Visual intelligent supervision method, system, equipment and medium

Abstract

The invention discloses a visual intelligent supervision method, system and device and a medium. The method comprises the following steps: obtaining supervision data of a construction site; the method comprises the following steps: calculating a wireless transmission rate and delay time for transmitting supervision data through an edge computing device, batching the supervision data according to the wireless transmission rate and the delay time, and transmitting the supervision data to a rear-end processing layer; when the back-end processing layer receives the supervision data, the supervision data is stored by adopting a cloud storage technology or a distributed storage system; a logistic regression model is improved by introducing weighted features and an adaptive learning rate, and the improved logistic regression model is used as a classification model; and training the classification model according to the supervision data to obtain a big data analysis model, analyzing the real-time supervision data based on the big data analysis model, and displaying the real-time supervision data through a sliding window. Therefore, the problem that safety accidents occur frequently in a construction area due to the fact that an existing real-time sensing system for electric power infrastructure risk operation is relatively weak and monitoring equipment is insufficient is solved.

Description

Technical Field

[0001] The present application relates to the technical field of electric power construction supervision, and in particular to a visual intelligent supervision method, system, equipment and medium. Background Art

[0002] Grid construction is an important part of power system construction and maintenance. Due to the special nature of the power infrastructure construction area, there are a large number of personnel, high mobility, and a complex and changeable working environment. These problems directly threaten the life safety of on-site construction personnel and also affect the construction efficiency and quality of power infrastructure projects. In addition, the perception system of power infrastructure risk operations is relatively weak, and monitoring equipment is insufficient, resulting in frequent safety accidents in the construction area, which also brings huge risks and unnecessary losses to the construction of power infrastructure projects. In order to improve construction efficiency and ensure construction safety, it is urgent to design a visual intelligent supervision method. Summary of the invention

[0003] The present application provides a visual intelligent supervision method, system, equipment and medium, which are used to solve the problem that the real-time perception system of existing power infrastructure risk operations is relatively weak and the monitoring equipment is insufficient, resulting in frequent safety accidents in the construction area.

[0004] In view of this, the first aspect of the present application provides a visual intelligent supervision method, the method comprising:

[0005] Obtaining supervision data of the construction site through supervision equipment, wherein the supervision equipment includes: personnel positioning equipment using GPS and RFID technology;

[0006] Calculate the wireless transmission rate and delay duration for transmitting the supervision data by an edge computing device, batch the supervision data according to the wireless transmission rate and the delay duration, and transmit the batches to the backend processing layer;

[0007] When the backend processing layer receives the supervision data, the supervision data is stored using cloud storage technology or a distributed storage system;

[0008] The logistic regression model is improved by introducing weighted features and adaptive learning rate, and the improved logistic regression model is used as a classification model;

[0009] The classification model is trained according to the supervision data to obtain a big data analysis model, and the real-time supervision data is analyzed based on the big data analysis model and displayed through a sliding window.

[0010] Optionally, the calculating of a wireless transmission rate and a delay duration for transmitting the supervision data by an edge computing device, batching the supervision data according to the wireless transmission rate and the delay duration, and transmitting the batches to a backend processing layer specifically includes:

[0011] After filtering and preprocessing by the edge computing device, the wireless transmission rate and delay time are calculated in real time, the network status within the preset time period is predicted, and the wireless transmission rate threshold and the delay time threshold are dynamically adjusted according to the network status. The supervision data is then batched according to the real-time wireless transmission rate threshold and the delay time threshold and transmitted to the back-end processing layer.

[0012] Optionally, the improving the logistic regression model by introducing weighted features and adaptive learning rate, and using the improved logistic regression model as a classification model, specifically includes:

[0013] Setting input feature vectors, weighted feature vectors and model parameters to build a classification model, wherein the classification model is a logistic regression model;

[0014] The loss function of the logistic regression model is optimized using an adaptive learning rate to obtain a final classification model, wherein the loss function is a cross entropy loss function.

