CN109426714B

CN109426714B - Method and device for detecting person changing and method and device for verifying user identity

Info

Publication number: CN109426714B
Application number: CN201710766078.8A
Authority: CN
Inventors: 曾岳伟
Original assignee: Advanced New Technologies Co Ltd
Current assignee: Advanced New Technologies Co Ltd; Advantageous New Technologies Co Ltd
Priority date: 2017-08-30
Filing date: 2017-08-30
Publication date: 2022-04-19
Anticipated expiration: 2037-08-30
Also published as: CN109426714A

Abstract

The embodiment of the application provides a method and a device for detecting a person change and a method and a device for verifying a user identity, wherein the method for detecting the person change comprises the following steps: acquiring a first execution parameter of an action executor executing a specific action; and determining whether the action performers performing the specific action are the same person according to the first performance parameter of the specific action. The method and the device for detecting the person changing and the method and the device for verifying the user identity provided by the embodiment of the application can be applied to the field of user identity verification, and the user identity is verified based on the execution parameters of the specific action.

Description

Method and device for detecting person changing and method and device for verifying user identity

Technical Field

The present application relates to the field of authentication, and in particular, to a method and an apparatus for detecting a change of a person, and a method and an apparatus for authenticating a user.

Background

In order to ensure the security of network operation, a user needs to authenticate before performing certain specific operations in the internet, for example, before performing purchase payment operations by the user using the internet, the user needs to authenticate.

In order to improve the accuracy of identity authentication, living body detection may be performed on a user, for example, the user is required to perform some authentication actions, so as to determine that an object to be authenticated is a living body, rather than a non-living body such as a video or a picture. In the living body detection process, if different users alternately complete the verification action specified by the server side, for example, different users alternately complete the hand swinging action specified by the server side, an attack is caused to the user authentication, and the accuracy of the authentication is reduced.

Therefore, it is necessary to provide a method for detecting whether the verification action is performed by the same executor, so as to improve the attack resistance of the user authentication and improve the accuracy of the authentication.

Disclosure of Invention

The embodiment of the application aims to provide a method and a device for detecting a person change and a method and a device for verifying a user identity, which can determine whether a specific action is executed and completed by the same executor or not according to an execution parameter of the specific action, thereby improving the attack resistance of the user identity verification and the accuracy of the identity verification.

In order to solve the above technical problem, the embodiment of the present application is implemented as follows:

the embodiment of the application provides a method for detecting the change of people, which comprises the following steps:

acquiring a first execution parameter of an action executor executing a specific action;

and determining whether the action performers performing the specific action are the same person according to the first performance parameter of the specific action.

The embodiment of the application provides a user identity authentication method, which comprises the following steps:

acquiring video data of a user to be verified for executing a specific action;

determining a first execution parameter of the user to be verified for executing the specific action according to the acquired video data;

and according to the first execution parameter of the user to be verified for executing the specific action and the historical execution parameter of the user to be verified for executing the specific action, performing identity verification on the user to be verified.

The embodiment of the application provides a detection device trades people, includes:

the parameter acquisition module is used for acquiring a first execution parameter of the action executor for executing the specific action;

and the person changing detection module is used for determining whether the action executors executing the specific action are the same person or not according to the first execution parameter of the specific action.

The embodiment of the application provides a user authentication device, which comprises:

the data acquisition module is used for acquiring video data of a user to be verified for executing a specific action;

the parameter determining module is used for determining a first execution parameter of the user to be verified for executing the specific action according to the acquired video data;

and the identity authentication module is used for authenticating the identity of the user to be authenticated according to the first execution parameter of the user to be authenticated for executing the specific action and the historical execution parameter of the user to be authenticated for executing the specific action.

The embodiment of the application provides a detection equipment trades people, includes:

a processor; and

a memory arranged to store computer executable instructions that, when executed, cause the processor to:

An embodiment of the present application provides a user authentication device, including:

a processor; and

acquiring video data of a user to be verified for executing a specific action;

Embodiments of the present application provide a storage medium for storing computer-executable instructions, which when executed implement the following processes:

acquiring video data of a user to be verified for executing a specific action;

By the method and the device for detecting the person changing and the method and the device for verifying the user identity, whether the specific action is executed by the same executor can be determined according to the first execution parameter for executing the specific action, and the identity of the user to be verified can be verified according to the first execution parameter for executing the specific action by the user to be verified and the historical execution parameter for executing the specific action by the user to be verified, so that the attack resistance of the user identity verification is improved and the accuracy of the identity verification is improved based on the characteristic that the execution parameter for executing the specific action is difficult to imitate.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

Fig. 1 is a schematic view of a scene of a human exchange detection and a user identity verification provided in an embodiment of the present application;

FIG. 2 is a schematic flow chart of a first method for detecting a human exchange according to an embodiment of the present disclosure;

fig. 3a is a schematic diagram of video data provided by an embodiment of the present application;

FIG. 3b is a schematic diagram of video data corresponding to each identified specific action performed according to an embodiment of the present application;

fig. 4 is a schematic diagram of a training process of the recognition model provided in this embodiment;

FIG. 5 is a diagram illustrating calculation of a first execution parameter for a particular action;

FIG. 6 is a second flowchart of a human exchange detection method according to an embodiment of the present disclosure;

FIG. 7 is a third schematic flow chart illustrating a method for detecting a human exchange according to an embodiment of the present disclosure;

fig. 8 is a first flowchart of a user identity authentication method according to an embodiment of the present application;

fig. 9 is a schematic flowchart of a second method for authenticating a user according to an embodiment of the present application;

FIG. 10 is a schematic diagram illustrating a first module of a human exchange detection apparatus according to an embodiment of the present application;

FIG. 11 is a schematic diagram illustrating a second module of the human exchange detection apparatus according to the embodiment of the present application;

fig. 12 is a schematic block diagram illustrating a user authentication apparatus according to an embodiment of the present disclosure;

FIG. 13 is a schematic structural diagram of a human exchange detection apparatus according to an embodiment of the present application;

fig. 14 is a schematic structural diagram of a user authentication device according to an embodiment of the present application.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The embodiment of the application provides a method and a device for detecting a person changing and a method and a device for verifying a user identity, which can determine whether a specific action is executed and completed by the same executor according to an execution parameter of the specific action, thereby improving the attack resistance of the user identity verification and the accuracy of the identity verification.

