Method and system for generating real-time update

Abstract

To provide a method and a system for automatically generating one or more real-time updates to at least one live event.SOLUTION: In an embodiment, a processing unit [102] is connected to a storage unit [106] and a display unit [104], and the processing unit [102] fetches a content stream of at least one live event and identifies at least one moment from the content stream. On the basis of the identified moment, at least one real-time update is generated by the processing unit [102]. The generated real-time update is then displayed on the display unit [104].SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] FIELD OF THE DISCLOSURE The present disclosure relates generally to information technology and content distribution methods and systems. More particularly, the present disclosure relates to methods and systems for generating real-time updates to live events. [Background technology]

[0002] The following description of related art is intended to provide background information related to the field of the present disclosure. This section may include some aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section is not intended as an admitted statement of prior art, but rather serves only to enhance the reader's understanding of the present disclosure.

[0003] With advancements in technology and an emphasis on real-time content delivery to users, there has been an increase in the telecast of important global events via content platforms. Both global consumers and businesses are turning to content delivery platforms to make events more accessible across various devices. Events may include time-bound events such as, but not limited to, sporting events, elections, budgets, natural disasters, and other live events. Content delivery platforms today offer both live and static events.

[0004] However, as viewers' time constraints increase, they tend to look for instantaneous follow-ups of live events rather than following the entire duration of the event. Live events generally span a fixed duration. For example, sports competitions / matches are currently viewed through live streams on TV or content distribution platforms. However, if viewers do not watch a live event from the beginning of the event, they are constrained to miss out on learning about important highs and lows of the event and events that demonstrated importance to the live event. Therefore, during the time when viewers are not following up on a live event, they are forced to miss part or the entire live event because they are unable to know what significance occurred in the event during that short period of time. Viewers must watch the live event for the entire elapsed time, which may not always be available.

[0005] Existing solutions for event media visualization are riddled with various shortcomings. One major drawback is that viewers must watch event highlights on a linear TV channel or another content distribution platform, such as an over-the-air (OTT) application. This is in line with broadcasters' preferences for viewing only specific sections of event media that are relevant and important for display to users. While other video sharing platforms publish highlights, they are released after the live event has ended or not in real time. Important events are often published with a delay (usually after the live event has ended), requiring manual publishing efforts. Publishing efforts often incur significant production costs due to editors along the aggregation line. This cost increases significantly when multiple transformations are required to evaluate event information to generate moments using those timelines. Additionally, sourcing royalty-free moments from different platforms also poses potential challenges that only increase the complexity and expense of the process.

[0006] There is currently no existing solution that provides real-time updates on a live / ongoing event, and there is a need for allowing viewers to catch up on past key events of an event (whether live or past) in a chronological manner as desired by the viewer.

[0007] Thus, there are several limitations to existing solutions, and there is a need to provide an efficient solution for automated event media visualization to overcome these and other such limitations of known solutions. Summary of the Invention [Problem to be solved by the invention]

[0008] This section is provided to introduce, in a simplified form, certain objects and aspects of the present invention, which are further described below in the description. To overcome at least some of the problems associated with known solutions, such as those provided in the previous section, it is an object of the present invention to significantly reduce the limitations and disadvantages of the prior art, as discussed above.

[0009] One objective of the present invention is to keep the viewer updated in real time with the key happenings of a live event.

[0010] Another object of the present invention is to update viewers of live events in real time with relevant video segments and text of key happenings.

[0011] It is yet another object of the present invention to help viewers catch up on past key events of an event (live or past) through a collection of updates arranged in a chronological order.

[0012] Yet another object of the present invention is to update the viewer in real time (within a predefined short time instance) with the main happenings in a live / ongoing event through moments consisting of short visual titles representing the happenings.

[0013] It is yet another object of the present invention to generate and add real-time updates to the chronology as events progress. [Means for solving the problem]

[0014] This section is provided to introduce, in a simplified form, some aspects of the disclosure that are further described below in the Detailed Description. This Summary is not intended to identify key features or scope of the claimed subject matter.

[0015] One aspect of the present disclosure may relate to a method for automatically generating one or more real-time updates for at least one live event. The method comprises fetching, by a processing unit, a content stream associated with the at least one live event. Further, the method comprises identifying, by the processing unit, at least one moment from the content stream. Hereinafter, the method comprises generating, by the processing unit, at least one real-time update for the at least one moment. Further, the method comprises displaying, by the processing unit, the at least one real-time update on a display unit.

[0016] In an exemplary aspect of the present disclosure, content streams are fetched from one or more external utilities comprising at least one of live streaming events and news events.

[0017] In an exemplary aspect of the present disclosure, identifying at least one moment from the content stream further comprises categorizing, by a processing unit, one or more input data of the content stream into one of at least one related event and at least one unrelated event. Further, identifying at least one moment from the content stream further comprises calculating an importance score for the at least one related event. Further, the method includes identifying at least one moment from the at least related event based on the importance score.

