Content recognition and communication system

Patent metadata

Field	Value
Publication number	US-2018246486-A1
Application number	US-201715445340-A
Country	US
Kind code	A1
Filing date	Feb 28, 2017
Priority date	Feb 28, 2017
Publication date	Aug 30, 2018
Grant date	—

Abstract

System and methods for processing information acquired from distributed sources are provided. The system may receive activity data samples from a plurality of collectors in a plurality of different independent locations in an organization. The system may identify baseline metrics associated with the activity data samples. The system may perform machine-based recognition of the activity data samples and associate the activity data samples with weight factors. The system may weigh the baseline metrics with the weight factors to generate adjusted metrics. The system may communicate activity information based on a logical combination of the activity data samples, context information recognized in the activity data samples, and metrics related to the activity information. Devices or networks connected with the system may receive and/or query a state of the organization including the activity data samples, context information recognized in the activity data samples, and/or metrics related to the activity information.

First claim

What is claimed is:

1 . A system comprising:
data acquisition controller circuitry to receive, from a plurality of collectors in a plurality of different independent locations in an organization, activity data samples comprising at least one of audio data, image data, machine data, or sensor data; activity type classifier circuitry to search a memory configured to store previously classified activity data samples associated with baseline activity scores and identify a baseline activity score for the activity data samples based on a comparison between the activity data samples and the previously classified activity data samples, the activity type classification circuitry further configured to link, in the memory, the baseline activity score with the activity data samples; content recognition circuitry configured to recognize activity context information in the activity data samples, the content recognition circuitry further configured to search the memory, the memory further configured to store an association between previously classified activity context information and predefined weight factors, the content recognition circuity further configured to identify a weight factor based on a comparison between the activity context information and the previously classified activity context information; activity scoring circuitry configured to weight the baseline activity score with the weight factor to generate an adjusted activity score corresponding to the activity data samples; content controller circuitry configured to match the activity context information with restricted information stored in the memory and generate modified activity context information which excludes the restricted information; event modeler circuitry configured to calculate a variance score based on a comparison between the baseline activity score and the adjusted activity score; and content provider circuitry configured to communicate a message including at least one of the modified activity context information, the variance score, or the adjusted activity score.

2 . The system of claim 1 , wherein the message comprises a plurality of adjusted activity scores and an identifier of each of the plurality of different independent locations, the plurality of adjusted activity scores including the adjusted activity score.

3 . The system of claim 2 , wherein the message is responsive by a display interface to display a heat map of the organization, the heat map including a graphical representation of the plurality of different independent locations marked with colors, each of the colors corresponding to a respective adjusted activity score from the plurality of adjusted activity scores.

4 . The system of claim 1 , wherein the organization comprises a building and the plurality of different independent locations comprise rooms within the building.

5 . The system of claim 1 , wherein the content provider circuitry is further configured to control one or more building hardware devices based on the adjusted activity score.

6 . The system of claim 1 , wherein the activity context information recognized in the activity data samples includes at least one of an image, a video, or an audio clip.

7 . The system of claim 1 , wherein the activity context information includes an image, wherein the content controller circuitry is configured to modify a portion of the image included in the restricted information and retain a remainder of the image not included in the restricted information.

8 . The system of claim 1 , wherein the event modeler circuitry is further configured to:
receive a range of time, identify a plurality of baseline activity scores generated from the activity data samples received over the range of time, identify a plurality of adjusted activity scores generated from respective activity data samples received over the range of time, and calculate the variance score based on a comparison of the plurality of adjusted activity scores and the plurality of baseline activity scores.

9 . A computer-implemented method, the computer-implemented method comprising:
receiving, from data collectors in an organization, activity data samples comprising audio data and image data; classifying, by a processor, the activity data samples with an activity type identifier by searching a memory configured to store previously classified activity data samples associated with the activity type identifier and comparing the activity data samples with the previously classified activity data samples, the activity type identifier associated with a baseline activity score; recognizing, with a speech-to-text processor and an image recognition processor, activity context information included in the activity data samples; identifying, by the processor, a topical indicator which classifies the activity context information by comparing the activity context information with previously classified activity context information stored in the memory, the previously classified activity context information linked with a topical indicator and the topical indicator linked with a weight factor; weighing, by the processor, the baseline activity score with the weight factor to generate an adjusted activity score; securing, by the processor, the activity context information by comparing the activity context information to restricted activity context information included in a restricted content database and modifying the activity context information to generate modified activity context information which excludes the restricted activity context information; and communicating, by the processor, a message including the modified activity context information.

10 . The computer-implemented method of claim 9 , further comprising the step of generating, by the processor, the message by combining the modified activity context information with a template comprising content arranged in a predefined format.

11 . The computer-implemented method of claim 10 , further comprising
selecting, by the processor, the template from a plurality of templates, each of the plurality of templates associated with a corresponding score range, the adjusted activity score being within the corresponding score range of the template.

12 . The computer-implemented method of claim 10 , further comprising:
identifying, by the processor, a predefined metric associated a the datafield of the template, the datafield comprising a placeholder for variable content; selecting, by the processor, the modified information based on a comparison between the predefined metric and the adjusted activity score.

13 . The computer-implemented method of claim 9 , further comprising:
identifying, in a memory, a plurality of activity identifiers, each activity identifier linked with respective adjusted activity scores and respective activity context information.

14 . The computer-implemented method of claim 13 , further comprising:
identifying, by the processor, a trend in the respective adjusted activity scores corresponding to the plurality of activity identifiers; and communicating the message in response to the trend.

15 . The computer-implemented method of claim 14 , further comprising:
comparing, by the processor, the trend of the respective adjusted activity scores to predefined trends linked with respective templates and identifying a template from the respective templates based on a comparison of the trend with the predefined trends; and generating, by the processor, the message by adding the modified activity context information to a datafield of the template, wherein the templates comprises

Assignees

• Accenture Global Solutions Ltd

Inventors

• Krasadakis Georgios

Classifications

• G05B2219/24015

  Monitoring · CPC title

• G05B19/048

  Monitoring; Safety · CPC title

• G05B19/0426 Primary

  Programming the control sequence · CPC title

• G06F21/6245

  Protecting personal data, e.g. for financial or medical purposes · CPC title

• G06F17/30259

  Physics · mapped topic