CN113850836A

CN113850836A - Employee behavior identification method, device, equipment and medium based on behavior track

Info

Publication number: CN113850836A
Application number: CN202111150070.1A
Authority: CN
Inventors: 谢鹏; 赖众程; 李会璟; 梁俊杰; 李林毅
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2021-09-29
Filing date: 2021-09-29
Publication date: 2021-12-28
Anticipated expiration: 2041-09-29

Abstract

The invention relates to the field of artificial intelligence, and discloses a method for identifying staff behaviors based on behavior tracks, which comprises the following steps: identifying a staff portrait picture by using a face identification model; if the employee portrait picture is determined to be an internal employee picture, generating an internal employee motion track, and detecting violation conditions of internal employees; if the employee portrait picture is determined to be an external employee image, generating an external employee motion track; if the external staff does not have the accompanying staff image, violation information of the external staff is obtained; and if the image of the accompanying staff exists, inputting the motion trail of the accompanying staff and the motion trail of the external staff into the support vector machine model to obtain the distance between the accompanying staff and the external staff, and detecting the violation condition of the external staff. The invention also relates to a block chain technology, and violation information can be stored in block chain link points. The invention also provides a device, equipment and a medium for identifying the staff behaviors based on the behavior tracks. The invention can improve the accuracy of detecting the violation condition of the staff.

Description

Employee behavior identification method, device, equipment and medium based on behavior track

Technical Field

The invention relates to the field of artificial intelligence, in particular to a method and a device for identifying staff behaviors based on behavior tracks, electronic equipment and a storage medium.

Background

With the development of mobile internet, most of operation rooms in enterprises need face recognition when entering and exiting, but the enterprises are internally divided into internal employees and external employees, and the internal employees and the external employees may have violation conditions due to different behaviors. For example, when an internal employee enters the operating room, the card is not punched, and when other employees enter the operating room, the card is illegal, and when an external employee does not have access control authority, the internal employee needs to accompany the external employee, and after the external employee enters the operating room, the distance between the external employee and the internal employee is limited to be too far away, and the card is illegal. In the prior art, whether the violation condition of the staff exists in the work can not be accurately identified only through face identification, and great potential safety hazard is brought to a work area.

Disclosure of Invention

The invention provides a method and a device for identifying staff behaviors based on behavior tracks, electronic equipment and a computer medium, and mainly aims to improve the accuracy of detection of staff violation conditions.

In order to achieve the above object, the employee behavior identification method based on the behavior track provided by the invention comprises the following steps:

acquiring a picture of the employee to be identified, and identifying the picture of the employee to be identified by using a pre-constructed face identification model to obtain a portrait picture of the employee;

judging whether the staff face pictures are matched with a preset internal staff face library or not;

if the employee portrait picture is matched with the internal employee face library consistently, determining that the employee portrait picture is an internal employee picture, acquiring track coordinates of the employee portrait picture, generating an internal employee motion track according to the track coordinates, and determining violation conditions of internal employees corresponding to the employee picture to be identified according to the internal employee motion track;

if the matching of the employee portrait pictures and the internal employee face library is inconsistent, determining that the employee portrait pictures are external employee pictures, acquiring track coordinates of the employee portrait pictures, and generating external employee motion tracks according to the track coordinates;

judging whether an image of a companion employee exists in the employee portrait images;

if the image of the accompanying employee does not exist in the image of the employee portrait, outputting violation information of external employees;

if the image of the accompanying staff exists in the staff portrait picture, acquiring a motion trail of the accompanying staff, inputting the motion trail of the accompanying staff and the motion trail of the external staff into a preset support vector machine model, obtaining the distance between the accompanying staff and the external staff, and determining the violation condition of the external staff according to the distance between the accompanying staff and the external staff.

Optionally, the generating an internal employee motion trajectory according to the trajectory coordinates includes:

acquiring position coordinates of a plurality of cameras for shooting the employee pictures to be identified, and connecting the position coordinates to obtain path tracks associated with the cameras;

fusing the track coordinates and the path track to obtain a plurality of fused tracks of the cameras and the track coordinates;

and determining real-time position information of the internal employee image according to the fusion track, and generating the internal employee motion track according to the real-time position information.

