CN112949546A - Off-duty detection method and device based on artificial intelligence perception of station service state - Google Patents
Off-duty detection method and device based on artificial intelligence perception of station service state Download PDFInfo
- Publication number
- CN112949546A CN112949546A CN202110291962.7A CN202110291962A CN112949546A CN 112949546 A CN112949546 A CN 112949546A CN 202110291962 A CN202110291962 A CN 202110291962A CN 112949546 A CN112949546 A CN 112949546A
- Authority
- CN
- China
- Prior art keywords
- station
- target object
- current
- image data
- workstation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
- G06Q10/1091—Recording time for administrative or management purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Multimedia (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Human Computer Interaction (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The method comprises the steps of detecting station identification of a current station and whether a target object exists on the current station based on station image data of the current station, then counting off-post time of the target object based on a detection result, and finally carrying out off-post reminding according to the off-post time of the target object. Compared with the existing off-post detection system which usually needs to preset a working time interval, when a worker leaves off the post for some reason to do other temporary work, the system can not automatically respond to the situation.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to an off-duty detection method and device based on artificial intelligence perception of station service states.
Background
The business hall is used as a display window of the power system facing the society, and the service level of the work such as business handling, charging and the like can directly reflect the impression of people on the power service. Whether a customer can be waited for the first time or not and whether a worker can solve the customer problem in time or not in the daily work of a business hall is the important factor for guaranteeing the customer service satisfaction. In order to improve the overall service level of business hall workers, office organizations such as government offices and banks are provided with off-post detection systems according to requirements.
However, the existing off-duty detection system usually needs to set a working time interval in advance, but when a worker leaves off duty for some reason to do other temporary work, the system cannot automatically respond to the situation, and the situation of off-duty false alarm is easily caused.
Disclosure of Invention
In view of this, an object of the present application is to provide an off-post detection method and apparatus based on artificial intelligence perception of a station service state, which combine and analyze a station identifier and a target object of a current station, so as to avoid the occurrence of an off-post false alarm and improve the accuracy of off-post detection.
In a first aspect, the application provides an off-post detection method based on artificial intelligence perception of a station service state, and the off-post detection method includes:
detecting a station identifier of a current station and whether a target object exists on the current station or not based on station image data of the current station;
counting the off-duty time of the target object based on the detection result;
and performing off-Shift reminding according to the off-Shift time of the target object.
Preferably, the detecting, based on the workstation image data of the current workstation, the workstation identifier of the current workstation and whether the target object exists on the current workstation includes:
detecting a station identifier of a current station based on station image data of the current station;
if the station identification indicates that the current station is in a service state, detecting whether a target object exists on the current station based on the station image data;
or inputting the station image data of the current station into a pre-trained target detection model, and identifying the station identifier of the current station and whether a target object exists on the current station.
Preferably, the target detection model is trained by:
acquiring a plurality of station image data samples containing station identifications and target objects;
and inputting the station image data samples into a pre-constructed deep learning model for training to obtain a trained target detection model.
Preferably, if the station identifier indicates that the current station is in a service state, detecting whether a target object exists on the current station based on the station image data includes:
if the station identification indicates that the current station is in a service state, detecting whether image characteristic identification is included in the station image data;
if the image data of the station is detected to comprise the image characteristic identification, determining that a target object exists on the current station;
and if the image characteristic identification is not included in the station image data, determining that no target object exists on the current station.
Preferably, the image feature identification comprises at least one of: a head image, a body upper part image and a body whole image.
Preferably, the performing off Shift reminding according to the off Shift time of the target object includes:
acquiring a preset off-duty specified time threshold;
and if the off-Shift time exceeds the off-Shift specified time threshold, sending a prompt to the target object.
Preferably, the off-duty reminding comprises any one of a short message reminding, a voice call reminding and a broadcast reminding.
