SYSTEM AND METHOD FOR RECOMMENDING CORRELATED AND ANTI-CORRELATED CONTENT - Patent application

Abstract

In the present invention, a system and method are described for providing content recommendations to a user based on the elapsed play time of a current content on a user device. A recommendation server having a memory and a processor can be used to compare the elapsed play time of the current content and compare the elapsed play time with one or more thresholds. If the elapsed play time is less than a first threshold, anti-correlated content to the current content can be recommended and presented on or using the user device.

Description

[Technical Field]

[0001] This application claims priority to U.S. Nonprovisional Patent Application No. 17 / 867,103, filed July 18, 2022, which itself claims priority to U.S. Provisional Patent Application No. 63 / 348,827, filed June 3, 2022. These and all other referenced external materials are incorporated herein by reference in their entirety. If a definition or usage of a term in a reference incorporated by reference contradicts or is incompatible with the definition of that term set forth herein, the definition of the term set forth herein shall be deemed to control.

[0002] The field of the invention is recommendation systems and methods. [Background technology]

[0003] The following description includes information that may be helpful in understanding the present invention. The following description is not an admission that any of the information provided herein is prior art or relevant to the claimed invention, or that any publication referenced, expressly or impliedly, is prior art.

[0004] Online stores and user-generated media platforms utilize recommendation systems to facilitate browsing of large numbers of items. Such systems generally rely on centrally stored data about user preferences and on intrinsic characteristics of items (i.e., content-based recommenders) or other user preferences (i.e., collaborative filtering recommenders).

[0005] For example, existing video playback applications known to the inventors create digital correlations between media titles available to a consumer based on content metadata and the consumer's viewing habits. Such applications often recommend only similar or correlated media titles to a consumer after media playback of a content piece has finished. These recommendations are generally based on the user having finished viewing the original content and the content provider having a list of similar content to recommend that is correlated to the current title.

[0006] All publications identified herein are incorporated by reference to the same extent as if each individual publication or patent application was specifically and individually indicated to be incorporated by reference. In the event that a definition or usage of a term in an incorporated reference contradicts or is incompatible with a definition of that term set forth herein, the definition of the term set forth herein shall apply and the definition of the term in the reference shall not apply.

[0007] Therefore, there is a need for a system and method for recommending anti-correlated content. Summary of the Invention

[0008] The present subject matter provides apparatus, systems, and methods for providing a recommendation system for a vehicular content delivery network, particularly for recommending correlated and anti-correlated content to a user based on the elapsed time of the content being viewed. Preferably, such systems and methods are utilized in conjunction with in-vehicle networks, such as in-flight entertainment systems used on airplanes and other vehicles. However, it is contemplated that the systems and methods described herein may be utilized in other networks unrelated to vehicles. For example, it is contemplated that the systems and methods described herein may be used with any service or system that provides a set of content with recommendations, which may include, for example, content streaming services such as NETFLIX®, DISNEY+®, HULU®, on-demand content available at hotels and other lodging facilities, etc.

[0009] In some embodiments, a server having a processor and non-transitory memory is provided, the server being communicatively coupled to a network configured to distribute content to multiple users. In embodiments related to a vehicle, the server may be communicatively coupled to an in-vehicle network for distributing content to multiple users within the vehicle. For example, the server may be connected to multiple in-flight entertainment devices, such as those typically located in the seatbacks of the vehicle, but may also be connected to one or more user devices. Exemplary in-flight entertainment systems and devices are described in U.S. Patent No. 9,015,776, entitled "Entertainment Systems Utilizing Field Replaceable Storage Units," and U.S. Patent No. 1,017,3605, entitled "Display Unit for a Vehicle." Exemplary user devices may include, for example, smartphones, tablet PCs, laptop computers, glasses with built-in displays or projector systems, and other portable computing devices capable of receiving and displaying or projecting content, televisions or other displays, and other devices that may be used to view or access content.

[0010] Contemplated recommendation systems and methods may generate a set of recommended content for a user that may be based on the content piece currently being played by the user (e.g., genre, rating, content tags or other metadata, or other information associated with the content piece) and / or based on one or more characteristics of the user (e.g., content previously played by the user or other usage statistics, a user profile, identifying information about the user, etc.).

