IOT-BASED CALL ASSISTANT DEVICE

• US 20190057079A1
• Filed: 10/23/2018
• Published: 02/21/2019
• Est. Priority Date: 06/01/2015
• Status: Active Grant

• Current Assignee: Zoominfo Converse LLC
• Original Assignee: AffectLayer, Inc. (ZoomInfo Technologies, Inc.)
• Inventors: Raanani, Roy, Levy, Russell, Breakstone, Micha Yochanan
• Granted Patent: US 10,679,013 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 40/216 using statistical methods
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 25/63 for estimating an emotional state
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/2038 Call context notifications
• CPC Class Codes: H04M 2203/357 Autocues for dialog assistance
• CPC Class Codes: H04M 3/2236 Quality of speech transmission monitoring
• CPC Class Codes: H04M 3/42059 Making use of the calling party identifier
• CPC Class Codes: H04M 3/5141 Details of processing calls and other types of contacts in an unified manner unified messaging in packet-switching networks H04L51/56
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements
• CPC Class Codes: H04M 3/5183 Call or contact centers with computer-telephony arrangements

Abstract

A call assistant device is used to command a call management system to perform a specified task in association with a specified call. The call assistant device can be an Internet of Things (IoT) based device, which can include one or more buttons and connect to a communication network wirelessly. When a user activates the call assistant device, e.g., presses a button, the call assistant device sends a message to the call management system to perform a specified task. Upon receiving the message, the call management system executes the specified task in association with a specified call of the user. The task to be performed can be any task that can be performed in association with a call, e.g., generating a summary of the call, bookmarking a specified moment in the call, sending a panic alert to a particular user, or generating an action item.

Claims

1. A computer-implemented method, comprising:

receiving, at a computer system, a message from a call assistant device, wherein the call assistant device is associated with a user of the computer system, and wherein the message includes (a) a timestamp indicative of a time the message is sent from the call assistant device, (b) a device identification (ID) of the call assistant device, and (c) a type of action performed by the user on the call assistant device;

determining, at the computer system and based on the type of action, a specified task to be performed in association with a specified call the user participated in, wherein the specified call is a conversation between the user and a set of speakers;

executing the specified task in association with the specified call; and

generating a result from executing the specified task.

2. The computer-implemented method of claim 1, wherein receiving the message includes receiving the message in response to invoking of a button on the call assistant device.

3. The computer-implemented method of claim 1, wherein the type of action performed by the user on the call assistant device includes at least one of a gesture performed by the user in association with the call assistant device, a number of times a button of the call assistant device is pressed, or a duration for which the button is pressed.

4. The computer-implemented method of claim 1, wherein determining the specified task includes:

determining the specified task based on the device ID and the user input type.

5. The computer-implemented method of claim 1, wherein determining the specified task includes:

storing, at a storage system, an association between a device ID of each of multiple call assistant devices and a specified function for a specified user input.

6. The computer-implemented method of claim 1, wherein determining the specified task includes:

storing, at a storage system, an association between a device ID of each of multiple call assistant devices and a user ID of a user the corresponding call assistant device is associated with.

7. The computer-implemented method of claim 1, wherein determining the specified task includes:

determining a user ID of the user based on the device ID, and

determining the specified call from among multiple calls whose metadata includes the user ID of the user.

8. The computer-implemented method of claim 7, wherein determining the specified call includes:

determining if the specified call is an ongoing call, and

responsive to a determination that the specified call is the ongoing call, obtaining real-time call data associated with the ongoing call.

9. The computer-implemented method of claim 7, wherein determining the specified call includes:

determining, at the computer system, that the specified call is a recording of the conversation between the user and the set of speakers,

identifying the recording using the timestamp in the message, and

obtaining the recording of the specified call.

10. The computer-implemented method of claim 1, wherein determining the specified task includes:

extracting multiple features from the specified call, wherein the multiple features include at least one of characteristics of the user, characteristics of a speaker of the set of speakers, or characteristics associated with the conversation of the specified call, and

executing, using one or more of the multiple features, the specified task.

11. The computer-implemented method of claim 10, wherein executing the specified task includes generating a summary of the conversation based on the multiple features.

12. The computer-implemented method of claim 11, wherein generating the summary includes generating the summary by performing a semantic analysis of the multiple features, the multiple features including one or more words or phrases in the call.

13. The computer-implemented method of claim 12, wherein generating the summary includes generating the summary using any of a rule-based, artificial intelligence (Al), machine-learning (ML), or natural language processing (NLP) techniques.

14. The computer-implemented method of claim 10, wherein executing the specified task includes generating an action item of the specified call based on the multiple features, the multiple features including one or more words or phrases in the call that are indicative of an action item.

15. The computer-implemented method of claim 10, wherein executing the specified task includes generating a panic alert, the panic alert sending a notification to a specified user in an event the specified call is an ongoing call.

16. The computer-implemented method of claim 10, wherein executing the specified task includes generating a bookmark at a specified temporal location of the specified call corresponding to the timestamp, wherein the bookmark, upon access, enables playing of the specified call from the specified temporal location.