In a second aspect, the present application further provides an off-post detection device based on artificial intelligence perception station service state, the off-post detection device includes:
the detection module is used for detecting the station identification of the current station and whether a target object exists on the current station based on the station image data of the current station;
the statistic module is used for counting the off-duty time of the target object based on the detection result;
and the reminding module is used for reminding off duty according to the off duty time of the target object.
In a third aspect, the present application further provides an electronic device, including: the system comprises a processor, a memory and a bus, wherein the memory stores machine readable instructions executable by the processor, the processor and the memory are communicated through the bus when an electronic device runs, and the machine readable instructions are executed by the processor to execute the steps of the off duty detection method based on the service state of the artificial intelligence perception workstation.
In a fourth aspect, the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the off-Shift detection method based on the service state of the artificial intelligence perception workstation.
The application provides a station leaving detection method and device based on artificial intelligence perception station service state, wherein the station leaving detection method comprises the steps of detecting station identification of a current station and whether a target object exists on the current station or not based on station image data of the current station, then counting off time of the target object based on a detection result, and finally carrying out off-post reminding according to the off-post time of the target object.
Compared with the method that the working time interval is required to be preset by an off-post detection system in the prior art, but when workers leave off the post for some reason to do other temporary work, the system cannot automatically respond to the situation, the off-post analysis method detects the station identification of the current station and whether the target object exists on the current station, and then performs the off-post analysis based on the detection result, so that the station identification and the target object of the current station are combined and analyzed, the situation of off-post misinformation can be avoided, and the accuracy of the off-post detection is improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a flowchart of an off-duty detection method based on station service state sensing by artificial intelligence according to an embodiment of the present disclosure;
fig. 2 is a block diagram of a flow of a business hall off duty detection method according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an off-duty detection apparatus for sensing a service state of a workstation based on artificial intelligence according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. Every other embodiment that can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present application falls within the protection scope of the present application.
First, an application scenario to which the present application is applicable will be described. The method and the system can be applied to off-duty detection systems of business halls, the business halls serve as display windows of the power system facing the society, service levels of business handling, charging and other work can be handled, and impressions of people on power service can be directly reflected. Under the condition that three services of power distribution, power transmission and power transformation all meet the requirements of people, the service level of a business hall is particularly important. Whether a customer can be waited for the first time or not and whether a worker can solve the customer problem in time or not in the daily work of a business hall is the key to ensuring the customer service satisfaction, and further, the business hall service level is improved.
In order to improve the overall service level of business hall workers, office organizations such as government offices and banks are provided with off-post detection systems according to requirements. The off-post detection system can detect off-post in the monitoring area, and when abnormal conditions occur, the system can actively trigger alarm. The staff off-post detection system under intelligent video analysis can automatically detect the working post of a worker, once the fact that the time that the worker is not in a working area exceeds the set time is found, the system can give an alarm in real time, alarm information is transmitted to a monitoring end, and then voice prompt is given through a field voice camera to enable the worker to return to the working post in time.
However, the existing off-duty detection system usually needs to set a working time interval in advance, and when a worker leaves off duty for some reason to do other temporary work, the system cannot automatically respond to the situation and falsely reports the situation as off duty.
Based on the above, the embodiment of the application provides a station leaving detection method and device based on artificial intelligence perception of station service states.
Referring to fig. 1, fig. 1 is a flowchart illustrating an off-duty detection method based on artificial intelligence perception of a service state of a workstation according to an embodiment of the present disclosure. As shown in fig. 1, the off-Shift detection method provided in the embodiment of the present application is applied to an off-Shift detection system, and includes:
s110, detecting the station identification of the current station and whether the target object exists on the current station based on the station image data of the current station.
Firstly, the station image data is image data of a current station and has a certain association relation with the current station, when a monitoring camera shoots, the monitoring camera can obtain the image data of a plurality of stations, the image data of each station are separated from each other to obtain the station image data of the current station, and information data related to a target object can be obtained by analyzing the station image data of the current station.
