CN105074613A - Method and system for content discovery - Google Patents

Abstract

A system, method and graphic user interface for facilitating content discovery. The system and method including the selection (1402) of a number of display regions based on a display type, and the selection (1404) of item categories to be displayed in the display regions in accordance with a content discover process. The content discovery process is a greedy process that includes a multi-way search process (700) that tracks a user's item category selections and removes non-selected item categories displayed in the displayed regions from future display in the display regions during the content discovery process, and an item category selection process (900) that selects at least one item category that has not been displayed in the display regions and was not previously non-selected during the multi-way search process (700).

Description

Method and system for content discovery

References to related provisional applications

This application claims priority to US Provisional Application No. 61/756,021, entitled "METHODAND SYSTEM FOR CONTENT DISCOVERY," filed January 24, 2013, the entire contents of which are incorporated herein by reference.

technical field

The present disclosure relates generally to digital content systems and methods for efficiently searching through large volumes of media content graphically, and more particularly to systems, methods, and graphical user interfaces for assisting content discovery.

Background technique

Home entertainment systems, including televisions and media centers, are merging with the Internet and providing access to a vast number of available sources of content (eg, videos, movies, television shows, music, etc.). The expansion in the number of available sources necessitates new strategies for navigating the media interfaces associated with such systems and making content recommendations and selections.

The large number of possible content sources presents interface challenges that have not been successfully resolved in the home media entertainment arena. The challenge involves successfully presenting a large number of elements (programs, feeds, etc.) to the user without requiring tedious navigation through multiple display pages or content hierarchies.

Furthermore, most existing search paradigms assume that users know what they are looking for at the outset, however, in general, mechanisms that allow a process of discovery and crosslinkage are preferable and appropriate.

One way to allow the process of discovery and cross-linking is to track a user's viewing/purchasing habits over time. However, tracking users' viewing/purchasing habits over a long period of time to generate relevant recommendations also has the drawback of being time-consuming.

The present disclosure aims to overcome these drawbacks.

Contents of the invention

Systems, methods, and graphical user interfaces for assisting content discovery. The systems and methods include selecting (1402) a plurality of display areas based on display type, and selecting (1404) categories of items to be displayed in the display areas based on a content discovery process. The content discovery process is a greedy process that includes a multi-path search process (700) and an item category selection process (900) that tracks the user's item category selection during the content discovery process and displays in the future in the display area Unselected item categories displayed in the display area are removed, and the item category selection process (900) selects at least one item category that has not been displayed in the display area and was not previously unselected during the multi-pass search process (700).

Description of drawings

These and other aspects, features and advantages of the present disclosure will be described and will become apparent from the following detailed description read in conjunction with the accompanying drawings.

In the drawings, like reference numerals indicate like elements throughout the views.

FIG. 1 is a block diagram of an exemplary system for delivering content according to the present disclosure;

2 is a block diagram of an exemplary set-top box/digital video recorder (DVR) according to the present disclosure;

3 is a perspective view of an exemplary remote control, tablet, and/or second screen device according to an embodiment of the present disclosure;

Figure 4 illustrates a number of gestures according to an embodiment of the disclosure;

FIG. 5 illustrates an exemplary embodiment of an exemplary user interface of the present disclosure;

FIG. 6 is an exemplary embodiment of the generalized multi-path search algorithm of the present disclosure;

Fig. 7 is based on the algorithm of Fig. 6, shows the exemplary embodiment of the flowchart of generalized multi-path search processing of the present disclosure;

Figure 8 is an exemplary embodiment of the greedy selection algorithm of the present disclosure;

Figure 9 is based on the algorithm of Figure 8, showing an exemplary embodiment of a flowchart of the selection process of the present disclosure;

FIG. 10 is an exemplary embodiment of a user interface of the present disclosure;

FIG. 11 is another exemplary embodiment of a user interface of the present disclosure;

FIG. 12 is yet another exemplary embodiment of a user interface of the present disclosure;

FIG. 13 is an exemplary embodiment of a user interface displaying final recommendations according to the present disclosure; and

FIG. 14 is an exemplary embodiment of a flowchart showing recommendation processing of the present disclosure.

It should be understood that the drawing(s) are for purposes of illustrating the concepts of the disclosure and are not necessarily the only possible configuration for illustrating the disclosure.

Detailed ways

It should be understood that the elements shown in the figures may be implemented in various forms of hardware, software, or a combination thereof. Preferably, these elements are implemented as a combination of hardware and software on one or more suitably programmed general-purpose devices, which may include a processor, memory, and input/output interfaces. Herein, the phrase "coupled" is defined to mean connected directly to or indirectly connected through one or more intervening components. Such intermediate components may include component-based software and hardware.

This specification illustrates the principles of the disclosure. It will thus be appreciated that those skilled in the art will be able to devise various arrangements that, although not explicitly described or shown herein, embody the principles of the disclosure and are included within its spirit and scope.

All examples and conditional language set forth herein are for instructive purposes to assist the reader in understanding the principles of the disclosure and concepts proposed by the inventors to advance the field, and are not to be viewed as limiting to the expressly stated examples and conditions.

