Operation behavior monitoring method and apparatus, electronic device, and storage medium

1. An operation behavior monitoring method, comprising:

acquiring target historical operation behavior data of a target user, and performing data statistics on the target historical operation behavior data according to different dimensions to establish a multi-dimensional coordinate system, wherein coordinate axes in the multi-dimensional coordinate system are in one-to-one correspondence with the dimensions;

determining, in response to receiving a target operation behavior, a target data item corresponding to the target operation behavior in each of the dimensions, and determining whether a marking point corresponding to the target data item exists in the multi-dimensional coordinate system;

increasing a density of the marking point by one under the condition that the marking point corresponding to the target data item exists in the multi-dimensional coordinate system;

under the condition that the marking point corresponding to the target data item does not exist in the multi-dimensional coordinate system, determining the marking point corresponding to the target data item in the multi-dimensional coordinate system, and setting the density of the marking point to be one, wherein a coordinate value of the marking point corresponding to the target data item is less than 1 under the condition that the target data item exists in the target historical operation behavior data, and the coordinate value of the marking point corresponding to the target data item is greater than 1 under the condition that the target data item does not exist in the target historical operation behavior data; and

calculating a center of gravity corresponding to each of the coordinate axes according to the density of all the marking points on each of the coordinate axes, and determining a target point based on all the centers of gravity to perform safety monitoring on the target operation behavior according to the position of the target point.

2. The operation behavior monitoring method according to claim 1 , wherein the performing data statistics on the target historical operation behavior data according to different dimensions to establish a multi-dimensional coordinate system comprises:

performing the data statistics on the target historical operation behavior data according to different dimensions to obtain all data items contained in each of the dimensions and a frequency of each of the data items, and normalizing the frequency to obtain a standard frequency of each of the data items; and

establishing a multi-dimensional coordinate system, and marking each of the data items on a coordinate axis corresponding to the dimension to which each of the data items belongs based on the standard frequency of each of the data items, wherein the coordinate axes in the multi-dimensional coordinate system are in one-to-one correspondence with the dimensions, A=1−f A , A is the coordinate value of a marking position of the data item, and f A is the standard frequency of the data item.

3. The operation behavior monitoring method according to claim 2 , wherein after the marking each of the data items on a coordinate axis corresponding to the dimension to which each of the data items belongs based on the standard frequency of each of the data items, the method further comprises:

determining a total number of data items corresponding to each of the coordinate axes, and calculating a unit distance p of each of the coordinate axes, wherein p=1/S, and S is the total number of the data items;

the determining a marking point corresponding to the target data item in the multi-dimensional coordinate system comprises:

determining B=1−f B under the condition that the target data item exists in the target historical operation behavior data, wherein B is the coordinate value of the marking point of the target data item, and f B is the standard frequency of the target data item in the target historical operation behavior data; and

determining B=1+bp under the condition that the target data item does not exist in the target historical operation behavior data, wherein b is a positive integer and b is negatively correlated with the frequency of the target data item in the target operation behavior.

4. The operation behavior monitoring method according to claim 2 , wherein before the normalizing the frequency to obtain a standard frequency of each of the data items, the method further comprises:

acquiring historical operation behavior data of all users, and determining duplicate data items in the historical operation behavior data of different users;

denoising the duplicate data items in the target historical operation behavior data according to principle that a higher frequency of the duplicate data items corresponds to a lower weight, to update the frequency of the data items;

the normalizing the frequency to obtain a standard frequency of each of the data items comprises:

normalizing an updated frequency to obtain the standard frequency of each of the data items.

5. The operation behavior monitoring method according to claim 4 , wherein a frequency updating formula of the data item is:

f

0

=

k

×

f

2

F

×

N

n

,

wherein f 0 is the updated frequency of the data item, f is an original frequency of the data item, F is a sum of the frequencies of the data items in historical operation behavior data corresponding to all users, N is the total number of the users, n is the total number of users who have the data item, and k is an experience coefficient.

6. The operation behavior monitoring method according to claim 1 , wherein the performing safety monitoring on the target operation behavior according to the position of the target point comprises:

determining whether the target point is within a preset safe area, and determining that the target operation behavior is a safe operation behavior under the condition that the target point is within a preset safe area;

or, calculating a safe confidence level of the target operation behavior based on a distance between the target point and an original point in the multi-dimensional coordinate system, wherein the safe confidence level is negatively correlated with the distance between the target point and the original point in the multi-dimensional coordinate system.

7. The operation behavior monitoring method according to claim 1 , wherein the dimensions comprise a work directory, an operation instruction and a login identification.

