Point table data acquisition method and equipment based on Internet of Things equipment, and medium

Abstract

The invention discloses a point table data collection method and device based on an Internet of Things device and a medium, and the method comprises the steps: obtaining a historical point table file, determining key features in the historical point table file, and training a corresponding recognition model based on the key features; wherein the identification model comprises an equipment column identification model, a measuring point column identification model, an address column identification model and an equipment measuring point column identification model; receiving a point table file provided by an equipment manufacturer or a fully mechanized coal mining system, and identifying an equipment column, a measuring point column and an address column in the point table file through the trained identification model; outputting a point table file in a corresponding format according to an identification result; wherein the format comprises an equipment column, a measuring point column, an equipment column, a measuring point column and an address column.

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to a point table data collection method, device and medium based on Internet of Things devices. Background Art

[0002] In the current industrial IoT environment, the entire process from field data collection to the IoT platform creating device storage data and mapping it to physical devices still faces many challenges. Traditionally, this process is highly dependent on manual operations. Implementers not only need to have a deep understanding of the point table information provided by the equipment manufacturer or the integrated collection system, but also must be familiar with the configuration process of the edge gateway and the device registration method on the IoT platform. This not only increases the time cost of training implementation personnel, but also significantly increases the difficulty and complexity of product implementation in the project.

[0003] Although the IoT platform has made some progress in device data collection technology, it still faces multiple challenges in practical applications, especially in large-scale projects. First, due to the surge in the number and types of devices, the manual configuration process has become extremely cumbersome and error-prone, resulting in low overall implementation efficiency. Second, although the IoT platform and edge gateway provide certain technical support for the registration of large-scale devices or measurement points, the automatic recognition capability of the point table information provided by the equipment manufacturer or the integrated collection system is still insufficient, and it is impossible to achieve closed-loop automation from point table recognition to data collection. In addition, the inconsistency of the point table format further exacerbates the difficulty and complexity of manual identification of the point table.

[0004] More importantly, the current IoT data collection implementation process is still highly dependent on manual operations and lacks a complete and efficient automated data collection solution. This not only limits the application and promotion of IoT technology in a wider range of scenarios, but also hinders the process of achieving comprehensive intelligence and automation in the industrial IoT. Summary of the invention

[0005] The embodiments of the present application provide a point table data collection method, device and medium based on an Internet of Things device to solve the above-mentioned technical problems.

[0006] On the one hand, an embodiment of the present application provides a point meter data collection method based on an Internet of Things device, including:

[0007] Obtain a historical point table file, and determine key features in the historical point table file, so as to train a corresponding recognition model based on the key features; wherein the recognition model includes a device column recognition model, a measurement point column recognition model, an address column recognition model, and a device measurement point column recognition model;

[0008] Receive the point table file provided by the equipment manufacturer or the comprehensive mining system, and identify the equipment column, measurement point column and address column in the point table file through the trained recognition model;

[0009] According to the recognition result, a point table file of a corresponding format is output; wherein the format includes a device column and a measuring point column, as well as a device column, a measuring point column and an address column.

[0010] In one implementation of the present application, determining the key features in the historical point table file to train a corresponding recognition model based on the key features specifically includes:

[0011] Based on the data characteristics corresponding to the point table data, determine the key features in the historical point table file, and remove the header data in the key features to obtain the target key features;

[0012] The data characteristics of the point table data include the format and regularity of the equipment column, the measuring point column and the address column;

[0013] Convert the target key features into corresponding word vectors, and use the word vectors as input for model training;

[0014] The model is trained using the random forest algorithm and the number of trees is set.

[0015] In one implementation of the present application, the device column, the measurement point column and the address column in the point table file are identified by using a trained recognition model, specifically including:

[0016] The point table file is identified by the trained equipment column identification model and the measuring point column identification model to output the corresponding equipment column serial number and the measuring point column serial number;

[0017] The point table file is identified by using the trained address column identification model to output the corresponding address column serial number.