Moreover, all statements herein reciting principles, aspects, and embodiments of the disclosure, as well as specific examples thereof, are intended to encompass both structural and functional equivalents thereof. Additionally, it is intended that all such equivalents include both currently known equivalents as well as equivalents developed in the future, ie, any elements developed that perform the same function, regardless of structure.

Thus, for example, it will be appreciated by those skilled in the art that the block diagrams presented herein represent conceptual views of illustrative circuitry embodying the principles of the disclosure. Similarly, it will be understood that any flow diagrams, flowcharts, state transition diagrams, pseudorandom code, etc. representations substantially embodied in a computer-readable medium and thus executed by a computer or processor (whether such computer or processor is explicitly shown or not) of various treatments.

The functions of the various elements shown in the figures may be provided through the use of dedicated hardware as well as hardware capable of executing the software, in association with appropriate software. When provided by a processor, the functions may be provided by a single dedicated processor, by a single shared processor, or by multiple individual processors, some of which may be shared. Furthermore, explicit use of the terms "processor" or "controller" should not be taken to refer exclusively to hardware capable of executing software, and may implicitly include, but not be limited to, digital signal processor ("DSP") hardware, A read-only processor ("ROM"), a random access memory ("RAM"), and a non-volatile storage device for storing software.

Other conventional and/or custom hardware may also be included. Similarly, any switches shown in the figures are conceptual only. Their function may be carried out through the operation of program logic, through dedicated logic, through the interaction of program control and dedicated logic, or even manually, the particular technique being optional to the implementer as clearly understood from the context.

In its claims, an element expressed as a means for performing a specified function is intended to cover any way of performing that function, including, for example, a) a combination of circuit elements performing that function or b) any form of software ( Thus including firmware, microcode, etc.), the software is combined with appropriate circuitry for running the software to perform the function. The present disclosure defined by such claims resides in the fact that the functionality provided by the various recited means is combined and brought together in the manner claimed. Accordingly, any means capable of providing those functions are considered equivalent to those shown herein.

The proposed disclosure is directed to methods and systems for content discovery. More specifically, the method and system for content discovery recommends desired items to users from categories of items (eg, movies, music, dishes, etc.) through a minimum number of questions or recommendations.

Turning now to FIG. 1 , a block diagram of an embodiment of a system 100 for delivering content to households or end users is shown. The content may originate from a content source 102, such as a movie studio, production company, or the like. Content may be served in at least one of two forms. One form may be a broadcast form of content. Broadcast content is provided to a broadcast affiliate manager 104, which is typically a national broadcast service such as American Broadcasting Corporation (ABC), National Broadcasting Corporation (NBC), Columbia Broadcasting System (CBS), and the like. The Broadcast Affiliate Manager may collect and store content, and may schedule delivery of the content through a delivery network, shown as Delivery Network 1 (106). Delivery network 1 (106) may include satellite link transmissions from a national center to one or more regional or local centers. Delivery network 1 (106) may also include localized content delivery using localized delivery systems such as over-the-air broadcast, satellite broadcast, or cable broadcast. The locally delivered content is provided to a receiving device 108 in the user's home where the user will then search for the content. It will be appreciated that receiving device 108 can take many forms and may be implemented as a set-top box/digital video recorder (DVR), gateway, modem, or the like. Additionally, the receiving device 108 may serve as an entry point or gateway to a home network system that includes additional devices in the home network that are configured as either clients or peer devices.

The second form of content is called featured content. Featured content may include content delivered as premium viewing, premium viewing, or otherwise not provided to the Broadcast Affiliate Manager, such as movies, video games, music, e-books, movie posters, album covers, dish data, or other media elements. In many cases, featured content may be user-requested content. Featured content may be delivered to content manager 110 . The content manager 110 may be a service provider, such as an Internet website affiliated with a content provider, broadcast service, or delivery network service. Content manager 110 may also incorporate Internet content into the delivery system. The content manager 110 may deliver the content to the user's receiving device 108 through a separate delivery network, Delivery Network 2 (112). Delivery network 2 (112) may comprise a high-speed broadband Internet type communication system. It is important to note that all or part of Delivery Network 2 (112) may also be used to deliver content from Broadcast Affiliate Manager 104 and all or part of Delivery Network 1 (106) may be used to deliver content from Content Manager 110 Content. In addition, users can also directly obtain content from the Internet via the delivery network 2 ( 112 ), without having the content managed by the content manager 110 .

Several adaptations are possible with separately delivered content. In one possible approach, featured content is provided as an augmentation to broadcast content, providing alternative display, purchase and promotion options, enhanced material, and the like. In another embodiment, featured content may completely replace some of the programming content provided as broadcast content. Finally, featured content may be completely separate from broadcast content and may simply be an alternative medium that users may choose to utilize. For example, featured content could be a library of movies that are not yet available for broadcast content.