And secondly, the station identification is used for representing whether the current station is in a service state, namely for representing whether the current station is in a normal service state or a suspended service state. The station identification can be a service state indication board of a service window where the current station is located, and when the prompt information on the service state indication board is service suspension, the current station is in a service suspension state; and when the prompt information on the service state indicator is in the process of handling each service, the current station is considered to be in a normal service state. When the current workstation is in the service state, if the target object is not on the workstation, the target object can be considered to be in the off-duty state.
The target object refers to a worker on the station in a specific time period, and the worker on the current station can be determined according to a schedule of a business hall, so that if the worker leaves the post, the worker can know who sends the alarm reminding information.
And S120, counting the off-Shift time of the target object based on the detection result.
The first type is that the station identifier of the current station indicates that the current station is in a service state, and a target object exists on the current station; the second method is that the station mark of the current station indicates that the current station is in a service state, and no target object exists on the current station; the third is that the station mark of the current station indicates that the current station is in a service suspension state, and a target object exists on the current station; fourthly, the station identification of the current station indicates that the current station is in a service suspension state, and no target object exists on the current station; regarding the first, third and fourth detection results, the condition of the current station is considered to be in a normal state, when the second detection result occurs, the current station is considered to be abnormal, namely, the target object of the current station is abnormal off duty, and then the off duty time of the target object is counted.
S130, reminding off duty according to the off duty time of the target object.
Here, the off-post specified time threshold is set in advance, and whether or not to perform off-post reminding on the target object is determined according to the magnitude relation between the off-post time of the target object and the off-post specified time threshold.
When the off-Shift time of the target object exceeds the off-Shift specified time threshold, carrying out off-Shift reminding on the target object; when the off-duty time of the target object does not exceed the off-duty specified time threshold, the target object does not need to be reminded of going off duty, and the detection mode can avoid the problem of misjudgment of the target object due to the off-duty caused by a temporary event, wherein the temporary event can be water receiving and drinking, going to a toilet, leading assignment, temporary work and the like.
Furthermore, a hierarchical off-post specified time threshold value can be set, and when the off-post time of the target object triggers the first-level off-post specified time threshold value, the off-post detection system directly sends a reminding message to the target object; when the off-post time of the target object triggers the second off-post specified time threshold, the off-post detection system sends alarm information to the management monitoring personnel, so that the management monitoring personnel can know the off-post condition of the target object and perform manual intervention on the target object in time, and the target object is reminded to return to the station in time without influencing the continuous work.
The embodiment of the application provides a station leaving detection method based on artificial intelligence perception of station service states, which comprises the steps of detecting station identification of a current station and whether a target object exists on the current station based on station image data of the current station, then counting off-post time of the target object based on a detection result, and finally carrying out off-post reminding according to the off-post time of the target object. Furthermore, the station identification of the current station and the target object on the current station can be detected, and off-post analysis is performed based on the detection result, so that the station identification of the current station and the target object are combined and analyzed, the situation of off-post false alarm can be avoided, and the off-post detection accuracy is improved.
In the embodiment of the present application, as a preferred embodiment, the step S110 includes:
detecting a station identifier of a current station based on station image data of the current station; if the station identification indicates that the current station is in a service state, detecting whether a target object exists on the current station based on the station image data; or inputting the station image data of the current station into a pre-trained target detection model, and identifying the station identifier of the current station and whether a target object exists on the current station.
In the step, two implementation modes are included for detecting the station identifier of the current station and whether the target object exists on the current station or not based on the station image data of the current station.
The first implementation mode is that firstly, the station identifier of the current station is detected based on the station image data of the current station, and if the station identifier indicates that the current station is in a service state, whether the target object exists on the current station is detected based on the station image data. The station identification and the target object are detected in sequence, so that the detection time and the detection cost can be saved, and if the station identification indicates that the current station is not in a service state (in a service suspension state), the subsequent target object detection is not needed.