Optionally, the acquiring the track coordinates of the staff portrait picture includes:

acquiring indoor position information of a plurality of cameras for shooting the pictures of the employees to be identified;

acquiring positioning information of the internal employee image;

and obtaining the track coordinates of the internal employee image according to the position information and the positioning information.

Optionally, the inputting the movement trajectory of the accompanying staff and the movement trajectory of the external staff into a preset support vector machine model to obtain the distance between the accompanying staff and the external staff includes:

mapping the movement track of the accompanying staff and the movement track of the external staff to a multi-dimensional coordinate to obtain a movement track coordinate set;

constructing a plurality of hyperplane functions according to the motion trail coordinate set;

determining two parallel hyperplane functions in the hyperplane functions by using a preset geometric interval, and performing formula conversion on the two parallel hyperplane functions to obtain a constraint condition;

converting the constraint condition into an unconstrained condition by utilizing the Lagrange number multiplication, and calculating the unconstrained condition to obtain an optimal hyperplane in the two parallel hyperplane functions;

and calculating the movement track of the accompanying staff and the movement track of the external staff by using the optimal hyperplane to obtain the distance between the accompanying staff and the external staff.

Optionally, the optimal hyperplane is obtained by the following formula:

f(x)＝(w^tx+b)

wherein f (x) represents an optimal hyperplane function, w^tIs a coordinate set of the motion trail, x is the distance between the accompanying staff and the external staff, and b is a real number displacement item.

Optionally, the determining whether the employee portrait images are matched with a preset internal employee face library consistently includes:

acquiring a staff identification corresponding to the staff image, matching the staff portrait picture and the corresponding staff identification with a preset internal staff face library to obtain a matching numerical value, if the matching numerical value is smaller than a preset threshold value, determining that the staff portrait picture is inconsistent with the internal staff face library in matching, and if the matching numerical value is larger than or equal to the preset threshold value, determining that the staff portrait picture is consistent with the internal staff face library in matching.

Optionally, the recognizing the employee image to be recognized by using the pre-constructed face recognition model to obtain an employee image, including:

performing feature extraction on the employee picture to be recognized by using a convolution pooling layer in the face recognition model to obtain a feature map;

utilizing an up-sampling layer in the face recognition model to up-sample the feature map to obtain a feature sampling map;

splicing the feature sampling image and the feature image by using a full connection layer in the face recognition model to obtain a spliced image;

and outputting the spliced picture by using an activation function in the face recognition model to obtain the staff portrait picture.

In order to solve the above problem, the present invention further provides an employee behavior recognition apparatus based on a behavior trace, where the apparatus includes:

the face recognition module is used for acquiring a picture of the employee to be recognized, and recognizing the picture of the employee to be recognized by using a pre-constructed face recognition model to obtain a portrait picture of the employee;

the staff matching module is used for judging whether the staff portrait pictures are matched with a preset internal staff face library or not;

the internal employee violation detection module is used for determining that the employee portrait picture is an internal employee image if the employee portrait picture is matched with the internal employee face library consistently, acquiring track coordinates of the employee portrait picture, generating an internal employee motion track according to the track coordinates, and determining violation conditions of internal employees corresponding to the employee picture to be identified according to the internal employee motion track;

the external staff track generation module is used for determining that the staff portrait picture is an external staff image if the matching of the staff portrait picture and the internal staff face library is inconsistent, acquiring track coordinates of the staff portrait picture and generating an external staff movement track according to the track coordinates;

the accompanying staff judging module is used for judging whether an accompanying staff image exists in the staff portrait image or not;

and the external employee violation detection module is used for outputting violation information of external employees if the accompanying employee image does not exist in the employee portrait picture, acquiring a movement track of an accompanying employee if the accompanying employee image exists in the employee portrait picture, inputting the movement track of the accompanying employee and the movement track of the external employee into a preset support vector machine model to obtain the distance between the accompanying employee and the external employees, and determining violation conditions of the external employees according to the distance between the accompanying employee and the external employees.

In order to solve the above problem, the present invention also provides an electronic device, including:

a memory storing at least one computer program; and

and the processor executes the computer program stored in the memory to realize the employee behavior identification method based on the behavior track.

