Detecting events from customer support sessions

Patent metadata

Field	Value
Publication number	US-10097690-B1
Application number	US-201815922662-A
Country	US
Kind code	B1
Filing date	Mar 15, 2018
Priority date	Mar 15, 2018
Publication date	Oct 9, 2018
Grant date	Oct 9, 2018

Abstract

Text of customer support sessions of a company may be processed to detect events that are taking place. For example, an event may be a service disruption. The company may desire to detect the events and take action to address them. The events may be detected by processing customer support sessions during a test window and computing test counts, where each test count corresponds to a topic and a customer parameter. The topics may be determined from the customer support sessions and the customer parameters may relate to information about the customer (e.g., services received by the customer). Baseline counts may also be computed that correspond to typical or expected behavior when no event is occurring. Event detection scores may be computed by processing the test counts and baseline counts and used to determine if an event has occurred. The process may be repeated for subsequent test windows.

First claim

What is claimed is:

1. A system, comprising:
at least one server computer comprising at least one processor and at least one memory, the at least one server computer configured to:
process a group of customer support sessions for each time window of a sequence of time windows;
obtain information about possible customer parameters, wherein each customer parameter relates to information about a customer;
obtain a first group of customer support sessions from one of the sequence of time windows, wherein the first group comprises a first customer support session;
determine a first plurality of topics by processing text of the first group of customer support sessions with a neural network, wherein each customer support session of the first group is associated with a topic of the first plurality of topics;
for each customer support session of the first group, select a subset of the possible customer parameters that correspond to the customer support session;
process the first group of customer support sessions to generate a customer support count profile, the customer support count profile comprising a plurality of counts, by incrementing a subset of the plurality of counts corresponding to (i) a topic of the first customer support session and (ii) a first subset of the possible customer parameters corresponding to the first customer support session;
determine that an event has occurred by processing the customer support count profile; and
provide information about the event and/or the customer support count profile to an event console.

2. The system of claim 1 , wherein the at least one server computer is further configured to:
compute first baseline counts, wherein each baseline count of the first baseline counts corresponds to (i) a topic of the first plurality of topics and (ii) a customer parameter of the possible customer parameters;
compute first event detection scores by processing the customer support count profile and the first baseline counts, wherein each event detection score of the first event detection scores corresponds to (i) a topic of the first plurality of topics and (ii) a customer parameter of the possible customer parameters; and
determine that the event has occurred using the first event detection scores.

3. The system of claim 2 , wherein the at least one server computer is further configured to provide an event report to the event console in response to the determining that the event has occurred.

4. The system of claim 3 , wherein the event report comprises at least a portion of the customer support count profile.

5. A system for detecting events by processing customer support sessions, the system comprising:
at least one server computer comprising at least one processor and at least one memory, the at least one server computer configured to:
process a group of customer support sessions for each time window of a sequence of time windows to determine if an event occurred in the group of customer support sessions, wherein the sequence of time windows comprises a first time window and a second time window;
obtain information about possible customer parameters, wherein each customer parameter relates to information about a customer;
obtain a first group of customer support sessions from the first time window;
determine a first plurality of topics by processing text of the first group of customer support sessions with a neural network, wherein each customer support session of the first group is associated with a topic of the first plurality of topics;
for each customer support session of the first group, select a subset of the possible customer parameters that correspond to the customer support session;
compute a first customer support count profile for the first group, wherein each count of the first customer support count profile corresponds to (i) a topic of the first plurality of topics and (ii) a customer parameter of the possible customer parameters;
process a first customer support session of the first group by incrementing a subset of the counts of the first customer support count profile corresponding to (i) a topic of the first customer support session and (ii) a first subset of the possible customer parameters corresponding to the first customer support session;
compute first baseline counts, wherein each baseline count of the first baseline counts corresponds to (i) a topic of the first plurality of topics and (ii) a customer parameter of the possible customer parameters;
compute first event detection scores by processing the first customer support count profile and the first baseline counts, wherein each event detection score of the first event detection scores corresponds to (i) a topic of the first plurality of topics and (ii) a customer parameter of the possible customer parameters;
determine that no events occurred by processing the first event detection scores;
obtain a second group of customer support sessions from the second time window;
determine a second plurality of topics by processing text of the second group of customer support sessions with the neural network, wherein each customer support session of the second group is associated with a topic of the second plurality of topics;
for each customer support session of the second group, select a subset of the possible customer parameters that correspond to the customer support session;
compute a second customer support count profile for the second group, wherein each count of the second customer support count profile corresponds to (i) a topic of the second plurality of topics and (ii) a customer parameter of the possible customer parameters;
process a second customer support session of the second group by incrementing a subset of the counts of the second customer support count profile corresponding to (i) a topic of the second customer support session and (ii) a second subset of the possible customer parameters corresponding to the second customer support session;
compute second baseline counts, wherein each baseline count of the second baseline counts corresponds to (i) a topic of the second plurality of topics and (ii) a customer parameter of the possible customer parameters;
compute second event detection scores by processing the second customer support count profile and the second baseline counts, wherein each event detection score of the second event detection scores corresponds to (i) a topic of the second plurality of topics and (ii) a customer parameter of the possible customer parameters; and
determine that a first event occurred by processing the second event detection scores.

6. The system of claim 5 , wherein the system is implemented a third-party company providing services to a company, and wherein the customer support sessions comprise messages from customers of the company.

7. The system of claim 5 , wherein the at least one server computer is configured to transmit a notification to at least one of a person or an event console in response to determining that the first event occurred.

8. The system of claim 5 , wherein the at least one server computer is configured to, in response to determining that the first event occurred, cause information to be presented to a person, the information comprising two or more of:
a date and time of the first event;
words of a topic corresponding to the first event;
a description of a topic category corresponding to the first event;
a description of customer parameters corresponding to the first event; and
a number of customer support sessions corresponding to the first event.

9. The system of claim 5 , wherein the at least one server computer is configured to determine the first plurality of topics by processing the first group of customer support sessions

Assignees

• Asapp Inc

Inventors

• Henry Shawn

Classifications

• G06N3/045

  Combinations of networks · CPC title

• G06N3/08

  Learning methods · CPC title

• H04M3/5175

  Call or contact centers supervision arrangements · CPC title

• G06F40/279 Primary

  Recognition of textual entities · CPC title

• H04M3/5183 Primary

  Call or contact centers with computer-telephony arrangements · CPC title