[0011] It is further contemplated that such a system may be configured to generate a set of anti-correlated content that may be based on the content piece currently being played by the user (e.g., genre, rating, content tags or other metadata, or other information associated with the content piece) and / or may be based on one or more characteristics of the user (e.g., content previously played by the user or other usage statistics, a user profile, identifying information about the user, etc.). The type of recommendation (i.e., correlated or anti-correlated) presented to the user preferably depends on the elapsed time of the content piece being played. In some embodiments, anti-correlated content may be displayed to the user during a first portion (first elapsed time period), and correlated content may be displayed to the user during a second portion (second elapsed time period) after the first portion (i.e., some time after the first elapsed time period). In this manner, the systems and methods described herein enable anti-correlated content to be recommended to the user as an addition to or alternative to correlated content based on the elapsed time or percentage of playback of the content piece.

[0012] Various objects, features, aspects and advantages of the present subject matter will become more apparent from the following detailed description of preferred embodiments, taken in conjunction with the accompanying drawings, in which like numerals represent like elements. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 1 is a diagram of one embodiment of a recommendation system. [Figure 2] 1 is a flowchart of one embodiment of a method for providing recommendations to a user. [Figure 3] 1 illustrates an exemplary user interface showing correlated content being displayed at the end of a current media playback. [Figure 4] 1 illustrates an exemplary user interface showing anti-correlated content being displayed at the beginning of a current media playback. [Figure 5]1 illustrates an exemplary user interface showing correlated content being displayed at the end of a current media playback. [Figure 6] An example of categorizing content is shown below. DETAILED DESCRIPTION OF THE INVENTION

[0014] Throughout the following description, numerous references are made to servers, services, interfaces, portals, platforms, or other systems formed of computing devices. It should be understood that the use of such terms is intended to represent one or more computing devices having at least one processor configured to execute software instructions stored on a computer-readable, tangible, non-transitory medium. For example, a server may include one or more computers operating as a web server, database server, or other type of computer server to perform the roles, responsibilities, or functions described.

[0015] As used herein, terms such as "component," "module," and "system" refer to computer-related entities, hardware, firmware, software, a combination of software and hardware, or the execution of software. For example, a component may be, but is not limited to, a procedure running on a processor, a processor, an object, a thread of execution, a program, and / or a computer. For example, both an application running on a computing device and the computing device may be a component. One or more components may reside within a processor and / or thread of execution. A component may be localized within one computer. A component may be distributed across two or more computers. Furthermore, components may be implemented by various computer-readable media having various data structures stored thereon. For example, components may communicate through local and / or remote processing according to signals having one or more data packets (e.g., data transmitted over a network such as the Internet to another system, and / or signals from one component interacting with other components in local and distributed systems).

[0016] The operations of the example logical blocks, configurations, modules, circuits, means, logic, and algorithms described herein may be implemented by electronic hardware, computer software, or a combination of electronic hardware and computer software. To clearly illustrate the interchangeability of hardware and software, algorithms, steps, and / or operations are generally described in terms of their functional aspects. Whether a function is implemented as hardware or software depends on the particular application or design constraints imposed on the system.

[0017] The following description provides numerous example embodiments of the inventive subject matter. While each embodiment represents a single combination of inventive elements, the inventive subject matter is considered to include all possible combinations of the disclosed elements. Thus, if one embodiment comprises elements A, B, and C and a second embodiment comprises elements B and D, the inventive subject matter is considered to include other combinations of A, B, C, or D, even if not explicitly disclosed.

[0018] While the description herein may focus on aircraft, it is believed that the systems and methods described herein may likewise be used in ships, trains, buses, and other vehicles, as well as content distribution systems and methods used outside of vehicles.

[0019] The present subject matter describes systems and methods for providing content recommendations to one or more users, where the content recommendations vary depending on the elapsed time of the current media playback.

[0020] In one embodiment shown in FIG. 1 , system 100 is configured to provide content recommendations to one or more devices 110A-110N. In some embodiments, devices 110A-110N are connected to network 130, which may be an in-vehicle network, but may also be a home or other network. In other embodiments, devices may be connected to a local or remote content server or another server via a wired or wireless network. System 100 includes recommendation server 120 having processor 122 and memory 124 communicatively coupled to processor 122. Processor 122 may be formed with one or more cores and may include processors such as, for example, a central processing unit (CPU), a general-purpose graphics processing unit (GPGPU), and other commercially available components. Processor 122 may read computer programs stored in memory 124 and process data as described herein.

