Multi-source highway energy data processing system

Abstract

The invention discloses a multi-source highway energy data processing system, and relates to the field of data processing, and the system comprises a preset relation determination server, a central processor, a plurality of intelligent devices, and fog computing servers corresponding to the intelligent devices. The intelligent devices of different models are used for collecting energy data of different types; the preset relationship determination server is used for uploading an association relationship between the intelligent equipment and the fog computing server to the central processing unit; the central processing unit is used for determining a data processing program corresponding to the fog computing server according to the model of the intelligent equipment; the fog computing server corresponding to the intelligent device is used for unifying the format of the energy data collected by the intelligent device into a preset format and performing mask processing on preset sensitive words through the data processing program determined by the central processing unit to obtain processed energy data. The problems that data formats are diversified, one-by-one processing through a central processing unit is tedious, real-time performance is insufficient, and data security and privacy protection are insufficient can be solved.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a processing system for multi-source highway energy data. Background Art

[0002] With the in-depth promotion of the intelligent construction of highways, the effective processing of multi-source energy data has become the key to improving highway operation efficiency, ensuring traffic safety, and saving energy and reducing emissions.

[0003] Regarding the related technologies for processing multi-source highway data, there is currently a method for processing multi-source data of highway traffic survey stations, including: using multi-source initial data and initial acquisition data of highway traffic survey stations as the data sources of highway traffic survey stations; processing the data sources according to a set data processing model to obtain traffic data; performing data matching according to the spatio-temporal characteristics of the traffic data to obtain the traffic data included in the traffic survey statistical data indicators with different characteristics; and processing and reasoning the traffic data including each highway traffic survey statistical data indicator according to the corresponding processing and reasoning methods of each traffic survey statistical data indicator to obtain each highway traffic survey statistical data indicator.

[0004] However, the above solutions still have the following problems: (1) Diversified data formats: Since highway energy data comes from different sensors and devices, the data formats may vary greatly, and it is rather cumbersome to process them one by one through a central processor. (2) Insufficient real-time performance: For highway energy data, real-time performance is very important. However, the current data processing methods may have problems with insufficient real-time performance when processing a large amount of data, resulting in the inability to obtain processing results in a timely manner and affecting the timeliness of decision-making. (3) Insufficient data security and privacy protection: During the data processing process, the transmission and storage of sensitive data may be involved.

[0005] In summary, how to solve the problems of diversified data formats, cumbersome processing one by one through a central processor, insufficient real-time performance, and insufficient data security and privacy protection has become an urgent problem for those skilled in the art. Summary of the Invention

[0006] The purpose of this application is to provide a processing system for multi-source highway energy data to solve the problems of diversified data formats, cumbersome processing one by one through a central processor, insufficient real-time performance, and insufficient data security and privacy protection.

[0007] To achieve the above purpose, the following solutions are provided in this application.

[0008] This application provides a processing system for multi-source highway energy data. The processing system for multi-source highway energy data includes a preset relationship determination server, a central processing unit, multiple intelligent devices, and fog computing servers corresponding to each of the intelligent devices. Different types of intelligent devices among the multiple intelligent devices are used to collect different types of energy data. The preset relationship determination server is configured to, for each intelligent device, obtain all alternative servers within the preset range of the intelligent device, send test data and a test program corresponding to the test data to each alternative server, determine the alternative server that first returns a test result as the fog computing server corresponding to the intelligent device, and upload the association relationship between the intelligent device and the fog computing server to the central processing unit. The central processing unit is configured to determine a data processing program corresponding to the fog computing server according to the model of the intelligent device. The data processing program includes a format unification program and a preset sensitive word masking processing program. The fog computing server corresponding to the intelligent device is configured to obtain the energy data collected by the intelligent device, and through the data processing program corresponding to the fog computing server determined by the central processing unit, unify the format of the energy data collected by the intelligent device into a preset format and perform masking processing on preset sensitive words in the energy data collected by the intelligent device to obtain processed energy data.

[0009] Optionally, each alternative server runs the test program to obtain a test result corresponding to the test data and returns the test result to the preset relationship determination server.

[0010] Optionally, the processor level of each alternative server is greater than or equal to Intel Core i5, the operating memory is greater than or equal to 8GB, and the storage capacity is greater than or equal to 500GB.

