System for automated capture and analysis of business information for security and client-facing infrastructure reliability
A system for fully integrated collection of business impacting data, analysis of that data and generation of both analysis driven business decisions and analysis driven simulations of alternate candidate business actions has been devised and reduced to practice. This business operating system may be used to monitor and predictively warn of events that impact the security of business infrastructure and may also be employed to monitor client-facing services supported by both software and hardware to alert in case of reduction or failure and also predict deficiency, service reduction or failure based on current event data.
1. A system for fully integrated collection and analysis of empirical and simulated data and generation of analysis-driven simulations of alternate candidate decisions comprising:
a plurality of computing devices each comprising at least a processor, a memory, and a network interface;
wherein a plurality of programming instructions stored in one or more of the memories and operating on one or more of the processors of the plurality of computing devices causes the plurality of computing devices to:
based on a request for action recommendations from a user device, retrieve a plurality of data from a plurality of sources via one or more data networks;
receive a plurality of analysis parameters and control commands via the one or more data networks;
aggregate and store retrieved information for analysis;
perform a plurality of analyses and data transformations or simulations on the retrieved data based on the analysis parameters;
augment the results of data analyses and transformations or simulations with domain-specific machine learning based at least in part on the retrieved data and the received analysis parameters and control commands;
automatically generate and execute one or more viable action pathway simulations using the augmented results; and
present recommended actions to the user device.
2. The system of claim 1 , wherein the aggregated data is received from a plurality of sensors of heterogeneous types and is stored in a multidimensional time series data store.
3. The system of claim 1 , wherein a directed computational graph retrieves streams of input from one or more of the plurality of data sources, filters data to remove data records from the stream, splits filtered data streams into two or more identical parts, and sends the two or more identical parts for independent analysis and simulation.
4. The system of claim 1 , wherein a graph stack service organizes data retrieved from the multidimensional time series database into graph formats where the objects are represented as vertices and the relationships between them as edges of the graph.
5. A method for fully integrated collection and analysis of data and generation of analysis-driven simulations of alternate candidate decisions comprising the steps of:
based on a request for action recommendations from a user device, retrieving a plurality of data from a plurality of sources via one or more data networks;
receiving a plurality of analysis parameters and control commands via the one or more data networks;
aggregating and store retrieved information for analysis;
performing a plurality of analyses and data transformations on the retrieved data based on the analysis parameters;
augmenting the results of data analyses and transformations with domain-specific machine learning based at least in part on the retrieved data and the received analysis parameters and control commands;
automatically generating and executing one or more action pathway simulations using the augmented results; and
presenting recommended actions to the user device.
6. The method of claim 5 , wherein the aggregated data is received from a plurality of sensors of heterogeneous types and is stored in a multidimensional time series data store.
7. The method of claim 5 , wherein a directed computational graph retrieves streams of input from one or more of the plurality of data sources, filters data to remove data records from the stream, splits filtered data streams into two or more identical parts, and sends the two or more identical parts for independent analysis and simulation.
8. The method of claim 5 , wherein a graph stack service organizes data retrieved from the multidimensional time series database into graph formats where the objects are represented as vertices and the relationships between them as edges of the graph.
9. A computer-readable, non-transitory medium comprising a plurality of programming instructions that, when operating on a plurality of computing devices each comprising at least a processor, a memory, and a network interface, cause the plurality of computing devices to carry out the method of claim 5 .