The second implementation mode is that the workstation image data of the current workstation is input into a pre-trained target detection model, and the workstation identification of the current workstation and whether a target object exists on the current workstation are identified. Here, the station identifier and the target object are detected simultaneously by using the target detection model, and whether the current station indicated by the station identifier of the current station is in a service state and whether the target object exists on the current station can be directly obtained by using one target detection model. Therefore, the result can be identified through one target detection model, and the operation is convenient.
Specifically, the target identification model is a deep learning model, and different network models are set up to test and evaluate an open source data set in target detection. In the embodiment of the application, the deep learning model is a YOLOv5s network structure, and the workstation identification and the target object in the workstation image data are identified through the YOLOv5s network structure.
Before the workstation image data is identified by using the YOLOv5s deep learning model, the model needs to be trained in advance.
When the target detection model is trained, a data sample related to a station identification for identifying a current station and a data sample related to whether a target object exists on the current station can be simultaneously input into the target detection model for training, or the target detection model can be divided into two sub-models, and the two sub-models are respectively trained.
Further, step S110 trains the target detection model by:
acquiring a plurality of station image data samples containing station identifications and target objects; and inputting the station image data samples into a pre-constructed deep learning model for training to obtain a trained target detection model.
Here, need be to station image data when a large amount of daily services are gathered to the business office, mark station sign and target object, wherein, target object can be the staff, and the station sign can be service status sign.
In order to improve the identification precision and robustness of the model, the workstation image data sample is expanded by using an IMGAUG data enhancement tool, the modes of fuzzification, plane rotation, mirror image turning, Gaussian noise, scaling and the like of a data set picture are included, and the workstation image data sample is used for training a YOLOv5s target detection model used in the embodiment of the application.
Here, a plurality of workstation image data samples including the workstation identifiers and the target objects may be input into a pre-constructed deep learning model, and the deep learning model is trained at the same time, so that the trained target detection model may directly detect the workstation identifiers of the current workstation and whether the target objects exist on the current workstation. And a plurality of station image data samples containing station identifications and station image data samples containing target objects can be respectively input into the deep learning model for training to obtain two trained sub-models, and the two trained sub-models are respectively used for detecting the station identifications of the current station and detecting whether the target objects exist on the current station.
Preferably, in step S110, if the workstation identifier indicates that the current workstation is in the service state, detecting whether a target object exists on the current workstation based on the workstation image data includes:
if the station identification indicates that the current station is in a service state, detecting whether image characteristic identification is included in the station image data; if the image data of the station is detected to comprise the image characteristic identification, determining that a target object exists on the current station; and if the image characteristic identification is not included in the station image data, determining that no target object exists on the current station.
Here, the image feature identifier is included in a particular region of the workstation image data, where the particular region may be the region where the workstation is located. For example, the area where the workstation pointed by the monitoring camera is located may be a case where the shooting position or angle of the monitoring camera is fixed, or the area where the workstation pointed by the monitoring camera is located may be a case where the shooting position of the monitoring camera is fixed but the angle is changed, and the monitoring camera rotates to a certain angle range.
Further, the image feature identification comprises at least one of: a head image, a body upper part image and a body whole image.
The target detection system inputs image characteristic marks of all workers corresponding to the station in advance, and the image characteristic marks form an image characteristic data set, wherein the image characteristic marks can be head images, upper body images of a human body or whole body images of the human body, so that the workers corresponding to the current station in a certain working time period can be determined according to a shift schedule of a business hall, and the image characteristic marks corresponding to the workers are obtained.
Specifically, when off-duty detection is performed, a target worker of a current station can be determined according to a schedule; then determining an image characteristic identifier corresponding to the target worker from the image characteristic data set; and then, whether the person on the current station is the target worker can be judged according to the determined image characteristic identification corresponding to the target worker.
In the embodiment of the present application, as a preferred embodiment, the step S130 includes:
acquiring a preset off-duty specified time threshold; and if the off-Shift time exceeds the off-Shift specified time threshold, sending a prompt to the target object.