8. An electronic device, comprising:

a memory, configured to store a computer program; and

a processor, when executing the computer program, configured for:

acquiring target historical operation behavior data of a target user, and performing data statistics on the target historical operation behavior data according to different dimensions to establish a multi-dimensional coordinate system, wherein coordinate axes in the multi-dimensional coordinate system are in one-to-one correspondence with the dimensions;

determining, in response to receiving a target operation behavior, a target data item corresponding to the target operation behavior in each of the dimensions, and determining whether a marking point corresponding to the target data item exists in the multi-dimensional coordinate system;

increasing a density of the marking point by one under the condition that the marking point corresponding to the target data item exists in the multi-dimensional coordinate system;

under the condition that the marking point corresponding to the target data item does not exist in the multi-dimensional coordinate system, determining the marking point corresponding to the target data item in the multi-dimensional coordinate system, and setting the density of the marking point to be one, wherein a coordinate value of the marking point corresponding to the target data item is less than 1 under the condition that the target data item exists in the target historical operation behavior data, and the coordinate value of the marking point corresponding to the target data item is greater than 1 under the condition that the target data item does not exist in the target historical operation behavior data; and

calculating a center of gravity corresponding to each of the coordinate axes according to the density of all the marking points on each of the coordinate axes, and determining a target point based on all the centers of gravity to perform safety monitoring on the target operation behavior according to the position of the target point.

9. The electronic device according to claim 8 , wherein the performing data statistics on the target historical operation behavior data according to different dimensions to establish a multi-dimensional coordinate system comprises:

performing the data statistics on the target historical operation behavior data according to different dimensions to obtain all data items contained in each of the dimensions and a frequency of each of the data items, and normalizing the frequency to obtain a standard frequency of each of the data items; and

establishing a multi-dimensional coordinate system, and marking each of the data items on a coordinate axis corresponding to the dimension to which each of the data items belongs based on the standard frequency of each of the data items, wherein the coordinate axes in the multi-dimensional coordinate system are in one-to-one correspondence with the dimensions, A=1−f A , A is the coordinate value of a marking position of the data item, and f A is the standard frequency of the data item.

10. The electronic device according to claim 9 , wherein after the marking each of the data items on a coordinate axis corresponding to the dimension to which each of the data items belongs based on the standard frequency of each of the data items, the processor is further configured for:

determining a total number of data items corresponding to each of the coordinate axes, and calculating a unit distance p of each of the coordinate axes, wherein p=1/S, and S is the total number of the data items;

the determining a marking point corresponding to the target data item in the multi-dimensional coordinate system comprises:

determining B=1−f B under the condition that the target data item exists in the target historical operation behavior data, wherein B is the coordinate value of the marking point of the target data item, and f B is the standard frequency of the target data item in the target historical operation behavior data; and

determining B=1+bp under the condition that the target data item does not exist in the target historical operation behavior data, wherein b is a positive integer and b is negatively correlated with the frequency of the target data item in the target operation behavior.

11. The electronic device according to claim 9 , wherein before the normalizing the frequency to obtain a standard frequency of each of the data items, the processor is further configured for:

acquiring historical operation behavior data of all users, and determining duplicate data items in the historical operation behavior data of different users;

denoising the duplicate data items in the target historical operation behavior data according to principle that a higher frequency of the duplicate data items corresponds to a lower weight, to update the frequency of the data items;

the normalizing the frequency to obtain a standard frequency of each of the data items comprises:

normalizing an updated frequency to obtain the standard frequency of each of the data items.

12. The electronic device according to claim 11 , wherein a frequency updating formula of the data item is:

f

0

=

k

×

f

2

F

×

N

n

,

wherein f 0 is the updated frequency of the data item, f is an original frequency of the data item, F is a sum of the frequencies of the data items in historical operation behavior data corresponding to all users, N is the total number of the users, n is the total number of users who have the data item, and k is an experience coefficient.

13. The electronic device according to claim 8 , wherein the performing safety monitoring on the target operation behavior according to the position of the target point comprises:

determining whether the target point is within a preset safe area, and determining that the target operation behavior is a safe operation behavior under the condition that the target point is within a preset safe area;

or, calculating a safe confidence level of the target operation behavior based on a distance between the target point and an original point in the multi-dimensional coordinate system, wherein the safe confidence level is negatively correlated with the distance between the target point and the original point in the multi-dimensional coordinate system.

14. The electronic device according to claim 8 , wherein the dimensions comprise a work directory, an operation instruction and a login identification.

