Data processing method and device

Abstract

The invention discloses a data processing method and device, and the method comprises the steps: obtaining point cloud data in a range of a target counter in a process that a target user handles a business at the target counter, and recognizing the figure point cloud data in the point cloud data; determining the number of figures in the figure point cloud data; when the number of the figures is greater than 1, determining a figure spatial form in the figure point cloud data, the figure spatial form being a spatial form of figures including the target user in a range where the target counter is located; comparing the figure spatial form with the warning form; when the figure spatial form is consistent with the warning form, warning is reported, accurate recognition and timely warning of the spatial forms of the figures including the target user in the range of the target counter are achieved, and the situation that the target counter needs to be warned due to the fact that the figure spatial form needing to be warned exists in the range of the target counter is effectively avoided. And the safety problems of user privacy leakage, property loss and the like caused by the fact that a worker does not accurately recognize and warn in time are solved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a data processing method and device. Background Art

[0002] With the rapid development of bank branch construction, the security of the business handling areas of bank branches is very important, and banks have also made strict requirements on the operating norms of business handling areas.

[0003] The traditional method usually involves staff manually discovering behaviors in the business processing area that are likely to cause safety issues and manually giving reminders.

[0004] However, under the traditional method, there is a situation where staff fail to accurately identify and promptly remind behaviors that are likely to lead to safety problems. Summary of the invention

[0005] In view of this, the purpose of this application is to provide a data processing method and device to accurately identify and promptly warn of behaviors that may cause security issues in the business handling area, and better protect the privacy and property safety of users. The specific plan is as follows:

[0006] In a first aspect, the present application provides a data processing method, the method comprising:

[0007] When a target user handles business at a target counter, point cloud data within the range of the target counter is obtained, wherein the point cloud data includes person point cloud data;

[0008] Identifying the person point cloud data in the point cloud data;

[0009] Determining the number of characters in the character point cloud data;

[0010] When the number of characters is greater than 1, determining the character spatial form in the character point cloud data, the character spatial form being the spatial form of the characters including the target user within the range of the target counter;

[0011] Comparing the character's spatial form with the warning form, the warning form being the form that needs to be warned;

[0012] When the character's spatial form is consistent with the warning form, a warning is reported.

[0013] Optionally, comparing the character's spatial form with the warning form includes:

[0014] Counting the number of point cloud data in which the character's spatial form overlaps with the warning form;

[0015] The number of the overlapping point cloud data is compared with a first threshold value, where the first threshold value is the minimum number of overlapping point cloud data required to determine that the spatial form of the person is consistent with the warning form.

[0016] Optionally, when the character's spatial form is consistent with the warning form, reporting a warning includes:

[0017] When the number of the overlapping point cloud data is greater than or equal to the first threshold, a warning is reported.

[0018] Optionally, the method further comprises:

[0019] When the number of the overlapping point cloud data is less than the first threshold, no warning is reported.

[0020] Optionally, the method further comprises:

[0021] Acquire a first three-dimensional coordinate, where the first three-dimensional coordinate is the three-dimensional coordinate of the hand point cloud data of the target user;

[0022] Acquire a second three-dimensional coordinate, where the second three-dimensional coordinate is a three-dimensional coordinate of the point cloud data of the PIN pad;

[0023] When the first three-dimensional coordinates and the second three-dimensional coordinates have overlapping dimensions, counting the number of point cloud data with overlapping dimensions, wherein the overlapping dimensions refer to the overlapping of the first three-dimensional coordinates and the second three-dimensional coordinates in three dimensions;

[0024] When the number of point cloud data overlapping in the dimension exceeds a second threshold, determining the number of characters in the character point cloud data, wherein the second threshold is the minimum number of overlapping point cloud data for determining that the target user is entering a password;

[0025] When the number of characters is greater than 1, a warning is reported.

