CN111125670B

CN111125670B - Sliding track man-machine recognition method and device, electronic equipment and storage medium

Info

Publication number: CN111125670B
Application number: CN201911303764.7A
Authority: CN
Inventors: 徐祥智
Original assignee: Midea Group Co Ltd
Current assignee: Midea Group Co Ltd
Priority date: 2019-12-17
Filing date: 2019-12-17
Publication date: 2022-03-01
Anticipated expiration: 2039-12-17
Also published as: CN111125670A

Abstract

The invention relates to the technical field of computers, and provides a sliding track man-machine identification method, a sliding track man-machine identification device, electronic equipment and a storage medium, wherein the method comprises the following steps: respectively generating corresponding vertical lines for all sliding lines generated at the same time interval in the sliding operation process; and determining a human-computer recognition result of the sliding track formed by the sliding lines according to the distribution condition of the vertical lines corresponding to the sliding lines respectively. The distribution situation of each vertical line generated in the sliding operation process can reflect the stability situation of the sliding operation in the sliding operation process, and the stability situation of the sliding operation can accurately reflect the possibility that the sliding operation is operated by a machine, so that the embodiment of the invention can determine the processing mode of the human-machine recognition result of the sliding operation according to the distribution situation of the vertical lines respectively corresponding to each sliding line generated in the sliding process, and can more accurately determine whether the sliding track is operated by the machine.

Description

Sliding track man-machine recognition method and device, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of computers, in particular to a sliding track man-machine identification method and device, electronic equipment and a storage medium.

Background

With the development of internet technology, a website or a system bears more and more information of users or enterprises, and if the website or the system does not take preventive measures for the access of lawless persons, network security risks exist, and economic losses of the users or the enterprises are possibly caused.

The sliding verification code is used as a security authentication technology, is convenient for users to understand and use, is widely applied to man-machine authentication, can realize identity authentication of a visitor through a network, and prevents lawbreakers from accessing websites or systems. Meanwhile, the sliding verification code meets the requirement of identity security verification, and is also focused by attackers, and various attack tools developed to simulate human behaviors begin to challenge the security of the sliding verification code.

An attacker can generate human-like trajectory batch operations through an attack tool to bypass detection, and continuously upgrade his forged data during the countermeasure process to continuously bypass the same upgraded detection techniques. Therefore, in the technical countermeasures with both sides being upgraded, it is important how to take advantage of countermeasures with the attack tools of the attacker. In view of the above problems in the related art, no effective solution has been proposed at present.

The above information disclosed in this background section is only for enhancement of understanding of the background of the disclosure and therefore it may contain information that does not constitute prior art that is already known to a person of ordinary skill in the art.

Disclosure of Invention

The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a sliding track man-machine recognition method which can accurately determine whether the sliding operation is machine operation.

The invention also provides a sliding track man-machine recognition device.

The invention also provides the intelligent equipment.

The invention also provides the electronic equipment.

The invention also provides a non-transitory computer readable storage medium.

According to one embodiment of the invention, the sliding track man-machine identification method comprises the following steps:

respectively generating corresponding vertical lines for all sliding lines generated at the same time interval in the sliding operation process;

and determining a human-computer recognition result of the sliding track formed by the sliding lines according to the distribution condition of the vertical lines corresponding to the sliding lines respectively.

According to the sliding track man-machine recognition method provided by the embodiment of the invention, the distribution situation of each vertical line generated in the sliding operation process can reflect the stability situation of the sliding operation in the sliding operation process, and the stability situation of the sliding operation can accurately reflect the possibility that the sliding operation is operated as a machine, so that the embodiment of the invention can determine the processing mode of the sliding operation man-machine recognition result according to the distribution situation of the vertical lines respectively corresponding to each sliding line generated in the sliding process, and can more accurately determine whether the sliding track is operated as the machine.

According to an embodiment of the present invention, the determining, according to the distribution of the vertical lines corresponding to the sliding lines, a result of human-computer recognition of the sliding trajectory formed by the sliding lines specifically includes:

determining a human-computer recognition result of a sliding track consisting of sliding lines according to one or more of the total number of the vertical lines, the distance between the vertical lines and the length of the vertical lines;

wherein the length of each vertical line is related to the sliding pressure of the sliding operation in the corresponding time period.

According to an embodiment of the present invention, the determining, according to one or more of the total number of the vertical lines, the distance between the vertical lines, and the length of the vertical lines, a result of human-computer recognition of the sliding trajectory composed of the sliding lines specifically includes:

and determining a human-computer recognition result of the sliding track formed by the sliding lines according to the area distribution condition of a quadrangle formed by four end points of every two adjacent vertical lines.

and determining a man-machine recognition result of the sliding track consisting of the sliding lines according to one or more of the total number of the vertical lines, the distribution of the distances between the adjacent vertical lines and the distribution of the lengths of the vertical lines.

According to an embodiment of the present invention, the determining, according to one or more of the total number of the vertical lines, the distribution of the distances between adjacent vertical lines, and the distribution of the lengths of the vertical lines, a result of human-computer recognition of a sliding trajectory composed of sliding lines specifically includes:

determining a human-machine recognition result of a sliding track formed by sliding lines according to one or more of the first machine recognition index, the second machine recognition index and the third machine recognition index;

wherein the determining process of the first machine identification index, the second machine identification index and the third machine identification index comprises:

determining the total number of each vertical line as a first number, and determining a first machine identification index according to the first number and the matching result of each subinterval in the first interval set;

determining the number equal to the first numerical value in the distances between every two adjacent vertical lines as a second number, determining a second machine identification index according to the matching result of the second number and each subinterval in the second interval set, or determining the difference between the distances between every two adjacent vertical lines, and determining a second machine identification index according to the matching result of the sum of the differences and each subinterval in the third interval set;

determining the number of the lengths of the vertical lines, which is equal to the second numerical value, as a third number, and determining a third machine identification index according to the matching result of the third number and each subinterval in the fourth interval set, or determining the difference value of the lengths of every two adjacent vertical lines, and determining a third machine identification index according to the matching result of the sum of the difference values and each subinterval in the fifth interval set;

wherein the first numerical value is the value with the highest frequency of occurrence in each distance; the second value is the value with the highest frequency of occurrence in each length; each subinterval in the first interval set is determined according to the total length of the sliding operation and the speed distribution statistic of the artificial sliding operation; each subinterval in the second interval set, each subinterval in the third interval set, each subinterval in the fourth interval set, and each subinterval in the fifth interval set is determined according to the number of time periods included in a sliding operation process.

According to an embodiment of the present invention, the determining, according to one or more of the first machine identification index, the second machine identification index, and the third machine identification index, a result of human-machine identification of a sliding trajectory formed by sliding lines specifically includes:

determining the man-machine recognition result of the sliding track consisting of all sliding lines according to a first relation model, wherein the first relation model is Index k₁*a*Index₁+k₂*b*Index₂+k₃*c*Index₃；

If the condition that Index is not less than Q is determined to be met, determining that the human-computer recognition result of the sliding track formed by the sliding lines is machine operation, otherwise, determining that the human-computer recognition result of the sliding track formed by the sliding lines is human operation;

wherein Index represents a human-machine recognition result Index of the sliding track, Index₁Representing a first machine-identification Index, Index₂Indicating a second machine identification Index, Index₃Represents a third machine identification index, a, b, and c represent weights of the first to third machine identification indexes, respectively, and a + b + c is 1; k is a radical of₁、k₂And k₃Participation control factors respectively representing the first to third machine identification indexes, the corresponding participation control factor being 1 when the corresponding machine identification index participates in the identification control, and 0 when the corresponding machine identification index does not participate in the identification control, wherein k is₁、k₂And k₃At least one value of the preset identification threshold value is 1, and the value of the preset identification threshold value Q is related to the number of machine identification indexes participating in identification control and the value of the machine identification indexes participating in identification control.