[0018] In an exemplary aspect of the present disclosure, generating at least one real-time update further comprises determining one or more tags for the at least one moment. The method further comprises generating, by a processing unit, a text summary for the at least one moment. Further, the method comprises identifying, by the processing unit, an image for the at least one associated moment based on the text summary and the one or more tags. Further, the method comprises combining, by the processing unit, the text summary and the identified image to generate the at least one real-time update.

[0019] In an exemplary aspect of the present disclosure, the method further comprises determining, by a processing unit, a progress of the content stream for the at least one live event. Further, the method comprises dynamically merging, by the processing unit, at least one real-time update into a timeline based on the progress. Hereinafter, the method comprises displaying, by the processing unit, the timeline on a display unit.

[0020] Another aspect of the present disclosure may relate to a system for automatically generating one or more real-time updates for at least one live event. The system includes a processing unit coupled to a storage unit and a display unit. The processing unit is configured to fetch a content stream related to the at least one live event. The processing unit is further configured to identify at least one moment from the content stream. The processing unit is further configured to generate at least one real-time update for the at least one moment. The display unit is configured to display the at least one real-time update.

[0021] Yet another aspect of the present disclosure may relate to a non-transitory computer-readable storage medium storing instructions for automatically generating one or more real-time updates for at least one live event, the instructions including executable code that, when executed by one or more units of the system, causes a processing unit of the system to fetch a content stream associated with the at least one live event. The instructions, when executed by the system, further cause the processing unit of the system to identify at least one moment from the content stream. The instructions, when executed by the system, further cause the processing unit of the system to generate at least one real-time update for the at least one moment. The instructions, when executed by the system, further cause a display unit to display the at least one real-time update.

[0022] The accompanying drawings incorporated herein constitute a part of this disclosure. The components in the drawings are not necessarily drawn to scale, emphasis instead being placed on clearly illustrating the principles of the present disclosure. Some drawings may use block diagrams to illustrate components and may not show the internal circuitry of each component. Those skilled in the art will appreciate that the disclosure of such drawings includes a disclosure of electrical components or circuitry commonly used to implement such components. While exemplary connections between subcomponents are shown in the accompanying drawings, those skilled in the art will appreciate that other connections may be possible without departing from the scope of the present invention. All subcomponents within a component may be connected to each other unless otherwise specified. [Brief explanation of the drawings]

[0023] [Figure 1] FIG. 1 illustrates an exemplary system for automatically generating real-time updates to a live event, according to an exemplary embodiment of the present invention. [Figure 2]FIG. 2 illustrates an exemplary method for automatically generating real-time updates to a live event according to an exemplary embodiment of the present invention. [Figure 3] FIG. 3 illustrates an exemplary method for automatic generation of real-time updates to real-time events, according to an exemplary embodiment of the present invention. [Figure 4] FIG. 4 illustrates an exemplary method

[0400] for a backend to publish real-time updates to real-time events according to an exemplary embodiment of the present invention. [Figure 5] A diagram showing an exemplary implementation of generated moments of real-time events

[0500] according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0024] In the following description, for purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present invention. However, it will be apparent that embodiments of the present invention may be practiced without these specific details. Some features described below may each be used independently of one another or with any combination of other features. Individual features may not address any of the problems described above, or may address only some of the problems described above. Some of the problems described above may not be fully addressed by any of the features described herein. Exemplary embodiments of the present invention are described below, as illustrated in the various figures.

[0025] The following description provides only exemplary embodiments and is not intended to limit the scope, applicability, or configuration of the present disclosure. Rather, the following description of exemplary embodiments provides those skilled in the art with an enabling description for implementing the exemplary embodiments. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the present disclosure as described.

[0026] Specific details are provided in the following description to provide a thorough understanding of the present embodiments. However, it will be understood by those skilled in the art that the present embodiments may be practiced without these specific details. For example, circuits, systems, processes, and other components may be shown as components in block diagram form in order not to obscure the present embodiments in unnecessary detail.

[0027] Also, it should be noted that individual embodiments may be described as a process that is depicted as a flowchart, a flow diagram, a data flow diagram, a structure diagram, or a block diagram. While a flowchart may depict operations as a sequential process, many of the operations may be performed in parallel or simultaneously. Additionally, the order of operations may be rearranged. A process is terminated when its operations are completed, but may have additional steps not included in the diagram.

[0028] The words "exemplary" and / or "demonstrative" are used herein to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited by such examples. Additionally, any aspect or design described herein as "exemplary" and / or "demonstrative" should not necessarily be construed as preferred or advantageous over other aspects or designs, nor is it meant to exclude equivalent exemplary structures and techniques known to those skilled in the art. Furthermore, to the extent the terms "includes," "has," "contains," and other similar words are used in either the detailed description or the claims, such terms are intended to be inclusive (similar to the term "comprising" as an open transition) without excluding any additional or other elements.

[0029] As used herein, a "processing unit" or "processor" or "operational processor" includes one or more processors, where a processor refers to any logical circuitry for processing instructions. The processor may be a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor, multiple microprocessors, one or more microprocessors associated with a (digital signal processing) DSP core, a controller, a microcontroller, an application-specific integrated circuit, a field programmable gate array circuit, any other type of integrated circuit, etc. The processor may perform signal coding, data processing, input / output processing, and / or any other function that enables operation of a system according to the present disclosure. More particularly, the processor or processing unit is a hardware processor.