[0011] Optionally, the central processing unit is further configured to obtain a format unification program and a preset sensitive word masking processing program corresponding to each energy data type, obtain the correspondence between the energy data type and the model of the intelligent device, and obtain the correspondence between the model of the intelligent device and the format unification program and the preset sensitive word masking processing program.

[0012] Optionally, the fog computing server corresponding to the intelligent device is further configured to store the processed energy data, and when the storage is completed, generate an energy data processing record and upload it to the central processing unit. The energy data processing record includes the energy data collection time, the energy data type, and the name of the data processing program.

[0013] Optionally, the fog computing server corresponding to the intelligent device is further configured to obtain an energy data processing requirement and upload it to the central processing unit.

[0014] Optionally, the central processing unit is further configured to determine an energy data processing record corresponding to the energy data processing requirement based on the time range and energy data type in the energy data processing requirement, obtain the processed energy data corresponding to the energy data processing requirement from the fog computing server corresponding to the energy data processing record, determine an edge computing server corresponding to the requirement keyword according to the requirement keyword corresponding to the energy data processing requirement, send the energy data processing requirement and the processed energy data corresponding to the energy data processing requirement to the edge computing server, obtain a processing result returned by the edge computing server, and send the processing result to the fog computing server that uploads the energy data processing requirement.

[0015] Optionally, the requirement keyword corresponding to the energy data processing requirement is extracted by the central processing unit from the energy data processing requirement through a preset keyword extraction algorithm.

[0016] Optionally, the edge computing server corresponding to the requirement keyword is determined by the central processing unit according to the requirement keyword corresponding to the energy data processing requirement and the corresponding relationship between the preset requirement keyword and the edge computing server.

[0017] Optionally, the energy data type includes voltage data and current data.

[0018] According to the specific embodiments provided by the present application, the present application has the following technical effects.

[0019] The present application provides a processing system for multi-source highway energy data. Through the fog computing server, the data generated by intelligent devices is sent to a server (fog computing server) that can be processed within a preset range, realizing the nearby processing of data and solving the problem of insufficient real-time performance. The central processing unit of the present application can determine the data processing program corresponding to the fog computing server according to the model of the intelligent device (the data processing program includes a format unification program and a preset sensitive word masking processing program). Then, through the data processing program in the fog computing server, the format of the energy data is unified into a preset format and the preset sensitive words in the energy data are masked to obtain the processed energy data, avoiding the problem of diverse data formats and the cumbersome process of processing different format data one by one through the central processing unit. In addition, since the sensitive words involved in different energy data types are different, the present application maps different preset sensitive word masking processing programs for different energy data types, solving the problem of insufficient data security and privacy protection. Description of the Drawings

[0020] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0021] Figure 1 The structural schematic diagram of a processing system for multi-source highway energy data provided by an embodiment of the present application. Specific embodiments

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0023] The purpose of the present application is to provide a processing system for multi-source highway energy data to solve the problems of diverse data formats, cumbersome processing one by one by the central processing unit, insufficient real-time performance, and insufficient data security and privacy protection.

[0024] To make the above objects, features, and advantages of the present application more obvious and understandable, the following will further describe the present application in detail with reference to the drawings and specific embodiments.

[0025] As Figure 1 shown, a processing system for multi-source highway energy data provided by the present application includes a preset relationship determination server 103, a central processing unit 104, multiple intelligent devices 101, and fog computing servers 102 corresponding to each intelligent device 101.

[0026] Among the multiple intelligent devices 101, intelligent devices 101 of different models are used to collect different types of energy data. Among them, the types include voltage data and current data.

[0027] The preset relationship determination server 103 is used to obtain all alternative servers within the preset range of each intelligent device 101, send test data and the corresponding test program to each alternative server, determine the alternative server that returns the test result first as the fog computing server 102 corresponding to the intelligent device 101, and upload the association relationship between the intelligent device 101 and the fog computing server 102 to the central processing unit 104. Among them, each alternative server runs the test program to obtain the test result corresponding to the test data and returns the test result to the preset relationship determination server 103. The processor level of each alternative server is greater than or equal to Intel Core i5, the running memory is greater than or equal to 8GB, and the storage capacity is greater than or equal to 500GB.

[0028] Among them, the specific steps of sending the test data and the corresponding test program to each alternative server are as follows.

[0029] 1. The preset relationship determination server 103 is used to obtain all alternative servers within the preset range of each intelligent device 101 and perform the following steps.

[0030] 2. Test data generation: Generate data samples for testing according to the type, data acquisition frequency, and processing requirements of the intelligent device 101.