[0026] Optionally, before identifying the person point cloud data in the point cloud data, the method further includes:

[0027] The point cloud data is preprocessed, wherein the preprocessing includes removing noise points and outliers in the point cloud data.

[0028] In a second aspect, the present application provides a data processing device, the device comprising a device for executing the data processing method in the first aspect or any possible implementation of the first aspect, the device comprising an acquisition unit, an identification unit, a first determination unit, a second determination unit, a comparison unit, and a reporting unit:

[0029] The acquisition unit is used to acquire point cloud data within the range of the target counter when the target user handles business at the target counter, wherein the point cloud data includes person point cloud data;

[0030] The identification unit is used to identify the person point cloud data in the point cloud data;

[0031] The first determining unit is used to determine the number of people in the person point cloud data;

[0032] The second determining unit is used to determine the character spatial form in the character point cloud data when the number of characters is greater than 1, wherein the character spatial form is the spatial form of the characters including the target user within the range where the target counter is located;

[0033] The comparison unit is used to compare the character's spatial form with a warning form, wherein the warning form is a form that needs to be warned;

[0034] The reporting unit is used to report a warning when the character's spatial form is consistent with the warning form.

[0035] In a third aspect, the present application provides an electronic device, the electronic device comprising:

[0036] Memory for storing computer programs or computer instructions;

[0037] A processor is used to execute the computer program or computer instructions stored in the memory, so that the electronic device executes the method described in the first aspect of the present application or any possible implementation method of the first aspect according to the computer instructions.

[0038] In a fourth aspect, the present application provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the method described in the first aspect of the present application or any possible implementation of the first aspect.

[0039] In a fifth aspect, the present application provides a computer-readable storage medium, comprising computer instructions, wherein the computer instructions instruct a computer to execute the method described in the first aspect of the present application or any possible implementation of the first aspect.

[0040] Based on the implementations provided in the above aspects, this application can also be further combined to provide more implementations.

[0041] It can be seen from the above technical solutions that the present application has the following beneficial effects:

[0042] The technical solution of the present application obtains point cloud data within the range of the target counter during the process of the target user handling business at the target counter, identifies the point cloud data of people in the point cloud data, determines the number of people in the point cloud data, and when the number of people is greater than 1, determines the spatial form of the people in the point cloud data, the spatial form of the people is the spatial form of the people including the target user within the range of the target counter, compares the spatial form of the people with the warning form, the warning form is the form that needs to be warned, and when the spatial form of the people is consistent with the warning form, it means that at this time, the people including the target user within the range of the target counter have a form that needs to be warned, and reports a warning. In this way, when the target user handles business at the target counter, the spatial form of the people including the target user within the range of the target counter can be accurately identified and warned in time, effectively avoiding security issues such as user privacy leakage and property loss caused by the staff failing to accurately identify and warn the spatial form of people who need to be warned within the range of the target counter. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0044] Figure 1 This is a flow chart of a data processing method in an embodiment of the present application;

[0045] Figure 2 This is a flow chart of a data processing method in an embodiment of the present application;

[0046] Figure 3 This is a schematic diagram of the structure of a data processing device in an embodiment of the present application;

[0047] Figure 4 This is a flow chart of a data processing method in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0049] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0050] As described in the background art, the traditional method usually uses the staff to manually discover behaviors that are likely to cause safety problems in the business handling area and manually remind them. However, in the traditional method, there is a situation where the staff cannot accurately identify behaviors that are likely to cause safety problems and remind them in time.

[0051] Based on this, an embodiment of the present application provides a data processing method, which, in the process of a target user handling business at a target counter, obtains point cloud data within the range of the target counter, identifies point cloud data of people in the point cloud data; determines the number of people in the point cloud data; when the number of people is greater than 1, determines the spatial form of the people in the point cloud data, where the spatial form of the people is the spatial form of the people including the target user within the range of the target counter; compares the spatial form of the people with the warning form; when the spatial form of the people is consistent with the warning form, reports a warning, thereby achieving accurate identification and timely warning of the spatial form of the people including the target user within the range of the target counter, and effectively avoiding security issues such as user privacy leakage and property loss caused by the staff failing to accurately identify and promptly warn the staff due to the existence of spatial forms of people who need to be warned within the range of the target counter.

