Description:TECHNICAL FIELD
[001] The present disclosure relates to the field of an advertisement generation system. In particular, the present disclosure provides a system and a method for generating and transmitting personalized advertisements to a user device in real-time.

BACKGROUND
[002] Currently, online advertisers collect data based on user search patterns and display advertisements that match characteristics of search criteria. These advertisements are not tied to events happening around the user due to challenges in tracking the events happening around user's geographical location.
[003] The inability to tailor advertisements based on the events occurring around users presents several drawbacks in field of targeted marketing. This limitation hinders potential for the advertisers to capitalize on real-time opportunities and trends. By not aligning advertisements with current events, promotions may miss a chance to resonate with users who are actively engaged or interested in specific happenings. Secondly, a lack of event-based advertisement generation diminishes contextual relevance of advertisements. Users are more likely to engage with content that reflects their immediate surroundings, interests, or ongoing events. Failure to integrate contextual information results in advertisements appearing disjointed or irrelevant, leading to decreased user engagement and effectiveness.
[004] Furthermore, an absence of event-driven advertisement customization limits the adaptability of advertising strategies. In dynamic and rapidly changing environments, advertisers are constrained in their ability to promptly adjust campaigns based on unfolding events, making it challenging to maintain relevance and responsiveness in the ever-evolving digital landscape. Overall, the drawback of not generating advertisements based on events around users underscores the missed opportunities for timely, contextually relevant, and adaptive advertising, potentially impacting the overall effectiveness of marketing efforts.
[005] Many techniques have been evolved to obviate the above-mentioned issues, for instance, certain prior arts describe a system and a method for automatically transforming pre-existing advertising creatives, originally adapted for the first content service environment, into advertising creatives suitable for the second content service environment. The transformed advertising creatives are suitable for initiating a new advertising campaign. The system transforms advertising creatives from search advertisements and display advertisements into creatives for a stream advertising campaign. Stream advertisements are subsequently placed into a stream of content displayed on a user device.
[006] Few other prior arts describe a system and a method for providing information about an advertisement campaign to an advertiser. The system includes means for organizing advertisement campaign information into one or more ad groups and a web interface to receive advertiser inputs and provide system alerts about the advertisement campaign information to the advertiser. The system further includes a campaign data store configured to store advertisement campaign account data and an alerting system to produce system alerts about the performance of the advertisement campaign.
[007] Yet another prior art describes a system and a method for dynamically generating an advertisement in a video stream. The video stream content associated with a user device is received. Video analytics data, indicating a recognized scene in the video stream content, is obtained. An advertisement to be generated and inserted into the video stream content is then selected based on the recognized scene. An advertisement template for generating the selected advertisement is obtained. Video advertisement content corresponding to the advertisement is generated based on the advertisement template and the video analytics data. The video advertisement content is then inserted into the video stream content, and the modified video stream content is transmitted to the user device.
[008] The conventional methods and systems cited above suffer from the drawback of employing more complex computation methods for generating advertisements. Additionally, these conventional methods and systems do not generate advertisements with respect to the user’s location and the events occurring in proximity to the user.
[009] Therefore, there is a need to address the drawbacks mentioned above and any other shortcomings, or at the very least, provide a valuable alternative to the existing methods and systems.

OBJECTS OF THE PRESENT DISCLOSURE
[010] A general object of the present disclosure is to provide an efficient and a reliable system and method that obviates the above-mentioned limitations of existing systems and methods in an efficient manner.
[011] An object of the present disclosure is to provide a system and a method that transmits personalized advertisements to users by considering events happening around the users are more likely to be relevant to the user’s immediate needs and interests.
[012] Another object of the present disclosure is to provide a system and a method for automatically generating personalized advertisements for users using an Artificial Intelligence (AI) engine without needs of a human intervention.
[013] Yet another object of the present disclosure is to provide a system and a method for transmitting personalized advertisements in real-time to a user device.

SUMMARY
[014] Aspects of the present disclosure relate to the field of an advertisement generation system. In particular, the present disclosure provides a system and a method for generating and transmitting personalized advertisements to a user device in real-time.