Receiving device 108 may receive different types of content from one or both of Delivery Network 1 and Delivery Network 2 . The receiving device 108 processes the content and provides separation of the content based on the user's preferences and commands. Receiving device 108 may also include a storage device, such as a hard drive or an optical disk drive, to record and playback audio and video content. Further details of the operation of the receiving device 108 and features associated with playback of stored content are described below in conjunction with FIG. 2 . The processed content is provided to a display device 114 . Display device 114 may be a conventional 2D type display or alternatively may be an advanced 3D display.

Receiving device 108 may also interface to a second screen, such as touch screen control device 116 . Touch screen control device 116 may be adapted to provide user control of receiving device 108 and/or display device 114 . The touch screen control device 116 may also have the capability to display video content. The video content may be a graphical item, such as a user interface item (as discussed below), or may be part of the video content delivered to the display device 114 . Touch screen control device 116 may interface to receiving device 108 using any known signal transmission system (e.g., infrared (IR) or radio frequency (FR) communication), and may include standard protocols (e.g., Infrared Data Association (IRDA) standard, Wi-Fi, Bluetooth, etc.) or any other proprietary protocol. The operation of touch screen control device 116 will be described in more detail below.

Alternatively, receiving or media device 108 and touch screen control device 116 may be integrated into the same device. Examples of media devices with touch screens include, but are not limited to: computers, laptops, wireless phones, cell phones, smart phones, personal media players, MP3 players, personal digital assistants (PDAs), tablet devices, digital video recorders , Gateway, etc. For purposes of illustration, the term reception or media device can cover all these types of devices.

In the example of FIG. 1 , the system 100 also includes a backend server 118 and a practice database 120 . As discussed in more detail below, the backend server 118 may include a content discovery application (e.g., a dish discovery application, a music discovery application, an e-book discovery application, a movie discovery application, etc.) that analyzes the user's selections (e.g., , media assets or content selections) and make recommendations based on those selections. The routine database 120 may be where the user selections are stored (alternatively, the selections or selection habits may be stored anywhere else in the system 100, e. middle), the control device 116, 300, and/or the display device 114). In some cases, custom database 120 may be part of backend server 118 . In this example, backend server 118 (and custom database 120) is connected to system 100 and accessed through delivery network 2 (112). In this example, the movie database may reside entirely on the backend server 118 , and each question and answer is communicated between the user's device ( 114 , 108 and 200 , and/or 115 and 300 ) and the server 118 . An advantage of this approach is that it is easily scalable to large databases without requiring the database to be transferred to the front end. One disadvantage of this approach is that the content discovery application will require an Internet connection. As discussed above, other implementations (such as having a content discovery application and movie database resident in the display device 114, the receiving device 108, 200, the touchscreen control device 116, 300, or any combination of these devices) are considered within within the scope of this disclosure. It should be noted that the content discovery applications and algorithms contained herein may be partially implemented in Python code.

Turning now to FIG. 2 , a block diagram of an embodiment of a receiving device 200 is shown. Receiving device 200 may operate similarly to the receiving device described in FIG. 1 and may be included as part of a gateway device, modem, set-top box, or other similar communication device. The device 200 shown may also be incorporated into other systems including audio devices or display devices. In either case, for the sake of brevity, several components necessary to complete the operation of the system have not been shown, as they are well known to those skilled in the art.

In the device 200 shown in Figure 2, an input signal receiver 202 receives content. The input signal receiver 202 may be one of several known receiver circuits that are used to transmit signals over a number of possible networks, including over the air, cable, satellite, Ethernet, fiber optic, and telephone line networks. The signal provided by one of them is received, demodulated, and decoded. The input signal receiver 202 may select and retrieve desired input signals based on user input provided through the control interface or touchpad interface 222 . Touchpad interface 222 may include an interface for touch screen devices. The touchpad interface 222 may also be adapted to interface to cellular phones, tablet computers, mice, high-end remote devices, and the like.

The decoded output signal is provided to the input stream processor 204 . The input stream processor 204 performs final signal selection and processing, and includes separating the video and audio content of the content stream. Audio content is provided to an audio processor 206 for conversion from a received format (eg, compressed digital signal) to an analog waveform signal. The analog waveform signal is provided to an audio interface 208 and further provided to a display device or an audio amplifier. Alternatively, audio interface 208 may provide a digital signal to an audio output device or display device using a High Definition Multimedia Interface (HDMI) cable or an alternative audio interface (eg, via Sony/Philips Digital Interconnect Format (SPDIF)). Audio interfaces may also include amplifiers for driving one or more sets of speakers. Audio processor 206 also performs any conversions necessary to store the audio signal.

Video output from input stream processor 204 is provided to video processor 210 . Video signals can be in one of several formats. The video processor 210 provides conversion of video content as necessary based on the input signal format. Video processor 210 also performs any conversions necessary to store the video signal.