[0021] The memory 124 may include at least one type of storage medium from the following: flash memory, hard disk, multimedia card micro, card-type memory (e.g., SD or XD memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, and optical disk. The recommendation server 120 may operate in conjunction with a web storage that performs storage functions for the memory 124 over the Internet.

[0022] Such devices may comprise, for example, user devices (portable computing devices) as described above, or devices that are part of an in-car entertainment system and are located within the vehicle, such as, for example, seatback display units.

[0023] Preferably, each of devices 110A-110N is communicatively coupled to a server via network 130, which may be a wired and / or wireless network. Each of devices 110A-110N preferably includes a display screen, projector, or other component(s) that allows a user to view or otherwise consume content and recommendations through use of the device. Recommendation server 120 may be configured to receive statistical or other information from one or more of devices 110A-110N.

[0024] The recommendation server 120 may also be communicatively coupled to a content server 126 configured to store a plurality of pieces of content. In other embodiments, at least some of the content may be stored on the user device.

[0025] Processor 122 is preferably configured to generate and present one or more recommendations for at least one of user devices 110A-110N based at least in part on the content currently being played using the device and the elapsed time of the currently playing content. Based on the elapsed time of the currently playing content, system 100 may recommend correlated and / or anti-correlated content to the currently playing content. For example, in a preferred embodiment, system 100 is configured to recommend anti-correlated content if the elapsed time of the current content is less than a first threshold and to recommend correlated content if the elapsed time of the current content is greater than a second threshold. The first and second thresholds may be the same, but are preferably different.

[0026] In some embodiments, the first threshold may be a particular percentage (e.g., 5%, 10%, 20%, etc.) of the total play time of the content. Thus, for a piece of content with a total play time of one hour (60 minutes), the first threshold may be the first 3 minutes (i.e., 5%), the first 6 minutes (i.e., 10%), the first 12 minutes (i.e., 20%), etc.

[0027] In other embodiments, the first threshold may be a fixed number of minutes, such as the first 5 minutes, the first 10 minutes, the first 15 minutes, etc.

[0028] Similarly, the second threshold could also be a particular percentage of the total play time of the content (e.g., 5%, 10%, 20%, etc.). Thus, for a content piece with a total play time of one hour (60 minutes), the second threshold could be the last 3 minutes (i.e., 5%), the last 6 minutes (i.e., 10%), the last 12 minutes (i.e., 20%), etc. However, in other embodiments, the second threshold could be a fixed number of minutes, such as the last 5 minutes, the last 10 minutes, the last 15 minutes, etc.

[0029] Furthermore, it is contemplated that there may be a period between the first and second thresholds during which no content is recommended, or content different from the correlated and anti-correlated content is recommended, or both the correlated and anti-correlated content is recommended, and during such a period, information about the content may be displayed instead of the recommended content.

[0030] In other embodiments, the first threshold may be equal to the second threshold, and in such embodiments, anti-correlated content may be recommended before (i.e., early) the first threshold, and correlated content may be recommended after (i.e., late) the first threshold.

[0031] Once system 100 determines whether to recommend correlated or anti-correlated content, it can then select the recommended content based at least on, for example, the content currently being played by the user or, if the user stops the content, the last content played by the user. In a simple example, content may be grouped into one of a set of categories. In the embodiment shown in FIG. 6, content may be grouped into one of eight different types or categories (e.g., content types 1-8). Opposing slices or pieces of the "wheel" may be considered to be conflicting or anti-correlated content. Thus, content 2 and content 6 are conflicting, as are content 3 and content 7, content 4 and content 8, and content 5 and content 1. As a specific example, content 2 may represent documentaries, and content 6 may represent science fiction. In such an example, a value for the type of the current content may be determined, and then the total number of types divided by 2 (here, 4) may be subtracted from the value to generate a subtotal. The system 100 may then check to determine if the subtotal is less than 0, and if so, multiply the result by −1 to arrive at the suggested content value (Z). Of course, if the subtotal is greater than 0, then the suggested content value (Z) is equal to the subtotal. This can be expressed as the following formula: (XN / 2)=Y; if Y<0, then Z=Y * -1; otherwise, Z=Y

[0032] The suggested content value (Z) is then used to determine the type of content to recommend, and specific content within that type or genre may be recommended based on one or more factors, such as the popularity of the content, the total play time of the content, a determination of whether the user has previously viewed the content, the content's rating, media details, content tags or other metadata, historical statistical data, etc.