[015] An aspect of the present disclosure relates to a method for generating personalized advertisements. The method includes fetching, by one or more processors from a database associated with a system, information corresponding to one or more events at one or more geographical locations and one or more user parameters of a plurality of users located in the one or more geographical locations. Further, the method includes extracting, by the one or more processors, one or more relevant events and clustering the plurality of users located in the one or more geographical locations corresponding to the one or more user parameters based on the fetched information. Further, the method includes shortlisting, by the one or more processors, the one or more relevant events corresponding to each of the plurality of clustered users based on the extraction and correlating, by the one or more processors, one or more user data of each user associated with said each of the plurality of clustered users and the shortlisted one or more relevant events. Further, the method includes automatically generating, by the one or more processors via an Artificial Intelligence (AI) module, the personalized advertisements for said each user based on the correlation and transmitting, by the one or more processors, the personalized advertisements in real-time to a user device associated with said each user.
[016] In an embodiment, for fetching, by the one or more processors, the information corresponding to the one or more events at the one or more geographical locations and the one or more user parameters of the plurality of users located in the one or more geographical locations, the method may include tracking, by the one or more processors, a plurality of media sources to determine the information corresponding to the one or more events at the one or more geographical locations and the one or more user parameters of the plurality of users and storing, by the one or more processors, the information corresponding to the one or more events and the one or more user parameters in the database.
[017] In an embodiment, for extracting, by the one or more processors, the one or more relevant events based on the fetched information, the method may include detecting, by the one or more processors, one or more keywords of each event from the fetched information and determining, by the one or more processors, that a score value of the one or more keywords exceeds a predefined threshold based on the detection. Further, the method may include segregating, by the one or more processors, the one or more relevant events based on the determination.
[018] In an embodiment, for shortlisting, by the one or more processors, the one or more relevant events corresponding to said each of the plurality of clustered users, the method may include determining, by the one or more processors, that a first similarity level between the one or more relevant events and said each of the plurality of clustered users is greater than a first threshold value and correlating, by the one or more processors, the one or more relevant events at the one or more geographical locations and said each of the plurality of clustered users located in the one or more geographical locations based on the determination.
[019] In an embodiment, the method may include tracking, by the one or more processors, activities of said each user at a plurality of media sources and storing, by the one or more processors, the one or more user data in the database.
[020] In an embodiment, for automatically generating, by the one or more processors via the AI module, the personalized advertisements for said each user based on the correlation, the method may include determining, by the one or more processors, that a second similarity level between the shortlisted one or more relevant events and the one or more user data of said each user is greater than a second threshold value and selecting, by the one or more processors, the one or more user data of said each user corresponding to the shortlisted one or more relevant events based on the determination. Further, the method may include automatically generating, by the one or more processors, the personalized advertisements based on the selection.
[021] In an embodiment, the one or more user parameters of the plurality of users may include at least one of: location, profession, demographics, transactions, gender, affluence level, Transaction per Customer (TPC), and age.
[022] In an embodiment, the one or more user data of said each of the plurality of clustered users may include at least one of: orders, search histories, browsing patterns, and questionnaires.
[023] Another aspect of the present disclosure relates to a system for generating personalized advertisements. The system includes one or more processors and a memory operatively coupled with the one or more processors, where the memory includes one or more instructions which, when executed, cause the one or more processors to fetch information corresponding to one or more events at one or more geographical locations and one or more user parameters of a plurality of users located in the one or more geographical locations from a database associated with the system. The one or more processors are to extract one or more relevant events and clustering the plurality of users located in the one or more geographical locations corresponding to the one or more user parameters based on the fetched information. Further, the one or more processors are to shortlist the one or more relevant events corresponding to each of the plurality of clustered users based on the extraction and correlate one or more user data of each user associated with said each of the plurality of clustered users and the shortlisted one or more relevant events. Further, the one or more processors are to automatically generate the personalized advertisements via an Artificial Intelligence (AI) module for said each user based on the correlation and transmit the personalized advertisements in real-time to a user device associated with said each user.
[024] In an embodiment, the one or more processors may determine that a similarity level between the shortlisted one or more relevant events and the one or more user data of said each user is greater than a threshold value and select the one or more user data of said each user corresponding to the shortlisted one or more relevant events based on the determination. Further, the one or more processors may automatically generate the personalized advertisements based on the selection.
[025] Various objects, features, aspects, and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent components.
BRIEF DESCRIPTION OF THE DRAWINGS
[026] The accompanying drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[027] FIG. 1 illustrates a flow chart of an example method for generating personalized advertisements in real-time based on event information, in accordance with an embodiment of the present disclosure.
