WO2023170459A1

WO2023170459A1 - System and method for managing access to event-related recommendations

Info

Publication number: WO2023170459A1
Application number: PCT/IB2022/055567
Authority: WO
Inventors: Ritesh Kumar Sahai; Manish Srivastava; Sweety Srivastava
Original assignee: Ritesh Kumar Sahai; Manish Srivastava
Priority date: 2022-03-10
Filing date: 2022-06-16
Publication date: 2023-09-14

Abstract

A system for managing access to event-related recommendation(s) is provided. The system includes a processing subsystem which includes an input module (40) which receives input(s) upon registration of a user. The processing subsystem also includes an object segregation module (50) which recognizes object(s) from each of multiple frames of streaming multimedia and segregates the object(s) under a first category. The processing subsystem also includes a linking module (60) which identifies object-related information about the object(s) in a system database, links multiple network-based informative systems with the system database when the object-related information remains unidentified in the system database, identifies the object-related information in the multiple network-based informative systems, links the object-related information with the object(s). The processing subsystem also includes a recommendation module (70) which trains a recommendation-related model, generates the event-related recommendations corresponding to multiple preferred events, and provides link(s) for the event-related recommendation(s), thereby managing the access to the event-related recommendation(s).

Description

SYSTEM AND METHOD FOR MANAGING ACCESS TO EVENT- RELATED RECOMMENDATIONS

EARLIEST PRIORITY DATE

This Application claims priority from a Complete patent application filed in India having Patent Application No. 202241013156, filed on March 10, 2022, and titled “SYSTEM AND METHOD FOR MANAGING ACCESS TO EVENT-RELATED RECOMMENDATIONS

FIELD OF INVENTION

Embodiments of a present disclosure relate to object detection in motion pictures, and more particularly to a system and method for managing access to one or more event- related recommendations.

BACKGROUND

Conventionally, people purchase items online by performing a keyword search on browsing platforms, E-commerce platforms, and the like. Basically, items visualized by a user in real life, televisions, movies, videos, or the like, are searched by performing the keyword search by searching for one or more related keywords online, and if similar items are available, then the user purchases the same even if the items don’t exactly match with the one seen earlier in real life, movies, videos, or the like. Therefore, in such as case, the user usually compromises with the quality, a degree of resemblance, originality, and the like of the items that the user purchases in comparison to the one viewed by the user. Also, the process is time-consuming and may not satisfy the actual needs of the user.

In one approach, if a user has a picture of an item seen by the user in movies, videos, or the like, then the user can use the same picture to search for the corresponding item being available for purchase. However, in such a case also there is a possibility of a certain percent of dissimilarity between the picture and the item that may be available for purchase. This is because, in this case also, the user has to input the picture in a search engine to search for similar pictures and then check for availability of similar products being available for sale. Also, such a process is also time-consuming and may not satisfy the actual needs of the user.

Hence, there is a need for an improved system and method for managing access to one or more event-related recommendations which addresses the aforementioned issues.

BRIEF DESCRIPTION

In accordance with one embodiment of the disclosure, a system for managing access to one or more event-related recommendations is provided. The system includes a processing subsystem hosted on a server. The processing subsystem is configured to execute on a network to control bidirectional communications among a plurality of modules. The processing subsystem includes an input module. The input module is configured to receive one or more inputs in real-time upon registration of a user. The one or more inputs include at least one of streaming multimedia being watched by the user and information associated with the corresponding streaming multimedia. The processing subsystem also includes an object segregation module operatively coupled to the input module. The object segregation module is configured to recognize one or more objects from each of a plurality of frames of the corresponding streaming multimedia using a convolutional neural network technique based on a plurality of object-related training datasets. The object segregation module is also configured to segregate the one or more objects under a first category by creating and assigning one or more first labels for the corresponding one or more objects upon recognizing the one or more objects being related to eatables. Further, the processing subsystem also includes a linking module operatively coupled to the object segregation module. The linking module is configured to identify object-related information corresponding to the one or more objects in a system database upon segregating the one or more objects. The linking module is also configured to link a plurality of network-based informative systems with the system database via a predefined linking interface, based on predefined linking criteria, when the object-related information remains unidentified in the system database. The linking module is also configured to identify the object- related information corresponding to the one or more objects, in the corresponding plurality of network-based informative systems using a web-crawling mechanism upon linking. Further, the linking module is also configured to link the object-related information with the corresponding one or more objects, by storing the corresponding object-related information in association with the corresponding one or more objects in the system database as updated-object-related information, upon identification. Furthermore, the processing subsystem also includes a recommendation module operatively coupled to the linking module. The recommendation module is configured to train a recommendation-related model in real-time with a plurality of real-time training datasets using machine learning upon extracting the object-related information and the updated-object-related information from the system database. The plurality of real-time training datasets includes a plurality of details corresponding to at least one of the corresponding object-related information, the corresponding updated-object-related information, a plurality of preferred events associated with the corresponding object-related information and the corresponding updated-object- related information, and predefined event-related criteria. The recommendation module is also configured to generate the one or more event-related recommendations corresponding to the plurality of preferred events using the recommendation-related model. Further, the recommendation module is also configured to provide one or more links for the one or more event-related recommendations based on the segregation of the one or more objects, thereby managing the access to the one or more event-related recommendations .