[0031] 3. Test program matching: Select a suitable test program from the preset test program library according to the characteristics of the test data to ensure that the test can accurately evaluate the processing ability and response speed of the alternative server.

[0032] 4. Test task distribution: Send the test data and the test program to all alternative servers simultaneously through the network communication protocol and start the timer to record the server response time.

[0033] 5. Test execution: After receiving the test task, the alternative server immediately runs the test program, processes the test data, and generates the test result.

[0034] 6. Test result feedback: After completing the test, each alternative server returns the test result to the preset relationship determination server 103, including key parameters such as calculation delay, data throughput rate, and storage performance.

[0035] 7. Optimal server selection: The preset relationship determination server 103 compares the test results of all alternative servers, selects the server that returns the test result first and meets the minimum performance threshold requirement, and determines it as the fog computing server 102 corresponding to the intelligent device 101.

[0036] 8. Association Relationship Storage: Upload the association relationship between the intelligent device 101 and the selected fog computing server 102 to the central processing unit 104 for subsequent data processing and task allocation.

[0037] The central processing unit 104 is used to determine the data processing program corresponding to the fog computing server 102 according to the model of the intelligent device 101; the data processing program includes a format unification program and a preset sensitive word masking program. The central processing unit 104 is also used to obtain the format unification program and the preset sensitive word masking program corresponding to each energy data type, obtain the correspondence between the energy data type and the model of the intelligent device 101, and obtain the correspondence between the model of the intelligent device 101 and the format unification program and the preset sensitive word masking program. Among them, the energy data types include voltage data and current data.

[0038] Among them, the running processes of the format unification program and the preset sensitive word masking program are as follows.

[0039] 1. Data Reception and Preprocessing.

[0040] (1) Receive the data sent by the intelligent device 101.

[0041] Data Transmission Protocol: Support multiple communication protocols such as MQTT, HTTP, and WebSocket to ensure that different types of intelligent devices can upload data.

[0042] Data Format: Can be JSON, XML, binary stream, etc.

[0043] (2) Data Integrity Check.

[0044] Packet Integrity Verification: Ensure that the data is not damaged during transmission.

[0045] Timestamp Comparison: Eliminate data with abnormal timestamps to prevent timing disorders.

[0046] Redundant Data Removal: Merge or deduplicate data repeatedly uploaded by the same device at the same time.

[0047] 2. Format Unification Processing (Format Unification Program).

[0048] The data formats of different intelligent devices may be different, so standardization processing is required for subsequent analysis and storage.

[0049] (1) Parse the data format.

[0050] Parse the JSON / XML data structure and extract key information (such as time, device ID, sensor data).

[0051] Parse the binary data stream and convert it into structured data.

[0052] (2) Unit conversion and normalization, including: energy unit conversion, voltage and current standardization, and time alignment.

[0053] (3) Structured storage, including: after unifying the data format, storing it in a database or cache system for subsequent analysis.

[0054] 3. Data cleaning and anomaly detection.

[0055] (1) Data noise filtering.

[0056] Sliding window filtering: Using the moving average algorithm to smooth the data and reduce random fluctuations.

[0057] Kalman filtering: Predicting and correcting sensor data to improve data reliability.

[0058] (2) Anomaly detection.

[0059] Threshold check: Data outside the set range is marked as abnormal.

[0060] (3) Machine learning anomaly detection: Training LSTM / Isolation Forest models based on historical data to automatically detect anomaly points.

[0061] Missing value handling: Interpolating to complete missing data.

[0062] (4) Sensitive information handling (preset sensitive word masking handler).

[0063] ① Sensitive information identification.

[0064] Identifying sensitive content in the data through regular expressions or deep learning NLP models, such as the following content.

[0065] License plate number (Lu A12345 → Lu A****5).

[0066] GPS coordinates (36.12345, 117.54321 → 36.*****, 117.*****)

[0067] Personal identity information (ID card 37010219900101XXXX → ID card 3701************)

[0068] ② Sensitive information masking.

[0069] Hash encryption: Using SHA-256 / MD5 to generate hash values, such as ID123456 → e99a18c428cb38d5f260853678922e03.

[0070] Character replacement: Partial character replacement, e.g., user mobile phone number 13812345678 → user mobile phone number 138****5678.

[0071] Data desensitization storage: Only store desensitized data to prevent leakage.

[0072] 5. Feature extraction and data analysis.

[0073] (1) Statistical feature calculation.

