Data processing method and device, equipment, storage medium and program product

Abstract

The invention provides a data processing method and device, equipment, a storage medium and a program product, and relates to the technical field of Internet of Things. The method comprises the following steps: acquiring index data of Internet of Things equipment collected at a plurality of time points belonging to at least two time intervals, and obtaining an index threshold value according to a statistical average quantity of the index data collected at the corresponding time interval and an adjusting constant corresponding to the time interval, and removing abnormal data in the obtained index data according to the index threshold corresponding to the time interval to which the time point of the collected index data belongs, obtaining preprocessed index data, then analyzing the preprocessed index data, and providing a production decision for the Internet of Things equipment according to an analysis result. Therefore, the abnormal data in the collected index data of the Internet of Things equipment can be removed more accurately, and the function and efficiency of the Internet of Things equipment can be enhanced by better utilizing the AIoT technology.

Description

Technical Field

[0001] The present disclosure relates to the technical field of Internet of Things, and in particular to a data processing method, device, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] AIoT, or "Artificial Intelligence of Things", refers to a technological trend or concept that combines artificial intelligence (AI) technology with the Internet of Things (IoT). This combination aims to enhance the functionality and efficiency of IoT devices by leveraging AI technology, thereby achieving smarter data processing, decision making, and service provision. Although AIoT has great potential, many existing manufacturing companies still face many challenges in the implementation process. Issues such as the diversity of data collection, the complexity of data processing, and data security limit the effective application of AIoT technology.

[0003] As mentioned above, how to process the data of IoT devices to better utilize AIoT technology to enhance the functionality and efficiency of IoT devices has become an urgent problem to be solved.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present disclosure is to provide a data processing method, device, electronic device, readable storage medium and program product to better utilize AIoT technology to enhance the function and efficiency of Internet of Things devices.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] According to one aspect of the present disclosure, there is provided a data processing method, comprising: acquiring index data of an Internet of Things device collected at multiple time points, the multiple time points belonging to at least two time intervals; removing abnormal data in the acquired index data according to an index threshold corresponding to the time interval to which the time point of collecting the index data belongs, to obtain preprocessed index data, the index threshold being obtained according to a statistical average of the index data collected in the corresponding time interval and an adjustment constant corresponding to the time interval; and analyzing the preprocessed index data to provide a production decision for the Internet of Things device according to the analysis result.

[0008] According to one embodiment of the present disclosure, the indicator data of the Internet of Things device includes data of the target parameters of the Internet of Things device, and the at least two time intervals include the target time interval; the method also includes: obtaining a data set of the target parameter corresponding to the target time interval; and obtaining an indicator threshold of the target parameter in the target time interval based on the median of the data in the data set and the adjustment constant corresponding to the target time interval.

[0009] According to one embodiment of the present disclosure, the indicator threshold of the target parameter in the target time interval is obtained according to the median of the data in the data set and the adjustment constant corresponding to the target time interval, including: obtaining the average value of the deviation of each data in the data set from the median; obtaining the indicator threshold of the target parameter in the target time interval according to the average value and the adjustment constant corresponding to the target time interval.

[0010] According to one embodiment of the present disclosure, the indicator threshold of the target parameter in the target time interval is obtained according to the average value and the adjustment constant corresponding to the target time interval, including: obtaining the adjustment constant corresponding to the target time interval; obtaining the indicator threshold of the target parameter in the target time interval according to the median and the product of the average value and the adjustment constant.

[0011] According to an embodiment of the present disclosure, the index data of the Internet of Things device includes data of multiple parameters of the Internet of Things device; the preprocessed index data is analyzed to provide a production decision for the Internet of Things device based on the analysis results, including: based on the integrated learning technology, the preprocessed data of multiple parameters are input into a combined model to obtain a model prediction result, and the combined model integrates the production prediction model corresponding to each parameter of the multiple parameters; the analysis result is obtained according to the model prediction result to provide a production decision for the Internet of Things device.