[0033] Once the content is selected, the recommended content may be presented or displayed on or with the user device.

[0034] Alternatively, in other embodiments, system 100 may select recommended content (correlated or anti-correlated content) based on content tags or other metadata associated with the currently playing content. In such embodiments, content pieces may be associated with one or more content tags or other information or metadata that can be used to select recommended content. The content tags or other information may, for example, list correlated and / or anti-correlated content selected by system 100. This is useful when the available content is known and finite, particularly when the number of available content titles is manageable (e.g., less than 250 content pieces). Thus, in such embodiments, system 100 may review metadata associated with the current content and then select recommended content based on the metadata. If a list of correlated or anti-correlated content is provided, system 100 may display the title and other information of the content associated with the appropriate list. In one example, such information may be displayed in a window overlaid on the current content, allowing the user to view titles, images, and / or other information associated with the recommended content.

[0035] It is contemplated that content tags or other metadata may be pre-associated with content, e.g., by the content provider or a third party, etc. Thus, when content is loaded onto or made available to a content server, some or all of the content may be associated with content tags or other metadata, e.g., as described above.

[0036] It is further contemplated that system 100 itself may associate content tags or other metadata with some or all of the content. Thus, for example, using various criteria, system 100 may analyze information related to each piece of content or content and assign or associate one or more tags or other metadata with the content. Such criteria may include, for example, genre, content ratings such as those provided by the Motion Picture Association of America (MPAA®) or other organizations, critic or peer ratings, total elapsed time of the content, type of content (e.g., movies, television, music, etc.), and / or usage statistics collected by system 100.

[0037] In still further embodiments, system 100 may select recommended content (correlated or anti-correlated content) based on various criteria, including those described above. For example, system 100 may utilize one or more artificial intelligence (AI) algorithms to select recommended content based on data collected by recommendation server 120. Usage statistics over time may be used to provide better recommendations to users based, for example, on content viewed or not viewed and the average length of time a content piece is viewed. If a majority of users who selected a content piece did not play the content to the end or to a certain point, system 100 may decide not to recommend that content piece to users in the future, regardless of whether the recommended content is correlated or anti-correlated content.

[0038] 2 shows one embodiment of a method 200 for recommending content to one or more users. In step 205, the age of the currently displayed content may be determined, such as with the recommendation server described above. This may occur automatically when the user pauses playback of the content, or when, for example, the user clicks on the display screen or otherwise interacts with the user device to invoke a menu.

[0039] In step 210, the elapsed time may be compared to a first threshold, such as by using a processor in the user device or a processor in the recommendation server. If the elapsed time is less than the first threshold, a set of anti-correlated content may be generated as recommended content in step 215a. If the elapsed time is greater than or equal to the first threshold, the elapsed time may be compared to a second threshold, such as by using a processor in the user device or a processor in the recommendation server in step 215b.

[0040] If the elapsed time is greater than the second threshold, a set of correlated content may be generated as recommended content in step 225a. If the elapsed time is less than or equal to the second threshold, information about the current content may be generated as recommended content in step 225b. Alternatively, both correlated and anti-correlated content may be displayed in step 225b.

[0041] Of course, if the first and second thresholds are the same, if the elapsed time is greater than or equal to the first threshold, step 215b may be skipped and in step 225a, a set of correlated content may be generated as recommended content.

[0042] In step 230, recommended content (eg, anti-correlated content, correlated content, or information about current content) may be presented to the user on or using the user device.

[0043] Alternatively, of course, it is contemplated that each piece of content may be associated with a set of correlated and / or anti-correlated content. In other words, the server need not generate a set of recommended content on the fly, but may pre-generate the set of content and present that information, for example, as the content is transferred or streamed. It is also contemplated that each piece of content may be pre-associated with a set of correlated and / or anti-correlated content, for example, by a content provider. In such an example, the content may be loaded onto a content server or other storage location and already associated with a set of correlated and / or anti-correlated content. When content is associated with correlated and anti-correlated content, method 200 only requires that the age of the current content be determined and that the age be compared to one or more thresholds, as described above. Then, based on the comparison results, the correlated or anti-correlated content may be presented to the user as suggested content.

