Industrial Internet of Things Master Service Platform Data Analysis Collaboration System and Method

Abstract

The present invention relates to the technical field of intelligent manufacturing, and specifically discloses an industrial Internet of Things main service platform data parsing and collaboration system and method, including: a user platform, a service platform, a management platform, a sensing network platform, and an object platform; the object platform includes a plurality of production devices, and each production device is provided with a sensing unit and a control unit, wherein the sensing unit is used to collect the physical quantities of equipment operation and product processing parameters, perform local preliminary screening and caching, mark emergency critical data, and transmit the data to the sensing network platform after removing invalid data to form preliminary sensing data; the sensing network platform includes a plurality of sensing network sub-platforms and corresponding sensing network databases. The purpose of the present invention is to provide an industrial Internet of Things main service platform data parsing and collaboration system and method to solve the technical problems of large data processing delay, poor production real-time performance, and low fault troubleshooting efficiency of the existing service platform.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent manufacturing, and specifically discloses an industrial Internet of Things master service platform data parsing and collaboration system and method. Background Art

[0002] With the rapid development of intelligent manufacturing technology, the industrial Internet of Things is increasingly widely used in the field of industrial production. A typical industrial Internet of Things system includes five major components: a user platform, a service platform, a management platform, a sensor platform, and an object platform, which cooperate with each other to achieve intelligent detection and control of the production line.

[0003] For example, a Chinese invention patent (publication number: CN114629940A) discloses an industrial Internet of Things system and control method that is conducive to system scalability. The system includes a user platform, a service platform, a management platform, a sensing network platform, and an object platform; the service platform and the sensing network platform are arranged independently; both the service platform and the sensing network platform include multiple sub-platforms, and each sub-platform is provided with a database, a processor, and / or an information channel; the object platform includes a production line, and the production line is equipped with multiple sensors; among the sub-platforms of the sensing network platform, the sensors connected to the same sub-platform of the sensing network platform use the same communication protocol; any sub-platform of the sensing network platform is connected to a unique sub-platform of the service platform through the management platform.

[0004] Under the above industrial Internet of Things architecture, although each platform performs its own functions, when facing complex and changing industrial production scenarios, many problems gradually emerge. For example, in a large data volume interaction scenario, such as a large machinery manufacturing factory, a large number of production devices (such as numerically controlled machine tools, automated assembly robotic arms, etc.) in the object platform continuously generate a huge amount of operation status data, product quality monitoring data, etc., and these data rush towards the service platform all at once. Since traditional service platforms mostly adopt a centralized architecture and lack an effective data shunting and collaborative processing mechanism, when the service platform faces such a huge data flood, it is overwhelmed. This not only leads to a significant increase in data processing latency, seriously affecting production efficiency, but also may cause the system to crash due to data backlog, resulting in the production line coming to a standstill and bringing huge economic losses to the enterprise.

[0005] For another example, in a real-time control scenario, taking the high-precision packaging production line of an electronic chip as an example, the production process has extremely high requirements for real-time performance. The production devices on the target platform must be adjusted immediately based on accurate data such as temperature, humidity, and equipment vibration frequency collected in real time by the sensor network platform to ensure product quality. However, in the current system, the data parsing between platforms lacks coordination. The production process adjustment instructions issued by the user platform, the resource allocation information of the management platform, and the real-time perception data of the sensor network platform cannot be quickly and effectively aggregated on the main service platform and converted into accurate control signals. This makes it difficult for the production devices to respond in a timely manner, easily resulting in an increase in the defective product rate and failing to meet the strict requirements of high-end manufacturing for product quality stability.

[0006] Another example is in the fault diagnosis and maintenance scenario. When a fault occurs in a certain link of the industrial Internet of Things system, such as a fault in the temperature control system of a reactor on a chemical production line, although the sensor network platform can capture abnormal temperature data, there is a lack of close data parsing coordination between the main service platform and other entities. The main service platform cannot timely jointly retrieve the historical maintenance records and operation parameter change curves of the reactor with the management platform, nor can it quickly communicate with the user platform about the impact of production interruption on order delivery. It is even more unable to efficiently integrate the real-time fault-related data continuously transmitted by the sensor network platform (such as abnormal fluctuations in the current of the heating element and abnormal opening of the temperature control valve), resulting in low fault troubleshooting efficiency and extended repair time, further exacerbating production delays and cost increases.

[0007] In the above existing industrial Internet of Things systems, there are serious deficiencies in data parsing coordination between the service platform and the user platform, management platform, sensor network platform, and target platform. When facing many key industrial production scenarios such as large-volume data interaction, real-time control, fault diagnosis and maintenance, a series of technical problems such as large data processing delay, poor production real-time performance, and low fault troubleshooting efficiency occur, which urgently need to be solved. Summary of the Invention

[0008] The purpose of the present invention is to provide an industrial Internet of Things main service platform data parsing coordination system and method to solve the technical problems of large data processing delay, poor production real-time performance, and low fault troubleshooting efficiency of the existing service platform.

[0009] To achieve the above purpose, the basic solution of the present invention is: an industrial Internet of Things main service platform data parsing coordination system, including a user platform, a service platform, a management platform, a sensor network platform, and a target platform;

[0010] The object platform includes multiple production devices, each of which is equipped with a sensing unit and a control unit. The sensing unit is used to collect the physical quantities of equipment operation and product processing parameters, conduct local preliminary screening and caching, mark emergency critical data, and transmit the data to the sensing network platform after removing invalid data, forming preliminary sensing data.

[0011] The sensing network platform includes multiple sensing network sub-platforms and corresponding sensing network databases, which are used to receive preliminary sensing data, adaptively adjust the sampling frequency to prevent data transmission congestion, conduct secondary screening and classification of the data, store the data in different databases according to rules, and at the same time conduct preliminary quantitative analysis to extract features, and then send the integrated and analyzed preliminary sensing data to the management platform.

[0012] The management platform includes multiple management sub-platforms and an independent management database, which are used to deeply interpret the preliminary sensing data based on the knowledge graph after receiving it, judge the equipment operation status, predict the fault risk, and store the preliminary sensing data together with the equipment status, fault prediction, and resource allocation plan in the management database, and form management data and send it to the service platform.

[0013] The service platform adopts an optimized combined post-fractional layout, including a main service database and several sub-service databases. Each sub-service database is correspondingly connected to a service sub-platform and is equipped with an intelligent shunt and collaborative caching mechanism. The main service database receives the management data and conducts summary and preliminary classification, and distributes it to the sub-service databases according to the type and priority. The service sub-platforms process and mine the data value in parallel and generate refined data service products and store them in the sub-service databases.

[0014] The user platform is used to receive data from the sub-service databases, track and update the load status of the sub-service databases and give early warnings of timeout delay thresholds, help users obtain useful data to guide decision-making and adjust the process. The user platform is also used to modify the data in the sub-service databases and feedback the requirements and instructions to the service platform, forming a closed-loop collaborative process.

[0015] The working principle and beneficial effects of this basic solution are as follows: After the sensing unit of the object platform collects the original data, local preliminary screening and caching are carried out, effectively reducing the transmission of invalid data and alleviating the network burden. After receiving the preliminary sensing data, the sensing network platform adaptively adjusts the sampling frequency to prevent data transmission congestion, conducts secondary screening and classification of the data, and stores the data in different databases, which helps to quickly respond to and process key data. This shunt mechanism reduces data congestion during transmission, improves the efficiency of data processing, and reduces the delay.

[0016] The sensing network platform conducts preliminary quantitative analysis on the data, extracts key features, such as statistical temperature trends, which enables subsequent platforms to perform in-depth analysis and decision-making more quickly. Feature extraction simplifies the data, enabling important information to be quickly identified and processed, improving the system's response speed and real-time performance.

[0017] Based on the knowledge graph, the management platform deeply interprets the data sent by the sensing network platform, judges the operating status of the equipment, predicts the risk of failure, and plans resource allocation, and forms management data to be sent to the service platform. This in-depth interpretation and management decision-making improve the intelligent level of the system, enabling the system to more accurately predict and respond to potential failures, and improving the efficiency of fault troubleshooting.

[0018] The service platform adopts a combined post-fractional layout of the main service database and the sub-service database. The sub-service database is connected to the service sub-platform with a high-speed processing chip, realizing intelligent data shunting and parallel processing, and improving the data processing speed. The intelligent shunting collaborative caching mechanism and parallel processing ability significantly reduce the data processing delay and improve the production real-time performance.

[0019] The user platform tracks data updates and the timeout delay threshold, provides early warnings, and helps users obtain useful data in a timely manner to guide decision-making and adjust processes. The real-time monitoring and early warning mechanism improve the user's control ability over the production process, enhancing the real-time performance and flexibility of production.

