Industrial equipment identification and protocol matching method, device and equipment and storage medium

Abstract

This application discloses an industrial equipment identification and protocol matching method, apparatus, device, and storage medium, relating to the field of industrial automation technology. The method includes: introducing a quality screening mechanism based on pitch angle and illuminance value during the image acquisition stage to ensure the validity of the input image, providing a data foundation for accurate identification of the subsequent equipment model; inputting the equipment image into a pruned quantized target detection model for local inference to identify the equipment model, avoiding network dependence and transmission delays caused by uploading images to the cloud for processing; after identifying the equipment model, further retrieving multiple candidate protocols from a local database based on the equipment model, and scoring the candidate protocols to match the target protocol, solving the problems of low efficiency in manual table lookup and difficulty in accurately selecting from multiple candidate protocols. Compared with existing technologies, this method achieves automated identification of equipment models and intelligent matching of protocols.

Description

Technical Field

[0001] This application relates to the field of industrial automation technology, and in particular to a method, apparatus, device and storage medium for industrial equipment identification and protocol matching. Background Technology

[0002] With the rapid development of the Industrial Internet and the large-scale deployment of on-site infrastructure such as communication base stations and computer rooms, the brands of remote devices connected to the on-site monitoring unit are becoming increasingly diverse, and the speed of updates and iterations of communication protocol versions of devices from different manufacturers is significantly accelerating. This makes it necessary for the on-site monitoring unit to frequently adapt to multiple types of devices and protocol versions.

[0003] Currently, industrial sites commonly use manual lookup tables for equipment identification and protocol matching. This involves field engineers carrying paper or electronic equipment-protocol lookup tables, manually searching for and configuring the corresponding protocol parameters based on the equipment label information. This experience-dependent approach suffers from low efficiency and high configuration error rates when dealing with diverse equipment types and rapidly updating protocol versions, making it difficult to meet the operational and maintenance needs for rapid onboarding of field equipment.

[0004] Therefore, how to quickly and accurately match the corresponding communication protocol based on the automated identification of remote devices in an industrial environment has become a technical problem that urgently needs to be solved in this field.

[0005] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0006] The main objective of this application is to provide a method, apparatus, device, and storage medium for industrial equipment identification and protocol matching, aiming to solve the technical problem of how to achieve automated identification and protocol configuration of industrial field equipment.

[0007] To achieve the above objectives, this application proposes an industrial equipment identification and protocol matching method, the method comprising: When the pitch angle and illumination value meet the shooting conditions, acquire device images according to the preset resolution; The device image is input into the pruned quantization target detection model to identify the device model, and multiple candidate protocols are determined from the local database based on the device model. Each candidate protocol is scored, and a target protocol is matched based on the scoring results.

[0008] In one embodiment, before acquiring the device image according to a preset resolution when the pitch angle and illumination value meet the shooting conditions, the method further includes: Obtain the pitch angle and illuminance value; When the pitch angle is greater than a preset angle threshold or the illuminance value is less than a preset illuminance threshold, the shutter function is disabled. When the pitch angle is less than or equal to a preset angle threshold or the illuminance value is greater than or equal to a preset illuminance threshold, it is determined that the pitch angle and the illuminance value meet the shooting conditions.

[0009] In one embodiment, the step of inputting the device image into a pruned quantization target detection model to identify the device model, and determining multiple candidate protocols based on the device model, includes: The device image is normalized. The normalized device image is used as the input to the pruned quantization target detection model to obtain the device model and corresponding confidence level output by the target detection model. When the confidence level is greater than or equal to a preset confidence threshold, multiple candidate protocols are determined from the local database based on the device model.

[0010] In one embodiment, after using the normalized device image as input to the pruned quantization target detection model to obtain the device model and corresponding confidence score output by the target detection model, the method further includes: When the confidence level is less than a preset confidence threshold, feature extraction is performed on the device image to obtain an anonymous feature vector; The anonymous feature vector is uploaded to the cloud so that the cloud generates an incremental update file based on the anonymous feature vector. The pruned quantized target detection model is updated based on the incremental update file.

[0011] In one embodiment, when the confidence level is greater than or equal to a preset confidence threshold, determining multiple candidate protocols from a local database based on the device model includes: When the confidence level is greater than or equal to a preset confidence threshold, a search is performed in the local database based on the device model to obtain the search results. The local database pre-stores mapping records between different device models and different protocols. Based on the search results, multiple candidate protocols were obtained.