[0044] As shown in FIG. 3 , a user is currently playing or has previously played a piece of content using user interface 300. The elapsed time of the currently playing or recently played (e.g., stopped) content is indicated at the bottom center of interface 300, with the elapsed time being closer to the end of the content than the beginning. As described above with reference to FIGS. 1-2 , if the elapsed time is above a second threshold (e.g., toward the end of the current content playback), a set of content correlated to the current content may be recommended, and if the elapsed time is below a first threshold (e.g., at the beginning of the current content playback), a set of content uncorrelated (anti-correlated) to the current content may be recommended. As described above, each of the first and second thresholds may be defined, for example, as a specific percentage of the total playback time of the current content or a specific elapsed time. In this way, the user may be recommended similar (correlated) content (e.g., content A, B, C) as the user nears the completion of the current media playback, likely indicating that the user enjoyed the current content. In contrast, a user may be recommended dissimilar or anti-correlated content (e.g., content X, Y, Z) at the beginning of playback of the current content, because a desire to change content early may indicate that the user prefers content that is different from the current content.

[0045] As described herein, it is contemplated that the type of content displayed (ie, correlated or anti-correlated) may be determined by one or more different schemes.

[0046] In one embodiment, if the playback position of the current content is less than or equal to 50% of the total playback time of the current content, anti-correlated content may be presented. If the playback position of the current content is more than 50% of the total playback time of the current content, correlated content may be presented.

[0047] In another embodiment, if the playback position of the current content is less than a first threshold (e.g., 20% of the total playback time of the current content), anti-correlated content may be presented; if the playback position of the current content is greater than a second threshold (e.g., 80% of the total playback time of the current content or less than 20% of the current content remaining), correlated content may be presented; and if the playback position is greater than the first threshold and less than or equal to the second threshold, no recommendation is presented.

[0048] In yet another embodiment, a range or ratio of anti-correlated and correlated content may be presented as the playback position of the current content changes over time from 0% to 100%. Thus, at the beginning of playback, 100% of the suggested content may be anti-correlated content, while in the middle there may be both anti-correlated and correlated content, and towards the end of playback, 100% of the suggested content may be correlated content.

[0049] 4 illustrates one embodiment of a user interface 400 used to display currently playing content. The elapsed time of the currently playing or recently played content (e.g., if the current content is stopped) is shown at the bottom center of the interface 300, with the elapsed time being closer to the beginning of the current content than to the end. In this example, the recommended content displayed in the overlay is anti-correlated content (X, Y, Z) because the elapsed time is less than a first threshold. As discussed above, it is contemplated that the title, image, or other information for each anti-correlated content piece may be displayed to the user in the overlay or in other ways.

[0050] 5 illustrates a user interface 400 used to display currently playing content. The elapsed time of the currently playing or recently played content (e.g., if the current content is stopped) is shown at the bottom center of the interface 300. Here, the elapsed time is closer to the end of the current content than to the beginning. In this example, the elapsed time exceeds a second threshold, so the recommended content displayed in the overlay is correlated content (A, B, C). As discussed above, it is contemplated that the title, image, or other information for each correlated content piece may be displayed to the user in the overlay or in other ways.

[0051] While the above-described embodiments have been generally described as being implemented by a server, those skilled in the art will appreciate that the present disclosure may be implemented in combination with computer-executable commands and / or other program modules executable on one or more computers, and / or by a combination of hardware and software. Software may include one or more routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Those skilled in the art will appreciate that the methods described herein may be performed by personal computers, handheld computing devices, servers, and other computer system configurations.

