Processing method for industrial internet identification analysis data

Abstract

The invention discloses a processing method for industrial internet identification analysis data, and the method specifically comprises the following steps: 1, carrying out the data processing near a device or a sensor, reducing the delay and bandwidth consumption, analyzing the data in real time, generating feedback, achieving the real-time decision through edge calculation, reducing the dependence on a cloud end, and improving the response speed; 2, dynamically adjusting a data stream processing strategy according to a real-time analysis result, preferentially processing important data, reducing unnecessary data processing burden, processing the data by adopting an event-driven mode, and triggering corresponding processing logic based on a specific event; the data transmission delay is reduced, the response time is shortened, the real-time processing capability is improved, unnecessary calculation is reduced, and the resource utilization rate is improved; the data security is enhanced by adopting a block chain technology, and the non-tampering and traceability of the data are ensured; the decision quality is improved through self-adaptive data stream processing, and the strategy is dynamically adjusted through real-time data.

Description

Technical Field

[0001] This invention belongs to the field of Internet data processing technology, specifically relating to a method for processing industrial Internet identifier resolution data. Background Technology

[0002] The Industrial Internet Identifier Resolution System has been increasingly widely used, with a large amount of related data being collected and stored in real time. Industrial Internet data covers a wide range of information, including user behavior, network infrastructure resources, mobile network development, Internet of Things development, user growth of Industrial Internet applications, and various types of user data. Industrial Internet data is also used for various analyses and predictions, such as descriptive analysis, diagnostic analysis, and predictive analysis. In-depth analysis and utilization of this Industrial Internet Identifier Resolution data can help improve production processes, increase production efficiency, reduce production costs, and enhance product added value.

[0003] The current processing method has the following shortcomings:

[0004] Traditional data processing methods may lead to delays in data transmission and processing, affecting real-time decision-making capabilities; resource waste: the data processing flow may not be optimized, resulting in a waste of computing and storage resources;

[0005] The lack of robust security mechanisms makes data vulnerable to cyberattacks and tampering; privacy breaches: centralized storage of sensitive data may lead to privacy breaches.

[0006] Lack of data sharing between different systems and departments leads to decisions based on incomplete information; slow response: unable to quickly adapt to market changes and user needs, affecting business flexibility;

[0007] The inability to effectively integrate multiple types of data limits opportunities for innovation and improvement; low levels of collaboration: the lack of effective cooperation between different fields limits the possibility of cross-domain innovation;

[0008] Poor data management can lead to rising storage costs; inadequate resource allocation can result in wasted resources and improper resource allocation due to a lack of intelligent decision-making.

[0009] Traditional architectures may not be flexible enough to quickly respond to changes and expand new functions; integration difficulties: integrating new technologies and systems may face challenges and affect overall system performance;

[0010] Traditional methods may not be able to perform in-depth data analysis, limiting the acquisition of insights; poor real-time performance: lack of real-time data analysis capabilities affects rapid decision-making. Summary of the Invention

[0011] The purpose of this invention is to provide a method for processing industrial internet identifier resolution data, in order to solve the problems of low efficiency, high cost, low security and lack of innovation that may result from traditional industrial internet identifier resolution data processing methods mentioned in the background art.

[0012] To achieve the above objectives, the present invention provides the following technical solution: a method for processing industrial internet identifier resolution data, specifically including the following steps:

[0013] Step 1: Perform data processing near the device or sensor to reduce latency and bandwidth consumption, analyze data in real time and generate feedback, and make real-time decisions through edge computing to reduce dependence on the cloud and improve response speed;

[0014] Step 2: Dynamically adjust the data stream processing strategy based on real-time analysis results, prioritize the processing of important data, reduce unnecessary data processing burden, and use an event-driven approach to process data, triggering corresponding processing logic based on specific events;

[0015] Step 3: Fuse data from different sensors to improve the depth and accuracy of the analysis, and use deep learning models to process multimodal data and extract more complex features;

[0016] Step 4: Create a digital twin of the device or system, update its status with real-time data, perform simulation and predictive analysis, simulate data processing flow under different operating scenarios, and optimize the decision support system;

[0017] Step 5: Process user feedback data using sentiment analysis technology to understand user satisfaction with the device or service, and optimize the data processing flow accordingly.