In accordance with another embodiment, a method for managing access to one or more event-related recommendations is provided. The method includes receiving one or more inputs in real-time upon registration of a user, wherein the one or more inputs include at least one of streaming multimedia being watched by the user and information associated with the corresponding streaming multimedia. The method also includes recognizing one or more objects from each of a plurality of frames of the corresponding streaming multimedia using a convolutional neural network technique based on a plurality of object-related training datasets. Further, the method also includes segregating the one or more objects under a first category by creating and assigning one or more first labels for the corresponding one or more objects upon recognizing the one or more objects being related to eatables. Furthermore, the method also includes identifying object-related information corresponding to the one or more objects in a system database upon segregating the one or more objects. Furthermore, the method also includes linking a plurality of network-based informative systems with the system database via a predefined linking interface, based on predefined linking criteria, when the object-related information remains unidentified in the system database. Furthermore, the method also includes identifying the object-related information corresponding to the one or more objects, in the corresponding plurality of network-based informative systems using a web-crawling mechanism upon linking. Furthermore, the method also includes linking the object-related information with the corresponding one or more objects, by storing the corresponding object-related information in association with the corresponding one or more objects in the system database as updated-object-related information, upon identification. Furthermore, the method also includes training a recommendation-related model in real-time with a plurality of real-time training datasets using machine learning upon extracting the object-related information and the updated-object-related information from the system database , wherein the plurality of real-time training datasets includes a plurality of details corresponding to at least one of the corresponding object-related information, the corresponding updated-object-related information, a plurality of preferred events associated with the corresponding object-related information and the corresponding updated-object-related information, and predefined event-related criteria. Furthermore, the method also includes generating the one or more event-related recommendations corresponding to the plurality of preferred events using the recommendation-related model. Furthermore, the method also includes providing one or more links for the one or more event-related recommendations based on the segregation of the one or more objects, thereby managing the access to the one or more event-related recommendations.

To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered limiting in scope. The disclosure will be described and explained with additional specificity and detail with the appended figures.

BRIEF DESCRIPTION OF THE DRAWINGS

The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which: FIG. 1 is a block diagram representation of a system for managing access to one or more event-related recommendations in accordance with an embodiment of the present disclosure;

FIG. 2 is a block diagram representation of an exemplary embodiment of the system for managing access to one or more event-related recommendations of FIG. 1 in accordance with an embodiment of the present disclosure;

FIG. 3 is a block diagram of a recommendation management computer or a recommendation management server in accordance with an embodiment of the present disclosure;

FIG. 4 (a) is a flow chart representing steps involved in a method for managing access to one or more event-related recommendations in accordance with an embodiment of the present disclosure; and

FIG. 4 (b) is a flow chart representing continued steps involved in a method of FIG. 4 (a) in accordance with an embodiment of the present disclosure.

Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.

DETAILED DESCRIPTION

For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present disclosure.

The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more devices or sub-systems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, sub-systems, elements, structures, components, additional devices, additional sub-systems, additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.

In the following specification and the claims, reference will be made to a number of terms, which shall be defined to have the following meanings. The singular forms “a”, “an”, and “the” include plural references unless the context clearly dictates otherwise.

Embodiments of the present disclosure relate to a system for managing access to one or more event-related recommendations. Basically, while watching streaming multimedia online, people often crave one or more objects seen in the corresponding streaming multimedia, for example, accessories worn by actors, the furniture shown in a video, a food item shown in a video, and the like. The people may expect one or more events to be available in association with the corresponding one or more objects. In one embodiment, the one or more events may correspond to being able to purchase the corresponding one or more objects, being able to purchase tickets to visit a site shown in a video, being able to book a trip to a location shown in a video and the like. Therefore, the one or more event-related recommendations may correspond to recommendations related to the one or more events as a user is watching the streaming multimedia, so that the user can immediately access the corresponding one or more event-related recommendations. Further, the system described hereafter in FIG. 1 is the system for managing the access to the one or more event-related recommendations.

FIG. 1 is a block diagram representation of a system (10) for managing access to one or more event-related recommendations in accordance with an embodiment of the present disclosure. The system (10) includes a processing subsystem (20) hosted on a server (30). In one embodiment, the server (30) may include a cloud server. In another embodiment, the server (30) may include a local server. The processing subsystem (20) is configured to execute on a network (not shown in FIG. 1) to control bidirectional communications among a plurality of modules. In one embodiment, the network may include a wired network such as a local area network (LAN). In another embodiment, the network may include a wireless network such as wireless fidelity (Wi-Fi), Bluetooth, Zigbee, near field communication (NFC), infra-red communication (RFID), or the like.

