Bot permissions

Patent metadata

Field	Value
Publication number	US-12126739-B2
Application number	US-202318327459-A
Country	US
Kind code	B2
Filing date	Jun 1, 2023
Priority date	Sep 20, 2016
Publication date	Oct 22, 2024
Grant date	Oct 22, 2024

Abstract

Permission control and management for messaging application bots is described. A method can include providing a messaging application, on a first computing device associated with a first user, to enable communication between the first user and another user, and detecting, at the messaging application, a user request. The method can also include programmatically determining that an action in response to the user request requires access to data associated with the first user, and causing a permission interface to be rendered in the messaging application, the permission interface enabling the first user to approve or prohibit access to the data associated with the first user. The method can include accessing the data associated with the first user and performing the action in response to the user request, upon receiving user input from the first user indicating approval of the access to the data associated with the first user.

First claim

What is claimed is:

1. A computer-implemented method comprising:
receiving, by a bot deployed within an application, a prediction from a suggestion machine-learned model;
generating, by the bot, a specific action, the generation of the specific action based on the prediction from the suggestion machine-learned model;
receiving, by the bot, a request of a user to perform the specific action;
programmatically determining, by the bot, that the specific action requires access to user data associated with the user;
causing, by the bot, a permission interface to be rendered, the permission interface enabling the user to approve access to the user data associated with the user;
receiving, by the bot, a user input indicating approval of the access to the user data associated with the user;
responsive to receiving the user input indicating approval of the access to the user data associated with the user, accessing, by the bot, the user data associated with the user; and
responsive to accessing the user data associated with the user, performing, by the bot, the specific action.

2. The method of claim 1 , wherein the specific action is related to a second user and the method further comprises:
obtaining, by the bot, permission from the second user to receive one or more messages from the bot; and
sending, by the bot, the one or more messages to the second user to obtain information associated with the specific action, wherein performing the specific action occurs responsive to receiving, by the bot, the information associated with the specific action from the second user.

3. The method of claim 1 , further comprising:
obtaining, by the bot, permission from a second user to approve access to user data associated with the second user; and
analyzing, by the bot, one or more messages between the first user and the second user, wherein the suggested action is determined based on analyzing the one or more messages.

4. The method of claim 1 , further comprising:
obtaining, by the bot, permission from a second user to approve access to user data associated with the second user;
receiving, by the bot, an indication from the user that a conversation between the user and the second user is confidential; and
abstaining from analysis, by the bot, of the conversation until the user or the second user reactivates the bot.

5. The computer-implemented method of claim 1 , wherein the programmatically determining that the specific action requires access to the user data associated with the user is performed by a second machine-learned model, the second machine-learned model taking as an input at least the user request for the application to perform the specific action.

6. The computer-implemented method of claim 1 , wherein:
the suggestion machine-learned model takes as an input at least a content from a device associated with the user;
the content is based on a context of the user; and
the context of the user comprises at least one of information on interactions of the user with one or more other users, one or more external conditions, one or more schedules of the user, or an activity of the user.

7. The computer-implemented method of claim 1 , further comprising directing the bot to perform the specific action in a particular style.

8. The computer-implemented method of claim 7 , where the particular style comprises one of a formal style, a playful style, a neutral style, or an emoji style.

9. The computer-implemented method of claim 1 , wherein the application is a messaging application.

10. A non-transitory computer-readable medium with instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform operations, the operations comprising:
receiving, by a bot deployed within an application, a prediction from a suggestion machine-learned model;
generating, by the bot, a specific action, the generation of the specific action based on the prediction from the suggestion machine-learned model;
receiving, by the bot, a request of a user to perform the specific action;
programmatically determining, by the bot, that the specific action requires access to user data associated with the user;
causing, by the bot, a permission interface to be rendered, the permission interface enabling the user to approve access to the user data associated with the user;
receiving, by the bot, a user input indicating approval of the access to the user data associated with the user;
responsive to receiving the user input indicating approval of the access to the user data associated with the user, accessing, by the bot, the user data associated with the user; and
responsive to accessing the user data associated with the user, performing, by the bot, the specific action.

11. The computer-readable medium of claim 10 , the operations further comprising:
assigning, by the bot, a sentiment score to a topic associated with the user based on a reaction of the user to the topic in a conversation, wherein the suggested action is based on the sentiment score for the topic.

12. The computer-readable medium of claim 10 , wherein the specific action is related to a second user and the operations further comprise:
obtaining, by the bot, permission from the second user to receive one or more messages from the bot;
determining, by the bot, a proximity between the first user and the second user in a social graph; and
providing, by the bot, a message to the user and the second user with a conversation style that is based on the proximity between the user and the second user in the social graph.

13. The non-transitory computer-readable medium of claim 10 , wherein:
the suggestion machine-learned model takes as an input at least a content from a device associated with the user;
the content is based on a context of the user; and
the context of the user comprises at least one of information on interactions of the user with one or more other users, one or more external conditions, one or more schedules of the user, or an activity of the user.

14. The non-transitory computer-readable medium of claim 10 , wherein the programmatically determining that the specific action requires access to the user data associated with the user is performed by a second machine-learned model, the second machine-learned model taking as an input at least the user request for the application to perform the specific action.

15. A system comprising:
one or more processors; and
a memory coupled to the one or more processors that stores instructions that, when executed by the one or more processors, cause the one or more processors to perform operations, the operations comprising:
receiving, by a bot deployed within an application, a prediction from a suggestion machine-learned model;
generating, by the bot, a specific action, the generation of the specific action based on the prediction from the suggestion machine-learned model;
receiving, by the bot, a request of a user to perform the specific action;
programmatically determining, by the bot, that the specific action requires access to user data associated with the user;
causing, by the bot, a permission interface to be rendered, the permission interface enabling the first user to approve access to the user data associated with the first user;
receiving, by the bot, a user input from the first user indicating approval of the access to the user data associated with the first user;
responsive to receiving the user input indicating approval of the access to the user data associated with the user, accessing, by the bot, the user data associated with the user; and

Assignees

• Google Llc

Inventors

• Fung Shelbian
• Dunn Richard
• Volkov Anton
• Rodriquez Adam

Classifications

• H04L63/10

  for controlling access to devices or network resources · CPC title

• H04L63/168 Primary

  above the transport layer · CPC title

• H04L9/3271 Primary

  using challenge-response · CPC title