# US 2016/0366084 A1 · Contextually driven messaging system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2016/0366084 A1
- Document ID: US20160366084A1
- Status: Published application
- Kind: A1
- Application number: 14/736,226
- Filed: 2015-06-10
- Published: 2016-12-15
- Earliest claimed: 2015-06-10
- Assignees: Google Inc.
- Applicants: Google Inc.
- Inventors: Evan Nicklas Wu Malahy
- Web page: https://patentgrep.com/patent/US20160366084A1

## CPC

- G06Q 10/107: Computer-aided management of electronic mailing [e-mailing]
- G10L 13/02: Methods for producing synthetic speech; Speech synthesisers
- H04L 51/224: providing notification on incoming messages, e.g. pushed notifications of received messages
- H04M 1/72436: for text messaging, e.g. short messaging services [SMS] or e-mails
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- H04M 1/72454: according to context-related or environment-related conditions
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

A method may include receiving, by a computing device associated with a user, a message from an origination source and receiving, by the computing device, an audio input. The method may also include determining, by the computing device and based at least in part on the audio input and contextual information, a probability that the user intends to send a response message to the origination source. The method may further include, responsive to determining that the probability the user intends to send the response message to the origination source satisfies a threshold probability, determining, by the computing device, that the user intends to send the response message to the origination source. The method may also include, responsive to determining that the user intends to send the response message to the origination source, generating, by the computing device and based on the audio input, the response message, and sending, by the computing device, the response message to the origination source.

## Claims

### Claim 1

A method comprising:
receiving, by a computing device associated with a user, a message from an origination source;
receiving, by the computing device, an audio input;
determining, by the computing device and based at least in part on the audio input and contextual information, a probability that the user intends to send a response message to the origination source;
responsive to determining that the probability the user intends to send the response message to the origination source satisfies a threshold probability, determining, by the computing device, that the user intends to send the response message to the origination source; and
responsive to determining that the user intends to send the response message to the origination source:
generating, by the computing device and based on the audio input, the response message; and
sending, by the computing device, the response message to the origination source.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
responsive to determining that the probability the user intends to send the response message to the origination source does not satisfy than the threshold probability:
outputting, by the computing device, a request for additional action by a user;
receiving, by the computing device and from the user; a second audio input indicative of the user's intent to send a message; and
sending, by the computing device and based at least in part on the second audio input, the response message to the origination source.

### Claim 3 (depends on 1)

The method of claim 1, wherein the origination source is a first origination source, the method further comprising:
prior to receiving the audio input, receiving, by the computing device, a message from a second origination source;
determining, by the computing device and based at least in part on the audio input and contextual information, a probability that the user intends to send the response message to the second origination source;
determining, by the computing device and based on the probability that the user intends to send the response message to the first origination source and the probability that the user intends to send the response message to the second origination source, whether the user intends to send the response message to the first origination source or to the second origination source; and
responsive to determining that the user intends to send the response message to the second origination source:
generating, by the computing device and based on the audio input, the response message; and
sending, by the computing device, the response message to the second origination source.

### Claim 4 (depends on 3)

The method of claim 3,
wherein determining that the user intends to send the response message to the first origination source is further responsive to determining that the probability the user intends to send the response message to the first origination source satisfies the threshold probability but the probability that the user intends to send the response message to the second origination source does not satisfy the threshold probability, and
wherein determining that the user intends to send the response message to the second origination source is further responsive to determining that the probability the user intends to send the response message to the second origination source satisfies the threshold probability but the probability that the user intends to send the response message to the first origination source does not satisfy than the threshold probability.

### Claim 5 (depends on 3)

The method of claim 3,
wherein determining that the user intends to send the response message to the first origination source is further responsive to determining that the probability the user intends to send the response message to the first origination source satisfies the threshold probability and is greater than the probability that the user intends to send the response message to the second origination source, and
wherein determining that the user intends to send the response message to the second origination source is further responsive to determining that the probability the user intends to send the response message to the second origination source satisfies the threshold probability and is greater than the probability that the user intends to send the response message to the first origination source.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
determining, by the computing device, a probability the user intends to listen to the message from the origination source; and
responsive to determining that the probability the user intends to listen to the message from the origination source satisfies a threshold probability for listening to messages:
generating, by the computing device and based on the message from the origination source; audio data; and
outputting, by the computing device, the audio data.

### Claim 7 (depends on 1)

The method of claim 1, wherein the contextual information includes one or more of:
frequency of incoming messages from the origination source, frequency of outgoing messages to the origination source, time since the last received message from the origination source, or time since the last sent message to the origination source.

### Claim 8 (depends on 1)

The method of claim 1, wherein the probability that the user intends to send the response message to the origination source is not based a user command.

### Claim 9

A device comprising:
an audio output device;
an audio input device;
a communication unit;
a message management module operable by at least one processor to:
receive, via the communication unit, a message from an origination source;
receive, via the audio input device, an audio input;
determine, based at least in part on the audio input and contextual information, a probability a the user associated with the device intends to send a response message to the origination source;
responsive to determining that the probability the user intends to send the response message to the origination source satisfies a threshold probability, determine, that the user intends to send the response message to the origination source; and
responsive to determining that the user intends to send the response message to the origination source:
generate, based on the audio input, the response message; and
send, via the communication unit, the response message to the origination source.