[0018] In one implementation of the present application, after the point table file is identified respectively by using the trained device column identification model and the measurement point column identification model, the method further includes:

[0019] If the output serial numbers of the equipment column identification model and the measuring point column identification model are the same, or at least one of the equipment column serial number and the measuring point column serial number is missing, then determining that the equipment measuring points in the point table file are one column;

[0020] The device column and the measuring point column in the point table file are segmented by using the trained device measuring point column recognition model to output corresponding device column serial numbers and measuring point column serial numbers.

[0021] In one implementation of the present application, after outputting the corresponding device column number and measurement point column number, the method further includes:

[0022] Invoke a third-party translation tool to encode the equipment column number and the measuring point column number respectively to obtain equipment names and equipment codes and measuring point names and measuring point codes;

[0023] Aggregating the device name, the device code, the measuring point name and the measuring point code according to the device column, and comparing the aggregated device template with the measuring point column;

[0024] If the aggregated device template is consistent with the measuring point column, the devices under the same device template are named in a preset naming manner.

[0025] In an implementation of the present application, if the aggregated device template is consistent with the measurement point column, after naming the devices under the same device template by a preset naming method, the method further includes:

[0026] Comparing the aggregated device template with existing templates of the Internet of Things platform to determine a plurality of similarities between the device template and each existing template in the Internet of Things platform;

[0027] In the case that there is a similarity exceeding a preset similarity threshold among the multiple similarities, adopting the device template and supplementing the measurement points of the device template;

[0028] Generate a batch import file for devices and register the devices.

[0029] In one implementation of the present application, after comparing the aggregated device template with an existing template of the Internet of Things platform to determine a plurality of similarities corresponding to the device template and each existing template in the Internet of Things platform, the method further includes:

[0030] If none of the multiple similarities exceeds a preset similarity threshold, generating a device template and an import file corresponding to the device template;

[0031] Call the device template and device import interface in the Internet of Things platform, and register the device template and device in the Internet of Things platform.

[0032] In one implementation of the present application, according to the recognition result, a point table file of a corresponding format is output, specifically including:

[0033] According to the recognition results, output the point table file in the format of device column, measurement point column and address column, and generate the corresponding edge gateway import point table;

[0034] Call the corresponding interface in the IoT platform to import the corresponding edge gateway import point table and send the standard format data of the IoT platform.

[0035] On the other hand, the embodiment of the present application further provides a point table data collection device based on an Internet of Things device, the device comprising:

[0036] at least one processor;

[0037] and, a memory communicatively coupled to the at least one processor;

[0038] Among them, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the point table data collection method based on the Internet of Things device as mentioned above.

[0039] On the other hand, an embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, which, when executed, implements a point table data collection method based on an Internet of Things device as described above.

[0040] The present application provides a method, device and medium for collecting point table data based on an Internet of Things device, which at least has the following beneficial effects:

[0041] By training specialized equipment column recognition models, measurement point column recognition models, address column recognition models and equipment measurement point column recognition models, key features can be quickly and accurately extracted from various historical point table files, and then newly received point table files can be efficiently processed, significantly improving processing speed and accuracy; point table files from different equipment manufacturers or comprehensive mining systems can be processed, and key column information equipment column, measurement point column and address column can be identified through models, so that the system has good compatibility with point table files of different formats, improving the flexibility and applicability of the system; according to the recognition results, point table files can be automatically converted into two standard formats, including only equipment column and measurement point column, and including equipment column, measurement point column and address column, which is convenient for subsequent data processing, analysis and management, and promotes data consistency and standardization; the automated recognition and format conversion process reduces the need for manual inspection and manual adjustment of point table files, reduces human resource consumption, improves work efficiency, and also reduces data problems caused by human errors; point table files in a unified format are more convenient for data integration, analysis and visualization, providing a solid foundation for applications such as equipment monitoring, fault diagnosis, and performance optimization, and helping to further improve overall production efficiency and operation and maintenance levels. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0043] Figure 1 A schematic diagram of a flow chart of a point table data collection method based on an Internet of Things device provided in an embodiment of the present application;

[0044] Figure 2 A schematic diagram of the internal structure of a point table data collection device based on an Internet of Things device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0046] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0047] Figure 1 A flowchart of a point table data collection method based on an Internet of Things device is provided in an embodiment of the present application.