[0030] As used herein, “computing device,” “user equipment,” “user device,” “smart user device,” “smart device,” “electronic device,” “mobile device,” “handheld device,” “wireless communication device,” “mobile communication device,” and “communication device” may refer to any electrical, electronic, and / or computing device or equipment capable of implementing features of the present disclosure. User equipment / devices may include, but are not limited to, mobile phones, smartphones, laptops, general-purpose computers, desktops, personal digital assistants, tablet computers, wearable devices, or any other computing devices capable of implementing features of the present disclosure. User devices may also include at least one input means configured to receive input from at least one of a transceiver unit, a processing unit, a storage unit, a detection unit, and any other such units required to implement features of the present disclosure.

[0031] As used herein, a "storage unit" or "memory unit" refers to a machine-readable medium or computer-readable medium, including any mechanism for storing information in a form readable by a computer or similar machine. For example, a computer-readable medium includes read-only memory ("ROM"), random-access memory ("RAM"), magnetic disk storage media, optical storage media, flash memory devices, or other types of machine-accessible storage media. A storage unit stores at least data that may be needed by one or more units of the system to perform their respective functions.

[0032] As used herein, "interface" or "user interface" refers to a shared boundary across which two or more separate components of a system exchange information or data. An interface may also be referred to as a set of rules or protocols that govern the communication or interaction of one or more modules or one or more units with each other, and also includes the methods, functions, or procedures that may be invoked.

[0033] All modules, units, and components used herein, unless expressly excluded herein, may be software modules or hardware processors, including general-purpose processors, special-purpose processors, conventional processors, digital signal processors (DSPs), multiple microprocessors, one or more microprocessors associated with a DSP core, controllers, microcontrollers, application-specific integrated circuits (ASICs), field-programmable gate array circuits (FPGAs), or any other type of integrated circuit.

[0034] As described in the Background section, known current solutions have several drawbacks. Known current solutions do not provide real-time updates for live events. Updates are generally generated after the expiration of a real-time event. Furthermore, generating updates involves manual effort and significant costs. The present invention relates to a novel method and system for event media visualization. More specifically, the method and system of the present invention relates to the automatic generation of real-time updates for real-time events. Specifically, the present invention relates to a system and method that generates updates in real time (within a pre-defined short time instance) by taking event information (through an API / feed), determining whether it qualifies as a relevant update, and generating a short text description and visual image related to the update. As the event progresses, the present invention selects some or all of the generated updates in real time based on their importance / relevance and automatically arranges them in chronological order in a timeline manner to show the order in which the events occurred, allowing viewers to view / navigate for a quick visual overview of the event or for portions of the event that have passed.

[0035] Referring to Figure 1, a system

[0100] for automatically generating one or more real-time updates for at least one live event is shown, according to an exemplary embodiment of the present invention. The system

[0100] includes at least one processing unit

[0102] , at least one display unit

[0104] , and at least one storage unit

[0106] . It is assumed that all of the components / units of the system

[0100] are connected to each other unless otherwise specified below. Although only a few units are shown in Figure 1, the system

[0100] may include multiple such units, or any number of such units, as needed to implement features of the present disclosure.

[0036] Furthermore, in one implementation, the system

[0100] may reside in a user / viewer device for implementing features of the present invention. The system

[0100] may be part of the user device, and / or may be separate from but in communication with the user device. In another implementation, the system

[0100] may reside in a server. In yet another implementation, the system

[0100] may reside partly in a server and partly in a user device. In one implementation, the method

[0200] as shown in FIG. 2 is performed by the system

[0100] as shown in FIG. 1.

[0037] The processing unit

[0102] is configured to fetch content streams related to at least one live event. In one implementation of the present disclosure, the content streams are fetched from one or more external utilities or applications that stream or broadcast the live event. The content stream refers to real-time, continuous information related to the live event. The one or more external utilities may be one of a live streaming utility, a news event, and the like. In one implementation of the present invention, the processing unit

[0102] may detect the beginning of at least one live event or a live event already in progress to begin fetching the content stream. In one example, the content streams of the live event are received through application programming interfaces (APIs) / feeds / streams present on the system

[0100] that are provided by one or more external utilities. In an exemplary embodiment of the present invention, if the live event relates to a cricket match, the one or more external utilities may include an API that may include a detailed live score or commentary feed.

[0038] Further, the processing unit

[0102] is configured to identify at least one moment from the content stream. To identify the at least one moment, the processing unit

[0102] is configured to analyze the content stream of at least one live event. In one implementation of the solution, a natural language processing model may be used to analyze the content stream. The natural language processing model may convert natural language in the content stream into machine-readable language. In one example, the analysis can be performed in real time using an intelligent model right from the start of the live event to the completion of the live event, where the intelligent model analyzes based on highlights of similar events that have previously been highlighted. The previous similar event highlights may be stored in the artificial intelligence (AI) model as training data based on which the system

[0100] identifies related events within the live event.