Basically, for a user to be able to access the one or more event-related recommendations while watching streaming multimedia, the user may have to use the system (10). As used herein, the term “streaming multimedia” is video and audio data transmitted over a computer network for immediate playback rather than for file download and later offline playback. In one exemplary embodiment, the streaming multimedia may include YOUTUBE® videos, internet radio and television broadcasts, corporate webcasts, a movie, and the like. Also, in one embodiment, the system (10) may be linked with one or more online streaming platforms such as YOUTUBE®, NETFLIX®, and the like as a plugin, an additional feature made available for free, an additional paid feature, or the like. In an alternative embodiment, the system (10) may be available as an independent platform for the user to use upon registration or subscription. Therefore, in an embodiment, the processing subsystem (20) may include a registration module (as shown in FIG. 2). The registration module may be configured to register the user with the system (10) upon receiving a plurality of user details via a user device. In one embodiment, the plurality of user details may include a username, contact details, a geographical location, or the like of the user. The plurality of user details may be stored in a system database (as shown in FIG. 2) of the system (10). In one embodiment, the system database may include a local database or a cloud database. Furthermore, in one embodiment, the user device may include a mobile phone, a tablet, a laptop, or the like.

Upon registration, the user may be able to use one or more features provided by the system (10). Further, for the system (10) to be able to do so, the system (10) may receive certain inputs, process the corresponding inputs, and generate results. Therefore, the processing subsystem (20) includes an input module (40). The input module (40) is configured to receive one or more inputs in real-time upon registration of the user. The one or more inputs include at least one of the streaming multimedia being watched by the user and information associated with the corresponding streaming multimedia. In an embodiment, the information associated with the streaming multimedia may include at least one of a media name, media creator details, a media genre, media performer details, and the like.

Upon receiving the one or more inputs, the one or more inputs may have to be processed or analyzed for extracting information about one or more objects from the one or more inputs. Thus, the processing subsystem (20) also includes an object segregation module (50) operatively coupled to the input module (40). The object segregation module (50) is configured to recognize one or more objects from each of a plurality of frames of the corresponding streaming multimedia using a convolutional neural network (CNN) technique based on a plurality of object-related training datasets. The object segregation module (50) is also configured to segregate the one or more objects under a first category by creating and assigning one or more first labels for the corresponding one or more objects upon recognizing the one or more objects being related to eatables. Basically, in an embodiment, the streaming multimedia may be composed of the plurality of frames of images positioned one after the other.

As used herein, the term “convolutional neural network” is a class of artificial neural networks, most commonly used for image processing, classification, segmentation, and also for other autocorrelated data. In one embodiment, the plurality of object- related training datasets may include a plurality of images, a plurality of videos, a plurality of shapes, a plurality of sizes, a plurality of colors, and the like of a plurality of objects classified under one or more classes along with information about the plurality of objects. In one embodiment, the plurality of objects may include a person, a car, a kite, a bird, a tree, a bag, a watch, and the like. Therefore, an object detection model may be generated using the CNN technique based on the plurality of object- related training datasets, then the object detection model may be used to detect and recognize the one or more objects via the object segregation module (50). Upon recognizing the one or more objects, the corresponding one or more objects may be segregated via the object segregation module (50). Suppose the one or more objects are recognized to be eatables. Then, the one or more objects may be segregated under the first category. In one embodiment, the first category may include a food category, eateries category, dishes category, or the like. Further, in one embodiment, the one or more first labels may correspond to ‘noodles’, ‘pizza’, ‘rice’, or the like.

Furthermore, in one exemplary embodiment, the object segregation module (50) may be configured to segregate the one or more objects under one or more second categories by creating and assigning one or more second labels for the corresponding one or more objects upon recognizing the one or more objects. In one embodiment, the one or more second categories may include a travel category, a retail industry category, a restaurant category, a tourism industry category, and the like. Also, in an embodiment, the one or more second labels may correspond to ‘boat’, ‘resort’, ‘fort’, ‘watch’, ‘dress’, ‘jewelry’, ‘actor’, or the like. Therefore, in an embodiment, the one or more second labels such as ‘boat’, ‘car’, ‘bus’, and the like may be classified under the travel category. Similarly, the one or more objects are classified under the one or more second categories.

Later, in an embodiment, the system database may have information about the one or more objects. Therefore, the processing subsystem (20) also includes a linking module (60) operatively coupled to the object segregation module (50). The linking module (60) is configured to identify object-related information corresponding to the one or more objects in the system database upon segregating the one or more objects. Further, in an embodiment, the object-related information present in the system database may be corresponding to a few of the one or more objects segregated by the object segregation module (50). The information corresponding to rest of the one or more objects may be available on a plurality of network-based informative systems. In one exemplary embodiment, the object-related information may include the information corresponding to the one or more objects such as, but not limited to, identity-related details of the one or more objects, availability of the one or more objects for sale, ratings associated with the corresponding one or more objects, a popularity level of the one or more objects, and the like.

In one embodiment, the plurality of network-based informative systems may include GOOGLE® search engine, WIKIPEDIA®, a plurality of other browsers, a plurality of knowledge- sharing platforms, a plurality of E-commerce platforms, and the like. Therefore, to get access to the information available on the plurality of network-based informative systems about the one or more objects, the plurality of network-based informative systems may have to be linked with the system database. Thus, the linking module (60) is also configured to link the plurality of network-based informative systems with the system database via a predefined linking interface, based on predefined linking criteria, when the object-related information remains unidentified in the system database. The linking module (60) is also configured to identify the object-related information corresponding to the one or more objects, in the corresponding plurality of network-based informative systems using a web-crawling mechanism upon linking. Further, the linking module (60) is also configured to link the object-related information with the corresponding one or more objects, by storing the corresponding object-related information in association with the corresponding one or more objects in the system database as updated-object-related information, upon identification. Also, in an embodiment, the object-related information may be available in one or more forms such as, but not limited to, a text form, an image form, a video form, and the like. Therefore, the updated-object-related information may also be present in the one or more forms.

