WO2019104873A1

WO2019104873A1 - Human-machine input operation identification method, apparatus and device, and readable storage medium

Info

Publication number: WO2019104873A1
Application number: PCT/CN2018/075660
Authority: WO
Inventors: 肖波
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2017-11-29
Filing date: 2018-02-07
Publication date: 2019-06-06
Also published as: CN108022101A

Abstract

A human-machine input operation identification method, apparatus and device and a readable storage medium. The human-machine input operation identification method comprises: when a loan input operation is detected on a mobile terminal, determining on the basis of a built-in coordinate system of the mobile terminal whether the mobile terminal is located within a preset coordinate range (S10); when the mobile terminal is located within the preset coordinate range, obtaining input data corresponding to the loan input operation, taking the input data as target input data and using same (S20); and when the mobile terminal is not located within the preset coordinate range, identifying the input operation corresponding to a loan request as a machine operation behavior (S30). The present invention resolves the technical problem of the difficulty in the identification of a dark industry behavior of gaining loan by cheating due to that a machine operation behavior cannot be effectively identified.

Description

Human-machine input operation identification method, device, device and readable storage medium

This application claims priority to Chinese Patent Application No. 200911234839.1, entitled "Human Machine Input Operation Identification Method, Apparatus, Equipment, and Readable Storage Medium", filed on November 29, 2017, all of which are entitled The content is incorporated into the application by reference.

Technical field

The present application relates to the field of computer application technologies, and in particular, to a human-machine input operation identification method, apparatus, device, and readable storage medium.

Background technique

At present, the long-term and disorderly development of Internet financial behavior has made it possible for the development of “black producers”. The black producers use existing loan platforms such as mobile apps to have weak wind control capabilities and adopt big data online audits. Excavating loopholes or weaknesses in risk control rules, forging and defrauding loans. If the existing microfinance platform is launched at the beginning of the line, it will be attacked by the black producers and the continuous multi-day loan application will occur over 10,000. Therefore, how effective is it? Identifying the black production behavior of fraudulent loans has become a problem for practitioners in the financial industry.

Summary of the invention

The main purpose of the present application is to provide a human-machine input operation identification method, device, device, and readable storage medium, which are intended to solve the problem of black-productive behavior in the prior art that fails to effectively identify the operation behavior of the machine and is difficult to identify fraudulent loans. technical problem.

To achieve the above objective, the present application provides a human-machine input operation identification method, and the human-machine input operation identification method includes:

When the loan input operation is detected on the mobile terminal, determining whether the mobile terminal is within a preset coordinate range based on the built-in coordinate system of the mobile terminal;

When the mobile terminal is in the preset coordinate range, acquiring input data corresponding to the loan input operation, using the input data as the target input data and adopting;

When the mobile terminal is not in the preset coordinate range, the loan request corresponding input operation is recognized as a machine operation behavior.

Optionally, the step of determining, according to the built-in coordinate system of the mobile terminal, whether the mobile terminal is in a preset coordinate range comprises:

Recording, by the angle value array value, the rotation angle of the mobile terminal in different directions, wherein the built-in coordinate system includes an X axis, a Y axis, and a Z axis, wherein the X axis, the Y axis, and the Z axis of the built-in coordinate system are fixed in a fixed manner, The mobile terminal is in the Z-axis direction with the direction perpendicular to the ground, and the rotation direction of the device in the horizontal plane is described by the rotation angle of the mobile terminal along the Z-axis. The mobile terminal is placed on the table, and the direction of the Z-axis is directed from the mobile terminal to the sky. The direction of the X axis is from left to right along the horizontal direction of the screen of the mobile terminal, and the direction of the Y axis is from the lower left corner of the screen to the top of the screen along the vertical direction of the screen, first The angle value, the second angle value, and the third angle value respectively represent the angle of rotation of the mobile terminal about the Z axis, the angle at which the mobile terminal is tilted about the X axis, and the rolling angle of the mobile terminal along the Y axis;

Determining the mobile terminal when the first angle value ranges from 0 to 90o, the second angle value ranges from -180o to 0o, and the third angle value ranges from -45o to 45o It is within the preset coordinate range.

Optionally, the input data includes a contact area of the finger with the touch screen of the mobile terminal, a contact contour of the finger and the touch screen of the mobile terminal, and an input pressure value when the user inputs, the input data corresponding to the loan input operation, and the input data Entering data as a target and taking steps include:

Obtaining input data corresponding to the loan input operation, normalizing the input data, and using the normalized input data as normalized data;

Obtaining a pre-stored BP neural network-based target model, and using the normalized data as an input vector of the target model to obtain an output vector;

When the output vector is within a preset range, the input data is taken as target input data and adopted.