[0012] In one embodiment, scoring each of the candidate protocols and matching the target protocol based on the scoring results includes: Each candidate protocol is scored based on its baud rate matching degree, check matching degree, historical success rate, and protocol selection rate to obtain a scoring result. Based on the scoring results, the target protocol is determined from multiple candidate protocols.

[0013] In one embodiment, after scoring each of the candidate protocols and matching the target protocol based on the scoring results, the method further includes: Obtain the current transmission link; The target protocol is written into the industrial field equipment corresponding to the device model through the current transmission link; The industrial field equipment is highlighted in the 3D digital twin interface, and a prompt message indicating that the protocol has been activated is generated.

[0014] Furthermore, to achieve the above objectives, this application also proposes an industrial equipment identification and protocol matching device, which includes: The acquisition module is used to acquire images from the device at a preset resolution when the pitch angle and illumination value meet the shooting conditions. The identification module is used to input the device image into the pruned quantization target detection model to identify the device model, and determine multiple candidate protocols from the local database based on the device model; The matching module is used to score each of the candidate protocols and match the target protocol based on the scoring results.

[0015] In addition, to achieve the above objectives, this application also proposes an industrial equipment identification and protocol matching device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the industrial equipment identification and protocol matching method described above.

[0016] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the industrial equipment identification and protocol matching method described above.

[0017] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the industrial equipment identification and protocol matching method described above.

[0018] This application proposes to acquire device images at a preset resolution when the pitch angle and illumination value meet the shooting conditions; input the device images into a pruned quantization target detection model to identify the device model, and determine multiple candidate protocols from a local database based on the device model; score each candidate protocol, and match the target protocol based on the scoring results. By introducing a quality screening mechanism for pitch angle and illumination value during the image acquisition stage, the validity of the input images is ensured, providing a data foundation for accurate identification of the device model. By inputting the device images into the pruned quantization target detection model for local inference to identify the device model, the network dependence and transmission delay caused by uploading images to the cloud for processing are avoided. After identifying the device model, multiple candidate protocols are further retrieved from the local database based on the device model, and the candidate protocols are scored to match the target protocol. This solves the problems of low efficiency of manual table lookup and difficulty in accurately selecting from multiple candidate protocols. Compared with the prior art, this achieves automated identification of device models and intelligent matching of protocols. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating an embodiment of the industrial equipment identification and protocol matching method of this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the industrial equipment identification and protocol matching method of this application; Figure 3 This is a schematic diagram of the module structure of the industrial equipment identification and protocol matching device according to an embodiment of this application; Figure 4 This is a schematic diagram of the hardware operating environment involved in the industrial equipment identification and protocol matching method in this application embodiment.

[0022] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0023] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0024] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0025] The main solution of this application embodiment is as follows: when the pitch angle and illumination value meet the shooting conditions, acquire device images according to a preset resolution; input the device images into the pruning quantization target detection model to identify the device model, and determine multiple candidate protocols from the local database according to the device model; score each candidate protocol, and match the target protocol according to the scoring results.

[0026] In this embodiment, for ease of description, the following description uses the terminal as the execution subject.

[0027] In industrial settings, equipment identification and protocol matching are typically done manually by looking up tables. This involves field engineers carrying paper or electronic equipment-protocol lookup tables and manually searching for and configuring the corresponding protocol parameters based on the equipment label information. This experience-dependent approach suffers from low efficiency and a high error rate when dealing with diverse equipment types and rapidly updating protocol versions, making it difficult to meet the maintenance needs for rapid onboarding of field devices.

[0028] This application provides a solution that ensures the validity of input images by introducing a quality screening mechanism based on pitch angle and illumination value during the image acquisition stage, providing a data foundation for accurate identification of subsequent device models. By inputting device images into a pruned quantization target detection model for local inference and identification of device models, the network dependency and transmission latency caused by uploading images to the cloud for processing are avoided. After identifying the device model, multiple candidate protocols are further retrieved from the local database based on the device model, and the candidate protocols are scored to match the target protocol. This solves the problems of low efficiency of manual table lookup and difficulty in accurately selecting from multiple candidate protocols. Compared with existing technologies, this achieves automated identification of device models and intelligent matching of protocols.

[0029] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or terminal capable of performing the above functions. The following description uses a terminal as an example to illustrate this embodiment and the subsequent embodiments.

[0030] Based on this, embodiments of this application provide a method for industrial equipment identification and protocol matching, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the industrial equipment identification and protocol matching method of this application.