[0048] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For the convenience of understanding and description, the following embodiments are described in detail by taking a server as an example.

[0049] It should be noted that the server may be a single device or a system consisting of multiple devices, that is, a distributed server, and this application does not make any specific limitation on this.

[0050] like Figure 1 As shown, an embodiment of the present application provides a point table data collection method based on an Internet of Things device, comprising:

[0051] 101. Obtain a historical point table file, and determine key features in the historical point table file, so as to train a corresponding recognition model based on the key features.

[0052] It should be noted that the identification model in the embodiment of the present application includes a device column identification model, a measurement point column identification model, an address column identification model and a device measurement point column identification model.

[0053] The equipment column, measuring point column and measuring point address column in the point table Excel file provided by the equipment manufacturer or the comprehensive mining system all have their own characteristics. For example, the equipment column and measuring point column are generally the real names of the equipment and measuring points. Equipment columns include fans, water pumps, etc., and measuring points are generally in the xx value format, such as temperature values, vibration values, current values, etc. There are also cases where equipment and measuring points are in one column and need to be split into two columns; the address column is generally in the format of DBX.DBDX.X, DBX.XX, 4xxxx, VX.XX, 1xxxx, etc.

[0054] Specifically, in one embodiment of the present application, determining key features in the historical point table file to train a corresponding recognition model based on the key features specifically includes:

[0055] Based on the data characteristics corresponding to the point table data, the key features in the historical point table file are determined, and the header data in the key features are removed to obtain the target key features;

[0056] Among them, the data characteristics of the point table data include the format and rules of the equipment column, the measurement point column and the address column;

[0057] Convert the target key features into corresponding word vectors, and use the word vectors as input for model training;

[0058] The model is trained using the random forest algorithm and the number of trees is set.

[0059] In one embodiment, when the algorithm model is trained, the acquired data (without the header) is first converted into a word vector model. This patent uses Word2Vec as input, and then the random forest algorithm function in sklearn is used for training. 100 trees are set, and the output results are the device column, measurement point column, and address column serial numbers. After obtaining the serial numbers, the Excel file consisting of the columns with the selected serial numbers is read and output, and the output is the two files mentioned above.

[0060] In one embodiment, it is assumed that the historical point table file contains data in the device column, the measurement point column, and the address column, and these data have a specific format and regularity, such as the device column always starts with "DEV_", the measurement point column always contains the "_PT" suffix, and the address column is a series of continuous hexadecimal numbers. By writing scripts or using data processing tools, these data that conform to the specific format and regularity are identified as key features. Among the identified key features, the header data is removed, that is, the rows containing column names or descriptive text are removed, and only the actual data rows are retained to obtain the target key features.

[0061] Convert text data in the target key features (such as device names, measurement point names) into word vectors. You can use pre-trained word embedding models, such as Word2Vec or BERT, to convert text into fixed-length vectors. For hexadecimal numbers in the address column, you can convert them to decimal numbers and directly input them into the model as numerical features. Combine the converted word vectors and numerical features into a complete feature set as input for model training.

[0062] The random forest algorithm is selected as the algorithm for model training because it is a powerful ensemble learning method suitable for processing complex data sets. The number of trees is set to 100, which means that 100 decision trees will be built in the random forest to make predictions together. The random forest model is trained using the transformed feature set as input so that it can learn the relationship and rules between the equipment column, measurement point column, and address column.

[0063] 102. Receive the point list file provided by the equipment manufacturer or the comprehensive mining system, and identify the equipment column, measurement point column and address column in the point list file through the trained recognition model.

[0064] Specifically, in one embodiment of the present application, the device column, the measurement point column and the address column in the point table file are identified by using a trained recognition model, specifically including:

[0065] The point table file is identified by the trained equipment column identification model and measuring point column identification model to output the corresponding equipment column serial number and measuring point column serial number;

[0066] The point table file is identified through the trained address column recognition model to output the corresponding address column serial number.