The first method is to set only one off-post specified time threshold, and when the off-post time exceeds the off-post specified time threshold, a prompt is sent to a target object, wherein the prompt sending mode can be short message prompt, voice telephone prompt, broadcast prompt, monitoring management personnel, and the monitoring management personnel prompt the staff to return to the station as soon as possible.
The second mode is that a threshold value of the specified time of the hierarchical leaving post is set, the numerical value of the threshold value of the specified time of the first level leaving post is small, which indicates that the leaving post time is short, and the corresponding influence is small, and for the condition, the target object can be directly reminded; the numerical value of the second off-post specified time threshold value is larger, which indicates that the off-post time is longer, and the corresponding influence is also large, and for the situation, manual intervention can be performed, for example, a monitoring manager is notified first, and then the monitoring manager reminds the target object to return to the station in time.
Specifically, when the off-Shift time of the target object exceeds a first-level off-Shift specified time threshold and is less than a second-level off-Shift specified time threshold, the off-Shift detection system directly performs off-Shift reminding on the target object, wherein the off-Shift reminding comprises any one of short message reminding, voice telephone reminding and broadcast reminding; when the off-post time of the target object exceeds the second off-post specified time threshold, the off-post detection system sends alarm information to the management monitoring personnel, so that the management monitoring personnel can know the off-post condition of the target object and perform manual intervention on the target object in time, and remind the target object to return to the station in time without influencing the continuous work.
Further, please refer to fig. 2, wherein fig. 2 is a block diagram of a flow of a business hall off-duty detection method provided by the embodiment of the present application, as shown in fig. 2:
step 1: target detection, specifically, target detection is carried out based on a YOLOv5s deep learning model, and various targets in the picture are identified, (the detection items comprise a work card pause service state, a work card normal service state and a person).
Step 2: judging whether the work card detected in the step 1 is in a service suspension state, if not, entering a step 3; if so, go to step 7.
And step 3: judging whether the target object detected in the step 1 is a person or not, if so, judging that a worker is present, and entering a step 7; if not, no staff exists, and the step 4 is carried out.
And 4, step 4: and (4) starting or continuing off duty timing according to the judgment result of the step (3) and no staff in the picture.
Here, the flow chart is a flow of detecting one frame, and if the detection result of the previous frame is on duty and the detection result of the current frame is off duty, the off duty timing is started; if the detection result of the previous frame is off duty and the detection result of the current frame is still off duty, continuing off duty timing.
And 5: judging whether the off-duty time exceeds the off-duty specified time threshold value or not according to the time timed in the step 4, and if so, entering a step 6; if not, the frame detection is finished.
Step 6: and 5, according to the judgment result of the step 5, when the off-duty timing exceeds the off-duty specified time threshold, alarming to remind a monitoring manager, and prompting the staff to return to the station as soon as possible by the monitoring manager.
And 7: and 3, clearing off the post timing if workers exist in the picture according to the judgment result of the step 3.
The off-post detection method based on the artificial intelligence perception station service state can detect whether a station mark of a current station and a target object exist on the current station, namely, the function of automatically recognizing the state of a staff information card is added, then off-post analysis is carried out based on a detection result, and therefore the station mark and the target object of the current station are combined and analyzed, operation of an automatic control off-post detection system is achieved, the problem that the off-post detection system cannot respond correctly and gives false off-post when a staff leaves an office to process temporary work is solved, meanwhile, the manual intervention degree of the system is effectively reduced, tedious operation of adjusting off-post detection system configuration due to influence of overall scheduling of a business hall is avoided, and off-post detection accuracy is improved.
Based on the same inventive concept, the embodiment of the present application further provides an off-post detection device based on the artificial intelligence perception station service state, which corresponds to the off-post detection method based on the artificial intelligence perception station service state.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an off-Shift detection apparatus based on station service state sensing by artificial intelligence according to an embodiment of the present application, and as shown in fig. 3, the off-Shift detection apparatus 300 includes:
the detection module 310 is configured to detect a workstation identifier of a current workstation and whether a target object exists on the current workstation based on workstation image data of the current workstation;
the counting module 320 is used for counting the off duty time of the target object based on the detection result;
and the reminding module 330 is configured to perform off-Shift reminding according to the off-Shift time of the target object.
