106 and/or 124 snapshot 127 of scene 103 of media asset 105 being generated for display when (or within a predetermined time of when) query 122 is received. Snapshot 127 may be pinned to the screen of one or more of user equipment devices 106 and 124 to enable the user to view scene 103 associated with query 122 and reference the objects shown in such scene when providing reply 138 to disambiguating query 126. In some embodiments, the media application may provide snapshot 127 in response to determining (e.g., based on metadata associated with media asset 105) that the current scene 103 associated with snapshot 127 (e.g., depicting actors 102 and 104) is likely to conclude prior to disambiguating query 126 and/or reply 138 being generated for output, or that an upcoming scene 107 (including car 121) to commence prior to disambiguating query 126 and/or reply 138 being generated for output does not depict one or more of actor 102 and actor 104, e.g., the objects at issue in query 122. For example, if the media application determines (e.g., based on metadata associated with media asset 105 and/or by analyzing frames of media asset 105) that a scene associated with snapshot 127 is a long monologue that is scheduled to last for five minutes, snapshot 127 may be less useful to user 120 because the objects at issue (e.g., actor 102 and actor 104) in query 122 are predicted to be, or are known to be, depicted in media asset 105 being played on user equipment 106.

The media application, in response to receiving reply 138 confirming that user 120 intended query 122 to reference actor 102 wearing the black shirt in scene 103 at issue in media asset 105, may generate for output reply 140 following confirmation reply 138 received from user 120. For example, reply 128 may be received by the media application running on user equipment device 124 while a next scene 107 of media asset 105 is playing on user equipment 106. In some embodiments, snapshot 127 may continue to be depicted by the media application when reply 140 is generated for output, to enable user 120 to view scene 103 that was at issue when query 122 was received by the media application. The media application may reference metadata of media asset 105 and/or the Internet (e.g., perform a query to a search engine to determine other movies that Leonardo DiCaprio starred in), a database (e.g., content source 802 of FIG. 8) and/or personal preferences of the user in generating for output the reply.

FIG. 2 shows a block diagram of an illustrative system for generating a disambiguating query based on a first object and a second object of a snapshot, in accordance with some embodiments of this disclosure. FIG. 2 is similar to FIG. 1 except that FIG. 2 shows query 222 being received by the media application running on user equipment 206 (e.g., a smart television). The media application may generate for display media asset 205 on user equipment 206. While a current scene 203 of media asset is being generated for display (or within a predetermined time thereof), the media application running on user equipment 206 may receive query 222 from user 220. Query 222 may be received by the media application in any suitable format (e.g., text-based input, audio or voice input, touch input, biometric input, or any combination thereof). The media application may, using similar techniques as discussed above, generate disambiguating query 226 based on query 222, in response to determining that query 222 is ambiguous, e.g., as to whether user 220 is referencing actor 202 or actor 204 depicted in scene 203 of media asset 205. In some embodiments, the media application running on user equipment 206 may generate for presentation snapshot 227 of scene 203, displayed in a portion of the screen depicting scene 207 of media asset 205 (e.g., displayed in an upper right-hand corner of the screen to avoid overlapping important portions of scene 207). In some embodiments, disambiguating query 226 may be text-based, e.g., to avoid interrupting audio of scene 207. Additionally or alternatively, the media application may pause media asset 207 while generating for output disambiguating query 226, and the media asset 207 may continue to be paused until reply 238 is received from user 220. The media application running on user equipment 206, in response to receiving confirmatory reply 238 from user 220, may generate for output reply 240, e.g., to provide an answer to the (now-clarified) query 222 of user 220.

FIGS. 3A-3C shows exemplary snapshots of a media asset, in accordance with some embodiments of this disclosure. The media application may generate for output snapshots 327, 329, 331 (e.g., which may correspond to snapshots 127 and 227 of FIGS. 1 and 2, respectively) in a variety of formats. Snapshot 327 may comprise indicator 323 to highlight and/or otherwise emphasize an object (e.g., actor 302) and/or a sub-element of the object (e.g., black shirt of actor 302) that may potentially be the object of an ambiguous query. For example, the media application may cause a box or overlay 323 to be generated for presentation around actor 302 alongside query 326, to assist the user in clarifying his or her query. The media application may alternatively or additionally generate for display snapshot 329 by zooming in on actor 302 at issue (and/or cropping out other portions of the relevant scene), along with query 333 referencing the “actor shown below,” e.g., to enable the media application to receive clarification form the user without any extraneous objects located in snapshot 329. In some embodiments, the media application may alternatively or additionally generate for display snapshot 331, which, along with disambiguating query 335, prompts a user to select the object he or she intended to refer to, e.g., actor 302 or actor 304. In response to receiving selection of one of the objects, e.g., a portion of the screen depicting actor 302, via a touch-sensitive screen, the media application may generate for output a reply to the confirmatory reply received from a user.

