Abstract: There are provided systems and methods for a compute platform for machine leaning model roll-out. A service provider, such as an electronic transaction processor for digital transactions, may provide intelligent decision-making through decision services that execute machine learning models. When deploying or updating machine learning models in these engines and decision services, a model package may include multiple models, each of which may have an execution graph required for model execution. When models are tested from proper execution, the models may have non-performant compute items, such as model variables, that lead to improper execution and/or decision-making. A model deployer may determine and flag these compute items as non-performant and may cause these compute items to be skipped or excluded from execution. Further, the model deployer may utilize a pre-production computing environment to generate the execution graphs for the models prior to deployment or upgrading.

Abstract: Methods, systems, and computer programs are presented for the generation of content in advance to enable quickly customized communications for multiple types of customers. One method includes an operation for identifying components of an image design that specifies how the components are combined to generate an image. For one or more of the identified components, variations of the components are generated using one of several generative artificial intelligence (GAI) models. The method further includes detecting a request, comprising user attributes, for the image. For one or more of the identified components, a respective variation is selected based on the user attributes, and a response image is created utilizing the image design and the one or more selected variations. Further, the response image is presented on a computer user interface.

Abstract: Techniques are disclosed for time constrained electronic request evaluation. A server system receives, from a computing device, a request submitted via an account, including a first set of characteristics associated with the request. The system executes a first machine-learning model to determine a first risk score for the request by inputting the first set of characteristics into the first model. The system generates an initial authentication decision for the request based on the first score and sends the decision to the device. The system executes a second, different machine-learning model to determine a second risk score for the request, by inputting the first set of characteristics and a second, different set of characteristics associated with the account into the second model. Based on the second score, the system determines a final authentication decision. The disclosed techniques may advantageously improve computer security and operations via identification of malicious electronic requests.

Abstract: Systems, methods, and computer program products are directed to machine learning techniques that use a separate embedding layer. This can allow for continuous monitoring of a processing system based on events that are continuously generated. Various events may have corresponding feature data associated with at least one action relating to a processing system. Embedding vectors that correspond to the features are retrieved from an embedding layer that is hosted on a separate physical device or a separate computer system from a computer that hosts the machine learning system. The embedding vectors are processed though the machine learning model, which may then make a determination (e.g. whether or not a particular user action should be allowed). Generic embedding vectors additionally enable the use of a single remote embedding layer for multiple different machine learning models, such as event driven data models.

Abstract: An edge computing system is deployed at a physical location and receives an input from one or more image/video sensing mechanisms. The edge computing system executes artificial intelligence image/video processing modules on the received image/video streams and generates metrics by performing spatial analysis on the images/video stream. The metrics are provided to a multi-tenant service computing system where additional artificial intelligence (AI) modules are executed on the metrics to execute perception analytics. Client applications can then be run on the output of the AI modules in the multi-tenant service computing system.

Abstract: Methods, systems, and computer programs are presented for generating multimodal content utilizing multimodal templates. One method includes presenting, in a user interface (UI), a template-selection option with one or more templates. Each template comprises a sequence of operations, where each operation comprises a prompt for creating items using generative artificial intelligence (GAI) tools. Further, each operation in the template is multimodal to be configurable to create text and configurable to create one or more images. The method further includes detecting a selection of a template in the UI. For each operation in the selected template, perform operations comprising: presenting, in the UI, the prompt associated with the operation; in response to receiving an input for the prompt, selecting a GAI tool based on a mode of the operation; providing the input to the selected GAI tool to generate the item; and presenting, in the UI, the generated item.

Abstract: Methods, systems, and computer programs are presented for generating multimodal content utilizing multimodal templates. One method includes presenting, in a user interface (UI), a template-selection option with one or more templates. Each template comprises a sequence of operations, where each operation comprises a prompt for creating items using generative artificial intelligence (GAI) tools. Further, each operation in the template is multimodal to be configurable to create text and configurable to create one or more images. The method further includes detecting a selection of a template in the UI. For each operation in the selected template, perform operations comprising: presenting, in the UI, the prompt associated with the operation; in response to receiving an input for the prompt, selecting a GAI tool based on a mode of the operation; providing the input to the selected GAI tool to generate the item; and presenting, in the UI, the generated item.

