Shaft data processing method, system and equipment based on edge calculation and medium

Abstract

The invention relates to the technical field of data processing, in particular to a wellbore data processing method, system and equipment based on edge computing and a medium. The method comprises the steps that wellbore data are collected, and the collected data are preprocessed; and analyzing the preprocessing result to obtain a hydrops prediction result corresponding to the wellbore data, and storing the wellbore data and the hydrops prediction result in edge calculation. The data acquisition and preprocessing technology based on edge calculation has great advantages. Firstly, a large amount of data can be quickly acquired from each data source by the technology, and real-time processing and preprocessing are carried out at an edge end, so that the data acquisition and processing efficiency is greatly improved; and secondly, the technology can fully utilize the characteristics of edge calculation to realize quick response and real-time control on the premise of meeting data security. Meanwhile, the edge computing technology has better flexibility and usability, the equipment maintenance and upgrading difficulty of the oil and gas field well site can be reduced, and the cost is reduced.

Description

Background Art

[0002] Oil and gas fields are an important part of the national economy, and their production and management have always been the focus of oil and gas companies and technicians. However, due to the many limitations of traditional methods of oil and gas field well site data acquisition and processing technology, data acquisition and processing efficiency is low and cannot meet the requirements of automated production and refined management of oil and gas fields. Summary of the invention

[0003] The technical problem to be solved by the present invention is to address the deficiencies of the prior art, specifically the problems of low data acquisition and processing efficiency, and specifically provide a wellbore data processing method, system, device and medium based on edge computing, as follows:

[0004] 1) In the first aspect, the present invention provides a wellbore data processing method based on edge computing, and the specific technical solution is as follows:

[0005] Collect wellbore data and pre-process the collected data;

[0006] The preprocessing results are analyzed to obtain the fluid accumulation prediction results corresponding to the wellbore data, and the wellbore data and the fluid accumulation prediction results are stored in edge computing.

[0007] The beneficial effects of a wellbore data processing method based on edge computing provided by the present invention are as follows:

[0008] Data collection and preprocessing technology based on edge computing has great advantages. First, this technology can quickly collect a large amount of data from various data sources and perform real-time processing and preprocessing at the edge, greatly improving the efficiency of data collection and processing. Secondly, this technology can make full use of the characteristics of edge computing to achieve rapid response and real-time control while ensuring data security. At the same time, edge computing technology has better flexibility and ease of use, which can reduce the difficulty of equipment maintenance and upgrades at oil and gas field well sites and reduce costs.

[0009] Based on the above solution, the present invention can also be improved as follows.

[0010] Furthermore, the wellbore data includes: wellbore temperature, wellbore pressure and production.

[0011] Furthermore, the preprocessing includes at least one of filtering, deleting missing values ​​and filling missing values.

[0012] Further, the process of analyzing the preprocessing results to obtain the liquid loading prediction results corresponding to the wellbore data is as follows:

[0013] The preprocessing results are processed by a random forest machine learning method to obtain an effusion prediction result.

[0014] 2) In the second aspect, the present invention also provides a wellbore data processing system based on edge computing, and the specific technical solution is as follows:

[0015] The acquisition module is used to: collect wellbore data and pre-process the collected data;

[0016] The processing module is used to: analyze the preprocessing results to obtain the fluid accumulation prediction results corresponding to the wellbore data, and store the wellbore data and the fluid accumulation prediction results in edge computing.

[0017] Based on the above solution, the present invention can also be improved as follows.

[0018] Furthermore, the wellbore data includes: wellbore temperature, wellbore pressure and production.

[0019] Furthermore, the preprocessing includes at least one of filtering, deleting missing values ​​and filling missing values.

[0020] Further, the process of analyzing the preprocessing results to obtain the liquid loading prediction results corresponding to the wellbore data is as follows:

[0021] The preprocessing results are processed by a random forest machine learning method to obtain an effusion prediction result.

[0022] 3) In a third aspect, the present invention further provides a computer device, comprising a processor, wherein the processor is coupled to a memory, wherein the memory stores at least one computer program, and wherein the at least one computer program is loaded and executed by the processor so that the computer device implements any of the above methods.

[0023] 4) In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein at least one computer program is stored in the computer-readable storage medium, and the at least one computer program is loaded and executed by a processor so that a computer implements any of the above methods.