In order to solve the above problem, the present invention further provides a computer medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the method for identifying staff behaviors based on behavior tracks.

In the embodiment of the invention, firstly, a pre-constructed face recognition model is used for recognizing employee pictures to be recognized to obtain employee portrait pictures; secondly, generating an internal staff movement track according to the track coordinates of the staff portrait pictures, and judging the violation of internal staff according to the internal staff movement track; and then whether the external staff has the violation caused by the accompanying staff is identified, the distance between the accompanying staff and the external staff is calculated by using a support vector machine model, and the violation behaviors of the external staff are judged according to the distance range between the accompanying staff and the external staff, so that the problem that whether the violation conditions exist in the work of the staff cannot be accurately identified can be solved, the potential safety hazard problem of a work area is reduced, and the accuracy of detecting the violation conditions of the staff is improved. Therefore, the employee behavior recognition method, the employee behavior recognition device, the electronic equipment and the storable medium based on the behavior track, which are provided by the embodiment of the invention, can improve the accuracy of detecting the violation condition of the employee.

Drawings

Fig. 1 is a schematic flow chart of an employee behavior identification method based on a behavior trajectory according to an embodiment of the present invention;

fig. 2 is a schematic block diagram of an employee behavior recognition apparatus based on a behavior trace according to an embodiment of the present invention;

fig. 3 is a schematic internal structural diagram of an electronic device implementing an employee behavior recognition method based on a behavior trace according to an embodiment of the present invention;

the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The embodiment of the invention provides an employee behavior identification method based on behavior tracks. The execution subject of the employee behavior recognition method based on the behavior track includes, but is not limited to, at least one of electronic devices such as a server and a terminal, which can be configured to execute the method provided by the embodiment of the present application. In other words, the employee behavior recognition method based on the behavior trace may be executed by software or hardware installed in a terminal device or a server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.

Referring to a flow diagram of an employee behavior recognition method based on a behavior trace, which is shown in fig. 1 and provided by an embodiment of the present invention, in the embodiment of the present invention, the employee behavior recognition method based on the behavior trace includes:

and S1, acquiring a picture of the employee to be recognized, and recognizing the picture of the employee to be recognized by using a pre-constructed face recognition model to obtain a portrait picture of the employee.

In the embodiment of the invention, the picture of the employee to be identified is a picture to be identified containing a picture of the portrait of the employee, and the picture of the employee to be identified can be obtained from the picture which is shot by the camera and contains the portrait of the employee. The staff portrait picture is an identified picture containing staff portraits.

In the embodiment of the invention, before the pre-constructed face recognition model is used for recognizing the employee picture to be recognized, the employee picture to be recognized can be pre-processed, so that the defects of insufficient gray scale, noise, contrast and the like caused by different acquisition environments (such as illumination brightness, equipment performance and the like) and the problems of uncertain size and position of the portrait in the whole image caused by long and short distance and different focal lengths can be avoided, and the consistency of the size and position of the portrait in the portrait picture and the quality of the portrait picture can be improved by pre-processing the image.

In the embodiment of the invention, the pre-constructed face recognition model is used for carrying out feature extraction on the employee picture to be recognized to obtain the portrait features of the employee picture to be recognized, so that the employee portrait picture recognized the portrait of the employee is output. Wherein the face recognition model comprises: a convolution pooling layer, an upsampling layer, a full connection layer, and an activation function.

In detail, the identifying the employee image to be identified by using the pre-constructed face identification model to obtain the employee portrait image includes:

In the embodiment of the present invention, the upsampling refers to sampling the feature map to a specified resolution, for example, after a (416, 416, 3) employee image to be identified is subjected to a series of convolution pooling operations, a (13, 13, 16) feature map is obtained, and in order to compare the feature map with the corresponding employee image to be identified, the feature map needs to be changed to the (416, 416, 3) size, and this process is called upsampling.

Further, in order to better understand the feature semantic information of the feature sampling map, the feature sampling map and the feature map may be spliced to obtain a spliced image.

In an optional embodiment of the present invention, the upsampling may be implemented by a currently known linear interpolation algorithm, and the stitching may be implemented by a currently known stitching algorithm, such as a surf (speeded Up Robust features) algorithm, where the activation function may be a ReLU function, and may activate the stitched picture to obtain the staff portrait picture finally including the staff portrait.