[0031] In this embodiment, the industrial equipment identification and protocol matching method includes steps S10 to S30: Step S10: When the pitch angle and illumination value meet the shooting conditions, acquire the device image according to the preset resolution; It should be noted that the pitch angle is the tilt angle of the terminal relative to the horizontal plane, which is detected in real time by the terminal's built-in gyroscope sensor; the illuminance value is the light intensity of the environment in which the terminal is located, which is detected in real time by the terminal's built-in light sensor; the shooting conditions are the numerical range requirements that the pitch angle and illuminance value must meet; the preset resolution is a pre-set image size parameter used to adapt to the input specifications of the subsequent target detection model; and the device image is the image data obtained by resizing the original image containing the device label captured by the terminal's camera.

[0032] Specifically, the terminal obtains the current pitch angle value through a gyroscope sensor and the current illuminance value through a light sensor. The terminal compares the obtained pitch angle value with a preset angle threshold and the obtained illuminance value with a preset illuminance threshold. When the pitch angle value is less than or equal to the preset angle threshold and the illuminance value is greater than or equal to the preset illuminance threshold, the terminal determines that the current environment meets the shooting conditions and calls the camera interface to take a picture. The terminal adjusts the resolution of the captured raw image to a preset resolution to obtain the device image.

[0033] It is understandable that excessively large pitch angles or low illumination can lead to blurry images and difficulty in identifying device labels, thereby affecting the recognition accuracy of subsequent target detection models. Therefore, step S10 introduces a dual screening mechanism of pitch angle and illumination value during the image acquisition stage, which can avoid acquiring low-quality images, thereby improving the effectiveness of input images and the accuracy of subsequent device model recognition.

[0034] In one feasible implementation, before step S10, the following steps may be included: acquiring the pitch angle and illuminance value; disabling the shutter function when the pitch angle is greater than a preset angle threshold or the illuminance value is less than a preset illuminance threshold; and determining that the pitch angle and the illuminance value meet the shooting conditions when the pitch angle is less than or equal to the preset angle threshold or the illuminance value is greater than or equal to the preset illuminance threshold.

[0035] It should be noted that the preset angle threshold is the maximum allowed pitch angle for shooting, such as 75 degrees; the preset illuminance threshold is the minimum allowed light intensity for shooting, such as 50 lx; ​​the shutter function is the shooting trigger function of the terminal camera application. When the shutter function is disabled, the user cannot press the shooting button.

[0036] Specifically, the terminal monitors the pitch angle data output by the gyroscope sensor and the illuminance value data output by the light sensor in real time. The terminal compares the pitch angle data with a preset angle threshold of 75 degrees and the illuminance value data with a preset illuminance threshold of 50 lux. When the pitch angle is greater than 75 degrees or the illuminance value is less than 50 lux, the terminal displays a prompt message on the camera interface indicating that the angle or lighting does not meet the requirements, and disables the shutter button to prevent the user from taking pictures. When the pitch angle decreases to less than or equal to 75 degrees and the illuminance value increases to greater than or equal to 50 lux, the terminal unblocks the shutter button, allowing the user to take pictures.

[0037] In this embodiment, by disabling the shutter function in real time when the pitch angle or illumination value does not meet the requirements, and automatically restoring the shooting capability when the conditions are met, the problem of users taking low-quality images without their knowledge is solved, and closed-loop control of image acquisition quality is achieved, further ensuring the input quality of subsequent recognition processes.

[0038] The above are merely feasible implementations of step S10 provided in this embodiment. This embodiment does not specifically limit the specific implementation of step S10.

[0039] Step S20: Input the device image into the pruned quantization target detection model to identify the device model, and determine multiple candidate protocols from the local database based on the device model; It should be noted that the pruned and quantized object detection model is a lightweight model obtained by sequentially performing convolution kernel pruning and weight quantization on the original object detection model. Convolution kernel pruning is used to remove redundant convolution kernels in the model to compress the model size, and weight quantization is used to convert 32-bit floating-point weights into 8-bit integers to improve inference speed. The device model is a string of information output by the object detection model to uniquely identify the device type. The local database is a structured data file stored locally on the terminal, in which a mapping relationship between device models and protocol data is pre-established. The candidate protocol is one or more protocol data that have a mapping relationship with the identified device model.

[0040] Specifically, the terminal normalizes the device image obtained in step S10 by dividing the value of each pixel in the image by 255 to obtain normalized image data. The terminal then inputs the normalized image data into the pruned quantization target detection model. After forward computation, the model outputs a device model string and its corresponding confidence score. The terminal uses the device model string as a search keyword to perform a matching search in the local database index. Based on the matching search results, the terminal retrieves all protocol data corresponding to the device model from the local database and identifies all the retrieved protocol data as multiple candidate protocols.

