Data acquisition method based on Internet of Things

Abstract

The invention provides a data acquisition method based on the Internet of Things, and relates to the technical field of the Internet of Things, and the method comprises the steps: collecting the data of the Internet of Things; based on the Internet of Things data identification large model, performing first processing on the Internet of Things data to obtain a first processing result; wherein the first processing at least comprises data standardization and intelligent labeling; storing the first processing result; performing second processing on the first processing result based on an Internet of Things data identification large model to obtain a second processing result; wherein the second processing at least comprises data intelligent desensitization, reinforcement and recognizable processing; and performing data use analysis and exchange on the second processing result. According to the method, the data is automatically processed by using the Internet of Things data identification large model, the meaning and state of the data are effectively identified, the efficiency and accuracy of data acquisition, labeling, analysis and processing are improved, manual intervention is reduced, the labor cost is reduced, labeling errors and omission are reduced, and the automation and intelligence level of data processing is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of the Internet of Things, and particularly relates to a data acquisition method based on the Internet of Things. Background Art

[0002] At present, the Internet of Things technology can connect various sensors, devices, and machines to the network, and collect, transmit, and store a large amount of operation data in real time. With the rapid development of industrial Internet technology, more and more factories and production lines are starting to use the Internet of Things technology to achieve data acquisition.

[0003] However, in the traditional data acquisition process, there are the following problems:

[0004] 1. The amount of data is huge, the workload of manual analysis and annotation is large, and the efficiency is low.

[0005] 2. The data annotation process lacks automated means, and it is easy to have annotation errors or omissions.

[0006] 3. It is unable to effectively identify the meaning and status of data, resulting in insufficient accuracy in subsequent data analysis and decision-making.

[0007] In order to solve the above problems, the present invention proposes a data acquisition method based on the Internet of Things. Summary of the Invention

[0008] One of the purposes of the present invention is to provide a data acquisition method based on the Internet of Things, which uses an Internet of Things data recognition large model to automatically process data, effectively identifies the meaning and status of data, improves the efficiency and accuracy of data acquisition, annotation, analysis, and processing, reduces manual intervention, reduces labor costs, reduces annotation errors and omissions, effectively solves the problems of low efficiency and low accuracy in traditional data acquisition, and improves the automation and intelligence level of data processing.

[0009] A data acquisition method based on the Internet of Things provided by an embodiment of the present invention includes:

[0010] Collect Internet of Things data;

[0011] Based on the Internet of Things data recognition large model, perform a first processing on the Internet of Things data to obtain a first processing result; wherein, the first processing at least includes: data standardization, intelligent annotation;

[0012] Store the first processing result;

[0013] Based on the Internet of Things data recognition large model, perform a second processing on the first processing result to obtain a second processing result; wherein, the second processing at least includes: data intelligent desensitization, reinforcement, recognizable processing;

[0014] Perform data usage analysis and exchange on the second processing result.

[0015] Optionally, the collecting of Internet of Things data includes:

[0016] Collecting Internet of Things data of multiple devices through a data collection device;

[0017] Wherein, the multiple devices at least include: sensors, device monitors, and intelligent meters;

[0018] The Internet of Things data at least includes: temperature, humidity, pressure, current, rotation speed, device status, and operation time.

[0019] Optionally, the steps of data standardization at least include: removing noise, filling missing values, and standardizing the data format.

[0020] Optionally, the steps of intelligent annotation at least include: attaching corresponding data type labels to each data point; attaching corresponding status labels according to the interval to which the data value belongs or the judgment result; attaching collection timestamp labels to each data point.

[0021] Optionally, the storing of the first processing result includes:

[0022] Storing the first processing result in a structured database.

[0023] Optionally, the steps of data intelligent desensitization at least include: converting or replacing sensitive data.

[0024] Optionally, the steps of strengthening at least include: enhancing the quality of the data.

[0025] Optionally, the steps of recognizable processing at least include: identifying the type of data; judging whether the data is within the standard range; analyzing whether the data exceeds the normal working range of the device to identify risks.

[0026] Optionally, the data usage analysis and exchange of the second processing result include:

[0027] Based on the second processing result, supporting the factory for multi-dimensional real-time analysis and decision-making support such as factory equipment status, production efficiency, and energy consumption.