[0018] Step Six: Based on data usage frequency and importance, automatically migrate data to the storage layer to optimize storage costs, and perform version management on the data to track data changes and evolution for auditing and backtracking purposes;

[0019] Step 7: Establish a cross-industry data sharing platform to promote data collaboration and innovation across different fields, build data alliances with other enterprises or institutions, and jointly develop data processing and analysis capabilities.

[0020] As a preferred technical solution in this invention, in step two, blockchain technology is used to ensure the immutability and traceability of data, enhance the credibility of data, and automatically execute data processing and analysis tasks through smart contracts to improve efficiency and transparency.

[0021] As a preferred technical solution in this invention, the method for fusing data from different sensors in step three is as follows:

[0022] S1. Process and analyze the collected data;

[0023] S2. Data fusion: Based on the reliability and accuracy of the sensors, the data is weighted and averaged, and then multiple decision-making algorithms are used to combine the results of different sensors. Machine learning or deep learning models are used to combine multi-sensor data for prediction or classification.

[0024] S3. Integrate the data fusion module with other systems to ensure data flow.

[0025] As a preferred technical solution of the present invention, in step S1, the data processing and analysis includes data noise removal, data cleaning, time synchronization, standardization transformation and feature extraction.

[0026] As a preferred technical solution of the present invention, the steps of processing user feedback data using sentiment analysis technology in step five are as follows:

[0027] a. Obtain feedback data: Collect user feedback text from different channels and store the collected feedback data in a database or data warehouse;

[0028] b. Data preprocessing;

[0029] c. Select the appropriate sentiment analysis model;

[0030] d. Sentiment Score: Each piece of feedback is scored with a sentiment score, usually a numerical value representing the intensity of the sentiment, or a category label, to determine the sentiment polarity of the text and identify the user's sentiment inclination.

[0031] e. Results analysis: Summarize the sentiment analysis results, calculate the proportions of positive, negative, and neutral feedback, analyze sentiment change trends, and identify potential problems or areas for improvement in user feedback.

[0032] As a preferred technical solution of the present invention, the data preprocessing step in step b is as follows:

[0033] Text cleaning: Remove irrelevant information, including HTML tags, special characters, and punctuation marks;

[0034] Word segmentation: breaking down text into words or phrases to facilitate subsequent analysis;

[0035] Remove stop words: Remove common, meaningless words.

[0036] Stem extraction or word form reduction: reducing words to their basic form to reduce vocabulary size.

[0037] As a preferred technical solution of the present invention, in step c, the sentiment analysis module includes the following:

[0038] Dictionary-based model: Using a sentiment dictionary, sentiment is assessed by counting the number of positive and negative words in the text;

[0039] Machine learning method model: Train a classification model and use a labeled dataset to perform sentiment classification;

[0040] Deep learning method model: Using deep learning models, trained on a large amount of data, to capture complex emotional expressions.

[0041] Compared with the prior art, the beneficial effects of the present invention are:

[0042] 1. Reduce data transmission latency, speed up response time, improve real-time processing capabilities, and at the same time reduce unnecessary calculations and improve resource utilization;

[0043] 2. Employ blockchain technology to enhance data security and ensure the immutability and traceability of data;

[0044] 3. Improve decision-making quality through adaptive data stream processing, dynamically adjust strategies based on real-time data, and make decisions more targeted and effective;

[0045] 4. By integrating different types of data, discover potential business opportunities and areas for improvement; cross-domain data collaboration: promote knowledge and data sharing between different fields, and stimulate new cooperation and innovation;

[0046] 5. Reduce costs and intelligent data archiving: Optimize storage strategies, reduce storage costs, improve data management efficiency, and at the same time adopt edge computing to reduce dependence on cloud computing resources, thereby reducing cloud service costs;

[0047] 6. Through real-time updates and simulations, the system can quickly adapt to changes, improve its flexibility and scalability, and enable it to respond quickly to different events, facilitating the expansion and integration of new functions.