[0074] Mean, variance, median: Calculate the basic statistics of the device operation status.

[0075] Data frequency analysis: Analyze data volatility, e.g., FFT (Fast Fourier Transform) is used for power signal analysis.

[0076] (2) Pattern recognition.

[0077] Device status classification based on K-Means (such as three categories: normal, abnormal, and faulty).

[0078] Prediction analysis based on LSTM / Transformer (such as predicting the power load in the next 24 hours).

[0079] 6. Data storage and distribution.

[0080] (1) Store data.

[0081] Real-time database (InfluxDB / TimescaleDB): Used to store time-series data, such as power grid load and energy consumption data.

[0082] Object storage (MinIO / S3): Store large-scale unstructured data, such as video streams and log files.

[0083] Cache system (Redis): Store temporary data to improve query speed.

[0084] (2) Data distribution.

[0085] Push data to edge servers (MQTT / WebSocket).

[0086] Provide API interfaces for other systems to access (RESTful API, GraphQL).

[0087] Regularly synchronize data to the central processor 104 for large-scale data analysis.

[0088] The fog computing server 102 corresponding to the intelligent device 101 is used to obtain the energy data collected by the intelligent device 101, and through the data processing program corresponding to the fog computing server 102 determined by the central processing unit 104, unify the format of the energy data collected by the intelligent device 101 into a preset format and perform mask processing on the preset sensitive words in the energy data collected by the intelligent device 101 to obtain the processed energy data. The fog computing server 102 corresponding to the intelligent device 101 is also used to store the processed energy data. After the storage is completed, an energy data processing record is generated and uploaded to the central processing unit 104; the energy data processing record includes the energy data collection time, the energy data type, and the data processing program name.

[0089] Among them, the main functions of the preset format are as follows.

[0090] 1. Ensure data compatibility: Different intelligent devices may use different data formats (such as JSON, CSV, XML, binary stream), which need to be uniformly converted for subsequent processing.

[0091] 2. Ensure data integrity: Eliminate redundant information, complete missing fields, and avoid analysis errors caused by different data formats.

[0092] 3. Improve data processing efficiency: After unifying the format, data can be stored in the database more efficiently, reducing additional parsing costs.

[0093] 4. Standard content of the preset format.

[0094] 5. The preset format usually consists of a data structure and field standards to ensure that all energy data is stored and processed according to the same rules.

[0095] (1) Data structure.

[0096] Suppose the data collected by the intelligent device 101 is information about voltage, current, power, ambient temperature, etc., and the data structure of the preset format is uniformly defined.

[0097] (2) Field standards.

[0098] Different devices may use different units or different data types. For example: the voltage data of device A is 750V, and that of device B may be 750000mV, which needs to be uniformly converted; device C may lack temperature data, and the default value needs to be completed or filled by interpolation; device D may use °F, while the system requires uniform conversion to °C.

[0099] (3) Conversion process of the preset format.

[0100] The energy data uploaded by the intelligent device 101 needs to be format-converted by the fog computing server 102. The specific steps are as follows.

[0101] ①Data reception.

[0102] Device 101 sends data to fog computing server 102 via MQTT, HTTP or WebSocket.

[0103] The fog computing server 102 parses the data to obtain the data packet in the original format.

[0104] ②Format conversion.

[0105] Field renaming: If the data field names of device 101 are different (such as volt → voltage), perform standardized renaming.

[0106] Unit conversion: If device A transmits 750000 mV, convert it to 750 V. If the temperature is 97°F, convert it to 36.1°C (formula: (F - 32) * 5 / 9).

[0107] Time standardization: Device A may use Beijing time (GMT + 8), and uniformly convert it to UTC.

[0108] ③Data verification.

[0109] Integrity check: Ensure that all fields exist, and fill in the missing values by interpolation (such as linear interpolation).

[0110] Outlier detection: Mark voltages > 750 V or < 0 V as abnormal directly; alarm when the current fluctuates too much.

[0111] ④Format conversion result.

[0112] The converted data conforms to the preset format and is uploaded to the central processor 104 for further processing.

[0113] The fog computing server 102 corresponding to the intelligent device 101 is also used to obtain the energy data processing requirements and upload them to the central processor 104.