FIG. 4 shows a block diagram of an illustrative system for generating a disambiguating query based on a first object and a second object of a snapshot, in accordance with some embodiments of this disclosure. The media application may generate for display media asset 405 on user equipment 406, and perform processing shown in FIG. 4 in response to receiving a query (e.g., “Who is that actor?”) while scene 403 is being played.

At 426, the media application may identify the respective types of objects depicted in scene 403. For example, the media application may perform object or pattern recognition techniques, and/or edge detection or computer vision techniques on the image of scene 403 (and one or more associated frames or frames within a predetermined period thereof) to identify people, places, things, events, any other suitable objects, or any combination thereof, depicted therein. For example, detected object features thereof may be compared (e.g., pixel by pixel) to objects and associated features stored in a database (e.g., database 805 of FIG. 8) to determine whether the detected features match an object in the database. For example, the media application may identify an object in a scene at issue as a car (e.g., based on having a similar shape and size as an object stored in the database). In some embodiments, the media application may identify type of objects based on metadata associated with media asset 405 (e.g., indicating which actors are in a particular scene). In some embodiments, machine learning models (e.g., native Bayes model, logistic regression, neural networks, etc.) may be employed to classify objects extracted from scene 403. For example, the model may be trained on a plurality of labeled image pairs, where image data may be preprocessed and represented as feature vectors. In some embodiments, a third-party application may be utilized to extract objects from an image associated with scene 403.

At 428, the media application may determine a confidence level associated with the identified types. For example, the aforementioned image processing algorithm may output a confidence level associated with a prediction of a type of the object identified in scene 403. In some embodiments, the confidence level may be based on a percentage of features of the extracted object that match features of an object in the database (e.g., database 805 of FIG. 8), and/or the number of times the candidate object has been identified in the past. In some embodiments, the media application may retrieve information (e.g., from media content source 802 or based on an Internet search) to determine whether the predicted object is likely to be accurate (e.g., to confirm that a particular actor appears in the currently playing media asset). The confidence level, along with the identified type, may be provided to disambiguating query generator 438, which may be implemented by the media application.

At 430, based on the types of objects identified at 426, the media application may query database 432 to determine a disambiguation success rate associated with identified types of objects. For example, the media application may identify desk 417 and actor 402 wearing a black shirt, and may query database 432 to determine which object (e.g., in connection with media asset 405 or other media assets depicting similar objects) has been more successful in generating a disambiguating query in the past to predict user familiarity with each object. If the media application determines that disambiguating queries associated with features or the location of desk 417 have historically had a relatively low success rate (e.g., only 25% of such queries successfully disambiguated an initial query without requiring follow-up clarifying queries), but disambiguating queries associated with features or the location of the black shirt of actor 402 have been more successful (e.g., 75% of such queries successfully disambiguated an initial query without requiring follow-up clarifying queries), the media application may determine that a disambiguating query associated with the black shirt of actor 402 is preferable. Such success rate information may be provided to disambiguating query generator 438.

At 434, the media application may determine a number of pixels (or percentage of a current display) associated with each of the first object (e.g., actor 402) and the second object (e.g., actor 404). The media application may make this determination based on metadata associated with the media asset 405 (e.g., retrieving coordinates of objects in scene 403), and/or based on edge detection techniques to determine boundaries (e.g., edges, shape outline, border) of objects of scene 403 and/or analyzing pixel values of the area surrounding objects. For example, if the media application detects that brightness of adjacent pixels abruptly changes, the media application may determine that this is indicative of an edge of an object, and may calculate the number of pixels of the object based on the determined edges being the perimeter of the object. In some embodiments, the media application may use similar techniques to determine a number of pixels associated with objects that are sub-elements of a larger object (e.g., a number of pixels occupied by black shirt 408 being worn by actor 402, or a number of pixels associated with shoes 418 and/or pants 416 of actor 404). In some embodiments, the media application may assign certain features (e.g., a bright red sports car) depicted in a particular scene a higher prominence level than more common or mundane features (e.g., a gray van), to reflect the likelihood that a particular object is capturing the attention of the user and thus may be a suitable candidate for a disambiguating query. The media application may perform this determination by, for example, referencing a database storing information regarding which images are more likely to capture user attention, and/or based on identifying keyword tags for a particular scene (e.g., retrieved from metadata or generated based on image analysis) and referencing a corpus to determine which keywords are less common than others.

At 436, the media application may determine which objects (or sub-elements thereof) are prominently featured (e.g., the media application may determine that actor 402 is associated with more pixels of an image of scene 403 than actor 414, and/or that black shirt 408 of actor 402 is associated with more pixels than shoe 412). The media application may output such determinations to disambiguating query generator 438. In some embodiments, vector graphics may be employed in depicting scenes of media asset 105, and in such instance the media application may determine that when a particular object occupies more space on the screen than another object, that such object occupying more space is more prominent.