[0039] To identify the at least one moment, the processing unit

[0102] may be configured to categorize one or more input data coming in the content stream into one of at least one relevant event and at least one unrelated event. The at least one relevant event refers to an important milestone in the content stream. For example, in the case of a live cricket event, the at least one relevant event in the analyzed content stream may include a player completing 50 / 100 runs, a wicket, a catch-out, a missed wicket, a review, a win, a loss, etc. The unrelated event refers to a part of the content stream that does not contribute to generating real-time updates. For example, in a live natural disaster information, the at least one unrelated event in the content stream may include an advertisement, an interview with a nature expert, etc.

[0040] After categorizing the content stream into at least one related event and at least one unrelated stream, at least one moment may be identified from the at least one related event. The method further includes calculating an importance score for the at least one related event. The importance score refers to the risk or importance of the event. In one implementation of the present solution, a natural language processing AI model processes the event information and considers it as a moment based on the risk / importance of the event. Thus, in one implementation of the present disclosure, at least one moment may be identified based on the importance score. In one example, the processing unit may consider a content stream as a related event based on the number of words spoken within a predetermined duration and the speaker's high tone in the content. Note that, as used herein, "moment" refers to a portion of a predetermined time interval of a live event. For example, in the previous example of a live cricket match, a moment may include a 10-second clip of a batsman hitting a six.

[0041] In a further exemplary implementation, the intelligent model may have stored one or more moments from a previous event of a live cricket match event. In one example, the one or more moments include, but are not limited to, fours and sixes scored, a player's individual milestone, a hat trick, a missed catch by a leading batsman, or a century. The intelligent model may use one or more moments from a previous live cricket match event to identify one or more moments in the live event. Another instance may include an event such as a national budget presentation, which may have moments such as major regulatory changes affecting several industries.

[0042] The processing unit

[0102] is further configured to generate at least one real-time update for at least one moment. The at least one real-time update may include, but is not limited to, determining one or more tags, generating a text summary, and generating an image. In one implementation of the present invention, a natural language processing AI model processes the identified moments and generates one or more tags associated with the at least one moment. As used herein, "one or more tags" refers to attributes associated with at least one moment. For example, in the example of a live cricket tournament event, the one or more tags may include player names, event name, score, team name, opposing team name, tournament name, etc. Furthermore, a text summary may be generated based on the one or more tags. As used herein, a text summary refers to a short text description of at least one moment.

[0043] Further, the processing unit

[0102] identifies an image for at least one relevant event based on the generated text summary and one or more tags. In one example, the image may be selected from the storage unit

[0106] . In another example, the image may be generated using an intelligent model. The image may be pre-stored in the storage unit

[0106] by a system operator or may be stored from previously generated images. In one implementation of the present disclosure, the image may be identified based on at least one moment and a feeling of the live event. For example, if a moment in a live cricket match is related to a player scoring a run in the match, the selected image may include the player's name as a subject, along with the player wearing gear relevant to the match and in a celebratory pose. Furthermore, the generated text and the generated image may be combined to generate at least one real-time update.

[0044] The display unit

[0104] is configured to display at least one real-time update. In one example, the display unit

[0104] may be a content management system (CMS), such as a television application, a mobile application, a desktop application, etc. Displaying may include, but is not limited to, sending emails, messages, or notifications to the user. The at least one real-time update is displayed in real time.

[0045] The processing unit

[0102] may further store the real-time updates in the storage unit

[0106] . In one implementation of the present disclosure, the processing unit

[0102] is configured to store one or more real-time updates as the live event progresses. In one example, the one or more real-time updates may be stored along with a timestamp. Furthermore, the processing unit

[0102] is further configured to detect the progress of the at least one live event over a predetermined time period. The progress of the at least one live event refers to the continuation of the live event over some time period. For example, the at least one live event started at 4:00 PM. The predetermined time period is 10 minutes, and by 4:10 PM, three real-time updates have been stored in the storage unit

[0106] .

[0046] Further, the processing unit

[0102] is configured to select one or more generated real-time updates from the list of generated real-time updates. The processing unit

[0102] is configured to select one or more generated real-time updates from the generated real-time updates stored in the storage unit

[0106] . In one example, the processing unit

[0102] may select each of the generated real-time updates. In another example, the processing unit

[0102] may select one or more of the generated real-time updates based on a comparison of importance scores. In one implementation of the present disclosure, a generated real-time update with a high importance score may be selected by the processing unit

[0102] .

[0047] The processing unit

[0102] is further configured to dynamically merge one or more real-time updates to form a timeline. As used herein, a timeline refers to a collection of past real-time updates of a live event. The timeline may help a user catch up on what important events have passed in the live event within a short amount of time through the collection of video portions. The timeline updates as the live event progresses and continues to add more real-time updates as they are generated in real time. Thereafter, the processing unit

[0102] is configured to display the timeline to a user on the display unit

[0104] .