[0052] In order to make the technical solution of the present application clearer and easier to understand, the method provided by the present application is introduced below in conjunction with specific embodiments.

[0053] Figure 1 This is a flowchart of a data processing method provided in an embodiment of the present application. The data processing method provided in this embodiment includes the following steps:

[0054] S101: When a target user handles business at a target counter, point cloud data within the range of the target counter is obtained.

[0055] In the embodiment of the present application, the target user refers to a user who is handling business, the target counter is the counter where the target user is handling business, and the range of the target counter is an area with a set distance radiating outward from the position of the target counter as the center. According to experimental data, behaviors that are likely to cause security problems often occur within the range of the target counter. The behaviors that are likely to cause security problems in the process of the target user handling business include: people other than the target user communicating with the target user, people other than the target user having physical contact with the target user, people other than the target user taking pictures with mobile phones, and people other than the target user guiding the target user to handle business. These behaviors that are likely to cause security problems are not allowed to occur within the range of the target counter in the process of the target user handling business. For the behaviors that are likely to cause security problems, the traditional way is to observe, distinguish, and remind staff to avoid further security problems caused by these behaviors. Security issues refer to problems that threaten the privacy and property security of users.

[0056] Point cloud data refers to a collection of vectors in a three-dimensional coordinate system. The scenes and characters identified by point cloud data are three-dimensional. Compared with the most common two-dimensional images, namely pictures, they can more accurately judge the shape and movement of characters.

[0057] S102: Identify person point cloud data in the point cloud data.

[0058] Perform integrity check on the acquired original point cloud data. When the acquired point cloud data is invalid, terminate the processing of this point cloud data. When the point cloud data is directly unusable due to data loss, format error, file damage, etc., the point cloud data is deemed invalid.

[0059] When the quality of the acquired point cloud data is poor, such as point cloud shaking imaging, obvious holes in the point cloud data, excessive noise resulting in insufficient precision and accuracy, etc., a preprocessing method is performed to optimize the point cloud data.

[0060] In a possible implementation, before identifying the person point cloud data in the point cloud data, the point cloud data is preprocessed, and the preprocessing includes removing noise points and outliers in the point cloud data.

[0061] Noise points are random errors or deviations in an observation, including wrong values ​​and isolated points that deviate from expectations; outliers belong to observations, which may be generated by real data or noise, but in general, they are observations that are significantly different from most observations. Noise points and outliers are both data that need to be removed from point cloud data of poor quality.

[0062] By eliminating noise points, outliers and other data that do not meet the requirements in the point cloud data, optimized point cloud data is obtained, which is ready for the subsequent segmentation processing of the point cloud data.

[0063] PointNet is a deep learning network that directly processes point cloud data. Pointnet++ is an extended model based on Pointnet. It divides point cloud data into multiple subsets and extracts features for each subset separately, thus effectively extracting local and global features of point cloud data. Pointnet++ also adopts a multi-scale feature fusion method to make the model more generalized. Using the idea of ​​hierarchical feature extraction of PointNet++ network, a multi-layer sampling, grouping and feature extraction combined structure is designed to extract deep local features of point cloud data. At the same time, the multi-scale grouping (MSG) feature fusion method is used to solve the problem that the features learned in dense areas are not suitable for sparse areas when the point cloud data is unevenly distributed. The features of the current layer are obtained, and then the features of the current layer are sequentially sent to the combined structure, so that the point cloud data passes through three combined structures continuously. Each time it passes through a hierarchical structure, the point cloud data will be further processed, and then a smaller point set will be generated, which is a downsampling characterization process. The point cloud data is continuously downsampled to obtain a smaller number of feature points, and the hierarchical features of the point cloud data are gradually abstracted.