In one embodiment, the predefined linking criteria may correspond to at least one of a legal agreement between owners of the system (10) proposed in the present disclosure and that of the plurality of network-based informative systems for protecting terms and conditions of both, an agreement of purchase, a permission certificate, and the like. Also, as used herein, the term “web -crawling” is a process of systematically browsing World Wide Web in an automated manner. Therefore, as the object-related information is linked with the corresponding one or more objects visible in the corresponding streaming multimedia, the user may be able to access the same upon selecting the corresponding one or more objects. Later, upon becoming aware of the object-related information or the updated-object-related information, the user may be willing to perform one or more actions such as purchasing the one or more objects, making a reservation corresponding to the one or more objects, knowing more about the one or more objects, or the like.

Therefore, the processing subsystem (20) also includes a recommendation module (70) operatively coupled to the linking module (60). The recommendation module (70) is configured to train a recommendation-related model in real-time with a plurality of real-time training datasets using machine learning (ML) upon extracting the object- related information and the updated-object-related information from the system database. The plurality of real-time training datasets includes a plurality of details corresponding to at least one of the corresponding object-related information, the corresponding updated-object-related information, a plurality of preferred events associated with the corresponding object-related information, and the corresponding updated-object-related information, predefined event-related criteria, and the like. The recommendation module (70) is also configured to generate the one or more event- related recommendations corresponding to the plurality of preferred events using the recommendation-related model. In one embodiment, the one or more event-related recommendations may be generated for the user when the user may be watching the streaming multimedia. Also, in an embodiment, the one or more event-related recommendations may be directly generated when the object-related information is identified in the system database. In another embodiment, the one or more event- related recommendations may be generated when the updated-object-related information is identified in the system database. Further, the recommendation module (70) is also configured to provide one or more links for the one or more event-related recommendations based on the segregation of the one or more objects, thereby managing the access to the one or more event-related recommendations.

As used herein, the term “machine learning” is defined as an application of artificial intelligence (Al) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. In one embodiment, the plurality of preferred events may correspond to a purchasing option, a reservation option, a booking option, or the like. Also, in an embodiment, the preferred event- related criteria may include permission to access user details, checking an authenticity of the corresponding plurality of preferred events, securing access to the user details from a third party, or the like. Moreover, in one exemplary embodiment, the one or more event-related recommendations may include at least one of a travel package recommendation, a reservation recommendation, an object purchase recommendation, a nearby location recommendation, a nearby site recommendation, and the like. Further, in an embodiment, upon selecting the one or more links while watching the corresponding streaming multimedia, the user may be diverted to one or more external platforms such as one or more purchase platforms, one or more reservation platforms, one or more booking platforms, one or more E-commerce platforms, or the like.

Basically, after segregation of the one or more objects, when the object-related information is been searched in the plurality of network-based informative systems, suppose the object-related information such as the availability of the one or more objects for sale corresponds to a fact that the corresponding one or more objects may be unavailable for sale. Therefore, in order to make the corresponding one or more objects available for sale on at least one of the plurality of network-based informative systems, certain recommendations may be shared with the corresponding plurality of network-based informative systems. Thus, in an embodiment, the recommendation module (70) may also be configured to generate one or more object-related recommendations for the plurality of network-based informative systems using the recommendation-related model, based on the segregation of the one or more objects. The one or more object-related recommendations may include at least one of an object availability-related recommendation, a public interest-related recommendation, a public search-related recommendation, and the like. For example, the plurality of network-based informative systems may be recommended to make the corresponding one or more objects available for sale as the user may be interested to purchase the same.

Later, the plurality of network-based informative systems might make the corresponding one or more objects available for sale. Further, when the user visits the plurality of network-based informative systems directly, the user may further receive recommendations to purchase the corresponding one or more objects if interested, on the corresponding plurality of network-based informative systems, as the plurality of network-based informative systems are linked with the system database. Subsequently, in one embodiment, a media genre of the corresponding streaming multimedia being watched by the user may have to be identified if not provided in the information associated with the corresponding streaming multimedia. Therefore, in one embodiment, the processing subsystem (20) may also include a multimedia identification module (as shown in FIG. 2) operatively coupled to the object segregation module (50). The multimedia identification module may be configured to recognize one or more faces from the one or more objects using a face recognition technique based on a plurality of face-related training datasets when the corresponding one or more objects are segregated under a facial feature category. The multimedia identification module may also be configured to identify the media genre of the corresponding streaming multimedia based on at least one of the one or more inputs, the segregation of the one or more objects, the recognition of the one or more faces, and a plurality of media-genre-related training datasets.

As used herein, the term “face recognition technique” is defined as a technique capable of matching a human face from a digital image or a video frame against a database of faces. Therefore, in one embodiment, the plurality of face-related training datasets may include a plurality of images, a plurality of videos, or the like of a plurality of faces with a corresponding identity of each of the plurality of faces, a plurality of facial textures, color, a plurality of features, a plurality of shapes, and the like. Further, in one embodiment, the media genre may include action, adventure, horror, comedy, crime, science fiction, or the like. Therefore, in one embodiment, the plurality of media-genre-related training datasets may include a definition of the media genre in terms of a type of the one or more objects, a list of media genres, and the like.