[0052] The exemplary embodiments described above may be practiced in a distributed computing environment where certain tasks are performed by remote processing devices that are linked through a communications network, and in a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0053] The servers and computing devices described herein typically include various computer-readable media. Computer-readable media may be any type of computer-readable medium, including volatile and nonvolatile media, transient and non-transient media, and portable and non-portable media. By way of non-limiting example, computer-readable media may include computer-readable storage media and computer-readable transmission media. Computer-readable storage media include volatile and non-volatile media, transient and non-transient media, and portable and non-portable media configured in a predetermined manner or technology for storing information, such as computer-readable commands, data structures, program modules, or other data. Computer-readable storage media include, but are not limited to, random access memory (RAM), read-only memory (ROM), electrically erasable and programmable ROM (EEPROM), flash memory, or other memory technology, compact disc (CD)-ROM, digital video disc (DVD), or other optical disk storage device, magnetic cassette, magnetic tape, magnetic disk storage device, or other magnetic storage device, or other predetermined medium accessible by a computer and used to store desired information.

[0054] As used herein, unless the context indicates otherwise, the term "coupled" is intended to include both direct coupling (where the two elements coupled together are in contact with each other) and indirect coupling (where at least one additional element is disposed between the two elements). Thus, "coupled to" and "coupled with" are used interchangeably.

[0055] In some embodiments, numerical values ​​expressing quantities of ingredients, e.g., concentrations, reaction conditions, and so forth, used to describe and claim particular embodiments of the invention are understood to be modified in some cases by the term "about." Accordingly, in some embodiments, the numerical parameters set forth in the written description and attached claims are approximations that may vary depending on the desired properties sought to be obtained by a particular embodiment. In some embodiments, the numerical parameters should be construed in light of the number of reported significant digits and by applying ordinary rounding techniques. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of some embodiments of the invention are approximations, the numerical values ​​set forth in the specific examples are reported as precisely as practicable. The numerical values ​​presented in some embodiments of the invention may contain certain errors necessarily resulting from the standard deviation found in their respective testing measurements.

[0056] Unless the context dictates otherwise, all ranges set forth herein should be construed as inclusive of their endpoints, and open-ended ranges should be construed as including only commercially practical values. Similarly, all lists of values ​​should be considered as inclusive of intermediate values ​​unless the context dictates otherwise.

[0057] As used herein and throughout the claims that follow, the meanings of "a," "an," and "the" include plural references unless the context clearly indicates otherwise. Also, as used herein, the meaning of "in" includes "in" and "on," unless the context clearly indicates otherwise.

[0058] Recitation of ranges of values ​​herein is merely intended to serve as a shorthand method of referring individually to each separate value falling within the range. Unless otherwise stated herein, each individual value with a range is incorporated herein as if it were individually stated herein. All methods described herein can be performed in any suitable order unless otherwise stated herein or clearly contradicted by context. Any and all examples provided for specific embodiments herein, or the use of exemplary language (e.g., "for example," etc.), are intended merely to clarify the invention and do not otherwise limit the scope of the claimed invention. No language in the specification should be construed as indicating any non-claimed element essential to the practice of the invention.

[0059] Groupings of alternative elements or embodiments of the invention disclosed herein are not to be construed as limitations. Each group member may be referenced and claimed individually or in any combination with other members of the group or other elements present herein. One or more members of a group may be included in, or deleted from, a group for reasons of convenience and / or patentability. When such inclusion or deletion occurs, the specification shall be deemed to include the group as modified to satisfy the written recitation of all Markush groups used in the appended claims.

[0060] It should be apparent to those skilled in the art that numerous modifications beyond those already described exist without departing from the inventive concepts herein. Accordingly, the present subject matter should not be limited except in the spirit of the appended claims. Moreover, in interpreting both the specification and the claims, all terms should be interpreted in the broadest possible manner consistent with the context. In particular, the terms "comprises" and "comprising" should be interpreted as referring non-exclusively to elements, components, or steps, indicating that a referenced element, component, or step may be present, used, or combined with other elements, components, or steps not specifically referenced. When a claim herein refers to at least one item selected from the group consisting of A, B, C, and N, this sentence should be interpreted as requiring only one element from the group, and not A and N, B and N, etc.

Claims

1. A system for providing content recommendations to one or more users, wherein the system is Recommended server having a processor and memory, wherein the memory is communicatively coupled to the processor. Equipped with, The recommendation server is configured to receive recommendation content requests from the user device related to the current content, and the request includes at least the elapsed playback time of the current content. The recommendation server is configured to use the processor to compare the elapsed playback time with a first threshold, and if the elapsed playback time is less than the first threshold, to (i) generate a first content recommendation, and (ii) send the first content recommendation to the user device. The first content recommendation system includes dissimilar, or anticorrelated, content to the current content.