According to an embodiment of the present invention, the sliding track human-computer recognition method further includes:

determining the straightness of a sliding track consisting of all sliding lines;

correspondingly, the determining, according to the distribution of the vertical lines corresponding to the sliding lines, the human-computer recognition result of the sliding trajectory formed by the sliding lines specifically includes:

and determining the human-computer recognition result of the sliding track formed by the sliding lines according to the straightness of the sliding track formed by the sliding lines and the distribution of the vertical lines corresponding to the sliding lines respectively.

According to an embodiment of the present invention, the determining the human-computer recognition result of the sliding trajectory composed of the sliding lines according to the straightness of the sliding trajectory composed of the sliding lines and the distribution of the vertical lines corresponding to the sliding lines includes:

determining a first human-machine identification index of the sliding track formed by the sliding lines according to the straightness of the sliding track formed by the sliding lines;

determining a second human-machine recognition index of a sliding track formed by the sliding lines according to the distribution condition of the vertical lines corresponding to the sliding lines;

determining an identifier of the intelligent device corresponding to the sliding operation, and determining a human-computer recognition threshold corresponding to the intelligent device according to the identifier of the intelligent device;

determining a human-computer recognition result of the sliding operation according to a comparison result of the sum of the first human-computer recognition index and the second human-computer recognition index and the human-computer recognition threshold;

and the human-computer identification threshold value is obtained by continuously adjusting the values of the historical first human-computer identification index and the historical second human-computer identification index corresponding to the intelligent equipment.

It is to be understood that additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.

Drawings

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

Fig. 1 is a flowchart of a sliding track human-machine identification method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a sliding authentication code according to an embodiment of the present invention;

FIGS. 3 and 4 are a set of schematic diagrams comparing sliding tracks provided by an embodiment of the present invention;

FIGS. 5 and 6 are schematic diagrams of another set of comparative sliding tracks provided by an embodiment of the present invention;

FIGS. 7, 8 and 9 are schematic diagrams of a further group comparison of sliding tracks provided by an embodiment of the present invention;

FIG. 10 is another schematic diagram of a sliding authentication code according to an embodiment of the present invention;

fig. 11 is a schematic structural diagram of a sliding track human-machine recognition device according to an embodiment of the present invention;

fig. 12 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. 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 invention.

The method for identifying the sliding operation man-machine provided by the embodiment of the invention can be used in sliding operation scenes such as mouse sliding, touch pad sliding or pressure-sensitive equipment sliding, and the like, and the method is not limited in the embodiment of the invention.

Fig. 1 shows a flowchart of a sliding track human-machine identification method according to an embodiment of the present invention, and referring to fig. 1, the sliding track human-machine identification method according to the embodiment of the present invention includes:

step 101: respectively generating corresponding vertical lines for all sliding lines generated at the same time interval in the sliding operation process;

in this step, it should be noted that the human-machine recognition of the sliding track may be an explicit verification operation, for example, as shown in fig. 2, a sliding bar appears to perform a sliding operation of sliding the verification code. Furthermore, the human-machine recognition of the sliding trajectory can also be an implicit verification operation. For example, a detection flow may be inserted into the daily operation of the user, and for example, whether the sliding operation that generates the sliding track, such as screen pull-down, page turning, etc., is a human operation or a machine operation may be detected.

In this step, it should be noted that, during the sliding operation, corresponding perpendicular lines are generated for the sliding lines generated during the period of time at the same time interval (for example, 0.01, 0.02, 0.05 seconds). It should be noted that the interval time needs to be the same for the same trace.

As shown in fig. 3, during the sliding operation of the sliding verification code, a section of sliding line is generated at the same time interval, and accordingly, each section of sliding line is generated, a corresponding perpendicular line is generated for the generated sliding line (for example, the first perpendicular line is L1, and the following lines are L2, L3, L4, L5, and the like in sequence), and an intersection point (also called a foot) of each perpendicular line and the sliding line generated in the corresponding time period is an end point of the sliding line generated in the corresponding time period.

In this step, the perpendicular line refers to a perpendicular line perpendicular to the sliding line generated in each time period. That is, the angle between the perpendicular line and the sliding line generated in the corresponding time period is 90 °. It should be noted that, since the interval time period is small, and is generally less than 0.06 second, the slide line generated in one time period can be regarded as a straight line regardless of whether the entire slide trajectory is a straight line or a curved line, and therefore, a perpendicular line perpendicular to the slide line can be made. In this step, the length of the perpendicular line is related to the sliding pressure of the sliding operation in the corresponding period, and the larger the pressure, the longer the length of the perpendicular line, and the smaller the pressure, the shorter the length of the perpendicular line. As shown in fig. 3, when the corresponding vertical lines are respectively generated for the sliding lines generated at the same time period, the vertical lines may be simultaneously generated upward and downward with the end point of the sliding line generated at the corresponding time period as the start point. The length of the vertical line is determined by the sliding pressure in the corresponding time period, and if the sliding pressure is P1, a preset data table can be queried, the length corresponding to the sliding pressure P1 can be queried, and then when corresponding vertical lines are generated for sliding lines generated at the same time period, the queried length of the vertical line can be used as a constraint condition to determine the end points of the vertical line extending upwards and downwards. It should be added that, as shown in fig. 3, when the sliding line generated in the corresponding time period is no longer horizontal, the corresponding vertical line is no longer vertical, that is, the vertical line changes along with the straight condition of the sliding line generated in the corresponding time period, but the vertical line is always perpendicular to the sliding line generated in the corresponding time period.

In this step, it should be noted that, in the case that the entire sliding length is fixed, since the interval time is the same, the faster the sliding speed is, the larger the distance between two adjacent vertical lines is. The distance between two adjacent vertical lines generally refers to the distance between the two adjacent vertical lines and the foot of the corresponding slide line. Further, it is understood that the faster the sliding rate, the fewer the number of vertical lines that are ultimately generated.

Step 102: and determining a human-computer recognition result of the sliding track formed by the sliding lines according to the distribution condition of the vertical lines corresponding to the sliding lines respectively.

In this step, it should be noted that the distribution of the vertical lines may include: the total number of vertical lines, the distance between vertical lines, the length of vertical lines, etc. Wherein the meaning of the distance between the perpendicular lines and the meaning of the length of the perpendicular lines have been explained specifically in the above step 101.

Since the distribution of the vertical lines generated during the sliding operation can reflect the stability of the sliding operation (including the speed of the sliding operation, whether the sliding rate is stable, and the like) during the sliding operation, and the stability of the sliding operation can accurately reflect the possibility that the sliding operation is performed as a machine operation, the distribution of the vertical lines generated during the sliding operation can reflect the possibility that the sliding operation is performed as a machine operation.

