Ebay, Incorporated

Applied Materials, Inc.

Paypal, Inc.

Abhinav Kumar

Bhaven Avalani

Benjamin Schwarz

Charles Hardy

Ronald Francis Murphy

James Everett Lloyd

Michael Eynon

Faye Dai Hall

Sastry K Malladi

Weian Deng

Premendra Singh

Ravinder Purumala

Tarpan Dixit

Arun Raj Mony

Ping Zhao

Arun Rai Mony

A method includes determining a plurality of features of a first original image of a first product that are expected to be different for one or more products to be produced via manufacturing parameters of a manufacturing process compared to the first product. The method further includes adjusting one or more of the plurality of features of the first original image to generate a first synthetic image. The method further includes providing a plurality of images including the first original image and the first synthetic image to train a machine learning model to generate a trained machine learning model configured to generate output associated with updating the manufacturing parameters of the manufacturing process.

Adaptive non-rigid targeted deformation of images for synthetic image generation

Methods, systems, and non-transitory computer readable medium are described for automated image measurement for process development and optimization. An example method may include receiving an image of a product associated with a manufacturing process, wherein the product comprises a plurality of structures; identifying, using a trained machine learning model, a segment of the image that comprises a structure of the plurality of structures; determining a plurality of image measurements of the segment that comprises the structure; and storing the plurality of image measurements.

Self-measurement of semiconductor image using deep learning

A method includes providing attributes of a manufacturing process and an image of a product associated with the manufacturing process to a trained machine learning model. The method further includes obtaining, from the trained machine learning model, predictive data. The method further includes determining, based on the predictive data, image measurements of the image of the product associated with the manufacturing process. Manufacturing parameters of the manufacturing process are to be updated based on the image measurements.

Automated image measurement for process development and optimization

Methods, systems, and non-transitory computer readable medium are described for automated image measurement for process development and optimization. A method includes receiving an image of a product associated with a manufacturing process; determining, using a trained machine learning model, an image classification for the image; selecting, based on the image classification, one or more image processing algorithms for the image; pre-processing the image based on at least one of the one or more image processing algorithms to generate an enhanced image; measuring, using a first image processing algorithm of the one or more image processing algorithms, one or more attributes of the enhanced image to determine image measurements; and reporting the image measurements. The manufacturing parameters of the manufacturing process are to be updated based on the image measurements.

Methods, systems, and non-transitory computer readable medium are described for automated image measurement for process development and optimization. A method includes receiving original images including a first original image. Each original image is of a corresponding product associated with a manufacturing process. The method further includes performing, based on process information about the manufacturing process, feature extraction to identify features of the first original image that are expected to change based on manufacturing parameters of the manufacturing process. The method further includes generating a first synthetic image of synthetic images by performing targeted deformation of one or more of the features of the first original image. The method further includes using the original images and the synthetic images to train a machine learning model to automatically determine an image processing algorithm to use for measuring one or more attributes of images of product associated with the manufacturing process.

In various embodiments, a system, method, and a computer-readable medium for performing operations for tracking numerous software calls in an enterprise environment is provided. The method includes tracking, during a runtime operation of an enterprise environment, layers through which software calls pass. The tracking includes logging physical components involved in each of the software calls, annotating each of the physical components with metadata that is directly indicative of each of the physical components, and logging a reliance of each of the physical components on others of the physical components. Other systems and methods are disclosed.

Flow tracing of software calls

In various embodiments, a system and related method for organizing transactional data from an application environment is disclosed. In some embodiments, a system includes a file system and one or more daemon indexers in electrical communication with the file system. The file system is arranged as a non-relational and serverless file system to allow for cost-effectiveness with ready scalability. The file system is to receive, in substantially real-time, unsorted transactional data from a publishing module. The one or more daemon indexers are arranged to receive the unsorted transactional data from the file system, organize the unsorted transactional data by operational characteristics, and store the organized transactional data on the file system. Other systems and methods are disclosed.

Monitoring an application environment

In various exemplary embodiments, a system and a related method and a related computer-readable medium to perform the method, for tracking numerous software calls in an enterprise environment is provided. The method includes tracking, during a runtime operation of the enterprise environment, layers through which each of the software calls passes. The tracking includes logging each of a multitude of physical components involved in each of the software calls, annotating each of the physical components with associated metadata, logging each of a multitude of logical components involved in the software calls, annotating each of the logical components with associated metadata, and logging a reliance of each of the physical components and the logical components on other physical and logical components. A dependency map is generated indicating the layers tracked in each of the software calls.

Flow tracing though diverse logical and physical application and infrastructure layers/dependencies

A computer-implemented system and method for the definition, creation, management, transmission, and monitoring of errors in a SOA environment. An example embodiment includes: defining a common standard error data structure; automatically generating a unique identifier (ID) for each new error data instance; allowing customization of error data structure through extensions; creation and management of error instances that conform to this structure; ability to group errors across various dimensions; introducing the concept of an error library, the error library including a plurality of localizable error bundles, each of the error bundles including a plurality of error data instances for a particular domain, along with the associated metadata; automatically creating runtime artifacts for each error; ability to transmit errors either as faults or as part of the normal response payload; automatic error metric collection based on various error categories, and finally, tooling to help manage error libraries and reporting errors.

System and method for definition, creation, management, transmission, and monitoring of errors in SOA environment

Methods and systems to automatically respond to consider the weight of a request when responding to requests associated with resources are described. In one embodiment, an interface module may be configured to receive a request associated with consumer identifier and a resource. A calculator module may be configured to determine a weight of the request and a usage module configured to calculate, using a processor, a usage level associated with the consumer identifier, the usage level based on a usage history associated with the consumer identifier. An enforcer module may also be configured to respond to the request based on the usage level and the weight of the request. In one embodiment, the usage module may also be configured to update the usage level associated with the consumer identifier based on the weight of the request.

Weighted request rate limiting for resources

In various embodiments, a system and related method for organizing transactional data from a diverse and heterogeneous application environment is disclosed. In an example embodiment, a system includes a file system and one or more daemon indexers in electrical communication with the file system. The file system is arranged as a non-relational and serverless file system to allow for cost-effectiveness with ready scalability. The file system is to receive, in substantially real-time, unsorted transactional data from a publishing module. The one or more daemon indexers are arranged to receive the unsorted transactional data from the file system, organize the unsorted transactional data by operational characteristics, and store the organized transactional data on the file system.

Method and system to monitor a diverse heterogeneous application environment

A method to detect potential problems within a heterogeneous and diverse application environment. Operations data is received from a plurality of application servers within the application environment. The operations data pertains to operations performed at the plurality of application servers over a predetermined time interval. The operations data is aggregated. The aggregated data is compared to reference data, and a potential problem within the application environment is detected if the aggregated data deviates from the reference data in a predetermined manner.

Growing community of inventors

San Jose, CA, United States of America

Abhinav Kumar