And S2, judging whether the staff portrait picture is matched with a preset internal staff face library or not.

In the embodiment of the present invention, the internal employee face library is a face library constructed according to an internal employee identifier, where the internal employee identifier includes: internal employee ID and internal employee face.

In detail, the judging whether the employee portrait images are matched with a preset internal employee face library consistently includes:

In the embodiment of the invention, the matching numerical value is obtained by matching the staff face picture and the corresponding staff ID with the internal staff face library.

And S3, if the employee portrait picture is matched with the internal employee face library consistently, determining that the employee portrait picture is an internal employee picture, acquiring track coordinates of the employee portrait picture, generating an internal employee motion track according to the track coordinates, and determining the violation condition of the internal employee corresponding to the employee picture to be identified according to the internal employee motion track.

In the embodiment of the present invention, if the employee portrait image matches the internal employee face library consistently, determining that the employee portrait image is an internal employee image includes: and comparing the matching numerical value with a preset threshold value, and if the matching numerical value is greater than or equal to the preset threshold value, matching the staff portrait picture with the internal staff face library consistently, and determining that the staff portrait picture is an internal staff image.

In an embodiment of the present invention, if the matching value is 0.95 which is greater than the preset threshold value 0.9, and the employee identifier matches the internal employee face library consistently, the employee portrait picture may be identified as an internal employee picture.

In the embodiment of the invention, the track coordinate of the internal staff figure is obtained by identifying the internal staff figure through a plurality of cameras in layout, tracking and positioning the internal staff figure, and determining the track coordinate of the internal staff figure through the indoor position information of the cameras.

In detail, the acquiring of the track coordinates of the staff portrait images includes:

acquiring positioning information of the internal employee image;

In an embodiment of the present invention, the positioning information of the internal employee image may be obtained by positioning the internal employee image according to position information of a plurality of cameras arranged indoors and shooting areas of the plurality of cameras.

In the embodiment of the invention, in order to improve the accuracy of the track coordinate, shooting areas of different cameras, coordinates of the shooting areas and coordinates of markers in the shooting areas can be preset, and the track coordinate of the internal employee image is determined by combining the coordinates of the markers, the coordinates of a plurality of cameras and the positioning information of the internal employee image.

In detail, the generating of the internal staff movement locus according to the locus coordinates includes:

In the embodiment of the invention, the violation condition of the internal staff mainly means that the internal staff enters the operation room without checking a card and enters the operation room by following other staff.

In an optional embodiment of the invention, whether the internal staff movement track is included in a preset staff movement track library is inquired, if the internal staff movement track is not included, the internal staff enters an operation room for less than six minutes, access control information is obtained, internal staff ID is matched with the access control information, if the internal staff ID is matched with the access control information in a consistent manner, the internal staff is already checked, no violation behavior exists, if the internal staff ID is not matched with the access control information in a consistent manner, the internal staff is not checked, and violation behavior following other staff entering the operation room exists.

And S4, if the matching of the employee portrait picture and the internal employee face library is inconsistent, determining that the employee portrait picture is an external employee picture, acquiring the track coordinate of the employee portrait picture, and generating an external employee motion track according to the track coordinate.

In the embodiment of the present invention, if the employee portrait image matches the external employee face library consistently, determining that the employee portrait image is an external employee image includes: and comparing the matching numerical value with a preset threshold value, and if the matching numerical value is smaller than the preset threshold value, matching the staff portrait picture with the internal staff face library is inconsistent, and determining that the staff portrait picture is an external staff image.

In an optional embodiment of the present invention, the method for obtaining the track coordinates of the external staff image and generating the external staff motion track according to the track coordinates is similar to the method for obtaining the track coordinates of the internal staff image and generating the internal staff motion track according to the track coordinates in S3, and therefore, the description is omitted here.

And S5, judging whether the employee image picture contains an image of a companion employee.

In the embodiment of the invention, the external staff needs to accompany the internal staff when entering and exiting the operating room, the distance between the external staff and the accompanying staff when entering the operating room cannot exceed 3 meters, and the external staff breaks rules if the distance exceeds 3 meters.