[0041] It is understandable that, due to the possibility of weak network signals or no network coverage in industrial sites, it is impossible to access the cloud for image recognition in real time. Furthermore, the complete target detection model is large in size and has a slow inference speed, making it difficult to run in real time on terminal devices such as mobile phones. Therefore, step S20 is performed to use a lightweight model after pruning and quantization to complete the device model recognition locally on the terminal. This can avoid network dependence and transmission delays on cloud services, while reducing the model's consumption of terminal computing resources, thereby improving the real-time performance and availability of device recognition.

[0042] Step S30: Score each of the candidate protocols and match the target protocol according to the scoring results; It should be noted that the scoring result is a comprehensive score of each candidate protocol across multiple dimensions, used to quantify the compatibility of each protocol with the current equipment; the target protocol is the protocol with the highest score and the most suitable for distribution to industrial field equipment selected from multiple candidate protocols.

[0043] Understandably, since multiple candidate protocols retrieved from the local database are mapped to device models, but different protocols differ in parameters such as baud rate and verification method, and the success rate of on-site configuration of different protocols varies, if a protocol is selected and deployed based solely on manual experience, it is easy for the protocol activation to fail due to parameter mismatch or low historical success rate. Therefore, step S30 is performed to quantitatively score multiple candidate protocols in multiple dimensions and match the target protocol based on the scoring results. This can avoid relying on subjective judgment based on manual experience, thereby improving the scientific nature of protocol selection and the success rate of protocol activation.

[0044] In one feasible implementation, step S30 may include: scoring each candidate protocol based on its baud rate matching degree, check matching degree, historical success rate and protocol selection rate to obtain a scoring result; and determining a target protocol from multiple candidate protocols based on the scoring result.

[0045] It should be noted that baud rate matching degree is the degree of matching between the baud rate value of the candidate protocol and the default baud rate value of the field monitoring unit; verification matching degree is the degree of consistency between the verification method of the candidate protocol and the default verification method of the field monitoring unit; historical success rate is the proportion of the number of times the candidate protocol has been successfully configured in the past three months to the total number of configurations; and protocol selection rate is the proportion of the number of times the candidate protocol has been selected in the past three months to the total number of times all protocols of the same model of equipment have been selected.

[0046] Specifically, the terminal reads the default baud rate and default parity method of the field monitoring unit from the local configuration file. For each candidate protocol, the terminal compares its baud rate with the default baud rate; if they match, a first score (e.g., 100 points) is assigned, and if they do not match, a second score (e.g., 50 points) is assigned, thus obtaining the baud rate matching degree of the candidate protocol. The terminal then compares its parity method with the default parity method; if they match, a third score (e.g., 100 points) is assigned, and if they do not match, a fourth score (e.g., 40 points) is assigned, thus obtaining the parity matching degree of the candidate protocol. Finally, the terminal reads the number of successful configurations and the total number of configurations for the candidate protocol in the past three months from the local database. The historical success rate of the candidate protocol is obtained by dividing the number of successful attempts by the total number of attempts. The terminal reads the number of times the candidate protocol has been selected in the past three months and the total number of times all protocols of the same model have been selected from the local database. The selection rate of the candidate protocol is obtained by dividing the selection rate of the candidate protocol by the total number of attempts. The terminal multiplies the baud rate matching degree, parity matching degree, historical success rate and protocol selection rate by their respective weight coefficients and sums them to obtain the score of the candidate protocol. The terminal repeats the above scoring process for all candidate protocols to obtain the score of each candidate protocol. The terminal compares the score of each candidate protocol and determines the candidate protocol with the highest score as the target protocol.

[0047] In this embodiment, candidate protocols are quantitatively scored from four dimensions: baud rate matching degree, verification matching degree, historical success rate, and protocol selection rate. The target protocol is determined based on the comprehensive score, which solves the problem of scientifically selecting from multiple candidate protocols, realizes the objectivity and data-driven nature of the protocol matching process, and improves the accuracy of the adaptation between the target protocol and the field equipment.

[0048] In one feasible implementation, step S30 may include: obtaining the current transmission link; writing the target protocol into the industrial field device corresponding to the device model through the current transmission link; highlighting the industrial field device in the three-dimensional digital twin interface and generating a prompt message indicating that the protocol has been activated.

[0049] It should be noted that the current transmission link refers to the currently available communication connection method between the terminal and the industrial field equipment, including wireless fidelity links or Bluetooth low power links; the 3D digital twin interface is a visual interface that maps the status of industrial field equipment in real time in the form of a 3D model; and the prompt information is a text or graphic label used to provide feedback to the user on the results of the protocol.