Storage device 212 stores audio and video content received at the input. The storage device 212 allows for further processing under the control of the controller 214 and also based on commands received from the user interface 216 and/or the touchpad interface 222 (e.g., user selections or answers, such as fast forward (FF) and rewind (Rew). navigation instructions) to retrieve and playback content. Storage device 212 may be a hard disk drive, one or more mass integrated electronic memories such as static RAM (SRAM) or dynamic RAM (DRAM), or a swappable optical disk storage system such as compact disk (CD ) drive or digital video disc (DVD) drive).

The converted video signal from video processor 210 (whether originating from an input or from storage device 212 ) is provided to display interface 218 . The display interface 218 further provides display signals to display devices of the type described above. The display interface 218 may be an analog signal interface (eg, red-green-blue (RGB)), or a digital interface (eg, HDMI). It is to be understood that the display interface 218 will generate various screens for presenting content discovery results (eg, in a three-dimensional grid, a two-dimensional array, a one-dimensional shelf, etc.).

Controller 214 is interconnected via a bus to several components of device 200 , including input stream processor 204 , audio processor 206 , video processor 210 , storage device 212 , and user interface 216 . Controller 214 manages the conversion process for converting the input stream signal into a signal for storage on a storage device or for display. Controller 214 also manages the retrieval and playback of stored content. In addition, as will be described below, the controller 214 performs content discovery, and creation and adjustment of grids, arrays, and/or rack displays to present content (whether stored or to be delivered via a delivery network).

Controller 214 is also coupled to control memory 220 (e.g., volatile or nonvolatile memory including RAM, SRAM, DRAM, ROM, programmable ROM ( PROM), flash memory, electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), etc.). Control memory 220 may store instructions for use by controller 214 . The control memory may also store a database of elements, such as graphical elements containing content. The database may be stored as a schema of graphical elements (eg, graphical elements containing content, various graphical elements used to generate a displayable user interface for display interface 218, etc.). Alternatively, the memory may store the graphical elements in identified or grouped memory locations and use an access or location table to identify memory locations for various portions of information related to the graphical elements. Additional details related to the storage of graphical elements will be described below. Furthermore, the implementation of control memory 220 may include several possible embodiments, such as a single memory device, or more than one memory circuit communicatively connected or coupled together to form a shared or common memory. In addition, memory may be included within larger circuitry along with other circuitry, such as portions of bus communication circuitry.

Optionally, controller 214 can be adapted to extract metadata, standards, properties, etc. from audio and video media by using audio processor 206 and video processor 210, respectively. That is, the vertical blanking interval associated with the video, ancillary data fields, or metadata contained in the video signal, standards, characteristics, etc., in order to generate metadata that can be used for functions such as generating an electronic program guide, having descriptive information about received video, supporting auxiliary information services, etc. Similarly, the audio processor 206 working with the controller 214 can be adapted to recognize audio watermarks that may be in the audio signal. Such an audio watermark can then be used to perform some action (such as identification of the security of the audio signal, identifying the source of the audio signal) or to perform some other service. Also, the metadata, standards, properties, etc. that support the actions listed above can come from network sources processed by the controller 214 .

Turning now to FIG. 3 , the user interface process of the present disclosure employs input devices that can be used to express functions such as user selections and answers, fast forward, rewind, and the like. To allow this, a tablet or touchpad device 300 (the same as touchscreen device 116 shown in FIG. 1 and/or an integrated example of media device 108 and touchscreen device 116 ) may Touchpad interface 222 for interfacing. The touchpad device 300 allows operation of a receiving device or set-top box based on hand movements, or gestures, and actions through the pad that are translated into commands for the set-top box or other control device. In one embodiment, the touchpad 300 can simply act as a navigation tool to navigate and select from a shelf, array or grid display. In other embodiments, the touchpad 300 will additionally act as a display device that allows the user to more directly interact with the navigation through the display of content. The touchpad device may be included as part of a remote control device containing more conventional control functions, such as activator, alphanumeric, directional, actuator buttons, and the like. The touchpad device 300 can also include at least one camera element. As described below, touchpad device 300 (or display device 114 ) may utilize content or media asset discovery functionality (see, eg, FIGS. 6-9 and 14 ) to provide content and media recommendations to a user.

Turning now to FIG. 4, the use of a gesture sensing controller or touch screen (as shown) provides various types of user interaction. Input from the controller is used to define gestures, which in turn define specific contextual commands. The configuration of sensors (e.g., touchscreen sensors and/or inertial sensors, such as accelerometers and gyroscope sensors) may permit defining the movement of the user's fingers on the touchscreen, and may also permit defining the orientation of the controller itself in one or two dimensions. on the move. Two-dimensional motion (eg, diagonal, a combination of offset, pitch, and roll) can be used to define any three-dimensional motion, eg, roll. Various gestures are shown in FIG. 4 . Gestures are interpreted in context and identified by defined movements made by the user.