Optionally, the step of acquiring input data corresponding to the loan input operation, and normalizing the input data includes:

Obtaining input data corresponding to the loan input operation, and converting the input data into various parameter values that the computer can recognize;

Obtain the maximum and minimum values of all parameter values, and subtract all the parameter values from the minimum value to obtain a positive parameter value, and obtain the difference between the maximum value and the minimum value, and simultaneously use the positive parameter values The difference is divided to obtain the normalized normalized positive parameter values.

Optionally, the input data includes a time attribute of a loan input operation, the input data corresponding to the loan input operation is obtained, and the input data is used as the target input data, and the adopting steps include:

Obtain a minimum time gap between different loan input operations based on time attributes of different loan input operations;

When the minimum time gap is greater than the first preset time length, the input data corresponding to the loan input operation is acquired, and the input data is used as the target input data and adopted.

Optionally, after the step of acquiring a time gap between different loan input operations, the method includes:

When the minimum time gap is less than the first preset duration, the number of times of the loan input operation in the second preset duration is obtained, where the second preset duration is greater than the first preset duration;

When the number of times the loan input operation is greater than a preset number of times, the input data is discarded.

Optionally, after the step of identifying the loan request corresponding input operation as the machine operation behavior step, when the mobile terminal is not in the preset coordinate range, the method includes:

Acquiring the mobile device ID number corresponding to the operation behavior of the machine, and prohibiting receiving the loan request sent by the mobile terminal corresponding to the ID number within the third preset duration.

In addition, in order to achieve the above object, the present application further provides a human-machine input operation identification device, where the automatic test device includes:

a determining module, configured to determine, according to the built-in coordinate system of the mobile terminal, whether the mobile terminal is in a preset coordinate range when detecting a loan input operation on the mobile terminal;

a first acquiring module, configured to: when the mobile terminal is in a preset coordinate range, acquire input data corresponding to a loan input operation, and use the input data as target input data;

And an identifying module, configured to identify the loan request corresponding input operation as a machine operation behavior when the mobile terminal is not in a preset coordinate range.

Optionally, the first obtaining module includes:

a first acquiring unit, configured to record, by using an angle value array value, a rotation angle of the mobile terminal in different directions, wherein the built-in coordinate system includes an X axis, a Y axis, and a Z axis, wherein the X axis and the Y of the built-in coordinate system The axis and the Z axis are fixed in direction, the mobile terminal is in the Z-axis direction in a direction perpendicular to the ground, and the rotation direction of the device in the horizontal plane is described by the rotation angle of the mobile terminal along the Z-axis, and the mobile terminal is placed on the table, the direction of the Z-axis Pointing from the mobile terminal to the sky, the direction of the X-axis is from left to right along the horizontal direction of the screen of the mobile terminal, and the direction of the Y-axis is pointing from the lower left corner of the screen to the vertical direction of the screen. At the top of the screen, the first angle value, the second angle value, and the third angle value respectively represent the angle at which the mobile terminal rotates about the Z axis, the angle at which the mobile terminal is tilted about the X axis, and the mobile terminal along the Y axis Rolling angle

a judging unit, configured to: when the first angle value ranges from 0 to 90o, the second angle value ranges from -180o to 0o, and the third angle value ranges from -45o to 45o, It is determined that the mobile terminal is within a preset coordinate range.

Optionally, the input data includes a contact area of the finger with the touch screen of the mobile terminal, a contact contour of the finger and the touch screen of the mobile terminal, and an input pressure value, where the first acquisition module includes:

a second acquiring unit, configured to acquire input data corresponding to the loan input operation, normalize the input data, and use the normalized input data as normalized data;

a third acquiring unit, configured to acquire a pre-stored BP neural network-based target model, and use the normalized data as an input vector of the target model to obtain an output vector;

And a first adopting unit, configured to use the input data as a target input data when the output vector is within a preset range.

Optionally, the second obtaining unit includes:

Obtaining a subunit, configured to obtain input data corresponding to the loan input operation, and convert the input data into various parameter values that the computer can recognize;

The normalized subunit is used to obtain the maximum and minimum values of all parameter values, and subtract all the parameter values from the minimum value to obtain a positive parameter value, and obtain the difference between the maximum value and the minimum value. And dividing each positive parameter value by the difference to obtain the normalized normalized positive parameter values.