Disambiguating query generator 438 may compute one or more scores based on one or more of the input attributes (e.g., amount of pixels associated with each object, success rate of identified objects, confidence level of identified objects). In some embodiments, the media application may generate a data structure (e.g., as shown in FIGS. 5 and 6) for use by the disambiguating query generator in generating a suitable disambiguating query.

For example, based on the determined confidence level at 428, the media application may compute a score of 0.8 for a car predicted to be a specific model of a Mercedes-Benz (e.g., indicating the media application has determined there is a 70% probability that an identified object is a C200 Mercedes-Benz, as shown in the data structure of FIG. 6) and a score of 1.0 for shirt 408 of actor 402 predicted to be black (e.g., indicating the media application has determined there is a 100% probability that an identified object is a black shirt, as shown in the data structure of FIG. 5). In some embodiments, disambiguating query generator 438 may compute a success rate score based on determined success rate at 430. For example, as shown in FIG. 5, the media application may determine a past success rate score of 0.8 for black Armani shirt 408 (or similar objects thereto), indicating that 80% of disambiguating queries that referenced shirt 408 were successful in disambiguating query 422 received from a user. The media application may determine, on the other hand, that shoes 412 are associated with a success rate of 0.3, e.g., indicating that past disambiguating queries that reference shoes 412 (or similar objects thereto) only had a 30% success rate in disambiguating query 422 received from a user. Alternatively or additionally, the media application may compute a prominence score based on the determined number of pixels associated with the identified objects (and/or sub-elements of the identified objects. For example, as shown in FIG. 5, the media application may determine that black Armani shirt 408 is associated with a 0.6 prominence score (e.g., based on a number of pixels and optionally based on a color or overall appearance of shirt 408) whereas white polo shirt 414 is associated with a 0.4 prominence score. In some embodiments, the media application may sum the prominence scores of each element of an object to determine an overall prominence score for the object (e.g., the media application may determine that actor 402 is associated with a 0.8 prominence score based on a prominence scores of 0.6, 0.1, and 0.1 for shirt 408, jeans 410 and shoes 412).

Disambiguating query generator 438, which may be implemented by the media application, may generate for output one or more disambiguating queries in reply to query 422 based on one or more of the computed confidence score, success rate score and prominence score. In some embodiments, the media application may determine the highest score from among the computed confidence score, success rate score and prominence score for scene 403 and generate a disambiguating query based on such highest score. For example, for scene 403, the media application may determine that since black short sleeve shirt 408 received a confidence score of 1.0 in the example of FIG. 5, and no other score is higher than such confidence score, the disambiguating query should focus on black shirt 408 of actor 402. In some embodiments, the media application may compute an aggregated score based on at least two of the computed confidence score, success rate score and prominence score, to determine how to best generate a disambiguating query. For example, the media application may determine that the disambiguating query should focus on actor 402 rather than actor 404, since the combined confidence score, prominence score and past success rate score for actor 402 exceeds that of actor 404. In some embodiments, a predetermined formula may be utilized, to select certain attributes if a score for such attributes exceeds a predetermined amount. In some embodiments, machine learning techniques may be employed to identify patterns in data provided to a machine learning model, where the data may relate to past disambiguating queries that proved successful, e.g., to predict which attribute the disambiguating query should relate to in the current instance.

In some embodiments, the media application may select a minimal set of attributes for each object when generating a disambiguating query to minimize the number of disambiguating queries and length of disambiguating queries. For example, if the media application determines that that two or more actors in a scene are wearing a red shirt, the media application may focus on a different attribute for the disambiguating query that is more likely to be distinctive within the current scene, even if the shirts otherwise are associated with high prominence, confidence or success rate scores (e.g., a prediction of how well an object in the context of a current scene can assist with disambiguation). For example, the media application may identify a distinctive feature (e.g., a top hat) by determining that only a single instance of such object is present in a scene. The media application may additionally or alternatively focus on the most basic attributes to ensure the attributes used are understandable to the user (e.g., actor sitting down or actor standing up, adult actor versus young child actor). For example, the media application may reference a graph database structure to identify which attributes a user may be more likely to recognize. In some embodiments, the media application may take into account notable events that occurred or are occurring when query 422 is received (e.g., “Are you asking about the actor who just dunked a basketball?”).