[0020] In summary, through optimization at all links of data generation, transmission, processing, and application, the present invention improves the speed and accuracy of data processing, enhances the real-time response ability of the system, and improves the efficiency of fault diagnosis and maintenance. These technical means work together to form an efficient, intelligent, and collaborative data parsing and coordination system for the main service platform of the industrial Internet of Things. Through the above technical means, the technical problems of large data processing delay, poor production real-time performance, and low fault troubleshooting efficiency in the industrial Internet of Things are effectively solved.

[0021] Furthermore, the main service database or the management sub-platform is used to generate a timestamp while sending information to the user platform and attach it to the information; the user platform is used to calculate the delay between the time when the information actually received from the sub-service database and the timestamp, and perform corresponding processing according to different ranges of the delay. The corresponding processing includes:

[0022] When the delay is less than 30 milliseconds, the user platform displays to the user that the service sub-platform is working normally;

[0023] When the delay is between 30 milliseconds and 800 milliseconds, the user platform displays to the user that the service sub-platform has a network anomaly;

[0024] When the latency exceeds 800 milliseconds, the user platform accesses the service sub-platform and enters the fault handling mode.

[0025] When the main service database or the management sub-platform sends information to the user platform, a timestamp is generated. This timestamp records the exact moment when the information is sent, usually in milliseconds. The generation of the timestamp can be achieved through the high-precision clock built into the system to ensure its accuracy and consistency. The generated timestamp is attached to the information data packet and sent to the user platform together. After receiving the information, the user platform obtains the current system time, which represents the actual arrival moment of the information. Then, the user platform extracts the attached timestamp from the received information data packet, that is, the moment when the information is sent. By calculating the time difference between the current time and the timestamp, the user platform can obtain the time consumed for the entire transmission process from information sending to receiving, which is the latency. This calculation process can be implemented using a simple subtraction operation. More precisely: Latency = Current Time - Timestamp.

[0026] The user platform compares the calculated latency value with different preset time ranges to judge the working state of the service sub-platform. Specifically: When the latency is less than 30 milliseconds, it indicates that the data transmission of the service sub-platform is very fast, the system runs smoothly, and the user platform will display "Service sub-platform is working normally information" to the user, so that the user can understand that the system is in a good working state and can perform various operations normally. When the latency is between 30 milliseconds and 800 milliseconds, it shows that there may be a certain delay in the network of the service sub-platform, but it has not reached the level of serious failure. At this time, the user platform will display "Service sub-platform network abnormal information" to the user, reminding the user to pay attention to the network status and may need to take some measures, such as checking the network connection, restarting the device, etc., to try to improve the network delay problem. When the latency exceeds 800 milliseconds, it means that the network delay of the service sub-platform is very serious and may have affected the normal operation of the system. In this case, the user platform will automatically access the service sub-platform and enter the "fault handling mode". In the fault handling mode, the user platform may execute a series of diagnostic programs, such as detecting the connection status of the service sub-platform, querying the error log, analyzing the data transmission path, etc., to determine the specific cause of the fault and try to take corresponding repair measures, such as re-establishing the connection, adjusting the network configuration, etc., to restore the normal operation of the service sub-platform as soon as possible.

[0027] By attaching a timestamp when sending information and calculating the time delay when receiving it, the user platform can monitor the data transmission status of the service sub-platform in real time. This real-time monitoring mechanism enables users to promptly understand the system's operating conditions without waiting for regular system reports or manual checks, improving the system's response speed and user experience. The judgment of the time delay range provides a clear reference standard for the user platform, enabling it to accurately locate the working status of the service sub-platform. When network latency or a fault occurs, the user platform can quickly identify the problem and give corresponding prompt information to help users quickly find the root cause of the problem, reducing the time and effort required to troubleshoot the problem. When the time delay exceeds the preset threshold, the user platform automatically enters the fault handling mode and takes proactive measures for fault diagnosis and repair. This automated fault handling mechanism improves the system's reliability, reduces the risk of system interruption caused by network latency or faults, ensures the stable operation of the industrial Internet of Things system, and thus guarantees the continuity of industrial production and product quality.

[0028] The user platform displays different information to users according to different ranges of time delay, providing intuitive and easy-to-understand feedback on the system status. Users can adjust their operation strategies or take corresponding measures in a timely manner based on this information, enhancing the user's sense of control and satisfaction with the system and improving the overall user experience.

[0029] Furthermore, the user platform is also used to perform the following steps in the fault handling mode:

[0030] Calculate the time delay growth rate between the start time delay and the end time delay within a unit of time;

[0031] When the time delay growth rate is less than 0, the user platform continues to judge in the next unit of time until the time delay growth rate is not less than 0 or exits the fault handling mode;

[0032] When the time delay growth rate is between 0 and 30%, the user platform continues to judge in the next unit of time until the time delay growth rate is not less than 0 or exits the fault handling mode;

[0033] When the time delay growth rate is between 30 and 80%, the user platform generates network anomaly information of the service sub-platform for the user;

[0034] When the time delay growth rate is greater than 80%, the user platform generates information indicating that there is a fault in the corresponding management sub-platform for the user.

[0035] During the operation of the data parsing and collaboration system of the industrial Internet of Things main service platform, when the user platform detects that the information time delay from the sub-service database exceeds 800 milliseconds, it enters the fault handling mode. At this time, to accurately locate the root cause of the fault and track the development trend of the fault in real time, the user platform introduces the key indicator of time delay growth rate for in-depth analysis.

[0036] Specifically, the user platform records the starting value and the final value of the latency within a unit time (e.g., set to 1 second), and through a specific calculation logic: latency growth rate = (final latency - starting latency) / starting latency × 100%, the latency change situation within this period is obtained. This latency growth rate presented in percentage form can intuitively reflect the performance fluctuation trend of the service sub-platform or the relevant link in a short period of time.

[0037] When the calculated latency growth rate is less than 0, it means that the latency has shortened within this unit time, which may be due to the network's temporary self-repair, partial congestion alleviation, or other temporary factors. However, to ensure the continuous recovery of system stability, the user platform will not immediately determine that the fault has been resolved, but will continue to repeat the above calculation and judgment process in the next unit time until the latency growth rate is stably not less than 0, indicating that the system has returned to normal, or until other preset conditions for exiting the fault handling mode are met.

[0038] Similarly, when the latency growth rate is between 0 and 30%, the system is in a relatively mild fault fluctuation range. Although the latency has increased, the growth rate is relatively slow, which may be caused by a slight increase in network load, less intense resource competition, etc. The user platform continuously monitors and calculates the latency growth rate again in the next unit time to timely capture the development trend of the fault until the system recovers or the exit conditions are met.

[0039] When the latency growth rate is in the range of 30% to 80%, it indicates that the network link relied on by the service sub-platform has shown obvious performance degradation, and the data transmission efficiency has decreased significantly. Most likely, it is due to the superposition of factors such as network congestion, too high load on some nodes, or frequent small software-level faults. At this time, the user platform generates network exception information for the service sub-platform to the user, prompting the user to pay attention to the network status and possibly need to take preliminary troubleshooting or optimization measures.

[0040] Most seriously, when the latency growth rate is greater than 80%, such a sharp increase in latency indicates that there are deep-seated and structural fault hidden dangers in the system. It is very likely that the key link between the management sub-platform and the main service database is interrupted, or the management sub-platform itself has serious faults (such as database crashes, core processor overheating and crashing, etc.), resulting in blocked data transmission and processing stagnation. Based on this, the user platform accurately generates corresponding fault information for the management sub-platform to the user, guiding the user to quickly focus on the core area of the fault and carry out targeted repair work.

[0041] Through the multi - interval judgment mechanism of the time - delay growth rate, the fault type can be refined from the broad time - delay exceeding the standard to specific levels such as network anomalies and management sub - platform failures. This helps users quickly lock down the root cause of problems in complex industrial Internet of Things systems, reduce the blindness of fault troubleshooting, and greatly improve the maintenance efficiency. For example, in the Internet of Things system of a large - scale automated factory production line, once problems such as production stagnation and data update lag occur, based on the fault indication feedback from the user platform, users can quickly determine whether it is a loose network wiring (corresponding to network anomalies) or a key management server crash (corresponding to management sub - platform failures), avoiding indiscriminate troubleshooting of the entire system.

