Dell Products Inc.

Dhilip S Kumar

Hung The Dinh

Bijan Kumar Mohanty

Ajay Maikhuri

Sujit Kumar Sahoo

Shibi Panikkar

Rohit Gosain

Rajesh Krishnan

Ponnayan Sekar

Jaganathan Subramanian

Devaraj Marappa

Lokesh Dasam

Vidhyanshu Jain

Proma Mukherjee

Sarath Kumar Kalavala

Raja Sekhar Eega

Solleti Praveen Kumar

Astha Malhotra

Himesh Chopra

Sumanta Pandit

Smriti Mishra

Ashraf Afzal Syed

Seenivasan Manavalasamy

Souptik Banerjee

Sasikanta Sahoo

In one aspect, an example methodology implementing the disclosed techniques includes, by a computing device, receiving audio data corresponding to a spoken utterance by a first user and determining an accent of the audio data. The method also includes, by the computing device, neutralizing the accent of the audio data to a preconfigured accent and transmitting a modified audio data in the preconfigured accent to another computing device. The modified audio data includes the spoken utterance by the first user.

Accent personalization for speakers and listeners

Techniques are disclosed for domain-driven intent-based feedback data analysis. For example, a method comprises obtaining a feedback data set, and classifying the feedback data set into at least one domain of a plurality of domains. The feedback data set is mapped to a domain data set corresponding to the at least one domain, and a root cause is computed for the feedback data set to enable one or more actions to be taken in response to the feedback data set based on the root cause. By way of further example, computing the root cause for the feedback data set may further comprise utilizing at least one computed intent attribute, at least one computed sentiment attribute, and the domain data set to compute a decision on the root cause for the feedback data set.

Domain-driven feedback data analysis in information processing system

Techniques are disclosed for a multi-layer micro model analytics framework for analyzing or otherwise processing data. For example, a method comprises building two or more micro models respectively for two or more stages of a given process, wherein each micro model of the two or more micro models comprises a user interaction layer and a predictive learning layer that coordinate to train the micro model based on input to the user interaction layer and data accessible by the predictive learning layer for the corresponding stage of the two or more stages of the given process. The method then assembles the two or more micro models to perform analysis for the given process. In one non-limiting example, the given process is a new product introduction process and each micro model is built and trained to perform analytics for a specific lifecycle stage of the process.

Multi-layer micro model analytics framework in information processing system

Techniques are disclosed for enabling a multi-model and clustering database system. For example, a query from a client is received at a primary cluster in a clustering database system implemented over one or more processing platforms. The primary cluster analyzes the query to determine an intent of the query and, based on the intent of the query, to identify at least one secondary cluster from a plurality of secondary clusters in the clustering database system to execute the query. The primary cluster manages the plurality of secondary clusters, and one or more of the plurality of secondary clusters support a data model type that is different than a data model type of one or more others of the plurality of secondary clusters.

Multi-model and clustering database system

A method comprises analyzing a plurality of natural language inputs associated with at least one user, and determining a plurality of contexts for the plurality of natural language inputs based, at least in part, on the analysis. In the method, a plurality of relationships linked to the at least one user are identified based, at least in part, on the analysis, and the at least one user is classified in one or more categories based, at least in part, on the plurality of contexts and the plurality of relationships. At least one of the analyzing, determining, identifying and classifying is performed using one or more machine learning models.

Using machine learning for individual classification

Techniques for managing containerized workloads in a container computing environment are disclosed. For example, a method comprises the following steps. In a first mode, the method learns resources and execution times needed to process incoming workloads of a first workload type and a second workload type in a set of one or more clusters in a container-based computing environment. In a second mode, based on the learning of resources and execution times in the first mode, the method determines whether a subsequent incoming workload of the second workload type can be executed by one of the set of one or more clusters or whether an additional cluster should be created to process the subsequent incoming workload and then removed after processing the subsequent incoming workload is completed.

On-demand clusters in container computing environment

Methods, apparatus, and processor-readable storage media for data archival recommendation systems using artificial intelligence techniques are provided herein. An example computer-implemented method includes processing data associated with database operations performed across multiple database storage zones in one or more databases; generating, using one or more artificial intelligence techniques and based at least in part on the processing of data associated with the database operations performed across the multiple database storage zones, one or more temporal-based data archival recommendations for at least a portion of the multiple database storage zones in the one or more databases; and performing one or more automated actions based at least in part on the one or more temporal-based data archival recommendations.