[0067] In one embodiment, four models are trained to respectively identify the device column, the measuring point column, the device measuring point column, and the address column, and finally two excel files of the device column + measuring point column and the device column + measuring point column + address column are output. When constructing the training data set, it is important to distinguish between the device column, the measuring point column, and the device measuring point column. When the device column and the measuring point column are separated, two models are trained to respectively identify the device column and the measuring point column. When the device measuring points are in one column, one model is trained to output two columns, namely the device column and the measuring point column. To ensure a one-to-one correspondence between devices, measuring points, and attributes, no special treatment is performed on empty cells in the training set and the algorithm.

[0068] In one embodiment, it is assumed that the device column recognition model and the measuring point column recognition model have been trained, and these two models can respectively recognize the device column and the measuring point column in the point table file. When a new point table file is received, the device column recognition model is first used to recognize the file. The model will traverse each column in the file, determine which column is the device column based on the learned features, and output the corresponding device column serial number. For example, if the first column is the device column, the output serial number is 1. Next, the measuring point column recognition model is used to recognize the same point table file. Similarly, the model will traverse each column in the file, determine which column is the measuring point column, and output the corresponding measuring point column serial number. For example, if the third column is the measuring point column, the output serial number is 3.

[0069] Similarly, the address column recognition model has been trained, which can recognize the address column in the point table file. Use the address column recognition model to recognize the point table file. The model will traverse each column in the file, determine which column is the address column based on the learned features, and output the corresponding address column number. For example, if the second column is the address column, the output number is 2.

[0070] Through the above steps, the device column serial number, measurement point column serial number and address column serial number are obtained. These serial numbers indicate which column in the point table file is the device column, measurement point column and address column. These serial numbers can be used for subsequent data processing and analysis tasks. For example, the data of the device column, measurement point column and address column can be extracted according to these serial numbers for further analysis or storage in the database. In addition, these serial numbers can also be used to verify whether the format of the point table file is correct. If the identified serial number does not match the expected format, it means that there may be a problem with the format of the point table file, and further inspection and correction are required.

[0071] In one embodiment of the present application, after the point table file is identified respectively by the trained device column identification model and the measurement point column identification model, the following further includes:

[0072] If the output serial numbers of the equipment column identification model and the measuring point column identification model are the same, or at least one of the equipment column serial number and the measuring point column serial number is missing, the equipment measuring points in the point table file are determined to be one column;

[0073] The device column and the measuring point column in the point table file are segmented by the trained device measuring point column recognition model to output the corresponding device column serial number and measuring point column serial number.

[0074] In one embodiment, if the equipment measurement points are in one column, the algorithm model needs to call the Stanford NER toolkit to segment the column value into two columns. Stanford NER is a named entity recognition algorithm that can segment sentences. This article uses the equipment measurement point column value as input, and the equipment column and measurement point column values ​​as output for intensive training, which can perform more accurate segmentation. The algorithm results are the excel files of the equipment column, measurement point column, and address column after the value of the column is segmented by the serial number of the standby measurement point column.

[0075] In one embodiment, it is assumed that the device column identification model, the measuring point column identification model, and the device measuring point column identification model have been trained. When a new point table file is received, the device column identification model and the measuring point column identification model are first used to identify the file, and the corresponding device column serial number and measuring point column serial number are output respectively. Next, the output of these two serial numbers is checked. If the output serial numbers of the device column identification model and the measuring point column identification model are the same (that is, both point to the same column), or at least one of the device column serial number and the measuring point column serial number is missing (that is, at least one model does not identify the corresponding column), then it can be determined that the device measuring point information in the point table file is merged into one column.

[0076] Once it is determined that the device point information is in one column, the point table file is processed using the trained device point column recognition model. The device point column recognition model will split the merged device point column into separate device columns and point columns, and output the corresponding device column serial numbers and point column serial numbers. In this way, the correct device column and point column information can be obtained, even if they are merged together in the original point table file.