Later, upon identifying the media genre, the user may expect to receive certain recommendations related to the media genre of the corresponding streaming multimedia. Therefore, in an embodiment, the recommendation module (70) may be configured to generate one or more genre-related recommendations based on the identification of the media genre of the corresponding streaming multimedia. The one or more genre-related recommendations may include at least one of an entertainment recommendation, a recognized face-related current events recommendation, a recognized face-related future events recommendation, and the like. In addition, in an embodiment, the processing subsystem (20) may also include a bidding module (as shown in FIG. 2) operatively coupled to the recommendation module (70). the bidding module may be configured to accept a bid raised by the user for the one or more objects from the streaming multimedia based on at least one of availability of the one or more objects for bidding, and preset bidding criteria, upon receiving the corresponding one or more links. In one embodiment, the preset bidding criteria may include at least one of a bidding amount being greater than a predefined amount, one or more objects belonging to one or more actors or one or more actresses of a certain movie or a television show, and the like.

FIG. 2 is a block diagram representation of an exemplary embodiment of the system (10) for managing the access to the one or more event -related recommendations of FIG. 1 in accordance with an embodiment of the present disclosure. The system (10) includes the processing subsystem (20) hosted on the server (30). Suppose a person ‘A’ (80) is watching a movie ‘XYZ’ (90) on YOUTUBE®. As the person ‘A’ (80) is watching the movie ‘XYZ’ (90), the person ‘A’ (80) liked a jacket (100) being worn by a hero ‘B’ (110) in the movie ‘XYZ’ (90). Further, the person ‘A’ (80) notices an additional feature being provided by the YOUTUBE®, which enables people to purchase items shown in videos watched by people on YOUTUBE®. To activate this feature on a personal mobile phone (120) of the person ‘A’ (80), the person ‘A’ (80) must register with the system (10) enabling the corresponding feature. Therefore, the person ‘A’ (80) registers with the system (10) via the registration module (130) by providing a plurality of personal details via the personal mobile phone (120). The plurality of personal details is stored in the system database (140). Upon registration, the system (10) will be able to enable the person ‘A’ (80) to purchase the corresponding jacket (100) by performing the following steps such as initially receiving the movie ‘XYZ’ (90) as an input along with information related to the movie ‘XYZ’ (90), via the input module (40). Then, the one or more objects displayed in each of the plurality of frames of the movie ‘XYZ’ (90) are recognized and segregated under different categories via the object segregation module (50).

Later, information about each of the one or more objects is searched by web crawling and linked with the corresponding one or more objects via the linking module (60). Then, the one or more event-related recommendations corresponding to the plurality of preferred events such as a reservation event, a purchasing event, a booking event, and the like are generated via the recommendation module (70). Further, the one or more links are also provided for the one or more event-related recommendations via the recommendation module (70), for the person ‘A’ (80) to select and get access to purchasing the corresponding jacket (100), as the jacket (100) is a part of the one or more objects. The one or more event-related recommendations are basically redirecting the person ‘A’ (80) to an external link such as to an AMAZON® page, where one or more jackets similar to the jacket (100) shown in the corresponding movie ‘XYZ’ (90) are available for the person ‘A’ (80) to purchase. Later, the person ‘A’ (80) also observed that the corresponding jacket (100) has been made available for bidding purposes. So, the person ‘A’ (80) decides to raise the bid for the same. Later, the bid raised by the person ‘A’ (80) is accepted via the bidding module (150) by comparing the bidding amount with that of other users. Once the bid is accepted, the person ‘A’ (80) purchases the jacket (100) by paying the bidding amount. Further, after watching the movie ‘XYZ’ (90), the person ‘A’ (80) may be willing to receive certain recommendations for similar movies, other movies of heroes that were present in the movie ‘XYZ’ (90), movies having similar media genre and the like. Therefore, the system (10) also identifies the media genre of the movie ‘XYZ’ (90) by recognizing faces of one or more characters present in the movie ‘XYZ’ (90) via the multimedia identification module (160). Then, based on the media genre identified, the person ‘A’ (80) receives the one or more genre-related recommendations via the recommendation module (70). Suppose the media genre of the movie ‘xyz’ (90) identified is a horror movie. Therefore, the person ‘A’ (80) receives recommendations for horror movies, movies of people recognized in the movie ‘XYZ’ (90), and the like.

FIG. 3 is a block diagram of a recommendation management computer or a recommendation management server (170) in accordance with an embodiment of the present disclosure. The recommendation management server (170) includes processor(s) (180), and a memory (190) operatively coupled to a bus (200). The processor(s) (180), as used herein, means any type of computational circuit, such as, but not limited to, a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicitly parallel instruction computing microprocessor, a digital signal processor, or any other type of processing circuit, or a combination thereof.

Computer memory elements may include any suitable memory device(s) for storing data and executable program, such as read only memory, random access memory, erasable programmable read only memory, electrically erasable programmable read only memory, hard drive, removable media drive for handling memory cards and the like. Embodiments of the present subject matter may be implemented in conjunction with program modules, including functions, procedures, data structures, and application programs, for performing tasks, or defining abstract data types or low-level hardware contexts. Executable program stored on any of the above-mentioned storage media may be executable by the processor(s) (180).