[0064] After the downsampling structure, the local features of the point cloud data are obtained, and then the upsampling process of the point cloud data is realized through the reverse interpolation and jump connection methods. The point cloud data is also set to pass through a three-layer downsampling structure. First, the features of more surrounding point cloud data are completed with the existing fewer feature points through reverse interpolation, thereby realizing the upsampling transmission of the features of the point cloud data. At the same time, in order to supplement the global features of the points, the features of the corresponding layer of the downsampling are spliced ​​with the interpolation features using the jump connection method to obtain discriminable features. By upsampling the point cloud data, the key information of the characters in the point cloud data is continuously strengthened, and the image resolution of the point cloud data is restored.

[0065] After upsampling to enhance key information, the semantic label of each point cloud data is predicted through nonlinear transformation, and the score of each point cloud data is output to complete the point cloud data semantic segmentation task, obtain the point cloud data segmentation result, and identify the person point cloud data in the point cloud data segmentation result.

[0066] S103: Determine the number of people in the person point cloud data.

[0067] The number of people in the recognized person point cloud data is determined, where the number of people is the number of all people within the range where the target counter is located, including the target user.

[0068] S104: When the number of characters is greater than 1, determine the character spatial form in the character point cloud data.

[0069] When the number of people in the identified person point cloud data is greater than 1, it means that there are other people in the range of the target counter besides the target user. The person spatial form in the person point cloud data is determined. The person spatial form is the spatial form of the people including the target user in the range of the target counter. The person spatial form is marked by a label and the existing person spatial form is recorded. By calculating the offset between the midpoint of each person spatial form in the range of the target counter and the midpoint of the target counter, the person spatial form with the smallest offset from the midpoint of the target counter is determined to be the target user. Other person spatial forms with non-small offsets belong to other people other than the target user.

[0070] S105: Compare the character's spatial form and the warning form.

[0071] Warning patterns are patterns that require warnings. For example, when a target user is handling a business, a person other than the target user within the target counter has physical contact or verbal communication with the target user. In this case, there is a risk of guiding the target user to handle the business, which is considered a warning pattern. When a target user is handling a business, a person other than the target user within the target counter takes a photo of the target user, which is also a behavior that is likely to cause safety problems and is also considered a warning pattern. The setting standards for warning patterns are obtained through the accumulation of a large amount of experimental data and practical experience.

[0072] In one possible implementation, comparing the spatial form of a person with the warning form includes: counting the number of point cloud data that overlap with the warning form; comparing the number of overlapping point cloud data with a first threshold, the first threshold being the minimum number of overlapping point cloud data required to determine that the spatial form of the person is consistent with the warning form.

[0073] When the spatial form of the person overlaps with the warning form, the number of point cloud data of the overlapping part of the point cloud data of the spatial form of the person and the warning form is counted, and the number of overlapping point cloud data is compared with the first threshold value, which is the minimum number of overlapping point cloud data for determining that the spatial form of the person is consistent with the warning form. When the spatial form of the person does not overlap with the warning form, it means that there is no behavior that is likely to cause safety problems within the range of the target counter. When the spatial form of the person of the target user overlaps with the spatial form of the person outside the target user, the boundary is unclear, and there are outliers, it is considered that the person is in physical contact with the target user, which is also a warning form.

[0074] By comparing the number of point cloud data where the spatial form of the person and the warning form overlap with the first threshold, accurate identification of behaviors that are likely to cause safety problems can be achieved, avoiding the problem of untimely discovery and inaccurate identification of behaviors that are likely to cause safety problems caused by traditional manual identification methods.

[0075] S106: When the spatial form of the character is consistent with the warning form, report a warning.