[0048] In one example, a flood warning is issued in city X, but some people have to go to work, some are working from home, and some have to travel to other areas of the city for some urgent work. Since many people are busy at work and cannot always watch live news updates, the system

[0100] may fetch content streams from live news events and identify relevant events. Relevant events may include, but are not limited to, water entering houses in a particular area of ​​the city, the speed at which water is entering the city, disasters, roads blocked by police, etc. The system

[0100] may identify and filter out irrelevant events, such as advertisements, interviews with people, etc. The system

[0100] may generate text summaries for the relevant events, and based on the text summaries, images may be generated or extracted from the storage unit

[0106] . The text summary may be combined with the image to form at least one real-time update for the moment of water entering the house, with the text summary "Water reaches homes and businesses in area UVW in city X" displayed to the user whenever the user opens their computing device. In furtherance of generating the real-time updates, as one or more updates are generated, the one or more updates are stored in the storage unit

[0106] . The system

[0100] may select at least one update from the one or more updates to generate a timeline. The timeline shows a chronological sequence of events occurring during a flood disaster. For example, the timeline may include water breaching danger signs, villagers near the river being rescued, water flooding roads, water flooding homes, etc. The timeline and moments ease the user experience and reduce the amount of time required by the user for the news application to stay updated.

[0049] Reference is now made to FIG. 2 , which illustrates an exemplary method

[0200] for automatically generating one or more real-time updates for at least one live event according to an exemplary embodiment of the present invention. In one implementation, the method is performed by a system

[0100] such as that shown in FIG. 1 . The method begins at step

[0202] and proceeds to step

[0204] , where the method comprises fetching a content stream of at least one live event by a processing unit

[0102] . The content stream may be related to the at least one live event. In one implementation of the present disclosure, the content stream is fetched from one or more external utilities. The content stream refers to continuous real-time information of the live event. The one or more external utilities may be one of a live streaming utility, a news event utility, etc. In an exemplary implementation of the present invention, the beginning of at least one live event or a live event already in progress may be detected by the processing unit

[0102] to begin fetching the content stream. In one example, the content stream of the live event is received through an application programming interface (API) / feed / stream present on the system provided by one or more external utilities. In one exemplary embodiment of the invention, if the live event relates to a cricket match, the one or more external utilities may include an API that may include a detailed live score or commentary feed.

[0050] Further, in step

[0206] , the method comprises identifying at least one moment from the content stream by the processing unit

[0102] . The method further comprises analyzing the content stream of at least one live event by the processing unit

[0102] . In one implementation of the solution, a natural language processing model may be used to analyze the content stream. The natural language processing model may convert natural language in the content stream into machine-readable language. In one example, the analysis can be performed in real time using an intelligent model right from the start of the live event to the completion of the live event, where the intelligent model analyzes based on highlights of previous similar events that were prominent. The previous similar event highlights may be stored in the artificial intelligence (AI) model as training data based on which the system

[0100] identifies related events within the live event.

[0051] Based on the analysis, the method further comprises categorizing the content stream into one of at least one relevant event and at least one unrelated event. For example, the at least one relevant event refers to an important milestone in the content stream. For example, in the case of a live cricket event, the at least one relevant event in the analyzed content stream may include a player completing 50 / 100 runs, a wicket, a catch-out, a missed wicket, a review, a win, a loss, etc. The unrelated event refers to a portion of the content stream that does not contribute to generating real-time updates. For example, in a live natural disaster report, the at least one unrelated event in the content stream may include an advertisement, an interview with a nature expert, etc.

[0052] After categorizing the content stream into at least one related event and at least one unrelated stream, at least one moment may be identified from the at least related event. The method further includes calculating an importance score for the at least one related event. The importance score refers to the danger or importance of the event. In one example, the processing unit may consider the content stream as a related event based on the number of words spoken within a predetermined duration and the high tone of the speaker in the content. At least one moment may then be identified based on the importance score. For example, the related event with the highest importance score may be identified as the moment. Note that, as used herein, "moment" refers to a portion of a predetermined time interval of a live event. For example, in the previous example of a live cricket match, a moment may include a 10-second clip of a batsman hitting a six.

[0053] In a further exemplary implementation, the intelligent model may have stored one or more moments from a previous event of a live cricket match event. In one example, the one or more moments include, but are not limited to, fours and sixes scored, a player's individual milestone, a hat trick, a missed catch by a leading batsman, or a century. The intelligent model may use one or more moments from a previous live cricket match event to identify one or more moments in the live event. Another instance may include an event such as a national budget presentation, which may have moments such as major regulatory changes affecting several industries.

[0054] Next, in step

[0208] , the method comprises generating, by the processing unit

[0102] , at least one real-time update for the identified at least one moment. The at least one real-time update may include, but is not limited to, an image along with a summarized description of the moment. In one implementation of the present invention, a natural language processing AI model processes the at least one moment and generates one or more tags associated with the moment. As used herein, "one or more tags" refers to attributes associated with at least one moment. For example, in the example of a live cricket tournament event, the one or more tags may include player names, event name, score, team name, opposing team name, tournament name, etc. Furthermore, a text summary may be generated based on the one or more tags. As used herein, a text summary refers to a short text description of at least one moment.