Fig. 1 is a schematic view of a scene of the human exchange detection and the user identity verification provided in the embodiment of the present application, and the human exchange detection method and apparatus, the user identity verification method and apparatus provided in the embodiment of the present application may be applied to the scene shown in fig. 1. As shown in fig. 1, the scenario includes at least one client 100 and a server 200, and the client 100 is operated by a user and is communicatively connected to the server 200 through a network 300.

The client 100 may be a mobile phone, a tablet computer, a desktop computer, a portable notebook computer, a vehicle-mounted computer, etc. The client 100 may run the program module and send data to the server 200, such as the client 100 running a camera module and sending the captured image or video to the server 200, such as sending the captured action video of a user performing a specific action to the server 200.

The server 200 may be a physical server comprising independent hosts, or a virtual server carried by a cluster of hosts, or a cloud server. The server 200 may process the data uploaded by the client 100, for example, the server 200 receives an action video of a user performing a specific action uploaded by the client 100, processes the action video, determines whether the specific action is performed by the same user, and performs authentication on the user by the server 200.

The network 300 may include various types of wired or wireless networks. For example, Network 300 may include the Public Switched Telephone Network (PSTN) and the Internet.

Fig. 2 is a first flowchart of a method for detecting a human exchange according to an embodiment of the present application, where the method may be executed by a server, and as shown in fig. 2, the method at least includes the following steps:

in step S202, a first execution parameter of the action executor executing the specific action is obtained.

The specific action may be an action that is indicated to be performed by the action performer, or may be an action that is performed autonomously by the action performer. For example, in an authentication scenario, a particular action is an action that is indicative of an action performed by an action performer. The specific motion includes any one of blinking, shaking, and waving. The first performance parameter for performing the particular action may include one or more of a frequency parameter, a velocity parameter, and a magnitude parameter. If the particular action is a blink, the first performance parameters to perform the particular action may include one or more of a frequency parameter, a velocity parameter, a magnitude parameter at the time of the blink.

According to different application scenarios, the first execution parameter of the specific action may be an execution parameter for executing the specific action at the current time, or an execution parameter for executing the specific action before the current time. Taking an application scenario of performing authentication on a user as an example, the situations may include field authentication, authentication according to a previously acquired video, and the like. If the user is subjected to field identity authentication, the execution parameters of the user currently executing the specific action need to be acquired. And if the identity authentication is carried out according to the previously acquired video, extracting the execution parameters according to the video of which the user performs the specific action.

And step S204, determining whether the action performers performing the specific action are the same person according to the first performance parameter of the specific action.

The server determines the variance of first execution parameters for executing the specific action each time, the first execution parameters are in one-to-one correspondence with one execution process of the specific action, one specific action is executed corresponding to one first execution parameter, and if the variance of the first execution parameters is smaller than a corresponding set threshold value, the action executors for executing the specific action are determined to be the same person.

Since the first execution parameter may include one or more of a frequency parameter, a speed parameter, and a magnitude parameter, the server determines a variance of each corresponding item of the plurality of first execution parameters, for example, the first execution parameter may include a frequency parameter and a magnitude parameter, the server determines a variance of the frequency parameter and a variance of the magnitude parameter of the plurality of first execution parameters, and determines whether the variance of the frequency parameter is smaller than a corresponding set threshold, and whether the variance of the magnitude parameter is smaller than a corresponding set threshold, if both are smaller, the variance of the first execution parameter is determined to be smaller than the corresponding set threshold, the action performers performing the specific action are determined to be the same person, and if the variance of any corresponding item (e.g., the frequency parameter item) is equal to or greater than the corresponding set threshold, the action performers performing the specific action are determined not to be the same person.

For example, the server obtains first execution parameters for executing a specific action each time, and 3 first execution parameters in total, where each first execution parameter corresponds to executing a specific action once, and each first execution parameter includes a speed parameter v, a frequency parameter f, and an amplitude parameter d, for example, the first execution parameter 1 includes a speed parameter v1, a frequency parameter f1, and an amplitude parameter d1, the first execution parameter 2 includes a speed parameter v2, a frequency parameter f2, and an amplitude parameter d2, the first execution parameter 3 includes a speed parameter v3, a frequency parameter f3, and an amplitude parameter d3, the server extracts the first execution parameter 1, the first execution parameter 2, a speed parameter item, a frequency parameter item, and an amplitude parameter item in the first execution parameter 3, and forms a speed parameter item sequence (v1, v2, v3), a frequency parameter item sequence (f1, f2, f3), an amplitude parameter item sequence (d 1), d2, d 3). The server judges whether the variance of the speed parameter item sequences (v1, v2 and v3) is smaller than the corresponding set threshold value, judges whether the variance of the frequency parameter item sequences (f1, f2 and f3) is smaller than the corresponding set threshold value, judges whether the variance of the amplitude parameter item sequences (d1, d2 and d3) is smaller than the corresponding set threshold value, and if the variances are smaller than the set threshold values, the action performers who perform the specific action are determined to be the same person. And if the variance of a certain parameter item sequence is not less than the corresponding set threshold, determining that the action performers performing the specific action are not the same person.

In this embodiment, the setting threshold corresponding to the frequency parameter, the setting threshold corresponding to the speed parameter, and the setting threshold corresponding to the amplitude parameter may be the same or different. Since the variance may reflect the fluctuation of a set of data, by calculating the variance of the first execution parameter each time a specific action is executed, it is possible to determine whether the execution state is stable during the execution of the specific action a plurality of times, thereby determining whether the action performers who perform the specific action are the same person.

In one case, if the first execution parameters of each specific action executed twice are obtained, the difference between the two first execution parameters may also be calculated, and if the difference between each corresponding item is smaller than the respective predetermined difference, it is determined that the action performers who execute the specific action are the same person, otherwise, it is determined that the action performers who execute the specific action are not the same person.