17. The computer-implemented method of claim 10, wherein extracting the features includes extracting the features using any of Al, NL, or NLP techniques.

18. The computer-implemented method of claim 1, wherein the specified call is at least one of a video call, an online meeting, a virtual reality-based call, an augmented reality-based call, or an email interaction between the customer and the representative.

19. The computer-implemented method of claim 1, wherein receiving the message includes:

sending the message from the call assistant device to the computer system in response to receiving a user input at the call assistant device.

20. The computer-implemented method of claim 1, wherein receiving the message includes:

receiving an input from the user at the call assistant device,

generating, at the call assistant device, the message in response to the input,

determining that the call assistant device is not connected to a communication network,

storing the message in a memory of the call assistant device for later transmission to the computer system.

21. The computer-implemented method of claim 1, wherein receiving the message includes:

receiving the message in response to invoking a button associated with the call assistant device, the message including a voice command from the user,

analyzing the voice command to determine a task to performed, and

executing the task.

22. A computer-readable storage medium storing computer-readable instructions, comprising:

instructions for sending, from a call assistant device to a computer system, a message in response to a user input received at the call assistant device from a user, the message including (a) a timestamp indicative of a time the user input is received at the call assistant device, and (b) a device identification (ID) of the call assistant device;

instructions for determining, at the computer system, a specified task to be performed in association with a specified call the user participated in, wherein the specified call is a conversation between the user and a set of speakers; and

instructions for executing the specified task in association with the specified call, wherein the executing includes extracting multiple features of the specified call and executing the specified using one or more of the multiple features.

23. The computer-readable storage medium of claim 22, wherein the instructions for executing the specified task include:

instructions for analyzing the multiple features to obtain data for performing the specified task, and

instructions for executing the specified task based on the data.

24. The computer-readable storage medium of claim 23, wherein the instructions for analyzing the multiple features include:

instructions for obtaining the data from analyzing the multiple features, deriving the data from metadata of the call, or deriving the data based on data obtained from analyzing the multiple features.

25. The computer-readable storage medium of claim 23, wherein the instructions for determining the specified task include:

instructions for determining a user ID of the user based on the device ID, and

instructions for determining the specified call from among multiple calls whose metadata includes the user ID of the user.

26. The computer-readable storage medium of claim 25, wherein the instructions for determining the specified call include:

instructions for determining that the specified call is an ongoing call, and

instructions for obtaining real-time call data associated with the ongoing call.

27. The computer-readable storage medium of claim 25 include:

instructions for determining that the specified call is a recording of the conversation between the user and the set of speakers,

instructions for identifying the recording using the timestamp in the message, and

instructions for obtaining the recording of the specified call.

28. The computer-readable storage medium of claim 25 include:

instructions for determining that the specified is neither an ongoing call nor a recording of the conversation is available at the storage system, and

instructions for queuing the message in the storage system for later execution.

29. A system, comprising:

a call assistant device having a processor, memory, a network component, and an input component, the network component configured to connect the call assistant device to a communication network, the processor configured to send a message in response to activation of the input component by a user, the message including (a) a timestamp indicative of a time of activation of the input component, and (b) a device identification (ID) of the call assistant device;

a first component that is configured to receive the message from the call assistant device;

a second component that is configured to determine a specified task to be performed in association with a specified call the user participated in, wherein the specified call is a conversation between the user and a set of speakers;

a third component that is configured to extract multiple features from the specified call, wherein the multiple features include any of characteristics of the user, the set of speakers or a conversation of the specified call; and

a fourth component that is configured to execute, using one or more of the multiple features, the specified task.

30. The system of claim 29, wherein the input component is a button, and wherein the call assistant device is activated based on a gesture performed by the user in association with the button, one or more presses of the button, a duration for which the button is pressed, or a duration between consecutive presses of the button.

31. An Internet-of-Things based device, comprising:

a network component that is configured to connect the device to a communication network;

a memory that is configured to store a device identification (ID) of the device;

an input component that is configured to be activated by a user; and

a processor that is configured to send a message to a computer system over the communication network, wherein the message is sent in response to activation of the input component, the message including (a) a timestamp indicative of a time of activation of the input component, and (b) a device identification (ID) of the device, wherein the device causes the computer system to;

execute a specified task in association with a specified call of the user, wherein the specified call is a conversation between the user and a set of speakers, wherein the specified task is determined based on the device ID and user ID of the user.

32. An Internet-of-Things based device, comprising:

a recording component to record a conversation between a user and a set of speakers; and

a call assistant device that is configured to detachably couple with the recording device, wherein the call assistant device is configured to;

connect to a communication network directly or via the recording component, and

send a message to a computer system over the communication network to execute a specified task in association with the conversation, wherein the message is sent in response to activation of the call assistant device, the message including (a) a timestamp indicative of a time of activation of the input component, and (b) a device identification (ID) of the call assistant device, wherein the specified task is determined based on the device ID and user ID of the user.