US 10,380,105 B2Granted

QA based on context aware, real-time information from mobile devices

AssigneeInternational Business Machines Corporation

InventorsSeraphin Bernard Calo, Douglas M Freimuth, Raghu Kiran Ganti, James J. Fan, Fan Ye

Life of this patent

Estimating the term…

Loading patent…

Abstract

A common infrastructure collects data from a plurality of mobile devices and traditional sensors at Internet scale to respond to natural language queries received at different applications. The infrastructure includes a semantic interpreter to translate the natural language query to a data request specification that is processed by the data collection system. The data collection system includes a phenomenon layer that expresses data and information needs in a declarative fashion and coordinates data collection and processing for queries. An edge layer manages devices, receives collection requirements from the backend layer, configures and instructs devices for data collection, and conducts aggregation and primitive processing of data. This layer contains network edge nodes, such as base stations in a cellular network. Each node manages a set of local data generating networked devices. The device agent data layer using common agents on the networked devices receives data collection instructions and performs data collection.

Claims20

Dependent claims

A method for question answering, the method comprising:

generating a plurality of natural language queries at applications running on a plurality of computing systems, each natural language query describing at least one phenomenon comprising an event occurring in real time at a given physical location within a time window that extends over a given duration of real time;
communicating the plurality of natural language queries to common mobile edge capture and analytics middleware in communication with plurality of computing systems running the applications;
translating each natural language query into a data request specification, each data request specification comprising an identification of types of data to be obtained that are responsive to the natural language query and that indicate an occurrence of the at least one phenomenon;
using the mobile edge capture and analytics middleware to identify common data needs across the plurality of applications and to determine data collection requirements in the data capture system responsive to the data request specification, the data collection requirements comprising raw data to be collected by a data capture system comprising a plurality of data capture devices, each data capture device running an instance of a common software agent capable of real-time collection of different types of data and each instance of the common software agent receiving data collection requirements from the mobile edge capture and analytics middleware, the raw data comprising time data within the time window, physical location data and physical sensor data;
using physical sensors located in the data capture devices in the data capture system that are disposed in the given physical location during the time window to obtain the raw data in real time;
using the common software agents to communicate the obtained raw data to the mobile edge capture and analytics middleware;
using the obtained raw data by combining the time data, physical location data and physical sensor data in the mobile edge capture and analytics middleware to identify occurrences of phenomena indicated by the physical sensors;
using the mobile edge capture and analytics middleware to store the time data, physical location data, physical sensor data and identified phenomena for use in responding to data collection requirements from the plurality of applications;
and
communicating raw data and identified occurrences of phenomena to the plurality of applications.

7 more elements

A computer-readable storage medium containing a computer-readable code that when read by a computer causes the computer to perform a method for question answering, the method comprising:

generating a plurality of natural language queries at applications running on a plurality of computing systems, each natural language query describing at least one phenomenon comprising an event occurring in real time at a given physical location within a time window that extends over a given duration of real time;
communicating the plurality of natural language queries to common mobile edge capture and analytics middleware in communication with plurality of computing systems running the applications;
translating each natural language query into a data request specification, each data request specification comprising an identification of types of data to be obtained that are responsive to the natural language query and that indicate an occurrence of the at least one phenomenon;
using the mobile edge capture and analytics middleware to identify common data needs across the plurality of applications and to determine data collection requirements in the data capture system responsive to the data request specification, the data collection requirements comprising raw data to be collected by a data capture system comprising a plurality of data capture devices, each data capture device running an instance of a common software agent capable of real-time collection of different types of data and each instance of the common software agent receiving data collection requirements from the mobile edge capture and analytics middleware, the raw data comprising time data within the time window, physical location data and physical sensor data;
using physical sensors located in the data capture devices in the data capture system that are disposed in the given physical location during the time window to obtain the raw data in real time;
using the common software agents to communicate the obtained raw data to the mobile edge capture and analytics middleware;
using the obtained raw data by combining the time data, physical location data and physical sensor data in the mobile edge capture and analytics middleware to identify occurrences of phenomena indicated by the physical sensors;
using the mobile edge capture and analytics middleware to store the time data, physical location data, physical sensor data and identified phenomena for use in responding to data collection requirements from the plurality of applications;
and
communicating raw data and identified occurrences of phenomena to the plurality of applications.

7 more elements

Dependencies are inferred from the claim text.