[0042] Continuous monitoring and judgment per unit time enable the user platform to be like a diligent "fault detective", real - time grasping the whole process of the system from the occurrence to the development of the fault. Whether the fault self - relieves, gradually deteriorates or remains in an unstable state, users can obtain information in the first time and adjust production strategies or allocate maintenance resources in a timely manner. For example, in an electronic chip packaging workshop, production has extremely high real - time requirements for environmental temperature and humidity. If there are time - delay problems in the Internet of Things system, through the real - time tracking of the user platform, operators can decide whether to suspend production and urgently allocate standby temperature - control equipment according to the dynamic time - delay growth rate to ensure that product quality is not affected.

[0043] Based on accurate fault location and real - time tracking, enterprise management can make more scientific production decisions according to the feedback from the user platform. When facing small network fluctuations that can be tolerated briefly (time - delay growth rate less than 30%), production can be maintained to avoid unnecessary production stoppage losses; while when facing serious fault hidden dangers (time - delay growth rate greater than 80%), production should be stopped immediately for maintenance to prevent malignant consequences such as a large number of defective products and further damage to equipment, effectively balancing production efficiency and product quality and enhancing the economic benefits of the enterprise.

[0044] Furthermore, the local preliminary screening, caching, marking of emergency and critical data, and removal of invalid data and then transmission to the sensor network platform include the following contents:

[0045] Conduct local preliminary screening on the collected data to remove irrelevant or redundant data;

[0046] Cache the screened data and mark emergency and critical data;

[0047] Remove invalid data, including error data, extreme values, and missing data;

[0048] Transmit the processed data to the sensor network platform to form preliminary perception data;

[0049] Among them, the removal of invalid data uses box plots to find outliers in the data and the method of replacing missing values for processing;

[0050] The MQTT protocol is adopted during the transmission process to adapt to low-bandwidth scenarios and achieve effective data transmission;

[0051] Before data transmission, edge computing is performed to filter and aggregate and preprocess the data.

[0052] Furthermore, the self-adaptive adjustment of the sampling frequency by the sensor network platform includes the following;

[0053] Set the acquisition duration, initial sampling frequency, maximum sampling frequency, and detection window length;

[0054] Generate a control signal according to the acquisition duration, initial sampling frequency, maximum sampling frequency, detection window length, amplitude and period of the excitation signal;

[0055] And send the excitation signal to the sensor;

[0056] The sensor works according to the excitation signal and outputs an analog signal;

[0057] The sensor network platform generates a control signal according to the acquisition duration, initial sampling frequency, maximum sampling frequency, detection window length, amplitude and period of the excitation signal, and sends the control signal to the excitation module; at the same time, preprocess the analog signal output by the sensor, and use the self-adaptive adjustment of the sampling frequency algorithm to adjust the sampling frequency in real time for data acquisition;

[0058] The sensor network platform is also used to detect the change rate and cumulative change amount of the sampling data in the detection window by calculating the number of sampling points. After corresponding processing of the ratio of the change rate and cumulative change amount of the data in adjacent time windows through a sliding time window, the real-time sampling frequency is adjusted; when the data changes rapidly, the sampling frequency is increased; when the data changes slowly, the sampling frequency is decreased.

[0059] Furthermore, the cache mechanism of the intelligent shunting system includes the following:

[0060] The service sub-platform identifies and classifies the received preliminary perception data;

[0061] The main service database intelligently selects a sub-service database for data routing according to the real-time load and performance indicators;

[0062] The service platform monitors the load conditions of the sub-service databases and dynamically adjusts the data flow direction to achieve load balancing;

[0063] The sub-service database decides the data caching strategy according to the preset caching rules and intelligent algorithms;

[0064] The service sub-platforms share the cache status information through a cooperation mechanism for cooperative cache management;

[0065] When the cached data is updated, the relevant service sub-platforms synchronously update their caches to maintain data consistency and real-time performance.

[0066] Furthermore, the intelligent shunting collaborative caching mechanism of the sub-service database and the service sub-platforms includes:

[0067] The sub-service database adopts a mixed intelligent algorithm of preset least recently used (LRU), least frequently used (LFU), and first in first out (FIFO) to determine the caching strategy of data;

[0068] The service sub-platforms share cache status information through a message queue or a distributed caching system to achieve cache data consistency and collaborative management;

[0069] The mixed intelligent algorithm dynamically adjusts the caching strategy according to data access frequency, popularity, and time sensitivity;

[0070] The collaborative cache management includes that when a service sub-platform updates or deletes cached data, other service sub-platforms receive change notifications and update their own cache status to maintain data consistency;

[0071] The caching strategy includes increasing the priority of data with high access frequency in the cache, preferentially caching key business data to reduce the caching of non-critical data, and setting a shorter cache time for data with high timeliness requirements.

[0072] Furthermore, sub-service database A receives preliminary perception data from the sensor network platform and decides to cache the latest preliminary perception data according to preset caching rules and the mixed intelligent algorithm;

[0073] The main service database monitors the load conditions of all sub-service databases and intelligently routes the preliminary perception data to sub-service database A with a lower load;

[0074] The service sub-platforms share cache status information through a distributed caching system. After receiving the cache status information of sub-service database A, service sub-platform B decides not to cache these data repeatedly;

[0075] When a new batch of preliminary perception data arrives, sub-service database A updates its cache and notifies service sub-platform B. After receiving the update notification, service sub-platform B synchronously updates its cache view to maintain data consistency;

[0076] The service platform monitors the load conditions of all sub-service databases. When it finds that the load of sub-service database B suddenly increases, it dynamically adjusts the data flow direction and routes a part of the data to sub-service database C with a lower load to achieve load balancing.

[0077] Furthermore, the intelligent shunting collaborative caching mechanism includes:

[0078] The sub-service database adopts a hybrid intelligent algorithm that combines the preset Least Recently Used (LRU) algorithm, Least Frequently Used (LFU) algorithm, and First In First Out (FIFO) algorithm, and combines a machine learning model to predict the data caching strategy. The specific formula is:

[0079] The LRU algorithm sorts according to the data access time and eliminates the least recently used data;

[0080] The LFU algorithm sorts according to the data access frequency and eliminates the data with the lowest access frequency;

[0081] The FIFO algorithm eliminates the earliest entered data according to the time order when the data enters the cache;

[0082] The hybrid intelligent algorithm dynamically adjusts the caching strategy according to the data access frequency F, popularity H, and time sensitivity T. The calculation formula is: C = αF + βH + γT, where α, β, and γ are weight coefficients, and α + β + γ = 1;

[0083] The machine learning model is based on historical data and real-time data to predict the future access pattern and importance of the data, and adjusts the weight coefficients α, β, and γ to optimize the caching strategy;

[0084] The main service database intelligently selects the sub-service database for data routing according to the real-time load L and performance metrics P, combined with the load trend and performance changes predicted by the prediction model. The selection formula is: S = f ( L , P , P pred), where f is the comprehensive evaluation function of the load and performance metrics, P pred is the predicted performance change;

[0085] The service platform monitors the load situation of the sub-service database and dynamically adjusts the data flow direction to achieve load balancing. The adjustment formula is: Δ D = k ( L max - L min) + Δ P pred, where ΔD is the data flow direction adjustment amount, k is the adjustment coefficient, Lmax and Lmin are the maximum and minimum loads of the sub-service database respectively, and Δ P pred is the load adjustment amount caused by the predicted performance change;

[0086] The service sub-platforms share the cache status information through a message queue or a distributed cache system to achieve the consistency and collaborative management of the cached data. The sharing formula is: S sync =S 1 ∪ S 2 ∪ … ∪ Sn , where S sync is a set of shared cache status information, S 1, S 2, ..., Sn are the cache status information of each service sub - platform;

[0087] When the cached data is updated, the relevant service sub - platforms synchronously update their caches to maintain data consistency and real - time performance. The update formula is: C new = C old ∪ Δ C , where C new is the updated cache data, C old is the cache data before update, and Δ C is the newly added or modified data;

[0088] The cache policy also includes increasing the priority of data with high access frequency in the cache, preferentially caching critical business data to reduce the caching of non - critical data, and setting a shorter cache time for data with high timeliness requirements. The specific formula is: P = f ( F , K , T , P pred), where P is the priority of the data in the cache, F is the data access frequency, K is the criticality index of the data, T is the timeliness requirement of the data, P pred is the predicted change in data priority, and f is the priority calculation function.

[0089] After the sensing unit of the object platform production device collects a large amount of raw data, it immediately starts the local preliminary screening process. Due to the complex production environment, the sensor will capture various types of information, but not all data is valuable for subsequent decision - making and control. For example, in a machining workshop, the sensor may simultaneously collect data such as the ambient temperature of the equipment shell, the illumination brightness of the workshop, and the vibration frequency of the key components of the equipment. At this time, according to the preset production process correlation rules, identify and remove data such as illumination brightness that is not directly related to the equipment operation status and product processing accuracy or is redundant, and only retain the core information that can reflect the equipment health status and product quality.

