comprising a plurality of instructions that in response to being executed on a computing device, causes the computing device to carry out operations according to any one of claims 12 to 19.
Some embodiments pertain to Example 21 that includes a system comprising a mechanism to carry out operations according to any one of claims 12 to 19.
Some embodiments pertain to Example 22 that includes an apparatus comprising means to carry out operations according to any one of claims 12 to 19.
Some embodiments pertain to Example 23 that includes a computing device arranged to carry out operations according to any one of claims 12 to 19.
Some embodiments pertain to Example 24 that includes a communications device arranged to carry out operations according to any one of claims 12 to 19. Some embodiments pertain to Example 25 that includes an apparatus to facilitate dynamic selection of avatars, comprising means for acquiring attributes, means for analyzing the attributes and means for facilitating selection of an avatar based on the user attributes.
Example 26 includes the subject matter of Example 25, wherein the attributes include at least one of profile information for a user and one or more recipients, information related to current circumstances of the user and the one or more recipients, facial attributes of a user
Example 27 includes the subject matter of Example 26, further comprising means for analyzing content of a message between the user and the one or more recipients to determine sentiment and interpersonal dynamics and means for selecting an avatar based on the the attributes and the content of the message.
Example 28 includes the subject matter of Example 27, further comprising means for monitoring facial attributes of the one or more recipients, means for receiving text data from the one or more recipients and means for selecting an updated avatar based on the facial attributes text data from the one or more recipients.
Example 29 includes the subject matter of Example 25, wherein the means for analyzing the user attributes comprises means for recognizing user facial attributes.
Some embodiments pertain to Example 30 that includes 30 at least one machine-readable medium comprising a plurality of instructions that in response to being executed on a computing device, causes the computing device to carry out operations comprising acquiring attributes, analyzing the attributes and facilitating selection of an avatar based on the user attributes.
Example 31 includes the subject matter of Example 30, wherein the attributes include at least one of profile information for a user and one or more recipients, information related to current circumstances of the user and the one or more recipients, facial attributes of a user.
Example 32 includes the subject matter of Example 31, comprising a plurality of instructions that in response to being executed on a computing device, causes the computing device to further carry out operations comprising, analyzing content of a message between the user and the one or more recipients to determine sentiment and interpersonal dynamics and selecting an avatar based on the attributes and the content of the message.
Example 33 includes the subject matter of Example 32, comprising a plurality of instructions that in response to being executed on a computing device, causes the computing device to further carry out operations comprising monitoring facial attributes of the one or more recipients, receiving text data from the one or more recipients and selecting an updated avatar based on the facial attributes text data from the one or more recipients.
Example 34 includes the subject matter of Example 30, wherein analyzing the user attributes comprises recognizing user facial attributes.
Example 35 includes the subject matter of Example 34, comprising a plurality of instructions that in response to being executed on a computing device, causes the computing device to further carry out operations comprising assigning an attribute similarity score to each available avatar model, ranking the available avatar models based on attribute similarity scores and recommending an avatar based on the ranked available avatar models.
The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. Numerous variations, whether explicitly given in the specification or not, such as differences in structure, dimension, and use of material, are possible. The scope of embodiments is at least as broad as given by the following claims.
| Filing Document | Filing Date | Country | Kind |
|---|---|---|---|
| PCT/CN2014/093596 | 12/11/2014 | WO | 00 |