Preferably, when the detecting module 310 is configured to detect the workstation identifier of the current workstation and whether the target object exists on the current workstation based on the workstation image data of the current workstation, the detecting module 310 is configured to:
detecting a station identifier of a current station based on station image data of the current station;
if the station identification indicates that the current station is in a service state, detecting whether a target object exists on the current station based on the station image data;
or inputting the station image data of the current station into a pre-trained target detection model, and identifying the station identifier of the current station and whether a target object exists on the current station.
Preferably, the detection module 310 is used to train the target detection model by:
acquiring a plurality of station image data samples containing station identifications and target objects;
and inputting the station image data samples into a pre-constructed deep learning model for training to obtain a trained target detection model.
Preferably, when the detecting module 310 is configured to detect whether a target object exists on the current workstation based on the workstation image data if the workstation identifier indicates that the current workstation is in the service state, the detecting module 310 is configured to:
if the station identification indicates that the current station is in a service state, detecting whether image characteristic identification is included in the station image data;
if the image data of the station is detected to comprise the image characteristic identification, determining that a target object exists on the current station;
and if the image characteristic identification is not included in the station image data, determining that no target object exists on the current station.
Preferably, the image feature identification comprises at least one of: a head image, a body upper part image and a body whole image.
Preferably, when the reminding module 330 is configured to perform off-Shift reminding according to the off-Shift time of the target object, the reminding module 330 is configured to:
acquiring a preset off-duty specified time threshold;
and if the off-Shift time exceeds the off-Shift specified time threshold, sending a prompt to the target object.
Preferably, the off-duty reminding comprises any one of a short message reminding, a voice call reminding and a broadcast reminding.
The off-post detection device based on the artificial intelligence perception station service state comprises a detection module, a statistics module and a reminding module, wherein the detection module is used for detecting a station identifier of a current station and whether a target object exists on the current station based on station image data of the current station; the statistic module is used for counting the off-duty time of the target object based on the detection result; and the reminding module is used for reminding off duty according to the off duty time of the target object. Therefore, the station identification and the target object of the current station are combined and analyzed, the occurrence of false off-post alarm can be avoided, and the accuracy of off-post detection is improved.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 4, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.
The memory 420 stores machine-readable instructions executable by the processor 410, when the electronic device 400 runs, the processor 410 communicates with the memory 420 through the bus 430, and when the machine-readable instructions are executed by the processor 410, the steps of the off-duty detection method based on the artificial intelligence perception workstation service state in the method embodiment shown in fig. 1 may be executed.
An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the step of the off-post detection method based on the service state of the artificial intelligence sensing workstation in the method embodiment shown in fig. 1 may be executed.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application 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 functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the exemplary embodiments of the present application, and are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A off-post detection method based on artificial intelligence perception of station service state is characterized by comprising the following steps:
detecting a station identifier of a current station and whether a target object exists on the current station or not based on station image data of the current station;
counting the off-duty time of the target object based on the detection result;
and performing off-Shift reminding according to the off-Shift time of the target object.
2. The off-post detection method of claim 1, wherein the detecting, based on the workstation image data of the current workstation, the workstation identifier of the current workstation and whether the target object exists on the current workstation comprises:
detecting a station identifier of a current station based on station image data of the current station;
if the station identification indicates that the current station is in a service state, detecting whether a target object exists on the current station based on the station image data;
or inputting the station image data of the current station into a pre-trained target detection model, and identifying the station identifier of the current station and whether a target object exists on the current station.
3. The off-Shift detection method according to claim 2, wherein the target detection model is trained by:
acquiring a plurality of station image data samples containing station identifications and target objects;
and inputting the station image data samples into a pre-constructed deep learning model for training to obtain a trained target detection model.