The memory (190) includes a plurality of subsystems stored in the form of executable program which instructs the processor(s) (180) to perform method steps illustrated in FIG. 4. The memory (190) includes a processing subsystem (20) of FIG 1. The processing subsystem (20) further has following modules: an input module (40), an object segregation module (50), a linking module (60), and a recommendation module (70).

The input module (40) is configured to receive one or more inputs in real-time upon registration of a user, wherein the one or more inputs include at least one of streaming multimedia being watched by the user and information associated with the corresponding streaming multimedia.

The object segregation module (50) is configured to recognize one or more objects from each of a plurality of frames of the corresponding streaming multimedia using a convolutional neural network technique based on a plurality of object-related training datasets. The object segregation module (50) is also configured to segregate the one or more objects under a first category by creating and assigning one or more first labels for the corresponding one or more objects upon recognizing the one or more objects being related to eatables

The linking module (60) is configured to link a plurality of network-based informative systems with a system database (140) based on predefined linking criteria upon segregating the one or more objects. The linking module (60) is also configured to identify object-related information corresponding to the one or more objects, in the corresponding plurality of network-based informative systems using a web-crawling mechanism upon linking. Further, the linking module (60) is also configured to link the object-related information with the corresponding one or more objects, by storing the corresponding object-related information in association with the corresponding one or more objects in the system database (140), upon identification.

The recommendation module (70) is configured to train a recommendation-related model in real-time with a plurality of real-time training datasets using machine learning based on the object-related information linked with the one or more objects. The plurality of real-time training datasets includes a plurality of details corresponding to at least one of the corresponding object-related information, a plurality of preferred events associated with the corresponding object-related information, and predefined event-related criteria. The recommendation module (70) is also configured to generate the one or more event-related recommendations corresponding to the plurality of preferred events using the recommendation-related model. The recommendation module (70) is also configured to provide one or more links for the one or more event- related recommendations based on the segregation of the one or more objects, thereby managing the access to the one or more event-related recommendations. The bus (200) as used herein refers to be internal memory channels or computer network that is used to connect computer components and transfer data between them. The bus (200) includes a serial bus or a parallel bus, wherein the serial bus transmits data in a bitserial format and the parallel bus transmits data across multiple wires. The bus (200) as used herein, may include but not limited to, a system bus, an internal bus, an external bus, an expansion bus, a frontside bus, a backside bus, and the like.

FIG. 4 (a) is a flow chart representing steps involved in a method (210) for managing access to one or more event-related recommendations in accordance with an embodiment of the present disclosure. FIG. 4 (b) is a flow chart representing continued steps involved in the method (210) of FIG. 4 (a) in accordance with an embodiment of the present disclosure. The method (210) includes receiving one or more inputs in real-time upon registration of a user, wherein the one or more inputs include at least one of streaming multimedia being watched by the user and information associated with the corresponding streaming multimedia in step 220. In one embodiment, receiving the one or more inputs may include receiving the one or more inputs by an input module (40).

The method (210) also includes recognizing one or more objects from each of a plurality of frames of the corresponding streaming multimedia using a convolutional neural network technique based on a plurality of object-related training datasets in step 230. In one embodiment, recognizing the one or more objects may include recognizing the one or more objects by an object segregation module (50).

Furthermore, the method (210) includes segregating the one or more objects under a first category by creating and assigning one or more first labels for the corresponding one or more objects upon recognizing the one or more objects being related to eatables in step 240. In one embodiment, segregating the one or more objects under the first category may include segregating the one or more objects under the first category by the object segregation module (50).

In one exemplary embodiment, the method (210) may also include segregating the one or more objects under one or more second categories by creating and assigning one or more second labels for the corresponding one or more objects upon recognizing the one or more objects. In such embodiment, segregating the one or more objects under the one or more second categories may include segregating the one or more objects under the one or more second categories by the object segregation module (50).

Furthermore, the method (210) also includes identifying object-related information corresponding to the one or more objects in a system database upon segregating the one or more objects in step 245. In an embodiment, identifying the object-related information in the system database may include identifying the object-related information in the system database by a linking module (60).

Furthermore, the method (210) also includes linking a plurality of network-based informative systems with the system database via a predefined linking interface, based on predefined linking criteria, when the object-related information remains unidentified in the system database in step 250. In one embodiment, linking the plurality of network-based informative systems with the system database may include linking the plurality of network-based informative systems with the system database by the linking module (60). Furthermore, the method (210) also includes identifying the object-related information corresponding to the one or more objects, in the corresponding plurality of networkbased informative systems using a web-crawling mechanism upon linking in step 260. In one embodiment, identifying the object-related information may include identifying the object-related information by the linking module (60).

Furthermore, the method (210) also includes linking the object-related information with the corresponding one or more objects, by storing the corresponding object- related information in association with the corresponding one or more objects in the system database as updated-object-related information, upon identification in step 270. In one embodiment, linking the object-related information with the corresponding one or more objects may include linking the object-related information with the corresponding one or more objects by the linking module (60).