[0076] When the character's spatial form is consistent with the warning form, and when the number of overlapping point cloud data of the character's spatial form and the warning form is greater than or equal to the first threshold, the character's spatial form is considered to be consistent with the warning form, indicating that there are behaviors that are likely to cause safety problems within the range of the target counter. In this case, a warning is reported in time to prevent more serious safety problems from being caused by behaviors that are likely to cause safety problems, such as user privacy leaks, property losses, etc.

[0077] Furthermore, for the warning system, the warning classification, warning level, and warning action can be set. The warning system uses computer technology to visualize the segmentation results of the point cloud data into recognition result images. The staff can log in to the warning system to view the recognition result images. The warning system counts the spatial forms of the recognized people according to the bank's business outlets, time, level, and frequency of occurrence. The staff logs in to the alarm system to view and download statistical information, and further formulates relevant specifications based on the statistical information, and takes targeted measures to improve user safety.

[0078] In a possible implementation, when the number of overlapping point cloud data is greater than or equal to a first threshold, a warning is reported.

[0079] When the number of overlapping point cloud data of the character's spatial form and the warning form is greater than or equal to the first threshold, the character's spatial form is determined to be consistent with the warning form, and a warning is reported. At this time, there are behaviors that are likely to cause safety problems within the range of the target counter. The first threshold is the minimum number of overlapping point cloud data for determining that the character's spatial form is consistent with the warning form.

[0080] By comparing the number of point cloud data in which the spatial form of the person and the warning form overlap with the first threshold, and reporting a warning in a timely manner when the number of overlapping point cloud data is greater than or equal to the first threshold, accurate identification and timely warning of behaviors that are likely to cause safety problems within the range of the target counter are achieved, effectively avoiding the problems of inaccurate identification and untimely warning when traditional methods of manually identifying behaviors that are likely to cause safety problems are used.

[0081] In a possible implementation, when the number of overlapping point cloud data is less than a first threshold, no warning is reported.

[0082] When the number of point cloud data in which the spatial form of the person and the warning form overlap is less than the first threshold, it is determined that the spatial form of the person and the warning form are inconsistent, and there is no behavior that is likely to cause safety problems within the range of the target counter, and no warning is reported at this time.

[0083] By comparing the number of point cloud data in which the spatial form of the person and the warning form overlap with the first threshold, when the number of overlapping point cloud data is less than the first threshold, no warning is reported, thereby achieving accurate identification of behaviors that may easily lead to safety problems within the range of the target counter, and no warning is reported when the spatial form of the person does not meet the standard consistent with the warning form, effectively avoiding the situation where traditional methods cause false warnings due to inaccurate recognition of the spatial form of people within the range of the target counter by staff.

[0084] As can be seen from the above, an embodiment of the present application provides a data processing method. In the process of a target user handling business at a target counter, the method obtains point cloud data within the range of the target counter, identifies point cloud data of people in the point cloud data, and determines the number of people in the point cloud data. When the number of people is greater than 1, the method determines the spatial form of the people in the point cloud data. The spatial form of the people is the spatial form of the people including the target user within the range of the target counter. The spatial form of the people is compared with the warning form. The warning form is the form that needs to be warned. When the spatial form of the people is consistent with the warning form, it means that at this time, there is a form of people including the target user within the range of the target counter that needs to be warned, and a warning is reported. In this way, when the target user handles business at the target counter, the spatial form of the people including the target user within the range of the target counter can be accurately identified and warned in time, effectively avoiding security issues such as user privacy leakage and property loss caused by the staff failing to accurately identify and warn the spatial form of people who need to be warned within the range of the target counter.