In one embodiment of the invention, the internal employee ID corresponding to the external employee ID can be inquired through the entrance and exit of the preset operation room, the entrance guard information is obtained, and whether the external employee image has the accompanying employee image or not can be judged by judging whether the entrance guard information comprises the accompanying employee ID or not and judging whether the image obtained by the preset gate post camera comprises the accompanying employee image or not.

And S6, if the image of the accompanying employee does not exist in the image of the employee portrait, outputting the violation information of the external employee.

In the embodiment of the invention, if the entrance guard information does not include the ID of the accompanying staff, the violation information of the external staff is obtained, and if the entrance guard information includes the ID of the accompanying staff, the image acquired by a preset entrance guard camera is used for feature extraction, and the violation information of the external staff can also be obtained without extracting the image of the accompanying staff.

In an embodiment of the invention, whether the ID of the accompanying employee exists in the access control information is judged, and further, the face recognition is performed on the accompanying employee to avoid that when an external employee enters an operation room, the internal employee uses the ID of the internal employee and the ID of the accompanying employee to punch a card for the access control, but only the external employee actually enters the operation room.

S7, if the image of the accompanying staff exists in the portrait picture of the staff, obtaining the movement track of the accompanying staff, inputting the movement track of the accompanying staff and the movement track of the external staff into a preset support vector machine model, obtaining the distance between the accompanying staff and the external staff, and determining the violation condition of the external staff according to the distance between the accompanying staff and the external staff.

In the embodiment of the present invention, if the employee portrait image has the image of the accompanying employee, the method for obtaining the movement track of the accompanying employee is similar to the method for obtaining the track coordinate of the employee portrait image in S3, and generating the movement track of the internal employee according to the track coordinate, and therefore details are not repeated here.

In the embodiment of the invention, the working principle of the support vector machine is that a plurality of hyperplane functions are constructed by mapping the movement locus of the accompanying staff and the movement locus of the external staff to multi-dimensional coordinates, and the optimal hyperplane in the hyperplane functions is selected, so that the distance between the accompanying staff and the external staff is obtained according to the optimal hyperplane.

In detail, the inputting the movement locus of the accompanying staff and the movement locus of the external staff into a preset support vector machine model to obtain the distance between the accompanying staff and the external staff comprises:

In the embodiment of the invention, the maximum distance between the two parallel hyperplane functions is the maximum interval, and the constraint condition can be obtained according to the maximum interval; the constraint condition is that an optimal value of the objective function is found in a limited space; the optimal hyperplane is a plane for segmenting the external person motion track coordinate subset and the accompanying person motion track coordinate subset, wherein the motion track coordinate set comprises: the external person movement track coordinate subset and the accompanying person movement track coordinate subset. Further, the optimal hyperplane is obtained by the following formula:

f(x)＝(w^tx+b)

In an optional embodiment of the invention, the movement tracks of the accompanying staff and the movement tracks of the external staff can be respectively sampled into 12 sets of movement track sets every 5 seconds, the 12 sets of movement track sets are calculated by utilizing the optimal hyperplane, and the distances between a plurality of sets of accompanying staff and the external staff are obtained.

In the embodiment of the invention, after the violation information of the external staff and the violation information of the internal staff are obtained, the violation staff are warned, so that the violation event is prevented from happening, and the safety of the staff is further protected.

In the embodiment of the invention, firstly, a pre-constructed face recognition model is used for recognizing employee pictures to be recognized to obtain employee portrait pictures; secondly, generating an internal staff movement track according to the track coordinates of the staff portrait pictures, and judging the violation of internal staff according to the internal staff movement track; and then whether the external staff has the violation caused by the accompanying staff is identified, the distance between the accompanying staff and the external staff is calculated by using a support vector machine model, and the violation behaviors of the external staff are judged according to the distance range between the accompanying staff and the external staff, so that the problem that whether the violation conditions exist in the work of the staff cannot be accurately identified can be solved, the potential safety hazard problem of a work area is reduced, and the accuracy of detecting the violation conditions of the staff is improved. Therefore, the employee behavior recognition method based on the behavior track provided by the embodiment of the invention can improve the accuracy of detecting the violation condition of the employee.