[0077] Through the above steps, the device column serial number and the measurement point column serial number after segmentation are obtained. These serial numbers indicate which column in the point table file is the device column and which column is the measurement point column. These serial numbers can be used for subsequent data processing and analysis tasks. For example, the data of the device column and the measurement point column can be extracted according to these serial numbers for further analysis or storage in the database. In addition, this method also improves the flexibility and compatibility of point table file processing, making it possible to process point table files of different formats and accurately extract the required information.

[0078] In one embodiment of the present application, after outputting the corresponding device column number and measurement point column number, the method further includes:

[0079] Call a third-party translation tool to encode the equipment column number and the measuring point column number respectively to obtain the equipment name and equipment code as well as the measuring point name and measuring point code;

[0080] Aggregate the device name, device code, measurement point name and measurement point code according to the device column, and compare the aggregated device template with the measurement point column;

[0081] If the aggregated device template is consistent with the measurement point column, the devices under the same device template are named using the preset naming method.

[0082] In one embodiment, in addition to the name, the Internet of Things platform also has a code as a unique identifier for a device template (product), device or measuring point. A translation tool can be used to translate the Chinese of the device template (product), device and measuring point into a code, or a script of the coding rule (written during implementation) can be called to generate a device code according to the device template (product) and generate a measuring point code according to the device.

[0083] Since the IoT platform generally has two concepts, device template (product) and device, the device template (product) is the abstraction of a type of device. This type of device has the same measurement points. The device template (product) has strong constraints on the device, that is, the measurement points of the devices under the device template (product) are the same. Therefore, the device column + measurement point column in the result obtained in the previous step can be classified, and then named to obtain the import table file of the device template (product). The specific steps are to aggregate according to the device column, and then compare whether the measurement point column is consistent. If it is consistent, it is a device under the same device template (product), and the naming method is device name + "template".

[0084] In one embodiment, it is assumed that the device column number and the measuring point column number have been obtained through the previous steps, and it is known which columns in the point table file these numbers correspond to. Call a third-party translation tool (such as an API or software library) to encode the text content in the device column number and the measuring point column number. For the column corresponding to the device column number, obtain the device name and device code; for the column corresponding to the measuring point column number, obtain the measuring point name and measuring point code. Next, the measuring point name and measuring point code are aggregated according to the device name and device code in the device column. This means that for each unique device, all its measuring point information is aggregated together. The result of the aggregation is a device template, which contains all the measuring point information of the device.

[0085] Compare the aggregated device template with the original point list to ensure the accuracy of the information. If the point information in the device template is exactly the same as the information in the point list, then you can confirm that the device template is correct. Once the accuracy of the device template is confirmed, use the preset naming method to name the devices under the same device template. The preset naming method may be a rule or pattern that generates a unique device name based on certain attributes of the device (such as device type, location, serial number, etc.). In this way, you can ensure that all devices under the same device template have consistent and easy-to-understand naming rules.

[0086] Finally, a list of devices named according to the preset naming method and the corresponding measurement point information are obtained. This information can be used for subsequent data processing, analysis, monitoring or report generation tasks. This method can improve the automation of point table file processing, reduce manual intervention, and ensure data accuracy and consistency.

[0087] In one embodiment of the present application, if the aggregated device template is consistent with the measurement point list, after naming the devices under the same device template by a preset naming method, the method further includes:

[0088] Comparing the aggregated device template with the existing templates of the IoT platform to determine multiple similarities between the device template and each existing template in the IoT platform;

[0089] When a similarity among multiple similarities exceeds a preset similarity threshold, a device template is used, and measurement points are supplemented for the device template;

[0090] Generate a batch import file for devices and register the devices.

[0091] In one embodiment, if the device template (product) already exists in the IoT platform, such as a cloud-edge collaborative IoT platform, the device template (product) is defined in the cloud, and the edge end pulls the device template (product) from the cloud for use. By comparing the device template (product) in the IoT platform and the device template (product) classification in the import table file, it can be decided to use the device template (product) in the platform or add a new device template (product). During the comparison process, if the consistency rate reaches 50%, it is considered that the device template (product) in the platform is used, and then the device template (product) in the platform is supplemented with measurement points.