[0055] The method further comprises identifying an image for at least one relevant event based on the generated text summary and one or more tags. In one example, the image may be selected from the storage unit

[0106] . In another example, the image may be generated using an intelligent model. The image may be pre-stored in the storage unit

[0106] by a system operator or may be stored from previously generated images. In one implementation of the present disclosure, the image may be identified based on at least one moment and a feeling of the live event. For example, if a moment in a live cricket match relates to a player scoring a run in the match, the selected image may include the player's name as a subject, along with the player wearing gear relevant to the match and in a celebratory pose. The method further comprises combining the generated text with the identified image to generate at least one real-time update.

[0056] Next, in step

[0210] , the method comprises displaying at least one real-time update on the display unit

[0104] . In one example, the display unit

[0104] may be a content management system (CMS), such as a television application, a mobile application, a desktop application, etc. Displaying may include, but is not limited to, sending emails, messages, or notifications to the user. Thus, the at least one real-time update is displayed to the user in real time. The method

[0200] ends in step

[0212] .

[0057] Furthermore, the present invention encompasses storing the generated real-time updates in the storage unit

[0106] . In one implementation of the present invention, one or more real-time updates may be stored along with a timestamp. The method further comprises detecting, by the processing unit

[0102] , a progress of the at least one live event over a predetermined time period. The progress of the at least one live event refers to the continuation of the live event over some time period. For example, the at least one live event started at 4:00 PM. The predetermined time period is 10 minutes, and by 4:10 PM, three real-time updates have been stored in the storage unit

[0106] .

[0058] The method further comprises selecting, by the processing unit

[0102] , one or more generated real-time updates from the generated real-time updates stored in the storage unit

[0106] . In one example, the processing unit

[0102] may select each of the generated real-time updates. In another example, the processing unit

[0102] may select one or more of the generated real-time updates based on a comparison of importance scores. In one implementation of the present disclosure, the generated real-time update having a high importance score may be selected by the processing unit

[0102] . The method further comprises combining, by the processing unit

[0102] , one or more real-time updates to form a timeline. As used herein, a timeline refers to a collection of past real-time updates of a live event. The timeline may help a user catch up on what important events have passed in the live event within a short amount of time through a collection of video portions. The timeline updates as the live event progresses, continuing to add more real-time updates as they are generated in real time. Further, the method comprises displaying the timeline to a user on a display unit

[0104] by the processing unit

[0102] .

[0059] Referring to FIG. 3, an exemplary method

[0300] for automatic generation of real-time updates for at least one real-time event according to an exemplary embodiment of the present disclosure is illustrated. In one implementation of the present disclosure, the method

[0300] is performed by the system

[0100] . In step

[0302] , one or more external utilities may send content streams of at least one live event to an analysis unit. In one example, the content streams may include, but are not limited to, statistics, audio, video, etc. In one implementation of the present disclosure, the one or more external utilities may be one of an application programming interface (API), a stream, a feed, etc. In one example, the streams include a live radio stream. In another example, the feeds include news data, audio, or video feeds. In step

[0304] , the content streams of the live event are analyzed by an analysis unit. In one implementation of the present solution, the analysis unit may be a natural language processing model or an artificial intelligence model. The analysis unit may convert natural language in the audio or video into system-readable language.

[0060] In step

[0306] , the content stream converted into machine-readable language is further analyzed to check whether the content stream qualifies as a relevant or irrelevant event. In one example, the analysis is based on the danger / importance of the event. In one example, the analysis unit may consider the content as a significant event based on the number of words spoken within a given duration or the high tone of the speaker in the content. In another example, the analysis may be performed in real time, from the start of the event to its completion, using intelligence derived from highlights of previous similar events that were prominent. Previous similar event highlights may be fed into an artificial intelligence (AI) system as training data based on which the system

[0100] identifies such moments in the live event. For example, in the case of a live cricket match event, there may be many prominent moments, such as fours and sixes scored, individual player milestones, hat tricks, missed catches by leading batsmen, or centuries. Another instance may include an event such as a national budget presentation, which may have moments such as major regulatory changes affecting several industries.

[0061] If the content stream does not qualify as a related event, the method

[0300] proceeds to step

[0308] . In step

[0308] , the system

[0100] may not take any action on the content. If the content qualifies as a related event, the method

[0300] proceeds to step

[0310] . In step

[0310] , one or more tags may be generated for the selected content. In one implementation, the one or more tags are attributes associated with the selected content. For example, in the previous example of a live cricket match, the one or more associated tags may include player names, event, score, team, opposing team, tournament name, etc. Furthermore, a text generation model may be used to generate one or more associated text descriptions. The one or more associated text descriptions may be based on an analysis of the selected content and the one or more tags. In one implementation of the present invention, the associated text description may include a textual summary or title of the selected content.