[0015] Optionally, the monitoring equipment further includes: a video monitoring device for acquiring a real-time video stream of the construction site, an environmental sensor for monitoring environmental parameters, and a displacement sensor for detecting displacement and vibration of the construction equipment.

[0016] Optionally, the classification model is trained according to the supervision data to obtain a big data analysis model, the real-time supervision data is analyzed based on the big data analysis model, and displayed through a sliding window, and then further includes:

[0017] When a risk is predicted to occur at the construction site, an early warning message is generated.

[0018] Optionally, the personnel positioning device using GPS and RFID technology specifically includes:

[0019] RFID readers are installed at key locations on the construction site, and RFID tags are placed on construction workers so that the RFID readers can obtain the location information of the construction workers; at the same time, the positioning data of the construction workers is regularly obtained through GPS equipment.

[0020] Optionally, the transmission to the back-end processing layer specifically includes: using 5G / 4G network or LoRa technology to transmit the batched supervision data to the back-end processing layer.

[0021] A second aspect of the present application provides a visual intelligent supervision system, the system comprising:

[0022] An acquisition unit is used to acquire the supervision data of the construction site through a supervision device, wherein the supervision device includes: a personnel positioning device using GPS and RFID technology;

[0023] A transmission unit, configured to calculate a wireless transmission rate and a delay time for transmitting the supervision data through an edge computing device, batch the supervision data according to the wireless transmission rate and the delay time, and transmit the batches to a backend processing layer;

[0024] A storage unit, used for storing the supervision data by using cloud storage technology or a distributed storage system when the back-end processing layer receives the supervision data;

[0025] A construction unit is used to improve the logistic regression model by introducing weighted features and adaptive learning rate, and use the improved logistic regression model as a classification model;

[0026] An analysis unit is used to train the classification model according to the supervision data to obtain a big data analysis model, analyze the real-time supervision data based on the big data analysis model, and display it through a sliding window.

[0027] A third aspect of the present application provides a visual intelligent monitoring device, the device comprising a processor and a memory:

[0028] The memory is used to store program code and transmit the program code to the processor;

[0029] The processor is used to execute the steps of the visual intelligent supervision method as described in the first aspect according to the instructions in the program code.

[0030] The fourth aspect of the present application provides a computer-readable storage medium, which is used to store program code, and the program code is used to execute the visual intelligent supervision method described in the first aspect above.

[0031] It can be seen from the above technical solutions that this application has the following advantages:

[0032] This application provides a visual intelligent supervision method, a visual intelligent supervision device and method based on the Internet of Things and artificial intelligence, which collects construction site data through multiple sensors and uses data analysis and processing technology to achieve real-time monitoring and risk warning of the construction process. This solves the problem that the existing real-time perception system of risk operations in power infrastructure is relatively weak and the monitoring equipment is insufficient, resulting in frequent safety accidents in the construction area. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A flowchart of a visual intelligent supervision method provided in an embodiment of the present application;

[0034] Figure 2 A schematic diagram of the structure of a visual intelligent supervision system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0036] See also Figure 1 A visual intelligent supervision method provided in an embodiment of the present application includes:

[0037] Step 101: Obtain supervision data of the construction site through supervision equipment, wherein the supervision equipment includes: a personnel positioning device using GPS and RFID technology.

[0038] In one embodiment, the supervision device further comprises:

[0039] Video surveillance equipment for acquiring real-time video streams of the construction site, environmental sensors for monitoring environmental parameters, and displacement sensors for detecting displacement and vibration of construction equipment.

[0040] It should be noted that:

[0041] Video surveillance equipment: Deploy high-definition cameras at the construction site to provide real-time video streaming.

[0042] Environmental sensors: including temperature, humidity, gas concentration and other sensors, which monitor environmental parameters in real time.

[0043] Displacement sensors: Installed on key construction equipment and structures to monitor their displacement and vibration.

[0044] Personnel positioning equipment: Use GPS and RFID technology to locate construction personnel in real time.