Optionally, the input data includes a time attribute of a loan input operation, and the first obtaining module includes:

a fourth obtaining unit, configured to acquire a minimum time gap between different loan input operations based on time attributes of different loan input operations;

The second adopting unit is configured to acquire input data corresponding to the loan input operation when the minimum time gap is greater than the first preset time length, and use the input data as the target input data.

Optionally, the first obtaining module further includes:

a fifth acquiring unit, configured to acquire a number of times of the loan input operation in the second preset duration when the minimum time gap is less than the first preset duration, wherein the second preset duration is greater than the first preset duration;

The judging unit is configured to discard the input data when the number of the loan input operations is greater than a preset number of times.

Optionally, the human-machine input operation identification device further includes:

The second obtaining module is configured to obtain the mobile terminal ID number corresponding to the operation behavior of the machine, and prohibit receiving the loan request sent by the mobile terminal corresponding to the ID number within the third preset duration.

In addition, in order to achieve the above object, the present application further provides a human-machine input operation recognition device, where the human-machine input operation recognition device includes: a memory, a processor, a communication bus, and a human-machine input operation identifier stored on the memory. program,

The communication bus is used to implement a communication connection between the processor and the memory;

The processor is configured to execute the human-machine input operation recognition program to implement the following steps:

Moreover, to achieve the above objects, the present application also provides a readable storage medium storing one or more programs, the one or more programs being executable by one or more processors Used for:

The present application determines whether the mobile terminal is within a preset coordinate range based on a built-in coordinate system of the mobile terminal when detecting a loan input operation on the mobile terminal; when the mobile terminal is in a preset coordinate range Obtaining input data corresponding to the loan input operation, using the input data as the target input data and adopting; when the mobile terminal is not in the preset coordinate range, identifying the loan request corresponding input operation as a machine operation behavior. In the present application, it is determined whether the mobile terminal is in a preset coordinate range by using a built-in coordinate system of the mobile terminal, that is, by determining whether the gesture of the mobile phone when the user inputs characters or the like is normal, so as to achieve the purpose of human-machine operation recognition. . Therefore, the technical problem of the black production behavior that is difficult to identify the fraudulent loan due to the failure to effectively identify the operation behavior of the machine in the prior art is solved, and the experience is improved.

DRAWINGS

1 is a schematic flow chart of a first embodiment of an applicant input operation identification method;

2 is a schematic flow chart of a second embodiment of an applicant input operation identification method;

FIG. 3 is a schematic structural diagram of a device in a hardware operating environment involved in a method according to an embodiment of the present application.

The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings.

Detailed ways

It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting.

The present application provides a human-machine input operation identification method. In the first embodiment of the present applicant's input operation identification method, referring to FIG. 1, the human-machine input operation identification method includes:

Step S10: When detecting a loan input operation on the mobile terminal, determining, according to the built-in coordinate system of the mobile terminal, whether the mobile terminal is in a preset coordinate range;

It should be noted that the human-machine input operation identification method of the present embodiment is applied to the loan APP of the mobile terminal, so as to identify the black producer behavior of the bulk application for the loan in the loan APP.

When the loan input operation is detected on the mobile terminal, determining whether the mobile terminal is in a preset coordinate range based on the built-in coordinate system of the mobile terminal, wherein the loan input operation may be a trigger of a loan request, and the loan information Upload, the operation of the loaner's identity, etc. The mobile terminal includes a mobile phone, a tablet, and the like. It should be noted that a built-in coordinate system is disposed inside the mobile terminal, and the built-in coordinate system is generally a three-dimensional coordinate system.

The step S10 includes:

Step S11, recording an angle of rotation of the mobile terminal in different directions by using an array value of angle values, wherein the built-in coordinate system includes an X-axis, a Y-axis, and a Z-axis, wherein the X-axis, the Y-axis, and the Z-axis of the built-in coordinate system Pointing fixed, the mobile terminal is in the Z-axis direction in a direction perpendicular to the ground, and the rotation direction of the device in the horizontal plane is described by the rotation angle of the mobile terminal along the Z-axis, and the mobile terminal is placed on the table, and the direction of the Z-axis is from the mobile terminal. Pointing to the sky, the direction of the X-axis is from left to right along the horizontal direction of the screen of the mobile terminal, and the direction of the Y-axis is from the lower left corner of the screen to the top of the screen along the vertical direction of the screen. The first angle value, the second angle value, and the third angle value respectively represent an angle at which the mobile terminal rotates about the Z axis, an angle at which the mobile terminal is tilted about the X axis, and a rolling angle of the mobile terminal along the Y axis;