[0048] 7. Improve the depth and accuracy of data analysis through data analysis and feature extraction, and obtain the sentiment tendencies of user feedback through sentiment analysis to help optimize products and services;

[0049] 8. By sharing data and resources, we can promote collaboration and knowledge sharing among teams and improve overall work efficiency. Attached Figure Description

[0050] Figure 1 This is a schematic diagram of the steps of the present invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] Please see Figure 1 This invention provides a technical solution: a method for processing industrial internet identifier resolution data, specifically including the following steps:

[0053] Step 1: Perform data processing near the device or sensor to reduce latency and bandwidth consumption, analyze data in real time and generate feedback, and make real-time decisions through edge computing to reduce dependence on the cloud and improve response speed;

[0054] Step 2: Dynamically adjust the data stream processing strategy based on real-time analysis results, prioritize the processing of important data, reduce unnecessary data processing burden, and use an event-driven approach to process data, triggering corresponding processing logic based on specific events;

[0055] Step 3: Fuse data from different sensors to improve the depth and accuracy of the analysis, and use deep learning models to process multimodal data and extract more complex features;

[0056] Step 4: Create a digital twin of the device or system, update its status with real-time data, perform simulation and predictive analysis, simulate data processing flow under different operating scenarios, and optimize the decision support system;

[0057] Step 5: Process user feedback data using sentiment analysis technology to understand user satisfaction with the device or service, and optimize the data processing flow accordingly.

[0058] Step Six: Based on data usage frequency and importance, automatically migrate data to the storage layer to optimize storage costs, and perform version management on the data to track data changes and evolution for auditing and backtracking purposes;

[0059] Step 7: Establish a cross-industry data sharing platform to promote data collaboration and innovation across different fields, build data alliances with other enterprises or institutions, and jointly develop data processing and analysis capabilities.

[0060] In this embodiment, in step two, blockchain technology is used to ensure the immutability and traceability of data, enhance the credibility of data, and automatically execute data processing and analysis tasks through smart contracts to improve efficiency and transparency.

[0061] In this embodiment, the method for fusing data from different sensors in step three is as follows:

[0062] S1. Process and analyze the collected data;

[0063] S2. Data fusion. Based on the reliability and accuracy of the sensors, conduct weighted averaging on the data, then use various decision algorithms to synthesize the results of different sensors, and utilize machine learning or deep learning models to combine multi-sensor data for prediction or classification;

[0064] S3. Integrate the data fusion module with other systems to ensure data circulation.

[0065] In this embodiment, in S1, the processing and analysis of data include denoising the data, data cleaning, time synchronization, standardization conversion, and feature extraction.

[0066] In this embodiment, in step five, the steps of processing user feedback data by sentiment analysis technology are as follows:

[0067] a. Obtain feedback data: Collect user feedback texts from different channels (such as social media, customer reviews, questionnaires, etc.), and store the collected feedback data in a database or data warehouse;

[0068] b. Data preprocessing;

[0069] c. Select the corresponding sentiment analysis model;

[0070] d. Sentiment scoring: Conduct sentiment scoring on each piece of feedback. Usually, it is a numerical value representing the sentiment intensity, or a classification label (such as positive, negative, neutral), to judge the sentiment polarity of the text and determine the user's sentiment tendency.

[0071] e. Result analysis: Summarize the sentiment analysis results, calculate the proportions of positive, negative, and neutral feedback, as well as analyze the sentiment change trend to identify potential problems or improvement points in user feedback.

[0072] In this embodiment, in step b, the data preprocessing steps are as follows:

[0073] Text cleaning: Remove irrelevant information, including HTML tags, special characters, and punctuation marks;

[0074] Word segmentation: Split the text into words or phrases for subsequent analysis;

[0075] Stop word removal: Remove common meaningless words (such as "de", "shi", "zai", etc.).

[0076] Stem extraction or lemmatization: Restore the words to their basic forms to reduce the vocabulary.

[0077] In this embodiment, in step c, the sentiment analysis modules include the following:

[0078] Dictionary-based model: Using sentiment dictionaries (such as SentiWordNet, AFINN, etc.), sentiment is assessed by counting the number of positive and negative words in the text;

[0079] Machine learning methods and models: Train a classification model (such as support vector machine, random forest, etc.) and use a labeled dataset to classify sentiment (positive, negative, neutral);

[0080] Deep learning method models: Using deep learning models (such as LSTM, BERT, etc.) to train on a large amount of data to capture complex emotional expressions.