[0045] Specifically: Deploy high-definition cameras at the construction site to collect real-time video streams, and compress the collected real-time video streams. Specifically, use the basic equation of H.264: R=S / T, where R is the bit rate, S is the size of the video frame, and T is the time interval. After compressing the video stream, it is transmitted to the back-end processing layer through the communication layer. In addition, environmental parameters are collected through various sensors, and the collected data is transmitted to the back-end processing layer through the sensor interface. Use GPS and RFID technology to locate construction personnel in real time, install RFID readers at key locations on the construction site, and construction personnel wear RFID tags. GPS equipment regularly sends positioning data and transmits it through the wireless network. The RFID reader collects personnel location data in real time and transmits it to the back-end processing layer through the communication layer.

[0046] Step 102: Calculate the wireless transmission rate and delay time for transmitting the supervision data through the edge computing device, batch the supervision data according to the wireless transmission rate and delay time, and transmit them to the back-end processing layer.

[0047] It should be noted that this application uses edge computing devices, specifically: deploying edge computing nodes on site to perform preliminary data processing and filtering to reduce the pressure on the back-end server. The communication layer includes: wireless network, specifically: using 5G / 4G network or LoRa and other low-power wide area network technologies to achieve high-speed data transmission.

[0048] In one embodiment, step 102 specifically includes:

[0049] After filtering and preprocessing by edge computing equipment, the wireless transmission rate and delay time are calculated in real time, the network status within the preset time period is predicted, and the wireless transmission rate threshold and delay time threshold are dynamically adjusted according to the network status. The supervision data is then batched according to the real-time wireless transmission rate threshold and delay time threshold and transmitted to the back-end processing layer.

[0050] It should be noted that by calculating the wireless transmission rate and delay time in real time, the batch size and time interval of data transmission are dynamically adjusted to ensure optimal data transmission. The network status within the preset time is predicted based on the real-time calculated wireless transmission rate and delay time, and an adaptive threshold adjustment mechanism is introduced based on the predicted network status to flexibly set the preset conditions of transmission rate and delay.

[0051] Set the initial preset rate threshold and preset delay threshold. If the current network rate is higher than the preset rate threshold and the delay is lower than the preset delay threshold, increase the transmission batch size; if the current network rate is lower than the preset rate threshold and the delay is higher than the preset delay threshold, reduce the transmission batch size or temporarily stop the transmission.

[0052] At the same time, the real-time monitored wireless transmission rate and delay duration are input into the machine learning model to predict the network status within the preset time, and the transmission rate threshold and the preset delay threshold are dynamically adjusted according to the predicted network status. Specifically, if the predicted network status is good, the corresponding rate threshold is increased and the delay threshold is reduced; otherwise, the opposite is true.

[0053] The wireless transmission rate calculation formula is as follows:

[0054] ;

[0055] In the formula, is the transmission rate, is the channel bandwidth, is the signal-to-noise ratio.

[0056] The delay time calculation formula is as follows:

[0057] ;

[0058] In the formula, is the total delay, To calculate the delay, is the transmission delay, To handle delays.

[0059] Step 103: When the backend processing layer receives the supervision data, the supervision data is stored using cloud storage technology or a distributed storage system.

[0060] It should be noted that the backend processing layer uses cloud storage technology or a distributed storage system to maintain a large amount of construction site data transmitted by the edge end, so that big data analysis can be used to conduct in-depth mining and analysis of the collected data, as shown in step 104.

[0061] Step 104: Improve the logistic regression model by introducing weighted features and adaptive learning rate, and use the improved logistic regression model as a classification model.

[0062] In one embodiment, step 104 specifically includes:

[0063] Set the input feature vector, weighted feature vector and model parameters to build a classification model, which is a logistic regression model;

[0064] The loss function of the logistic regression model is optimized using an adaptive learning rate to obtain the final classification model, where the loss function is a cross entropy loss function.

[0065] Step 105: Train the classification model according to the supervision data to obtain a big data analysis model, analyze the real-time supervision data based on the big data analysis model, and display it through a sliding window.