[0114] The central processing unit 104 is also used to determine an energy data processing record corresponding to the energy data processing requirement based on the time range and energy data type in the energy data processing requirement, obtain the processed energy data corresponding to the energy data processing requirement from the fog computing server 102 corresponding to the energy data processing record, determine the edge computing server corresponding to the requirement keyword according to the requirement keyword corresponding to the energy data processing requirement, send the energy data processing requirement and the processed energy data corresponding to the energy data processing requirement to the edge computing server, obtain the processing result returned by the edge computing server, and send the processing result to the fog computing server 102 that uploads the energy data processing requirement. Among them, the requirement keyword corresponding to the energy data processing requirement is extracted by the central processing unit 104 from the energy data processing requirement through a preset keyword extraction algorithm. The edge computing server corresponding to the requirement keyword is determined by the central processing unit 104 according to the requirement keyword corresponding to the energy data processing requirement and the corresponding relationship between the preset requirement keyword and the edge computing server.

[0115] Among them, the extraction process of the preset keyword extraction algorithm is as follows.

[0116] 1. The core objectives of the preset keyword extraction algorithm.

[0117] Automatically identify the key content in the energy data processing requirement.

[0118] Efficiently match a suitable edge computing server to optimize data processing efficiency.

[0119] Improve scalability and support different types of energy data processing scenarios.

[0120] 2. The process of the keyword extraction algorithm.

[0121] (1) Input of the energy data processing requirement.

[0122] The energy data processing requirement may be input in ways such as text description, structured data, JSON format, etc.

[0123] For example, a typical energy data processing requirement may be: "It is necessary to perform anomaly detection on the voltage fluctuation of the high-voltage DC bus and perform real-time power prediction."

[0124] (2) Preprocessing.

[0125] Text cleaning: Remove noise information such as stop words (such as "of", "and") and punctuation marks.

[0126] Tokenization: Split the input text into words or phrases, e.g., ["High Voltage DC", "Bus Voltage", "Fluctuation", "Anomaly Detection", "Real-time", "Power Prediction"]; POS Tagging: Identify nouns, verbs, adjectives, etc. to improve extraction accuracy.

[0127] (3) Keyword extraction.

[0128] Use a hybrid algorithm based on TF-IDF + rule matching + semantic parsing to extract requirement keywords: TF-IDF (Term Frequency - Inverse Document Frequency).

[0129] Calculate the importance of words in energy data processing requirements and eliminate common non-critical information.

[0130] Rule-based keyword matching.

[0131] Pre-define a core technical word list for the energy field (such as "Power Prediction", "Anomaly Detection", "Energy Consumption Optimization").

[0132] If the requirement text contains these keywords, directly extract them as requirement keywords.

[0133] BERT-based semantic parsing.

[0134] Use a pre-trained language model (such as BERT) to analyze the semantics of the requirement text.

[0135] For example: Input: "High Voltage DC Bus Voltage Fluctuation Anomaly Detection"; Keywords extracted after BERT parsing may be: ["High Voltage DC", "Bus Voltage", "Anomaly Detection"]; This can improve the ability to extract keywords with multiple meanings and context dependencies.

[0136] (4) Requirement keyword output.

[0137] Through the above algorithm, extract the core requirement keywords for energy data processing requirements. For example: Input requirement: "Need to perform anomaly detection on the High Voltage DC bus voltage fluctuation and perform real-time power prediction."; Extracted requirement keywords: ["High Voltage DC", "Bus Voltage", "Anomaly Detection", "Power Prediction"].

[0138] The data upload module includes: a preset relationship determination server drive unit, which is used to obtain all alternative servers within the preset range of the intelligent device 101 through the preset relationship determination server 103; wherein, the processor level of the alternative server is greater than or equal to Intel Core i5, the operating memory is greater than or equal to 8GB, and the storage capacity is greater than or equal to 500GB; the preset relationship determination server 103 sends test data and the test program corresponding to the test data to the alternative servers; so that the alternative servers run the test program to obtain the test results corresponding to the test data, and return the test results to the preset relationship determination server 103; and then determine the alternative server that first returns the test results as the fog computing server 102; the preset relationship determination server 103 uploads the association relationship between the intelligent device 101 and the fog computing server 102 to the central processing unit 104.

[0139] The multi-source highway energy data processing system provided by this application may further include a program upload module, which is used to upload the format unified program and the preset sensitive word masking program corresponding to each energy data type to the central processing unit 104; upload the corresponding relationship between the energy data type and the specific model of the intelligent device 101 to the central processing unit 104; upload the corresponding relationship between the specific model of the intelligent device 101 and the format unified program and the preset sensitive word masking program to the central processing unit 104.