For example, if only one vertical line is generated or no vertical line is generated during the entire sliding operation, it indicates that the sliding speed is too fast, that is, the sliding speed is greater than a certain preset threshold, which indicates that the sliding trajectory has a greater probability of being generated by the machine operation. For another example, if the distances between the vertical lines generated in the whole sliding operation process are more consistent or uniform, it indicates that the sliding speed in the whole sliding process is more consistent or uniform, which indicates that the sliding trajectory has a greater probability of being generated by the machine operation. For another example, assuming that the lengths of the vertical lines generated during the entire sliding operation are substantially the same (assuming that the lengths are related to the sliding pressure), it indicates that the sliding pressure is more uniform or even during the entire sliding operation, which indicates that the sliding trajectory has a greater probability of being generated by the machine operation.

As can be seen from the above description, in the method for identifying a sliding track by a human-machine according to the embodiment of the present invention, since the distribution of the vertical lines generated during the sliding operation can reflect the stability of the sliding operation during the sliding operation, and the stability of the sliding operation can accurately reflect the possibility that the sliding operation is a machine operation, the embodiment of the present invention can more accurately determine whether the sliding operation that generates the sliding track is a machine operation.

Further, based on the content of the foregoing embodiment, in this embodiment, the determining, according to the distribution of the vertical lines corresponding to the sliding lines, a result of human-computer recognition of the sliding trajectory composed of the sliding lines specifically includes:

In this embodiment, when determining the human-machine recognition result of the sliding trajectory composed of the sliding lines according to the distribution of the vertical lines corresponding to the sliding lines, the following processing methods may be respectively adopted:

firstly, determining a human-computer recognition result of a sliding track formed by sliding lines according to the total number of all vertical lines generated in the sliding operation process;

determining a human-computer recognition result of a sliding track formed by sliding lines according to the distance between the vertical lines generated in the sliding operation process;

thirdly, determining a human-computer recognition result of a sliding track formed by sliding lines according to the length of each vertical line generated in the sliding operation process;

determining a human-computer recognition result of the sliding track formed by the sliding lines according to the total quantity of the vertical lines and the distance between the vertical lines;

determining a human-computer recognition result of a sliding track consisting of sliding lines according to the total amount of the vertical lines and the length of the vertical lines;

determining the human-computer recognition result of the sliding track formed by the sliding lines according to the distance between the vertical lines and the length of the vertical lines generated in the sliding operation process;

and determining a human-computer recognition result of the sliding track formed by the sliding lines according to the total number of the vertical lines, the distance between the vertical lines and the length of the vertical lines.

For the first processing mode:

in this embodiment, it should be noted that the human-machine recognition result of the sliding trajectory composed of the sliding lines may be determined according to the total number of the vertical lines generated during the sliding operation. The sliding speed is high and the sliding is fast in the sliding operation process of the machine, and the sliding speed is low and the sliding is slow in the artificial sliding operation process, so that whether the machine is operated or not can be determined according to the sliding speed. The magnitude of the sliding rate is represented by the number of generated vertical lines in the present embodiment. For a sliding verification code of the same length, the smaller the number of vertical lines generated, the higher the sliding rate, and thus the greater the probability of machine operation. A set of comparative examples as shown in fig. 3 and 4, in which the number of vertical lines in fig. 3 is large and the number of vertical lines in fig. 4 is small, it can be seen that the sliding rate corresponding to fig. 3 is low and the sliding rate corresponding to fig. 4 is high, and therefore, compared with fig. 3 and 4, the possibility of human operation is high in fig. 3 and the possibility of machine operation is high in fig. 4.

For example, it is assumed that the average possible number of vertical lines for the entire sliding operation is 35, which is determined based on the total length of the sliding operation of the sliding verification code and the speed distribution statistics of the human sliding operation. In the case shown in fig. 3, since the number of vertical lines is 32, which is relatively close to the number of vertical lines that may be present on average in the entire sliding operation, the possibility of the manual operation is relatively high in the case shown in fig. 3, while in the case shown in fig. 4, since the number of vertical lines is 4, which is much smaller than the number of vertical lines that may be present on average in the entire sliding operation, the possibility of the machine operation is relatively high in the case shown in fig. 4. It should be noted that a smaller number of vertical lines indicates a higher slip rate and thus a higher probability of machine operation.

For the second processing mode:

in this embodiment, it should be noted that the human-machine recognition result of the sliding trajectory composed of the sliding lines may be determined according to the distance between the vertical lines generated during the sliding operation. The time intervals of every two vertical lines are the same, so that when the distances between every two adjacent vertical lines are different, the sliding speed in the sliding operation process is changed, generally, the sliding speed of machine operation is consistent or stable, and the sliding speed of manual operation is random or fluctuated, so that the stability of the sliding speed can be judged according to the distance between every two vertical lines, and whether the machine operation is performed or not is determined according to the stability judgment result of the sliding speed. A set of comparative examples shown in fig. 5 and fig. 6, wherein the distance fluctuation between two adjacent vertical lines in fig. 5 is relatively large and not consistent, and the distance fluctuation between two adjacent vertical lines in fig. 6 is relatively small and consistent, so that it can be seen that the sliding speed corresponding to fig. 5 is relatively random or fluctuated, and the sliding speed corresponding to fig. 6 is relatively consistent or stable, so that fig. 5 has a relatively high possibility of human operation compared with fig. 6, and fig. 6 has a relatively high possibility of machine operation.

For example, as shown in fig. 5, in the vertical line generated during the sliding operation, it is assumed that the distance between two adjacent vertical lines is (3,2,2,2,1,1, 3,2,1,1,1,2,2,1,1,1,1,1,1,2,2,1,1,1,1,1, 2), and in the distance set, the number of the distances 3 is 2, the number of the distances 2 is 11, the number of the distances 1 is 19, that is, the number of the most 1 in the distance set is 19/32 ═ 0.59, and is less than the preset distance fluctuation stability determination threshold value 0.6. Therefore, the distance fluctuation stability condition is not satisfied, and therefore, the consistency of the distances among the vertical lines is not good, namely, the sliding speed is relatively fluctuated or the sliding speed variability is relatively large, and further, the possibility that the corresponding sliding operation is manual operation is relatively high.

As shown in fig. 6, in the vertical line generated during the sliding operation, the distance between two adjacent vertical lines is assumed to be (1,1,1,1,1,1,1,1,1, 2,2,1,1,1,1,1, 1), since the number of distances 2 in the distance set is 4, the number of distances 1 in the distance set is 33, that is, the ratio of 1 to the largest number is 33/37-0.89, which is greater than the preset distance fluctuation stability determination threshold value 0.6, it can be said that, the distance fluctuation stability condition is met, so that the consistency of the distance between every two vertical lines is relatively good, namely that the sliding rate is fixed or the sliding rate variability is relatively small, and further that the possibility that the corresponding sliding operation is machine operation is relatively high.