[0066] In one embodiment, step 105 further includes: generating early warning information when a risk is predicted to occur at the construction site.

[0067] What needs to be explained about steps 104 and 105 is:

[0068] Select a classification algorithm, divide the supervision data of the construction site into a training set and a test set, standardize or normalize the data of the training set and the test set, and establish a classification model. The goal of the classification model is to predict the occurrence of a certain risk at the construction site.

[0069] Suppose the input feature vector is X=[x1,x2,...,x N ], the weighted eigenvector is W=[w1,w2,...,w n ], the model parameters are θ=[θ1,θ2,...θ3];

[0070] The established classification model is a logistic regression model, expressed as:

[0071] ;

[0072] The cross entropy loss function used is:

[0073] ;

[0074] in, is the number of training samples, is the true label of the i-th sample.

[0075] Optimizing the loss function includes:

[0076] For Parameters The gradient of is:

[0077] ;

[0078] Using adaptive learning rate :

[0079] ;

[0080] In the formula, is the initial learning rate, is the attenuation parameter, is the number of iterations.

[0081] In each iteration, the parameters are updated according to the gradient and the adaptive learning rate:

[0082] ;

[0083] The above model can effectively improve the flexibility and optimization effect of the logistic regression model by introducing weighted features and adaptive learning rate, adapt to the importance of different features and dynamically adjust the learning rate to accelerate convergence.

[0084] The big data analysis model analyzes the construction site data in real time, displays the analysis results through a scrolling window, and generates early warning information when it predicts that some kind of risk will occur at the construction site.

[0085] Specifically, the rolling window can be expressed as:

[0086] ;

[0087] In the formula, is the i-th window, is the window start time, is the timestamp of the data point, is the window length.

[0088] The embodiment of the present application provides a visual intelligent supervision method, a visual intelligent supervision device and method based on the Internet of Things and artificial intelligence, which collects construction site data through multiple sensors and uses data analysis and processing technology to achieve real-time monitoring and risk warning of the construction process. This solves the problem that the existing real-time perception system of risk operations in power infrastructure is relatively weak and the monitoring equipment is insufficient, resulting in frequent safety accidents in the construction area.

[0089] The above is a visualized intelligent supervision method provided in an embodiment of the present application, and the following is a visualized intelligent supervision system provided in an embodiment of the present application.

[0090] See also Figure 2 , a visual intelligent supervision system provided in an embodiment of the present application includes:

[0091] The acquisition unit 201 is used to acquire the supervision data of the construction site through the supervision equipment, wherein the supervision equipment includes: a personnel positioning device using GPS and RFID technology.

[0092] The transmission unit 202 is used to calculate the wireless transmission rate and delay time for transmitting the supervision data through the edge computing device, batch the supervision data according to the wireless transmission rate and delay time, and transmit them to the back-end processing layer.

[0093] The storage unit 203 is used to store the supervision data by using cloud storage technology or a distributed storage system when the back-end processing layer receives the supervision data.

[0094] The construction unit 204 is used to improve the logistic regression model by introducing weighted features and adaptive learning rate, and use the improved logistic regression model as a classification model.

[0095] The analysis unit 205 is used to train the classification model according to the supervision data to obtain a big data analysis model, analyze the real-time supervision data based on the big data analysis model, and display it through a sliding window.

[0096] Furthermore, a visual intelligent monitoring device is provided in an embodiment of the present application, and the device includes a processor and a memory:

[0097] The memory is used to store program code and transmit the program code to the processor;

[0098] The processor is used to execute the steps of the visual intelligent supervision method as described in the above method embodiment according to the instructions in the program code.

[0099] Furthermore, a computer-readable storage medium is provided in an embodiment of the present application, and the computer-readable storage medium is used to store program code, and the program code is used to execute the method described in the above method embodiment.

[0100] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0101] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0102] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0103] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0106] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.