[0024] It should be noted that the beneficial effects achieved by the technical solutions of the second to fourth aspects of the present invention and the corresponding possible implementation methods can be found in the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0026] Figure 1A schematic diagram of a flow chart of a wellbore data processing method based on edge computing according to an embodiment of the present invention;

[0027] Figure 2 It is a structural schematic diagram of a wellbore data processing system based on edge computing according to an embodiment of the present invention;

[0028] Figure 3 A schematic diagram of the architecture of a wellbore data processing method based on edge computing according to an embodiment of the present invention;

[0029] Figure 4 A schematic diagram of a computer device for a wellbore data processing method based on edge computing according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0031] like Figure 1 As shown, a wellbore data processing method based on edge computing in an embodiment of the present invention includes the following steps:

[0032] Collect wellbore data and pre-process the collected data;

[0033] The preprocessing results are analyzed to obtain the fluid accumulation prediction results corresponding to the wellbore data, and the wellbore data and the fluid accumulation prediction results are stored in edge computing.

[0034] The beneficial effects of a wellbore data processing method based on edge computing provided by the present invention are as follows:

[0035] Data collection and preprocessing technology based on edge computing has great advantages. First, this technology can quickly collect a large amount of data from various data sources and perform real-time processing and preprocessing at the edge, greatly improving the efficiency of data collection and processing. Secondly, this technology can make full use of the characteristics of edge computing to achieve rapid response and real-time control while ensuring data security. At the same time, edge computing technology has better flexibility and ease of use, which can reduce the difficulty of equipment maintenance and upgrades at oil and gas field well sites and reduce costs.

[0036] like Figure 3 As shown, the hardware architecture adopted by the present invention is based on a low-cost embedded development board. These development boards usually have a small size, low power consumption and good scalability, and can run various operating systems and development environments. And it is equipped with accessories such as a 4G communication module, an RS485 serial port, and a touch screen.

[0037] The present invention can select a suitable development board according to different needs and budgets. The performance of the development board, such as processor type and speed, memory capacity and scalability, is a key factor in making the selection.

[0038] The development board described in the present invention adopts a 1.5GHz 64-bit quad-core ARM Cortex-A72 processor and 1 / 2 / 4GB of LPDDR4-2400 SDRAM memory, which is suitable for more complex edge computing tasks.

[0039] based on Figure 3 The specific processing flow of this solution is as follows:

[0040] First, the wellbore data is collected and preprocessed. Then, the preprocessed data is analyzed to obtain the corresponding fluid accumulation prediction results. Finally, the original data and analysis results are stored in edge computing and sent to the remote server.

[0041] Among them, the shaft refers to a vertical or inclined project excavated from the ground to the ore body in well mining or underground engineering construction.

[0042] Wellbore data include but are not limited to: wellbore temperature, wellbore pressure, and wellbore gas production.

[0043] For the collection of wellbore data, the RS485 interface plus the MODBUS protocol is used to collect wellbore data through sensors, actuators and other devices.

[0044] Sensors include: temperature sensor, pressure sensor, gas flow sensor.

[0045] The actuator includes: development board intelligent gateway.

[0046] The collected data is transferred to the edge computing node for preprocessing:

[0047] Preprocessing includes but is not limited to: data filtering, removing missing values, and filling in missing values.

[0048] 1. Data Filtering

[0049] Delete invalid and duplicate data: The original data may contain a large amount of invalid, dirty, and duplicate data, which is not helpful for analysis and needs to be filtered and deleted in advance.

[0050] Remove outliers: There may be some outliers in the original data that are far away from the normal distribution. These outliers need to be identified and deleted, otherwise they will have a great negative impact on the analysis results.

[0051] 2. Remove missing values

[0052] If the number of missing values ​​in a sample or variable exceeds a certain proportion, such as more than half of the sample or variable, the information contained in this sample or variable is limited. If the data is forcibly filled, too much artificial information may be added, resulting in a reduction in the utility of the well site data. In this case, it is generally recommended to remove the entire sample or variable from the data, that is, to delete the missing values.

[0053] Missing values ​​refer to clustering, grouping, deletion or truncation of data due to lack of information in rough data. It means that the value of one or some attributes in the existing data set is incomplete.

[0054] 3. Missing Value Filling

[0055] Specifically, the preprocessing method of the present invention uses a sliding average method to smooth the collected data. Assume that the jth data point collected is x j , then the average value of the data point can be calculated by the following formula:

[0056]

[0057] Wherein, N represents the size of the sliding window, which can be adjusted according to specific circumstances.

[0058] By smoothing the collected data points, the impact of noise can be effectively reduced and the accuracy and reliability of the data can be improved. After preprocessing, the data will be sent to the cloud for further analysis and processing, thus providing more accurate and powerful support for oil and gas field production and management.