[0085] Figure 4This is a flow chart of a data processing method in an embodiment of the present application, which specifically includes the following steps: receiving point cloud data returned by an acquisition device, performing integrity check on the received raw point cloud data, preprocessing the point cloud data, removing noise points in the point cloud data through a filtering algorithm, and at the same time eliminating outliers that do not meet the requirements, identifying the point cloud data of people within the range where the target counter is located, and judging the number of people in the point cloud data of people. If the number of people is less than or equal to 1, the process ends and no subsequent operations are performed. If the number of people is greater than 1, determining the spatial form of the people in the point cloud data of people, comparing whether the spatial form of the people is consistent with the warning form, and if the number of point cloud data whose spatial form of the people overlaps with the warning form is greater than or equal to a first threshold, recognizing the person counter. When the spatial form of the person is consistent with the warning form, that is, there are behaviors that are likely to cause safety problems, when the spatial form of the person is consistent with the warning form, a warning is reported, which can accurately identify the behaviors that are likely to cause safety problems within the range of the target counter, and issue timely warnings, effectively protecting the privacy and property safety of the target user. If the number of point cloud data in which the spatial form of the person and the warning form overlap is less than the first threshold, it is considered that the spatial form of the person is inconsistent with the warning form, that is, there are no behaviors that are likely to cause safety problems within the range of the target counter. The situation is terminated directly without reporting the warning, effectively avoiding the situation in which the traditional method of staff inaccurately identifies the spatial form of people within the range of the target counter and causes false warnings.

[0086] In a possible implementation, when the target user is entering a password while handling business at the target counter, only the target user is allowed to be within the range of the target counter. If other people including the target user are within the range of the target counter at this time, a warning is reported. Figure 2 A specific implementation of a data processing method is provided for an embodiment of the present application, which specifically includes the following steps:

[0087] S201: Acquire the first three-dimensional coordinates.

[0088] The first three-dimensional coordinates are the three-dimensional coordinates of the target user's hand point cloud data.

[0089] S202: Acquire the second three-dimensional coordinates.

[0090] The second three-dimensional coordinates are the three-dimensional coordinates of the point cloud data of the password keyboard.

[0091] S203: When the first three-dimensional coordinates and the second three-dimensional coordinates have overlapping dimensions, count the number of point cloud data with overlapping dimensions.

[0092] When there is a dimension overlap between the first three-dimensional coordinate and the second three-dimensional coordinate, the dimension overlap means that each dimension in the three-dimensional dimension overlaps. At this time, the hand of the target user is in contact with the password keyboard, and the number of point cloud data with overlapping dimensions is counted.

[0093] S204: When the number of point cloud data with overlapping dimensions exceeds a second threshold, determine the number of people in the person point cloud data.

[0094] When the first three-dimensional coordinate and the second three-dimensional coordinate overlap in each dimension of the three-dimensional dimension, and the number of point cloud data with overlapping dimensions exceeds a second threshold, it is determined that the target user is entering a password at this time. The second threshold is the minimum number of overlapping point cloud data obtained after analyzing a large amount of sample data to determine that the target user is entering a password.

[0095] S205: When the number of characters is greater than 1, a warning is reported.

[0096] When the target user is entering the password, only the target user is allowed to be within the range of the target counter. When the number of people in the point cloud data within the range of the target counter is greater than 1, it means that there are other people in the range of the target counter besides the target user, and a warning is reported.

[0097] When the target user is entering the password, in order to prevent the target user's privacy from being leaked and causing property loss, only the target user is allowed to be within the range of the target counter. When the target user is entering the password, if the number of people within the range of the target counter is greater than 1, it means that there are other people within the range of the target counter in addition to the target user. A report warning is issued to prevent the target user's privacy from being leaked, effectively protecting the user's privacy and property security.

[0098] Based on the data processing method provided in the above embodiment, the present application embodiment also provides a data processing device, see Figure 3 , the device includes an acquisition unit, an identification unit, a first determination unit, a second determination unit, a comparison unit, and a reporting unit:

[0099] The acquisition unit 301 is used to acquire point cloud data within the range of the target counter when the target user handles business at the target counter, wherein the point cloud data includes person point cloud data;

[0100] The identification unit 302 is used to identify the person point cloud data in the point cloud data;

[0101] The first determining unit 303 is used to determine the number of people in the person point cloud data;

[0102] The second determining unit 304 is used to determine the character spatial form in the character point cloud data when the number of characters is greater than 1, wherein the character spatial form is the spatial form of the characters including the target user within the range where the target counter is located;

[0103] The comparison unit 305 is used to compare the character's spatial form with the warning form, and the warning form is the form that needs to be warned;

[0104] The reporting unit 306 is used to report a warning when the character's spatial form is consistent with the warning form.