Fig. 2 is a functional block diagram of the employee behavior recognition apparatus based on the behavior trace according to the present invention.

The employee behavior recognition apparatus 100 based on the behavior trace according to the present invention may be installed in an electronic device. According to the implemented functions, the employee behavior recognition device based on the behavior trajectory may include a face recognition module 101, an employee matching module 102, an internal employee violation detection module 103, an external employee trajectory generation module 104, an accompanying employee determination module 105, and an external employee violation detection module 106, where the modules may also be referred to as units, which are a series of computer program segments that can be executed by a processor of the electronic device and can complete a fixed function, and are stored in a memory of the electronic device.

In the present embodiment, the functions regarding the respective modules/units are as follows:

the face recognition module 101 is configured to acquire a picture of the employee to be recognized, and recognize the picture of the employee to be recognized by using a pre-constructed face recognition model to obtain a portrait picture of the employee.

In detail, the face recognition module 101 performs recognition on the employee image to be recognized by using a pre-constructed face recognition model by executing the following operations to obtain an employee portrait image, including:

In the embodiment of the present invention, the upsampling refers to sampling the feature map to a specified resolution, for example, after a (416, 416, 3) employee image to be identified is subjected to a series of convolution pooling operations, a (13, 13, 16) feature map is obtained, and in order to compare the feature map with the corresponding employee image to be identified, the feature map needs to be changed to the (416, 416, 3) size, and this process is called upsampling. Further, in order to better understand the feature semantic information of the feature sampling map, the feature sampling map and the feature map may be spliced to obtain a spliced image.

The staff matching module 102 is configured to determine whether the staff face pictures are matched with a preset internal staff face library consistently.

In detail, the staff matching module 102 determines whether the staff portrait images are matched with a preset internal staff face library by performing the following operations, including:

The internal employee violation detection module 103 is configured to determine that the employee portrait image is an internal employee image if the employee portrait image is matched with the internal employee face library consistently, obtain a track coordinate of the employee portrait image, generate an internal employee motion track according to the track coordinate, and determine a violation condition of an internal employee corresponding to the employee image to be identified according to the internal employee motion track.

In detail, the internal employee violation detection module 103 obtains the trajectory coordinates of the employee portrait image by performing the following operations, including:

acquiring positioning information of the internal employee image;

In detail, the internal employee violation detection module 103 generates an internal employee movement trajectory from the trajectory coordinates by performing the following operations, including:

The external staff track generation module 104 is configured to determine that the staff portrait images are external staff images, acquire track coordinates of the staff portrait images, and generate external staff motion tracks according to the track coordinates if the staff portrait images are not matched with the internal staff face library.

In an optional embodiment of the present invention, the method for acquiring the track coordinates of the external staff image and generating the external staff movement track according to the track coordinates is similar to the aforementioned method for acquiring the track coordinates of the internal staff image and generating the internal staff movement track according to the track coordinates, and therefore, the description is omitted here.

And the accompanying staff judging module 105 is used for judging whether an image of an accompanying staff exists in the staff portrait picture.

The external employee violation detection module 106 is configured to output violation information of an external employee if the image of the accompanying employee does not exist in the image of the employee, acquire a movement track of the accompanying employee if the image of the accompanying employee exists in the image of the employee, input the movement track of the accompanying employee and the movement track of the external employee to a preset support vector machine model, obtain a distance between the accompanying employee and the external employee, and determine a violation condition of the external employee according to the distance between the accompanying employee and the external employee.

In the embodiment of the invention, if the employee portrait images have the accompanying employee images, the method for acquiring the movement tracks of the accompanying employees is similar to the method for acquiring the track coordinates of the employee portrait images and generating the movement tracks of the internal employees according to the track coordinates, and therefore, the description is omitted.