In some embodiments, a character resolver framework may be employed when framing questions back to the user for confirmation of pronouns used in the query. An occurrence of a pronoun to identify a user or an object may be resolved into a temporary name based on the context available with additional support for partially filled characters. In some embodiments, if the media application receives a query “Who is that?”, the media application may respond with “Are you asking about the actor?”, based on resolving the pronoun in the context of a current scene of a media asset being played while the query is received. Pronoun resolution is discussed in more detail in U.S. Patent Application Publication No. US 2020/0074321 A1, filed Feb. 28, 2019, which is hereby incorporated by reference herein in its entirety.

At 440, the media application may output a disambiguating query based on the processing performed at 438. The media application may receive a confirmatory reply (e.g., reply 138 of FIG. 1 of “Yes” confirming that the subject of query 122 is actor 102), and output a reply 140 to the (now-disambiguated) query 122. In some embodiments, the media application may determine that reply 138 is not a confirmatory reply but rather is another ambiguous statement, e.g., “I am asking about the actor who is sitting down” when both actors are sitting down), and in response the media application may proceed through the steps of FIG. 4 to identify an additional disambiguating query focusing on attributes different from those of the disambiguating query output at 440 (e.g., since the user was not receptive to the initial disambiguating query).

FIG. 5 shows exemplary data structures 500, 501 used for generating a disambiguating query based on a first object and a second object depicted in a media asset, in accordance with some embodiments of this disclosure. Data structure 500 may be generated based one or more of metadata associated with a media asset and image processing performed by the media application. In some embodiments, each of a predefined number of frames or segments of a media asset may be associated with a corresponding data structure, e.g., 00:41-00:45 playback position. Exemplary data fields of data structure 500 may correspond to data related to an identified object (e.g., “Actor: Leonardo DiCaprio,” which may correspond to actor 102 of FIG. 1), current media asset 502 (e.g., “The Great Gatsby,” which may correspond to actor 105 of FIG. 1); appearance 504 (e.g., apparel being worn by actor 102), location 506 related to other objects (e.g., location of other objects, or edges of the screen, with respect to actor 102), and other roles (e.g., other media content that actor 102 has been cast in, such as “The Revenant” and “Titanic”). For example, media application, in generating reply 144 of FIG. 1, which includes a reference to “The Revenant” and “Titanic,” may reference data field 508. Exemplary data fields of data structure 501 may correspond to data related to an identified object (e.g., “Actor: Tobey Maguire,” which may correspond to actor 104 of FIG. 1), current media asset 510 (e.g., “The Great Gatsby” which may correspond to actor 105 of FIG. 1); appearance 512 (e.g., apparel being worn by actor 104), location 514 relative to other objects (e.g., location of other objects, or edges of the screen, with respect to actor 104), other roles (e.g., other media content that actor 104 has been cast in, such as “Spider-Man”). In some embodiments, each data structure may comprise static attributers (e.g., the name of the media asset, the name of the actor, etc., which are consistent throughout the duration of the media asset) and/or dynamic attributes (e.g., which change based on a current scene of the media asset, such as which objects are in a vicinity of the object at issue or what an actor's appearance looks like).

Such data structures 500, 501 may be referenced in generating a disambiguating query (e.g., query 140 of FIG. 1), e.g., confidence score 518, prominence score 520, past success rate score 522 of data structure 500, and confidence score 524, prominence score 526, past success rate score 528 of data structure 501. Such data structures 500, 501 may indicate individual scores for multiple objects as well as an aggregate score for an object comprising such multiple objects, e.g., a confidence score for different elements of the appearance of actor 102, as well as an overall confidence score for actor 102.

FIG. 6 shows an exemplary data structure 600 used for generating a disambiguating query based on a first object and a second object depicted in a media asset, in accordance with some embodiments of this disclosure. For example, data structure 600 may include information regarding a car, e.g., car 121 of FIG. 1 during 00:46-00:49 of playback, such as, for example, make 603 (e.g., “Mercedes-Benz”), model 604 (e.g., C200), color (e.g., white), In motion (e.g., Yes). In some embodiments, the media application may reference data structure 600 when determining whether to provide snapshot 127 of FIG. 1 to a user. For example, since actor 102 and/or actor 104 of FIG. 1, determined to be the subject of user query 122, are not referenced in data structure 600, which may correspond to frames immediately after the frames associated with FIG. 5, the media application may determine that a snapshot should be provided. In some embodiments, data structure 600 may be used to generate a reply to a received query of “I like that car”, where the reply may be “Which one, are you talking about the C200?” which may be provided based one or more of the confidence score 610, prominence score 612, or past success rate score 614, e.g., relatively high confidence scores of 0.7 and 0.8 for the make and model of the car, respectively. In some embodiments, each data structure may comprise static attributers (e.g., the name of the media asset, the name of the actor, etc., that are consistent throughout the duration of the media asset) and/or dynamic attributes (e.g., which change based on a current scene of the media asset, such as whether the car is in motion or not).