[028] FIG. 2 illustrates a block diagram of an example system for generating the personalized advertisements in real-time, in accordance with an embodiment of the present disclosure.
[029] FIG. 3 illustrates a flow chart of an example method for transmitting the personalized advertisements to a user device, in accordance with an embodiment of the present disclosure.
[030] FIG. 4 illustrates an exemplary computer system in which or with which embodiments of the present disclosure may be implemented.

DETAILED DESCRIPTION
[031] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosures as defined by the appended claims.
[032] Embodiments explained herein relate to an advertisement generation system. In particular, the present disclosure relates to a system and a method for generating and transmitting personalized advertisements to a user device in real-time. Various embodiments with respect to the present disclosure will be explained in detail with reference to FIGs. 1-4
[033] FIG. 1 illustrates a flow chart of an example method 100 for generating personalized advertisements in real-time based on event information, in accordance with an embodiment of the present disclosure.
[034] Referring to FIG. 1, at block 102, the method 100 may include tracking internet to index and collect information from search engines 102A and microblogs 102B to determine trending events happening in certain geographical locations using web crawlers. For example, the web crawlers may collect crowd-sourced information corresponding to the trending events that are taking place around the certain geographical locations. Real-time absorption of information from the crowd-sourced information is essential, as not every event elicits sufficient engagement to prompt individuals to take further actions, such as making purchases on an e-commerce website. To address these challenges in assessing the impact of events, the web crawlers gather data from micro-blogging platforms and analyse trending search patterns in search engines localized in different geographical locations. Conducting these data-crawling exercises on a regular basis allows online platforms to collect information about events that are gaining attention in specific localities.
[035] In certain scenarios, the event may be, but not limited to, meetings, competitions, rallies, social activities, sports activities, business activities, cultural activities, education-based activities, community activities, entertainment activities, political activities, charity activities, technology-based activities, bomb blast activities, murder activities, robbery activities, and the like. In some embodiments, these events may be either pre-planned (e.g., a scheduled meeting) or unplanned (e.g., a scientific discovery after years of research). The events may conclude either with unforeseen outcomes (e.g., a team’s victory in a game) or a forecasted result (e.g., rolling out of a scheme by a political party) or may be postponed to another day (e.g., postponing the marriage). The events may either be natural (e.g., a bright rainbow after rain) or may be man-made (e.g., the completion of a building).
[036] Once the web crawlers track the trending events around the particular location, at block 104, the method 100 may include filtering positive events and negative events separately using a sentiment analysis filter. For example, the negative events may be, but not limited to, bomb blasts, murder, and the like. These negative events may be ignored by the sentiment analysis filter based on keywords such as, bomb blast, murder, theft, robbery, natural calamities, and the like, which represent negative activities happening at the certain geographical locations because it is not ethical for any reputable online platform to promote its business based on the negative sentiments of users. Once the sentiment analysis filter filters the negative events, a list of positive events may be finalized. For example, the positive events may be, but not limited to, social activities, sports activities, business activities, cultural activities, education-based activities, community activities, entertainment activities, political activities, charity activities, technology-based activities, and the like.
[037] At block 106, the method 100 may include maintaining user parameters in a database. For example, the user parameters may include, but not limited to, location information of a user, profession of the user, demography of the user, transaction details of the user, gender, affluence level, Transaction per Customer (TPC), age, and the like. At block 108, the method 100 may include parallelising a smaller cluster of users based on the user parameters. For example, by creating small clusters of users based on various categories such as affluence level within the platform (low, mid, high) reflecting users’ purchasing behaviour, gender, TPC, age groups, and profession. Simultaneously, events identified through sentiment analysis are also narrowed down to a specific set of users in localized geographical areas.
[038] At block 110, the method 100 may include parallelising may be performed based on the locality of positive events and the semantic similarity of these events with the user parameters. This includes computing semantic similarity between events clustered in geographical locations and the user parameters in small clusters. Filtering out combinations of the user parameters and the events exceeding a specified threshold for semantic similarity helps refine the information presented, recognizing that not every user is interested in all the events around them. Factors such as personal interest, geographical location, collaborative behaviour, faith, and educational background further contribute to an individual’s inclination to stay informed about these events.