[0050] Specifically, the terminal detects the available communication connection between itself and the industrial field device, and selects the one with the best signal strength or the highest connection stability from the Wi-Fi link and Bluetooth Low Energy link as the current transmission link; the terminal sends the target protocol determined in step S30 to the industrial field device through the selected current transmission link, and the industrial field device receives and writes the target protocol; after successfully sending the protocol, the terminal locates the 3D model corresponding to the industrial field device in the 3D digital twin interface, adjusts the display color of the 3D model to a highlighted state, and at the same time pops up or floats the text prompt message "Protocol activated" in the interface.

[0051] In this embodiment, by automatically selecting the optimal transmission link to send the target protocol and highlighting the device and generating prompt information in the three-dimensional digital twin interface, the problems of unclear link selection and unintuitive operation result feedback during the protocol sending process are solved. This realizes the automated execution of protocol sending and the visual confirmation of operation results, thereby improving the user's operating experience and on-site operation efficiency.

[0052] The above are merely feasible implementations of step S30 provided in this embodiment. This embodiment does not specifically limit the specific implementation of step S30.

[0053] This embodiment provides a method for industrial equipment identification and protocol matching. When the pitch angle and illumination value meet the shooting conditions, an image of the equipment is acquired at a preset resolution. The equipment image is input into a pruned quantization target detection model to identify the equipment model, and multiple candidate protocols are determined from a local database based on the equipment model. Each candidate protocol is scored, and a target protocol is matched based on the scoring results. By introducing a quality screening mechanism for pitch angle and illumination value during the image acquisition stage, the validity of the input image is ensured, providing a data foundation for accurate identification of the subsequent equipment model. By inputting the equipment image into the pruned quantization target detection model for local inference to identify the equipment model, the network dependency and transmission latency caused by uploading images to the cloud for processing are avoided. After identifying the equipment model, multiple candidate protocols are further retrieved from the local database based on the equipment model, and the candidate protocols are scored to match the target protocol. This solves the problems of low efficiency in manual table lookup and difficulty in accurately selecting from multiple candidate protocols. Compared with existing technologies, this method achieves automated identification of equipment models and intelligent matching of protocols.

[0054] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 The industrial equipment identification and protocol matching method further includes steps S21 to S23 in step S20: Step S21: Normalize the device image; It should be noted that normalization is a data conversion process that adjusts the numerical range of image pixel values ​​to a preset range.

[0055] Specifically, the terminal acquires the device image collected in step S10. The device image consists of multiple pixels, each of which has an original pixel value ranging from 0 to 255. The terminal iterates through each pixel in the device image, divides the original pixel value of each pixel by 255, and obtains a normalized pixel value. The terminal then recombines the normalized pixel values ​​according to the pixel arrangement order of the original image to obtain the normalized device image.

[0056] It is understandable that since the image data used by the object detection model during the training phase has been normalized, its internal weight parameters have been adapted to input values ​​in the range of 0 to 1. If the original pixel values ​​in the range of 0 to 255 are directly input into the model, the distribution of the model input data will be inconsistent with that during the training phase, affecting the model's recognition accuracy. Therefore, step S21, which normalizes the device image, can avoid the degradation of model performance caused by differences in the distribution of input data, thereby improving the accuracy of the device model output by the object detection model.

[0057] Step S22: Use the normalized device image as input to the pruned quantization target detection model to obtain the device model and corresponding confidence level output by the target detection model; It should be noted that confidence level is the degree of certainty that the target detection model is about its output device model identification result, and it is represented by a value between 0 and 1. The higher the value, the more reliable the identification result.

[0058] Specifically, the terminal loads the normalized device image obtained in step S21 into memory and passes the image data as an input parameter to the inference interface of the pruned quantization object detection model; the pruned quantization object detection model performs multi-layer convolution calculation, feature extraction and classification prediction on the input image data, and generates a probability value corresponding to each possible device model in the output layer of the model; the terminal extracts the device model string with the highest probability value from the model output and uses the highest probability value as the confidence level corresponding to the device model.

[0059] It is understandable that due to wear, dirt, or differences in shooting angles of equipment labels in different industrial sites, the features of some equipment images may not be obvious, and the recognition results of the target detection model for such images may not be reliable enough. Therefore, step S22 is performed to output the corresponding confidence level while obtaining the equipment model. This can provide a quantitative basis for the credibility of the recognition results in subsequent processes, thereby avoiding configuration errors caused by directly performing protocol matching when the recognition results are unreliable, and improving the fault tolerance and reliability of the entire method.