Abstract: Systems, methods, and computer program products are directed to machine learning techniques that use a separate embedding layer. This can allow for continuous monitoring of a processing system based on events that are continuously generated. Various events may have corresponding feature data associated with at least one action relating to a processing system. Embedding vectors that correspond to the features are retrieved from an embedding layer that is hosted on a separate physical device or a separate computer system from a computer that hosts the machine learning system. The embedding vectors are processed though the machine learning model, which may then make a determination (e.g. whether or not a particular user action should be allowed). Generic embedding vectors additionally enable the use of a single remote embedding layer for multiple different machine learning models, such as event driven data models.

Abstract: There are provided systems and methods for a compute platform for machine leaning model roll-out. A service provider, such as an electronic transaction processor for digital transactions, may provide intelligent decision-making through decision services that execute machine learning models. When deploying or updating machine learning models in these engines and decision services, a model package may include multiple models, each of which may have an execution graph required for model execution. When models are tested from proper execution, the models may have non-performant compute items, such as model variables, that lead to improper execution and/or decision-making. A model deployer may determine and flag these compute items as non-performant and may cause these compute items to be skipped or excluded from execution. Further, the model deployer may utilize a pre-production computing environment to generate the execution graphs for the models prior to deployment or upgrading.

Abstract: Methods, systems, and computer programs are presented for providing an interactive canvas tool to generate multimodal, personalized content. One method includes providing a user interface (UI) for a canvas tool to generate multimodal content. The canvas tool comprises a prompt panel, a variations panel, and a canvas configured to present items of several types, such as a text type and an image type. The method further includes receiving text input including a textual description with instruction for generating an item, where the canvas tool is configured to generate items from the several types. The method further includes providing the text input to a generative artificial intelligence (GAI) tool, and presenting one or more variations based on an output of the GAI tool. The method further includes detecting a selection of one of the variations in the variations panel, and adding the selected variation to the canvas in the UI.

Abstract: Methods, systems, and computer programs are presented for enhancing a machine-generated product image. One method includes an operation for receiving a request on a user interface (UI) to generate an image, where the request comprises a description of the image to be generated and identification of a product for inclusion in the image. The method further includes operations for generating, by a generative artificial intelligence (GAI) model, a first image based on the request, analyzing the first image to identify a presentation of the product in the first image, and selecting a product image from a database of product images based on the identification of the product. The method further includes replacing the presentation of the product in the first image with the selected product image to obtain a second image, and causing presentation in the UI of the second image.

Abstract: There are provided systems and methods for a compute platform for machine leaning model roll-out. A service provider, such as an electronic transaction processor for digital transactions, may provide intelligent decision-making through decision services that execute machine learning models. When deploying or updating machine learning models in these engines and decision services, a model package may include multiple models, each of which may have an execution graph required for model execution. When models are tested from proper execution, the models may have non-performant compute items, such as model variables, that lead to improper execution and/or decision-making. A model deployer may determine and flag these compute items as non-performant and may cause these compute items to be skipped or excluded from execution. Further, the model deployer may utilize a pre-production computing environment to generate the execution graphs for the models prior to deployment or upgrading.

Abstract: Methods, systems, and computer programs are presented for providing a prompt tool with interactive entry. One method includes operations for providing a multimodal prompt tool for entering textual description of an item to be generated, and detecting an input that is one of a special character entered in the textual description or a mouse action requesting assistance. Furthermore, a menu is presented with options for the item to be generated, and a list of products, previously added to a data store, is obtained. Further, the method includes providing the list of products for selection; in response to a selection of a product from the list of products, including text associated with the selected product in the textual description; and detecting submittal of the textual description. Further, the textual description is entered as input to a generative artificial intelligence (GAI) tool, and causing presentation of items generated by the GAI tool.