In this embodiment, the X-axis Y-axis and the Z-axis of the three-dimensional coordinate system are set in the terminal, and the X-axis, the Y-axis, and the Z-axis of the three-dimensional coordinate system are fixedly oriented, and the terminal is oriented in the Z-axis direction perpendicular to the ground, with the terminal edge. The Z-axis rotation angle is used to describe the direction of rotation of the device in the horizontal plane. The phone is placed on the table. The direction of the Z-axis is from the phone to the sky. The direction of the X-axis is from left to right along the horizontal direction of the screen. The direction is from the lower left corner of the screen to the top of the screen along the vertical direction of the screen. The angle value array value is used to record the rotation angle of the mobile phone in different directions. The first angle value, the second angle value, and the third angle value are angles. The value of the three variables represents the angle of rotation of the mobile phone around the Z axis, the angle of tilt of the mobile phone around the X axis, the angle of the mobile phone along the Y axis, the first angle value ranges from 0 to 360o, and 0o represents north ( North); 90o means East, 180o means South, 270o means West; the second angle value ranges from -180o ≤ second angle ≤180o, starting from the top of the phone ( The screen is placed horizontally downwards On the desktop), until the phone is rotated 180o along the X axis, during this rotation, the second angle value will change from 0o to -180o, that is, the value of the second angle value when lifting from the top of the phone. Will gradually become smaller until it equals -180o. If you lift from the bottom of the phone until the phone is rotated 180o along the X axis, the second angle value will change between 0o and 180o, and the value of the second angle will gradually increase until it equals 180o; the third angle The value range is -90o ≤ third angle value ≤ 90o, assuming the phone screen is placed horizontally on the desktop, then if the desktop is flat, the value of the third angle should be 0. When the left side of the mobile phone is gradually raised, the value of the third angle value gradually becomes smaller until the mobile phone is placed perpendicular to the desktop, and the value of the third angle value is -90o. When the right side of the phone is gradually raised, the value of the third angle value is gradually increased until the phone is placed perpendicular to the desktop, and the value of the third angle value is 90o. Continue to scroll right or left while in the vertical position, and the value of the third angle value will continue to change between -90o and 90o.

Step S12, when the first angle value ranges from 0 to 90o, the second angle value ranges from -180o to 0o, and the third angle value ranges from -45o to 45o, The mobile terminal is in a preset coordinate range.

It should be noted that, when the input operation is performed manually, the posture of the mobile terminal or the coordinate range of the mobile terminal is determined, that is, the mobile terminal is determined to be within the preset coordinate range. In this embodiment, the preset coordinate range is a range in which the loan APP is pre-stored, and the range may be: the first angle value ranges from 0 to 90o, and the second angle value ranges from -180o to 0o, and The value of the third angle is in the range of -45o to 45o, that is, when the range of the first angle value, the second angle value, and the third angle value are simultaneously satisfied, determining that the mobile terminal is in the preset coordinate range If the first angle value, the second angle value, and the third angle value are not in the corresponding range, it is determined that the mobile terminal is not in the preset coordinate range, and further, in the preset determination time Determining whether a value of the first angle value, the second angle value, and the third angle value is sent, and when any one of the first angle value, the second angle value, and the third angle value changes, It is determined that the mobile terminal is within a preset coordinate range. If it is determined that all the values of the first angle value, the second angle value, and the third angle value have not changed during the preset judgment time, it is determined that the mobile terminal is not in the preset coordinate range.

Step S20, when the mobile terminal is in the preset coordinate range, acquire input data corresponding to the loan input operation, and use the input data as the target input data and adopt;

When the mobile terminal is in the preset coordinate range, the input data corresponding to the loan input operation is acquired, and the input data is used as the target input data, wherein the input data of the user includes the touch screen of the finger and the mobile terminal when the user inputs Contact area, contact contour of the finger and the touch screen of the mobile terminal, input pressure value, etc., when the mobile terminal is in the preset coordinate range, acquire input data corresponding to the loan input operation, and use the input data as the target input data and adopt That is, the data is used as human-entered loan data to perform a loan operation process according to the input loan data, wherein the loan operation process.

Step S30: When the mobile terminal is not in the preset coordinate range, identify the loan request corresponding input operation as a machine operation behavior.

And determining, when the mobile terminal is not in the preset coordinate range, the loan request corresponding input operation as a machine operation behavior, or further, when the mobile terminal is not in the preset coordinate range, further determining the first When the value of any one of the angle value, the second angle value, and the third angle value has changed, when the change does not occur, the loan request corresponding input operation is recognized as a machine operation behavior.