[0060] In one feasible implementation, step S22 may include: when the confidence level is less than a preset confidence threshold, performing feature extraction on the device image to obtain an anonymous feature vector; uploading the anonymous feature vector to the cloud so that the cloud generates an incremental update file based on the anonymous feature vector; and updating the pruned quantized target detection model according to the incremental update file.

[0061] It should be noted that the preset confidence threshold is a pre-set confidence level boundary used to determine whether the recognition result is reliable, for example, 0.85; the anonymous feature vector is a numerical sequence extracted from the device image to characterize the image features, and this numerical sequence has removed identifiable sensitive information such as the device serial number; the incremental update file is a lightweight model patch file generated in the cloud based on the anonymous feature vector, containing new device feature parameters.

[0062] Specifically, the terminal compares the confidence score obtained in step S22 with a preset confidence threshold of 0.85. When the confidence score is less than 0.85, the terminal determines that the current recognition result is unreliable and triggers the model update process. The terminal inputs the device image collected in step S10 into the feature extraction network, and after multi-layer convolution calculation, outputs a 512-byte numerical sequence, which is the anonymous feature vector. The terminal uploads the anonymous feature vector to the cloud server via the MQTT (Message Queuing Telemetry Transport) protocol. After receiving the anonymous feature vector, the cloud server inputs it into a large-scale object detection model deployed in the cloud for knowledge distillation processing, generating a patch file (incremental update file) of less than 100 kilobytes. The cloud server stores the incremental update file in a designated location and records its version information. When the terminal detects that the current network connection is Wi-Fi and is in an idle state, it automatically sends an update request to the cloud server to obtain the incremental update file. The terminal loads the incremental update file into the pruned quantization object detection model and performs hot updates on some weight parameters of the model. The update process does not require restarting the application.

[0063] In this embodiment, by triggering an incremental learning process of edge-cloud collaboration when the confidence level is below a threshold, only anonymous feature vectors are uploaded and lightweight patch files are downloaded. This solves the problem of privacy leakage risk and high traffic consumption caused by the traditional model update method of uploading the original image and downloading the full model. It realizes the dynamic evolution of the model under the premise of protecting device privacy and improves the model's ability to recognize new devices.

[0064] The above are merely feasible implementations of step S22 provided in this embodiment. This embodiment does not specifically limit the specific implementation of step S22.

[0065] Step S23: When the confidence level is greater than or equal to a preset confidence threshold, determine multiple candidate protocols from the local database based on the device model.

[0066] It is understandable that since a confidence level greater than or equal to a preset confidence threshold indicates that the current device model identification result is reliable, protocol matching can be performed directly based on that model. If a forced matching is performed when the confidence level is insufficient, it may lead to an incorrect protocol selection. Therefore, step S23 is performed, and the protocol retrieval process is only started when the identification result is reliable. This can avoid the failure to send the protocol due to matching the protocol based on the wrong device model, thereby improving the accuracy of protocol matching.

[0067] In one feasible implementation, step S23 may include: when the confidence level is greater than or equal to a preset confidence threshold, performing a search in a local database based on the device model to obtain search results, wherein the local database pre-stores mapping records between different device models and different protocols; and obtaining multiple candidate protocols based on the search results.

[0068] It should be noted that the search results are a collection of data returned by the local database after searching based on the device model; the mapping records between different device models and different protocols are data table entries established in the local database to associate device models and their supported protocols.

[0069] Specifically, after confirming that the confidence level obtained in step S22 is greater than or equal to the preset confidence threshold of 0.85, the terminal uses the device model string obtained in step S22 as the search keyword; the terminal searches for all mapping records that match the device model in the full-text search index of the local database; the terminal extracts the complete protocol data corresponding to each record from the mapping records returned by the database, including parameters such as baud rate and check method; the terminal organizes all the extracted protocol data into a list to obtain multiple candidate protocols.

[0070] In this embodiment, candidate protocols are obtained by searching the local database based on the device model when the confidence level meets the threshold. This solves the problem that manual table lookup requires manually flipping through the reference table and is time-consuming. It realizes fast and automated protocol retrieval and improves the efficiency of on-site protocol matching.

[0071] The above are merely feasible implementations of step S23 provided in this embodiment. This embodiment does not specifically limit the specific implementation of step S23.