The method for detecting the person change in the embodiment of the application obtains a first execution parameter of an action executor executing a specific action, and determines whether the action executor executing the specific action is the same person or not according to the first execution parameter of the specific action. Therefore, by the method for detecting the person changing in the embodiment of the application, whether the specific action is executed by the same executor or not can be determined, so that whether the users performing living body detection are the same user or not can be identified when the method is applied to a user identity verification scene, the attack resistance of user identity verification is improved, and the accuracy of identity verification is improved.

In step S202, the first execution parameter for the action executor to execute the specific action may be: acquiring video data of a specific action executed by an action executor; identifying the video data by utilizing an identification model corresponding to the specific action so as to determine the time and the amplitude of each specific action executed by the action executor; and determining the first execution parameter of each execution of the specific action by the action performer according to the time and the amplitude of each execution of the specific action by the action performer. Since the specific action is manually executed, each execution process of the specific action is slightly different, and therefore the first execution parameter of each execution of the specific action by the action executor is unique.

Specifically, the client prompts the action performer to perform a specific action and shoots an action video of the action performer performing the specific action, such as shooting a blink video when the action performer blinks, the client sends the action video of the action performer performing the specific action to the server, and the server acquires video data of the action performer performing the specific action according to the action video of the action performer performing the specific action.

Specifically, the action video is composed of a plurality of continuous video frames, each frame has a respective identifier, and each frame carries a magnitude of a specific action performed by the action performer, such as a blinking magnitude or a hand-waving magnitude of the user. After the server acquires the action video, a first corresponding relation between each frame of video frame in the action video and the amplitude of the specific action can be determined, or determining a second correspondence between key video frames in the motion video and the amplitude of the particular motion, the server determining video data from the first correspondence or the second correspondence, the video data may indicate a time to perform the particular motion and the amplitude of performing the particular motion, in one case, the video data comprises the identification of each frame of video frame and the amplitude of the specific action corresponding to each frame of video frame, the time corresponding to each frame of video frame is indicated by the identification of each frame of video frame, and therefore, the time for executing the specific action is indicated, and in another case, the video data comprises the time stamp of each frame of video frame and the amplitude of the specific action corresponding to each frame of video frame, and the time for executing the specific action is indicated by the time stamp of each frame of video frame. It should be noted that, determining the key video frame is a common method in the field of video processing, and the method for determining the key video frame from the motion video is not limited in this embodiment, and various algorithms for determining the key video frame are within the scope of this embodiment.

Fig. 3a is a schematic diagram of video data provided in an embodiment of the present application, in fig. 3a, a horizontal axis indicates an identifier of each frame of video frames, which may be a sequence number of each frame of video frames, an arrangement order of the sequence numbers of each video frame is consistent with a time stamp order of each video frame, and a vertical axis indicates an amplitude of a specific action in each frame of video frames, which may be floating point data, and has a value range of (0,1), and a corresponding relationship between a plurality of frames of video frames in an action video and the amplitude of the specific action can be reflected by fig. 3 a.

The server acquires video data of a specific action executed by an action executor, and then identifies the video data by using an identification model corresponding to the specific action to determine the time and amplitude of the specific action executed by the action executor each time.

In this embodiment, an identification model is trained, and the identification model corresponds to a specific action one by one, and can identify whether input video data corresponds to an entire execution cycle of the specific action, that is, whether the input video data is the entire video data for executing the specific action once. Based on the foregoing description about video data, video data may represent the amplitude of the specific action performed corresponding to each frame of video frame, therefore, in this embodiment, starting from the starting video frame of the specific action, video data of a predetermined number of video frames in the video data is extracted and input to the recognition model, if the recognition model determines that the input video data corresponds to a complete execution cycle, the input video data is marked, and starting from the last frame of video frame corresponding to the input video data, video data of a predetermined number of video frames after extraction is input to the recognition model in the time sequence of the video data for continuing recognition, otherwise, if the recognition model determines that the input video data does not correspond to a complete execution cycle, the server starts from the last frame of video frame corresponding to the input video data and continues recognition in the time sequence of the video data, and extracting video data of a certain number of video frames, forming new input video data together with the input video data, inputting the new input video data into the identification model, so that the identification model continuously judges whether the new input video data corresponds to a complete execution cycle, repeating the steps, and identifying in the video data by utilizing the identification model to obtain the video data corresponding to each execution of a specific action.

For example, the server extracts video data corresponding to a first frame and a second frame from the video data, inputs the video data into the identification model, if the identification model determines that the video data corresponding to the first frame and the second frame are complete video data for executing a specific action, the server continues to extract the video data corresponding to a third frame and a fourth frame from the video data, and inputs the video data into the identification model for continuing identification, otherwise, if the identification model determines that the video data corresponding to the first frame and the second frame are not complete video data for executing a specific action, the server extracts the video data corresponding to the third frame and the fourth frame again, and inputs the video data corresponding to the first frame to the fourth frame into the identification model for identification.

Fig. 4 is a schematic diagram of a training process of the recognition model provided in this embodiment, and as shown in fig. 4, the process includes:

in step S402, positive and negative samples are collected.

Selecting a plurality of segments of video data segmented according to the execution period of the specific action as positive samples, wherein each segment of video data represents the corresponding relation between a plurality of frames of video frames in one execution period of the specific action and the amplitude of the specific action, and selecting a plurality of segments of video data or irregular video data which are not segmented according to the execution period of the specific action as negative samples.

Step S404, training the model by using the positive and negative samples.

And inputting enough positive and negative samples into the machine learning model for model training to obtain a trained model.

Step S406, detecting whether the trained model meets the test requirement, if so, executing step S408, otherwise, returning to step S404.

And detecting whether the trained model meets the test requirements, if so, carrying out recognition test on the trained model, judging whether the false recognition rate and the recognition rejection rate of the recognition result meet the preset requirements, if so, determining that the model training is finished, otherwise, returning to the step S404 for re-training.

Step S408, model training is completed.

In a specific embodiment, an adaboost general machine training method may be used to perform model training to obtain a recognition model.