[0012] According to an embodiment of the present disclosure, the preprocessed indicator data is analyzed to provide a production decision for the Internet of Things device based on the analysis result, including: inputting the preprocessed indicator data into a production prediction model to obtain a model prediction result, wherein the production prediction model is obtained by training based on transfer learning technology; and obtaining the analysis result based on the model prediction result to provide a production decision for the Internet of Things device.

[0013] According to an embodiment of the present disclosure, the method also includes: determining whether the preprocessed indicator data is sensitive data; if it is determined that the preprocessed indicator data is sensitive data, encrypting and transmitting the preprocessed indicator data using quantum encryption technology; analyzing the preprocessed indicator data to provide a production decision for the Internet of Things device based on the analysis results, including: decrypting and analyzing the encrypted preprocessed indicator data to provide a production decision for the Internet of Things device based on the analysis results.

[0014] According to one embodiment of the present disclosure, the method also includes: uploading a summary of the preprocessed indicator data to a blockchain network; encrypting and transmitting the preprocessed indicator data; uploading a summary of the transmission result data to the blockchain network; and comparing whether the summary of the preprocessed indicator data before transmission stored in the blockchain network is consistent with the summary of the transmission result data.

[0015] According to one embodiment of the present disclosure, the method also includes: determining whether the preprocessed indicator data is sensitive data; if it is determined that the preprocessed indicator data is sensitive data, storing the preprocessed indicator data on the first cloud platform; if it is determined that the preprocessed indicator data is non-sensitive data, storing the preprocessed indicator data on the second cloud platform.

[0016] According to another aspect of the present disclosure, there is provided a data processing device, including: an acquisition module, used to acquire indicator data of an Internet of Things device collected at multiple time points, wherein the multiple time points belong to at least two time intervals; a preprocessing module, used to remove abnormal data in the acquired indicator data according to an indicator threshold corresponding to the time interval to which the time point at which the indicator data is collected belongs, to obtain preprocessed indicator data, wherein the indicator threshold is obtained based on the statistical average of the indicator data collected in the corresponding time interval and an adjustment constant corresponding to the time interval; and an analysis module, used to analyze the preprocessed indicator data to provide production decisions for the Internet of Things device according to the analysis results.

[0017] According to another aspect of the present disclosure, an electronic device is provided, comprising: a memory, a processor, and executable instructions stored in the memory and executable in the processor, wherein the processor implements any of the above methods when executing the executable instructions.

[0018] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, and when the executable instructions are executed by a processor, any of the above methods is implemented.

[0019] The embodiments of the present disclosure provide a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0020] The data processing method provided by the embodiments of the present disclosure obtains indicator data of the Internet of Things device collected at multiple time points belonging to at least two time intervals, obtains the indicator threshold according to the statistical average of the indicator data collected in the corresponding time interval and the adjustment constant corresponding to the time interval, removes abnormal data in the obtained indicator data according to the indicator threshold corresponding to the time interval to which the time point of collecting the indicator data belongs, obtains preprocessed indicator data, and then analyzes the preprocessed indicator data to provide production decisions for the Internet of Things device according to the analysis results, so as to more accurately remove the abnormal data in the collected indicator data of the Internet of Things device, and better utilize AIoT technology to enhance the function and efficiency of the Internet of Things devices.

[0021] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other objects, features and advantages of the present disclosure will become more apparent by describing in detail example embodiments thereof with reference to the attached drawings.

[0023] Figure 1 A schematic diagram showing a system architecture in an embodiment of the present disclosure.

[0024] Figure 2 A flow chart of a data processing method in an embodiment of the present disclosure is shown.

[0025] Figure 3 A flow chart showing another data processing method in an embodiment of the present disclosure.

[0026] Figure 4 Shows Figure 3 FIG. 4 is a schematic diagram of the processing process of step S304 in one embodiment.

[0027] Figure 5 Shows Figure 4 FIG. 4 is a schematic diagram of the processing process of step S404 in one embodiment.

[0028] Figure 6 according to Figure 2 A schematic diagram of a data transmission process in an embodiment is shown.

