International Business Machines Corporation

Sudhanshu Sekher Sar

Sudheesh S Kairali

Satyam Jakkula

Sarbajit Kumar Rakshit

Anbumunee Ponniah

Nagesha Rao Krishnan

Soumya Prasada

Balakrishnan Rajenderan

Brunda Panthula

Layana Abraham

Maureen Kraft

A method, computer program product, and computer system for optimizing locations of micro-warehouses that minimize an aggregate carbon footprint within a geographical region. A first trained artificial intelligence model is used to extract, for a geographical region, a product demand of users located in the geographical region over a fixed time period, and delivery location clusters within the geographical region. The delivery location clusters output by the first trained artificial intelligence model is input into a regression model, the regression model outputting recommended locations of temporary micro-warehouses within the geographical region. A second trained artificial intelligence model is used to modify the recommended locations and output optimized locations based on reducing an aggregate carbon footprint caused by emissions resulting from transportation to and from the temporary micro-warehouses.

Minimizing aggregate carbon footprint within geographical region

Mechanisms are provided for controlling docking of an edge capacity with a cloud computing system. A bill of materials (BOM) enabled agent, executing on the edge capacity, sends a BOM data structure specifying components of a configuration of the edge capacity. A lookup operation of components of the BOM data structure is performed in a BOM controls mapping data structure to identify controls or policies applicable to the components of the BOM data structure. The identified controls/policies are transmitted to the BOM enabled agent for execution to determine if there are any violations. Results of the identified controls or policies are received which specify whether there are any violations of the controls/policies. In response to at least one violation being detected, docking of the edge capacity with the cloud computing system is denied. In response to no violations, the edge capacity docks with the cloud computing system.

Dynamic SBOM based secure docking of edge capacity to existing computing systems

A method, computer program product, and computer system are provided for smart log shipping in a heterogeneous computing environment. A first edge device and a second edge device in a heterogeneous cloud computing environment are identified. The first edge device is caused to transmit collected log data associated with the first edge device to the second edge device based on a lack of network connectivity between the first edge device and a cloud data center. The transmitted collected log data is received from the second edge device.

Smart log shipping in a heterogenous cloud computing environment

A computer-implemented method according to one embodiment includes establishing a handshake between a security and compliance center (SCC) and a first operator of a first cluster via a manager component therebetween. An operand mapping of the SCC is updated, and the established handshake is used to cause the update to be communicated to the first operator of the first cluster. A computer program product according to another embodiment includes a computer readable storage medium having program instructions embodied therewith. The program instructions are readable and/or executable by a computer to cause the computer to perform the foregoing method. A system according to another embodiment includes a processor, and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor. The logic is configured to perform the foregoing method.

Using a handshake to communicate between a security and compliance center (SCC) and at least a first operator

Provided are a computer program product, system, and method for generating expanded content in a video stream based on predicting viewer behavior. A determination is made of promoted content rendered in the video. In response to determining the promoted content, invoking at least one machine learning model to perform determining whether a viewer of the video is interested in the promoted content and generating expanded content for a duration in response to determining that the viewer of the video is interested in the promoted content. The rendering of the video is paused and the expanded content is rendered for the duration while pausing the rendering of the video. The rendering of the video is continued in response to completing the rendering of the expanded content.

Generating expanded content in a video stream based on predicting viewer behavior

A method and system provide computer system security for a focus computer system (FCS). The method comprises creating a security digital twin (SDT) for the FCS with an associated security ontology for the FCS. A potential threat analyzer receives a potential threat object (PTO), and maps it to an enterprise attack vector pattern. The method further comprises searching, on another computer system (OCS) for a predicted attack pattern having a similar pattern to the enterprise attack vector pattern. Conditioned upon finding the predicted attack pattern, and using a potential threat handler locating an action mitigation plan (AMP) related to the predicted attack pattern in the data fabric associated with the OCS, the method further comprises copying the OCS predicted attack pattern to an FCS predicted attack pattern store, copying the OCS AMP to an FCS AMP store, and defending the FCS from the PTO using the AMP.

Fast forwarded security issue identification using digital twins

A machine learning system for dynamically segmenting inventory includes a memory having instructions therein, and at least one processor configured to execute the instructions to, using a reinforcement learning agent ('RLA'): determine, based at least in part on first inventory data corresponding to at least a portion of a first prediction time window for the RLA, a second prediction time window for the RLA; segment a first supply of inventory, based at least in part on the second prediction time window and at least a portion of the first inventory data; determine, based at least in part on second inventory data corresponding to at least a portion of the second prediction time window, a third prediction time window for the RLA; and segment a second supply of inventory, based at least in part on the third prediction time window and at least a portion of the second inventory data.

Dynamic inventory segmentation with predicted prediction time window

Embodiments of the present invention disclose a method, computer program product, and system for catalog digitization. A method including receiving observed information including physical attributes of a plurality of products, assigning an importance to each physical attribute, organizing the products into product categories based on the physical attributes and their corresponding importance, determining a product profile for of the products based on the product category of each of the products and a likelihood of any two attributes being observed together with respect to each of the products, identifying a match between two products based on a similarity between the physical attributes of the two products and their corresponding importance, and a comparison between the product profiles of the two products, preparing a product description based on a combination of the physical attributes of the two matching products, and creating a digital product catalog comprising the product description.

Growing community of inventors

Bengaluru, India

Sudhanshu Sekher Sar