[0140] The multi-source highway energy data processing system provided by this application has the following advantages.

[0141] 1. Through the fog computing server, this application realizes sending the data generated by the intelligent device to the servers (fog computing servers) within the preset range that can process it, realizes the local processing of data, and solves the problem of insufficient real-time performance.

[0142] 2. The central processing unit of this application can determine the data processing program corresponding to the fog computing server according to the specific model of the intelligent device (the data processing program includes a format unified program and a preset sensitive word masking program), and then unify the format of the energy data into a preset format and mask the preset sensitive words in the energy data through the data processing program in the fog computing server to obtain the processed energy data, avoiding the cumbersome problem of processing different format data one by one through the central processing unit.

[0143] 3. Since the sensitive words involved in different energy data types are different, this application maps different preset sensitive word masking programs for different energy data types, solving the problem of insufficient data security and privacy protection.

[0144] In this article, specific examples are used to illustrate the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation on the present application.

Claims

1. A system for processing multi-source highway energy data, characterized in that: The processing system of multi-source highway energy data includes a preset relationship determination server, a central processor, a plurality of smart devices and a fog computing server corresponding to each of the smart devices; Different models of smart devices among the multiple smart devices are used to collect different types of energy data; The preset relationship determination server is used to obtain all candidate servers within a preset range of each smart device, send test data and a test program corresponding to the test data to each candidate server, determine the first candidate server that returns a test result as the fog computing server corresponding to the smart device, and upload the association relationship between the smart device and the fog computing server to the central processor; The central processor is used to determine the data processing program corresponding to the fog computing server according to the model of the smart device; the data processing program includes a format unification program and a preset sensitive word mask processing program; The fog computing server corresponding to the smart device is used to obtain the energy data collected by the smart device, and through the data processing program corresponding to the fog computing server determined by the central processor, unifies the format of the energy data collected by the smart device into a preset format and masks the preset sensitive words in the energy data collected by the smart device to obtain the processed energy data.

2. The processing system for multi-source highway energy data according to claim 1 is characterized in that: Each of the candidate servers runs the test program to obtain a test result corresponding to the test data, and returns the test result to the preset relationship determination server.

3. The processing system for multi-source highway energy data according to claim 1 is characterized in that: The processor level of each candidate server is greater than or equal to Intel Core i5, the running memory is greater than or equal to 8GB, and the storage capacity is greater than or equal to 500GB.

4. The processing system for multi-source highway energy data according to claim 1 is characterized in that: The central processor is also used to obtain the format unification program and preset sensitive word mask processing program corresponding to each energy data type, obtain the correspondence between the energy data type and the model of the smart device, and obtain the correspondence between the model of the smart device and the format unification program and the preset sensitive word mask processing program.

5. The processing system for multi-source highway energy data according to claim 4 is characterized in that: The fog computing server corresponding to the smart device is also used to store the processed energy data. After storage is completed, an energy data processing record is generated and uploaded to the central processor; the energy data processing record includes energy data collection time, energy data type and data processing program name.

6. The processing system for multi-source highway energy data according to claim 5 is characterized in that: The fog computing server corresponding to the smart device is also used to obtain energy data processing requirements and upload them to the central processor.

7. The processing system for multi-source highway energy data according to claim 6 is characterized in that: The central processor is also used to determine the energy data processing record corresponding to the energy data processing demand based on the time range and energy data type in the energy data processing demand, obtain the processed energy data corresponding to the energy data processing demand from the fog computing server corresponding to the energy data processing record, determine the edge computing server corresponding to the demand keyword according to the demand keyword corresponding to the energy data processing demand, send the energy data processing demand and the processed energy data corresponding to the energy data processing demand to the edge computing server, obtain the processing result returned by the edge computing server, and send the processing result to the fog computing server that uploaded the energy data processing demand.

8. The processing system for multi-source highway energy data according to claim 7 is characterized in that: The demand keyword corresponding to the energy data processing demand is extracted from the energy data processing demand by the central processor through a preset keyword extraction algorithm.

9. The system for processing multi-source highway energy data according to claim 7, characterized in that: The edge computing server corresponding to the demand keyword is determined by the central processor according to the demand keyword corresponding to the energy data processing demand and the corresponding relationship between the preset demand keyword and the edge computing server.

10. The processing system for multi-source highway energy data according to claim 7, characterized in that: The energy data type includes voltage data and current data.

Images