Method for processing information by intelligent agent and intelligent agent

Patent metadata

Field	Value
Publication number	US-11200509-B2
Application number	US-201615196932-A
Country	US
Kind code	B2
Filing date	Jun 29, 2016
Priority date	Dec 30, 2013
Publication date	Dec 14, 2021
Grant date	Dec 14, 2021

Abstract

A method for processing information by an intelligent agent and the intelligent agent, where the method comprises: a first intelligent agent sends a request message to a second intelligent agent, where the request message includes an invitation message or a recommendation message; the first intelligent agent receives a decision message fed back by the second intelligent agent, where the decision message is determined according to the invitation message or the recommendation message and a knowledge model of the second intelligent agent; and the first intelligent agent updates, according to the decision message, a knowledge model of the first intelligent agent or sends a notification message to a first user account corresponding to the first intelligent agent. By using these technical solutions, information on a social network may be learned and processed by means of interaction with another intelligent agent, thereby implementing mining of data on the social network.

First claim

What is claimed is:

1. A method for processing information by an intelligent agent, the method comprising:
determining, by a first intelligent agent, that an object to which an invitation message or a recommendation message is to be sent is a second intelligent agent;
in response to determining that the object to which the invitation message or the recommendation message is to be sent is the second intelligent agent, sending, by the first intelligent agent, a request message to the second intelligent agent, wherein:
the request message comprises the invitation message or the recommendation message sent to the second intelligent agent, wherein: (1) each of the first intelligent agent and the second intelligent agent is a virtual machine learning program, (2) the first intelligent agent corresponds to a first user account and the second intelligent agent corresponds to a second user account, and (3) the first intelligent agent sends the request message to the second intelligent agent without receiving an instruction to send the request message by a first user of the first account; and
the sending comprises predicting, by the first intelligent agent, an idle time of a second user account by learning a historical posting time of the second user account, and sending, by the first intelligent agent, the request message to the second intelligent agent at the idle time of the second user account; and

receiving, by the first intelligent agent, a decision message fed back by the second intelligent agent, wherein the decision message is a message that is determined by the second intelligent agent according to a knowledge model of the second intelligent agent and any one of the invitation message or the recommendation message; and
updating, by the first intelligent agent according to the decision message, a knowledge model of the first intelligent agent or sending, by the first intelligent agent according to the decision message, a notification message to a first user account corresponding to the first intelligent agent.

2. The method according to claim 1 , wherein sending, by a first intelligent agent, a request message to a second intelligent agent comprises:
sending, by the first intelligent agent, the request message to the second intelligent agent at any moment.

3. The method according to claim 1 , wherein determining, by the first intelligent agent, that an object to which the invitation message or the recommendation message is to be sent is the second intelligent agent comprises:
determining, by the first intelligent agent, the invitation message or the recommendation message according to operation information of a user account corresponding to the other intelligent agent; and
determining, according to the invitation message or the recommendation message and the label of the other intelligent agent, that the object to which the invitation message or the recommendation message is to be sent is the second intelligent agent.

4. The method according to claim 1 , wherein:
when the request message is a learning invitation message, the decision message comprises related information of the second intelligent agent to be shared with the first intelligent agent, or the decision message is refusing to share related information of the second intelligent agent with the first intelligent agent, wherein the related information comprises at least any one of the following: a learning model, data, and activity arrangement; and
updating, by the first intelligent agent according to the decision message, a knowledge model of the first intelligent agent or sending, by the first intelligent agent according to the decision message, a notification message to a first user account corresponding to the first intelligent agent comprises:
learning, by the first intelligent agent, the related information of the second intelligent agent when the decision message is the related information of the second intelligent agent to be shared with the first intelligent agent, and updating the knowledge model of the first intelligent agent, or
updating, by the first intelligent agent when the decision message is refusing to share the related information of the second intelligent agent with the first intelligent agent, the knowledge model of the first intelligent agent according to a case in which the second intelligent agent refuses the learning invitation message.

5. The method according to claim 4 , wherein after learning, by the first intelligent agent, the related information of the second intelligent agent when the decision message is the related information of the second intelligent agent to be shared with the first intelligent agent, and updating the knowledge model of the first intelligent agent, the method further comprises:
obtaining, by the first intelligent agent, a learning outcome by using learned content and by comparing the decision message with the knowledge model of the first intelligent agent; and
feeding back, by the first intelligent agent, the learning outcome to the second intelligent agent, so that the second intelligent agent updates the knowledge model of the second intelligent agent according to the learning outcome.

6. The method according to claim 1 , wherein:
when the request message is an activity invitation message, the decision message comprises a message for agreeing to or refusing an activity invitation; and
updating, by the first intelligent agent according to the decision message, a knowledge model of the first intelligent agent or sending, by the first intelligent agent according to the decision message, a notification message to a first user account corresponding to the first intelligent agent comprises:
sending, by the first intelligent agent when the decision message is the message for agreeing to the activity invitation, the notification message to the first user account corresponding to the first intelligent agent, so that information that the second intelligent agent accepts the activity invitation is displayed on the first user account, or
updating, by the first intelligent agent when the decision message is the message for refusing the activity invitation, the knowledge model of the first intelligent agent according to a case in which the second intelligent agent refuses the activity invitation message.

7. The method according to claim 1 , wherein:
when the request message is the recommendation message, the decision message comprises accepting or refusing the recommendation message; and
updating, by the first intelligent agent according to the decision message, a knowledge model of the first intelligent agent or sending, by the first intelligent agent according to the decision message, a notification message to a first user account corresponding to the first intelligent agent comprises:
updating, by the first intelligent agent, the knowledge model of the first intelligent agent according to the decision message when the decision message is accepting or refusing the recommendation message.

8. The method according to claim 1 , wherein determining, by the first intelligent agent, that the object to which the invitation message or the recommendation message is to be sent is the second intelligent agent, comprises:
obtaining, by the first intelligent agent according to a label of the first intelligent agent and a label of another intelligent agent, a measurement value of an interest similarity between a first user corresponding to the first user account and a user corresponding to the other intelligent agent, wherein the other intelligent agent refers to an intelligent agent that has an association relationship with the first intelligent agent; and
determining, according to the measurement value, that the object to which the invitation mess

Assignees

• Huawei Tech Co Ltd

Inventors

• Yang Qiang
• Song Yangqiu
• Leung Wing Ki
• Lu Zhengdong

Classifications

• G06N5/022

  Knowledge engineering; Knowledge acquisition · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• G06F16/2465

  Query processing support for facilitating data mining operations in structured databases · CPC title

• G06N5/043

  Distributed expert systems; Blackboards · CPC title