[0092] In one embodiment, it is assumed that the device template has been aggregated through the previous steps, and now this template needs to be compared with the existing templates on the IoT platform. A similarity calculation algorithm (such as cosine similarity, Jaccard similarity, etc.) is used to calculate the similarity between the device template and each existing template in the IoT platform. The result of the comparison is a similarity list, and each element in the list represents the similarity between the device template and an existing template in the IoT platform.

[0093] Check the similarity list. If there is a similarity that exceeds the preset similarity threshold, it means that the device template is very similar to an existing template in the IoT platform. In this case, the device template is adopted and the measurement points of the device template are supplemented according to the measurement point information of the existing template to ensure the integrity of the device template. Once the device template is prepared (either original or supplemented with measurement points), a device batch import file is generated. This file contains the necessary information of all devices, such as device name, device code, measurement point name, measurement point code, etc., and is organized in the format required by the IoT platform.

[0094] Upload the generated device batch import file to the IoT platform and register the devices. The IoT platform will create new device records based on the information in the import file and add them to the platform's device database. After registration is complete, these devices can be monitored, managed, and controlled on the IoT platform.

[0095] Finally, new devices are registered on the IoT platform, and these devices have been configured according to the device template. These new devices can be used in various IoT applications, such as smart home, industrial monitoring, environmental monitoring, etc. In this way, a large number of devices can be quickly added to the IoT platform and the efficiency and accuracy of device management can be improved.

[0096] In one embodiment of the present application, after comparing the aggregated device template with the existing templates of the IoT platform to determine a plurality of similarities between the device template and each existing template in the IoT platform, the method further includes:

[0097] If multiple similarities do not exceed the preset similarity threshold, a device template and an import file corresponding to the device template are generated;

[0098] Call the device template and device import interface in the IoT platform, and register the device template and device in the IoT platform.

[0099] In one embodiment, it is assumed that the device template has been aggregated through the previous steps, and this template has been compared with the existing templates on the Internet of Things platform to obtain a similarity list. Checking this similarity list, it is found that all similarities do not exceed the preset similarity threshold. This means that the device template is not similar to the existing templates on the Internet of Things platform and is a brand new template. Since the device template is brand new, a corresponding device template file needs to be generated. This file contains all the necessary information of the device template, such as device name, device type, measurement point information, etc. At the same time, a device import file is also generated. This file contains the necessary information of all devices to be registered on the Internet of Things platform, and is organized in the format required by the Internet of Things platform.

[0100] Use the device template and device import interface provided by the IoT platform to upload the generated device template file and device import file to the IoT platform. During the upload process, you may need to provide some additional authentication information to ensure that you have the authority to perform these operations on the IoT platform. After the IoT platform receives the uploaded file, it will register the new device template and the corresponding device according to the information in the file. After the registration is completed, you can see these newly registered devices on the IoT platform's devices, and they have been configured according to the device template.

[0101] Finally, new device templates and corresponding devices registered on the IoT platform are obtained. These new devices can be used in various IoT applications, and because they are registered based on brand new device templates, they may have some unique functions or features. In this way, brand new devices and device templates can be quickly added to the IoT platform, and the functions and application scope of the IoT platform can be expanded.

[0102] 103. According to the recognition result, a point table file of a corresponding format is output.

[0103] It should be noted that the format in the embodiment of the present application includes a device column and a measurement point column, as well as a device column, a measurement point column and an address column.

[0104] Specifically, in one embodiment of the present application, according to the recognition result, a point table file of a corresponding format is output, which specifically includes:

[0105] According to the recognition results, output the point table file in the format of device column, measurement point column and address column, and generate the corresponding edge gateway import point table;

[0106] Call the corresponding interface in the IoT platform to import the corresponding edge gateway import point table and send the standard format data of the IoT platform.

[0107] In one embodiment, it is assumed that the device column, measurement point column and address column in the point table file have been identified through the previous steps, and the serial numbers of these columns have been obtained. According to these serial numbers, the data of the device column, measurement point column and address column are extracted from the original point table file, and a new point table file is output according to a certain format. This file only contains the three columns of data required, and the format and arrangement of the data meet the requirements.