2. The aforementioned recommended server is If the elapsed playback time exceeds the first threshold, a second content recommendation is generated. The second content recommendation is sent to the user device. It is further configured in this way, The system according to claim 1, wherein the second content recommendation comprises similar, or correlated, content to the current content.

3. The aforementioned recommended server is The elapsed playback time is compared with a second threshold that is greater than the first threshold. If the elapsed playback time exceeds the second threshold, a second content recommendation is generated. The second content recommendation is sent to the user device. It is further configured in this way, The system according to claim 1, wherein the second content recommendation comprises similar, or correlated, content to the current content.

4. The system according to claim 1, wherein the recommendation server causes the first content recommendation to be presented to the user device.

5. The system according to claim 3, wherein the recommendation server is further configured to generate a third content recommendation and transmit the third content recommendation to the user device when the elapsed playback time exceeds the first threshold and is less than or equal to the second threshold.

6. The system according to claim 1, wherein the user device comprises a smartphone, a tablet PC, a laptop computer, a desktop computer, glasses with a built-in display or projector system, a television, a display unit for an in-flight entertainment system, and a projector.

7. The system according to claim 1, wherein the first content recommendation is based on at least one of the genre of the current content, the content rating of the current content, the critic rating of the current content, the metadata of the current content, the performers of the current content, the running time of the current content, and tags or keywords related to the current content.

8. A method for providing content recommendations, wherein the method is To provide a recommended server having a processor and memory, wherein the processor is communicatively coupled to the memory, The system receives a recommended content request from the user device, including the elapsed playback time of the currently playing content on the user device. The elapsed regeneration time is compared with a first threshold, If the elapsed playback time is less than the first threshold, a first content recommendation is generated and the first content recommendation is sent to the user device. If the elapsed regeneration time is greater than or equal to the first threshold, the elapsed regeneration time is compared with a second threshold that is greater than the first threshold. If the elapsed playback time exceeds the second threshold, a second content recommendation is generated and the second content recommendation is sent to the user device. Equipped with, A method wherein the first content recommendation comprises dissimilar, or anticorrelated, content to the current content, and the second content recommendation comprises similar, or correlated, content to the current content.

9. The method according to claim 8, further comprising presenting the first content recommendation or the second content recommendation to the user device.

10. If the elapsed playback time exceeds the first threshold and is less than or equal to the second threshold, a third content recommendation is generated. Sending the third content recommendation to the user device, wherein the third content recommendation comprises correlated and incorrelated content with respect to the current content, The method according to claim 8, further comprising:

11. The method according to claim 10, wherein the processor causes the user device to present the third content recommendation.

12. The method according to claim 8, wherein the user device comprises a smartphone, a tablet PC, a laptop computer, a desktop computer, glasses with a built-in display or projector system, a television, a display unit for an in-flight entertainment system, and a projector.

13. The method according to claim 8, wherein the first or second content recommendation is based on at least one of the genre of the current content, the content rating of the current content, the critic rating of the current content, the metadata of the current content, the cast of the current content, the running time of the current content, and tags or keywords associated with the current content.

14. A method for providing content recommendations, wherein the method is The present invention provides a recommendation server having a processor and memory, wherein the processor is communicatively coupled to the memory, the recommendation server is communicatively coupled to a content server configured to store a set of content, the recommendation server generates a first content recommendation and a second content recommendation for each content piece of the set of content, the first content recommendation for each content piece comprises dissimilar, i.e., anticorrelated content for that content piece, and the second content recommendation for each content piece comprises similar, i.e., correlated content for that content piece. When a user interacts with a content piece that is currently playing, the elapsed playback time of the current content is compared with a first threshold, If the elapsed playback time is less than the first threshold, the first content recommendation is presented to the user device. If the elapsed playback time is equal to or greater than the first threshold, the elapsed playback time of the current content is compared with a second threshold. If the elapsed playback time exceeds the second threshold, the second content recommendation is presented to the user device, wherein the second threshold is greater than the first threshold. A method that includes [a certain feature].

15. The method according to claim 14, wherein the processor of the user device or the processor of the recommendation server compares the elapsed playback time of the current content with the first threshold, and if the elapsed playback time is less than the first threshold, the first content recommendation is presented.

Images