Abstract: This application discusses identifying data processing timeouts in live risk analysis systems. A service provider, such as an electronic transaction processor, may provide a production computing environment that includes a risk analysis system having one or more risk models, which may be machine-learning based. These risk models may be utilized in order to determine whether incoming data processing requests are fraudulent. To test these risk models using production data traffic, an audit computing environment made of a set of machines that do not service production computing environment requests, but that utilize databases and data connections as are used by the production systems. The audit computing environment may thus mirror the risk models and functionality of the production computing environment without the drawbacks of a typical fully separate testing environment.

Abstract: An edge computing system is deployed at a physical location and receives an input from one or more image/video sensing mechanisms. The edge computing system executes artificial intelligence image/video processing modules on the received image/video streams and generates metrics by performing spatial analysis on the images/video stream. The metrics are provided to a multi-tenant service computing system where additional artificial intelligence (AI) modules are executed on the metrics to execute perception analytics. Client applications can then be run on the output of the AI modules in the multi-tenant service computing system.

Abstract: There are provided systems and methods for a compute platform for machine leaning model roll-out. A service provider, such as an electronic transaction processor for digital transactions, may provide intelligent decision-making through decision services that execute machine learning models. When deploying or updating machine learning models in these engines and decision services, a model package may include multiple models, each of which may have an execution graph required for model execution. When models are tested from proper execution, the models may have non-performant compute items, such as model variables, that lead to improper execution and/or decision-making. A model deployer may determine and flag these compute items as non-performant and may cause these compute items to be skipped or excluded from execution. Further, the model deployer may utilize a pre-production computing environment to generate the execution graphs for the models prior to deployment or upgrading.

Abstract: An edge computing system is deployed at a physical location and receives an input from one or more image/video sensing mechanisms. The edge computing system executes artificial intelligence image/video processing modules on the received image/video streams and generates metrics by performing spatial analysis on the images/video stream. The metrics are provided to a multi-tenant service computing system where additional artificial intelligence (AI) modules are executed on the metrics to execute perception analytics. Client applications can then be run on the output of the AI modules in the multi-tenant service computing system.

Abstract: Techniques are disclosed for time constrained electronic request evaluation. A server system receives, from a computing device, a request submitted via an account, including a first set of characteristics associated with the request. The system executes a first machine-learning model to determine a first risk score for the request by inputting the first set of characteristics into the first model. The system generates an initial authentication decision for the request based on the first score and sends the decision to the device. The system executes a second, different machine-learning model to determine a second risk score for the request, by inputting the first set of characteristics and a second, different set of characteristics associated with the account into the second model. Based on the second score, the system determines a final authentication decision. The disclosed techniques may advantageously improve computer security and operations via identification of malicious electronic requests.

Abstract: Systems, methods, and computer program products are directed to machine learning techniques that use a separate embedding layer. This can allow for continuous monitoring of a processing system based on events that are continuously generated. Various events may have corresponding feature data associated with at least one action relating to a processing system. Embedding vectors that correspond to the features are retrieved from an embedding layer that is hosted on a separate physical device or a separate computer system from a computer that hosts the machine learning system. The embedding vectors are processed though the machine learning model, which may then make a determination (e.g. whether or not a particular user action should be allowed). Generic embedding vectors additionally enable the use of a single remote embedding layer for multiple different machine learning models, such as event driven data models.

Abstract: An edge computing system is deployed at a physical location and receives an input from one or more image/video sensing mechanisms. The edge computing system executes artificial intelligence image/video processing modules on the received image/video streams and generates metrics by performing spatial analysis on the images/video stream. The metrics are provided to a multi-tenant service computing system where additional artificial intelligence (AI) modules are executed on the metrics to execute perception analytics. Client applications can then be run on the output of the AI modules in the multi-tenant service computing system.