Furthermore, the method (210) also includes training a recommendation-related model in real-time with a plurality of real-time training datasets using machine learning upon extracting the object-related information and the updated-object-related information from the system database, wherein the plurality of real-time training datasets includes a plurality of details corresponding to at least one of the corresponding object-related information, the corresponding updated-object-related information, a plurality of preferred events associated with the corresponding object-related information and the corresponding updated-object-related information, and predefined event-related criteria in step 280. In one embodiment, training the recommendation-related model may include training the recommendation-related model by a recommendation module (70).

Furthermore, the method (210) also includes generating the one or more event-related recommendations corresponding to the plurality of preferred events using the recommendation-related model in step 290. In one embodiment, generating the one or more event-related recommendations may include generating the one or more event- related recommendations by the recommendation module (70).

Furthermore, the method (210) also includes providing one or more links for the one or more event-related recommendations based on the segregation of the one or more objects, thereby managing the access to the one or more event-related recommendations in step 300. In one embodiment, providing the one or more links may include providing the one or more links by the recommendation module (70).

Further, in one exemplary embodiment, the method (210) may also include recognizing one or more faces from the one or more objects using a face recognition technique based on a plurality of face-related training datasets when the corresponding one or more objects are segregated under a facial feature category. In such embodiment, recognizing the one or more faces may include recognizing the one or more faces by a multimedia identification module (160).

Also, in an embodiment, the method (210) may further include identifying a media genre of the corresponding streaming multimedia based on at least one of the one or more inputs, the segregation of the one or more objects, the recognition of the one or more faces, and a plurality of media-genre-related training datasets. In such embodiment, identifying the media genre of the corresponding streaming multimedia may include identifying the media genre of the corresponding streaming multimedia by the multimedia identification module (160).

Further, in one embodiment, generating one or more genre -related recommendations based on the identification of the media genre of the corresponding streaming multimedia, wherein the one or more genre-related recommendations includes at least one of an entertainment recommendation, a recognized face-related current events recommendation, and a recognized face-related future events recommendation. In such an embodiment, generating the one or more genre-related recommendations may include generating the one or more genre-related recommendations by the recommendation module (70).

Furthermore, in one exemplary embodiment, the method (210) may also include accepting a bid raised by the user for the one or more objects from the streaming multimedia based on at least one of availability of the one or more objects for bidding, and preset bidding criteria, upon receiving the corresponding one or more links. In such an embodiment, accepting the bid raised by the user may include accepting the bid raised by the user by a bidding module (150).

Further, from a technical effect point of view, the implementation time required to perform the method steps included in the present disclosure by the one or more processors of the system is very minimal, thereby the system maintains very minimal operational latency and requires very minimal processing requirements.

Various embodiments of the present disclosure enable the user to purchase travel tickets, book hotels, purchase accessories worn by an actor, purchase mouth-watering food items from eateries, recommend similar movies, and the like from a video with just a single click in real-time. The system can recognize and match an object or an item within the video to a marketplace wherein they can be purchased or recognize the area, location in the video to its exact geographical location, and the like. These objects or items are just a part of the video/movie playing on any platform but with a pause, they can become a world of information from shopping, dining, traveling to those very places on the video. Furthermore, the system proposed in the present disclosure is all about utilizing interest, desire as shown by the user, that is; leveraging consumer’s behavior and converting it into an opportunity for streaming content providers.

While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person skilled in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.

The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, order of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts need to be necessarily performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples.

Claims

WE CLAIM:

1. A system (10) for managing access to one or more event-related recommendations comprising: a processing subsystem (20) hosted on a server (30), and configured to execute on a network to control bidirectional communications among a plurality of modules comprising: an input module (40) configured to receive one or more inputs in realtime upon registration of a user, wherein the one or more inputs comprises at least one of streaming multimedia being watched by the user and information associated with the corresponding streaming multimedia; an object segregation module (50) operatively coupled to the input module (40), wherein the object segregation module (50) is configured to: recognize one or more objects from each of a plurality of frames of the corresponding streaming multimedia using a convolutional neural network technique based on a plurality of object-related training datasets; and segregate the one or more objects under a first category by creating and assigning one or more first labels for the corresponding one or more objects upon recognizing the one or more objects being related to eatables; a linking module (60) operatively coupled to the object segregation module (50), wherein the linking module (60) is configured to: identify object-related information corresponding to the one or more objects in a system database (140) upon segregating the one or more objects; link a plurality of network-based informative systems with the system database (140) via a predefined linking interface, based on predefined linking criteria, when the object-related information remains unidentified in the system database (140); identify the object-related information corresponding to the one or more objects, in the corresponding plurality of network-based informative systems using a web-crawling mechanism upon linking; and link the object-related information with the corresponding one or more objects, by storing the corresponding object-related information in association with the corresponding one or more objects in the system database (140) as updated-object-related information, upon identification; and a recommendation module (70) operatively coupled to the linking module (60), wherein the recommendation module (70) is configured to: train a recommendation-related model in real-time with a plurality of real-time training datasets using machine learning upon extracting the object-related information and the updated-object- related information from the system database (140), wherein the plurality of real-time training datasets comprises a plurality of details corresponding to at least one of the corresponding object-related information, the corresponding updated-object-related information, a plurality of preferred events associated with the corresponding object- related information and the corresponding updated-object- related information, and predefined event-related criteria; generate the one or more event-related recommendations corresponding to the plurality of preferred events using the recommendation-related model; and provide one or more links for the one or more event-related recommendations based on the segregation of the one or more objects, thereby managing the access to the one or more event-related recommendations .