Fig. 3b is a schematic diagram of video data corresponding to each identified specific action, which is executed each time according to the embodiment of the present application, where the horizontal and vertical axes of fig. 3b have the same meaning as fig. 3a, and as shown in fig. 3b, after the video data in fig. 3a is identified by using an identification model, multiple segments of video data are obtained, each segment of video data corresponds to a specific action, and each segment of video data represents a corresponding relationship between multiple frames of video frames and the amplitude of the specific action within one execution period of the specific action.

After identifying the video data corresponding to each execution of the specific action, since the video data can indicate the time of executing the specific action and the amplitude of executing the specific action, such as the time of executing the specific action indicated by the identifier or the timestamp of the video frame, the server determines the time of executing the specific action and the amplitude of executing the specific action, which are indicated by the video data corresponding to each execution of the specific action, as the time and the amplitude of executing the specific action, and can understand that the time and the amplitude of executing the specific action are the time of each frame of video frame and the amplitude of executing the specific action carried by each frame of video frame.

The server determines a first execution parameter of each execution of the specific action according to the time and the amplitude of each execution of the specific action, specifically one or more of the following three ways:

(1) determining a frequency parameter of each execution of the specific action according to the starting time and the ending time of each execution of the specific action; and,

(2) determining an amplitude parameter of each specific action according to the maximum amplitude and the minimum amplitude of each specific action; and,

(3) and determining a speed parameter of each execution of the specific action according to the starting time and the ending time of each execution of the specific action.

The frequency parameter is the reciprocal of the difference between the ending time and the starting time, the speed parameter is the difference between the ending time and the starting time, and the amplitude parameter is the difference between the maximum amplitude and the minimum amplitude of each specific action.

In this embodiment, determining the first execution parameter includes one or more of a frequency parameter, a speed parameter, and an amplitude parameter, which has the advantages of convenient parameter acquisition, easy implementation, and high parameter accuracy.

When the specific action is blinking, the execution cycle includes a closed eye process and an open eye process. The amplitude of the specific action performed in the video data, i.e. the blink amplitude, may be a ratio of eyes to a contour of a human face in the action video, e.g. a ratio of a height of the eyes to a height of the human face, and the amplitude parameter of the specific action may be a difference between a maximum blink amplitude and a minimum blink amplitude in one execution period.

When the specific motion is a panning motion, the execution cycle includes a process of panning the head from the current position and panning back to the current position. The amplitude of the specific action performed in the video data, i.e. the panning amplitude, may be a ratio of a moving distance of a vertical line in the face in the action video to a contour of the face, e.g. a ratio of a moving distance of a vertical line in the face to a width of the face, and the amplitude parameter of the specific action may be a difference between a maximum panning amplitude and a minimum panning amplitude in one execution period.

When the specific motion is a hand swing, the execution cycle includes a process in which the hand swings from the current position and back to the current position. The amplitude of the specific action performed in the video data, that is, the hand swing amplitude, may be a ratio of a moving distance of a hand in the action video to a face contour, for example, a ratio of a moving distance of a hand to a face width, and the amplitude parameter of the specific action may be a difference between a maximum hand swing amplitude and a minimum hand swing amplitude in one execution period.

Fig. 5 is a schematic diagram of calculating a first execution parameter of a specific action, fig. 5 illustrates a process of calculating the first execution parameter of the specific action in an execution period according to a correspondence relationship between a plurality of video frames of the specific action and a magnitude of the specific action in the execution period, taking a blinking action as an example, in fig. 5, a horizontal axis represents a sequence number of each video frame in the execution period, an arrangement order of the sequence numbers of each video frame is consistent with a time stamp order of each video frame, and a vertical axis represents a blinking magnitude corresponding to each video frame. In fig. 5, the maximum blink amplitude is m and the minimum blink amplitude is n in a certain execution period, so the amplitude parameter of the specific action in the execution period is determined to be m-n, the timestamp of the first frame of video frame in the execution period is p, the timestamp of the last frame of video frame in the execution period is q, so the speed parameter of the specific action in the execution period is determined to be q-p, and the frequency parameter of the specific action in the execution period is 1/(q-p).

Fig. 6 is a schematic flowchart of a second process of the human exchange detection method provided in the embodiment of the present application, where the process may be executed by a server, as shown in fig. 6, and the process includes:

in step S602, an action video of the action performer performing a specific action is acquired.

And step S604, determining video data of the action performer performing the specific action according to the action video.

In step S606, the video data corresponding to each execution of the specific motion is identified in the video data by using the identification model corresponding to the specific motion.

Step S608, determining the time and amplitude of each specific action according to the time and amplitude of each specific action, which is indicated by the video data corresponding to each specific action.

Step S610, determining an amplitude parameter and a frequency parameter for each execution of the specific action according to the time and the amplitude for each execution of the specific action.

Step S612, determining whether the variance of the plurality of amplitude parameters is smaller than the corresponding set threshold, if so, performing step S614, otherwise, performing step S618.

In step S614, it is determined whether the variance of the plurality of frequency parameters is smaller than the corresponding set threshold, if so, step S616 is executed, otherwise, step S618 is executed.

In step S616, it is determined that the action performers performing the specific action are the same person.

In step S618, it is determined that the action performers performing the specific action are not the same person.

By the method in the flow, the variance among the plurality of first execution parameters can be calculated, so that whether the action executors executing the specific actions are the same person or not can be determined. Based on the variance among the plurality of first execution parameters, the smoothness of the specific action execution process can be reflected, so that whether the action performers performing the specific action are the same person or not can be accurately determined.

In view of a situation that an action executor is a to-be-authenticated user needing to perform identity authentication, this embodiment further provides a method for detecting a human exchange, fig. 7 is a schematic diagram of a third flow of the method for detecting a human exchange provided in this embodiment of the present application, where the flow may be executed by a server, as shown in fig. 7, after acquiring, in step S202, a first execution parameter of a specific action executed by the action executor (i.e., the to-be-authenticated user), the process further includes:

step S702, obtaining the historical execution parameters of the user to be verified to execute the specific action.

