Ca, Inc.

Serge Mankovskii

Maria C Velez-Rojas

Steven Lloyd Greenspan

Jin Zhang

Nir Barak

James Donald Reno

Debra Jean Danielson

Prashant Parikh

Ye Chen

Esin Kiris

Michael C Roberts

Yaacov Bezalel

Steve Versteeg

Techniques are disclosed relating to training a neural network using private training data. In some embodiments, a central computing system is configured to maintain an at least partially trained neural network and information that specifies data formats for inputs to the model and outputs from the model. In some embodiments, partner computing systems maintain subsections of the neural network model and may train them using data that is not shared with other partner computing systems or the central computing system. Parameters resulting from the training may be transmitted to the central computing system. In some embodiments, the central computing system processes the parameters to generate the updated complete version of the neural network model and transmits parameters from the updated complete version of the model to the partner computing systems. The partner computing systems may use the updated complete model to detect anomalies in input data.

Distributed secure training of neural network model

A fork in a block chain data structure is identified, the block chain data structure including a first set of blocks each describing a respective transaction. The fork includes a first branch beginning with a first block and a second branch beginning with a different second block. The first branch includes a first set of blocks comprising at least the first block, and the second branch includes a second set of blocks including at least the second block. A determination is made, based on a consensus protocol, that the second branch is to be discarded. Accordingly, a meta block is generated to identify and describe the second branch. The meta block is to be included in a meta block chain data structure. The meta block chain data structure is separate from the block chain data structure and comprises meta blocks to record orphan branches of the block chain data structure.

Meta block chain

Provided is a process of conducting a collaborative session between two analytics graphical user interfaces (GUI), the process including: instructing a first computing device associated with a first user to display a first GUI having a first graph depicting a first set of values of a first metric; determining that the first graph is to be shared on a second computing device associated with a second user in a second GUI; inferring that the second user prefers to view the first metric in a second graph based on a record of previous interactions in which the second graph was selected to view the first metric; and in response, instructing the second computing device to display in the second GUI the second graph depicting at least some of the first set of values of the first metric.

Collaborative data analytics application

Systems and methods may include receiving data of a physical system. The systems and methods may include determining whether an anomalous event has occurred based on the data. The systems and methods may include, in response to determining that the anomalous event has occurred, capturing data of the physical system and of an environment. The systems and methods may include generating a virtual representation of the physical system and the environment based on the captured data. The systems and methods may include repeatedly simulating data of the virtual representation by varying parameters of the captured data. The systems and methods may include determining which parameters are a root cause of the anomalous event based on the simulated performance data. The systems and methods may include determining particular values of the parameters that are likely the root cause of the anomalous event to use as a trigger for a proactive process.

Self-learning simulation environments

A computing device is configured to parse a selected semi-structured or unstructured digital document. Once a document is selected, an appropriate parser is selected based on the content type of the document. The document is parsed and the data output to a metadata file. Additionally, any nested documents that are included in the selected document are also parsed using an appropriate parser with the being output to the metadata file. Once complete, the metadata file can be stored and analyzed by a user or administrator using tools that are used to model structured data files.

System and method for processing semi-structured data

Methods for managing access to protected resources within a computing environment and detecting anomalies related to access control events are described. An access control system may acquire a request for access to a protected resource, identify a username associated with the request, acquire contextual information associated with the request for access (e.g., a time of day associated with a location of a device making the request), acquire a baseline set of rules for the username, detect a deviation from the baseline set of rules based on the contextual information, acquire additional authentication information in response to detecting the deviation, authorize access to the protected resource based on the additional authentication information, generate a record of the request for access including the contextual information, and update the baseline set of rules if an intrusion to the access control system has not been detected within a threshold period of time.

Anomaly detection for access control events

Operational parameters of a running multiserver data processing system are automatically and repeatedly sampled and compared with constraints defined in a capacity and placement planning specification of the multiserver data processing system. Constraint violations are automatically declared as operational anomalies and, if serious enough, corresponding alarm signals are automatically produced.

Anomaly detection and alarming based on capacity and placement planning

According to an example computer-implemented method, shared media content is presented to a plurality of users during a collaborative session, with the session including a plurality of events. A breadcrumb trail of events occurring during the collaborative session is created. For each of the events, a descriptor is determined for the event, and the event is tagged in the breadcrumb trail with the descriptor. Responsive to receipt of a descriptor selection, a filtered breadcrumb trail including only events tagged with the selected descriptor is presented.

Method and apparatus for presenting a breadcrumb trail for a collaborative session

Monitoring circuitry monitors a computing device for configuration changes and performance changes. The monitoring circuitry also logs that data (CDD and PDD data) to a database. An analysis circuit analyzes the CDD and PDD data to determine whether an anomaly exists. If the analysis circuit determines that an anomaly exists, it generates an alarm to alert appropriate personnel to the anomaly.

Alarm notification based on detecting anomalies in big data

A system and method is provided for creating a trail of events. A plurality of data exchange events and a plurality of user interaction events are captured. A frame is generated based on the captured plurality of user interaction events. A cut is generated based on the captured plurality of data exchange events and the frame. The cut represents a historical trail of the plurality of user interaction events associated with the back-end data receive event and the back-end data send event.

Method and system for capturing expertise of a knowledge worker in an integrated breadcrumb trail of data transactions and user interactions

According to one embodiment, a method may include providing a representation of each of a plurality of nodes of an information technology (IT) environment to a plurality of administrators responsible for maintaining the IT environment. A plurality of scores for each of two or more of the plurality of nodes may be received. Each score may provide an assessment of a respective node of the plurality of nodes. One or more display characteristics may be determined for each node for which one or more scores was received. The display characteristics may comprise a size of a respective node that is based on the scores received for the respective node. The display characteristics may be provided to at least one administrator of the plurality of administrators responsible for maintaining the IT environment.

Growing community of inventors

San Ramon, CA, United States of America

Serge Mankovskii