[0107] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A visual intelligent supervision method, characterized in that: include: Obtaining supervision data of the construction site through supervision equipment, wherein the supervision equipment includes: personnel positioning equipment using GPS and RFID technology; Calculate the wireless transmission rate and delay duration for transmitting the supervision data by an edge computing device, batch the supervision data according to the wireless transmission rate and the delay duration, and transmit the batches to the backend processing layer; When the backend processing layer receives the supervision data, the supervision data is stored using cloud storage technology or a distributed storage system; The logistic regression model is improved by introducing weighted features and adaptive learning rate, and the improved logistic regression model is used as a classification model; The classification model is trained according to the supervision data to obtain a big data analysis model, and the real-time supervision data is analyzed based on the big data analysis model and displayed through a sliding window.

2. The visual intelligent supervision method according to claim 1 is characterized in that: The edge computing device is used to calculate the wireless transmission rate and delay duration for transmitting the supervision data, and the supervision data is batched according to the wireless transmission rate and the delay duration, and then transmitted to the backend processing layer, specifically including: After filtering and preprocessing by the edge computing device, the wireless transmission rate and delay time are calculated in real time, the network status within the preset time period is predicted, and the wireless transmission rate threshold and the delay time threshold are dynamically adjusted according to the network status. The supervision data is then batched according to the real-time wireless transmission rate threshold and the delay time threshold and transmitted to the back-end processing layer.

3. The visual intelligent supervision method according to claim 1 is characterized in that: The method improves the logistic regression model by introducing weighted features and adaptive learning rate, and uses the improved logistic regression model as a classification model, specifically including: Setting input feature vectors, weighted feature vectors and model parameters to build a classification model, wherein the classification model is a logistic regression model; The loss function of the logistic regression model is optimized using an adaptive learning rate to obtain a final classification model, wherein the loss function is a cross entropy loss function.

4. The visual intelligent supervision method according to claim 1 is characterized in that: The monitoring equipment also includes: a video monitoring device for acquiring a real-time video stream of the construction site, an environmental sensor for monitoring environmental parameters, and a displacement sensor for detecting the displacement and vibration of the construction equipment.

5. The visual intelligent supervision method according to claim 1 is characterized in that: The classification model is trained according to the supervision data to obtain a big data analysis model, the real-time supervision data is analyzed based on the big data analysis model, and displayed through a sliding window, and then further includes: When a risk is predicted to occur at the construction site, an early warning message is generated.

6. The visual intelligent supervision method according to claim 1 is characterized in that: The personnel positioning device using GPS and RFID technology specifically includes: RFID readers are installed at key locations on the construction site, and RFID tags are placed on construction workers so that the RFID readers can obtain the location information of the construction workers; at the same time, the positioning data of the construction workers is regularly obtained through GPS equipment.

7. The visual intelligent supervision method according to claim 1 is characterized in that: The transmission to the back-end processing layer specifically includes: using 5G / 4G network or LoRa technology to transmit the batched supervision data to the back-end processing layer.

8. A visual intelligent supervision system, characterized in that: include: An acquisition unit is used to acquire the supervision data of the construction site through a supervision device, wherein the supervision device includes: a personnel positioning device using GPS and RFID technology; A transmission unit, configured to calculate a wireless transmission rate and a delay time for transmitting the supervision data through an edge computing device, batch the supervision data according to the wireless transmission rate and the delay time, and transmit the batches to a backend processing layer; A storage unit, used for storing the supervision data by using cloud storage technology or a distributed storage system when the back-end processing layer receives the supervision data; A construction unit is used to improve the logistic regression model by introducing weighted features and adaptive learning rate, and use the improved logistic regression model as a classification model; An analysis unit is used to train the classification model according to the supervision data to obtain a big data analysis model, analyze the real-time supervision data based on the big data analysis model, and display it through a sliding window.

9. A visual intelligent monitoring device, characterized in that: The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the visual intelligent supervision method described in any one of claims 1-7 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program code, and the program code is used to execute the visual intelligent supervision method described in any one of claims 1-7.

Images