[0059] The specific process of analyzing the preprocessed data and obtaining the corresponding effusion prediction results is as follows:

[0060] The data analysis described in the present invention is mainly based on real-time calculations of processed data. By using a random forest algorithm to perform integrated learning of multiple decision trees on wellbore data, efficient and accurate prediction and classification of the liquid accumulation state of the gas wellbore can be achieved, thereby improving the gas well production efficiency and the accuracy of equipment maintenance.

[0061] The specific steps of random forest model training are as follows:

[0062] 1. Data preparation: The gas well borehole dataset preprocessed with historical data is used as training data. This dataset contains multiple samples, each of which consists of multiple features and corresponding liquid accumulation states. The gas well features are mainly composed of feature data collected by edge devices at the wellhead, such as gas production, wellhead oil pressure, wellhead casing pressure, and temperature.

[0063] 2. Random sampling: Randomly sample N samples from the training data set with replacement to form a new training subset. N is the number of training samples used by each decision tree, which is usually less than the total number of samples in the training data set.

[0064] 3. Random feature selection: Randomly select m features (m is much smaller than the total number of features) from all features to form a feature subset. In this way, each decision tree only considers a subset of the m features at each node split, avoiding correlation interference between features.

[0065] 4. Build a decision tree: Use the training subset and the selected feature subset to build a decision tree. At each node, find the optimal partition feature and partition threshold based on the selected feature subset. The termination condition can be reaching the maximum tree depth, the number of node samples is less than the threshold, etc.

[0066] 5. Repeat steps 2-4 to build multiple decision trees, each of which is an independent classification or regression model.

[0067] 6. Ensemble learning: For the effusion judgment problem, a voting method is adopted to decide the final effusion result based on the effusion prediction results of multiple decision trees.

[0068] 7. Model saving: Save the trained model as a pkl file for subsequent loading.

[0069] The trained random forest model is embedded in the data analysis module of the edge computing system to predict effusion. The specific steps are as follows:

[0070] 1. Input data:

[0071] Receive new gas well data as input, including characteristic data such as wellhead pressure, bottom hole pressure, wellbore temperature, etc.

[0072] 2. Feature processing:

[0073] The input wellbore data is preprocessed in the same way as the training data, including deletion of missing values, missing value filling, and outlier detection, to ensure the accuracy and completeness of the input data.

[0074] 3. Multiple decision tree predictions:

[0075] The preprocessed data is input into multiple trained decision trees for prediction. For classification problems, each decision tree will output a classification result.

[0076] 4. Ensemble learning:

[0077] For classification problems, the final classification result is determined by voting based on the classification results of multiple decision trees.

[0078] 5. Output prediction results:

[0079] Output the final prediction result, that is, the liquid accumulation state of the gas wellbore. For classification problems, the output result is 0 or 1, indicating no liquid accumulation or liquid accumulation.

[0080] In another embodiment, it also includes:

[0081] The data storage and transmission described in the present invention mainly uploads the processed data to the cloud to realize data storage, and can perform data analysis and decision-making in the cloud. At the same time, the data can also be sent to the terminal device through the Internet of Things technology to realize remote monitoring and control.

[0082] The data transmission described in the present invention adopts the MQTT transmission protocol and develops a network disconnection reconnection function to ensure effective data transmission.

[0083] The main process of data acquisition described in the present invention is as follows: configure the serial port name, baud rate, check bit, data bit, and stop bit of the host computer to ensure that the host computer can correctly communicate with the sensor or meter; then the host computer sends a hexadecimal MODBUS message to the sensor every 1 second to collect data, the sent MODBUS instruction contains the instrument address, function code, data, CRC check, and parses the returned hexadecimal MODBUS message.

[0084] The data transmission described in the present invention can receive instructions sent by the cloud server and perform functions such as remote control according to the instructions.

[0085] The data acquisition function described in the present invention can realize reverse data acquisition, that is, transmit the instructions of the development board to the instruments at the oil and gas field site to realize the change of the instrument settings;

[0086] The data acquisition function described in the present invention can realize reverse data acquisition, that is, transmit the instructions of the development board to the automation equipment to realize the automation control of the well site.

[0087] The data storage described in the present invention uses the driver of the SQLite database to connect and read and write the database. The present invention includes two database tables, namely a real-time data table and a daily production data table. The real-time data records instantaneous data every minute, and the daily production data table is mainly responsible for recording daily production data, etc.