4. The off-post detection method of claim 2, wherein detecting whether a target object exists on the current workstation based on the workstation image data if the workstation identifier indicates that the current workstation is in a service state comprises:
if the station identification indicates that the current station is in a service state, detecting whether image characteristic identification is included in the station image data;
if the image data of the station is detected to comprise the image characteristic identification, determining that a target object exists on the current station;
and if the image characteristic identification is not included in the station image data, determining that no target object exists on the current station.
5. The off-Shift detection method according to claim 4, wherein the image feature identification comprises at least one of: a head image, a body upper part image and a body whole image.
6. The off Shift detection method according to claim 1, wherein the performing off Shift reminding according to the off Shift time of the target object comprises:
acquiring a preset off-duty specified time threshold;
and if the off-Shift time exceeds the off-Shift specified time threshold, sending a prompt to the target object.
7. The off Shift detection method according to claim 1, wherein the off Shift reminder includes any one of a short message reminder, a voice call reminder, and a broadcast reminder.
8. The utility model provides a detection device off sentry based on artificial intelligence perception station service status which characterized in that, detection device off sentry includes:
the detection module is used for detecting the station identification of the current station and whether a target object exists on the current station based on the station image data of the current station;
the statistic module is used for counting the off-duty time of the target object based on the detection result;
and the reminding module is used for reminding off duty according to the off duty time of the target object.
9. An electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine readable instructions executable by the processor, when the electronic device runs, the processor and the memory communicate through the bus, and the processor executes the machine readable instructions to execute the steps of the off duty detection method based on the service state of the artificial intelligence perception workstation according to any one of claims 1 to 7.
10. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the off-Shift detection method based on station service status artificial intelligence perception according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110291962.7A CN112949546A (en) | 2021-03-18 | 2021-03-18 | Off-duty detection method and device based on artificial intelligence perception of station service state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110291962.7A CN112949546A (en) | 2021-03-18 | 2021-03-18 | Off-duty detection method and device based on artificial intelligence perception of station service state |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112949546A true CN112949546A (en) | 2021-06-11 |
Family
ID=76226593
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110291962.7A Pending CN112949546A (en) | 2021-03-18 | 2021-03-18 | Off-duty detection method and device based on artificial intelligence perception of station service state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112949546A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113489929A (en) * | 2021-08-06 | 2021-10-08 | 远见智诚市场调研咨询(广东)有限公司 | Method and device for monitoring supervision of garbage classification, computer equipment and storage medium |
| CN113640847A (en) * | 2021-06-17 | 2021-11-12 | 广州启盟信息科技有限公司 | Property positioning method, device and system based on GPS and image |
| CN113780231A (en) * | 2021-09-22 | 2021-12-10 | 国网内蒙古东部电力有限公司信息通信分公司 | Legacy tool detection method and device, electronic equipment and storage medium |
| CN113936293A (en) * | 2021-09-08 | 2022-01-14 | 重庆中科云从科技有限公司 | Video information-based off-duty personnel detection method, control device and storage medium |
| CN114429642A (en) * | 2021-12-23 | 2022-05-03 | 华能招标有限公司 | Abnormal behavior identification method for bid evaluation expert in remote bid evaluation video conference process |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104618685A (en) * | 2014-12-29 | 2015-05-13 | 国家电网公司 | Intelligent image analysis method for power supply business hall video monitoring |
| CN109637096A (en) * | 2019-01-09 | 2019-04-16 | 张珣 | Key post personnel leave the post early warning system |