Bumping 420 is defined by a two-stroke drag indicated to point in one direction (whether up, down, left, or right). The slam gesture is associated with a specific command in the context. For example, in time-shift mode, a left swipe gesture 420 indicates rewinding, while a right swipe gesture indicates fast forwarding. In other contexts, the slam gesture 420 is interpreted to increase by a certain value in the direction specified by the slam. Checking 440 is defined as a checkmark. It is similar to swipe down gesture 420 . Checklists are identified in context to indicate reminders, user tags, or select items or elements. Circling 440 is defined as drawing a circle in either direction. It is possible that two directions can be distinguished. However, to avoid confusion, drawing a circle is identified as a single command regardless of its orientation. Dragging 450 is defined as the angular movement of the controller (change in pitch and/or offset) while pressing a button (virtual or physical) on the tablet 300 (ie, "trigger dragging"). Drag gesture 450 can be used for navigation, speed, distance, time shift, rewind, and forward. Dragging 450 can be used to move a cursor, a virtual cursor, or a change of state, such as highlighting or selection on a display. Dragging 450 can be in any direction, and is generally used to navigate in both directions. However, on some interfaces it is preferable to modify the response to the drag command. For example, in some interfaces, depending on the position of the virtual cursor or the direction of movement, it is advantageous to operate in one dimension or direction relative to other dimensions or directions. Nodding 460 is defined by two quick trigger drag up and down vertical movements. A nod vibration 460 may be used to indicate "yes" or "accept". Hua X (X-ing) 470 is defined as drawing the character "X". Draw X470 is used for "delete" or "block" commands. Wagging 480 is defined by two trigger-drag rapid back and forth horizontal movements. The shake gesture 480 may be used to indicate "no," "cancel," select "other," or move a displayed or virtual object (eg, a cursor) horizontally.

Depending on the complexity of the sensor system, only simple one-dimensional movements or gestures may be allowed. For example, a simple right or left movement on the sensor as shown here can produce a fast forward or rewind function. Additionally, multiple sensors can be included and placed at different locations on the touch screen. For example, a horizontal sensor for left and right movement could be placed in one point and used for volume up/down, while a vertical sensor for up and down movement could be placed in a different point and used for channel up/down. In this way, specific gesture mappings can be used. A user may interact with the user interface of the present disclosure using gestures performed on the tablet 300, as discussed in more detail below.

The following discussion presents methods, systems, and user interfaces for assisting content delivery in accordance with the present disclosure such that ideas from categories of items (e.g., movies, music, dishes, etc.) are sorted through a minimum number of questions or recommendations. Recommended items to users.

There is a lot of tabular content online, such as lists of restaurants, movies, products, etc., where each item has multiple attributes, some of which are carefully created using meaningful and common tags, while others include arbitrary user-specified Label. So how does a user discover items of interest to him or her in such a collection?

One way is to provide a search bar and have the user enter the attributes of the item they want, and provide a ranking list of items relevant to the user's query. Another way is to provide a series of navigation menus with categories to allow the user to browse and drill down to a list of desired items. Most sites like Netflix, Yelp, etc. allow a combination of both. Typically, however, the properties that users care about and use for searching or navigating are very large, and most interfaces have some drawbacks. For example, these items are often organized in tree taxonomies, but the taxonomy trees are often unbalanced. Therefore, not all objects can be found with a small number of steps. Second, the branching factor of the tree may be huge, which may affect the availability of the system. For example, Yelp users can choose from 100 types of dishes, but only 9 can be displayed on the screen of the mobile phone at the same time (Fig. 5b). According to traditional user interfaces, as in Netflix (Fig. 5a), users tend to stop after a few clicks through the menu (e.g., foreign films and dramas), and then are faced with a list of movies that, while satisfying their criteria, do not Still far from the final project they are interested in and includes many unwanted projects (eg, foreign drama romance and foreign drama thriller).

One of the concerns of this disclosure is the existence of modern devices that users find very convenient, such as tablets and smartphones. What interface will help users find content on such a device? Consider the example of a user using a tablet (eg, iPad) application to find a movie. Movies have many standard attributes (e.g., genre, actors, etc.), as well as many non-standard categories that are becoming increasingly important in online platforms (e.g., Recently Watched, Coming Soon, Editor's Picks, NYTimes reviews, etc.), and includes user-generated categories based on reviews and other tagging services (eg, better than Pulp Fiction, famous car races, etc.). What is an appropriate and intuitive way for users to find the movies they are interested in?

Emerging apps take advantage of both aspects of modern interfaces. First, there's the big screen. Instead of filling large screens with numerous categories represented in text on a white background (Figures 5a and 5b), which are common in web applications, these applications often use large thumbnails that convey more information about More information selected by the user (Fig. 5c and Fig. 5d). Second, users prefer to interact by touch, so often these apps let users touch these thumbnails and browse menus to make selections, rather than tap to expand a long list of text options.

These features can be used in a straightforward manner: take the existing interface on the web application and replace individual items with thumbnails, allowing users to flip and scroll and make selections by touching their options, rather than clicking with a mouse. Armed with these aspects, however, the present disclosure returns to interface design for the user and addresses how to make the user interface more intuitive and efficient. More specifically, this disclosure makes the following contributions:

First, content discovery using a modern interface is formatted as a multi-way search against k categories. The algorithm of the present disclosure is given a series of "queries" corresponding to k categories, and the user selects from these categories (or selects an "other" option). This disclosure focuses on minimizing, even in the worst case, the number of such queries a user needs to find an item of interest to him or her (regardless of the distribution of categories of items or what the user wants to find).