2. The system (10) as claimed in claim 1, wherein the object segregation module (50) is configured to segregate the one or more objects under one or more second categories by creating and assigning one or more second labels for the corresponding one or more objects upon recognizing the one or more objects.

3. The system (10) as claimed in claim 1, wherein the one or more event- related recommendations comprises at least one of a travel package recommendation, a reservation recommendation, an object purchase recommendation, a nearby location recommendation, and a nearby site recommendation .

4. The system (10) as claimed in claim 1, wherein the recommendation module (70) is configured to generate one or more object-related recommendations for the plurality of network-based informative systems using the recommendation-related model, based on the segregation of the one or more objects, wherein the one or more object-related recommendations comprises at least one of an object availability-related recommendation, a public interest-related recommendation, and a public search-related recommendation.

5. The system (10) as claimed in claim 1, wherein the processing subsystem (20) comprises a bidding module (150) operatively coupled to the recommendation module (70), wherein the bidding module (150) is configured to accept a bid raised by the user for the one or more objects from the streaming multimedia based on at least one of availability of the one or more objects for bidding, and preset bidding criteria, upon receiving the corresponding one or more links.

6. The system (10) as claimed in claim 1, wherein the processing subsystem (20) comprises a multimedia identification module (160) operatively coupled to the object segregation module (50), wherein the multimedia identification module (160) is configured to: recognize one or more faces from the one or more objects using a face recognition technique based on a plurality of face-related training datasets, when the corresponding one or more objects are segregated under a facial feature category; and identify a media genre of the corresponding streaming multimedia based on at least one of the one or more inputs, the segregation of the one or more objects, the recognition of the one or more faces, and a plurality of media-genre -related training datasets.

7. The system (10) as claimed in claim 6, wherein the recommendation module (70) is configured to generate one or more genre-related recommendations based on the identification of the media genre of the corresponding streaming multimedia, wherein the one or more genre-related recommendations comprises at least one of an entertainment recommendation, a recognized face-related current events recommendation, and a recognized face-related future events recommendation.

8. A method (210) for managing access to one or more event-related recommendations comprising: receiving, by an input module (40), one or more inputs in real-time upon registration of a user, wherein the one or more inputs comprises at least one of streaming multimedia being watched by the user and information associated with the corresponding streaming multimedia; (220) recognizing, by an object segregation module (50), one or more objects from each of a plurality of frames of the corresponding streaming multimedia using a convolutional neural network technique based on a plurality of object-related training datasets; (230) segregating, by the object segregation module (50), the one or more objects under a first category by creating and assigning one or more first labels for the corresponding one or more objects upon recognizing the one or more objects being related to eatables; (240) identifying, by a linking module (60), object-related information corresponding to the one or more objects in a system database upon segregating the one or more objects; (245) linking, by the linking module (60), a plurality of network-based informative systems with the system database via a predefined linking interface, based on predefined linking criteria, when the object-related information remains unidentified in the system database;(250) identifying, by the linking module (60), the object-related information corresponding to the one or more objects, in the corresponding plurality of networkbased informative systems using a web-crawling mechanism upon linking; (260) linking, by the linking module (60), the object-related information with the corresponding one or more objects, by storing the corresponding object-related information in association with the corresponding one or more objects in the system database as updated-object-related information, upon identification; (270) training, by a recommendation module (70), a recommendation-related model in real-time with a plurality of real-time training datasets using machine learning upon extracting the object-related information and the updated-object- related information from the system database, wherein the plurality of real-time training datasets comprises a plurality of details corresponding to at least one of the corresponding object-related information, the corresponding updated-object- related information, a plurality of preferred events associated with the corresponding object-related information and the corresponding updated-object- related information, and predefined event-related criteria; (280) generating, by the recommendation module (70), the one or more event- related recommendations corresponding to the plurality of preferred events using the recommendation-related model; and (290) providing, by the recommendation module (70), one or more links for the one or more event-related recommendations based on the segregation of the one or more objects, thereby managing the access to the one or more event-related recommendations (300).

9. The method (210) as claimed in claim 8, comprises segregating, by the object segregation module (50), the one or more objects under one or more second categories by creating and assigning one or more second labels for the corresponding one or more objects upon recognizing the one or more objects.

10. The method (210) as claimed in claim 8, comprises accepting, by a bidding module (150), a bid raised by the user for the one or more objects from the streaming multimedia based on at least one of availability of the one or more objects for bidding, and preset bidding criteria, upon receiving the corresponding one or more links.

11. The method (210) as claimed in claim 8, comprises: recognizing, by a multimedia identification module (160), one or more faces from the one or more objects using a face recognition technique based on a plurality of face-related training datasets when the corresponding one or more objects are segregated under a facial feature category; and identifying, by the multimedia identification module (160), a media genre of the corresponding streaming multimedia based on at least one of the one or more inputs, the segregation of the one or more objects, the recognition of the one or more faces, and a plurality of media-genre-related training datasets.