In this embodiment, the historical execution parameters may be obtained by obtaining the video data of the specific action, and stored after obtaining, so as to be used in the user authentication later. Taking a certain user a as an example, historical execution parameters of the user a for executing a specific action, including frequency, amplitude and other related parameters capable of reflecting the habit and the characteristic of the user a for executing the specific action, may be stored in advance, and then it may be determined whether an action executor executing the specific action is the user a himself or herself according to the historical execution parameters of the user a.

In the step, the historical execution parameters of the specific action executed by the user to be verified each time are acquired by calling the pre-stored historical execution parameters of the specific action. Similar to the foregoing, the historical performance parameters may include one or more of a speed parameter, a frequency parameter, and an amplitude parameter.

In step S704, if the first execution parameter matches the historical execution parameter, it is determined that the user to be verified passes the verification.

And if the variance between the first execution parameter and the historical execution parameter is smaller than the corresponding set threshold, determining that the user to be verified passes the verification.

The variance between the first execution parameter and the historical execution parameter refers to the variance of corresponding items in the first execution parameter and the historical execution parameter, if the variance of each corresponding item is smaller than a corresponding set threshold value, the user to be verified is determined to pass the verification, and if the variance of one corresponding item is not smaller than the corresponding set threshold value, the user to be verified is determined to not pass the verification. The set threshold values corresponding to the variances of the corresponding items may be the same or different.

For example, the server obtains 3 first execution parameters and also obtains 3 historical execution parameters, where each historical execution parameter and each first execution parameter correspond to an execution process of a specific action, and the server extracts speed parameter items, frequency parameter items and amplitude parameter items in the first execution parameter 1, the first execution parameter 2, the first execution parameter 3, the historical execution parameter 1, the historical execution parameter 2 and the historical execution parameter 3 respectively to form a speed parameter item sequence, a frequency parameter item sequence and an amplitude parameter item sequence. The server judges whether the variance of the speed parameter item sequence is smaller than the corresponding set threshold value, judges whether the variance of the frequency parameter item sequence is smaller than the corresponding set threshold value, judges whether the variance of the amplitude parameter item sequence is smaller than the corresponding set threshold value, and determines that the user to be verified passes the verification if the variances of the amplitude parameter item sequence and the set threshold value are smaller than the corresponding set threshold value. If the variance of a certain parameter item sequence (such as a frequency parameter item) is not smaller than the corresponding set threshold, determining that the user to be verified is not verified.

The variance can reflect the fluctuation condition of a group of data, so that whether the state of executing a specific action is stable can be reflected by calculating the variance between the first execution parameter and the historical execution parameter, if the variance between the first execution parameter and the historical execution parameter is smaller than the corresponding set threshold value, the action executor corresponding to the first execution parameter and the action executor corresponding to the historical execution parameter can be considered as the same person, and the user to be verified is determined to be verified.

If a first execution parameter for executing a specific action and a historical execution parameter for executing the specific action are obtained, difference values of corresponding items in the first execution parameter and the historical execution parameter can be respectively calculated, if the difference value of each corresponding item is smaller than a corresponding difference threshold value, an action executor corresponding to the first execution parameter and an action executor corresponding to the historical execution parameter are determined to be the same person, the user to be verified is determined to pass the verification, and if the difference value of a certain corresponding item is equal to or larger than the corresponding difference threshold value, the user to be verified is determined not to pass the verification.

By the method in the embodiment, after the first execution parameter of the specific action executed by the action executor each time is acquired, whether the action executor executing the specific action is the same person or not can be determined, and after the first execution parameter of the specific action executed by the action executor and the historical execution parameter of the specific action executed by the action executor are acquired, the identity of the action executor can be verified, so that the attack resistance of user identity verification is improved, and the accuracy of identity verification is improved.

In view of the fact that the method for detecting a person change in the present embodiment can be applied to the field of user authentication, this embodiment also provides a method for user authentication, fig. 8 is a schematic diagram of a first process of the method for user authentication provided in the embodiment of the present application, where the process may be executed by a server, as shown in fig. 8, and the process includes the following steps:

step S802, an action video of a user to be verified executing a specific action is obtained.

Specifically, the client prompts the user to be verified to execute a specific action, shoots an action video of the user to be verified to execute the specific action, such as shooting a blink video when the user to be verified blinks, and sends the shot action video to the server, so that the server obtains the action video of the user to be verified to execute the specific action.

Step S804, determining a first execution parameter for the user to be verified to execute the specific action according to the acquired video data.

Specifically, video data is identified by using an identification model corresponding to a specific action so as to determine the time and amplitude of each specific action executed by a user to be verified; and determining a first execution parameter of the user to be verified for executing the specific action each time according to the time and the amplitude of the user to be verified for executing the specific action each time. The specific process of this step may refer to the description of step S202, which is not described herein.

Step 806, according to the first execution parameter of the user to be verified executing the specific action and the historical execution parameter of the user to be verified executing the specific action, performing identity verification on the user to be verified. Wherein, the historical execution parameters can be stored in advance and called when needed.

Specifically, the server calculates the variance of the first execution parameter of each specific action executed by the user to be verified, determines whether the variance of the first execution parameter of each specific action executed by the user to be verified is smaller than a corresponding set threshold, determines whether the first execution parameter of each specific action executed by the user to be verified is matched with the historical execution parameter of each specific action executed by the user to be verified, and determines that the user to be verified passes the verification if the variance of the first execution parameter of each specific action executed by the user to be verified is smaller than the corresponding set threshold and the first execution parameter of each specific action executed by the user to be verified is matched with the historical execution parameter of each specific action executed by the user to be verified, otherwise, determines that the user to be verified fails the verification.

The server determines whether the variance of the first execution parameter of the user to be verified executing the specific action each time is smaller than the corresponding set threshold, and determines whether the first execution parameter of the user to be verified executing the specific action matches the historical execution parameter of the user to be verified executing the specific action.

The variance of the first execution parameter of the user to be verified executing the specific action each time is smaller than the corresponding set threshold, which indicates that the action executors executing the specific action each time are the same person, and the first execution parameter of the user to be verified executing the specific action is matched with the historical execution parameter of the user to be verified executing the specific action, which indicates that the user to be verified is the historical user corresponding to the historical execution parameter.