[0105] As can be seen from the above, the embodiment of the present application provides a data processing device. In the process of the target user handling business at the target counter, the acquisition unit 301 obtains the point cloud data within the range of the target counter, the identification unit 302 identifies the point cloud data of the person in the point cloud data, the first determination unit 303 determines the number of people in the person point cloud data, when the number of people is greater than 1, the second determination unit 304 determines the spatial form of the person in the person point cloud data, the spatial form of the person is the spatial form of the person including the target user within the range of the target counter, the comparison unit 305 compares the spatial form of the person with the warning form, the warning form is the form that needs to be warned, when the spatial form of the person is consistent with the warning form, it means that the person including the target user within the range of the target counter at this time has a form that needs to be warned, the reporting unit 306 reports the warning, thereby realizing that when the target user handles business at the target counter, the spatial form of the person including the target user within the range of the target counter is accurately identified and warned in time, effectively avoiding the security problems such as user privacy leakage and property loss caused by the staff failing to accurately identify and warn the spatial form of the person who needs to be warned within the range of the target counter.

[0106] As a possible implementation manner, the comparison unit 305 is specifically configured to:

[0107] Counting the number of point cloud data in which the character's spatial form overlaps with the warning form;

[0108] The number of the overlapping point cloud data is compared with a first threshold value, where the first threshold value is the minimum number of overlapping point cloud data required to determine that the spatial form of the person is consistent with the warning form.

[0109] As a possible implementation manner, the reporting unit 306 is specifically configured to:

[0110] When the number of the overlapping point cloud data is greater than or equal to the first threshold, a warning is reported.

[0111] As a possible implementation manner, the reporting unit 306 is further configured to:

[0112] When the number of the overlapping point cloud data is less than the first threshold, no warning is reported.

[0113] As a possible implementation manner, the obtaining unit 301 is specifically configured to:

[0114] Acquire a first three-dimensional coordinate, where the first three-dimensional coordinate is the three-dimensional coordinate of the hand point cloud data of the target user;

[0115] The acquisition unit 301 is further used for:

[0116] Acquire a second three-dimensional coordinate, where the second three-dimensional coordinate is a three-dimensional coordinate of the point cloud data of the PIN pad;

[0117] The device also includes a statistical unit, which is used to:

[0118] When the first three-dimensional coordinates and the second three-dimensional coordinates have overlapping dimensions, counting the number of point cloud data with overlapping dimensions, wherein the overlapping dimensions refer to the overlapping of the first three-dimensional coordinates and the second three-dimensional coordinates in three dimensions;

[0119] The first determining unit 303 is specifically configured to:

[0120] When the number of point cloud data overlapping in the dimension exceeds a second threshold, determining the number of characters in the character point cloud data, wherein the second threshold is the minimum number of overlapping point cloud data for determining that the target user is entering a password;

[0121] The reporting unit 306 is specifically used for:

[0122] When the number of characters is greater than 1, a warning is reported.

[0123] In a possible implementation manner, the device further includes a preprocessing unit, configured to:

[0124] The point cloud data is preprocessed, wherein the preprocessing includes removing noise points and outliers in the point cloud data.

[0125] The present application provides an electronic device, the electronic device comprising:

[0126] Memory for storing computer programs or computer instructions;

[0127] The processor is used to execute the computer program or computer instruction stored in the memory, so that the electronic device executes the method provided by the above embodiment.

[0128] The embodiment of the present application also provides a computer program product including instructions, which, when executed on a computing device, enables the computing device to execute the method provided in the above embodiment.