FIGS. 7-8 describe exemplary devices, systems, servers, and related hardware for generating a disambiguating query based on a first object and a second object depicted in a media asset, in accordance with some embodiments of the present disclosure. FIG. 7 shows generalized embodiments of illustrative user equipment devices 700 and 701. For example, user equipment device 700 may be a smartphone device. In another example, user equipment system 701 may be a user television equipment system (e.g., user equipment 106 of FIG. 1). User television equipment system 701 may include set-top box 716. Set-top box 716 may be communicatively connected to microphone 718, speaker 714, and display 712. In some embodiments, microphone 718 may receive voice commands for the media application. In some embodiments, display 712 may be a television display or a computer display. In some embodiments, set-top box 716 may be communicatively connected to user input interface 710. In some embodiments, user input interface 710 may be a remote control device. Set-top box 716 may include one or more circuit boards. In some embodiments, the circuit boards may include processing circuitry, control circuitry, and storage (e.g., RAM, ROM, hard disk, removable disk, etc.). In some embodiments, the circuit boards may include an input/output path. More specific implementations of user equipment devices are discussed below in connection with FIG. 7. Each one of user equipment device 700 and user equipment system 701 may receive content and data via input/output (I/O) path 702. I/O path 702 may provide content (e.g., broadcast programming, on-demand programming, Internet content, content available over a local area network (LAN) or wide area network (WAN), and/or other content) and data to control circuitry 704, which includes processing circuitry 706 and storage 708. Control circuitry 704 may be used to send and receive commands, requests, and other suitable data using I/O path 702, which may comprise I/O circuitry. I/O path 702 may connect control circuitry 704 (and specifically processing circuitry 706) to one or more communications paths (described below). I/O functions may be provided by one or more of these communications paths, but are shown as a single path in FIG. 7 to avoid overcomplicating the drawing.

Control circuitry 704 may be based on any suitable processing circuitry such as processing circuitry 706. As referred to herein, processing circuitry should be understood to mean circuitry based on one or more microprocessors, microcontrollers, digital signal processors, programmable logic devices, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), etc., and may include a multi-core processor (e.g., dual-core, quad-core, hexa-core, or any suitable number of cores) or supercomputer. In some embodiments, processing circuitry may be distributed across multiple separate processors or processing units, for example, multiple of the same type of processing units (e.g., two Intel Core i7 processors) or multiple different processors (e.g., an Intel Core i5 processor and an Intel Core i7 processor). In some embodiments, control circuitry 704 executes instructions for the media application stored in memory (e.g., storage 708). Specifically, control circuitry 604 may be instructed by the media application to perform the functions discussed above and below. In some implementations, any action performed by control circuitry 604 may be based on instructions received from the media application.

In client/server-based embodiments, control circuitry 704 may include communications circuitry suitable for communicating with a media application server or other networks or servers. The instructions for carrying out the above mentioned functionality may be stored on a server (which is described in more detail in connection with FIG. 7. Communications circuitry may include a cable modem, an integrated services digital network (ISDN) modem, a digital subscriber line (DSL) modem, a telephone modem, Ethernet card, or a wireless modem for communications with other equipment, or any other suitable communications circuitry. Such communications may involve the Internet or any other suitable communication networks or paths (which is described in more detail in connection with FIG. 7). In addition, communications circuitry may include circuitry that enables peer-to-peer communication of user equipment devices, or communication of user equipment devices in locations remote from each other (described in more detail below).

Memory may be an electronic storage device provided as storage 708 that is part of control circuitry 704. As referred to herein, the phrase “electronic storage device” or “storage device” should be understood to mean any device for storing electronic data, computer software, or firmware, such as random-access memory, read-only memory, hard drives, optical drives, digital video disc (DVD) recorders, compact disc (CD) recorders, BLU-RAY disc (BD) recorders, BLU-RAY 3D disc recorders, digital video recorders (DVR, sometimes called a personal video recorder, or PVR), solid state devices, quantum storage devices, gaming consoles, gaming media, or any other suitable fixed or removable storage devices, and/or any combination of the same. Storage 708 may be used to store various types of content described herein as well as media application data described above. Nonvolatile memory may also be used (e.g., to launch a boot-up routine and other instructions). Cloud-based storage, described in relation to FIG. 7, may be used to supplement storage 708 or instead of storage 708.