[0062] Next, in step 0312, a similarity algorithm may be applied. The similarity algorithm refers to comparing the generated text description with one or more previously generated text descriptions to select an image representing the generated text description. In step 0314, once the similarity algorithm is applied, an image representing the text description along with its accompanying sentiment is selected from the storage unit. In one implementation of the present disclosure, the storage unit may contain previously generated real-time images or images previously stored by a system operator. In another implementation of the present disclosure, if an image cannot be found in the repository of images, an image may be created using an image creation model. For example, if the moment relates to player X scoring 50 in a T20 match for country A, B, or C, the image would have player X as the subject along with an image of the player wearing the equipment relevant to the T20 match. Furthermore, player X is shown in a celebratory pose with the bat. The image may be selected from the repository of images or created using an image creation model.

[0063] Further, in step 0316, the image and the text description are combined using a transparent overlay of the text description on the image. The image and the text description are collectively referred to as a real-time update. In one embodiment of the present disclosure, the transparent overlay may be in one of the Portable Network Graphics (PNG) formats. In step 0318, the real-time update may be published on the computing device. In one embodiment of the present disclosure, the real-time update may be published along with metadata. Metadata refers to additional information related to the real-time update. The metadata may include, but is not limited to, a date, a description of the event, one or more tags for the event, and an image format. Further, in step 0320, the published real-time update may be stored in the backend of the system 0100. Storing the published real-time update allows for easy retrieval for further generation of real-time updates. Furthermore, the published real-time update may be easily updated in real time.

[0064] Referring to FIG. 4, an exemplary method

[0400] for backend publishing of one or more real-time updates for at least one real-time event is shown, according to an exemplary embodiment of the present invention. In one exemplary embodiment, the backend publishing of one or more real-time updates is for a live cricket final match. The cricket tournament final is scheduled for Thursday. Most of the people interested in the match are busy at the office, in classes, or at other events because it is a workday. Not everyone can afford to take time off, and it is an important and interesting match. Real-time updates of a live cricket match can solve this purpose because, with the help of their mobile application or a system installed on their laptop or desktop

[0100] , people can continue their work and check the real-time updates on their computing device in between. Furthermore, if people are in a meeting and cannot check the real-time updates in real time, they may look through a timeline of real-time updates to view highlights of the match in chronological order at a later time. An exemplary method

[0400] for fetching a content stream and publishing real-time updates is as follows:

[0065] The method

[0400] begins at step

[0402] , where an external utility begins saving a content stream of a live event. In an exemplary aspect of the present disclosure, the external utility may be a radio broadcast or a dedicated utility with real-time statistics of the live cricket match. In step

[0404] , an analysis unit receives a content stream of the live cricket match from the external utility. The content stream may include, but is not limited to, audio of commentators' comments and statistics of the live cricket match. In step

[0406] , the analysis unit may save the content stream in a real-time database. In step

[0408] , the content stream may be further published by the real-time database on a display. Next, in step

[0410] , an automatic moment generation unit may fetch relevant data from the published content stream. An intelligent model may be used to identify the relevant data. The intelligent model may be supplied with historical data of similar cricket match events to identify the relevant data. In step

[0412] , the relevant data goes to a production pipeline. The production pipeline refers to a unit for generating text summaries and images related to the fetched content stream.

[0066] In steps

[0414] and

[0416] , the production pipeline applies the intelligent model to generate a text summary for the fetched content stream. Furthermore, based on the generated text summary, a vector database may be accessed to identify images related to the text summary. The images may be stored in the vector database by a system operator or may be generated using the intelligent model. The production model receives the text summary and the images. The production model may combine the text summary and the images using a transparent overlay to generate at least one moment. Further, in step

[0418] , at least one moment may be published. In step

[0420] , the published moment may be received at the backend, and metadata related to the at least one moment may be received together with the generated moment. In step

[0422] , metadata related to the at least one moment may be published together with the generated moment. In step

[0424] , the generated moment, together with the metadata, may be stored in the real-time database and the cache. In step

[0426] and in step

[0428] , the moment may be notified and displayed to the user.

[0067] Referring to Figure 5, an exemplary implementation of an exemplary image having one or more real-time updates for an exemplary event according to an exemplary embodiment of the present invention is shown. In the context of Figure 5, an exemplary event such as a running football match is considered. As shown in Figure 5, real-time updates corresponding to the event, i.e., a running football match, are shown. It may be noted that the exemplary event and corresponding real-time updates as shown in Figure 5 are merely examples and do not limit the scope of the present subject matter. Any other event, such as a cricket match, a natural disaster, election count news, etc., may be considered, and any updates in light of the event may be considered. All such examples will be considered within the scope of the present subject matter.

[0068] As shown in FIG. 5, a player named "Matt Breida" runs left and covers an 8-yard touchdown to score for the New York Giants (NYG). The event may be referred to as a content stream. The processing unit

[0102] may fetch the content stream and identify the content stream as at least one moment. Based on the identification, a text summary may be titled "Matt Breida runs near left end for an 8-yard touchdown." The one or more tags may be the player's name "Matt Breida," the running direction, the team's score, etc. Based on the text summary and the one or more tags, an image of the player running with the football may be created or fetched from the storage unit

[0106] . The text summary and the image are combined and displayed on the display unit

[0104] with real-time updates, as shown in FIG. 5.