### Claim 10 (depends on 9)

The device of claim 9, wherein the message management module is further operable by the at least one processor to:
responsive to determining that the probability the user intends to send the response message to the origination source does not satisfy the threshold probability:
output, via the audio output device, a request for additional action by a user;
receive, via the audio input device; a second audio input indicative of the user's intent to send a message; and
send, via the communication unit and based at least in part on the second audio input, the response message to the origination source.

### Claim 11 (depends on 9)

The device of claim 9, wherein the origination source is a first origination source, wherein the message management module is further operable by the at least one processor to:
prior to receiving the audio input, receive, via the communication unit, a message from a second origination source;
determine, based at least in part on the audio input and contextual information, a probability that the user intends to send the response message to the second origination source;
determine, based on the probability that the user intends to send the response message to the first origination source and the probability that the user intends to send the response message to the second origination source, whether the user intends to send the response message to the first origination source or to the second origination source; and
responsive to determining that the user intends to send the response message to the second origination source:
generate, based on the audio input, the response message; and
send, via the communication network, the response message to the second origination source.

### Claim 12 (depends on 11)

The device of claim 11,
wherein determining that the user intends to send the response message to the first origination source is further responsive to determining that the probability the user intends to send the response message to the first origination source satisfies the threshold probability but the probability that the user intends to send the response message to the second origination source does not satisfy than the threshold probability, and
wherein determining that the user intends to send the response message to the second origination source is further responsive to determining that the probability the user intends to send the response message to the second origination source satisfies the threshold probability but the probability that the user intends to send the response message to the first origination source does not satisfy the threshold probability.

### Claim 13 (depends on 11)

The device of claim 11,
wherein determining that the user intends to send the response message to the first origination source is further responsive to determining that the probability the user intends to send the response message to the first origination source satisfies the threshold probability and is greater than the probability that the user intends to send the response message to the second origination source, and
wherein determining that the user intends to send the response message to the second origination source is further responsive to determining that the probability the user intends to send the response message to the second origination source satisfies the threshold probability and is greater than the probability that the user intends to send the response message to the first origination source.

### Claim 14 (depends on 9)

The device of claim 9, wherein the message management module is further operable by the at least one processor to:
determine a probability the user intends to listen to the message from the origination source; and
responsive to determining that the probability the user intends to listen to the message from the origination source satisfies a threshold probability for listening to messages:
generate, based on the message from the origination source; audio data; and
output, via the audio output device, the audio data.

### Claim 15 (depends on 9)

The device of claim 9, wherein the contextual information includes one or more of:
frequency of incoming messages from the origination source, frequency of outgoing messages to the origination source, time since the last received message from the origination source, or time since the last sent message to the origination source.

### Claim 16 (depends on 9)

The device of claim 9, wherein the probability that the user intends to send the response message to the origination source is not based a user command.

### Claim 17

A computer-readable storage medium comprising instructions that, when executed, configure one or more processors of a computing system to:
receive a message from an origination source;
receive an audio input;
determine, based at least in part on the audio input and contextual information, a probability that a user associated with the computing system intends to send a response message to the origination source;
responsive to determining that the probability the user intends to send the response message to the origination source satisfies a threshold probability, determine that the user intends to send the response message to the origination source; and
responsive to determining that the user intends to send the response message to the origination source:
generate, based on the audio input, the response message; and
send the response message to the origination source.

### Claim 18 (depends on 17)

The computer-readable storage medium of claim 17, wherein the instructions, when executed, further configure the one or more processors to:
responsive to determining that the probability the user intends to send the response message to the origination source does not satisfy the threshold probability:
output a request for additional action by a user;
receive a second audio input indicative of the user's intent to send a message; and
send, based at least in part on the second audio input, the response message to the origination source.

### Claim 19 (depends on 17)

The computer-readable storage medium of claim 17, wherein the instructions, when executed, further configure the one or more processors to:
prior to receiving the audio input, receive a message from a second origination source;
determine, based at least in part on the audio input and contextual information, a probability that the user intends to send the response message to the second origination source;
determine, based on the probability that the user intends to send the response message to the first origination source and the probability that the user intends to send the response message to the second origination source, whether the user intends to send the response message to the first origination source or to the second origination source; and
responsive to determining that the user intends to send the response message to the second origination source:
generate, based on the audio input, the response message; and
send the response message to the second origination source.

### Claim 20 (depends on 17)

The computer-readable storage medium of claim 17, wherein the instructions, when executed, further configure the one or more processors to:
determine a probability the user intends to listen to the message from the origination source; and
responsive to determining that the probability the user intends to listen to the message from the origination source satisfies a threshold probability for listening to messages:
generate, based on the message from the origination source; audio data; and
output the audio data.