15. A non-transitory computer-readable storage medium, storing a computer program which, when executed by a processor, implements the operations comprising:

acquiring target historical operation behavior data of a target user, and performing data statistics on the target historical operation behavior data according to different dimensions to establish a multi-dimensional coordinate system, wherein coordinate axes in the multi-dimensional coordinate system are in one-to-one correspondence with the dimensions;

determining, in response to receiving a target operation behavior, a target data item corresponding to the target operation behavior in each of the dimensions, and determining whether a marking point corresponding to the target data item exists in the multi-dimensional coordinate system;

increasing a density of the marking point by one under the condition that the marking point corresponding to the target data item exists in the multi-dimensional coordinate system;

under the condition that the marking point corresponding to the target data item does not exist in the multi-dimensional coordinate system, determining the marking point corresponding to the target data item in the multi-dimensional coordinate system, and setting the density of the marking point to be one, wherein a coordinate value of the marking point corresponding to the target data item is less than 1 under the condition that the target data item exists in the target historical operation behavior data, and the coordinate value of the marking point corresponding to the target data item is greater than 1 under the condition that the target data item does not exist in the target historical operation behavior data; and

calculating a center of gravity corresponding to each of the coordinate axes according to the density of all the marking points on each of the coordinate axes, and determining a target point based on all the centers of gravity to perform safety monitoring on the target operation behavior according to the position of the target point.

16. The non-transitory computer-readable storage medium according to claim 15 , wherein the performing data statistics on the target historical operation behavior data according to different dimensions to establish a multi-dimensional coordinate system comprises:

performing the data statistics on the target historical operation behavior data according to different dimensions to obtain all data items contained in each of the dimensions and a frequency of each of the data items, and normalizing the frequency to obtain a standard frequency of each of the data items; and

establishing a multi-dimensional coordinate system, and marking each of the data items on a coordinate axis corresponding to the dimension to which each of the data items belongs based on the standard frequency of each of the data items, wherein the coordinate axes in the multi-dimensional coordinate system are in one-to-one correspondence with the dimensions, A=1−f A , A is the coordinate value of a marking position of the data item, and f A is the standard frequency of the data item.

17. The non-transitory computer-readable storage medium according to claim 16 , wherein after the marking each of the data items on a coordinate axis corresponding to the dimension to which each of the data items belongs based on the standard frequency of each of the data items, the operations further comprise:

determining a total number of data items corresponding to each of the coordinate axes, and calculating a unit distance p of each of the coordinate axes, wherein p=1/S, and S is the total number of the data items;

the determining a marking point corresponding to the target data item in the multi-dimensional coordinate system comprises:

determining B=1−f B under the condition that the target data item exists in the target historical operation behavior data, wherein B is the coordinate value of the marking point of the target data item, and f B is the standard frequency of the target data item in the target historical operation behavior data; and

determining B=1+bp under the condition that the target data item does not exist in the target historical operation behavior data, wherein b is a positive integer and b is negatively correlated with the frequency of the target data item in the target operation behavior.

18. The non-transitory computer-readable storage medium according to claim 16 , wherein before the normalizing the frequency to obtain a standard frequency of each of the data items, the operations further comprise:

acquiring historical operation behavior data of all users, and determining duplicate data items in the historical operation behavior data of different users;

denoising the duplicate data items in the target historical operation behavior data according to principle that a higher frequency of the duplicate data items corresponds to a lower weight, to update the frequency of the data items;

the normalizing the frequency to obtain a standard frequency of each of the data items comprises:

normalizing an updated frequency to obtain the standard frequency of each of the data items.

19. The non-transitory computer-readable storage medium according to claim 18 , wherein a frequency updating formula of the data item is:

f

0

=

k

×

f

2

F

×

N

n

,

wherein f 0 is the updated frequency of the data item, f is an original frequency of the data item, F is a sum of the frequencies of the data items in historical operation behavior data corresponding to all users, N is the total number of the users, n is the total number of users who have the data item, and k is an experience coefficient.

20. The non-transitory computer-readable storage medium according to claim 15 , wherein the performing safety monitoring on the target operation behavior according to the position of the target point comprises:

determining whether the target point is within a preset safe area, and determining that the target operation behavior is a safe operation behavior under the condition that the target point is within a preset safe area;

or, calculating a safe confidence level of the target operation behavior based on a distance between the target point and an original point in the multi-dimensional coordinate system, wherein the safe confidence level is negatively correlated with the distance between the target point and the original point in the multi-dimensional coordinate system.