[0028] Other features and advantages of the present invention will be described in the subsequent specification, and part of them will be obvious from the specification, or understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the written specification and the drawings.

[0029] The technical solutions of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0030] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention. In the accompanying drawings:

[0031] Figure 1 is a schematic flowchart of a data acquisition method based on the Internet of Things in an embodiment of the present invention;

[0032] Figure 2 is another schematic flowchart of a data acquisition method based on the Internet of Things in an embodiment of the present invention. Detailed Embodiments

[0033] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to explain and illustrate the present invention and are not used to limit the present invention.

[0034] An embodiment of the present invention provides a data acquisition method based on the Internet of Things, as Figure 1 shown, including:

[0035] S1. Collect Internet of Things data;

[0036] S2. Based on the Internet of Things data recognition large model, perform a first processing on the Internet of Things data to obtain a first processing result; wherein, the first processing at least includes: data standardization, intelligent annotation;

[0037] S3. Store the first processing result;

[0038] S4. Based on the Internet of Things data recognition large model, perform a second processing on the first processing result to obtain a second processing result; wherein, the second processing at least includes: data intelligent desensitization, strengthening, recognizable processing;

[0039] S5. Perform data usage analysis and exchange on the second processing result.

[0040] The collection of the Internet of Things data includes:

[0041] Collect the Internet of Things data of multiple devices through a data collection device;

[0042] wherein, the multiple devices at least include: sensors, device monitors, and intelligent meters;

[0043] The Internet of Things data at least includes: temperature, humidity, pressure, current, rotational speed, device status, running time.

[0044] The steps of the data standardization at least include: removing noise, filling missing values, and standardizing the data format.

[0045] The steps of the intelligent annotation at least include: attaching corresponding data type labels to each data point; attaching corresponding status labels according to the interval to which the data value belongs or the judgment result; attaching the acquisition timestamp label to each data point.

[0046] The steps of the intelligent data desensitization at least include: converting or replacing sensitive data.

[0047] The steps of the strengthening at least include: enhancing the data quality.

[0048] The steps of the recognizable processing at least include: identifying the type of data; judging whether the data is within the standard range; analyzing whether the data exceeds the normal working range of the device to identify risks.

[0049] The working principle and beneficial effects of the above technical solutions are as follows:

[0050] As Figure 2 shown, the Internet of Things data is collected from multiple devices through a data collection device. These devices can include various sensors, device monitors, and intelligent meters, which are used to monitor the device status and environmental parameters and collect data in real time. Among the collected Internet of Things data, temperature, humidity, and pressure can be used for environmental monitoring to help judge whether the device is operating in the optimal working environment, and current, rotation speed, device status, and running time reflect the operating status of the device itself and can help evaluate the performance and working cycle of the device.

[0051] The large model for Internet of Things data recognition is a model obtained by training through machine learning algorithms using a large number of data standardization rules (data standardization rules are used to convert the original data into a unified standard format to ensure that all input data is consistent in terms of numerical range, unit, etc.), labeled test Internet of Things data (collect historical Internet of Things data in advance as test Internet of Things data and hand it over to data experts for annotation to obtain labeled test Internet of Things data), data annotation rules (annotating data types, data reflecting device status, data acquisition time, etc.), data desensitization rules (data desensitization rules ensure that the privacy data of users or devices will not be leaked by removing or encrypting sensitive information, for example: hashing rules), data strengthening rules (data strengthening rules aim to improve the generalization ability of the model by enhancing data quality and avoid overfitting or inefficient learning caused by data quality problems, for example: data cleaning, outlier detection and elimination), and data recognizable processing rules (identifying data types, data intervals, etc.) as training samples. Thus, the large model for Internet of Things data recognition can autonomously and automatically complete the steps of the above first processing and second processing.

[0052] When removing noise, irrelevant noise can be removed through filtering techniques (such as mean filtering and median filtering) to ensure the accuracy of the data. When filling in missing values, interpolation methods, regression methods, etc. can be used to fill in the missing data to ensure the integrity of the data. When standardizing the data format, through unified data standards and format normalization processing, it is ensured that the data can be uniformly used in subsequent steps.