[0081] Although embodiments of the invention have been shown and described (see the detailed description above), it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for processing industrial internet identifier resolution data, characterized in that: Specifically, the steps include the following: Step 1: Perform data processing near the device or sensor to reduce latency and bandwidth consumption, analyze data in real time and generate feedback, and make real-time decisions through edge computing to reduce dependence on the cloud and improve response speed; Step 2: Dynamically adjust the data stream processing strategy based on real-time analysis results, prioritize the processing of important data, reduce unnecessary data processing burden, and use an event-driven approach to process data, triggering corresponding processing logic based on specific events; Step 3: Fuse data from different sensors to improve the depth and accuracy of the analysis, and use deep learning models to process multimodal data and extract more complex features; Step 4: Create a digital twin of the device or system, update its status with real-time data, perform simulation and predictive analysis, simulate data processing flow under different operating scenarios, and optimize the decision support system; Step 5: Process user feedback data using sentiment analysis technology to understand user satisfaction with the device or service, and optimize the data processing flow accordingly. Step Six: Based on data usage frequency and importance, automatically migrate data to the storage layer to optimize storage costs, and perform version management on the data to track data changes and evolution for auditing and backtracking purposes; Step 7: Establish a cross-industry data sharing platform to promote data collaboration and innovation across different fields, build data alliances with other enterprises or institutions, and jointly develop data processing and analysis capabilities.

2. The method for processing industrial internet identifier resolution data according to claim 1, characterized in that: In step two, blockchain technology is used to ensure the immutability and traceability of data, enhance data credibility, and automatically execute data processing and analysis tasks through smart contracts to improve efficiency and transparency.

3. The method for processing industrial internet identifier resolution data according to claim 1, characterized in that: In step three, the method for fusing data from different sensors is as follows: S1. Process and analyze the collected data; S2. Data fusion: Based on the reliability and accuracy of the sensors, the data is weighted and averaged, and then multiple decision-making algorithms are used to combine the results of different sensors. Machine learning or deep learning models are used to combine multi-sensor data for prediction or classification. S3. Integrate the data fusion module with other systems to ensure data flow.

4. The method for processing industrial internet identifier resolution data according to claim 3, characterized in that: In S1, the data processing and analysis includes noise removal, data cleaning, time synchronization, standardization transformation, and feature extraction.

5. The method for processing industrial internet identifier resolution data according to claim 1, characterized in that: In step five, the steps for sentiment analysis technology to process user feedback data are as follows: a. Obtain feedback data: Collect user feedback text from different channels and store the collected feedback data in a database or data warehouse; b. Data preprocessing; c. Select the corresponding sentiment analysis model; d. Sentiment Score: Each piece of feedback is scored with a sentiment score, usually a numerical value representing the intensity of the sentiment, or a category label, to determine the sentiment polarity of the text and identify the user's sentiment inclination. e. Results analysis: Summarize the sentiment analysis results, calculate the proportions of positive, negative, and neutral feedback, analyze sentiment change trends, and identify potential problems or areas for improvement in user feedback.

6. The method for processing industrial internet identifier resolution data according to claim 5, characterized in that: In step b, the data preprocessing steps are as follows: Text cleaning: Remove irrelevant information, including HTML tags, special characters, and punctuation marks; Word segmentation: breaking down text into words or phrases to facilitate subsequent analysis; Stop word removal: Remove common meaningless words; Stem extraction or word form reduction: reducing words to their basic form to reduce vocabulary size.

7. The method for processing industrial internet identifier resolution data according to claim 5, characterized in that: In step c, the sentiment analysis module includes the following: Dictionary-based model: Using a sentiment dictionary, sentiment is assessed by counting the number of positive and negative words in the text; Machine learning method model: Train a classification model and use a labeled dataset to perform sentiment classification; Deep learning method model: Using deep learning models, trained on a large amount of data, to capture complex emotional expressions.

Images