[0090] The filtered data enters the caching process. The cache is like a temporary data "transfer station" that not only stores data but also marks it according to the urgency of the data and its critical impact on the production process. For example, for a chemical reactor, if the temperature and pressure data are approaching the threshold of chemical reaction runaway, these data will be marked as urgent and critical data for subsequent system priority processing to ensure production safety. Using the box plot, a statistical tool, and leveraging the quartile distribution characteristics of the data, outliers outside the reasonable range can be accurately located. For example, in the production of electronic devices, if the temperature of a certain solder joint suddenly appears as a maximum value far exceeding the normal welding temperature range, it can be determined as invalid data and excluded. At the same time, for missing values, through reasonable replacement methods, such as replacing them with the mean, median of historical data or predicted values of a specific model, the integrity and usability of the data are ensured.

[0091] The MQTT protocol is selected for the transmission process. This protocol is designed for low-bandwidth and unstable network environments and uses the publish / subscribe mode. It can achieve the effective transmission of data from the sensing unit to the sensor network platform with minimal overhead under limited network resources, ensuring that data is delivered in a timely manner and preventing the loss of key information due to network congestion.

[0092] Before the data is officially transmitted, edge computing comes into play. It filters data locally at the sensing unit close to the data generation source, removing duplicate and low-value information, and at the same time performs aggregation and preprocessing on relevant data. For example, aggregating the temperature data of the same type of device on multiple time series into the average temperature and temperature change trend over a period of time, reducing the amount of data to be transmitted, improving the transmission efficiency, and reducing the processing burden on the subsequent platform.

[0093] By removing irrelevant, redundant, and invalid data, the amount of data to be transmitted is significantly reduced, preventing the network resources from being occupied by useless information, enabling the limited bandwidth to focus on transmitting key data, ensuring the smoothness of data transmission, and preventing network congestion, especially in large-scale industrial Internet of Things deployment scenarios where numerous devices transmit data simultaneously, with remarkable effects.

[0094] The precise screening, marking, and invalid data processing mechanisms ensure that the data entering the subsequent process has high credibility and high relevance, providing a solid foundation for subsequent data-based analysis and decision-making, reducing the risk of misjudgment caused by incorrect or low-quality data, and improving the accuracy of decision-making in the entire industrial Internet of Things system. For example, in the field of precision manufacturing, high-quality data guarantees the high-precision control of product quality.

[0095] Flexibly adjust the sampling frequency according to the actual dynamics of the production site to ensure that sufficient detailed data can be collected at critical moments (such as precursors of equipment failures and critical changes in process parameters), providing detailed basis for fault diagnosis and process optimization, avoiding missing key information due to fixed sampling frequency, and improving the accuracy of data description of the production process. For example, in the monitoring of aero-engines, subtle performance fluctuations can be accurately captured to give early warnings of potential faults.

[0096] As an important node for data inflow, the service sub-platform quickly identifies and classifies the data when receiving the preliminary perception data from the sensor network platform according to the preset data type tags, source identifiers and production process association rules. For example, in an automotive manufacturing production line, data such as body welding quality monitoring data, engine assembly parameter data, and component painting thickness data are classified according to their respective technological processes for subsequent targeted processing.

[0097] The main service database monitors the load conditions of each sub-service database in real time. The load information covers multi-dimensional indicators such as data storage volume, processing task queue length, and current processing rate. At the same time, combined with performance indicators such as data read / write latency and system throughput, through the built-in intelligent algorithm (a comprehensive evaluation function of load and performance indicators), the optimal data routing scheme is calculated to intelligently allocate the preliminary perception data to the sub-service database with lower load and performance meeting requirements, ensuring balanced and efficient data processing. For example, in an e-commerce logistics warehousing Internet of Things system, according to the load conditions such as the frequency of goods in and out and the inventory counting task volume in different areas of the warehouse, the data flow of inventory management is reasonably allocated to different sub-service databases.

[0098] The service platform continuously monitors the load of the sub-service database. Once a load imbalance is detected, such as when several sub-service databases have a load far exceeding the average level due to a sudden influx of a large amount of data or concentrated processing tasks, immediately according to the preset dynamic adjustment strategy, by modifying the data flow rules, part of the data is diverted to the sub-service database with a lighter load to achieve global load balancing and ensure the stable operation of the system.

[0099] The sub-service database determines the data caching strategy based on preset caching rules, considering factors such as data access frequency, update frequency, and data importance, and combines intelligent algorithms (such as hybrid intelligent algorithms). For example, frequently queried product standard specification data, key parameters of recent production processes, etc. are cached to improve the data acquisition speed and reduce the overhead of repeated database queries. Between service sub-platforms, through a collaboration mechanism, an information sharing channel is built using message queues or distributed caching systems to exchange cache status information in real time, including cached data content, cache expiration period, data popularity, etc. When the cached data of a service sub-platform is updated, other relevant service sub-platforms are immediately notified through the shared channel to synchronize the cache update, ensuring data consistency and avoiding data processing errors or duplicate labor caused by cache inconsistency. The intelligent shunting and caching mechanism reduces the transmission delay and processing waiting time of data in the system. Each sub-service database processes corresponding types of data according to its own advantages, avoiding resource competition and centralized processing bottlenecks. For example, in a large-scale iron and steel production IoT system, data from different process links is shunted and processed to speed up the production rhythm and improve the overall production capacity.

[0100] Collaborative cache management ensures that no matter which service sub-platform the data is obtained from, its content and timeliness are consistent, avoiding problems such as production decision-making mistakes and equipment control conflicts caused by data inconsistency, and improving the reliability of the industrial IoT system operation. For example, in a multi-robot collaborative operation scenario, it ensures that each robot acts based on the same and latest task instruction data.

[0101] The hybrid intelligent algorithm combines machine learning models to accurately predict data requirements, optimize cache configuration, greatly improve the cache hit rate, reduce database query time, and enhance data acquisition speed. For example, in a large-scale financial transaction risk control IoT system with a large amount of data, key risk indicator data can be quickly retrieved to ensure the timeliness and security of transactions. Brief Description of the Drawings

[0102] Figure 1 It is a flow framework diagram of the industrial IoT main service platform data parsing and collaboration system of the embodiment of the present invention. Detailed Description of the Embodiment

[0103] The following is a further detailed description through specific embodiments:

[0104] The embodiment is basically as shown in the appendix Figure 1 : The industrial IoT main service platform data parsing and collaboration system includes a user platform, a service platform, a management platform, a sensor network platform, and an object platform;

[0105] The object platform includes multiple production devices, each of which is provided with a sensing unit and a control unit. The sensing unit is used to collect physical quantities of equipment operation (including temperature and pressure) and product processing parameters, perform local preliminary screening and caching, mark emergency critical data, remove invalid data, and then transmit the data to the sensing network platform to form preliminary sensing data;

[0106] The sensing network platform includes multiple sensing network sub-platforms and corresponding sensing network databases, which are used to receive preliminary sensing data, adaptively adjust the sampling frequency to prevent data transmission congestion, perform secondary screening and classification on the data, store the data in different databases according to rules, and at the same time perform preliminary quantitative analysis to extract features, and then send the integrated and analyzed preliminary sensing data to the management platform;

[0107] The management platform includes multiple management sub-platforms and an independent management database. After receiving the preliminary sensing data, it performs in-depth interpretation based on the knowledge graph, judges the equipment operation status, predicts the fault risk, and stores the preliminary sensing data together with the equipment status, fault prediction, and resource allocation plan in the management database. After forming management data, it sends the data to the service platform;

[0108] The service platform adopts an optimized combined fractional layout, including a main service database and several sub-service databases. Each sub-service database is correspondingly connected to a service sub-platform and is equipped with an intelligent shunt and collaborative caching mechanism. After receiving the management data, the main service database performs summarization and preliminary classification, and allocates the data to the sub-service databases according to the type and priority. The service sub-platforms process and mine the data value in parallel, and generate refined data service products and store them in the sub-service databases;

[0109] The user platform is used to receive data from the sub-service databases, track and update the load status of the sub-service databases, and give early warnings for timeout delay thresholds, helping users obtain useful data to guide decision-making and adjust processes. The user platform is also used to modify the data in the sub-service databases and feedback requirements and instructions to the service platform to form a closed-loop collaborative process.