Further, the present application provides a second embodiment of a human-machine input operation identification method. In the second embodiment, referring to FIG. 2, the input data includes a contact area of a finger with a touch screen of a mobile terminal, a finger and a mobile terminal when the user inputs. Touching the contact contour of the touch screen and inputting the pressure value, the obtaining the input data corresponding to the loan input operation, and using the input data as the target input data and adopting the steps include:

Step S21: Acquire input data corresponding to the loan input operation, normalize the input data, and use the normalized input data as normalized data;

Wherein, step S21 includes:

Step SA1: acquiring input data corresponding to the loan input operation, and converting the input data into various parameter values that can be recognized by the computer;

After obtaining the input data corresponding to the loan input operation, the input data is further determined to determine whether the input data operation is a machine input behavior or a human input behavior. It should be noted that the acquired user input data further includes the user performing data. The input contact area of the user's finger and the touch screen of the mobile terminal, the contact contour of the finger and the touch screen of the mobile terminal, and the input pressure value are input, and the input data corresponding to the loan input operation is acquired, and the input data of the obtained user is first converted into each computer-recognizable Parameter values are then normalized for each parameter value to convert all data to standard values.

In step SA2, the maximum value and the minimum value of all the parameter values are obtained, and all the parameter values are subtracted from the minimum value to obtain a positive parameter value, and the difference between the maximum value and the minimum value is obtained. The parameter value is simultaneously divided by the difference to obtain the normalized positive parameter values that are normalized.

The process of the normalization process may be to project the respective parameter values generated by the user's input data to between 0-1. The specific process can be divided by a large number, large number = maximum - minimum. The maximum value is the maximum value of all parameter values, and the minimum value is the minimum value of all parameter values. To avoid negative numbers, subtract all the parameter values from the minimum value before multiplying by the large number, and then multiply by the large number. For example, if the obtained parameter values are 100, 10, 20, -1, etc., then the maximum value is 100 and the minimum value is -1. To avoid negative numbers, first subtract the minimum value to get 101, 21, 31. 0. Then divided by 101, the corresponding parameter values are converted to 1, 21/101, 31/101, 0. The normalized processed input data is used as normalized data.

Step S22, acquiring a pre-stored BP neural network-based target model, and using the normalized data as an input vector of the target model to obtain an output vector;

A pre-stored target model based on BP neural network is constructed. The BP neural network model topology includes an input layer, a hidden layer and an output layer. The idea of the BP neural network algorithm is to estimate the error of the direct pre-layer of the output layer by using the error after the output, that is, the error of the actual output and the expected output, and then using this error to estimate the error of the previous layer. Passing on, we obtain error estimates for all other layers. Among them, BP neural network has learning function, and the essence of learning is to dynamically adjust the weight of each factor. Each normalized data is used as an input vector of the target model, and an output vector is obtained based on the input vector of the target model, and based on the output vector, it is determined whether the user data is a normal input operation.

Step S23, when the output vector is within a preset range, the input data is used as target input data and adopted.

When the output vector is within a preset range, the input data is taken as target input data and adopted. The input data is discarded when the output vector is not within the preset range.

In this embodiment, the input data corresponding to the loan input operation is acquired, the input data is normalized, the normalized input data is used as normalized data, and the pre-stored BP neural network is constructed. a target model, the normalized data is used as an input vector of the target model to obtain an output vector; when the output vector is within a preset range, the input data is used as target input data and adopted. Since the input data is further judged by the target model, the accuracy of the human-machine input operation recognition is improved.

Further, the present application provides a third embodiment of a human-machine input operation identification method. In the third embodiment, the input data includes a time attribute of a loan input operation, and the input data corresponding to the loan input operation is acquired. The input data is used as the target input data and the steps taken include:

Step S24: Obtain a minimum time gap between different loan input operations based on time attributes of different loan input operations;

Different time points for different loan input operations are different, and the time attributes of the different loan input operations are different, and a minimum time gap between different loan input operations is obtained, for example, the minimum time gap may be 1 ms, or 2 ms, and the like.

Step S25: When the minimum time gap is greater than the first preset duration, obtain input data corresponding to the loan input operation, and use the input data as the target input data.

When the minimum time gap is greater than the first preset time length, wherein the first preset time length may be 0.5 ms or the like, the input data is used as the target input data, and wherein the time when the machine inputs the data needs to be explained. The gap is greater than the first preset duration.

