Bot group messaging using general voice libraries

Patent metadata

Field	Value
Publication number	US-10897433-B2
Application number	US-201815936941-A
Country	US
Kind code	B2
Filing date	Mar 27, 2018
Priority date	Mar 27, 2017
Publication date	Jan 19, 2021
Grant date	Jan 19, 2021

Abstract

Methods, apparatuses, and computing systems are provided for bot messaging. In an implementation, a method may include one or more of receiving, by a group messaging service coupled to the internet and a group including one or more user nodes, a message including recorded audio, a message address and a first group identifier, and determining that the group includes a bot, the bot including a software application for performing one or more tasks over the internet. The method may also include selecting a voice library to process the recorded audio, processing, by the selected voice library, the recorded audio to produce enhanced text, determining whether the bot is a user bot responsive to a user node in the group or a group bot responsive to each of the one or more user nodes, and sending, by the group messaging service, the enhanced text to the determined user bot or group bot.

First claim

The invention claimed is:

1. A method comprising:
receiving, by a group messaging service configured to manage audio messaging between a plurality of user nodes in a group comprising at least a user node, a second user node, and a bot software application member node, a message from the user node comprising recorded audio and including a request, a user node identifier that identifies the user node, and a group identifier that identifies the group;
selecting a selected voice library from a plurality of voice libraries to process the recorded audio, a voice library including both a speech-to-text engine and a natural language unit configured to convert a received message into enhanced text in a format suited to processing by the bot;
processing, by the selected voice library, the recorded audio to produce the enhanced text comprising the request;
sending, by the group messaging service, the enhanced text to the bot;
receiving, at the group messaging service, a reply from the bot, the reply comprising information indicating completion of the request; and
sending, to the user node and the second user node, a group reply indicating completion of the request.

2. The method of claim 1 , wherein:
the message further comprises a bot identifier that identifies the bot; and
the method further comprises selecting the selected voice library based on the bot identifier.

3. The method of claim 1 , wherein processing the recorded audio comprising:
decoding the recorded audio to obtain decoded audio;
converting, by the speech-to-text engine of the selected voice library, the decoded audio to decoded text; and
enhancing, by the natural language unit of the selected voice library, the decoded text to create the enhanced text.

4. The method of claim 1 , wherein;
the recorded audio comprises the group identifier, wherein the group messaging service extracts the group identifier from the enhanced text;
the method further comprises determining a type of bot the bot is between:
a group bot responsive to any member of the group; and
a user bot responsive to a selected user node from the group.

5. The method of claim 1 , further comprising:
sending the message, by the group messaging service, to each of the plurality of user nodes in the group besides the user node in response to receiving the message.

6. The method of claim 1 , wherein selecting a voice library to process the recorded audio comprises:
selecting a preferred speech-to-text engine and a preferred natural language unit to produce the enhanced text to send to the bot.

7. The method of claim 1 , wherein the group messaging service receives the recorded audio as encoded audio.

8. The method of claim 1 , further comprising determining that the message identifies the bot and responsively sending the enhanced text to the bot.

9. The method of claim 1 , wherein;
the bot is identified in the message via a bot identifier;
the method further comprises:
comparing the bot identifier to a data structure including a list of members of the group to determine the bot is a group member; and
sending the enhanced text to the bot only when the bot identifier matches a data structure entry for the group corresponding to the bot.

10. A memory device storing instructions that, when executed, cause a processor to perform a method comprising:
receiving, by a group messaging service configured to manage audio messaging between a plurality of user nodes in a group comprising at least a user node, a second user node, and a bot software application member node, a message from the user node comprising recorded audio and including a request, a user node identifier that identifies the user node, and a group identifier that identifies the group;
selecting a selected voice library from a plurality of voice libraries to process the recorded audio, a voice library including both a speech-to-text engine and a natural language unit configured to convert a received message into enhanced text including a format suited to processing by the bot;
processing, by the selected voice library, the recorded audio to produce the enhanced text comprising the request;
sending, by the group messaging service, the enhanced text to the bot;
receiving, at the group messaging service, a reply from the bot, the reply comprising information indicating completion of the request; and
sending, to the user node and the second user node, a group reply at least indicating completion of the request.

11. The memory device of claim 10 , wherein:
the message further comprises a bot identifier that identifies the bot; and
the method further comprises selecting the selected voice library based on the bot identifier.

12. The memory device of claim 10 , wherein processing the encoded recorded audio comprises:
decoding the recorded audio to obtain decoded audio;
converting, by the speech-to-text engine of the selected voice library, the decoded audio to decoded text; and
enhancing, by the natural language unit of the selected voice library, the decoded text to create the enhanced text.

13. The memory device of claim 10 , wherein selecting a voice library to process the recorded audio comprises:
selecting a preferred speech-to-text engine and a preferred natural language unit to produce the enhanced text to send to the bot.

14. The memory device of claim 10 , wherein the group messaging service receives the recorded audio as encoded audio.

15. The memory device of claim 10 , the processor performing the method further comprising:
determining a type of bot the bot is between:
a group bot responsive to any member of the group; and
a user bot responsive to a selected user node from the group

sending the group reply to the user node and the second user node when the bot is the group bot; and
sending the reply from the bot to only the user node when the bot is the user bot.

16. The memory device of claim 10 , wherein:
the bot is identified in the message via a bot identifier;
the processor performing the method further comprising:
comparing the bot identifier to a data structure including a list of members of the group to determine the bot is a group member; and
sending the enhanced text to the bot only when the bot identifier matches a data structure entry for the group corresponding to the bot.

17. A computing system, comprising:
a memory comprising program instructions; and
a processor, operably coupled to the memory, wherein the program instructions, when executed by the processor, direct the computing system to:
receive, by a group messaging service configured to manage audio messaging between a plurality of user nodes in a group comprising at least a user node, a second user node, and a bot software application member node, a message from the user node comprising recorded audio and including a request, a user node identifier that identifies the user node, and a group identifier that identifies the group;
select a selected voice library from a plurality of voice libraries to process the recorded audio, a voice library including both a speech-to-text engine and a natural language unit configured to convert a received message into enhanced text including a format suited to processing by the bot;
process, by the selected voice library, the recorded audio to produce the enhanced text, comprising the request;
send, by the group messaging service, the enhanced text to the bot,
receive, at the group messaging service, a reply from the bot, the reply comprising information indicating completion of the request; and
send, to the user nod

Assignees

• Orion Labs

Inventors

• Robbins Jesse
• Albrecht Greg
• Juhlin Ellen

Classifications

• H04L51/04

  Real-time or near real-time messaging, e.g. instant messaging [IM] · CPC title

• G06F16/61

  Indexing; Data structures therefor; Storage structures · CPC title

• H04L51/02 Primary

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• H04L65/403

  Arrangements for multi-party communication, e.g. for conferences (data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15) · CPC title