[0110] Among them, the main service database or the management sub-platform is used to generate a timestamp while sending information to the user platform and attach it to the information; the user platform is used to calculate the delay between the time when it actually receives information from the sub-service database and the timestamp, and perform corresponding processing according to different ranges of the delay. The corresponding processing includes:

[0111] When the delay is less than 30 milliseconds, the user platform displays information indicating that the service sub-platform is working normally to the user;

[0112] When the delay is between 30 milliseconds and 800 milliseconds, the user platform displays information indicating that the network of the service sub-platform is abnormal to the user;

[0113] When the delay exceeds 800 milliseconds, the user platform accesses the service sub-platform and enters the fault handling mode.

[0114] The user platform is also used to perform the following steps in the fault handling mode:

[0115] Calculate the delay growth rate between the starting delay and the final delay within a unit time;

[0116] When the delay growth rate is less than 0, the user platform continues to judge in the next unit time until the delay growth rate is not less than 0 or exits the fault handling mode;

[0117] When the delay growth rate is between 0 and 30%, the user platform continues to judge in the next unit time until the delay growth rate is not less than 0 or exits the fault handling mode;

[0118] When the delay growth rate is between 30% and 80%, the user platform generates network exception information for the service sub-platform to the user;

[0119] When the delay growth rate is greater than 80%, the user platform generates information that there is a fault in the corresponding management sub-platform to the user.

[0120] Specifically, in an actual industrial production scenario, taking an automobile manufacturing factory as an example, the object platforms are distributed on each workshop production line and include a large number of production devices such as automobile engine assembly equipment, body welding robots, and painting devices. Each production device is equipped with an advanced sensing unit, which integrates a variety of high-precision sensors. For example, the temperature sensor uses a platinum resistance thermometer to accurately measure the heat generation of key parts of the equipment, the pressure sensor selects a high-precision strain gauge type sensor to accurately capture the pressure changes in the hydraulic and pneumatic systems, and acceleration sensors, displacement sensors, etc. are used to obtain operating physical quantities. There are also sensors using technologies such as laser measurement and machine vision to collect product processing parameters, such as the size accuracy of body welds and the bore diameter tolerance of engine cylinder blocks.

[0121] During operation, the sensing unit collects thousands of groups of raw data per second. First, through the built-in primary screening algorithm, according to the preset range of key indicators of automobile production processes, data unrelated to the normal operation of the equipment and product qualification is quickly eliminated, such as the brightness of workshop lighting and slight vibration data of non-critical parts. The filtered valid data is stored in the local high-speed cache chip, and the cache capacity is designed to store high-frequency acquisition data within 10 minutes according to the data generation rate of the equipment. At the same time, using the priority marking algorithm, once emergency key data such as engine overheating and abnormal welding current is detected, it is immediately marked as high priority to ensure priority transmission. For invalid data, a box plot combined with the statistical characteristics of historical data in the automotive industry is used to identify and remove extreme values generated by temporary sensor failures and missing data caused by communication interference, and the missing values are replaced by interpolation based on adjacent data or the average value of the same period in history. Finally, the processed data is transmitted to the sensing network platform through the wireless access point in the workshop according to the MQTT protocol to form preliminary sensing data, and the transmission frequency is dynamically adjusted according to the urgency of the data and the workshop network bandwidth, up to 100 times per second at most.

[0122] The sensing network platform sets up multiple sensing network sub-platforms in different areas of the factory workshop. Each sub-platform is connected to the sensing units of a group of production devices nearby and receives the preliminary sensing data from the object platform. Taking the body shop as an example, the sensing network sub-platform is connected to the sensing units of dozens of welding robots and assembly equipment.

[0123] The sub-platform is built with an adaptive sampling frequency adjustment module, with the initial set acquisition duration of 5 minutes, the initial sampling frequency of once every 10 seconds, the maximum sampling frequency of once every 1 second, and the detection window length of 1 minute. Control signals are generated according to factors such as the real-time production task volume in the workshop and the operation stability of the equipment. For example, during the trial production stage of a new vehicle model, the equipment is frequently debugged and the probability of anomalies is high. The control signal drives the excitation module to increase the amplitude and period of the excitation signal, so that the sensor increases the sampling frequency; during the stable production period of a mature vehicle model, the sampling frequency is appropriately reduced. At the same time, for the analog signal output by the sensor, a high-speed ADC chip is used for preprocessing. After being converted into a digital signal, according to the automotive production process flow and quality control nodes, the data is screened and classified for the second time. For example, the body welding quality data is stored in the welding process database, and the assembly accuracy data is stored in the assembly process database. Preliminary quantitative analysis is carried out using data mining algorithms to extract features, such as statistically analyzing the temperature fluctuation range of welding spots and the change trend of assembly gaps. The integrated and analyzed preliminary sensing data is sent to the management platform through the workshop backbone network every 30 seconds.

[0124] The management platform is located in the central control room of the factory and consists of multiple management sub-platforms. Each management sub-platform is responsible for managing one or several production lines, connecting to an independent management database, and storing knowledge graphs such as all historical data, process standards, and equipment maintenance manuals related to the production lines.

[0125] After receiving the preliminary perception data from the sensor network platform, the management sub-platform runs intelligent analysis software based on the knowledge graph. Taking the engine production line as an example, by comparing the real-time temperature and pressure data with the temperature-pressure curve model of the engine's normal operation, and combining information such as the cumulative operation time of the equipment and recent maintenance records, it accurately judges the equipment operation status and predicts potential failure risks, such as warning 30 minutes in advance about the possible power decline problem caused by piston ring wear. At the same time, according to the production order task volume and the real-time status of the equipment, it formulates a resource allocation plan, such as adjusting the material distribution order and arranging the online time of standby equipment. It packages the preliminary perception data, equipment status evaluation, failure prediction, and resource allocation plan as management data and sends it to the service platform through the factory's internal high-speed local area network every 2 minutes.

[0126] The service platform is set up in the factory's data center and adopts an optimized combined post-type layout. The main service database is equipped with a high-performance server cluster, which has the capabilities of mass storage and high-speed data processing, and is connected to multiple sub-service databases. The sub-service databases are divided according to the automotive production business modules, such as being divided into sub-service databases for powertrain, body, chassis, electronic and electrical, etc. Each sub-service database is correspondingly connected to a service sub-platform equipped with a GPU acceleration card to achieve parallel data processing.

[0127] After receiving the management data from the management platform, the main service database completes summarization and preliminary classification within 10 seconds, and intelligently selects a sub-service database for routing and distribution according to factors such as data business type, urgency, and priority of impact on production. For example, it preferentially distributes engine fault warning data to the powertrain sub-service database. The service sub-platform corresponding to the sub-service database uses deep learning algorithms to mine the data value, such as constructing a fault prediction model based on historical engine fault data and real-time operation parameters, generating refined data service products such as engine preventive maintenance suggestion reports and body painting quality optimization plans, and storing them in the sub-service database for the user platform to call at any time.

[0128] The user platform is deployed on the office terminals of factory managers and engineers as well as the handheld intelligent devices at the production site, facilitating the acquisition of information at any time. The user platform establishes a high-speed connection with the sub-service database and receives data from the sub-service database in real time.

[0129] Taking the workshop supervisor as an example, the terminal used by the supervisor refreshes the data pushed by the sub-service database every 5 seconds. Meanwhile, the load monitoring software is running to track the load status of the sub-service database, such as monitoring the data query response time and the number of concurrent data processing tasks. Once it is found that the delay between the actual time of receiving information from the sub-service database and the timestamp attached to the information exceeds the threshold, the corresponding processing mechanism is immediately activated. When the delay is less than 30 milliseconds, the terminal interface displays the normal operation information of the service sub-platform with a green icon; when the delay is between 30 milliseconds and 800 milliseconds, a yellow warning box pops up to display the network exception information of the service sub-platform; when the delay exceeds 800 milliseconds, it automatically connects to the corresponding service sub-platform and enters the fault handling mode.

[0130] In the fault handling mode, the user platform calculates the delay growth rate between the start delay and the end delay of the delay within a unit time (set to 1 second). If the workshop supervisor finds that the delay growth rate is less than 0, it indicates that the situation may be improving, and the user platform continues to judge in the next unit time until the delay growth rate is stable and not less than 0 or other conditions for exiting the fault handling mode are met, such as the network restoring normal bandwidth and the load of the service sub-platform dropping back to the normal range; when the delay growth rate is between 0 and 30%, continuous monitoring is also carried out; when the delay growth rate is between 30 and 80%, a red warning message is pushed to the workshop supervisor to inform the network exception information of the service sub-platform; when the delay growth rate is greater than 80%, the root cause of the problem is accurately located, and a severe fault alarm is pushed to the supervisor, indicating that there is a fault information in the corresponding management sub-platform, assisting it to quickly organize a maintenance team to troubleshoot key parts such as servers, network links, and databases involved in the management sub-platform.