In this embodiment, a minimum time gap between different loan input operations is obtained by time attributes based on different loan input operations; and when the minimum time gap is greater than the first preset time length, the input data corresponding to the loan input operation is acquired. The input data is used as the target input data and adopted. Since further judgment is made by the minimum time gap, the accuracy of the human-machine input operation recognition is improved.

Further, the present application provides a fourth embodiment of the human-machine input operation identification method. In the fourth embodiment, after the step of acquiring the time gap between different loan input operations, the method includes:

In step S26, when the minimum time gap is less than the first preset duration, the number of times of the loan input operation in the second preset duration is obtained, where the second preset duration is greater than the first preset duration;

When the minimum time gap is less than the first preset duration, the number of times of the loan input operation in the second preset duration is obtained, where the second preset duration is 10S or the like, and the second preset duration is greater than the first preset duration.

Step S27: When the number of times of the loan input operation is greater than a preset number of times, the input data is discarded and not used.

When the number of the loan input operations is greater than the preset number of times, the input data is discarded, and when the number of loan input operations is greater than 20 times, the loan input operation is defaulted to machine input, and the input data is input. Abandonment will not be used.

In this embodiment, when the minimum time gap is less than the first preset duration, the number of times of the loan input operation in the second preset duration is obtained, where the second preset duration is greater than the first preset duration;

When the number of times the loan input operation is greater than a preset number of times, the input data is discarded. This embodiment improves the accuracy of human-machine input operation recognition.

Further, based on the first embodiment of the applicant's input operation identification method, a fifth embodiment of the human-machine input operation identification method is provided. In the fifth embodiment, when the mobile terminal is not in the pre- When the coordinate range is set, the step of identifying the loan request corresponding input operation as a machine operation behavior step includes:

Step S40: Acquire a mobile terminal ID number corresponding to the operation behavior of the machine, and prohibit receiving the loan request sent by the mobile terminal corresponding to the ID number within a third preset duration.

In this embodiment, the machine operation behavior corresponding to the mobile terminal ID number is acquired, and the loan request sent by the mobile terminal corresponding to the ID number is prohibited from being received within the third preset time period, wherein the third preset duration is 1 Month, 1 year or even longer, when the user data is detected as abnormal input data, the terminal ID number corresponding to the abnormal input data is acquired, and an automatic alarm command is generated based on the acquired terminal ID number to implement automatic alarm processing.

In this embodiment, by acquiring the mobile device ID number corresponding to the operation behavior of the machine, the loan request sent by the mobile terminal corresponding to the ID number is prohibited from being received within the third preset time period. In order to prevent the machine from mimicking user behavior from the input source.

Referring to FIG. 3, FIG. 3 is a schematic structural diagram of a device in a hardware operating environment according to an embodiment of the present application.

The human-machine input operation identification device in the embodiment of the present application may be a PC, or may be a smart mobile terminal, a tablet computer, an e-book reader, and an MP3 (Moving Picture). Experts Group Audio Layer III, Motion Picture Expert Compress Standard Audio Level 3) Player, MP4 (Moving Picture Experts Group Audio Layer IV, dynamic imaging experts compress standard audio layers 4) terminal devices such as players and portable computers.

As shown in FIG. 3, the human-machine input operation identification device may include a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to implement connection communication between the processor 1001 and the memory 1005. The memory 1005 may be a high speed RAM memory or a stable memory (non-volatile) Memory), such as disk storage. The memory 1005 can also optionally be a storage device independent of the aforementioned processor 1001.

Optionally, the human-machine input operation identification device may further include a user interface, a network interface, a camera, and an RF (Radio) Frequency, RF) circuits, sensors, audio circuits, WiFi modules, and more. The user interface may include a display, an input unit such as a keyboard, and the optional user interface may also include a standard wired interface, a wireless interface. The network interface can optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

It will be understood by those skilled in the art that the human-machine input operation identification device structure shown in FIG. 3 does not constitute a limitation on the human-machine input operation recognition device, and may include more or less components than those illustrated, or may combine some Parts, or different parts.

As shown in FIG. 3, an operating system, a network communication module, and a human-machine input operation recognition program may be included in the memory 1005 as a computer storage medium. The operating system is a program that manages and controls the human-machine input operation to identify the hardware and software resources of the device, and supports the operation of the human-machine input operation recognition program and other software and/or programs. The network communication module is used to implement communication between components within the memory 1005 and to communicate with other hardware and software in the human input operation recognition device.