For the third treatment mode:

in this embodiment, it should be noted that the human-machine recognition result of the sliding trajectory composed of the sliding lines may be determined according to the length of each vertical line generated during the sliding operation. Because the length of each vertical line is related to the sliding pressure of the sliding operation in the corresponding time period, the sliding pressure change condition in the sliding process can be judged according to the length distribution condition of the vertical lines in the sliding operation process, and then whether the machine operation is more likely or the manual operation is more likely is determined according to the sliding pressure change condition. For example, when the sliding pressure during the sliding operation is relatively uniform and the variation is relatively small, the possibility of determining the machine operation is relatively high, and it is reflected in that the vertical length distributions are uniform, that is, when the vertical length distributions are uniform, the possibility of determining the machine operation is relatively high. When the sliding pressure in the sliding operation process is fluctuated and random and has larger variation, the possibility of manual operation is determined to be higher, and the vertical line distribution is reflected that the length distribution difference of each vertical line is larger or the length distribution is uneven, namely when the length distribution difference of each vertical line is larger or the length distribution is uneven, the possibility of machine operation is determined to be higher. Still referring to a set of comparative examples shown in fig. 5 and 6, wherein the vertical lengths in fig. 5 are not uniformly distributed, but the vertical lengths in fig. 6 are uniformly distributed, it can be seen that the sliding pressure corresponding to fig. 5 is random or fluctuated, and the sliding pressure corresponding to fig. 6 is uniform or stable, so that fig. 5 has a greater possibility of manual operation than fig. 6, and fig. 6 has a greater possibility of machine operation.

In this embodiment, it should be noted that, for the sliding operation performed by using the mouse, the sliding pressure is reflected in the dwell time of pressing the mouse, and if the dwell time of pressing the mouse in the corresponding time period is longer, the sliding pressure is generally considered to be larger. In the case of the sliding operation using the touch screen, the sliding pressure is expressed by the pressure when the touch screen is pressed, the dwell time when the touch screen is pressed, or the pressure when the touch screen is pressed and the dwell time when the touch screen is pressed.

In this embodiment, it should be noted that, because it is generally difficult to control the sliding pressure during the machine operation, that is, the sliding pressure is generally not changed during the machine operation, it is possible to determine whether the machine operation is performed by determining whether the sliding pressure is changed during the sliding process. In the present embodiment, the factor of the sliding pressure is reflected in the length of the vertical line, and therefore, it is possible to determine whether the possibility of the robot operation is high or the possibility of the human operation is high, based on the change in the length of the vertical line.

For the fourth treatment method:

in this embodiment, it should be noted that the human-machine recognition result of the sliding trajectory composed of the sliding lines may be determined according to the total number of the vertical lines and the distance between the vertical lines. As described above, since the total number of vertical lines and the distance between the vertical lines can be used for human-machine recognition, the recognition result will be more accurate if the two factors are combined.

For example, in the case shown in fig. 5 and fig. 6, as described above, according to the distance distribution between two adjacent vertical lines, it can be obtained that the distance between the vertical lines in the case shown in fig. 5 is not very consistent, that is, the sliding rate is relatively fluctuated or the sliding rate variability is relatively large, and further, the possibility that the corresponding sliding operation is a manual operation is relatively large. The situation shown in fig. 6 is relatively good in terms of the distance between the vertical lines, i.e. a constant slip rate or a relatively low variability of the slip rate, which in turn means that the corresponding slip operation is relatively likely to be a machine operation. On the basis, further combining the number of vertical lines, the number of vertical lines in fig. 5 is 33, and the number of vertical lines in fig. 6 is 38, it should be noted that under the same sliding length condition of the sliding verification code and the same interval time condition, the smaller the number of vertical lines, the faster the sliding speed is, and the sliding speed of the machine operation is generally faster than the sliding speed of the human operation. Therefore, it is understood that, in consideration of the number of vertical lines, the possibility of manual operation is relatively high in fig. 5, and the possibility of machine operation is relatively high in fig. 6. Therefore, the distance between each vertical line and the number of the vertical lines are comprehensively considered to obtain more accurate and more reliable identification results: the situation shown in fig. 5 is a manual operation and the situation shown in fig. 6 is a machine operation.

For the fifth treatment mode:

in this embodiment, it should be noted that the human-machine recognition result of the sliding trajectory composed of the sliding lines may be determined according to the total number of the vertical lines and the length of each vertical line. As described above, since the total number of the vertical lines and the length of each vertical line can be used for human-machine recognition, the recognition result will be more accurate if the two factors are combined.

For example, in the case shown in fig. 5, as described above, the vertical lines have uneven length distribution, i.e., the sliding pressure variability is relatively large, and thus the possibility that the corresponding sliding operation is a manual operation is relatively large. The vertical lines in fig. 6 are distributed more uniformly, which means that the variation of the sliding pressure is smaller, and thus the possibility that the corresponding sliding operation is the operation of the machine is higher. On the basis, further combining the number of vertical lines, the number of vertical lines in fig. 5 is 33, and the number of vertical lines in fig. 6 is 38, it should be noted that under the same sliding length condition of the sliding verification code and the same interval time condition, the smaller the number of vertical lines, the faster the sliding speed is, and the sliding speed of the machine operation is generally faster than the sliding speed of the human operation. Therefore, it is understood that, in consideration of the number of vertical lines, the possibility of manual operation is relatively high in fig. 5, and the possibility of machine operation is relatively high in fig. 6. Therefore, the length of each perpendicular line and the number of the perpendicular lines are considered together to obtain more accurate and more reliable identification results: the situation shown in fig. 5 is a manual operation and the situation shown in fig. 6 is a machine operation.

For the sixth treatment method:

in this embodiment, the human-machine recognition result of the sliding trajectory composed of the sliding lines may be determined based on the distance between the vertical lines and the length of each vertical line generated during the sliding operation.

For example, in the case shown in fig. 5 and fig. 6, as described above, according to the distance distribution between two adjacent vertical lines, it can be obtained that the distance between the vertical lines in the case shown in fig. 5 is not very consistent, that is, the sliding rate is relatively fluctuated or the sliding rate variability is relatively large, and further, the possibility that the corresponding sliding operation is a manual operation is relatively large. The situation shown in fig. 6 is relatively good in terms of the distance between the vertical lines, i.e. a constant slip rate or a relatively low variability of the slip rate, which in turn means that the corresponding slip operation is relatively likely to be a machine operation. On the basis, the length distribution of the vertical lines is further combined. In the case shown in fig. 5, the length distribution of each vertical line is not uniform, i.e. the variability of the sliding pressure is relatively large, and further the possibility that the corresponding sliding operation is a manual operation is relatively large. The vertical lines in fig. 6 are distributed more uniformly, which means that the variation of the sliding pressure is smaller, and thus the possibility that the corresponding sliding operation is the operation of the machine is higher. Therefore, the distance between every two vertical lines and the length of every two vertical lines are comprehensively considered, so that a more accurate and more reliable identification result can be obtained: the situation shown in fig. 5 is a manual operation and the situation shown in fig. 6 is a machine operation.

In addition, in another embodiment of the present invention, when determining the result of human-computer recognition of the sliding trajectory composed of the sliding lines according to the distance between the vertical lines and the length of the vertical lines generated during the sliding operation, the following method may be further adopted:

In the present embodiment, as shown in fig. 7 (the thick horizontal line in the horizontal direction in fig. 7 is a sliding track, and the thin vertical line in the vertical direction is a vertical line), four end points A, B, C and D of two adjacent vertical lines may form a quadrangle, and similarly, four end points of any other two adjacent vertical lines in fig. 7 may form a quadrangle.