[0131] Through the above specific implementation methods of the close cooperation of each platform, the data parsing and cooperation system of the industrial Internet of Things main service platform can operate efficiently, effectively solve the technical problems of large data processing delay, poor production real-time performance, and low fault troubleshooting efficiency of the existing service platform, and ensure the intelligent and efficient promotion of industrial production.

[0132] In other embodiments, local preliminary screening, caching, marking of emergency and critical data, and removal of invalid data are performed before transmitting to the sensor network platform, including the following contents:

[0133] Perform local preliminary screening on the collected data to remove irrelevant or redundant data;

[0134] Cache the screened data and mark the emergency and critical data;

[0135] Remove invalid data, including error data, extreme values, and missing data;

[0136] Transmit the processed data to the sensor network platform to form preliminary perception data;

[0137] Among them, the removal of invalid data is processed by using a box plot to find outliers in the data and by replacing missing values;

[0138] The MQTT protocol is adopted during the transmission process to adapt to low-bandwidth scenarios and achieve effective data transmission;

[0139] Before data transmission, edge computing is performed to filter and aggregate and preprocess the data.

[0140] The adaptive adjustment of the sampling frequency by the sensor network platform includes the following contents;

[0141] Set the acquisition duration, initial sampling frequency, maximum sampling frequency, and detection window length;

[0142] Generate a control signal according to the acquisition duration, initial sampling frequency, maximum sampling frequency, detection window length, amplitude and period of the excitation signal;

[0143] And send the excitation signal to the sensor;

[0144] The sensor works according to the excitation signal and outputs an analog signal;

[0145] The sensor network platform generates a control signal according to the acquisition duration, initial sampling frequency, maximum sampling frequency, detection window length, amplitude and period of the excitation signal, and sends the control signal to the excitation module; at the same time, preprocess the analog signal output by the sensor, and use the adaptive adjustment sampling frequency algorithm to adjust the sampling frequency in real time for data acquisition;

[0146] The sensor network platform is also used to detect the change rate and cumulative change amount of the sampling data in the detection window by calculating the number of sampling points. After corresponding processing of the ratio of the change rate and cumulative change amount of the data in adjacent time windows through a sliding time window, the real-time sampling frequency is adjusted; when the data changes rapidly, the sampling frequency is increased; when the data changes slowly, the sampling frequency is decreased.

[0147] In specific use: The sensing unit is equipped with an advanced microprocessor and an intelligent screening algorithm built-in. For a numerically controlled machine tool, its sensor can collect hundreds of data points per second, covering information such as the displacement of each axis of the equipment, cutting force, spindle speed, motor current, and dimensional accuracy of the workpiece. The algorithm quickly identifies and removes irrelevant data according to the preset production process rules. For example, data such as the ambient light intensity in the workshop and the slight vibration of the equipment shell are directly removed because they have no direct relation to the machining accuracy of the machine tool and the operation stability of the equipment. At the same time, redundant data cannot escape the screening. For example, during the stable cutting stage, if multiple almost identical spindle speed values are continuously collected, only representative samples are retained, greatly reducing the amount of data for subsequent transmission and processing.

[0148] The filtered valid data is immediately stored in the local high-speed cache chip, and the cache capacity is dynamically allocated according to the device data generation rate and the urgency of the production task. Taking an automated assembly robot as an example, when performing a key assembly task, if it is detected that the assembly pressure of a certain key component is close to the preset upper limit, the microprocessor will immediately mark the pressure data and related information such as the component identification code and assembly time as emergency critical data to ensure priority processing in subsequent transmissions and guarantee the assembly quality and equipment safety.

[0149] When using the box plot method to remove outliers, take the cutting force data of a numerically controlled machine tool as an example. The system constructs a box plot model based on historical cutting force data and sets a reasonable interquartile range. When the cutting force data collected in real time exceeds this range, such as when the cutting force suddenly soars due to a sudden tool breakage, the outlier will be determined as invalid data and excluded. For missing values, if the motor current value collected at a certain moment is missing, the system will replace it by linear interpolation or taking the average value of adjacent time periods according to the change trend of the current value at the previous moment and combining the current operating state of the machine tool to ensure the continuity and integrity of the data.

[0150] Before data transmission, the edge computing module plays a key role. Still taking a numerically controlled machine tool as an example, it filters the cached data, removes data that appears repeatedly and has little guiding significance for the current machining task, and at the same time performs aggregation preprocessing on the relevant data. Aggregate the displacement data of each axis over a period of time (such as the past 10 seconds) into a displacement change curve, and statistically calculate characteristic quantities such as the average value, maximum value, and minimum value of the cutting force to reduce the dimension and total amount of the transmitted data. The MQTT protocol is used in the transmission process. In a complex electromagnetic environment such as a factory workshop with many low-bandwidth areas, the sensing unit of the numerically controlled machine tool, as the publisher, publishes the processed data to the corresponding MQTT broker server according to topics (such as device number, data type, etc.), and the sensing network platform, as the subscriber, receives it on demand to ensure efficient and stable data transmission and avoid data loss or delay caused by network congestion.

[0151] Taking the environmental monitoring sensor network sub-platform as an example, it is necessary to accurately collect environmental parameters such as temperature, humidity, and harmful gas concentration in the workshop. The initial set acquisition duration is 30 minutes, aiming to obtain a relatively complete environmental change trend; the initial sampling frequency is set to once every 5 minutes, which can neither overly occupy resources in the initial stage nor initially capture environmental changes; the maximum sampling frequency is increased to once every 1 minute to cope with sudden emergencies such as harmful gas leakage. The detection window length is set to 5 minutes to facilitate timely analysis of data changes. At the same time, according to factors such as the operating status of the ventilation system in the workshop (such as fan speed, ventilation volume) and whether there are special temperature and humidity requirements in the production process, the amplitude and period of the excitation signal are determined, and then a control signal is generated through the built-in signal generation algorithm to drive the external excitation module to generate the corresponding excitation signal and send it to the sensor.

[0152] After receiving the excitation signal, temperature and humidity sensors, harmful gas sensors, etc. start to work and output analog signals. On the one hand, the sensing network sub-platform synchronously feeds back the control signal to the excitation module to dynamically adjust the working state of the sensor and ensure the acquisition accuracy. On the other hand, for the analog signal output by the sensor, an analog-to-digital conversion and preprocessing are performed using a high-speed ADC chip to remove signal noise and calibrate the signal baseline. An adaptive sampling frequency adjustment algorithm is adopted to monitor data changes in real time. By calculating the sampling data change rate and cumulative change amount within the detection window of the sampling points, and using the sliding time window technology, the ratio of the data change rate and cumulative change amount in adjacent time windows is compared. If the concentration of harmful gases rises rapidly due to chemical leakage in a certain area of the workshop, the data change rate surges, and the ratio far exceeds the normal threshold, the system will immediately increase the sampling frequency from the original once every 5 minutes to once every 1 minute or even higher to capture the detailed process of harmful gas diffusion; conversely, during the environmental stable period, such as when the workshop is shut down for rest, the data changes slowly, and the system automatically reduces the sampling frequency to once every 10 minutes to save resources and avoid unnecessary data acquisition and storage.

[0153] In another embodiment, the intelligent shunt system cache mechanism includes the following contents:

[0154] The service sub-platform identifies and classifies the initially perceived data received;

[0155] The main service database intelligently selects a sub-service database for data routing according to real-time load and performance indicators;

[0156] The service platform monitors the load situation of the sub-service database and dynamically adjusts the data flow direction to achieve load balancing;

[0157] The sub-service database determines the data caching strategy according to the preset caching rules and intelligent algorithms;

[0158] Service sub - platforms share cache status information through a collaboration mechanism for collaborative cache management;

[0159] When the cached data is updated, relevant service sub - platforms synchronously update their caches to maintain data consistency and real - time performance.

[0160] The intelligent shunting collaborative cache mechanism of the sub - service database and the service sub - platforms includes:

[0161] The sub - service database adopts a mixed intelligent algorithm of preset least recently used, least frequently used, and first - in - first - out to determine the cache policy of data;

[0162] Service sub - platforms share cache status information through a message queue or a distributed cache system to achieve cache data consistency and collaborative management;

[0163] The mixed intelligent algorithm dynamically adjusts the cache policy according to data access frequency, popularity, and time sensitivity;

[0164] The collaborative cache management includes that when a service sub - platform updates or deletes cached data, other service sub - platforms receive change notifications and update their cache status to maintain data consistency;

[0165] The cache policy includes increasing the priority of data with high access frequency in the cache, preferentially caching critical business data to reduce the cache of non - critical data, and setting a shorter cache time for data with high timeliness requirements.