[0088] This solution improves data collection and processing efficiency: Traditional data collection and processing methods often require manual work, which is time-consuming, labor-intensive, and inefficient. However, the edge computing-based data collection and preprocessing method of the present invention can realize automatic data collection and real-time processing, greatly improving data processing efficiency and accuracy.

[0089] Improve data quality and availability: The present invention uses RS485 interface plus MODBUS protocol for data transmission during data collection, avoiding the problems of truncation and missing transmission that are prone to occur in traditional data collection methods. At the same time, in the data preprocessing link, data filtering, deletion of missing values, missing value filling and other operations are performed on the data to ensure data quality and availability.

[0090] Realize automated production and refined management of oil and gas fields: The present invention provides a fast and reliable data collection and liquid accumulation prediction method, which can improve the automated production and refined management level of oil and gas fields. Realizing real-time monitoring and management of data through the cloud can effectively guide the production and management of oil and gas fields.

[0091] Good market prospects: With the continuous development of society and the continuous advancement of science and technology, the demand for oil and gas field well site data acquisition and processing technology is also increasing. Data acquisition and preprocessing methods based on edge computing have high market prospects and market potential.

[0092] Example 1

[0093] Data acquisition node: located in the oil and gas field well site, responsible for collecting data from various sensors and transmitting it to the edge computing node.

[0094] Edge computing nodes: Located near the oil and gas field well site, they are responsible for receiving data sent by the data acquisition nodes and performing real-time calculations and preprocessing. Edge computing nodes have high computing power and storage capacity, and can quickly respond to and process large amounts of data.

[0095] Cloud server: As the center for subsequent data analysis and storage, it receives pre-processed data from edge computing nodes and performs further analysis and storage.

[0096] The above workflow is as follows:

[0097] Data acquisition nodes continuously collect data from various sensors in oil and gas fields, such as temperature, pressure, and flow.

[0098] The collected data is transmitted to the edge computing node via wireless or wired communication.

[0099] After receiving the data, the edge computing node performs real-time calculation and preprocessing, which includes data filtering, noise reduction, outlier detection and other processing steps.

[0100] The processed data is transmitted to the cloud server via the network for storage and further analysis.

[0101] The cloud server can further process the data through statistical analysis, data mining, etc. according to user needs, providing more insights and decision support.

[0102] Through this system, data collection and preprocessing tasks at oil and gas field well sites can be realized, which greatly improves the efficiency of data collection and processing and provides a basis for subsequent data analysis and decision-making.

[0103] Embodiment 2:

[0104] Data collection node: located in the oil and gas field well site, responsible for real-time collection of various key process parameters, such as temperature, pressure, flow, etc.

[0105] Edge computing node: Located near the well site, it receives and processes data sent by the data acquisition node, and calculates and predicts the changing trends of key process parameters in real time.

[0106] Control node: Based on the data and prediction results provided by the edge computing node, real-time adjustment and control of process parameters are performed.

[0107] Monitoring center: As the core of the entire system, it is responsible for centralized monitoring and management of the process control process of the oil and gas field well site, and provides alarm and fault diagnosis functions.

[0108] Cloud server: As the center for subsequent data analysis and decision-making, it receives data from edge computing nodes and monitoring centers and performs further analysis and storage.

[0109] Through this system, real-time monitoring and control of the process of oil and gas field well sites can be achieved, which improves the stability and reliability of the process, while reducing the difficulty and cost of equipment maintenance and upgrades.

[0110] These two examples demonstrate the application of edge computing-based data collection and preprocessing technology in the oil and gas field, which has strong feasibility and practicality. These technologies can improve data collection and processing efficiency, realize automated production and refined management, and are expected to be widely used and promoted in the oil and gas field industry.

[0111] Furthermore, the wellbore data includes: wellbore temperature, wellbore pressure and production.

[0112] Furthermore, the preprocessing includes at least one of filtering, deleting missing values ​​and filling missing values.

[0113] Further, the process of analyzing the preprocessing results to obtain the liquid loading prediction results corresponding to the wellbore data is as follows:

[0114] The preprocessing results are processed by a random forest machine learning method to obtain an effusion prediction result.

[0115] like Figure 2As shown, the present invention also provides a wellbore data processing system based on edge computing, and the specific technical solution is as follows:

[0116] The acquisition module 100 is used to: acquire wellbore data and pre-process the acquired data;

[0117] The processing module 200 is used to analyze the preprocessing results to obtain the liquid accumulation prediction results corresponding to the wellbore data, and store the wellbore data and the liquid accumulation prediction results in edge computing.