[0029] Figure 7 according to Figure 2 A schematic diagram of a data transmission process in another embodiment is shown.

[0030] Figure 8 is a flowchart of yet another data processing method according to an exemplary embodiment.

[0031] Fig. 9 Shows Figure 2 FIG. 5 is a schematic diagram of the processing process of step S206 in one embodiment.

[0032] Fig.10 Shows Figure 2 FIG. 5 is a schematic diagram of the processing process of step S206 in another embodiment.

[0033] Fig.11 A block diagram of a data processing device in an embodiment of the present disclosure is shown.

[0034] Fig.12 A block diagram showing another data processing device in an embodiment of the present disclosure.

[0035] Fig.13 A schematic structural diagram of an electronic device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0036] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The accompanying drawings are only schematic illustrations of the disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0037] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, devices, steps, etc. may be adopted. In other cases, well-known structures, methods, devices, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0038] In addition, the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present disclosure, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. The symbol " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0039] In this disclosure, unless otherwise clearly specified and limited, terms such as "connection" should be understood in a broad sense, for example, it can be an electrical connection or can communicate with each other; it can be directly connected or indirectly connected through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in this disclosure can be understood according to specific circumstances.

[0040] Some technical terms involved in the present disclosure are explained below.

[0041] AIoT, or "Artificial Intelligence of Things", refers to a technological trend or concept that combines artificial intelligence (AI) technology with the Internet of Things (IoT). This combination aims to enhance the functionality and efficiency of IoT devices by leveraging AI technology, thereby achieving smarter data processing, decision-making and service provision. AIoT integrates AI technology and IoT technology, generates and collects massive amounts of data from different dimensions through the Internet of Things and stores them in the cloud and edge, and then realizes the digitization and intelligent connection of all things through big data analysis and higher forms of artificial intelligence. The ultimate goal of the integration of IoT technology and artificial intelligence is to form an intelligent ecological system, in which different intelligent terminal devices, different system platforms, and different application scenarios are interconnected and integrated. In addition to the need for continuous technological innovation, the research and development of technical standards and test standards related to AIoT, the implementation of related technologies, the promotion and large-scale application of typical cases are also important issues that need to be broken through in the field of IoT and artificial intelligence at this stage. AIoT technology = AI (artificial intelligence) + IoT (Internet of Things), which mainly includes two aspects: 1. Internet of Things (IoT): refers to physical devices, vehicles, household appliances, etc. that can collect and exchange data connected to the Internet. These devices are typically equipped with sensors, software, and other technologies to connect and exchange data. 2. Artificial Intelligence (AI): involves technologies that enable machines to perform tasks that require human intelligence, such as learning, reasoning, self-correction, etc. In AIoT, AI is used to analyze data collected from IoT devices to make predictions or decisions.

[0042] PLC (Programmable Logic Controller) is a digital computing and operating electronic system designed for industrial environments. It uses programmable memory to internally store instructions for executing logical operations, sequential control, timing, counting and arithmetic operations, and controls various types of machinery or production processes through digital or analog input and output.

[0043] ERP (Enterprise Resource Planning) is based on information technology and provides a management platform for decision-making and operation means for enterprise decision-makers and employees with systematic management ideas. It was proposed by Gartner Group in the United States in 1990. Enterprise Resource Planning is the next generation of manufacturing system and resource planning software of MRP (Manufacture Resource Planning) II. In addition to the existing production resource planning, manufacturing, finance, sales, procurement and other functions of MRP II, there are also quality management, laboratory management, business process management, product data management, inventory, distribution and transportation management, human resources management and regular reporting systems. In my country, the meaning of ERP has been expanded, and all kinds of software used in enterprises have been included in the scope of ERP. It jumps out of the boundaries of traditional enterprises and optimizes the resources of enterprises from the scope of supply chain. It is a new generation of information system based on the era of network economy. It is mainly used to improve the business processes of enterprises to enhance the core competitiveness of enterprises.