In detail, the external employee violation detection module 106 inputs the movement trajectory of the accompanying employee and the movement trajectory of the external employee into a preset support vector machine model by performing the following operations, so as to obtain a distance between the accompanying employee and the external employee, including:

f(x)＝(w^tx+b)

In the embodiment of the invention, firstly, a pre-constructed face recognition model is used for recognizing employee pictures to be recognized to obtain employee portrait pictures; secondly, generating an internal staff movement track according to the track coordinates of the staff portrait pictures, and judging the violation of internal staff according to the internal staff movement track; and then whether the external staff has the violation caused by the accompanying staff is identified, the distance between the accompanying staff and the external staff is calculated by using a support vector machine model, and the violation behaviors of the external staff are judged according to the distance range between the accompanying staff and the external staff, so that the problem that whether the violation conditions exist in the work of the staff cannot be accurately identified can be solved, the potential safety hazard problem of a work area is reduced, and the accuracy of detecting the violation conditions of the staff is improved. Therefore, the employee behavior recognition device based on the behavior track provided by the embodiment of the invention can improve the accuracy of detecting the violation condition of the employee.

Fig. 3 is a schematic structural diagram of an electronic device implementing the employee behavior recognition method based on the behavior trace according to the present invention.

The electronic device may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further include a computer program stored in the memory 11 and executable on the processor 10, such as an employee behavior recognition program based on a behavior trace.

The memory 11 includes at least one type of media, which includes flash memory, removable hard disk, multimedia card, card type memory (e.g., SD or DX memory, etc.), magnetic memory, local disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used to store not only application software installed in the electronic device and various types of data, such as codes of employee behavior recognition programs based on behavior traces, but also temporarily store data that has been output or is to be output.

The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules (e.g., employee behavior recognition programs based on behavior tracks, etc.) stored in the memory 11 and calling data stored in the memory 11.

The communication bus 12 may be a PerIPheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The communication bus 12 is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.

Fig. 3 shows only an electronic device having components, and those skilled in the art will appreciate that the structure shown in fig. 3 does not constitute a limitation of the electronic device, and may include fewer or more components than those shown, or some components may be combined, or a different arrangement of components.

For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

Optionally, the communication interface 13 may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices.

Optionally, the communication interface 13 may further include a user interface, which may be a Display (Display), an input unit (such as a Keyboard (Keyboard)), and optionally, a standard wired interface, or a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.

It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.

The employee behavior recognition program stored in the memory 11 of the electronic device and based on the behavior trace is a combination of a plurality of computer programs, and when running in the processor 10, can realize that:

Specifically, the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the computer program, which is not described herein again.

Further, the electronic device integrated module/unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable medium. The computer readable medium may be non-volatile or volatile. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).

An embodiment of the present invention may further provide a computer medium, where the computer medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program may implement:

Further, the computer usable medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules 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 present embodiment.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.

The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An employee behavior identification method based on behavior tracks is characterized by comprising the following steps:

2. The employee behavior recognition method based on behavior trajectory according to claim 1, wherein the generating of the internal employee motion trajectory according to the trajectory coordinates comprises:

3. The employee behavior recognition method based on behavior track as claimed in claim 1, wherein the obtaining of track coordinates of the employee portrait photo comprises:

acquiring positioning information of the internal employee image;

4. The employee behavior recognition method based on the behavior track as claimed in claim 1, wherein the step of inputting the movement track of the accompanying employee and the movement track of the external employee into a preset support vector machine model to obtain the distance between the accompanying employee and the external employee comprises the steps of:

5. The employee behavior recognition method based on behavior tracks according to claim 4, wherein the optimal hyperplane is obtained by the following formula:

f(x)＝(w^tx+b)

6. The employee behavior recognition method based on behavior trajectory according to claim 1, wherein said determining whether the employee portrait image matches a preset internal employee face library comprises:

7. The behavior trace-based employee behavior recognition method according to any one of claims 1 to 6, wherein the face recognition model comprises: the method comprises a convolution pooling layer, an upper sampling layer, a full connection layer and an activation function, wherein a pre-constructed face recognition model is used for recognizing the employee pictures to be recognized to obtain the employee portrait pictures, and the method comprises the following steps:

8. An employee behavior recognition device based on a behavior track, the device comprising:

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores computer program instructions executable by the at least one processor to enable the at least one processor to perform a method of employee behaviour recognition based on a behaviour track according to any one of claims 1 to 7.

10. A computer medium storing a computer program, wherein the computer program, when executed by a processor, implements the method for employee behavior recognition based on behavior tracks according to any one of claims 1 to 7.