Control circuitry 704 may include video generating circuitry and tuning circuitry, such as one or more analog tuners, one or more MPEG-2 decoders or other digital decoding circuitry, high-definition tuners, or any other suitable tuning or video circuits or combinations of such circuits. Encoding circuitry (e.g., for converting over-the-air, analog, or digital signals to MPEG signals for storage) may also be provided. Control circuitry 704 may also include scaler circuitry for upconverting and downconverting content into the preferred output format of user equipment 700. Control circuitry 704 may also include digital-to-analog converter circuitry and analog-to-digital converter circuitry for converting between digital and analog signals. The tuning and encoding circuitry may be used by user equipment device 700, 701 to receive and to display, to play, or to record content. The tuning and encoding circuitry may also be used to receive guidance data. The circuitry described herein, including for example, the tuning, video generating, encoding, decoding, encrypting, decrypting, scaler, and analog/digital circuitry, may be implemented using software running on one or more general purpose or specialized processors. Multiple tuners may be provided to handle simultaneous tuning functions (e.g., watch and record functions, picture-in-picture (PIP) functions, multiple-tuner recording, etc.). If storage 708 is provided as a separate device from user equipment device 700, the tuning and encoding circuitry (including multiple tuners) may be associated with storage 708.

A user may send instructions to control circuitry 704 using user input interface 710. User input interface 710 may be any suitable user interface, such as a remote control, mouse, trackball, keypad, keyboard, touch screen, touchpad, stylus input, joystick, voice recognition interface, or other user input interfaces. Display 712 may be provided as a stand-alone device or integrated with other elements of each one of user equipment device 700 and user equipment system 701. For example, display 712 may be a touchscreen or touch-sensitive display. In such circumstances, user input interface 710 may be integrated with or combined with display 712. Display 712 may be one or more of a monitor, a television, a display for a mobile device, or any other type of display. A video card or graphics card may generate the output to display 712. The video card may be any processing circuitry described above in relation to control circuitry 704. The video card may be integrated with the control circuitry 704. Speakers 714 may be provided as integrated with other elements of each one of user equipment device 700 and user equipment system 701 or may be stand-alone units. The audio component of videos and other content displayed on display 712 may be played through the speakers 714. In some embodiments, the audio may be distributed to a receiver (not shown), which processes and outputs the audio via speakers 714.

The media application may be implemented using any suitable architecture. For example, it may be a stand-alone application wholly-implemented on each one of user equipment device 700 and user equipment system 701. In such an approach, instructions of the application are stored locally (e.g., in storage 708), and data for use by the application is downloaded on a periodic basis (e.g., from an out-of-band feed, from an Internet resource, or using another suitable approach). Control circuitry 704 may retrieve instructions of the application from storage 608 and process the instructions to rearrange the segments as discussed. Based on the processed instructions, control circuitry 704 may determine what action to perform when input is received from user input interface 710. For example, movement of a cursor on a display up/down may be indicated by the processed instructions when user input interface 710 indicates that an up/down button was selected.

In some embodiments, the media application is a client/server-based application. Data for use by a thick or thin client implemented on each one of user equipment device 700 and user equipment system 701 is retrieved on-demand by issuing requests to a server remote to each one of user equipment device 700 and user equipment system 701. In one example of a client/server-based guidance application, control circuitry 704 runs a web browser that interprets web pages provided by a remote server. For example, the remote server may store the instructions for the application in a storage device. The remote server may process the stored instructions using circuitry (e.g., control circuitry 704) to perform the operations discussed in connection with FIGS. 1-3 and 6-7.

In some embodiments, the media application may be downloaded and interpreted or otherwise run by an interpreter or virtual machine (run by control circuitry 704). In some embodiments, the media application may be encoded in the ETV Binary Interchange Format (EBIF), received by the control circuitry 704 as part of a suitable feed, and interpreted by a user agent running on control circuitry 704. For example, the media application may be an EBIF application. In some embodiments, the media application may be defined by a series of JAVA-based files that are received and run by a local virtual machine or other suitable middleware executed by control circuitry 704. In some of such embodiments (e.g., those employing MPEG-2 or other digital media encoding schemes), the media application may be, for example, encoded and transmitted in an MPEG-2 object carousel with the MPEG audio and video packets of a program.

FIG. 8 is a diagram of an illustrative streaming system, in accordance with some embodiments of this disclosure. User equipment devices 808, 809, 810 (e.g., user equipment device 106) may be coupled to communication network 806. Communication network 806 may be one or more networks including the Internet, a mobile phone network, mobile voice or data network (e.g., a 7G or LTE network), cable network, public switched telephone network, or other types of communication network or combinations of communication networks. Paths (e.g., depicted as arrows connecting the respective devices to the communication network 806) may separately or together include one or more communications paths, such as a satellite path, a fiber-optic path, a cable path, a path that supports Internet communications (e.g., IPTV), free-space connections (e.g., for broadcast or other wireless signals), or any other suitable wired or wireless communications path or combination of such paths. Communications with the client devices may be provided by one or more of these communications paths but are shown as a single path in FIG. 8 to avoid overcomplicating the drawing.