In the embodiment of the application, the server can also send the authentication result to the client so that the user to be authenticated can obtain the authentication result.

In consideration of various ways of verifying the identity of the user, the identity verification result of the user to be verified obtained in step S806 may be used as one of the decision information for determining the identity of the user to be verified, and cooperate with other decision information for determining the identity of the user to be verified to jointly determine the identity of the user to be verified.

The user identity authentication method in the embodiment of the application obtains video data of a user to be authenticated for executing a specific action, determines a first execution parameter of the user to be authenticated for executing the specific action according to the obtained video data, and performs identity authentication on the user to be authenticated according to the first execution parameter of the user to be authenticated for executing the specific action and a historical execution parameter of the user to be authenticated for executing the specific action. By the user identity authentication method in the embodiment of the application, the identity of the user to be authenticated can be authenticated according to the first execution parameter of the specific action and the historical execution parameter of the user to be authenticated for executing the specific action, so that the attack resistance of the user identity authentication is improved and the accuracy of the identity authentication is improved based on the characteristic that the execution parameter for executing the specific action is difficult to imitate.

Fig. 9 is a schematic flowchart of a second flow of a user identity authentication method according to an embodiment of the present application, where as shown in fig. 9, the flow may be executed by a server, and the flow includes:

step S902, obtaining an action video of an action executor executing a specific action;

step S904, determining video data of the user to be verified for executing the specific action according to the action video;

step S906, determining a first execution parameter of the user to be verified for executing the specific action according to the determined video data;

step S908, determining whether the variance of the first execution parameter of each specific action executed by the user to be verified is smaller than the corresponding set threshold;

if so, go to step S910, otherwise go to step S914.

Step S910, judging whether the first execution parameter of the user to be verified executing the specific action is matched with the historical execution parameter of the user to be verified executing the specific action;

if so, go to step S912, otherwise go to step S914.

In step S912, the user identity is verified.

In step S914, the user authentication is not passed.

Without limiting the execution sequence of step S908 and step S910, it may be determined whether the variance of the first execution parameter is smaller than the corresponding set threshold, or whether the first execution parameter and the historical execution parameter match.

Through the embodiment, the condition that no person is changed in the process of executing the specific action can be ensured, and the person executing the specific action is the user to be verified, so that the user is subjected to double identity authentication, and the reliability of the identity authentication of the user is ensured.

Corresponding to the above-mentioned method for detecting a person change, an embodiment of the present application further provides a device for detecting a person change, fig. 10 is a schematic view of a first module composition of the device for detecting a person change provided by the embodiment of the present application, and as shown in fig. 10, the device includes:

a parameter obtaining module 1001, configured to obtain a first execution parameter of an action executor executing a specific action;

the human exchange detection module 1002 is configured to determine whether an action executor executing the specific action is the same person according to the first execution parameter of the specific action.

Optionally, the parameter obtaining module 1001 is specifically configured to,

acquiring video data of the action executor executing the specific action;

identifying the video data using an identification model corresponding to the particular action to determine a time and a magnitude for each performance of the particular action;

determining a first execution parameter for each execution of the particular action based on a time and a magnitude for each execution of the particular action.

Optionally, the parameter obtaining module 1001 is further specifically configured to,

identifying, in the video data, video data corresponding to each execution of the specific action by using an identification model corresponding to the specific action, the video data indicating a time and a magnitude of the execution of the specific action;

and determining the time and amplitude of each execution of the specific action according to the video data corresponding to each execution of the specific action.

Optionally, the parameter obtaining module 1001 is also specifically adapted to one or more of the following ways,

determining a frequency parameter of each execution of the specific action according to the starting time and the ending time of each execution of the specific action; and,

determining a speed parameter of each execution of the specific action according to the starting time and the ending time of each execution of the specific action; and,

and determining the amplitude parameter of each execution of the specific action according to the maximum amplitude and the minimum amplitude of each execution of the specific action.

Alternatively, the people-change detection module 1002 is specifically configured to,

determining a variance of a first execution parameter for each execution of the particular action;

and if the variance of the first execution parameter is smaller than the corresponding set threshold, determining that the action executors executing the specific action are the same person.

The person-changing detection device in the embodiment of the application acquires a first execution parameter of an action executor executing a specific action, and determines whether the action executor executing the specific action is the same person or not according to the first execution parameter of the specific action. Therefore, the person-changing detection device in the embodiment of the application can determine whether the specific action is executed by the same executor or not, and can identify whether the users performing living body detection are the same user or not when being applied to the user identity verification scene, so that the attack resistance of the user identity verification is improved, and the accuracy of the identity verification is improved.

Fig. 11 is a schematic diagram illustrating a second module composition of the human exchange detection apparatus according to the embodiment of the present application, and as shown in fig. 11, the action executor is a to-be-authenticated user who needs to perform identity authentication; the device also includes:

a history parameter obtaining module 1101, configured to obtain a history execution parameter of the user to be verified executing the specific action;

a user identity authentication module 1102, configured to determine that the user to be authenticated passes authentication if the first execution parameter matches the historical execution parameter.

Optionally, the user identity verification module 1102 is specifically configured to determine that the user to be verified passes verification if the variance between the first execution parameter and the historical execution parameter is smaller than a corresponding set threshold.

Optionally, the specific action is an action that indicates the action performer to perform.

Optionally, the specific motion comprises any one of blinking, shaking, and waving.

By the device in the embodiment, after the first execution parameter of the specific action executed by the action executor each time is acquired, whether the action executor executing the specific action is the same person or not can be determined, and after the first execution parameter of the specific action executed by the action executor and the historical execution parameter of the specific action executed by the action executor are acquired, the identity of the action executor can be verified, so that the attack resistance of user identity verification is improved, and the accuracy of identity verification is improved.