Data archival recommendation systems using artificial intelligence techniques

Methods, apparatus, and processor-readable storage media for augmenting identifying metadata related to group communication session participants using artificial intelligence techniques are provided herein. An example computer-implemented method includes processing, using a first set of artificial intelligence techniques, image data associated with participants of a group communication session and/or video data associated with participants of the group communication session; processing, using a second set of artificial intelligence techniques, audio data associated with participants of the group communication session; identifying at least one of the participants of the group communication session based on the processing of the image data, the processing of the video data, and/or the processing of the audio data; augmenting, in connection with at least one interface associated with the group communication session, identifying metadata attributed to the at least one identified participant; and performing one or more automated actions based on the augmenting of the identifying metadata.

Augmenting identifying metadata related to group communication session participants using artificial intelligence techniques

A method comprises receiving a set of raw worker data records associated with one or more worker activities of a worker, each raw worker data record comprising one or more of an image, a video, information from a sensor, information from interaction with a tool, and information from interaction with a device. A first analysis, configured to analyze the set of raw worker data records for one or more indications regarding whether any worker activities include one or more undesired behaviors, is performed on the set of raw worker data records. Based on the first analysis, a second analysis, configured to categorize and document worker behavior as a function of time, is performed. Based on the second analysis, a third analysis, configured to analyze worker behavior for undesired conditions, is performed. Based on at least one of the second and third analysis, a summary of worker activity is generated.

Intuitive AI-powered worker productivity and safety

Techniques are disclosed for hyper-segmented personalization using machine learning-based models in an information processing system. For example, a method obtains one or more product experience recommendation data sets respectively from one or more product entities, and one or more purchase experience recommendation data sets respectively from one or more commerce entities. The method applies a federated ensemble-based machine learning algorithm to at least one of the one or more purchase experience recommendation data sets and at least one of the one or more product experience recommendation data sets to generate a personalized model, and causes adaptation of a purchasing interface of at least one of the one or more commerce entities with respect to a given user based on the personalized model.

Hyper-segmented personalization using machine learning-based models in an information processing system

Methods, apparatus, and processor-readable storage media for automatically prioritizing supply chain-related demand using artificial intelligence techniques are provided herein. An example computer-implemented method includes processing supply-chain related data using a first set of artificial intelligence techniques trained based at least in part on historical demand availability data; processing supply-chain related data using a second set of artificial intelligence techniques trained based at least in part on historical supply availability data; processing supply-chain related data using a third set of artificial intelligence techniques trained based at least in part on historical production availability data; prioritizing multiple orders within a supply chain environment by processing, using a fourth set of artificial intelligence techniques, results from the first set of artificial intelligence techniques, the second set of artificial intelligence techniques, and the third set of artificial intelligence techniques; and performing one or more automated actions based on the prioritization of the multiple orders.

Automatically prioritizing supply chain-related demand using artificial intelligence techniques

A method comprising: receiving, at a computing device, a first input specifying a first time window for a meeting and a first set of recipients who are invited to attend the meeting, the first set being a non-empty set; receiving, at the computing device, a second input specifying a plurality of segments within the meeting, for each of the plurality of segments, the second input specifying a respective second time window for the segment, and a respective second set of recipients who are invited to attend the segment, each second set of recipients being a subset of the first set, and each second time window being a time window that falls entirely within the first time window; and generating one or more invites based on the first and second input and transmitting the one or more invites to the recipients in the first set.

Meeting invite segmentation

A method comprises receiving a request to combine data from a plurality of data collections based on one or more constraints, and analyzing the request using one or more machine learning algorithms to determine an order by which respective ones of the plurality of data collections are to be searched. The respective ones of the plurality of data collections are searched according to the determined order, and an output of combined data from the searching is generated in response to the request.

Management of database join operations

Techniques are provided for managing an end-to-end software development life cycle. A software development lifecycle management system performs a plurality of stages of work for developing a software application, and records transactions which result from performing the plurality of stages of work, in an immutable digital ledger. The immutable digital ledger can be a blockchain ledger.

Trust and traceability for software development life cycle

In one aspect, an example methodology implementing the disclosed techniques includes, by a product subscription service, receiving information regarding a hardware asset being returned at an end of a subscription and predicting, using a first machine learning (ML) model, whether the hardware asset has reached EOL. The method also includes, responsive to predicting that the hardware asset has reached EOL, creating, by the product subscription service, a work order to dispatch an eco-partner. The method may further include, by the product subscription service, responsive to predicting that the hardware asset has not reached EOL, predicting, using a second ML model, one or more new subscription orders matching the hardware asset and recommending the one or more matching new subscription orders as possible fits for the hardware asset.

Growing community of inventors

Bengaluru, India

Dhilip S Kumar