[039] At block 112, the method 100 may include parallelly running semantic similarity of products with shortlisted events and determining a similarity level between the products and the shortlisted events for selecting the products that are corresponding to the shortlisted events based on the similarity level. For example, generating the semantic similarity matrix between the top-most relevant products with the events that were short-listed in the previous step for each user in a parallelised manner and selecting the largest value in this matrix and noting down its corresponding event and product for each user.
[040] At block 114, the method 100 may include maintaining user data in the database, where the user data may include, but not limited to, previous order histories, search histories, browsing patterns, questionnaires sent by the online platform, and the like. At block 116, the method 100 may include parallelizing for each user with top-most relevant products. At block 118, the method 100 may include generating advertisement featuring images and text that may be broadcasted to customers, either through phone notifications or as a banner on a homepage of the platform using a generative Artificial Intelligence (AI) module. For example, for generating the advertisement, the method 100 may include constructing a prompt containing information about the event, product, user data, and any applicable discounts and requesting a text-generating AI module to produce a short catchy title. Using the generated catchy title as one input, along with the other previous inputs of the event, product, user data, and discount (if any), the image-generating AI module may generate the personalized advertisement, where the personalized advertisement may be transmitted to a user device associated with each user. When the user clicks on the advertisement, the user may be taken to a page containing a targeted product.
[041] FIG. 2 illustrates a block diagram 200 of an example system 202 for generating personalized advertisements in real-time, in accordance with an embodiment of the present disclosure.
[042] Referring to FIG. 2, the system 202 may include one or more processors 204, a memory 206, and an interface(s) 208. The one or more processors 204 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuitries, and/or any devices that manipulate data based on operational instructions. Among other capabilities, the one or more processor(s) 204 may be configured to fetch and execute computer-readable instructions stored in the memory 206 of the system 202. The memory 206 may store one or more computer-readable instructions or routines, which may be fetched and executed to create or share the data units over a network service. The memory 206 may include any non-transitory storage device including, for example, volatile memory such as Random-Access Memory (RAM), or non-volatile memory such as Erasable Programmable Read-Only Memory (EPROM), flash memory, and the like.
[043] The interface(s) 208 may comprise a variety of interfaces, for example, a variety of interfaces, for example, interfaces for data input and output devices, referred to as I/O devices, storage devices, and the like. The interface(s) 208 may facilitate communication of the system 202 with various devices coupled to it. The interface(s) 208 may also provide a communication pathway for one or more components of the system 202. Examples of such components include but are not limited to, processing engine(s) 210 and a database 212. The database 212 may include data that is either stored or generated as a result of functionalities implemented by any of the components of the processing engine(s) 210.
[044] In an embodiment, the processing engine(s) 210 may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing engine(s) 210. In examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processing engine(s) 210 may be processor executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the one or more processor(s) 204 may comprise a processing resource (for example, one or more processors), to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the processing engine(s) 210. In such examples, the system 202 may comprise the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separate but accessible to the system 202 and the processing resource. In other examples, the processing engine(s) 210 may be implemented by an electronic circuitry. The processing engine(s) 210 may include an extraction module 214, a clustering module 216, an event shortlisting module 218, a correlation module 220, a generation module 222, an AI module 224, and other module(s) 226. The other module(s) 226 may implement functionalities that supplement applications/functions performed by the processing engine(s) 210.
[045] In an online platform, targeted advertising plays an important role. The advertisements may be localized to individuals based on their geographical location, demographic behaviour, personal insights, local trends, the region’s current affairs, and the like. These advertisements may be personalized at a granular level, and the content needs to be generated dynamically to stay relevant over time and capture the user’s attention at an individual level. This transformation of advertisements into business opportunities for advertisers is facilitated by their ability to resonate with users on a personalized level.