Corresponding to the above-mentioned user authentication method, an embodiment of the present application further provides a user authentication apparatus, fig. 12 is a schematic diagram of module composition of the user authentication apparatus provided in the embodiment of the present application, and as shown in fig. 12, the apparatus includes:

a data obtaining module 1201, configured to obtain video data of a user to be authenticated performing a specific action;

a parameter determining module 1202, configured to determine, according to the obtained video data, a first execution parameter for the user to be authenticated to execute the specific action;

an identity verification module 1203, configured to perform identity verification on the user to be verified according to the first execution parameter of the user to be verified executing the specific action and the historical execution parameter of the user to be verified executing the specific action.

Optionally, the parameter determining module 1202 is specifically configured to identify the video data by using an identification model corresponding to the specific action, so as to determine a time and a magnitude of each time the user to be authenticated performs the specific action;

and determining a first execution parameter of the user to be verified for executing the specific action each time according to the time and the amplitude of the user to be verified for executing the specific action each time.

Optionally, the identity verification module 1203 is specifically configured to determine that the user to be verified passes the verification if a variance of a first execution parameter of the user to be verified, which executes the specific action each time, is smaller than a corresponding set threshold, and the first execution parameter of the user to be verified, which executes the specific action, matches with a historical execution parameter of the user to be verified, which executes the specific action.

The user identity authentication device in the embodiment of the application acquires video data of a user to be authenticated for executing a specific action, determines a first execution parameter of the user to be authenticated for executing the specific action according to the acquired video data, and performs identity authentication on the user to be authenticated according to the first execution parameter of the user to be authenticated for executing the specific action and a historical execution parameter of the user to be authenticated for executing the specific action. By the user identity authentication device in the embodiment of the application, the identity of the user to be authenticated can be authenticated according to the first execution parameter of the specific action and the historical execution parameter of the user to be authenticated for executing the specific action, so that the attack resistance of the user identity authentication is improved and the accuracy of the identity authentication is improved based on the characteristic that the execution parameter for executing the specific action is difficult to imitate.

Corresponding to the above-mentioned method for detecting a person change, an embodiment of the present application further provides a device for detecting a person change, and fig. 13 is a schematic structural diagram of the device for detecting a person change provided in the embodiment of the present application.

As shown in fig. 13, the people-change detection apparatus may have a relatively large difference due to different configurations or performances, and may include one or more processors 1301 and a memory 1302, where the memory 1302 may store one or more stored applications or data. Memory 1302 may be, among other things, transient or persistent storage. The application program stored in memory 1302 may include one or more modules (not shown), each of which may include a series of computer-executable instructions in the swap person detection device. Still further, processor 1301 may be configured to communicate with memory 1302 to execute a series of computer-executable instructions in memory 1302 on the people change detection apparatus. The people change detection apparatus may also include one or more power supplies 1303, one or more wired or wireless network interfaces 1304, one or more input-output interfaces 1305, one or more keyboards 1306, and the like.

In a particular embodiment, a people-change detection apparatus includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions in a people-change detection apparatus, and the one or more programs configured to be executed by one or more processors include computer-executable instructions for:

Optionally, the computer executable instructions, when executed, obtain a first execution parameter for the action performer to perform the particular action, comprising:

acquiring video data of the action executor executing the specific action;

Optionally, the computer-executable instructions, when executed, identify the video data using an identification model corresponding to the particular action to determine a time and a magnitude for each performance of the particular action, comprising:

Optionally, the computer executable instructions, when executed, determine a first execution parameter for each execution of the particular action based on a time and a magnitude of each execution of the particular action, including one or more of:

Optionally, the computer-executable instructions, when executed, determine whether an action performer performing the specific action is the same person according to the first performance parameter of the specific action, including:

Optionally, when the computer executable instruction is executed, the action executor is a to-be-authenticated user needing identity authentication; the method further comprises the following steps:

acquiring historical execution parameters of the user to be verified for executing the specific action;

and if the first execution parameter is matched with the historical execution parameter, determining that the user to be verified passes the verification.

Optionally, when executed, the determining that the user to be authenticated is authenticated if the first execution parameter matches the historical execution parameter includes:

By the aid of the equipment in the embodiment, after the first execution parameter of the action executor executing the specific action each time is acquired, whether the action executor executing the specific action is the same person or not can be determined, and after the first execution parameter of the action executor executing the specific action and the historical execution parameter of the action executor executing the specific action are acquired, the action executor can be subjected to identity verification, so that the attack resistance of user identity verification is improved, and the accuracy of identity verification is improved.

Corresponding to the user identity authentication method, an embodiment of the present application further provides a user identity authentication device, and fig. 14 is a schematic structural diagram of the user identity authentication device provided in the embodiment of the present application.

As shown in fig. 14, the user authentication apparatus may have a large difference due to different configurations or performances, and may include one or more processors 1401 and a memory 1402, and one or more stored applications or data may be stored in the memory 1402. Memory 1402 may be, among other things, transient storage or persistent storage. The application stored in memory 1402 may include one or more modules (not shown), each of which may include a series of computer-executable instructions for authenticating a user in a device. Still further, the processor 1401 may be arranged in communication with the memory 1402, and execute a series of computer executable instructions in the memory 1402 on the user authentication device. The user authentication apparatus may also include one or more power sources 1403, one or more wired or wireless network interfaces 1404, one or more input-output interfaces 1405, one or more keyboards 1406, and the like.

In one particular embodiment, a user authentication apparatus includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the user authentication apparatus, and the one or more programs configured to be executed by one or more processors include computer-executable instructions for:

acquiring video data of a user to be verified for executing a specific action;

Optionally, when executed, the computer-executable instructions determine, according to the obtained video data, a first execution parameter for the user to be authenticated to execute the specific action, including:

identifying the video data by using an identification model corresponding to the specific action so as to determine the time and the amplitude of each specific action executed by the user to be verified;

Optionally, when executed, the computer-executable instructions perform authentication on the user to be authenticated according to the first execution parameter of the user to be authenticated executing the specific action and the historical execution parameter of the user to be authenticated executing the specific action, including:

and if the variance of the first execution parameter of the specific action executed by the user to be verified each time is smaller than the corresponding set threshold, and the first execution parameter of the specific action executed by the user to be verified is matched with the historical execution parameter of the specific action executed by the user to be verified, determining that the user to be verified passes verification.