[0053] When labeling data type tags, according to the data source, label the type of each data point (for example, temperature, humidity, equipment status, etc.). When labeling status tags, according to whether the data value is within a specific range, assign a status tag to each data point. For example, when the temperature exceeds the set threshold, assign the "high temperature" tag. When labeling timestamp tags, all data points need to be marked with the acquisition timestamp to ensure the data has temporal order and facilitate maintaining the timeliness of the data during subsequent analysis.

[0054] When performing intelligent data desensitization, it can be processed through encryption, replacement, or anonymization to avoid privacy leakage. For example, the unique identifier of the device can be replaced with a hash value or encrypted data to protect the device identity from being directly exposed. When strengthening, data cleaning and other technologies can be adopted to ensure that the final data has high reliability. The improvement of data quality can ensure that during subsequent analysis, the analysis results are more accurate and reduce misjudgments. During recognizable processing, automatically identify the type of each piece of data (such as device status data, environmental monitoring data, etc.). According to the standard range, judge whether the data meets the prediction. If the data exceeds the standard range, it may indicate that there is an abnormality or fault in the device. Analyze whether the data exceeds the normal working range of the device, and judge potential risks through pattern recognition of the data. For example, abnormal fluctuations in current, rotational speed, etc. may indicate the risk of device failure.

[0055] The present invention uses an Internet of Things data recognition large model to automatically process data, effectively identify the meaning and status of the data, improve the efficiency and accuracy of data collection, annotation, analysis, and processing, reduce manual intervention, lower labor costs, reduce annotation errors and omissions, effectively solve problems such as low efficiency and low accuracy in traditional data collection, and improve the automation and intelligence level of data processing.

[0056] In one embodiment, storing the first processing result includes:

[0057] Store the first processing result in a structured database.

[0058] Store the first processing result (data that has been standardized and annotated) in a structured database. The structured database uses a relational database (such as MySQL, PostgreSQL) or a NoSQL database (such as MongoDB) to store this initially processed IoT data. Relational databases are suitable for handling structured data and can efficiently query and update data. Each data point is stored as a record based on information such as its data type, status label, timestamp, etc. The structured database can quickly query, index, and update data to ensure data persistence and accessibility.

[0059] In one embodiment, the data usage analysis and exchange of the second processing result includes:

[0060] Based on the second processing result, support the factory in performing real-time analysis and decision-making support in multiple dimensions such as factory equipment status, production efficiency, and energy consumption.

[0061] Through the second processing result, perform data analysis and exchange to support the decision-making process of the factory or other business systems. For example, using the second processing result, support the factory in performing the following multi-dimensional analysis:

[0062] Equipment status analysis: Real-time monitor the operating status of equipment, such as temperature, rotation speed, current, etc., judge the health status of the equipment, and perform fault prediction or warning.

[0063] Production efficiency analysis: Optimize the production process and improve production efficiency by analyzing data such as equipment running time and production cycle.

[0064] Energy consumption analysis: Based on the power consumption data of the equipment, help the enterprise monitor energy usage, optimize the energy management strategy, and reduce operating costs.

[0065] For another example, use the second processing result for the following data exchange:

[0066] Exchange the analysis results with other systems or platforms, such as sharing data with enterprise management systems, cloud platforms, decision support systems, etc.

[0067] In a specific Internet of Things (IoT) data collection scenario (e.g., a factory), problems such as incomplete data collection and insufficient data collection depth often occur due to the large area. Therefore, more comprehensive and in-depth data collection is required. To replace manual labor, a mobile data collection device (e.g., a drone equipped with a camera, an RFID card reader, a Bluetooth reader, etc.) can be used to perform mobile supplementary data collection. Before this, to ensure the proper conduct of mobile supplementary data collection and to ensure that the corresponding data can be collected as soon as possible (to ensure that the corresponding status of the device can be known as soon as possible), managers need to arrange how to perform mobile supplementary data collection at the fastest speed. However, the area of the IoT data collection scenario is very large, and the task volume for managers to make arrangements is extremely large, which cannot meet this requirement and may lead to problems such as incomplete arrangements and untimely arrangements. Based on this, in one embodiment, the data collection method based on the IoT further includes:

[0068] Generate a data interaction graph based on the second processing result;

[0069] Based on the data interaction graph, assist the user group in making decisions on mobile supplementary collection requirements;

[0070] Based on the mobile supplementary collection requirements, build a control assistance network in the mobile supplementary collection control model;

[0071] Based on the control assistance network, assist the user group in making decisions on mobile supplementary collection strategies in the mobile supplementary collection control model;

[0072] Execute the mobile supplementary collection strategy to perform mobile supplementary collection of new IoT data.