[046] The system 202 may track media sources to determine the information corresponding to the events at geographical locations, user parameters of users, and activities of the user at the media sources for storing the information corresponding to the events and the user parameters along with user data in the database 212. The system 202 may fetch information corresponding to events at geographical locations and user parameters of users located in the geographical locations. In some embodiments, the user parameters may include, but not limited to, location, profession, demographics, transactions, gender, affluence level, TPC, age, and the like. The extraction module 214 may detect keywords of events from the fetched information and determine whether a score value of the keywords exceeds a predefined threshold or not. For example, if the keywords represent negative incidents such as bomb blast, robbery, murder, and the like, the extraction module 214 may determine that the score value of the keywords exceeds the predefined threshold. Similarly, if the keywords represent positive incidents such as cricketer scored century, student scored state first mark, politician introduces a good scheme, and the like, the extraction module 214 may determine that the score value of the keywords is less than the predefined threshold. When the score value exceeds the predefined threshold, the extraction module 214 may segregate relevant events (or positive events) and irrelevant events (or negative events). The extraction module 214 may extract only the relevant events by excluding the irrelevant events. The clustering module 216 may cluster the users located in the geographical locations corresponding to the user parameters based on the fetched information.
[047] Once the extraction module 214 extracts the relevant events and the clustering module 216 clusters the users located in the geographical locations, the event shortlisting module 218 may determine whether a first similarity level between the relevant events and the clustered users is greater than a first threshold value. The event shortlisting module 218 may correlate the relevant events at the geographical locations and the clustered users located in the geographical locations for shortlisting the relevant events corresponding to the clustered users. Once the relevant events corresponding to the clustered users are shortlisted, the correlation module 220 may correlate the user data and the shortlisted relevant events. In some embodiments, the user data may include, but not limited to, previous order histories, search histories, browsing patterns, questionnaires sent by the online platform, and the like.
[048] Based on the correlation of the user data and the shortlisted relevant events, the generation module 222 may determine whether a second similarity level between the shortlisted relevant events and the user data is greater than a second threshold value or not. When the second similarity level between the shortlisted relevant events and the user data is greater than the second threshold value, the generation module 222 may select the user data corresponding to the shortlisted relevant events to automatically generate the personalized advertisements for the users using the AI module 224. Once the personalized advertisements are generated, the system 202 may transmit the personalized advertisements to a user device associated with the users. The personalized advertisements may be a combination of image and text, and there is a necessity for the image and text to be coherent with each other.
[049] In certain scenarios, consider two individuals, named X and Y, where X resides in city A and Y resides in city B, respectively. X and Y are fans of their local sports team such as team A and team B, belonging to the franchise of a league, where X is a fan of team A and Y is a fan of team B. Additionally, in the past, both X and Y have browsed the online platform for information about sports persons A1 belonging to team A and B1 belonging to team B, respectively, who belong to their favourite teams. Suppose a match begins between team A and team B at 8 PM and the sports person A1 is performing well and is trending in local media. Simultaneously, the online platform, such as an e-commerce website, may send a personalized advertisement to user X. This advertisement may include an image of sports person A1 with a caption highlighting their innings, aiming to promote merchandise and enhance the platform’s sales. Similarly, user Y may be targeted with a personalized advertisement in real-time, either when sports person B1 is performing well or whenever their team is experiencing heightened sentiments as the match progresses. By utilizing the user data, the online platform has automatically personalized user X’s favourite sports personality as the sports person A1. The platform has also autonomously mapped products, specifically merchandise, related to the sports person A1 that align with the ongoing event (sports, in this example). By leveraging positive trends occurring either in the user’s locality or in other areas of their keen interest, the online platform may strategically tap into the user’s cognitive behaviour to convert the latest and real-time generated trends into business opportunities.
[050] FIG. 3 illustrates a flow chart of an example method 300 for generating personalized advertisements to a user device, in accordance with an embodiment of the present disclosure.
[051] Referring to FIG. 3, at block 302, the method 300 may include fetching information corresponding to one or more events at one or more geographical locations and one or more user parameters of a plurality of users located in the one or more geographical locations. Further, the method 300 may include tracking a plurality of media sources to determine the information corresponding to the one or more events at the one or more geographical locations and the one or more user parameters of the plurality of users and storing the information corresponding to the one or more events and the one or more user parameters in the database.
[052] At block 304, the method 300 may include extracting one or more relevant events and clustering the plurality of users located in the one or more geographical locations corresponding to the one or more user parameters based on the fetched information. Further, the method 300 may include detecting one or more keywords of each event from the fetched information and determining that a score value of the one or more keywords exceeds a predefined threshold for segregating the one or more relevant events.
[053] At block 306, the method 300 may include shortlisting the one or more relevant events corresponding to each of the plurality of clustered users based on the extraction. Further, the method 300 may include determining that a first similarity level between the one or more relevant events and said each of the plurality of clustered users is greater than a first threshold value and correlating the one or more relevant events at the one or more geographical locations and said each of the plurality of clustered users located in the one or more geographical locations based on the determination.