[0118] Furthermore, the wellbore data includes: wellbore temperature, wellbore pressure and production.

[0119] Furthermore, the preprocessing includes at least one of filtering, deleting missing values ​​and filling missing values.

[0120] Further, the process of analyzing the preprocessing results to obtain the liquid loading prediction results corresponding to the wellbore data is as follows:

[0121] The preprocessing results are processed by a random forest machine learning method to obtain an effusion prediction result.

[0122] In the above embodiments, although the steps are numbered S1, S2, etc., these are only specific embodiments given by the present invention. Those skilled in the art may adjust the execution order of S1, S2, etc. according to actual conditions, which is also within the protection scope of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0123] It should be noted that the beneficial effects of the wellbore data processing system based on edge computing provided by the above embodiment are the same as the beneficial effects of the wellbore data processing method based on edge computing, which will not be repeated here. In addition, when the system provided by the above embodiment realizes its functions, it only takes the division of the above functional modules as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to actual conditions to complete all or part of the functions described above. In addition, the system and method embodiments provided by the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0124] like Figure 4As shown, a computer device 300 of an embodiment of the present invention includes a processor 320, the processor 320 is coupled to a memory 310, and the memory 310 stores at least one computer program 330, and the at least one computer program 330 is loaded and executed by the processor 320, so that the computer device 300 implements any one of the above-mentioned wellbore data processing methods based on edge computing, specifically:

[0125] The computer device 300 may have relatively large differences due to different configurations or performances, and may include one or more processors 320 (Central Processing Units, CPU) and one or more memories 310, wherein at least one computer program 330 is stored in the one or more memories 310, and the at least one computer program 330 is loaded and executed by the one or more processors 320, so that the computer device 300 implements a wellbore data processing method based on edge computing provided in the above embodiment. Of course, the computer device 300 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output, and the computer device 300 may also include other components for realizing device functions, which will not be repeated here.

[0126] A computer-readable storage medium in an embodiment of the present invention stores at least one computer program, and the at least one computer program is loaded and executed by a processor so that the computer implements a wellbore data processing method based on edge computing according to any one of the above claims.

[0127] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0128] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs any of the above-mentioned wellbore data processing methods based on edge computing.

[0129] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and represent the definition of a specific order or sequence. The order of use of similar objects can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0130] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0131] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0132] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A wellbore data processing method based on edge computing, characterized in that: include: Collect wellbore data and pre-process the collected data; The preprocessing results are analyzed to obtain the fluid accumulation prediction results corresponding to the wellbore data, and the wellbore data and the fluid accumulation prediction results are stored in edge computing.

2. A wellbore data processing method based on edge computing according to claim 1, characterized in that: The wellbore data include: wellbore temperature, wellbore pressure and wellbore gas production.

3. A wellbore data processing method based on edge computing according to claim 1, characterized in that: The preprocessing includes at least one of filtering, deleting missing values ​​and filling missing values.

4. A wellbore data processing method based on edge computing according to claim 1, characterized in that: The process of analyzing the preprocessing results to obtain the liquid loading prediction results corresponding to the wellbore data is as follows: The preprocessing results are processed by a random forest machine learning method to obtain an effusion prediction result.

5. A wellbore data processing system based on edge computing, characterized in that: include: The acquisition module is used to: collect wellbore data and pre-process the collected data; The processing module is used to: analyze the preprocessing results to obtain the fluid accumulation prediction results corresponding to the wellbore data, and store the wellbore data and the fluid accumulation prediction results in edge computing.

6. A wellbore data processing system based on edge computing according to claim 5, characterized in that: The wellbore data include: wellbore temperature, wellbore pressure and production.

7. A wellbore data processing system based on edge computing according to claim 5, characterized in that: The preprocessing includes at least one of filtering, deleting missing values ​​and filling missing values.

8. A wellbore data processing system based on edge computing according to claim 5, characterized in that: The process of analyzing the preprocessing results to obtain the liquid loading prediction results corresponding to the wellbore data is as follows: The preprocessing results are processed by a random forest machine learning method to obtain an effusion prediction result.

9. A computer device, characterized in that: The computer device includes a processor, which is coupled to a memory, in which at least one computer program is stored, and the at least one computer program is loaded and executed by the processor so that the computer device implements a wellbore data processing method based on edge computing as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: At least one computer program is stored in the computer-readable storage medium, and the at least one computer program is loaded and executed by the processor so that the computer implements the wellbore data processing method based on edge computing as described in any one of claims 1 to 4.

Images