| CN110826538A (en) * | 2019-12-06 | 2020-02-21 | 合肥科大智能机器人技术有限公司 | Abnormal off-duty identification system for electric power business hall |
| CN111666841A (en) * | 2020-05-25 | 2020-09-15 | 山西长河科技股份有限公司 | Method for identifying off-duty personnel in window of government hall by utilizing artificial intelligence |
| CN112163453A (en) * | 2020-08-25 | 2021-01-01 | 同济大学 | Personnel state detection method and system under man-machine cooperation environment |
-
2021
- 2021-03-18 CN CN202110291962.7A patent/CN112949546A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104618685A (en) * | 2014-12-29 | 2015-05-13 | 国家电网公司 | Intelligent image analysis method for power supply business hall video monitoring |
| CN109637096A (en) * | 2019-01-09 | 2019-04-16 | 张珣 | Key post personnel leave the post early warning system |
| CN110826538A (en) * | 2019-12-06 | 2020-02-21 | 合肥科大智能机器人技术有限公司 | Abnormal off-duty identification system for electric power business hall |
| CN111666841A (en) * | 2020-05-25 | 2020-09-15 | 山西长河科技股份有限公司 | Method for identifying off-duty personnel in window of government hall by utilizing artificial intelligence |
| CN112163453A (en) * | 2020-08-25 | 2021-01-01 | 同济大学 | Personnel state detection method and system under man-machine cooperation environment |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113640847A (en) * | 2021-06-17 | 2021-11-12 | 广州启盟信息科技有限公司 | Property positioning method, device and system based on GPS and image |
| CN113489929A (en) * | 2021-08-06 | 2021-10-08 | 远见智诚市场调研咨询(广东)有限公司 | Method and device for monitoring supervision of garbage classification, computer equipment and storage medium |
| CN113936293A (en) * | 2021-09-08 | 2022-01-14 | 重庆中科云从科技有限公司 | Video information-based off-duty personnel detection method, control device and storage medium |
| CN113780231A (en) * | 2021-09-22 | 2021-12-10 | 国网内蒙古东部电力有限公司信息通信分公司 | Legacy tool detection method and device, electronic equipment and storage medium |
| CN114429642A (en) * | 2021-12-23 | 2022-05-03 | 华能招标有限公司 | Abnormal behavior identification method for bid evaluation expert in remote bid evaluation video conference process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112949546A (en) | Off-duty detection method and device based on artificial intelligence perception of station service state | |
| CN112333431B (en) | Scene monitoring method and device, electronic equipment and storage medium | |
| CN106845890B (en) | Storage monitoring method and device based on video monitoring | |
| CN106991072B (en) | Online self-learning event detection model updating method and device | |
| CN110598604A (en) | Intelligent supervision method and device for classified garbage putting and computer storage medium | |
| CN109446094B (en) | Stuck detection method and device, electronic equipment and storage medium | |
| CN114782897A (en) | Dangerous behavior detection method and system based on machine vision and deep learning | |
| CN112087603A (en) | Intelligent examination room supervision method | |
| CN114200877B (en) | Monitoring method and device for electric equipment | |
| CN108267170B (en) | Environment monitoring method and device | |
| CN113052049B (en) | Off-duty detection method and device based on artificial intelligent tool identification | |
| CN113936293A (en) | Video information-based off-duty personnel detection method, control device and storage medium | |
| CN111126167B (en) | Method and system for quickly identifying serial activities of multiple specific personnel | |
| CN110598567A (en) | Community-based garbage management method and system and computer-readable storage medium | |
| CN116433029A (en) | Power operation risk assessment method, system, equipment and storage medium | |
| CN115410112A (en) | Elevator abnormal stay recognition method and device and storage medium | |
| CN111428963B (en) | Data processing method and device | |
| CN112507972A (en) | Performance assessment system based on block chain | |
| CN110688273B (en) | Classification model monitoring method and device, terminal and computer storage medium | |
| CN111126326A (en) | Crane counterweight automatic identification system and method based on image identification technology | |
| CN110458114B (en) | Method and device for determining number of people and storage medium | |
| CN109800727A (en) | A kind of monitoring method and device | |
| CN115661762B (en) | Library environment intelligent monitoring management system and method | |
| CN115206042B (en) | Intelligent monitoring method, device, equipment and medium for industrial control safety | |
| CN215897774U (en) | Eye protection equipment for mobile terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |