Trend identification and behavioral analytics system and methods

Patent metadata

Field	Value
Publication number	US-9760838-B1
Application number	US-201615071037-A
Country	US
Kind code	B1
Filing date	Mar 15, 2016
Priority date	Mar 15, 2016
Publication date	Sep 12, 2017
Grant date	Sep 12, 2017

Abstract

Methods, apparatus, and systems for analyzing data trends are described herein. The present disclosure includes the identification of trending terms in data through the use of an unsupervised algorithm. Trends are identified and counted during a first and second time period. The frequency and co-occurrence of groups of terms is compared to determine a set of trending terms without reference to a library of pre-defined terms. The set of trending terms is displayed to a user.

First claim

What is claimed is:

1. A system for analyzing data relating to trends, which comprises:
a processor;
an analysis module, wherein the analysis module is a non-transitory computer readable medium operably connected to the processor, wherein the non-transitory computer readable medium comprises a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, wherein the plurality of instructions when executed:
analyze a first plurality of communications occurring over a first time period based on voice data and non-voice data;
determine a first plurality of terms based on the analyzed first plurality of communications;
analyze a second plurality of communications occurring over a second time period based on voice data and non-voice data;
determine a second plurality of terms based on the analyzed second plurality of communications;
compare the terms of the first plurality of terms and the second plurality of terms based on one or more factors including a frequency of the terms in each of the first and second time periods;
identify a set of trending terms based on the comparison of the terms without reference to a library of pre-defined terms;
identify a subset of communications from the first and the second plurality of communications in which an identified trending term is absent;
analyze the subset of communications to determine a signal associated with the identified absent trending term; and
communicate the identified set of trending terms, the identified absent trending term, and the signal associated with the identified absent trending term to be displayed to a user; and

a display device configured to display the identified set of trending terms, the identified absent trending term, and the signal associated with the identified absent trending term to a user.

2. The system of claim 1 , wherein the first time period and the second time period have fixed lengths that are equal.

3. The system of claim 2 , wherein the first time period and the second time period are sequential and do not overlap.

4. The system of claim 1 , wherein communicating the set of trending terms further comprises instructions that, when executed, transmit the set of trending terms to a communication distributor.

5. The system of claim 1 , wherein the instruction to identify the set of trending terms further comprises establishing a frequency threshold, and including terms that exceed the frequency threshold in the identified set of trending terms.

6. The system of claim 1 , wherein the one or more factors further comprises a co-occurrence of two or more terms.

7. The system of claim 6 , which further comprises instructions, that when executed, identify a set of trending terms that comprises one or more sets based on a frequency of co-occurring terms from the comparison of terms.

8. The system of claim 1 , wherein the terms of the first plurality of terms and the second plurality of terms each independently comprise one or more words, ideograms, hashtags, numbers, single letters, abbreviations, or written symbols.

9. The system of claim 1 , wherein each term of the identified set of trending terms comprises one or more words.

10. The system of claim 9 , wherein each term of the identified set of trending terms comprises between one and ten words.

11. The system of claim 1 , wherein the analysis module further comprises a memory, the analysis module being configured to receive and store the first plurality of terms and the second plurality of terms in the memory, configured to compare the first plurality of terms to the second plurality of terms, configured to store the identified set of trending terms, or a combination thereof.

12. The system of claim 1 , further comprising a routing engine configured to send an automated message to an external source based on the set of trending terms.

13. A method for analyzing data related to trends, which comprises:
recording, by one or more processors, a first plurality of communications occurring over a first time period based on voice data and non-voice data;
determining a first plurality of terms based on the first plurality of communications;
recording, by one or more processors, a second plurality of communications occurring over a second time period based on voice data and non-voice data;
determining a second plurality of terms based on the second plurality of communications;
comparing the terms of the first plurality of terms and the second plurality of terms based on one or more factors including a frequency of the terms in each of the first and second time periods;
identifying a set of trending terms based on the comparison of the terms without reference to a library of pre-defined terms, wherein the set of trending terms comprises a set of most frequent terms;
identifying a subset of communications from the first and second plurality of communications in which an identified trending term is absent;
analyzing the subset of communications to determine a signal associated with the identified absent trending term; and
displaying the identified set of trending terms, the identified absent trending term, and the signal associated with the identified absent trending term to a user.

14. The method of claim 13 , wherein the first time period and the second time period have fixed lengths that are equal.

15. The method of claim 14 , wherein the first time period and the second time period are sequential and do not overlap.

16. The method of claim 13 , which further comprises executing instructions to transmit the identified set of trending terms to a communication distributor.

17. The method of claim 13 , wherein the identifying the set of trending terms further comprises establishing a frequency threshold, and including terms that exceed the frequency threshold in the identified set of trending terms.

18. The method of claim 13 , wherein the one or more factors further comprises a co-occurrence of two or more terms.

19. The method of claim 18 , which further comprises instructions that, when executed, identify a set of trending terms that comprises one or more sets based on a frequency of co-occurring terms from the comparison of terms.

20. The method of claim 13 , wherein the terms of the first plurality of terms and the second plurality of terms each independently comprise one or more words, ideograms, hashtags, numbers, single letters, abbreviations, or written symbols.

21. The method of claim 13 , wherein each term of the identified set of trending terms comprises one or more words.

22. The method of claim 13 , wherein each term of the identified set of trending terms comprises between one and ten words.

23. A system for analyzing trend data, which comprises:
a processor;
an analysis module, wherein the analysis module is a non-transitory computer readable medium operably connected to the processor, wherein the non-transitory computer readable medium comprises a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, wherein the plurality of instructions when executed:
analyze a first plurality of communications occurring over a first time period and determine a first plurality of terms;
analyze a second plurality of communications occurring over a second time period and determine a second plurality of terms;
determine a frequency that each term of the first plurality of terms and the second plurality of t

Assignees

• Mattersight Corp

Inventors

• Danson Christopher
• Brown Douglas
• Warford Roger
• Traba Andrew
• Heller Jordana

Classifications

• G06N5/04 Primary

  Inference or reasoning models · CPC title

• G06N5/045

  Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence · CPC title

• G06F40/279 Primary

  Recognition of textual entities · CPC title

• G06N20/00

  Machine learning · CPC title

• G06N99/005 Primary

  Physics · mapped topic