[0129] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program so that the computer program executes the method provided in the above embodiment.

[0130] Through the description of the above implementation methods, it can be known that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a storage medium, such as a read-only memory (ROM) / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute the methods described in each embodiment of the present application or some parts of the embodiments.

[0131] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, in which the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0132] The above description is merely an exemplary embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. A data processing method, characterized in that: The method comprises: When a target user handles business at a target counter, point cloud data within the range of the target counter is obtained, wherein the point cloud data includes person point cloud data; Identifying the person point cloud data in the point cloud data; Determining the number of characters in the character point cloud data; When the number of characters is greater than 1, determining the character spatial form in the character point cloud data, the character spatial form being the spatial form of the characters including the target user within the range of the target counter; Comparing the character's spatial form with the warning form, the warning form being the form that needs to be warned; When the character's spatial form is consistent with the warning form, a warning is reported.

2. The method according to claim 1, characterized in that The comparing the character's spatial form with the warning form includes: Counting the number of point cloud data in which the character's spatial form overlaps with the warning form; The number of the overlapping point cloud data is compared with a first threshold value, where the first threshold value is the minimum number of overlapping point cloud data required to determine that the spatial form of the person is consistent with the warning form.

3. The method according to claim 2, characterized in that When the spatial form of the character is consistent with the warning form, reporting a warning includes: When the number of the overlapping point cloud data is greater than or equal to the first threshold, a warning is reported.

4. The method according to claim 2, characterized in that: The method further comprises: When the number of the overlapping point cloud data is less than the first threshold, no warning is reported.

5. The method according to claim 1, characterized in that The method further comprises: Acquire a first three-dimensional coordinate, where the first three-dimensional coordinate is the three-dimensional coordinate of the hand point cloud data of the target user; Acquire a second three-dimensional coordinate, where the second three-dimensional coordinate is a three-dimensional coordinate of the point cloud data of the PIN pad; When the first three-dimensional coordinates and the second three-dimensional coordinates have overlapping dimensions, counting the number of point cloud data with overlapping dimensions, wherein the overlapping dimensions refer to the first three-dimensional coordinates and the second three-dimensional coordinates having overlapping dimensions in each of the three dimensions; When the number of point cloud data overlapping in the dimension exceeds a second threshold, determining the number of characters in the character point cloud data, wherein the second threshold is the minimum number of overlapping point cloud data for determining that the target user is entering a password; When the number of characters is greater than 1, a warning is reported.

6. The method according to claim 1, characterized in that Before identifying the person point cloud data in the point cloud data, the method further includes: The point cloud data is preprocessed, wherein the preprocessing includes removing noise points and outliers in the point cloud data.

7. A data processing device, characterized in that: The device comprises an acquisition unit, an identification unit, a first determination unit, a second determination unit, a comparison unit, and a reporting unit: The acquisition unit is used to acquire point cloud data within the range of the target counter when the target user handles business at the target counter, wherein the point cloud data includes person point cloud data; The identification unit is used to identify the person point cloud data in the point cloud data; The first determining unit is used to determine the number of people in the person point cloud data; The second determining unit is used to determine the character spatial form in the character point cloud data when the number of characters is greater than 1, wherein the character spatial form is the spatial form of the characters including the target user within the range where the target counter is located; The comparison unit is used to compare the character's spatial form with a warning form, wherein the warning form is a form that needs to be warned; The reporting unit is used to report a warning when the character's spatial form is consistent with the warning form.

8. An electronic device, characterized in that: The electronic device comprises: Memory for storing computer programs or computer instructions; A processor, configured to execute a computer program or computer instruction stored in the memory, so that the electronic device executes the method as claimed in any one of claims 1 to 6.

9. A computer program product, characterized in that When the computer program product is run on a computer, the computer is caused to execute the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The method comprises computer instructions, wherein the computer instructions instruct a computer to execute the method according to any one of claims 1 to 6.

Images