Although communications paths are not drawn between user equipment devices, these devices may communicate directly with each other via communications paths as well as other short-range, point-to-point communications paths, such as USB cables, IEEE 1394 cables, wireless paths (e.g., Bluetooth, infrared, IEEE 702-11x, etc.), or other short-range communication via wired or wireless paths. The user equipment devices may also communicate with each other directly through an indirect path via communication network 806.

System 800 includes a media content source 802 and a server 804, which may comprise or be associated with database 805. Communications with media content source 802 and server 804 may be exchanged over one or more communications paths but are shown as a single path in FIG. 8 to avoid overcomplicating the drawing. In addition, there may be more than one of each of media content source 802 and server 804, but only one of each is shown in FIG. 8 to avoid overcomplicating the drawing. If desired, media content source 802 and server 804 may be integrated as one source device.

In some embodiments, server 804 may include control circuitry 811 and a storage 814 (e.g., RAM, ROM, Hard Disk, Removable Disk, etc.). Storage 814 may store a one or more databases (e.g., disambiguation success rate database 432 of FIG. 4, data structures 500, 501 of FIG. 5, data structure 600 of FIG. 6). Server 804 may also include an input/output path 812. I/O path 812 may provide device information, or other data, over a local area network (LAN) or wide area network (WAN), and/or other content and data to the control circuitry 811, which includes processing circuitry, and storage 814. The control circuitry 811 may be used to send and receive commands, requests, and other suitable data using I/O path 812, which may comprise I/O circuitry. I/O path 812 may connect control circuitry 804 (and specifically processing circuitry) to one or more communications paths.

Control circuitry 811 may be based on any suitable processing circuitry such as one or more microprocessors, microcontrollers, digital signal processors, programmable logic devices, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), etc., and may include a multi-core processor (e.g., dual-core, quad-core, hexa-core, or any suitable number of cores) or supercomputer. In some embodiments, control circuitry 811 may be distributed across multiple separate processors or processing units, for example, multiple of the same type of processing units (e.g., two Intel Core i7 processors) or multiple different processors (e.g., an Intel Core i5 processor and an Intel Core i7 processor). In some embodiments, the control circuitry 811 executes instructions for an emulation system application stored in memory (e.g., the storage 814). Memory may be an electronic storage device provided as storage 814 that is part of control circuitry 811.

Server 804 may retrieve guidance data from media content source 802, process the data as will be described in detail below, and forward the data to user equipment devices 808, 809, 810. Media content source 802 may include one or more types of content distribution equipment including a television distribution facility, cable system headend, satellite distribution facility, programming sources (e.g., television broadcasters, such as NBC, ABC, HBO, etc.), intermediate distribution facilities and/or servers, Internet providers, on-demand media servers, and other content providers. NBC is a trademark owned by the National Broadcasting Company, Inc., ABC is a trademark owned by the American Broadcasting Company, Inc., and HBO is a trademark owned by the Home Box Office, Inc. Media content source 802 may be the originator of content (e.g., a television broadcaster, a Webcast provider, etc.) or may not be the originator of content (e.g., an on-demand content provider, an Internet provider of content of broadcast programs for downloading, etc.). Media content source 802 may include cable sources, satellite providers, on-demand providers, Internet providers, over-the-top content providers, or other providers of content. Media content source 802 may also include a remote media server used to store different types of content (including video content selected by a user), in a location remote from any of the client devices. Media content source 802 may also provide metadata that can be used to in analyzing a received query and generating a disambiguating query as described above.

Client devices may operate in a cloud computing environment to access cloud services. In a cloud computing environment, various types of computing services for content sharing, storage or distribution (e.g., video sharing sites or social networking sites) are provided by a collection of network-accessible computing and storage resources, referred to as “the cloud.” For example, the cloud can include a collection of server computing devices (such as, e.g., server 804), which may be located centrally or at distributed locations, that provide cloud-based services to various types of users and devices connected via a network such as the Internet via communication network 806. In such embodiments, user equipment devices may operate in a peer-to-peer manner without communicating with a central server.

FIG. 9 is a flowchart of a detailed illustrative process for generating a disambiguating query based on a first object and a second object depicted in a media asset, in accordance with some embodiments of this disclosure. In various embodiments, the individual steps of process 900 may be implemented by one or more components of the devices and systems of FIGS. 1-8. Although the present disclosure may describe certain steps of process 900 (and of other processes described herein) as being implemented by certain components of the devices and systems of FIGS. 1-8, this is for purposes of illustration only, and it should be understood that other components of the devices and systems of FIGS. 1-8 may implement those steps instead. For example, the steps of process 900 may be executed at device 809 and/or server 912 of FIG. 8 to perform the steps of process 900.

At 902, control circuitry (e.g., control circuitry 704 of FIG. 7 and/or control circuitry 811 of FIG. 8) may receive input for playing a media asset (e.g., media asset 105 of FIG. 1). In some embodiments, the media asset may be played on user equipment 808 (e.g., a computer) or 810 (e.g., smart TV) in response to a command received from user equipment 809 (e.g., a mobile device running the media application to perform remote control operations).