[0044] Blockchain technology is a new type of decentralized information technology. The data or information stored in the blockchain has the characteristics of "unforgeable", "full traceability", "traceability", "openness and transparency", and "collective maintenance". Based on these characteristics, blockchain technology has laid a solid "trust" foundation, created a reliable "cooperation" mechanism, and has broad application prospects.

[0045] A smart contract is a computer protocol designed to disseminate, verify or execute contracts in an information-based manner. Smart contracts allow for trusted transactions without a third party, which are traceable and irreversible. The purpose of smart contracts is to provide a security method superior to traditional contracts and reduce other transaction costs associated with contracts. A blockchain smart contract is a piece of code written on the blockchain that is automatically executed once an event triggers the terms of the contract. In other words, it is executed when the conditions are met, without the need for human control.

[0046] Ensemble learning is a machine learning method that generates the final prediction result by combining the prediction results of multiple models (usually called base models or weak models). The main purpose of this method is to improve the accuracy and robustness of the prediction and reduce the risk of overfitting by combining the power of multiple models.

[0047] Transfer learning is a machine learning method that improves the learning effect of another related task by using the knowledge learned on one task. This method is particularly suitable for situations where the target task data is small or difficult to obtain, because it can borrow a large amount of data and learned feature representations from the source task to improve the learning efficiency and performance of the target task.

[0048] Adaptive Decision Systems are intelligent systems that can continuously adjust and optimize their decision rules based on environmental changes and new data. Such systems usually combine machine learning, data mining, statistical analysis and other technologies to achieve the goal of continuously improving decision quality in a dynamic environment.

[0049] As a core component of Industry 4.0, AIoT uses the combination of artificial intelligence technology and Internet of Things technology to achieve real-time data collection, analysis and decision support in the production process. The introduction of this technology has brought new opportunities to the manufacturing industry.

[0050] However, despite the huge potential of AIoT, many existing manufacturing companies still face many challenges in the implementation process. Issues such as the diversity of data collection, the complexity of data processing, and data security limit the effective application of AIoT technology. Therefore, it is particularly important to build an AIoT system that integrates intelligent machines, real-time analysis, and secure transmission.

[0051] Therefore, the present invention proposes an intelligent manufacturing data processing method and system based on AIoT to realize the safe collection, analysis and utilization of IoT device data.

[0052] Figure 1 An exemplary system architecture 10 of an AIoT-based smart manufacturing processing system to which the data processing method or data processing device of the present disclosure may be applied is shown.

[0053] like Figure 1 As shown, the system architecture 10 may include a three-layer architecture: a device layer 102 , a network layer 104 , and an analysis layer 106 .

[0054] The device layer 102 can be used to implement data collection (S1022), data preprocessing (S1024) and data aggregation (S1026) based on AIoT. The relevant indicator data of IoT devices can be collected in a variety of ways. Some exemplary implementations of the types and methods of collecting indicator data can be referred to Figure 2 Step S202. Then, data preprocessing is performed by edge computing to improve data quality. Some exemplary implementations can be referred to Figure 2 Step S204.

[0055] A standardized data format can also be defined at the device layer 102 to achieve data aggregation. After preprocessing, various collected data are aggregated to integrate time series and spatial data. The following two exemplary data aggregation methods can be used:

[0056] (1) Edge computing aggregation: On edge devices close to the data source, edge computing is used to achieve preliminary data aggregation and analysis, reducing the amount of data transmission, and uploading key data to the cloud for in-depth analysis when necessary. Standardized application programming interfaces (APIs) and data formats are introduced to support unified processing of multiple data sources and reduce the complexity of data integration.

[0057] (2) Cloud computing aggregation: Upload large amounts of scattered data to the cloud for centralized storage and aggregation processing, and use the powerful computing power and storage resources of cloud computing to achieve complex data processing and aggregation tasks.

[0058] The network layer 104 can be used to implement data encryption (S1042), data transmission (S1044) and storage (S1046) of AIoT smart manufacturing. Advanced encryption technology can be used to ensure the security of data in transmission. Some exemplary implementations can be referred to Figure 2 Step S206. A hybrid storage architecture can be used to improve the security and performance of the system. Some exemplary implementations can be found in Figure 8 .