In the human-machine input operation identification device shown in FIG. 3, the processor 1001 is configured to execute the human-machine input operation recognition program stored in the memory 1005, and implement the following steps:

Further, the step of determining whether the mobile terminal is in a preset coordinate range based on the built-in coordinate system of the mobile terminal includes:

Further, the input data includes a contact area of the finger with the touch screen of the mobile terminal when the user inputs, a contact contour of the finger and the touch screen of the mobile terminal, and an input pressure value, and the input data corresponding to the loan input operation is acquired, and the input data is used as The target input data and the adoption steps include:

Further, the step of acquiring input data corresponding to the loan input operation, and normalizing the input data includes:

Further, the input data includes a time attribute of a loan input operation, the input data corresponding to the loan input operation is obtained, and the input data is used as the target input data, and the adopting steps include:

Further, after the step of acquiring the time gap between different loan input operations, the method includes:

Further, after the step of identifying the loan request corresponding input operation as the machine operation behavior step, when the mobile terminal is not in the preset coordinate range, the method includes:

The embodiment of the applicant's input operation and identification device is basically the same as the embodiment of the above-mentioned human-machine input operation identification method, and details are not described herein again.

The present application provides a readable storage medium storing one or more programs, the one or more programs being further executable by one or more processors for implementing the above The steps of the human-machine input operation identification method described.

The specific embodiment of the readable storage medium of the present application is substantially the same as the embodiment of the above-described human-machine input operation identification method, and details are not described herein again.

The above is only a preferred embodiment of the present application, and is not intended to limit the scope of the patent application, and the equivalent structure or equivalent process transformations made by the specification and the drawings of the present application, or directly or indirectly applied to other related technical fields. The same is included in the scope of patent processing of this application.

Claims

A human-machine input operation recognition method, wherein the human-machine input operation recognition method comprises:

When the loan input operation is detected on the mobile terminal, determining whether the mobile terminal is within a preset coordinate range based on the built-in coordinate system of the mobile terminal;

When the mobile terminal is in the preset coordinate range, acquiring input data corresponding to the loan input operation, using the input data as the target input data and adopting;

When the mobile terminal is not in the preset coordinate range, the loan request corresponding input operation is recognized as a machine operation behavior.
The human-machine input operation identification method according to claim 1, wherein the step of determining whether the mobile terminal is in a preset coordinate range based on the built-in coordinate system of the mobile terminal comprises:

Recording, by the angle value array value, the rotation angle of the mobile terminal in different directions, wherein the built-in coordinate system includes an X axis, a Y axis, and a Z axis, wherein the X axis, the Y axis, and the Z axis of the built-in coordinate system are fixed in a fixed manner, The mobile terminal is in the Z-axis direction with the direction perpendicular to the ground, and the rotation direction of the device in the horizontal plane is described by the rotation angle of the mobile terminal along the Z-axis. The mobile terminal is placed on the table, and the direction of the Z-axis is directed from the mobile terminal to the sky. The direction of the X axis is from left to right along the horizontal direction of the screen of the mobile terminal, and the direction of the Y axis is from the lower left corner of the screen to the top of the screen along the vertical direction of the screen, first The angle value, the second angle value, and the third angle value respectively represent the angle of rotation of the mobile terminal about the Z axis, the angle at which the mobile terminal is tilted about the X axis, and the rolling angle of the mobile terminal along the Y axis;

Determining the mobile terminal when the first angle value ranges from 0 to 90o, the second angle value ranges from -180o to 0o, and the third angle value ranges from -45o to 45o It is within the preset coordinate range.
The human-machine input operation recognition method according to claim 1, wherein the input data includes a contact area of the finger with the touch screen of the mobile terminal, a contact contour of the finger and the touch screen of the mobile terminal, and an input pressure value when the user inputs.

The obtaining the input data corresponding to the loan input operation, using the input data as the target input data, and adopting the steps include:

Obtaining input data corresponding to the loan input operation, normalizing the input data, and using the normalized input data as normalized data;

Obtaining a pre-stored BP neural network-based target model, and using the normalized data as an input vector of the target model to obtain an output vector;

When the output vector is within a preset range, the input data is taken as target input data and adopted.
The human-machine input operation identification method according to claim 3, wherein the obtaining input data corresponding to the loan input operation, and the normalizing the input data comprises:

Obtaining input data corresponding to the loan input operation, and converting the input data into various parameter values that the computer can recognize;

Obtain the maximum and minimum values of all parameter values, and subtract all the parameter values from the minimum value to obtain a positive parameter value, and obtain the difference between the maximum value and the minimum value, and simultaneously use the positive parameter values The difference is divided to obtain the normalized normalized positive parameter values.
The human-machine input operation recognizing method according to claim 1, wherein the input data includes a time attribute of a loan input operation, the input data corresponding to the loan input operation is acquired, and the input data is used as a target input data. And the steps taken include:

Obtain a minimum time gap between different loan input operations based on time attributes of different loan input operations;

When the minimum time gap is greater than the first preset time length, the input data corresponding to the loan input operation is acquired, and the input data is used as the target input data and adopted.
The human-machine input operation identification method according to claim 5, wherein the step of acquiring a time gap between different loan input operations comprises:

When the minimum time gap is less than the first preset duration, the number of times of the loan input operation in the second preset duration is obtained, where the second preset duration is greater than the first preset duration;

When the number of times the loan input operation is greater than a preset number of times, the input data is discarded.
The human-machine input operation identifying method according to claim 1, wherein the step of identifying the loan request corresponding input operation as a machine operation behavior step when the mobile terminal is not in a preset coordinate range After that:

Acquiring the mobile device ID number corresponding to the operation behavior of the machine, and prohibiting receiving the loan request sent by the mobile terminal corresponding to the ID number within the third preset duration.
A human-machine input operation recognition device, wherein the human-machine input operation recognition device comprises:

a determining module, configured to determine, according to the built-in coordinate system of the mobile terminal, whether the mobile terminal is in a preset coordinate range when detecting a loan input operation on the mobile terminal;

a first acquiring module, configured to: when the mobile terminal is in a preset coordinate range, acquire input data corresponding to a loan input operation, and use the input data as target input data;

And an identifying module, configured to identify the loan request corresponding input operation as a machine operation behavior when the mobile terminal is not in a preset coordinate range.
A human-machine input operation recognition device, wherein the human-machine input operation recognition device comprises: a memory, a processor, a communication bus, and a human-machine input operation recognition program stored on the memory,

The communication bus is used to implement a communication connection between the processor and the memory;

The processor is configured to execute the human-machine input operation recognition program to implement the steps of the human-machine input operation recognition method according to claim 1.
A human-machine input operation recognition device, wherein the human-machine input operation recognition device comprises: a memory, a processor, a communication bus, and a human-machine input operation recognition program stored on the memory,

The communication bus is used to implement a communication connection between the processor and the memory;

The processor is configured to execute the human-machine input operation recognition program to implement the steps of the human-machine input operation identification method according to claim 2.
A human-machine input operation recognition device, wherein the human-machine input operation recognition device comprises: a memory, a processor, a communication bus, and a human-machine input operation recognition program stored on the memory,

The communication bus is used to implement a communication connection between the processor and the memory;

The processor is configured to execute the human-machine input operation recognition program to implement the steps of the human-machine input operation identification method according to claim 3.
A human-machine input operation recognition device, wherein the human-machine input operation recognition device comprises: a memory, a processor, a communication bus, and a human-machine input operation recognition program stored on the memory,

The communication bus is used to implement a communication connection between the processor and the memory;

The processor is configured to execute the human-machine input operation recognition program to implement the steps of the human-machine input operation recognition method according to claim 4.
A human-machine input operation recognition device, wherein the human-machine input operation recognition device comprises: a memory, a processor, a communication bus, and a human-machine input operation recognition program stored on the memory,

The communication bus is used to implement a communication connection between the processor and the memory;

The processor is configured to execute the human-machine input operation recognition program to implement the steps of the human-machine input operation recognition method according to claim 5.
A readable storage medium, wherein the readable storage medium stores a man-machine input operation recognition program, and the human-machine input operation recognition program is executed by a processor to implement the human-machine input according to claim 1. The steps to operate the identification method.
A readable storage medium, wherein the readable storage medium stores a man-machine input operation recognition program, and the human-machine input operation recognition program is executed by a processor to implement the human-machine input according to claim 2. The steps to operate the identification method.
A readable storage medium, wherein the readable storage medium stores a man-machine input operation recognition program, and the human-machine input operation recognition program is executed by a processor to implement the human-machine input according to claim 3. The steps to operate the identification method.
A readable storage medium, wherein the readable storage medium stores a man-machine input operation recognition program, and the human-machine input operation recognition program is executed by a processor to implement the human-machine input according to claim 4. The steps to operate the identification method.
A readable storage medium, wherein the readable storage medium stores a man-machine input operation recognition program, and the human-machine input operation recognition program is executed by a processor to implement the human-machine input according to claim 5. The steps to operate the identification method.
A readable storage medium, wherein the readable storage medium stores a man-machine input operation recognition program, and the human-machine input operation recognition program is executed by a processor to implement the human-machine input according to claim 6. The steps to operate the identification method.