[0166] The sub - service database A receives preliminary perception data from the sensor network platform and decides to cache the latest preliminary perception data according to the preset cache rules and the mixed intelligent algorithm;

[0167] The main service database monitors the load conditions of all sub - service databases and intelligently routes the preliminary perception data to the sub - service database A with lower load;

[0168] Service sub - platforms share cache status information through a distributed cache system. After receiving the cache status information of the sub - service database A, the service sub - platform B decides not to cache these data repeatedly;

[0169] When a new batch of preliminary perception data arrives, the sub - service database A updates its cache and notifies the service sub - platform B. After receiving the update notice, the service sub - platform B synchronously updates its cache view to maintain data consistency;

[0170] The service platform monitors the load conditions of all sub - service databases. When it finds that the load of the sub - service database B suddenly increases, it dynamically adjusts the data flow direction and routes a part of the data to the sub - service database C with lower load to achieve load balancing.

[0171] The intelligent shunt collaborative caching mechanism includes:

[0172] The sub-service database adopts a hybrid intelligent algorithm that combines the preset Least Recently Used (LRU) algorithm, Least Frequently Used (LFU) algorithm, and First In First Out (FIFO) algorithm, and combines a machine learning model to predict the data caching strategy. The specific formula is:

[0173] The LRU algorithm sorts according to the data access time and eliminates the least recently used data;

[0174] The LFU algorithm sorts according to the data access frequency and eliminates the data with the lowest access frequency;

[0175] The FIFO algorithm sorts according to the time order when the data enters the cache and eliminates the data that entered the earliest;

[0176] The hybrid intelligent algorithm dynamically adjusts the caching strategy according to the data access frequency F, popularity H, and time sensitivity T. The calculation formula is: C = αF + βH + γT, where α, β, and γ are weight coefficients, and α + β + γ = 1;

[0177] The machine learning model is based on historical data and real-time data to predict the future access pattern and importance of the data, and adjusts the weight coefficients α, β, and γ to optimize the caching strategy;

[0178] The main service database intelligently selects a sub-service database for data routing according to the real-time load L and performance metrics P, combined with the load trend and performance changes predicted by the prediction model. The selection formula is: S = f ( L , P , P pred), where f is the comprehensive evaluation function of the load and performance metrics, P pred is the predicted performance change;

[0179] The service platform monitors the load situation of the sub-service database and dynamically adjusts the data flow direction to achieve load balancing. The adjustment formula is: Δ D = k ( L max - L min) + Δ P pred, where ΔD is the data flow direction adjustment amount, k is the adjustment coefficient, Lmax and Lmin are the maximum and minimum loads of the sub-service database respectively, and Δ P pred is the load adjustment amount caused by the predicted performance change;

[0180] Among the service sub - platforms, the cache status information is shared through a message queue or a distributed cache system to achieve the consistency and collaborative management of cache data. The sharing formula is: S sync = S 1 ∪ S 2 ∪ … ∪ Sn , where S sync is the set of shared cache status information, S 1, S 2, ..., Sn are the cache status information of each service sub - platform;

[0181] When the cached data is updated, the relevant service sub - platforms synchronously update their caches to maintain data consistency and real - time performance. The update formula is: C new = C old ∪ Δ C , where C new is the updated cache data, C old is the cache data before the update, and Δ C is the newly added or modified data;

[0182] The cache policy also includes increasing the priority of data with a high access frequency in the cache, preferentially caching key business data to reduce the caching of non - key data, and setting a shorter cache time for data with high timeliness requirements. The specific formula is: P P = f ( F , K , T , P , P pred), where P is the priority of the data in the cache, F is the data access frequency, K is the criticality index of the data, T is the timeliness requirement of the data,

[0183] In specific use: The service sub - platform receives the preliminary perception data from the sensor network platform, and these data contain key information such as the operating status of the device and environmental parameters. The service sub - platform identifies and classifies the data according to the type and characteristics of the data. For example, temperature data, pressure data, vibration data, etc. are classified and stored separately for subsequent processing and analysis.

[0184] The main service database monitors the load conditions of all sub-service databases in real time, including performance metrics such as data processing volume, storage space occupancy rate, response time, etc. When there is new preliminary perception data to be stored, the main service database will intelligently select a sub-service database with a lower load for data routing based on the current load conditions and performance metrics. For example, if the load of sub-service database A is lower than that of other sub-service databases, the main service database will route the data to sub-service database A, thus achieving load balancing and avoiding the impact of excessive load on a certain sub-service database on data processing speed and system stability.

[0185] The sub-service database determines the data caching strategy according to the preset caching rules and the hybrid intelligent algorithm. The hybrid intelligent algorithm combines the Least Recently Used (LRU), Least Frequently Used (LFU), and First In First Out (FIFO) algorithms, comprehensively considering factors such as data access frequency, popularity, and time sensitivity, and dynamically adjusts the caching strategy. For example, for data with a high access frequency, such as real-time monitoring data, it will be cached preferentially; for critical business data, such as equipment failure warning data, it will also be cached preferentially to ensure quick access to key information; while for data with high timeliness requirements, such as production progress update data, a shorter caching time will be set to ensure data real-time.

[0186] The machine learning model plays an important role in formulating the caching strategy. Based on historical data and real-time data, it predicts the future access patterns and importance of data, thereby adjusting the weight coefficients α, β, γ in the hybrid intelligent algorithm. For example, if the model predicts that the failure probability of a certain device will increase, the priority of the data related to this device in the cache will be increased to ensure that relevant data can be quickly obtained for processing when a failure occurs.

[0187] The service sub-platforms share the cache status information through a message queue or a distributed cache system to achieve the consistency and collaborative management of cached data. When a service sub-platform updates or deletes cached data, it will send a change notification to other service sub-platforms. For example, after service sub-platform B receives the cache status information of sub-service database A, if it finds that sub-service database A has already cached certain data, then service sub-platform B will decide not to cache these data repeatedly to avoid data redundancy and waste of storage space.

[0188] When the cached data is updated, the relevant service sub-platforms will synchronously update their cache views to maintain data consistency and real-time. For example, when a new batch of preliminary perception data arrives, sub-service database A will update its cache and notify service sub-platform B. After receiving the update notification, service sub-platform B will synchronize the new data to its own cache to ensure that all service sub-platforms can access the latest data.

[0189] The service platform continuously monitors the load conditions of all sub-service databases. When it is found that the load of a certain sub-service database suddenly increases, for example, the load of sub-service database B exceeds the preset threshold, the service platform will dynamically adjust the data flow direction and route a part of the data to the sub-service database C with a lower load. This adjustment is based on the consideration of load balancing, aiming to optimize the overall performance of the system and prevent the operation efficiency of the entire system from being affected due to the overload of a single sub-service database.

[0190] The above are only embodiments of the present invention, and common knowledge such as specific structures and characteristics known in the solutions is not described in detail herein. It should be noted that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can still be made, and these should also be regarded as the protection scope of the present invention, which will not affect the implementation effect of the present invention and the practicality of the patent. The protection scope required by this application should be subject to the content of its claims, and the specific implementation manners described in the specification can be used to interpret the content of the claims.

Claims

1. Industrial Internet of Things main service platform data analysis and coordination system, including: The user platform, service platform, management platform, sensor network platform and object platform are characterized by: The object platform includes a plurality of production devices, each of which is provided with a sensing unit and a control unit, wherein the sensing unit is used to collect physical quantities of equipment operation and product processing parameters, perform local preliminary screening and caching, mark urgent key data, remove invalid data and transmit to the sensor network platform to form preliminary sensing data; The sensor network platform includes multiple sensor network sub-platforms and corresponding sensor network databases, which are used to receive preliminary perception data, adaptively adjust the sampling frequency to prevent data transmission congestion, perform secondary screening and classification on the data, and store them in different databases according to rules, perform preliminary quantitative analysis and extract features, and send the preliminary perception data after integration and analysis to the management platform; The management platform includes multiple management sub-platforms and an independent management database, which is used to receive the preliminary perception data, conduct in-depth interpretation based on the knowledge graph, judge the equipment operation status, predict the failure risk, and store the preliminary perception data together with the equipment status, failure prediction, and resource allocation plan in the management database, and send it to the service platform after forming management data; The service platform adopts an optimized combination and post-fractional layout, including a main service database and several sub-service databases. Each sub-service database is connected to a corresponding service sub-platform and is equipped with an intelligent shunting collaborative cache mechanism. The main service database receives management data and summarizes and preliminarily classifies it, and distributes it to the sub-service database according to type and priority. The service sub-platform processes and mines data value in parallel, generates refined data service products and stores them in the sub-service database; The user platform is used to receive data from the sub-service database, and to track and update the load status of the sub-service database and issue an overtime delay threshold warning, helping users obtain useful data to guide decision-making and adjust processes. The user platform is also used to modify the sub-service database data and feed back requirements and instructions to the service platform to form a closed-loop collaborative process.