Second, this disclosure formally addresses this issue. Compared with the OPT _k responses that the user needs to make through the best and best algorithm in the worst case, this disclosure proposes an algorithm and process that can prove that the user makes at most (e/e-1) OPT _k logn queries , where n is the number of items. Double Greedy Algorithm and Processing Use the first greedy algorithm (Fig. 6 and Fig. 7) to exclude as many possibilities as possible for each query, and use the second greedy algorithm (Fig. 8 and Fig. 9) to find the closest to the optimal query Inquire for answers. The benefit of the double greedy algorithm and processing is that it is very efficient compared to traditional approaches.

In general, according to the present disclosure, content discovery can be visualized, as described below. Each item or graphical element (eg, movie, restaurant, etc.) can represent a set of categories (eg, category, type of cuisine, etc.). The user may have a specific target item in mind and may select an item using a device with multi-select functionality, such as a tablet or phone (e.g., touch screen device 116, 300) or a TV and remote device (114 and 116, 300)). According to the present disclosure, the system can present items representing multiple categories on a tablet, phone, or TV. The user is allowed to interact with and select from the options presented. The process of the present disclosure is repeated until the user identifies a target item that satisfies all of his options. The content discovery system can be viewed as a questioner and the user as an answerer. The questioner interacts with the respondent by asking questions (eg, selecting a displayed item or graphical element representing a category of items or by selecting "Other" which may represent a category of items not previously presented to the user). A primary goal of the disclosed system is to ensure that there are as few interactions or questions as possible before the desired item (eg, movie, restaurant, etc.) is presented to the user.

For example, consider a user using a tablet application to discover a restaurant of his or her interest. This disclosure assumes that restaurants have many standard attributes (e.g., type of cuisine, price, etc.), many non-standard categories (kid-friendly, good customer service, takeout or delivery options, setting, loudness, etc.), and user Categories generated by the labeling service (eg, name of pastry chef of the day, fresh fish delivery date, etc.). A user might want to find an Asian-inspired restaurant with a modern setting that is kid-friendly.

How should this setting be formatted? Consider the following:

What kind of user interface does the system provide to the user? This disclosure assumes that the system presents categories. In the example above, this would correspond to categories such as Asian, Kid Friendly. An alternative is to assume that the system shows a combination of categories, eg, Asian and kid-friendly, expensive and delivered on Mondays, and so on.

• What are the user's exact choices and what are his or her responses? This disclosure adapts the convention that a user indicates a category describing their goals over the k categories being shown. Natural tablet user interface interaction allows the user to touch one of these categories and cause the tablet application to immediately proceed to the next round (ie, present the user with the next set of questions or item categories). This simple convention has two nuances. (i) Assume that more than one category describes the target item. In this case, the present disclosure assumes that the user indicates any applicable category, without burdening the user with the need to be more precise and pick the "most" applicable category under any notion of distance. (ii) Assume that no category is applied to the target item. This may be because the options for k categories cannot cover the entire space of possible targets. Therefore, the present disclosure requires the user to be provided with the (k+1)th option for the remaining item categories, which include all combinations of item categories not represented in the k options. It should be noted that the (k+1)th option is generally not captured by any single category.

Referring now to FIG. 7 , there is shown a generalized multi-way search process 700 of the present disclosure implementing the generalized multi-way search algorithm 600 of FIG. 6 . At step 702, a version space (i.e., all items satisfying all answers so far) is initialized to all items in the database (i.e., hypothesis space "H"), and at step 704, the number of questions asked is tracked. The counter is set to 1. At step 706, it is determined whether the number of items in the version space (ie, all items satisfying all answers so far) is greater than one. In other words, whether the desired item(s) have been found. It should be noted that 1 may represent a single item or multiple items (eg, 3 items, 7 items, etc.) depending on the display on which the items are presented (eg, TV, phone, tablet, etc.). If the desired item has been found (ie, the number of items in the version space is less than or equal to 1), then at step 708, the item(s) are output and provided (eg, displayed) to the user. If not, then at step 710, new questions are generated for the user according to the greedy selection algorithm 800 of FIG. 8 and the greedy selection algorithm 900 of FIG. 9 discussed in more detail below (i.e., the user is presented with k item categories + 1 special category (eg, Other)). Next, at step 712, the user answers the new question by selecting one of the k item categories or a special additional category (ie, the user selects one of the k+1 categories). Then, in response to the user's answer (ie, selection), the version space is updated. If the user selects one of the k categories, then at step 714, the version space is updated to include either the category item the user has selected and the category item previously selected by the user (i.e., the category item that has satisfied the user's answers so far). intersection between. If the user selects another category (i.e., the "+1" category), then at step 716, the version space is updated to include the intersection between: the complement of the union of the currently displayed categories (i.e. A category item for any of the displayed categories. For example, if images representing the crime, horror, and comedy categories were being displayed to the user and the user selected "Other", the complement of the union of these displayed images would not be crime category, not horror category, and not comedy category) and the category item previously selected by the user. Next, at step 718, a counter "t" is incremented. Likewise, the counter reflects the number of questions the user has been asked (ie, the number of times the user has selected the presented category item (k+1)). Process 700 then repeats iteratively until it is determined at step 706 that the number of items in the version space (ie, all items satisfying all answers so far) is less than or equal to one.