[0073] The user group includes multiple managers; the mobile supplementary collection requirement is the preliminary requirement for the user group to make decisions on mobile supplementary data collection for the IoT data collection scenario, and the data interaction graph can assist the user in making decisions on this requirement. The mobile supplementary collection model is a three-dimensional simulation model of the IoT data collection scenario, the mobile supplementary collection strategy is the final strategy that the user group further decides to execute for mobile supplementary data collection for the IoT data collection scenario, and the control assistance network can assist the user in making decisions on this strategy. Finally, execute the mobile supplementary collection strategy to perform mobile supplementary collection of new IoT data.

[0074] By generating a data interaction graph, assisting the user group in making decisions on mobile supplementary collection requirements first, building a control assistance network for further assisting the user group based on it, and assisting the user group in making decisions on mobile supplementary collection strategies in the mobile supplementary collection control model based on it, the efficiency of managers in arranging how to perform mobile supplementary data collection is greatly improved, making it possible to meet the requirement that managers need to arrange how to perform mobile supplementary data collection at the fastest speed.

[0075] In one embodiment, generating a data interaction graph based on the second processing result includes:

[0076] Performing clustering processing on the second processing result to obtain a plurality of first clustering clusters;

[0077] Based on the importance analysis library, determining the importance of each first clustering cluster;

[0078] Sorting the first clustering clusters from largest to smallest according to importance to obtain a first clustering cluster sequence;

[0079] Supplementing adaptive content to every i-th first clustering cluster in the first clustering cluster sequence to obtain a second clustering cluster sequence; where K≤i≤N, and the sum of the importance of the first K - 1 first clustering clusters in the first clustering cluster sequence is closest to the importance sum threshold;

[0080] Dividing the second clustering cluster sequence into multiple local sequences; where there is a standard association relationship between the adaptive content supplemented in any two second clustering clusters in the same local sequence;

[0081] Based on the display configuration rules, performing display configuration on the template graph to obtain a data interaction graph; where the display configuration rules include: the content in the j-th graph layer of the template graph displays the content in the clusters of all the second clustering clusters in the j-th local sequence of the second clustering cluster sequence;

[0082] Among them, the determination steps of the adaptive content are as follows:

[0083] Taking the clustering category of the i-th first clustering cluster as the association target;

[0084] Taking the importance of the i-th first clustering cluster as the target threshold;

[0085] Determining a third clustering cluster from the first clustering cluster sequence; where there is an association between the clustering category of the third clustering cluster and the association target, and the difference between the importance of the third clustering cluster and the target threshold does not exceed the first difference threshold;

[0086] Performing feature extraction on the i-th first clustering cluster and the third clustering cluster to obtain a feature set;

[0087] Based on the feature set, generating an effective content selection rule;

[0088] Based on the effective content selection rule, selecting effective content from the multimodal information of the user group;

[0089] Based on the effective content, determining the adaptive content.

[0090] When clustering is performed on the second processing result, clustering is performed according to multiple clustering categories to obtain multiple first cluster clusters, wherein the first cluster clusters contain data of the same clustering category in the second processing result, i.e., the content in the cluster; the cluster categories include at least: the data belongs to the same device, the device to which the data belongs is located in the same device area, the environmental conditions of the device to which the data belongs are the same, the data generation time belongs to the same time period, etc.

[0091] The importance analysis library contains the importance corresponding to different first clusters. The importance represents the importance of the content in the cluster in the first cluster that the user group needs to view first. For example, the content in the cluster belongs to the same device, which is convenient for the user group to comprehensively analyze the situation of the device. The corresponding importance is 8; the importance corresponding to different first clusters can also be set in advance by technical personnel.