[054] At block 308, the method 300 may include correlating one or more user data of each user associated with said each of the plurality of clustered users and the shortlisted one or more relevant events. Further, the method 300 may include tracking activities of said each user at a plurality of media sources and storing, by the one or more processors, the one or more user data in the database.
[055] At block 310, the method 300 may include automatically generating via an Artificial Intelligence (AI) module, the personalized advertisements for said each user based on the correlation. Further, the method 300 may include determining that a second similarity level between the shortlisted one or more relevant events and the one or more user data of said each user is greater than a second threshold value and selecting the one or more user data of said each user corresponding to the shortlisted one or more relevant events based on the determination.
[056] At block 312, the method 300 may include transmitting the personalized advertisements in real-time to a user device associated with said each user.
[057] FIG. 4 illustrates an exemplary computer system in which or with which embodiments of the present disclosure may be implemented.
[058] As shown in FIG. 4, the computer system 400 may include an external storage device 410, a bus 420, a main memory 430, a read only memory 440, a mass storage device 450, a communication port 460, and a processor 470. A person skilled in the art will appreciate that the computer system 400 may include more than one processor and communication ports. The processor 470 may include various modules associated with embodiments of the present disclosure.
[059] In an embodiment, the communication port 460 may be any of an RS-232 port for use with a modem-based dialup connection, a 10/100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fiber, a serial port, a parallel port, or other existing or future ports. The communication port 460 may be chosen depending on a network, such a Local Area Network (LAN), Wide Area Network (WAN), or any network to which the computer system 400 connects.
[060] In an embodiment, the memory 430 may be a Random-Access Memory (RAM), or any other dynamic storage device commonly known in the art. The read-only memory 440 may be any static storage device(s) e.g., but not limited to, a Programmable Read Only Memory (PROM) chips for storing static information e.g., start-up or Basic Input/Output system (BIOS) instructions for the processor 470.
[061] In an embodiment, the mass storage device 450 may be any current or future mass storage solution, which can be used to store information and/or instructions. Exemplary mass storage solutions include, but are not limited to, Parallel Advanced Technology Attachment (PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives or solid-state drives (internal or external, e.g., having Universal Serial Bus (USB) and/or Firewire interfaces), one or more optical discs, Redundant Array of Independent Disks (RAID) storage, e.g., an array of disks (e.g., SATA arrays).
[062] In an embodiment, the bus 420 communicatively couples the processor(s) 470 with the other memory, storage, and communication blocks. The bus 420 may be, e.g., a Peripheral Component Interconnect (PCI)/PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), USB or the like, for connecting expansion cards, drives, and other subsystems as well as other buses, such a front side bus (FSB), which connects the processor 470 to computer system 400.
[063] Optionally, operator and administrative interfaces, e.g., a display, keyboard, joystick, and a cursor control device, may also be coupled to the bus 420 to support direct operator interaction with the computer system 400. Other operator and administrative interfaces may be provided through network connections connected through the communication port 460. Components described above are meant only to exemplify various possibilities. In no way should the aforementioned exemplary computer system 400 limit the scope of the present disclosure.
[064] While the foregoing describes various embodiments of the disclosure, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the disclosure is determined by the claims that follow. The disclosure is not limited to the described embodiments, versions, or examples, which are included to enable a person having ordinary skill in the art to make and use the disclosure when combined with information and knowledge available to the person having ordinary skill in the art.
ADVANTAGES OF THE PRESENT DISCLOSURE
[065] The present disclosure provides a system and a method for generating visual and textual advertisements at run-time in an automated manner which are more likely to be relevant to users
[066] The present disclosure provides an advertisement that is personalized and caters to taste of users for fostering a stronger connection between the users and an online platform.
[067] The present disclosure provides a system and a method for transmitting personalized advertisement related to events that are happening around users which leads to reach a right advertisement to a right audience at a right time.