Turning back to step 710, according to the present disclosure, the goal of this step is to maximize the number of excluded item categories. One problem is computing the next best problem (ie the optimal presentation of item categories to the user), during step 710 a maximum number of item categories must be excluded. Maximizing the number of excluded item categories is computationally very complex, since conventionally all possible item category combinations would have to be considered to maximize the number of excluded item categories in this step. The greedy algorithm of the present disclosure efficiently computes a near-optimal problem that is computationally much simpler than that of an optimal problem, thus speeding up the recommendation or questioning process of the present disclosure.

Turning now to FIG. 9 , the item category selection process or greedy selection on questions process 900 of the present disclosure implementing the greedy selection on questions algorithm 800 of FIG. 8 is shown. In this process, L represents the largest category in the optimal solution, and U represents the current set of items satisfying the user's answers or selections so far. First, at step 902, the optimal solution ^Ag (the set of selected item categories) is initialized as an empty set. Next, at step 904, the upper limit L of the set size in the optimal solution is initialized to 1. Then, in step 906, it is determined whether the upper limit L is less than or equal to the size of the version space U. If yes, then at step 908, all item category sets in the version space that cover less than L items are selected. Next, at step 910, from the selected sets, k sets _AL are selected or calculated. The k sets _AL cover the most items in the version space U. Then, at step 912, it is determined whether the k selected sets so far have greater utility than the optimal solution ^Ag . If yes, then at step 914, A _L is replaced by ^AL , and at step 916, the upper limit of the set size in the optimal solution L is increased by 1. If not, then at step 916 the upper limit of the set size in the optimal solution L is increased by 1. Then, at 906, it is determined again whether the upper limit L is less than or equal to the size of the version space U. If yes, steps 908, 910, 912, 914 and 916 are iteratively repeated until the upper limit L is not less than or equal to the size of the version space U. It should be noted that the loop from step 906 to step 912 is referred to as a FOR loop for all L=1, . . . , |U|. L is not known in advance, so solutions are computed for all L (step 910), and the best solution is selected (steps 912 and 914). Once it is determined that the upper limit ^L is not less than or equal to the size of the version space U, then at step 918, k item categories representing the optimal solution Ag are output and displayed to the user (generalized multiplex search process 700 shown in FIG. 7 in step 710).

Referring now to FIG. 10 , an exemplary user interface 1000 is shown in accordance with the present disclosure. In user interface 1000, a single category or question (ie, k=1) is presented to the user along with "other" options (ie, "k+1" options). When a user interacts with the system (e.g., receiving device 108, backend server and content discovery application 118, custom database 120, control device 116, and/or display device 114), the system performs the generalized multi-way search process 700 and Greedy selection process 900 of FIG. 9 . During the execution of these processes, the user will be repeatedly or iteratively provided with a single category or question along with the "Other" option until the user is provided with a final recommendation screen. In practice, user interface 1000 may be particularly useful in a TV environment, where it is most effective to present a few options or questions to the user, since the user may need to use the arrow keys of the remote control to select the displayed category or other options. Although not shown, it may also be useful in a TV environment to display both categories (ie, k=2) along with the "Other" option. It should be appreciated that the user can make gestures (eg, as discussed in FIG. 4 ) to make selections between the displayed categories and "Other" options by using a remote control that includes an inertial sensor.

Referring now to FIG. 11 , an exemplary user interface 1100 is shown in accordance with the present disclosure. In user interface 1100, three categories or questions (ie, k=3) are presented to the user along with "other" options (ie, "k+1" options). When a user interacts with the system (e.g., receiving device 108, backend server and content discovery application 118, custom database 120, control device 116, and/or display device 114), the system performs the generalized multi-way search process 700 and Greedy selection process 900 of FIG. 9 . During execution of these processes, the user will be repeatedly or iteratively presented with the three categories or questions along with the "Other" option until the user is presented with a final recommendation screen. In practice, user interface 1100 may be particularly useful in a small touchscreen environment (e.g., in a smartphone or handheld gaming platform), where it is more efficient to display slightly more options to the user than in a TV environment or option or question for a question, as the user only needs to touch the touchscreen of the small touchscreen to select the desired category or "Other" option.