[0108] Next, generate the corresponding edge gateway import point table based on the output point table file. The edge gateway import point table is a file in a specific format that contains all the devices, measurement points, and address information required by the edge gateway so that the edge gateway can communicate with these devices correctly. In the process of generating the edge gateway import point table, it is necessary to ensure that all devices, measurement points, and address information are correctly converted and mapped to the format required by the edge gateway.

[0109] Once the edge gateway import point table is generated, upload this file to the IoT platform using the corresponding interface provided by the IoT platform. During the upload process, you may need to provide some additional authentication information to ensure that you have the authority to perform these operations on the IoT platform. After the IoT platform receives the uploaded edge gateway import point table, it will start importing this file. During the import process, the IoT platform will parse the content in the file and add the device, measurement point and address information to the platform's database. After the import is complete, these newly added devices, measurement points and address information can be seen on the devices of the IoT platform, and they are ready to communicate with the edge gateway.

[0110] Finally, use the interface provided by the IoT platform to send data in a standard format to the IoT platform. This data may include real-time data of the device, alarm information, status updates, etc. After receiving this data, the IoT platform will process and analyze it and present the results to the end user or application. Through this process, the device, measurement point and address information in the point table file are successfully imported into the IoT platform, and the compatibility of this information with the edge gateway is ensured. This enables better monitoring and management of these devices and their integration into a larger IoT system. At the same time, the powerful functions and analysis tools provided by the IoT platform can be used to conduct in-depth analysis and processing of this data.

[0111] Finally, according to the table file content format required by the IoT platform's batch creation of device templates (products), batch creation of device interfaces, and batch import of measurement point interfaces in the edge gateway, call the format conversion script (written during implementation) for conversion, output the import table file, and then call the above interface to batch add device templates (products) and devices and batch import measurement points.

[0112] After completing the above steps, the implementer can check whether the device data is collected on the IoT platform, judge the collection quality, and then make adjustments based on the generated import table file and re-import to view the results until the expected results are achieved.

[0113] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, the embodiment of this application also provides a point table data collection device based on an Internet of Things device, whose structure is as follows: Figure 2 shown.

[0114] Figure 2 The internal structure diagram of a point table data collection device based on an Internet of Things device provided in an embodiment of the present application. Figure 2 As shown, the device includes:

[0115] at least one processor;

[0116] and, a memory communicatively coupled to the at least one processor;

[0117] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable the at least one processor to:

[0118] Obtain a historical point table file, and determine key features in the historical point table file, so as to train a corresponding recognition model based on the key features; wherein the recognition model includes a device column recognition model, a measurement point column recognition model, an address column recognition model, and a device measurement point column recognition model;

[0119] Receive the point list file provided by the equipment manufacturer or the comprehensive mining system, and identify the equipment column, measurement point column and address column in the point list file through the trained recognition model;

[0120] According to the recognition result, a point table file of a corresponding format is output; wherein the format includes a device column and a measuring point column, as well as a device column, a measuring point column and an address column.

[0121] The present application also provides a non-volatile computer storage medium storing computer executable instructions. When the computer executable instructions are executed, they can:

[0122] Obtain a historical point table file, and determine key features in the historical point table file, so as to train a corresponding recognition model based on the key features; wherein the recognition model includes a device column recognition model, a measurement point column recognition model, an address column recognition model, and a device measurement point column recognition model;

[0123] Receive the point list file provided by the equipment manufacturer or the comprehensive mining system, and identify the equipment column, measurement point column and address column in the point list file through the trained recognition model;

[0124] According to the recognition result, a point table file of a corresponding format is output; wherein the format includes a device column and a measuring point column, as well as a device column, a measuring point column and an address column.