[0069] The present disclosure further discloses a non-transitory computer-readable storage medium storing instructions for automatically generating one or more real-time updates for at least one live event. The instructions include executable code that, when executed by one or more units of a system, causes a processing unit

[0102] of the system to fetch a content stream related to the at least one live event. The instructions, when executed by the system, further cause the processing unit

[0102] of the system to identify at least one moment from the content stream. The instructions, when executed by the system, further cause the processing unit

[0102] of the system to generate at least one real-time update for the at least one moment. The instructions, when executed by the system, further cause a display unit

[0104] to display the at least one real-time update.

[0070] Accordingly, the present invention discloses a method and system for generating real-time updates for live events. The present invention represents a significant technological advance in the field of providing real-time updates for time-bound events such as elections, sports, festivals, live movie screenings, natural disasters, epidemics, and the like. The present invention provides moments and timelines tailored from multiple moments for real-time updates related to key happenings of live events. A technical effect of the present invention lies in its seamless integration of multiple components to produce rich video and text segments that present key happenings to users at both an individual level (i.e., a single moment is generated) and an aggregated level (multiple moments are generated in a chronological manner via a timeline). By utilizing natural language processing and generative artificial intelligence techniques, the present invention provides users with visual and textual summaries of live event media. The present invention represents a significant technological advancement and enriches the experience of content consumers and viewers by updating them in real time (within a time interval as short as 4-5 seconds) with key happenings in live / ongoing events through moments. Furthermore, the technological advances in the timeline feature help viewers catch up on what has passed in a live event within a short amount of time through a collection of visual stories that outline the moments. Furthermore, as the live event progresses as more moments are added to the timeline in real time, and after the event is completed, the timeline feature updates itself, thus further enhancing the user experience. The present solution is a fully automated solution for event media visualization, thus completely eliminating the need for manual editors to pick and edit moments from live stream videos.

[0071] While the invention has been described with reference to certain preferred embodiments and examples thereof, other embodiments, equivalents, and modifications are possible and are encompassed by the scope of this disclosure. [Explanation of symbols]

[0072] 100 systems 102 Processing Unit 104 Display Unit 106 Memory Unit

Claims

1. 1. A method for automatically generating one or more real-time updates for at least one live event, comprising: - fetching, by a processing unit [102], a content stream related to said at least one live event; - identifying by said processing unit [102] at least one moment from said content stream; - generating by said processing unit [102] at least one real-time update to said at least one moment; - Display unit displaying said at least one real-time update by said processing unit [102] on [104]; A method comprising the steps of: [200]

2. The method of claim 1, wherein the content stream is fetched from one or more external utilities comprising at least one of live streaming events and news events.

3. identifying the at least one moment from the content stream, - categorizing by the processing unit [102] one or more input data of the content stream into one of at least one related event and at least one unrelated event; - calculating by said processing unit [102] an importance score of said at least one relevant event; - identifying, by the processing unit [102], the at least one moment from the at least related events based on the importance score; The method of claim 1 [200] further comprising:

4. generating at least one real-time update; - determining by the processing unit [102] one or more tags for said at least one moment; - generating a text summary for the at least one moment by the processing unit [102]; - identifying, by the processing unit [102], an image for the at least one moment based on the text summary and the one or more tags; - combining, by the processing unit [102], the text summary and the identified images to generate the at least one real-time update; The method of claim 1 [200] further comprising:

5. - determining by the processing unit [102] the progress of the content stream relative to the at least one live event; - dynamically merging, by the processing unit [102], the at least one real-time update into a timeline based on the progress; - displaying said timeline by said processing unit [102] on said display unit [104]; The method of claim 1 [200] further comprising:

6. 1. A system [100] for automatically generating one or more real-time updates for at least one live event, comprising: a processing unit [102] connected to a storage unit [106], fetching a content stream associated with the at least one live event; and - identifying at least one moment from the content stream; generating at least one real-time update for the at least one moment; a processing unit [102] configured to: a display unit [104] connected to said processing unit [102], said display unit [104] being configured to display said at least one real-time update; A system comprising: [100]

7. The system of claim 6, wherein the content stream is fetched from one or more external utilities comprising at least one of a live streaming utility and a news event utility.

8. The processing unit [102] - categorizing one or more input data of the content stream into one of at least one related event and at least one unrelated event; - calculating an importance score for said at least one relevant event; - identifying the at least one moment from the at least one related event based on the importance score; and The system of claim 6, further configured to:

9. The processing unit [102] - determining one or more tags for said at least one moment; - generating a text summary for the at least one moment; - identifying an image for the at least one moment based on the text summary and the one or more tags; - combining the text summary and the identified image to generate the at least one real-time update; The system of claim 6, further configured to:

10. The processing unit [102] - determining a progress of the content stream relative to the at least one live event; - dynamically merging the one or more real-time updates into a timeline based on the progress; and - displaying said timeline on said display unit [104]; The system of claim 6, further configured to:

Images