METHOD AND SYSTEM FOR IDENTIFYING A HUMAN OR MACHINE

• US 20160315948A1
• Filed: 04/07/2016
• Published: 10/27/2016
• Est. Priority Date: 04/21/2015
• Status: Active Grant

• Current Assignee: Alibaba Group Holding Ltd.
• Original Assignee: Alibaba Group Holding Ltd.
• Inventors: Wan, Chaoxin, Wei, Xingguo, Lin, Songying
• Granted Patent: US 9,917,848 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 21/316 by observing the pattern of computer usage, e.g. typical user behaviour
• CPC Class Codes: G06F 21/55 Detecting local intrusion or implementing counter-measures
• CPC Class Codes: G06F 2221/2133 Verifying human interaction, e.g., Captcha
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: H04L 63/102 Entity profiles
• CPC Class Codes: H04L 63/126 the source of the received data
• CPC Class Codes: H04L 63/1408 by monitoring network traffic monitoring network traffic per se H04L43/00

Abstract

Identifying a human or machine is disclosed including sending a currently-triggered human or machine identification request to a server, receiving a first operation rendered by the server in response to the human or machine identification request, the first operation being configured to identify a human or machine and expressing an operation track for identifying the human or machine, and sending a second operation that was triggered in response to the first operation to the server to identify the human or machine on a triggering entity for the second operation based on a behavior characteristic model that was set in advance.

Claims

1. A method, comprising:

in response to a human or machine identification request sent by a client, sending information pertaining to a first operation configured to identify human or machine to the client to be displayed;

receiving a second operation that is submitted by the client, the second operation being triggered in response to an interactive operation performed on an operation track associated with the first operation; and

identifying a triggering entity for the second operation as either a human or a machine based on a behavior characteristic model, wherein the behavior characteristic model includes a classifier for human operations and machine operations, and the classifier is trained based on operation samples.

2. The method as described in claim 1, wherein behavioral characteristic data of the operation samples includes operative slide time length.

3. The method as described in claim 1, wherein behavioral characteristic data of the operation samples includes operative slide time length, the operative slide time length being obtained by determining a total time length of valid operations of the operation samples.

4. The method as described in claim 1, wherein behavioral characteristic data of the behavior characteristic model includes at least one of:

operative slide time length of at least one segment, center line-deviation frequency of at least one segment, and average deviation distance of at least one segment.

5. The method as described in claim 1, wherein:

behavioral characteristic data of the behavior characteristic model includes at least one of;

operative slide time length of at least one segment, center line-deviation frequency of at least one segment, and average deviation distance of at least one segment;

the operative slide time length of the at least one segment is obtained based at least in part on;

dividing a total operation time of the operation samples into a plurality of equal segments; and

calculating a time length of at least one operation segment;

the center line-deviation frequency of the at least one segment is obtained based at least in part on;

dividing the total operation time of the operation samples into a plurality of equal segments; and

calculating a number of deviations from a center axis for at least one operation segment; and

the average deviation distance of the at least one segment is obtained based on;

dividing the total operation time of at least one of the operation samples into a plurality of equal segments; and

calculating a distance of deviations from the center axis for the at least one operation segment.

6. The method as described in claim 1, wherein behavioral characteristic data of the operation samples comprises:

an operation triggering initial position and an operation triggering terminal position.

7. The method as described in claim 1, wherein:

behavioral characteristic data of the operation samples comprises;

operation triggering initial position and operation triggering terminal position; and

the operation triggering initial position and the operation triggering terminal position are obtained based on;

determining coordinates in the event that an operation sample begins to undergo triggering as the operation triggering initial position; and

determining coordinates in the event that the operation sample ceases to undergo triggering as the operation triggering terminal position.

8. The method as described in claim 1, wherein the identifying of the triggering entity for the second operation based on the behavior characteristic model comprises:

extracting to-be-identified behavioral characteristic data of the second operation;

in the event that the to-be-identified behavioral characteristic data conforms to a human operation, determining that the triggering entity of the second operation is human; and

in the event that the to-be-identified behavioral characteristic data conforms to a machine operation, determining that the triggering entity of the second operation is a machine.

9. The method as described in claim 1, further comprising:

after the identifying of the human or machine on the triggering entity for the second operation based on the behavior characteristic model that was set in advance;

in the event that a result of the human or machine identification is a machine, rejecting access requests sent by the machine; and

in the event that the result of the human or machine identification is a human, responding to access requests sent by the human.

10. A device, comprising:

one or more processors; and

one or more memories coupled with the one or more processors, wherein the one or more memories are configured to provide the one or more processors with instructions which when executed cause the one or more processors to;

in response to a human or machine identification request sent by a client, send information pertaining to a first operation configured to identify human or machine to the client to be displayed;

receive a second operation that is submitted by the client, the second operation being triggered in response to an interactive operation performed on an operation track associated with the first operation; and

identify a triggering entity for the second operation as either a human or a machine based on a behavior characteristic model, wherein the behavior characteristic model includes a classifier for human operations and machine operations, and the classifier is trained based on operation samples.

11. The device as described in claim 10, wherein the sending of the information pertaining to the first operation configured to identify human or machine to the client to be displayed comprises to:

extract to-be-identified behavioral characteristic data of the second operation;

determine that the triggering entity of the second operation is human in the event that the to-be-identified behavioral characteristic data conforms to a human operation; and

determine that the triggering entity of the second operation is a machine in the event that the to-be-identified behavioral characteristic data conforms to a machine operation.

12. The device as described in claim 10, wherein the one or more memories are further configured to provide the one or more processors with instructions which when executed cause the one or more processors to:

after the identifying of the triggering entity for the second operation as either human or machine based on the behavior characteristic model;

in the event that a result of the human or machine identification is a machine, reject access requests subsequently sent by the machine; and

in the event that the result of the human or machine identification is a human, respond to access requests subsequently sent by the human.

13. A computer program product being embodied in a tangible non-transitory computer readable storage medium and comprising computer instructions for:

in response to a human or machine identification request sent by a client, sending information pertaining to a first operation configured to identify human or machine to the client to be displayed;

receiving a second operation that is submitted by the client, the second operation being triggered in response to an interactive operation performed on an operation track associated with the first operation; and

identifying a triggering entity for the second operation as either a human or a machine based on a behavior characteristic model, wherein the behavior characteristic model includes a classifier for human operations and machine operations, and the classifier is trained based on operation samples.