US-12621540-B2 - Personalized real-time advertisement content generation

US12621540B2US 12621540 B2US12621540 B2US 12621540B2US-12621540-B2

Abstract

An embodiment predicts a most preferred product in a plurality of products, the predicting using a trained neural network, data of a user, and real-time availability data of the plurality of products, wherein the most preferred product is specific to the user. An embodiment generates, in real time, using a large language model, a script, the script comprising natural language text comprising a customized offer of the most preferred product to the user An embodiment generates, in real time, using the script and a generative adversarial network (GAN), a content customized to the most preferred product and the user, wherein the content comprises at least one of an audio portion and a video portion. An embodiment presents, on a device corresponding to the user, the content.

Inventors

Sarbajit K. Rakshit
Sathya Santhar
Sridevi Kannan

Assignees

INTERNATIONAL BUSINESS MACHINES CORPORATION

Dates

Publication Date: 20260505
Application Date: 20240202

Claims (20)

1 . A computer-implemented method comprising: predicting a most preferred product in a plurality of products, the predicting using a trained neural network, data of a user, and real-time availability data of the plurality of products, wherein the most preferred product is specific to the user, and wherein the data of the user comprises an activity being performed by the user at a time of the predicting, and the user's mode of travel; generating, in real time, using a large language model, a script, the script comprising natural language text comprising a customized offer of the most preferred product to the user; generating, in real time, using the script and a generative adversarial network (GAN), a content customized to the most preferred product and the user, wherein the content comprises at least one of an audio portion and a video portion; and presenting, on a device corresponding to the user, the content.
2 . The computer-implemented method of claim 1 , further comprising: predicting, using context data corresponding to the user, the most preferred product.
3 . The computer-implemented method of claim 1 , wherein an input to the GAN comprises scene data, wherein the scene data describes a scene that has a degree of similarity with a context of the script, and wherein predicting the most preferred product in the plurality of products comprises: computing, using the trained neural network, a probability distribution corresponding to the plurality of products, wherein the most preferred product is the highest probability product in the probability distribution.
4 . The computer-implemented method of claim 1 , wherein generating the script comprises: constructing a prompt to the large language model, the prompt comprising the most preferred product; and causing, using the prompt, the large language model to generate the script.
5 . The computer-implemented method of claim 1 , wherein the audio portion of the content comprises text of the script converted into audio form.
6 . The computer-implemented method of claim 1 , wherein the video portion of the content comprises video generated by the GAN.
7 . A computer program product comprising one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by a processor to cause the processor to perform operations comprising: predicting a most preferred product in a plurality of products, the predicting using a trained neural network, data of a user, and real-time availability data of the plurality of products, wherein the most preferred product is specific to the user, and wherein the data of the user comprises an activity being performed by the user at a time of the predicting, and the user's mode of travel; generating, in real time, using a large language model, a script, the script comprising natural language text comprising a customized offer of the most preferred product to the user; generating, in real time, using the script and a generative adversarial network (GAN), a content customized to the most preferred product and the user, wherein the content comprises at least one of an audio portion and a video portion; and presenting, on a device corresponding to the user, the content.
8 . The computer program product of claim 7 , wherein the stored program instructions are stored in a computer readable storage device in a data processing system, and wherein the stored program instructions are transferred over a network from a remote data processing system.
9 . The computer program product of claim 7 , wherein the stored program instructions are stored in a computer readable storage device in a server data processing system, and wherein the stored program instructions are downloaded in response to a request over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system, further comprising: program instructions to meter use of the program instructions associated with the request; and program instructions to generate an invoice based on the metered use.
10 . The computer program product of claim 7 , further comprising: predicting, using context data corresponding to the user, the most preferred product.
11 . The computer program product of claim 7 , wherein an input to the GAN comprises scene data, wherein the scene data describes a scene that has a degree of similarity with a context of the script, and wherein predicting the most preferred product in the plurality of products comprises: computing, using the trained neural network, a probability distribution corresponding to the plurality of products, wherein the most preferred product is the highest probability product in the probability distribution.
12 . The computer program product of claim 7 , wherein generating the script comprises: constructing a prompt to the large language model, the prompt comprising the most preferred product; and causing, using the prompt, the large language model to generate the script.
13 . The computer program product of claim 7 , wherein the audio portion of the content comprises text of the script converted into audio form.
14 . The computer program product of claim 7 , wherein the video portion of the content comprises video generated by the GAN.
15 . A computer system comprising a processor and one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by the processor to cause the processor to perform operations comprising: predicting a most preferred product in a plurality of products, the predicting using a trained neural network, data of a user, and real-time availability data of the plurality of products, wherein the most preferred product is specific to the user, and wherein the data of the user comprises an activity being performed by the user at a time of the predicting, and the user's mode of travel; generating, in real time, using a large language model, a script, the script comprising natural language text comprising a customized offer of the most preferred product to the user; generating, in real time, using the script and a generative adversarial network (GAN), a content customized to the most preferred product and the user, wherein the content comprises at least one of an audio portion and a video portion; and presenting, on a device corresponding to the user, the content.
16 . The computer system of claim 15 , further comprising: predicting, using context data corresponding to the user, the most preferred product.
17 . The computer system of claim 15 , wherein an input to the GAN comprises scene data, wherein the scene data describes a scene that has a degree of similarity with a context of the script, and wherein predicting the most preferred product in the plurality of products comprises: computing, using the trained neural network, a probability distribution corresponding to the plurality of products, wherein the most preferred product is the highest probability product in the probability distribution.
18 . The computer system of claim 15 , wherein generating the script comprises: constructing a prompt to the large language model, the prompt comprising the most preferred product; and causing, using the prompt, the large language model to generate the script.
19 . The computer system of claim 15 , wherein the audio portion of the content comprises text of the script converted into audio form.
20 . The computer system of claim 15 , wherein the video portion of the content comprises video generated by the GAN.