[0092] The first clusters are sorted from large to small according to the importance to form a first cluster sequence, so that the first cluster to which the content in the cluster that the user group views first is ranked higher. The importance and threshold can be set to 30, and the sum of the importance of the first K-1 first clusters in the first cluster sequence is constrained to be closest to the importance and threshold, so that the value of K can be unique, and the sum of the importance of the first K-1 first clusters is closest to the importance and threshold, indicating that the user group has basically learned important information by displaying the content in each cluster of the first K-1 first clusters. Starting from the Kth first cluster, personalized adaptive content can be added.

[0093] The standard association relationship between adaptive contents refers to the association relationship between the adaptive contents that are mutually adapted, for example: the contents of interest to a certain expert in the expert group, the contents within the management authority scope of different experts in the expert group, etc.; setting a constraint that there is a standard association relationship between the adaptive contents added to the second clusters in the same local sequence divides the second cluster sequence into multiple local sequences.

[0094] The template map is a map used as a template for generating a data interaction map. It contains sub-maps at multiple map levels. Sub-maps at different map levels can display different contents separately. The smaller the map level, the higher the priority of displaying the corresponding content. After the data interaction map is generated in this way, the user group can view the contents in the corresponding clusters from the low map level to the high map level.

[0095] When determining the adaptive content, it is necessary to consider the common suitability between the output of the current adaptive content and the adaptive content to be output shortly afterwards. Therefore, the associated target and the target threshold are determined respectively, and the third clustering cluster is determined. The association between the clustering category and the management target means that the clustering categories are similar, and the data of different clustering categories can jointly play a synergistic role in the decision-making of the mobile supplementary collection requirements of the user group, etc. The first difference threshold can be set to 5. Constraining the difference between the importance of the third clustering cluster and the target threshold not to exceed the first difference threshold can make the third clustering cluster be the first clustering cluster not far after the i-th first clustering cluster.

[0096] Extract the feature sets of the i-th first clustering cluster and the third clustering cluster. The features in this feature set at least include: the content types in their respective clusters, the data association relationships between the contents in their respective clusters. The generated effective content selection rule refers to the rule for selecting the effective content that can be used as the basis for determining the adaptive content reflected by the features in the feature set. For example: if the feature in the feature set is the situation of a certain device to be managed in the cluster content type, then the corresponding effective content selection rule is to select the historical managed situations of the user group as the effective content, and supplement it into the i-th first clustering cluster. When the user group views the cluster content at this atlas level, they can compare it with their own historical managed situations to decide whether they want to draw on and reference it to determine the mobile supplementary collection requirements.

[0097] Through the multi-level clustering and adaptive content supplementation strategy, it is possible to efficiently generate a data interaction atlas that meets the user's needs according to the clustering category and importance of the data. The data is first processed by clustering to form multiple first clustering clusters, and sorted according to the importance of the content in the clusters to ensure that the most important content is displayed first. This not only optimizes the display order of the data, but also through the supplementation of adaptive content, enables the user to obtain personalized recommendation information based on historical behavior and management requirements when viewing the data. The combination of the determination of adaptive content and clustering analysis not only improves the relevance of the information, but also enhances the interactivity of the atlas. The third clustering cluster is accurately screened out, the feature set is generated, and the effective content selection rule is generated through the feature set, so as to provide more accurate and personalized information for the user. By dividing the second clustering cluster sequence into local sequences and displaying them at different atlas levels, the system can ensure the hierarchy and orderliness of the information, facilitating the user to browse according to their needs.

[0098] The data interaction atlas not only improves the user's analysis efficiency, but also enhances the intelligence of the decision support system, enabling the user to more effectively extract information highly relevant to their needs from the vast amount of data, thereby improving the overall decision-making quality and response speed, and greatly enhancing the accuracy of their decision-making mobile supplementary collection requirements.

[0099] In one embodiment, based on the demand for mobile supplementary production, a control auxiliary network is built in the mobile supplementary production control model, including:

[0100] Perform fuzzy logic analysis on the mobile supplementary procurement demand to obtain a fuzzy logic set;

[0101] Based on fuzzy logic sets, multiple mobile supplementary mining routes are marked in the mobile supplementary mining control model;

[0102] Generate sight line preprocessing rules and route triggering rules for each mobile supplementary mining route;

[0103] Determine the control auxiliary network based on the sight preprocessing rules and route triggering rules of each mobile supplementary mining route;

[0104] The sight line preprocessing rules include:

[0105] When determining whether there are more than a threshold number of first trajectory points whose straight-line spacing with the starting position of the moving supplementary mining route does not exceed the spacing threshold continuously generated on the target trajectory to be preprocessed, a portion of the trajectory before the last first trajectory point on the target trajectory is eliminated;

[0106] The route triggering rules include:

[0107] Analyze multiple groups of one-to-one corresponding second trajectory points and generation times of the preprocessed target trajectory;

[0108] Mapping the vertical distance between the corresponding second trajectory point and the mobile supplementary mining route at each generation time and at different generation times into the distance-time curve to obtain the target curve;

[0109] Extract multiple trough values ​​and peak values ​​on the target curve;

[0110] When the differences between the trough values ​​and the peak values ​​do not exceed the second difference threshold, the mobile supplementary mining route is triggered as the basis for the mobile supplementary mining strategy decision.

[0111] The demand for mobile supplementary collection will reflect fuzzy logic. Fuzzy logic refers to the arrangement logic of mobile data supplementary collection represented by the mobile supplementary collection demand. For example, the mobile supplementary collection demand refers to collecting the on-site working screen of a certain type of equipment in a certain area. The parsed fuzzy logic is to collect the working screen of each device in turn. The mobile supplementary collection demand is parsed by fuzzy logic to form a fuzzy logic set.

[0112] When marking the mobile supplementary sampling route, determine the mutation logic of the fuzzy logic in the fuzzy logic set (the mutation logic is the arrangement logic after the user group will suddenly change from the fuzzy logic, for example: transfer to take pictures of the on-site work of the surrounding staff), determine the supplementary sampling areas corresponding to the fuzzy logic and the mutation logic in the mobile supplementary sampling control model, that is, the on-site areas where data supplementary sampling is required as indicated by each logic, and finally, connect the centers of the two on-site areas to obtain the mobile supplementary sampling route.

[0113] The sight line preprocessing rule is a rule for preprocessing the sight line trajectories generated by each user in the user group within the recent preset time, and the preset time can be 100 seconds; the route triggering rule is a rule for analyzing whether the preprocessed sight line trajectories trigger the mobile supplementary mining route. Finally, the sight line preprocessing rules and route triggering rules of each mobile supplementary mining route form a control auxiliary network.

[0114] Accordingly, the method of assisting the user group in deciding the mobile supplementary procurement strategy in the mobile supplementary procurement control model based on the control auxiliary network includes:

[0115] Display the mobile supplementary mining control model after the control auxiliary network is built to the user group;

[0116] Obtain the viewing sight track of each user in the user group within the recent preset time;

[0117] Based on the sight line preprocessing rule, the sight line trajectory is preprocessed; wherein the sight line trajectory is used as the target trajectory to be preprocessed;

[0118] Based on the route triggering rules, determine whether to trigger the mobile supplementary mining route according to the pre-processed viewing line of sight trajectory;

[0119] When triggered, the triggered mobile supplementary procurement route is simultaneously displayed to each user in the user group, so that each user group can decide on the mobile supplementary procurement route that needs to be finally adopted as the mobile supplementary procurement strategy.

[0120] The number threshold can be 3; the spacing threshold can be 5 cm; when more than the number threshold of first trajectory points whose straight-line spacing with the starting position of the moving supplementary mining route does not exceed the spacing threshold are continuously generated on the target trajectory to be preprocessed, it means that the user begins to want to trigger the moving supplementary mining route, and the part of the trajectory before the last first trajectory point on the target trajectory is eliminated.

[0121] The horizontal axis of the spacing-time curve is time, and the vertical axis is the spacing distance. The vertical spacing between the corresponding second trajectory point and the mobile supplementary mining route at each generation time and different generation times is mapped into the spacing-time curve to obtain the target curve.

[0122] The second difference threshold can be 3 cm; when the differences between each valley value and peak value pairwise do not exceed the second difference threshold, it indicates that the user definitely wants to trigger the mobile supplementary acquisition route, and the mobile supplementary acquisition route is used as the decision-making basis for the mobile supplementary acquisition strategy. In practical applications, the user can view the control assistance network. When wanting to arrange for mobile data supplementary acquisition, the eyes should try to focus on the starting position of a certain mobile supplementary acquisition route, and then look from the starting position of the mobile supplementary acquisition route to the ending position as much as possible, and the system will automatically trigger the corresponding mobile supplementary acquisition route.