[0072] This embodiment provides a method for industrial equipment identification and protocol matching. The method involves normalizing the equipment image, using the normalized image as input to a pruned quantization target detection model, and obtaining the equipment model output by the model along with its corresponding confidence level. When the confidence level is greater than or equal to a preset confidence threshold, multiple candidate protocols are determined from a local database based on the equipment model. Because normalization ensures the image data distribution aligns with the model training phase, and the pruned quantization target detection model performs equipment model identification locally on the terminal, protocol retrieval is only performed when the identification result's confidence level meets the threshold. This avoids identification errors caused by differences in input data distribution, identification delays due to network dependence, and protocol selection errors caused by forced matching with low confidence levels. It solves the technical problem of difficulty in real-time equipment model identification and rapid protocol matching in industrial environments with weak or no network coverage, thus achieving efficient and accurate local identification of equipment models and rapid protocol retrieval based on the identification results.

[0073] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the industrial equipment identification and protocol matching method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0074] This application also provides an industrial equipment identification and protocol matching device, please refer to... Figure 3 The industrial equipment identification and protocol matching device includes: The acquisition module 10 is used to acquire device images according to a preset resolution when the pitch angle and illumination value meet the shooting conditions; The identification module 20 is used to input the device image into the pruned quantization target detection model to identify the device model, and determine multiple candidate protocols from the local database based on the device model; The matching module 30 is used to score each of the candidate protocols and match the target protocol based on the scoring results.

[0075] The industrial equipment identification and protocol matching device provided in this application, employing the industrial equipment identification and protocol matching method in the above embodiments, can solve the technical problem of how to achieve automated identification and protocol configuration of industrial field equipment. Compared with the prior art, the beneficial effects of the industrial equipment identification and protocol matching device provided in this application are the same as those of the industrial equipment identification and protocol matching method provided in the above embodiments, and other technical features in the industrial equipment identification and protocol matching device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0076] The acquisition module 10 is also used to acquire pitch angle and illuminance value; when the pitch angle is greater than a preset angle threshold or the illuminance value is less than a preset illuminance threshold, the shutter function is disabled; when the pitch angle is less than or equal to the preset angle threshold or the illuminance value is greater than or equal to the preset illuminance threshold, the pitch angle and the illuminance value are determined to meet the shooting conditions.

[0077] The identification module 20 is further configured to normalize the device image; use the normalized device image as input to the pruned quantization target detection model to obtain the device model output by the target detection model and the corresponding confidence level; when the confidence level is greater than or equal to a preset confidence threshold, determine multiple candidate protocols from the local database based on the device model.

[0078] The identification module 20 is further configured to extract features from the device image to obtain an anonymous feature vector when the confidence level is less than a preset confidence threshold; upload the anonymous feature vector to the cloud so that the cloud generates an incremental update file based on the anonymous feature vector; and update the pruned quantization target detection model according to the incremental update file.

[0079] The identification module 20 is further configured to, when the confidence level is greater than or equal to a preset confidence threshold, perform a search in a local database based on the device model to obtain search results, wherein the local database pre-stores mapping records between different device models and different protocols; based on the search results, multiple candidate protocols are obtained.

[0080] The matching module 30 is further configured to score each candidate protocol based on its baud rate matching degree, check matching degree, historical success rate and protocol selection rate, and obtain a scoring result; and to determine the target protocol from multiple candidate protocols based on the scoring result.

[0081] The matching module 30 is also used to obtain the current transmission link; write the target protocol into the industrial field device corresponding to the device model through the current transmission link; highlight the industrial field device in the three-dimensional digital twin interface and generate a prompt message indicating that the protocol has been activated.

[0082] This application provides an industrial equipment identification and protocol matching device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the industrial equipment identification and protocol matching method in the first embodiment described above.

[0083] The following is for reference. Figure 4 This document illustrates a structural schematic diagram of an industrial equipment identification and protocol matching device suitable for implementing embodiments of this application. The industrial equipment identification and protocol matching device in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The industrial equipment identification and protocol matching device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0084] like Figure 4As shown, the industrial equipment identification and protocol matching device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the industrial equipment identification and protocol matching device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the industrial equipment identification and protocol matching device to communicate wirelessly or wiredly with other devices to exchange data. Although industrial equipment identification and protocol matching devices with various systems are shown in the figure, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0085] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0086] The industrial equipment identification and protocol matching device provided in this application, employing the industrial equipment identification and protocol matching method described in the above embodiments, can solve the technical problem of how to achieve automated identification and protocol configuration of industrial field equipment. Compared with the prior art, the beneficial effects of the industrial equipment identification and protocol matching device provided in this application are the same as those of the industrial equipment identification and protocol matching method provided in the above embodiments, and other technical features of this industrial equipment identification and protocol matching device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0087] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0088] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0089] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the industrial equipment identification and protocol matching method in the above embodiments.