In this embodiment, it should be noted that, since the size of the area of the quadrangle formed by the four end points of two adjacent vertical lines is determined by the distance between two adjacent vertical lines and the lengths of the two vertical lines, the area of the quadrangle formed by the four end points of two adjacent vertical lines can comprehensively reflect the influence of the two factors, i.e., the distance between the vertical lines and the length of the vertical line, on the sliding track, and therefore, according to the area distribution, a relatively accurate human-machine recognition result can be obtained. In addition, the area of a quadrangle formed by four end points of every two adjacent vertical lines is convenient to calculate, and calculation results are convenient to compare, so that the human-computer recognition result of the sliding track formed by the sliding lines can be accurately and conveniently determined according to the distance between the vertical lines and the length of each vertical line generated in the sliding operation process.

As shown in fig. 7, two adjacent vertical lines are formed into a quadrangle (forming two adjacent vertical lines into a quadrangle means forming four end points of two adjacent vertical lines into a quadrangle), the area of each quadrangle is calculated, and then the human-machine recognition result of the sliding track formed by each sliding line is determined according to the distribution of the areas of all the quadrangles. For example, if the areas of the quadrangles formed by two adjacent vertical lines are approximately the same or are uniformly distributed, the velocity is stable or uniform in the whole sliding operation process, and therefore, the possibility that the sliding operation is a machine is relatively high.

For example, if H quadrangles are obtained in total and the number of quadrangles having the same area is G, if the result of G/H is larger than a predetermined threshold (e.g., 0.6), it indicates that the sliding speed is more uniform or more uniform throughout the sliding operation, and further indicates that the possibility that the sliding operation is a machine is higher.

For another example, the higher the proportion of quadrangles having the same area among quadrangles formed by two adjacent vertical lines is, the higher the possibility that the sliding operation is performed by the machine is.

In the present embodiment, as shown in fig. 7, since the proportion of quadrangles having the same area among quadrangles formed by two adjacent vertical lines is high, the possibility of the machine operation shown in fig. 7 is high.

In the case shown in fig. 8 and 9, the proportion of quadrangles having the same area among quadrangles formed by two adjacent vertical lines is low, so that the possibility of manual operation in fig. 8 and 9 is high.

For the seventh treatment method:

in this embodiment, the human-machine recognition result of the sliding trajectory composed of the sliding lines may be determined according to the total number of the vertical lines, the distance between the vertical lines, and the length of the vertical lines.

For example, in the case shown in fig. 5 and fig. 6, as described above, according to the distance distribution between two adjacent vertical lines, it can be obtained that the distance between the vertical lines in the case shown in fig. 5 is not very consistent, that is, the sliding rate is relatively fluctuated or the sliding rate variability is relatively large, and further, the possibility that the corresponding sliding operation is a manual operation is relatively large. The situation shown in fig. 6 is relatively good in terms of the distance between the vertical lines, i.e. a constant slip rate or a relatively low variability of the slip rate, which in turn means that the corresponding slip operation is relatively likely to be a machine operation. On the basis, the length distribution of the vertical lines is further combined. In the case shown in fig. 5, the length distribution of each vertical line is not uniform, i.e. the variability of the sliding pressure is relatively large, and further the possibility that the corresponding sliding operation is a manual operation is relatively large. The vertical lines in fig. 6 are distributed more uniformly, which means that the variation of the sliding pressure is smaller, and thus the possibility that the corresponding sliding operation is the operation of the machine is higher. On the basis, further combining the number of vertical lines, the number of vertical lines in fig. 5 is 33, and the number of vertical lines in fig. 6 is 38, it should be noted that under the same sliding length condition of the sliding verification code and the same interval time condition, the smaller the number of vertical lines, the faster the sliding speed is, and the sliding speed of the machine operation is generally faster than the sliding speed of the human operation. Therefore, it is understood that, in consideration of the number of vertical lines, the possibility of manual operation is relatively high in fig. 5, and the possibility of machine operation is relatively high in fig. 6. Therefore, the distance between every two vertical lines, the length of every two vertical lines and the number of the vertical lines are comprehensively considered, so that more accurate and more reliable identification results can be obtained: the situation shown in fig. 5 is a manual operation and the situation shown in fig. 6 is a machine operation.

In this embodiment, it should be noted that, when the human-machine recognition result of the sliding trajectory composed of the sliding lines is determined according to two or three of the total number of the vertical lines, the distance between the vertical lines, and the length of the vertical lines, the obtained human-machine recognition result is more accurate.

Further, based on the content of the foregoing embodiment, in this embodiment, the determining, according to one or more of the total number of the vertical lines, the distance between the vertical lines, and the length of the vertical lines, the result of human-computer recognition of the sliding trajectory composed of the sliding lines specifically includes:

In this embodiment, the determining the human-machine recognition result of the sliding track composed of the sliding lines according to the distance between the vertical lines may include: and determining the human-computer recognition result of the sliding track formed by the sliding lines according to the uniformity distribution condition of the distance between the adjacent vertical lines. For example, if the distance distribution between adjacent vertical lines is more uniform or even, it can be determined that the human-machine recognition result of the sliding track composed of the sliding lines is larger. For example, if a plurality of vertical lines are generated during the sliding operation, and the distance between every two adjacent vertical lines is (2,2,2,2,2,2,2, 2) or (4,4,4,3,3,3,3,2,2,2), the distance distribution between the adjacent vertical lines is relatively uniform or even. Since the sliding speed of the machine operation is more consistent or stable, and the sliding speed of the manual operation is more random or fluctuated, whether the machine operation is performed or not can be determined by judging the stability of the sliding speed, that is, whether the machine operation is performed or not can be determined by judging the uniformity distribution condition of the distance between adjacent vertical lines.

In this embodiment, the determining the human-machine recognition result of the sliding track formed by the sliding lines according to the length of each vertical line may include: and determining a human-computer recognition result of the sliding track formed by the sliding lines according to the uniformity distribution condition of the lengths of the vertical lines. For example, if the length distribution of each vertical line is more uniform or even, it can be determined that the human-machine recognition result of the sliding trajectory composed of each sliding line is larger. For example, if a plurality of vertical lines are generated during the sliding operation and the length of each vertical line is (6,6,6,6,6,6, 6) or (4,4,4,5,5,5,5, 6,6), the distribution of the lengths of the vertical lines is relatively uniform or even. Since the length of each vertical line is related to the sliding pressure of the sliding operation in the corresponding time period, and the sliding pressure in the corresponding time period is generally stable for the machine operation, the possibility of determining the machine operation is high when the sliding pressure during the sliding operation is relatively consistent and the variation is relatively small, and the possibility of determining the machine operation is high when the sliding pressure during the sliding operation is relatively fluctuated and random and the variation is relatively large.