[0125] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0126] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0127] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0128] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0129] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0130] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0131] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0132] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0133] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0134] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0135] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0136] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A point table data collection method based on Internet of Things devices, characterized in that: The method comprises: Obtain a historical point table file, and determine key features in the historical point table file, so as to train a corresponding recognition model based on the key features; wherein the recognition model includes a device column recognition model, a measurement point column recognition model, an address column recognition model, and a device measurement point column recognition model; Receive the point table file provided by the equipment manufacturer or the comprehensive mining system, and identify the equipment column, measurement point column and address column in the point table file through the trained recognition model; According to the recognition result, a point table file of a corresponding format is output; wherein the format includes a device column and a measuring point column, as well as a device column, a measuring point column and an address column.

2. According to claim 1, a point table data collection method based on Internet of Things devices is characterized in that: Determining the key features in the historical point table file to train a corresponding recognition model based on the key features specifically includes: Based on the data characteristics corresponding to the point table data, determine the key features in the historical point table file, and remove the header data in the key features to obtain the target key features; The data characteristics of the point table data include the format and regularity of the equipment column, the measuring point column and the address column; Convert the target key features into corresponding word vectors, and use the word vectors as input for model training; The model is trained using the random forest algorithm and the number of trees is set.

3. The point table data collection method based on Internet of Things devices according to claim 1 is characterized in that: Using the trained recognition model, the device column, the measurement point column and the address column in the point table file are identified, specifically including: The point table file is identified by the trained equipment column identification model and the measuring point column identification model to output the corresponding equipment column serial number and the measuring point column serial number; The point table file is identified by using the trained address column identification model to output the corresponding address column serial number.

4. The point table data collection method based on Internet of Things devices according to claim 3 is characterized in that: After the point table file is identified respectively by the trained equipment column identification model and the measurement point column identification model, the method further includes: If the output serial numbers of the equipment column identification model and the measuring point column identification model are the same, or at least one of the equipment column serial number and the measuring point column serial number is missing, then determining that the equipment measuring points in the point table file are one column; The device column and the measuring point column in the point table file are segmented by using the trained device measuring point column recognition model to output corresponding device column serial numbers and measuring point column serial numbers.

5. The point table data collection method based on Internet of Things devices according to claim 4 is characterized in that: After outputting the corresponding device column number and measurement point column number, the method further includes: Invoke a third-party translation tool to encode the equipment column number and the measuring point column number respectively to obtain equipment names and equipment codes and measuring point names and measuring point codes; Aggregating the device name, the device code, the measuring point name and the measuring point code according to the device column, and comparing the aggregated device template with the measuring point column; If the aggregated device template is consistent with the measuring point column, the devices under the same device template are named in a preset naming manner.

6. The point table data collection method based on Internet of Things devices according to claim 5 is characterized in that: If the aggregated device template is consistent with the measuring point sequence, after naming the devices under the same device template in a preset naming manner, the method further includes: Comparing the aggregated device template with existing templates of the Internet of Things platform to determine a plurality of similarities between the device template and each existing template in the Internet of Things platform; In the case that there is a similarity exceeding a preset similarity threshold among the multiple similarities, adopting the device template and supplementing the measurement points of the device template; Generate a batch import file for devices and register the devices.

7. The point table data collection method based on Internet of Things devices according to claim 6 is characterized in that: After comparing the aggregated device template with existing templates of the Internet of Things platform to determine a plurality of similarities between the device template and each existing template in the Internet of Things platform, the method further includes: If none of the multiple similarities exceeds a preset similarity threshold, generating a device template and an import file corresponding to the device template; Call the device template and device import interface in the Internet of Things platform, and register the device template and device in the Internet of Things platform.

8. The point table data collection method based on Internet of Things devices according to claim 3 is characterized in that: According to the recognition results, the point table file of the corresponding format is output, including: According to the recognition results, output the point table file in the format of device column, measurement point column and address column, and generate the corresponding edge gateway import point table; Call the corresponding interface in the IoT platform to import the corresponding edge gateway import point table and send the standard format data of the IoT platform.

9. A point meter data collection device based on an Internet of Things device, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; Wherein, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a point table data collection method based on an Internet of Things device as described in any one of claims 1-8.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: When the computer executable instructions are executed, a point table data collection method based on an Internet of Things device as described in any one of claims 1 to 8 is implemented.

Images