, Claims:1. A method (300) for generating personalized advertisements, comprising:
fetching (302), by one or more processors (204) from a database (212) associated with a system (202), information corresponding to one or more events at one or more geographical locations, and one or more user parameters of a plurality of users located in the one or more geographical locations;
extracting (304), by the one or more processors (204), one or more relevant events, and clustering the plurality of users located in the one or more geographical locations corresponding to the one or more user parameters based on the fetched information;
shortlisting (306), by the one or more processors (204), the one or more relevant events corresponding to each of the plurality of clustered users based on the extraction;
correlating (308), by the one or more processors (204), one or more user data of each user associated with said each of the plurality of clustered users and the shortlisted one or more relevant events;
automatically generating (310), by the one or more processors (204) via an Artificial Intelligence (AI) module, the personalized advertisements for said each user based on the correlation; and
transmitting (312), by the one or more processors (204), the personalized advertisements in real-time to a user device associated with said each user.
2. The method (300) as claimed in claim 1, wherein fetching (302), by the one or more processors (204), the information corresponding to the one or more events at the one or more geographical locations and the one or more user parameters of the plurality of users located in the one or more geographical locations comprises:
tracking, by the one or more processors (204), a plurality of media sources to determine the information corresponding to the one or more events at the one or more geographical locations and the one or more user parameters of the plurality of users; and
storing, by the one or more processors (204), the information corresponding to the one or more events and the one or more user parameters in the database (212).
3. The method (300) as claimed in claim 1, wherein extracting (304), by the one or more processors (204), the one or more relevant events based on the fetched information comprises:
detecting, by the one or more processors (204), one or more keywords of each event from the fetched information;
determining, by the one or more processors (204), that a score value of the one or more keywords exceeds a predefined threshold based on the detection; and
segregating, by the one or more processors (204), the one or more relevant events based on the determination.
4. The method (300) as claimed in claim 1, wherein shortlisting (306), by the one or more processors (204), the one or more relevant events corresponding to said each of the plurality of clustered users comprises:
determining, by the one or more processors (204), that a first similarity level between the one or more relevant events and said each of the plurality of clustered users is greater than a first threshold value; and
correlating, by the one or more processors (204), the one or more relevant events at the one or more geographical locations and said each of the plurality of clustered users located in the one or more geographical locations based on the determination.
5. The method (300) as claimed in claim 1, comprising:
tracking, by the one or more processors (204), activities of said each user at a plurality of media sources; and
storing, by the one or more processors (204), the one or more user data in the database (212).
6. The method (300) as claimed in claim 1, wherein automatically generating (310), by the one or more processors (204) via the AI module, the personalized advertisements for said each user based on the correlation comprises:
determining, by the one or more processors (204), that a second similarity level between the shortlisted one or more relevant events and the one or more user data of said each user is greater than a second threshold value;
selecting, by the one or more processors (204), the one or more user data of said each user corresponding to the shortlisted one or more relevant events based on the determination; and
automatically generating, by the one or more processors (204), the personalized advertisements based on the selection.
7. The method (300) as claimed in claim 1, wherein the one or more user parameters of the plurality of users comprise at least one of: location, profession, demographics, transactions, gender, affluence level, Transaction per Customer (TPC), and age.
8. The method (300) as claimed in claim 1, wherein the one or more user data of said each of the plurality of clustered users comprises at least one of: orders, search histories, browsing patterns, and questionnaires.
9. A system (202) for generating personalized advertisements, comprising:
one or more processors (204); and
a memory (206) operatively coupled with the one or more processors (204), wherein the memory (206) comprises one or more instructions which, when executed, cause the one or more processors (204) to:
fetch information corresponding to one or more events at one or more geographical locations, and one or more user parameters of a plurality of users located in the one or more geographical locations from a database (212) associated with the system (202);
extract one or more relevant events, and clustering the plurality of users located in the one or more geographical locations corresponding to the one or more user parameters based on the fetched information;
shortlist the one or more relevant events corresponding to each of the plurality of clustered users based on the extraction;
correlate one or more user data of each user associated with said each of the plurality of clustered users and the shortlisted one or more relevant events;
automatically generate the personalized advertisements via an Artificial Intelligence (AI) module for said each user based on the correlation; and
transmit the personalized advertisements in real-time to a user device associated with said each user.
10. The system (202) as claimed in claim 9, wherein the one or more processors (204) are to:
determine that a similarity level between the shortlisted one or more relevant events and the one or more user data of said each user is greater than a threshold value;
select the one or more user data of said each user corresponding to the shortlisted one or more relevant events based on the determination; and
automatically generate the personalized advertisements based on the selection.