Further, based on the content of the foregoing embodiment, in this embodiment, the determining the result of human-computer recognition of the sliding trajectory composed of the sliding lines according to one or more of the total number of the vertical lines, the distribution of the distances between the adjacent vertical lines, and the distribution of the lengths of the vertical lines specifically includes:

In this embodiment, it should be noted that the first machine identification index is determined according to the matching result between the first number of vertical lines generated during the sliding operation and each sub-interval in the first interval set. For example, assuming that the number of vertical lines that may appear on average in the entire sliding operation is determined to be 10 according to the total length of the sliding operation of the sliding verification code and the speed distribution statistics of the artificial sliding operation, each subinterval in the first set of intervals may be determined to be { (0,2), (2,4), (4,6), (6,8), (8,10) }. Since the smaller the number of vertical lines, the higher the slip rate and thus the greater the likelihood of machine operation, the greater the corresponding first machine indicator. Accordingly, the first machine identification indicator corresponding to each subinterval may be set to {10,8,6,4,2 }. For example, assuming that the first number of vertical lines generated during the sliding operation is 0, since the subinterval in the first interval set corresponding to the first number 0 is the subinterval (0,2), and the first machine identification index corresponding to the subinterval (0,2) is 10, the first machine identification index may be determined to be 10. It will be appreciated that a first number of perpendicular lines generated during a sliding operation of 0, indicating a very fast sliding speed, is a relatively high probability of indicating a sliding operation as a machine. It should be noted that, because the machine has a large sliding speed and a fast sliding speed during the sliding operation, and the human has a small sliding speed and a slow sliding speed during the sliding operation, it can be determined whether the machine is operating according to the magnitude of the sliding speed. The magnitude of the sliding rate is represented by the number of generated vertical lines in the present embodiment. For a sliding verification code of the same length, the smaller the number of vertical lines generated, the higher the sliding rate, and thus the greater the probability of machine operation.

In addition, in this embodiment, the second machine identification index may be determined according to a matching result between a second number equal to the first value in the distance between every two adjacent vertical lines and each sub-interval in the second interval set. For example, assuming that the number of time periods included in the sliding operation process of the sliding verification code is 10 (assuming that one time period is 0.1s, the time consumed by the whole sliding process is 1s), the sub-intervals in the second interval set can be determined as { (0,2), (2,4), (4,6), (6,8), (8,10) }. The greater the number of the distances between two adjacent vertical lines, which is the same as the distance with the highest frequency of occurrence, the more consistent or stable the slip rate is, and the greater the possibility of indicating the machine operation is, and thus the greater the corresponding second machine index is. Therefore, the second machine identification index corresponding to each subinterval may be set to {2,4,6,8,10 }. For example, assuming that the distance between two adjacent vertical lines is (4,4,2,2,2,4,4,4,4,4), in this case, the second number equal to the first value in the distance between two adjacent vertical lines during the sliding operation is 7, since the subintervals in the second interval set corresponding to the second number 7 are the subintervals (6,8), and the second machine identification index corresponding to the subintervals (6,8) is 8, it may be determined that the second machine identification index is 8. It can be understood that a second number of 7 (70% of the distances between all the two adjacent vertical lines are consistent) equal to the first value (the value 4 with the highest occurrence frequency) among the distances between two adjacent vertical lines during the sliding operation indicates that the sliding speed is stable during the whole sliding process, and therefore indicates that the possibility of the sliding operation as a machine is high.

In addition, in this embodiment, the second machine identification index may also be determined according to a matching result between a sum of differences between distances of every two adjacent vertical lines and each subinterval in the third interval set. For example, assuming that the number of time periods included in the sliding operation process of the sliding verification code is 10 (assuming that one time period is 0.1s, the entire sliding process takes 1s), and the distance fluctuation statistic value between adjacent time periods is 1, each subinterval in the third interval set may be determined to be { (0,2), (2,6), (6,10), (10,12), (12,16) }. The corresponding second machine indicator is larger because the smaller the sum of the differences between the distances of two adjacent vertical lines, the more consistent or stable the slip rate is, and thus the greater the likelihood of machine operation. Therefore, the second machine identification index corresponding to each subinterval may be set to {10,8,6,4,2 }. For example, assuming that the distance between two adjacent vertical lines is (4,4,2,2,2,2,4,4,4,4), in this case, the sum of the differences between the distances of two adjacent vertical lines during the sliding operation is 4, since the subinterval in the third interval set corresponding to 4 is the subinterval (2,6), and the second machine identification index corresponding to the subinterval (2,6) is 8, it may be determined that the second machine identification index is 8. It can be understood that the sum of the differences between the distances of two adjacent vertical lines during the sliding operation is 4 (only small fluctuations occur in the individual distances), which indicates that the sliding speed is stable during the whole sliding process, and only small changes and fluctuations occur, thus indicating that the possibility of the sliding operation being a machine is relatively high.

Further, in the present embodiment, the third machine recognition index may be determined based on a result of matching a third number equal to the second value in each of the vertical line lengths during the sliding operation with each of the subintervals in the fourth interval set. For example, assuming that the number of time periods included in the sliding operation of the sliding verification code is 10, each sub-interval in the fourth interval set may be determined to be { (0,2), (2,4), (4,6), (6,8), (8,10) }. The greater the number of vertical line lengths equal to the length having the highest frequency of occurrence, the more uniform or stable the slip rate, the more uniform or stable the slip pressure, the more uniform or stable the slip rate and the slip pressure, and the greater the possibility of machine operation, the greater the corresponding third machine indicator. Therefore, the third machine identification index corresponding to each subinterval may be set to {2,4,6,8,10 }. For example, assuming that the length of each vertical line is (6,6,6,6,6,6,6,6,6,5), in this case, the third number equal to the second value in each vertical line length during the sliding operation is 9, since the subinterval in the fourth set of intervals corresponding to the third number 9 is the subinterval (8,10), and the third machine identification index corresponding to the subinterval (8,10) is 10, it can be determined that the third machine identification index is 10. It is understood that the third number of the vertical line lengths during the sliding operation, which is equal to the second number (the value 6 having the highest frequency of occurrence), is 9 (90% of the vertical lines are identical in length among all the vertical lines), which indicates that the sliding pressure is stable throughout the sliding operation, and thus it can be said that the possibility of the sliding operation being a machine is relatively high.

In addition, in this embodiment, a third machine identification index may also be determined according to a matching result between a sum of differences between lengths of two adjacent vertical lines in the sliding operation process and each subinterval in the fifth interval set; for example, assuming that the number of time periods included in the sliding operation of the sliding verification code is 10 and the fluctuation statistic of the vertical line height between adjacent time periods is 1, each subinterval in the fifth set of intervals may be determined to be { (0,2), (2,6), (6,10), (10,12), (12,16) }. The corresponding third machine indicator is larger because the smaller the sum of the differences between the heights of two adjacent vertical lines, the more consistent or stable the sliding pressure is, and thus the greater the possibility of machine operation. Therefore, the third machine identification index corresponding to each subinterval may be set to {10,8,6,4,2 }. For example, assuming that the length of each perpendicular line is (6,6,6,6,6,6,6,6,5,5), in this case, the sum of the differences between the lengths of two adjacent perpendicular lines during the sliding operation is 1, since the subinterval in the fifth interval set corresponding to 1 is the subinterval (0,2), and the third machine identification index corresponding to the subinterval (0,2) is 10, it may be determined that the third machine identification index is 10. It can be understood that the sum of the difference values of the lengths of two adjacent vertical lines in the sliding operation process is 2 (only a small fluctuation occurs in the length of a single vertical line), which indicates that the sliding pressure in the whole sliding process is stable, and only a small change and fluctuation occur, so that the possibility that the sliding operation is a machine is relatively high.