Description

BACKGROUND The present invention relates generally to advertisement content generation. More particularly, the present invention relates to a method, system, and computer program for personalized real-time advertisement content generation. As used herein, real-time content generation, or content generation performed in real-time, refers to content generation that is performed within a specified time period of an event triggering the content generation. The specified time period is generally on the order of one second or less. Thus, real-time content generation is unlike content that is generated and stored for later playback. As used herein, personalized content generation refers to generating content that is generated according to the inferred needs or desires of a particular user. Dynamic advertisements, or ads, unlike traditional static ads, are adjustable in content and presentation based on real-time data, contextual factors, and individual user attributes. By harnessing the power of advanced technology, dynamic ads provide a highly personalized and engaging experience to consumers, maximizing relevance and thus sales of a product being advertised. Unlike traditional static ads that display the same content to all viewers, dynamic ads are adaptable, using data points such as user behavior, location, browsing history, demographics, and environmental conditions to customize the ad content, so that an individual ad viewer sees an ad that resonates with the viewer's specific interests and needs. Dynamic ads are presented in various forms, ranging from simple text and still images to more complex multimedia presentations including video and interactive elements. A dynamic ad presentation system typically makes real-time decisions about which content to display, tailoring displayed content to an individual user. One of the key strengths of dynamic ads lies in their ability to maximize relevancy while minimizing ad fatigue. Instead of bombarding users with repetitive content, dynamic ads provide fresh and engaging experiences, enhancing user engagement and mitigating the risk of ad blindness. As a result, businesses use dynamic ads to achieve a multitude of objectives, such as retargeting, product recommendations, location-based promotions, and time-sensitive offers. Dynamic Creative Optimization (DCO) is an approach to advertising that tailors ad content in real-time to individual users, contexts, and preferences. By leveraging data-driven insights and advanced algorithms, DCO transforms static ad campaigns into dynamic and personalized experiences. DCO allows advertisers to dynamically adjust various ad elements, such as images, text, offers, and calls-to-action, to align with each viewer's unique characteristics. SUMMARY The illustrative embodiments provide for personalized real-time advertisement content generation. An embodiment includes predicting a most preferred product in a plurality of products, the predicting using a trained neural network, data of a user, and real-time availability data of the plurality of products, wherein the most preferred product is specific to the user. An embodiment includes generating, in real time, using a large language model, a script, the script comprising natural language text comprising a customized offer of the most preferred product to the user. An embodiment includes generating, in real time, using the script and a generative adversarial network (GAN), a content customized to the most preferred product and the user, wherein the content comprises at least one of an audio portion and a video portion. An embodiment includes presenting, on a device corresponding to the user, the content. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each configured to perform the actions of the embodiment. An embodiment includes a computer usable program product. The computer usable program product includes a computer-readable storage medium, and program instructions stored on the storage medium. An embodiment includes a computer system. The computer system includes a processor, a computer-readable memory, and a computer-readable storage medium, and program instructions stored on the storage medium for execution by the processor via the memory. BRIEF DESCRIPTION OF THE DRAWINGS The novel features believed characteristic of the invention are set forth in the appended claims. The invention itself, however, as well as a preferred mode of use, further objectives, and advantages thereof, will best be understood by reference to the following detailed description of the illustrative embodiments when read in conjunction with the accompanying drawings, wherein: FIG. 1 depicts a block diagram of a computing environment in accordance with an illustrative embodiment; FIG. 2 depicts a flowchart of an example process for loading of process software in accordance with an illustrative embodime