[0123] Through the construction of fuzzy logic parsing and control assistance network, it provides intelligent support for the decision-making of the mobile supplementary acquisition strategy. First, through fuzzy logic parsing, the supplementary acquisition requirements of the user are accurately identified, and multiple mobile supplementary acquisition routes are marked accordingly, ensuring the precise matching of requirements and strategies. The line-of-sight preprocessing rule and route triggering rule enable the system to respond to the user's behavior in real time and automatically trigger relevant supplementary acquisition routes through the intelligent analysis of the user's viewing trajectory, greatly improving the automation level and user experience of the system. By accurately mapping the distance and time between trajectory points, the high reliability of route triggering is ensured, and at the same time, the triggering conditions are determined through valley and peak analysis, further optimizing the decision-making basis. For practical applications, the user only needs to focus on the starting position of a specific supplementary acquisition route, and the system will automatically identify and trigger the corresponding mobile supplementary acquisition route according to the user's line-of-sight trajectory, reducing the intervention of manual operations and improving work efficiency and accuracy. Overall, this system can not only effectively optimize the selection of supplementary acquisition routes, but also dynamically adjust the supplementary acquisition strategy through intelligent analysis, with high adaptability and forward-looking, providing strong technical support for the implementation of mobile supplementary acquisition.

[0124] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications.

Claims

1. A data acquisition method based on the Internet of Things, characterized in that, Including: Collecting Internet of Things (IoT) data; Based on the IoT data recognition large model, performing a first processing on the IoT data to obtain a first processing result; wherein, the first processing at least includes: data standardization, intelligent annotation; Storing the first processing result; Based on the IoT data recognition large model, performing a second processing on the first processing result to obtain a second processing result; wherein, the second processing at least includes: data intelligent desensitization, strengthening, recognizable processing; Performing data usage analysis and exchange on the second processing result.

2. The data acquisition method based on the Internet of Things according to claim 1, characterized in that The collecting of the IoT data includes: Collecting the IoT data of multiple devices through a data collection device; Wherein, the multiple devices at least include: sensors, device monitors, and intelligent meters; The IoT data at least includes: temperature, humidity, pressure, current, rotation speed, device status, operation time.

3. The data acquisition method based on the Internet of Things according to claim 1, wherein The steps of the data standardization at least include: removing noise, filling in missing values, standardizing the data format.

4. The data acquisition method based on the Internet of Things according to claim 1, characterized in that The steps of the intelligent annotation at least include: tagging each data point with a corresponding data type label; tagging with a corresponding status label according to the interval to which the data value belongs or the judgment result; tagging each data point with a collection timestamp label.

5. The data acquisition method based on the Internet of Things according to claim 1, characterized in that The storing of the first processing result includes: Storing the first processing result in a structured database.

6. The data acquisition method based on the Internet of Things according to claim 1, characterized in that The steps of the data intelligent desensitization at least include: converting or replacing sensitive data.

7. The data acquisition method based on the Internet of Things according to claim 1, wherein The steps of the strengthening at least include: enhancing the quality of the data.

8. The data acquisition method based on the Internet of Things according to claim 1, wherein The steps of the recognizable processing at least include: identifying the type of the data; judging whether the data is within the standard range; analyzing whether the data exceeds the normal working range of the device to identify risks.

9. The data acquisition method based on the Internet of Things according to claim 1, wherein The performing of the data usage analysis and exchange on the second processing result includes: Based on the second processing result, supporting the factory to conduct multi-dimensional real-time analysis and decision-making support on factory equipment status, production efficiency, energy consumption, etc.

10. The data acquisition method based on the Internet of Things according to claim 1, characterized in that, It also includes: Generating a data interaction graph based on the second processing result; Based on the data interaction graph, assisting the user group to make decisions on mobile supplementary collection requirements; Based on the mobile supplementary collection requirements, building a control assistance network in the mobile supplementary collection control model; Based on the control assistance network, assisting the user group to make decisions on mobile supplementary collection strategies in the mobile supplementary collection control model; Executing the mobile supplementary collection strategy to supplement and collect new IoT data in a mobile manner.

Images