Referring now to FIG. 12 , an exemplary user interface 1200 is shown in accordance with the present disclosure. In user interface 1200, seven categories or questions (ie, k=7) are presented to the user along with "other" options (ie, "k+1" options). When a user interacts with the system (e.g., receiving device 108, backend server and content discovery application 118, custom database 120, control device 116, and/or display device 114), the system performs the generalized multi-way search process 700 and Greedy selection process 900 of FIG. 9 . During execution of these processes, the user will be repeatedly or iteratively presented with the seven categories or questions along with the "Other" option until the user is presented with the final recommendation screen. In practice, the user interface 1200 may be particularly useful in a large touch screen environment (e.g., a tablet computer), where it is more efficient to present a greater number of options or questions to the user than in a TV environment or a small touch screen environment. options or questions because the user only needs to touch the touchscreen of the large touchscreen to select the desired category or "other" option and the large touchscreen has a large enough area to display a large number of categories or questions.

Referring now to FIG. 13 , an exemplary final recommendation screen or user interface 1300 of the present disclosure is shown. Once the generalized multiplex search process 700 of FIG. 7 and the greedy selection process 900 of FIG. 9 are complete, screen 1300 is shown. Screen 1300 presents the user with a selection of final items (eg, movies, restaurants, etc.) for the user to consume (eg, store, purchase, watch, download, etc.).

Referring now to FIG. 14 , a recommendation process 1400 of the present disclosure is shown. Initially, at step 1402, several display areas (for example, areas corresponding to k and k+1) are selected according to display types or display devices. For example, as discussed above, if the display device is a TV, one display area can be selected (k=1 as shown in Figure 10); if the display device is a small touch screen device, three display areas can be selected (as shown in Figure 10 k=3 as shown in Figure 11); if the display device is a large touch screen device, seven display areas can be selected (k=7 as shown in Figure 12). Then, at step 1404, item categories are selected for display in the display area according to the content or item category discovery process. The content discovery process includes the generalized multiplex search process 700 of FIG. 7 and the greedy selection process 900 of FIG. 9 .

Although embodiments incorporating the teachings of the present disclosure have been shown and described in detail herein, those skilled in the art will readily devise many other varied embodiments that still incorporate these teachings. Having described preferred embodiments of systems, methods, and user interfaces for facilitating content discovery (these embodiments are intended to be illustrative and not limiting), it is noted that, given the above teachings, those skilled in the art will be able to out modifications and changes. It is therefore to be understood that changes may be made in the particular embodiments of the disclosure which are disclosed within the scope of the present disclosure.

Claims (20)

1. A method for recommending items, the method comprising: selecting (1402) a plurality of display regions based on display type; and Item categories to be displayed in the display area are selected (1404) according to the content discovery process. 2. The method of claim 1, further comprising displaying the selected plurality of item categories in the display area. 3. The method of claim 2, further comprising: identifying (712) the item category selected by the user; and A plurality of item categories displayed in the display area are changed (710) based on the identified item categories and the content discovery process. 4. The method of claim 1, wherein the number of selected display areas is different for different display types (1000, 1100, 1200). 5. The method of claim 4, wherein the different display types include at least one of: a TV, a phone, and a tablet. 6. The method of claim 5, wherein the TV has a smaller display area than the phone, and the phone has a smaller display area than the tablet. 7. The method of claim 1, wherein the content discovery process comprises: A multi-pass search process (700) that tracks user item category selections during the content discovery process and removes items displayed in the display area from future displays in the display area. , the item category that is not selected; and An item category selection process (900) that selects at least one item category that has not been displayed in the display area and was not previously unselected during the multi-way search process (700). 8. The method of claim 7, wherein the selection of the at least one item category is further based on the number of items in the at least one item category. 9. The method of claim 8, wherein the number of said items in said at least one item category is greater than items in other item categories that have also not been displayed in said display area and were not previously unselected Number of. 10. The method of claim 7, wherein said multi-way search process (700) and said item category selection process (900) are greedy processes. 11. A system for recommending items, comprising: means for selecting (1402) a plurality of display regions based on a display type; and means for selecting (1404) a category of items to be displayed in said display area in accordance with a content discovery process. 12. The system of claim 11, further comprising means for displaying the selected plurality of item categories in the display area. 13. The system of claim 12, further comprising: means for identifying (712) the category of items selected by the user; and Means for changing (710) a plurality of item categories displayed in the display area based on the identified item categories and the content discovery process. 14. The system of claim 11, wherein the number of selected display areas is different for different display types (1000, 1100, 1200). 15. The system of claim 14, wherein the different display types include at least one of: a TV, a phone, and a tablet. 16. The system of claim 15, wherein the TV has a smaller display area than the phone, the phone has a smaller display area than the tablet. 17. The system of claim 11, wherein the content discovery process comprises: A multi-pass search process (700) that tracks user item category selections during the content discovery process and removes items displayed in the display area from future displays in the display area. , the item category that is not selected; and An item category selection process (900) that selects at least one item category that has not been displayed in the display area and was not previously unselected during the multi-way search process (700). 18. The system of claim 17, wherein selection of the at least one item category is further based on a number of items in the at least one item category. 19. The system of claim 18 , wherein the number of items in the at least one item category is greater than items in other item categories that have also not been displayed in the display area and that were not previously unselected Number of. 20. The system of claim 17, wherein the multi-way search process (700) and the item category selection process (900) are greedy processes.