2. The data analysis and collaboration system of the main service platform of the industrial Internet of Things according to claim 1 is characterized by: The main service database or the management sub-platform is used to generate a timestamp while sending information to the user platform, and attach it to the information; the user platform is used to calculate the time delay between the time when the information from the sub-service database is actually received and the timestamp, and perform corresponding processing according to different ranges of the time delay, and the corresponding processing includes: When the latency is less than 30 milliseconds, the user platform displays information to the user that the service sub-platform is working normally; When the latency is between 30 milliseconds and 800 milliseconds, the user platform displays service sub-platform network abnormality information to the user; When the delay exceeds 800 milliseconds, the user platform accesses the service sub-platform and enters the fault handling mode.

3. The data analysis and collaboration system of the main service platform of the industrial Internet of Things according to claim 2 is characterized by: The user platform is further configured to perform the following steps in the fault handling mode: Calculate the delay growth rate between the starting delay and the final delay of the delay per unit time; When the delay growth rate is less than 0 or between 0 and 30%, the user platform continues to make judgments in the next unit time until the delay growth rate is not less than 0 or the fault handling mode is exited; When the latency growth rate is between 30% and 80%, the user platform generates service sub-platform network anomaly information to the user; When the delay growth rate is greater than 80%, the user platform generates fault information of the corresponding management sub-platform to the user.

4. The data analysis and collaboration system of the main service platform of the industrial Internet of Things according to claim 3 is characterized by: The local preliminary screening, caching, marking of urgent key data, removal of invalid data and transmission to the sensor network platform include the following: Conduct local preliminary screening of the collected data to remove irrelevant or redundant data; Cache filtered data and mark urgent and critical data; Remove invalid data, including erroneous data, extreme values, and missing data; The processed data is transmitted to the sensor network platform to form preliminary perception data; Among them, invalid data is removed by using a box plot to find outliers in the data and by replacing missing values; The MQTT protocol is used during the transmission process to adapt to low-bandwidth scenarios and achieve effective data transmission; Before data transmission, edge computing is performed to filter and aggregate the data for pre-processing.

5. The data analysis and collaboration system of the main service platform of the industrial Internet of Things according to claim 4 is characterized by: The sensor network platform adaptively adjusts the sampling frequency including the following contents: Set the acquisition duration, initial sampling frequency, maximum sampling frequency and detection window length; Generate a control signal according to the acquisition duration, the initial sampling frequency, the maximum sampling frequency and the detection window length, the amplitude and the period of the excitation signal; and sending the excitation signal to the sensor; The sensor works according to the excitation signal and outputs an analog signal; The sensor network platform generates a control signal according to the acquisition duration, initial sampling frequency, maximum sampling frequency, detection window length, amplitude and period of the excitation signal, and sends the control signal to the excitation module; at the same time, the analog signal output by the sensor is preprocessed, and the sampling frequency is adjusted in real time by using an adaptive sampling frequency adjustment algorithm for data acquisition; The sensor network platform is also used to calculate the sampling data change rate and cumulative change in the detection window by calculating the number of sampling points. By sliding the time window, the data change rate and cumulative change ratio in adjacent time windows are processed accordingly to adjust the real-time sampling frequency. When the data changes faster, the sampling frequency is increased; when the data changes slower, the sampling frequency is reduced.

6. The data analysis and collaboration system of the main service platform of the industrial Internet of Things according to claim 5 is characterized by: The intelligent offloading collaborative caching mechanism includes the following contents: The service sub-platform identifies and classifies the received preliminary perception data; The main service database intelligently selects the sub-service database for data routing based on real-time load and performance indicators; The service platform monitors the load of the sub-service database and dynamically adjusts the data flow to achieve load balancing; The sub-service database determines the data caching strategy based on the preset caching rules and intelligent algorithms; The service sub-platforms share cache status information through a collaborative mechanism and perform collaborative cache management; When the cached data is updated, the relevant service sub-platforms synchronously update their caches to maintain data consistency and real-time performance.

7. The data analysis and collaboration system of the main service platform of the industrial Internet of Things according to claim 6 is characterized by: The intelligent offloading and collaborative caching mechanism of the sub-service database and the service sub-platform includes: The sub-service database uses a preset hybrid intelligent algorithm of least recently used, least frequently used, and first-in-first-out to determine the data cache strategy; The service sub-platforms share cache status information through message queues or distributed cache systems to achieve consistency and collaborative management of cache data; The hybrid intelligent algorithm dynamically adjusts the cache strategy based on data access frequency, heat and time sensitivity; The collaborative cache management includes when a service sub-platform updates or deletes cache data, other service sub-platforms receive change notifications and update their own cache states to maintain data consistency; The cache strategy includes increasing the priority of frequently accessed data in the cache, giving priority to caching critical business data to reduce the caching of non-critical data, and setting a shorter cache time for data with high timeliness requirements.

8. The data analysis and collaboration system of the main service platform of the industrial Internet of Things according to claim 7 is characterized by: Sub-service database A receives the preliminary perception data from the sensor network platform and decides to cache the most recent preliminary perception data based on the preset cache rules and hybrid intelligent algorithm; The main service database monitors the load of all sub-service databases and intelligently routes the initial perception data to the sub-service database A with lower load; The service sub-platforms share cache status information through the distributed cache system. After receiving the cache status information of the sub-service database A, the service sub-platform B decides not to cache the data repeatedly. When a new batch of preliminary perception data arrives, sub-service database A updates its cache and notifies service sub-platform B. After receiving the update notification, service sub-platform B synchronously updates its cache view to maintain data consistency; The service platform monitors the load of all sub-service databases. When it finds that the load of sub-service database B suddenly increases, it dynamically adjusts the data flow and routes part of the data to sub-service database C with a lower load to achieve load balancing.

9. The data analysis and collaboration system of the main service platform of the industrial Internet of Things according to claim 8 is characterized by: The intelligent offloading collaborative caching mechanism includes: The sub-service database uses a hybrid intelligent algorithm of the preset least recently used LRU algorithm, the least frequently used LFU algorithm, and the first-in first-out FIFO algorithm, combined with a machine learning model to predict the data cache strategy. The specific formula is: The LRU algorithm sorts data based on access time and eliminates the least recently used data; The LFU algorithm sorts data based on access frequency and eliminates the data with the lowest access frequency; The FIFO algorithm eliminates the earliest data according to the time order in which the data enters the cache; The hybrid intelligent algorithm dynamically adjusts the cache strategy according to data access frequency F, heat H and time sensitivity T. The calculation formula is: C = αF + βH + γT, where α, β, and γ are weight coefficients, and α + β + γ = 1; The machine learning model predicts the future access pattern and importance of data based on historical data and real-time data, and adjusts the weight coefficients α, β, and γ to optimize the cache strategy; The main service database intelligently selects the sub-service database for data routing based on the real-time load L and performance index P, combined with the load trend and performance changes predicted by the prediction model. The selection formula is: S = f ( L , P , P pred), where f is the comprehensive evaluation function of load and performance indicators, P pred is the predicted performance change; The service platform monitors the load of the sub-service database and dynamically adjusts the data flow to achieve load balancing. The adjustment formula is: Δ D = k ( L max- L min)+Δ P pred, where ΔD is the data flow adjustment amount, k is the adjustment coefficient, Lmax and Lmin are the maximum and minimum loads of the sub-service database, Δ P pred is the load adjustment caused by the predicted performance change; The service sub-platforms share cache status information through message queues or distributed cache systems to achieve consistency and collaborative management of cache data. The sharing formula is: S sync= S 1∪ S 2∪…∪ Sn ,in S sync is a shared cache status information collection, S 1, S 2, ..., Sn Cache status information for each service platform; When the cached data is updated, the relevant service sub-platforms synchronously update their caches to maintain data consistency and real-time performance. The update formula is: C new= C old∪Δ C ,in C new is the updated cache data, C old is the cache data before update, Δ C For newly added or modified data; The cache strategy also includes increasing the priority of frequently accessed data in the cache, caching key business data first to reduce the cache of non-key data, and setting a shorter cache time for data with high timeliness requirements. The specific formula is: P = f ( F , K , T , P pred), where P is the priority of the data in the cache, F is the data access frequency, K is the key indicator of the data, and T is the timeliness requirement of the data. P pred is the predicted performance change, and f is the priority calculation function.

10. A data analysis and collaboration method for an industrial Internet of Things main service platform, characterized in that: A system as claimed in any one of claims 1 to 9 is employed.

Images