The user identity authentication device in the embodiment of the application acquires video data of a user to be authenticated for executing a specific action, determines a first execution parameter of the user to be authenticated for executing the specific action according to the acquired video data, and performs identity authentication on the user to be authenticated according to the first execution parameter of the user to be authenticated for executing the specific action and a historical execution parameter of the user to be authenticated for executing the specific action. Through the user identity authentication device in the embodiment of the application, the identity of the user to be authenticated can be authenticated according to the first execution parameter of the specific action and the historical execution parameter of the user to be authenticated for executing the specific action, so that the attack resistance of the user identity authentication is improved and the accuracy of the identity authentication is improved based on the characteristic that the execution parameter for executing the specific action is difficult to imitate.

Based on the above method for detecting a person change, an embodiment of the present application further provides a storage medium, which is used to store computer-executable instructions, and in a specific embodiment, the storage medium may be a usb disk, an optical disk, a hard disk, and the like, and when the computer-executable instructions stored in the storage medium are executed by a processor, the following processes can be implemented:

acquiring video data of the action executor executing the specific action;

The storage medium in the embodiment of the application acquires a first execution parameter of the action executor executing the specific action, and determines whether the action executor executing the specific action is the same person according to the first execution parameter of the specific action. Therefore, the storage medium in the embodiment of the application can determine whether the specific action is executed by the same executor or not, so that whether the users performing living body detection are the same user or not can be identified when the storage medium is applied to a user identity verification scene, the attack resistance of user identity verification is improved, and the accuracy of identity verification is improved.

Through the storage medium in the embodiment, after the first execution parameter of the action executor executing the specific action each time is acquired, whether the action executor executing the specific action is the same person or not can be determined, and after the first execution parameter of the action executor executing the specific action and the historical execution parameter of the action executor executing the specific action are acquired, the identity of the action executor can be verified, so that the attack resistance of the user identity verification is improved, and the accuracy of the identity verification is improved.

Based on the user identity authentication method, an embodiment of the present application further provides a storage medium for storing computer-executable instructions, and in a specific embodiment, the storage medium may be a usb disk, an optical disk, a hard disk, and the like, and when the computer-executable instructions stored in the storage medium are executed by a processor, the following processes may be implemented:

acquiring video data of a user to be verified for executing a specific action;

The storage medium in the embodiment of the application acquires video data of a user to be verified for executing a specific action, determines a first execution parameter of the user to be verified for executing the specific action according to the acquired video data, and performs identity verification on the user to be verified according to the first execution parameter of the user to be verified for executing the specific action and a historical execution parameter of the user to be verified for executing the specific action. By the storage medium in the embodiment of the application, the identity of the user to be authenticated can be authenticated according to the first execution parameter of the specific action and the historical execution parameter of the user to be authenticated for executing the specific action, so that the attack resistance of the user identity authentication is improved and the accuracy of the identity authentication is improved based on the characteristic that the execution parameter for executing the specific action is difficult to imitate.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method of detecting a person change, comprising:

determining whether the action performers performing the specific action are the same person according to the first performance parameter of the specific action;

wherein, the determining whether the action performers performing the specific action are the same person according to the first performance parameter of the specific action includes:

determining a variance of a first execution parameter for each execution of the particular action; if the variance of the first execution parameter is smaller than the corresponding set threshold, determining that the action executors executing the specific action are the same person; or,

acquiring historical execution parameters of the action executor executing the specific action; and if the first execution parameter is matched with the historical execution parameter, determining that the action executor passes identity verification, and determining that the action executor executing the specific action is the same person.

2. The method of claim 1, obtaining a first execution parameter for an action performer to perform a particular action, comprising:

acquiring video data of the action executor executing the specific action;

3. The method of claim 2, identifying the video data using an identification model corresponding to the particular action to determine a time and magnitude of each performance of the particular action, comprising:

4. The method of claim 2, determining first performance parameters for each performance of the particular action based on a time and magnitude for each performance of the particular action, comprising one or more of:

5. The method of any of claims 1-4, wherein determining that the action performer is authenticated if the first performance parameter matches the historical performance parameter comprises:

and if the variance between the first execution parameter and the historical execution parameter is smaller than the corresponding set threshold, determining that the action executor passes the verification.

6. The method of any of claims 1 to 4, the particular action being an action that is indicative of the action performer performing.

7. The method of any of claims 1 to 4, wherein the specific action comprises any of blinking, shaking, waving.

8. A method of user authentication, comprising:

acquiring video data of a user to be verified for executing a specific action;

determining whether an action executor executing the specific action is the same person or not according to a first execution parameter of the to-be-verified user executing the specific action and a historical execution parameter of the to-be-verified user executing the specific action, and performing identity verification on the to-be-verified user;

according to the first execution parameter of the user to be verified for executing the specific action and the historical execution parameter of the user to be verified for executing the specific action, the identity verification of the user to be verified comprises the following steps:

9. The method of claim 8, wherein determining, according to the acquired video data, a first execution parameter for the user to be authenticated to execute the specific action comprises:

10. A changer detection device comprising:

the person changing detection module is used for determining whether the action executors executing the specific action are the same person or not according to the first execution parameter of the specific action;

wherein, the people changing detection module is used for:

11. A user authentication apparatus comprising:

the identity authentication module is used for determining whether an action executor executing the specific action is the same person or not according to a first execution parameter of the user to be authenticated for executing the specific action and a historical execution parameter of the user to be authenticated for executing the specific action, and authenticating the identity of the user to be authenticated;

the identity authentication module is configured to determine that the user to be authenticated passes authentication if a variance of a first execution parameter of the user to be authenticated, which executes the specific action each time, is smaller than a corresponding set threshold, and the first execution parameter of the user to be authenticated, which executes the specific action, matches a historical execution parameter of the user to be authenticated, which executes the specific action.

12. An exchange detection apparatus comprising:

a processor; and

13. A user authentication apparatus comprising:

a processor; and

acquiring video data of a user to be verified for executing a specific action;

14. A storage medium storing computer-executable instructions that when executed implement the following:

15. A storage medium storing computer-executable instructions that when executed implement the following:

acquiring video data of a user to be verified for executing a specific action;