[0090] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0091] The aforementioned computer-readable storage medium may be included in the industrial equipment identification and protocol matching device; or it may exist independently and not be assembled into the industrial equipment identification and protocol matching device.

[0092] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the industrial equipment identification and protocol matching device, the industrial equipment identification and protocol matching device performs the following actions: when the pitch angle and illumination value meet the shooting conditions, it acquires an image of the equipment at a preset resolution; it inputs the image of the equipment into a pruned quantization target detection model to identify the equipment model, and determines multiple candidate protocols from a local database based on the equipment model; it scores each candidate protocol, and matches a target protocol based on the scoring results.

[0093] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0094] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0095] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0096] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described industrial equipment identification and protocol matching method, thereby solving the technical problem of how to achieve automated identification and protocol configuration of industrial field equipment. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the industrial equipment identification and protocol matching method provided in the above embodiments, and will not be repeated here.

[0097] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the industrial equipment identification and protocol matching method described above.

[0098] The computer program product provided in this application can solve the technical problem of how to achieve automated identification and protocol configuration of industrial field equipment. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the industrial equipment identification and protocol matching method provided in the above embodiments, and will not be repeated here.

[0099] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for industrial equipment identification and protocol matching, characterized in that, The method includes: When the pitch angle and illumination value meet the shooting conditions, acquire device images according to the preset resolution; The device image is input into the pruned quantization target detection model to identify the device model, and multiple candidate protocols are determined from the local database based on the device model. Each candidate protocol is scored, and a target protocol is matched based on the scoring results.

2. The method as described in claim 1, characterized in that, Before acquiring the device image according to the preset resolution when the pitch angle and illumination value meet the shooting conditions, the process also includes: Obtain the pitch angle and illuminance value; When the pitch angle is greater than a preset angle threshold or the illuminance value is less than a preset illuminance threshold, the shutter function is disabled. When the pitch angle is less than or equal to a preset angle threshold or the illuminance value is greater than or equal to a preset illuminance threshold, it is determined that the pitch angle and the illuminance value meet the shooting conditions.

3. The method as described in claim 1, characterized in that, The step involves inputting the device image into a pruned quantization target detection model to identify the device model, and determining multiple candidate protocols based on the device model, including: The device image is normalized. The normalized device image is used as the input to the pruned quantization target detection model to obtain the device model and corresponding confidence level output by the target detection model. When the confidence level is greater than or equal to a preset confidence threshold, multiple candidate protocols are determined from the local database based on the device model.

4. The method as described in claim 3, characterized in that, After using the normalized device image as input to the pruned quantization target detection model to obtain the device model and corresponding confidence score output by the target detection model, the method further includes: When the confidence level is less than a preset confidence threshold, feature extraction is performed on the device image to obtain an anonymous feature vector; The anonymous feature vector is uploaded to the cloud so that the cloud generates an incremental update file based on the anonymous feature vector. The pruned quantized target detection model is updated based on the incremental update file.

5. The method as described in claim 3, characterized in that, When the confidence level is greater than or equal to a preset confidence threshold, multiple candidate protocols are determined from a local database based on the device model, including: When the confidence level is greater than or equal to a preset confidence threshold, a search is performed in the local database based on the device model to obtain the search results. The local database pre-stores mapping records between different device models and different protocols. Based on the search results, multiple candidate protocols were obtained.

6. The method as described in claim 1, characterized in that, The step of scoring each of the candidate protocols and matching the target protocol based on the scoring results includes: Each candidate protocol is scored based on its baud rate matching degree, check matching degree, historical success rate, and protocol selection rate to obtain a scoring result. Based on the scoring results, the target protocol is determined from multiple candidate protocols.

7. The method as described in claim 1, characterized in that, After scoring each of the candidate protocols and matching the target protocol based on the scoring results, the process further includes: Obtain the current transmission link; The target protocol is written into the industrial field equipment corresponding to the device model through the current transmission link; The industrial field equipment is highlighted in the 3D digital twin interface, and a prompt message indicating that the protocol has been activated is generated.

8. An industrial equipment identification and protocol matching device, characterized in that, The device includes: The acquisition module is used to acquire images from the device at a preset resolution when the pitch angle and illumination value meet the shooting conditions. The identification module is used to input the device image into the pruned quantization target detection model to identify the device model, and determine multiple candidate protocols from the local database based on the device model; The matching module is used to score each of the candidate protocols and match the target protocol based on the scoring results.

9. An industrial equipment identification and protocol matching device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the industrial equipment identification and protocol matching method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the industrial equipment identification and protocol matching method as described in any one of claims 1 to 7.

Images