Further, based on the content of the foregoing embodiment, in this embodiment, the determining, according to one or more of the first machine identification index, the second machine identification index, and the third machine identification index, a result of human-machine recognition of a sliding trajectory composed of sliding lines specifically includes: determining the man-machine recognition result of the sliding track consisting of all sliding lines according to a first relation model, wherein the first relation model is Index k₁*a*Index₁+k₂*b*Index₂+k₃*c*Index₃；

wherein Index represents a sliding trackIndex of man-machine recognition result, Index₁Representing a first machine-identification Index, Index₂Indicating a second machine identification Index, Index₃Represents a third machine identification index, a, b, and c represent weights of the first to third machine identification indexes, respectively, and a + b + c is 1; k is a radical of₁、k₂And k₃Participation control factors respectively representing the first to third machine identification indexes, the corresponding participation control factor being 1 when the corresponding machine identification index participates in the identification control, and 0 when the corresponding machine identification index does not participate in the identification control, wherein k is₁、k₂And k₃At least one value of the preset identification threshold value is 1, and the value of the preset identification threshold value Q is related to the number of machine identification indexes participating in identification control and the value of the machine identification indexes participating in identification control.

In this embodiment, the human-machine recognition result of the sliding trajectory composed of the respective sliding lines may be determined according to any one, any two, or three of the three machine recognition indexes. It should be noted that, when two or three of the three machine identification indexes are used to determine the human-machine identification result of the sliding track formed by the sliding lines, different weights may be assigned to the corresponding machine identification indexes according to the importance of the corresponding machine identification indexes. For example, when the consistency or uniformity of the distance between the vertical lines with respect to the number of vertical lines is more important for determining whether the machine operation is performed, the weight of the second machine recognition index may be set to be a larger value and the weight of the first machine recognition index may be set to be a smaller value, so that the determination is more reasonable and the human-machine recognition result is more accurate.

In this embodiment, it should be noted that the sliding track man-machine recognition method provided in this embodiment is not only applicable to the straight track shown in fig. 2 and the broken-line track shown in fig. 10, but also applicable to a curved track (such as an S-shaped curved track, a serpentine curved track, etc.). For the curve track, similar to the scheme described above, the man-machine judgment can be completely performed according to the number of the corresponding generated vertical lines in the sliding process, the distribution uniformity among the distances of the vertical lines, and the distribution uniformity among the lengths of the vertical lines. In the present embodiment, since the corresponding vertical line is generated for the slide line generated at a short time interval, the slide line generated at a short time interval does not affect the curved trajectory, and the slide line generated at a short time interval can be approximated to a straight line even for the curved trajectory, so that the corresponding vertical line can be generated for the curved trajectory.

Further, based on the content of the foregoing embodiment, in this embodiment, the method for identifying a sliding track by a human-computer further includes:

In this embodiment, it should be noted that the straightness of the sliding track can also reflect the possibility of the machine operating. For example, if the straightness of the slide trajectory generated during the sliding operation is high, the slide trajectory has a high probability of being generated by the machine operation. However, if the straightness of the sliding trajectory generated during the sliding operation is low, the sliding trajectory has a high probability of being generated by a person for the operation. Therefore, whether the sliding track is the machine operation or not can be determined in an auxiliary mode according to the straightness of the sliding track formed by the sliding lines. The straightness of the sliding track is understood to mean the linear rate of the sliding track. In this embodiment, the linear rate of the sliding trajectory can be calculated as follows: drawing a straight line according to two end points of the sliding track, and then determining the coincidence rate of the sliding track formed by all sliding lines and the straight line, wherein the coincidence rate is the straight line rate.

In the present embodiment, it should be noted that, since the distribution of the vertical lines generated during the sliding operation can reflect the stability of the sliding operation during the sliding operation, the stability of the sliding operation can accurately reflect the possibility that the sliding operation is the machine operation. In addition, the straightness of the sliding track can reflect the possibility that the sliding track is operated by the machine, so that the embodiment of the invention comprehensively considers the straight track condition and the sliding stability condition in the sliding verification code process, and can more accurately determine whether the sliding track is operated by the machine.

Further, based on the content of the foregoing embodiment, in this embodiment, the determining the result of human-computer recognition of the sliding trajectory composed of the sliding lines according to the straightness of the sliding trajectory composed of the sliding lines and the distribution of the vertical lines corresponding to the sliding lines respectively specifically includes:

In this embodiment, the higher the straightness of the sliding trajectory is, the larger the value of the first human-machine recognition index is, the smaller the total number of the vertical lines corresponding to each sliding line is, the more uniform the distance distribution between the adjacent vertical lines is, or the more uniform the length distribution of each vertical line is, the larger the value of the second human-machine recognition index is.

In the present embodiment, when determining the first human recognition index, it is necessary to judge the straightness of the sliding trajectory generated during the sliding operation. As described above, the higher the straightness of the sliding trajectory, the larger the value of the first human recognition index, and accordingly, the higher the possibility that the human recognition result is a machine operation. Specifically, when determining the straightness of the sliding trajectory, the straightness may be determined according to a coincidence ratio of the sliding trajectory and a target straight line, where the target straight line is a straight line determined according to two end points of the sliding trajectory. For example, the sliding verification code for performing security verification is: if the object a (if the object a is a slider) is slid to the position B, it can be determined that the position of the object a is the first end point, and the position of the position B is the second end point, and the corresponding target straight line is a straight line formed by connecting the first end point and the second end point with a straight line. In this embodiment, the straightness of the sliding track is determined by determining the coincidence ratio of the sliding track and the target straight line, and if the coincidence ratio is high, it indicates that the sliding track is relatively straight, and if the coincidence ratio is low, it indicates that the sliding track is relatively not straight. For example, when the coincidence rate is 80% -100%, the corresponding first human identification index may take a value of 8-10, when the coincidence rate is 60% -80%, the corresponding first human identification index may take a value of 6-8, when the coincidence rate is 40% -60%, the corresponding first human identification index may take a value of 4-6, when the coincidence rate is 20% -40%, the corresponding first human identification index may take a value of 2-4, and when the coincidence rate is 0% -20%, the corresponding first human identification index may take a value of 0-2. It should be noted that, for a broken line type sliding track, the broken line type sliding track can be divided into a plurality of straight line segments, and then each straight line segment is respectively subjected to straightness judgment, and finally the straightness of the final sliding track is determined according to the straightness of each straight line segment. For example, for the broken line type sliding track shown in fig. 10, the broken line type sliding track can be divided into 3 straight line segments, and then each straight line segment is respectively subjected to straightness determination, and finally the straightness of the final sliding track is determined according to the straightness of the 3 straight line segments. In this embodiment, the specific calculation method of the coincidence ratio is not limited, and for example, the coincidence ratio may be calculated according to the coincidence condition of the coordinates of the locus points.

In this embodiment, the human-machine recognition result of the sliding operation is determined according to the comparison result of the sum of the first human-machine recognition index and the second human-machine recognition index and the preset recognition threshold, and if the sum of the first human-machine recognition index and the second human-machine recognition index is greater than the human-machine recognition threshold, the sliding operation is determined as a machine operation, otherwise, the sliding operation is determined as a human operation. The man-machine identification threshold value is obtained by continuously adjusting the values of the historical first man-machine identification index and the historical second man-machine identification index corresponding to the intelligent equipment. If the first human-computer recognition index and the second human-computer recognition index detected in a period of historical time are higher, the human-computer recognition threshold value can be increased so as to improve the human-computer recognition accuracy. And if the first human-computer recognition index and the second human-computer recognition index detected in a period of historical time are both low, the human-computer recognition threshold value can be reduced. This is because some users have a high straightness of sliding operation, and a high sliding rate or a stable sliding rate, and at this time, if the initial threshold value that is not adjusted is used for determination, a false determination may occur, and further, the actual operation behavior of the user may be determined as the machine behavior. However, some users have very low straightness of sliding operation, very slow sliding speed or very unstable sliding speed, and at this time, if an unadjusted initial threshold is adopted for judgment, a missing judgment phenomenon may occur, and further, the machine operation behavior may be judged as the user behavior.