At 904, control circuitry (e.g., control circuitry 704 of FIG. 7) plays the requested media asset (e.g., media asset 105). In some embodiments, the media asset may be transmitted (e.g., streamed or downloaded) from a media server (e.g., media content source 802 of FIG. 8) and caused to be presented at user equipment (e.g., smart television 106 of FIG. 1).

At 906, control circuitry (e.g., control circuitry 704 of FIG. 7 and/or control circuitry 811 of FIG. 8) monitors whether a query (e.g., query 122) has been receiving while the media asset is being played. If the control circuitry determines that no query has been received, the media asset continues to be presented and the control circuitry continues to wait for such a query. If the control circuitry determines that the query has been received during the playing of the media asset, processing proceeds to 908. The query may be received by the control circuitry in any suitable format (e.g., text, voice, tactile, biometric input, or any combination thereof).

At 908, control circuitry (e.g., control circuitry 704 of FIG. 7 and/or control circuitry 811 of FIG. 8) determines whether the query (e.g., query 122) is related to the media asset (e.g., media asset 105). For example, the control circuitry performs automatic speech recognition and/or NLP processing and/or template-based slot filling to determine an intent and a context of the query, e.g., the control circuitry determines that query 122 of “Who is that actor?” relates to the ongoing media asset being presented by way of the control circuitry, and proceeds to 910. If the control circuitry determines the query does not relate to the media asset (e.g., “What is the weather like today?”), processing returns to 904, e.g., the media asset continues to be played, and the control circuitry optionally may reply to the unrelated query with a suitable response.

At 910, control circuitry (e.g., control circuitry 704 of FIG. 7 and/or control circuitry 811 of FIG. 8) identifies first and second objects in one or more frames of the media asset that is being presented when (or within a predefined period of time of) the query being received. For example, the control circuitry references metadata (e.g., the data shown in FIG. 5) associated with the media asset (e.g., media asset 105) and/or performs image processing techniques to identify a first actor (e.g., actor 102 of FIG. 1, including black shirt 108 and other aspects of the appearance of actor 102) and a second actor (e.g., actor 104 of FIG. 1, including white shirt 114 and other aspects of the appearance of actor 104).

At 912, control circuitry (e.g., control circuitry 704 of FIG. 7 and/or control circuitry 811 of FIG. 8) determines whether the identified first and second objects are to continue being presented longer than a predefined period (e.g., 15 seconds). For example, the control circuitry retrieves metadata associated with an upcoming scene (or otherwise predicts based on a current scene) whether the identified objects will still be depicted in the media asset during such predefined period. If the control circuitry determines the identified objects are not to be present for longer than a predefined period, processing proceeds to 914. Otherwise, processing proceeds to 922.

At 914, control circuitry (e.g., control circuitry 704 of FIG. 7 and/or control circuitry 811 of FIG. 8) causes capture of a snapshot (e.g., snapshot 127 of FIG. 1) of the current frames or segment being presented (e.g., scene 103 of FIG. 1). For example, a snapshot of the current screen may be captured locally, or a remote server (e.g., server 804 of FIG. 8) may transmit a snapshot of the scene at issue.

At 916, control circuitry (e.g., control circuitry 704 of FIG. 7 and/or control circuitry 811 of FIG. 8) determines whether a second device is detected. For example, user equipment 106 of FIG. 1 determines whether user equipment 124 is within a predefined vicinity, and/or on a same local network (e.g., a home Wi-Fi network, a Bluetooth) as user equipment 106 (and optionally, whether user equipment 124 is running the same media application as user equipment 106, to control presentation of media asset 105 on user equipment 106).

At 918, in response to detecting the second device, control circuitry (e.g., control circuitry 704 of FIG. 7 and/or control circuitry 811 of FIG. 8) generates for display the snapshot (e.g., snapshot 127 of FIG. 1) on the second device (e.g., user equipment device 124). For example, user equipment device 106 of FIG. 1 may capture the snapshot and transmit the snapshot to user equipment device 124 for presentation to user 120. On the other hand, at 920, in response to determining that a second device has not been detected, the first device (e.g., user equipment device 206 of FIG. 2) may capture the snapshot (e.g., snapshot 227 of FIG. 2) and pin snapshot 227 to a portion of the display to avoid obstructing the view of the ongoing media asset 205.

At 922, control circuitry (e.g., control circuitry 704 of FIG. 7 and/or control circuitry 811 of FIG. 8) determines whether in the query (e.g., query 122) there is ambiguity as to whether the query is related to the first object or the second object. For example, the control circuitry compares the results of the query analysis performed at