In addition, the specific value of the human-computer identification threshold can be set according to the security verification level of the corresponding website or system. For example, if a website or system requires a higher level of security verification, the predetermined identification threshold may be set lower to avoid missed judgment. For another example, if a certain website or system has a low requirement on the security verification level and a high requirement on the user experience, the preset identification threshold may be set higher, so as to avoid that the user experience is reduced due to the occurrence of misjudgment easily.

For example, the following table 1 illustrates a value rule of the human-computer identification index, assuming that the straightness of the sliding track is good, the corresponding first human-computer identification index is 8 points, assuming that the distance between each vertical line is also good, the corresponding score is 8 points, assuming that the length consistency of each vertical line is also good, the corresponding score is 8 points, assuming that the number of each vertical line is 2, the corresponding score is 8 points, and so on.

TABLE 1

In this embodiment, it should be noted that the cases shown in table 1 are only examples and are not limiting, and in practical application, the contents included in the second human-machine recognition index and the values of each index are not limited to the contents shown in table 1.

Based on the same inventive concept, another embodiment of the present invention provides a sliding track human-machine recognition device, referring to fig. 11, the sliding track human-machine recognition device provided in this embodiment includes: a generation module 21 and an identification module 22, wherein:

the generating module 21 is configured to generate corresponding vertical lines for each sliding line generated at the same time interval in the sliding operation process;

and the recognition module 22 is configured to determine a human-machine recognition result of the sliding track formed by the sliding lines according to the distribution of the vertical lines corresponding to the sliding lines.

Based on the content of the foregoing embodiment, in this embodiment, the identification module 22 is specifically configured to:

Based on the content of the foregoing embodiment, in this embodiment, the sliding track human-machine recognition device further includes:

the determining module is used for determining the straightness of a sliding track consisting of all sliding lines;

correspondingly, the identification module is specifically configured to:

Based on the content of the foregoing embodiment, in this embodiment, the identification module is specifically configured to:

Since the sliding track human-machine recognition device provided by the embodiment can be used for executing the sliding track human-machine recognition method described in the above embodiment, the working principle and the beneficial effect are similar, so detailed description is omitted here, and specific contents can be referred to the description of the above embodiment.

Based on the same inventive concept, another embodiment of the present invention provides an intelligent device, which includes the sliding track human-machine recognition apparatus as described in the above embodiments.

The intelligent equipment provided by the embodiment of the invention can be mobile phones, tablets, computers, remote controllers, operation control devices, remote control devices, cloud servers and other intelligent equipment.

Since the intelligent device provided by this embodiment includes the sliding track human-machine recognition device described in the above embodiment, the working principle and the beneficial effect thereof are similar, and therefore detailed description is omitted here, and specific contents can be referred to the description of the above embodiment.

Based on the same inventive concept, another embodiment of the present invention provides an electronic device, which specifically includes the following components, with reference to fig. 12: a processor 301, a memory 302, a communication interface 303, and a communication bus 304;

the processor 301, the memory 302 and the communication interface 303 complete mutual communication through the communication bus 304; the communication interface 303 is used for implementing transmission between the related devices;

the processor 301 is configured to call a computer program in the memory 302, and when the processor executes the computer program, the processor implements all the steps of the sliding trajectory human-computer recognition method, for example, when the processor executes the computer program, the processor implements the following steps: respectively generating corresponding vertical lines for all sliding lines generated at the same time interval in the sliding operation process; and determining a human-computer recognition result of the sliding track formed by the sliding lines according to the distribution condition of the vertical lines corresponding to the sliding lines respectively.

Based on the same inventive concept, another embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements all the steps of the sliding trajectory human-machine identification method described above, for example, the processor implements the following steps when executing the computer program: respectively generating corresponding vertical lines for all sliding lines generated at the same time interval in the sliding operation process; and determining a human-computer recognition result of the sliding track formed by the sliding lines according to the distribution condition of the vertical lines corresponding to the sliding lines respectively.

In addition, the logic instructions in the memory may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on such understanding, the above technical solutions may be essentially or partially implemented in the form of software products, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and include instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the sliding trajectory man-machine recognition method according to the embodiments or some parts of the embodiments.

In the description of the present invention, it should be noted that the terms "upper", "lower", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, which are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and operate, and thus, should not be construed as limiting the present invention. Unless expressly stated or limited otherwise, the terms "mounted," "connected," and "connected" are intended to be inclusive and mean, for example, that they may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.

In addition, in the present invention, terms such as "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.

Moreover, in the present invention, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, 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 identical elements in a process, method, article, or apparatus that comprises the element.

Furthermore, in the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A sliding track human-computer recognition method is characterized by comprising the following steps:

determining a human-computer recognition result of a sliding track formed by all sliding lines according to the distribution condition of the vertical lines corresponding to all the sliding lines;

the determining of the human-computer recognition result of the sliding track formed by the sliding lines according to the distribution of the vertical lines corresponding to the sliding lines respectively specifically includes:

wherein the length of each vertical line is related to the sliding pressure of the sliding operation in the corresponding time period;

the determining the human-computer recognition result of the sliding track formed by the sliding lines according to one or more of the total number of the vertical lines, the distance between the vertical lines and the length of the vertical lines specifically comprises:

2. The method for human-computer recognition of a sliding trajectory according to claim 1, wherein the determining the human-computer recognition result of the sliding trajectory composed of the sliding lines according to one or more of the total number of the vertical lines, the distance between the vertical lines, and the length of the vertical lines specifically comprises:

3. The method for human-computer recognition of a sliding trajectory according to claim 2, wherein the determining the human-computer recognition result of the sliding trajectory composed of the sliding lines according to one or more of the total number of the vertical lines, the distribution of the distances between the adjacent vertical lines, and the distribution of the lengths of the vertical lines specifically comprises:

4. The sliding trajectory human-machine recognition method according to claim 3, wherein the determining the human-machine recognition result of the sliding trajectory composed of the sliding lines according to one or more of the first machine recognition index, the second machine recognition index and the third machine recognition index specifically comprises:

5. The sliding track human-computer recognition method according to claim 1, further comprising:

6. The sliding track human-computer recognition method according to claim 5, wherein the determining the human-computer recognition result of the sliding track composed of the sliding lines according to the straightness of the sliding track composed of the sliding lines and the distribution of the vertical lines corresponding to the sliding lines respectively comprises:

7. A sliding track man-machine recognition device, characterized by comprising:

the generating module is used for respectively generating corresponding vertical lines for all sliding lines generated at the same time interval in the sliding operation process;

the recognition module is used for determining a human-computer recognition result of a sliding track formed by all the sliding lines according to the distribution condition of the vertical lines respectively corresponding to all the sliding lines;

the identification module is specifically configured to:

8. An intelligent device, characterized by comprising the sliding track man-machine recognition device according to claim 7.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the sliding trajectory human-machine recognition method according to any one of claims 1 to 6 are implemented when the processor executes the program.

10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the sliding trajectory human-machine recognition method according to any one of claims 1 to 6.