[0059] The analysis layer 106 can be used to implement data analysis modeling (S1062), real-time decision support (S1064) and feedback optimization (S1066) of AIoT intelligent manufacturing. By establishing a dynamically updated knowledge base and introducing an adaptive decision system, AI decision support is provided, and a closed-loop feedback system is established to continuously optimize the model. Some exemplary implementations can be referred to Figure 2 Step S208.

[0060] Figure 2 FIG. 1 is a flow chart of a data processing method according to an exemplary embodiment. Figure 2The method shown can be applied, for example, to Figure 1 System architecture 10 is shown.

[0061] refer to Figure 2 , the method 20 provided in the embodiment of the present disclosure may include the following steps S202 to S208.

[0062] In step S202, indicator data of the Internet of Things device collected at multiple time points is obtained, and the multiple time points belong to at least two time intervals.

[0063] In some embodiments, the indicator data of the IoT device may include data of multiple parameters of the IoT device, and the multiple parameters may include target parameters.

[0064] The data of multiple parameters of IoT devices may include the following types of data:

[0065] Production data: including output, production efficiency, production line status, etc.

[0066] Sensor data: temperature, pressure, vibration, humidity, position, voltage and current, including environmental data (such as air quality, noise level, light intensity, etc.);

[0067] Equipment status data: including operating time, maintenance records, fault records, etc.

[0068] Equipment attribute data: including equipment process parameters, quality data, energy consumption data and other data.

[0069] When preprocessing or other operations are performed on the data of a parameter of an IoT device, the parameter becomes the target parameter.

[0070] In some embodiments, various types of smart sensors (such as temperature, pressure, and vibration sensors) and edge devices can be used for real-time data collection. The frequency and type of data collection can be dynamically adjusted through intelligent algorithms to ensure that the most valuable data is collected under different production conditions. AI functions can also be integrated into sensors to determine when more data needs to be collected based on real-time analysis, thereby avoiding unnecessary data redundancy and improving the practicality of data.

[0071] In other embodiments, various production systems can be connected to build an adaptive data collection network to collect data from multiple data sources. For example, a PLC system used to control and monitor production equipment can be connected to build an adaptive data collection network to record various parameters in the production process. For another example, an ERP system used to integrate various business processes of an enterprise can be connected to build an adaptive data collection network to collect supply chain and inventory data.

[0072] In some embodiments, data related to intelligent manufacturing may be greatly affected by time factors. For example, data such as temperature and humidity are greatly affected by seasons, and data at different times of the day are also different; production data may be affected by peak seasons and off-seasons. The time for collecting data can be divided into at least two time intervals, and different data processing methods are used for different time intervals. For example, the time of each day can be divided into i time intervals: [t_1, t_2), [t_2, t_3), [t_3, t_4) ... [t_i, t_i+1); wherein the number of intervals i and the interval time span can be dynamically adjusted according to the specific actual situation. For another example, the time of each year can be divided into j time intervals [t_1', t_2'), [t_2', t_3'), [t_3', t_4') ... [t_j', t_j+1'), the interval time span can be, for example, a month, a quarter, etc., and the number of intervals j can also be adjusted accordingly. The at least two time intervals may include a target time interval. When data collected from a certain interval of the at least two time intervals is processed, the interval may be the target time interval.

[0073] In step S204, abnormal data in the acquired indicator data is removed according to the indicator threshold corresponding to the time interval to which the time point of collecting the indicator data belongs, so as to obtain the preprocessed indicator data, and the indicator threshold is obtained according to the statistical average of the indicator data collected in the corresponding time interval and the adjustment constant corresponding to the time interval.

[0074] In some embodiments, the collected indicator data can be cleaned and verified to ensure the quality of the data. Preprocessing is performed on data collected in different collection methods and from different systems to eliminate abnormal data and ensure data quality. For example, AI-driven intelligent data cleaning and feature extraction technology can be applied to achieve higher data quality by identifying and eliminating noise data in real time through deep learning models. Online learning mechanisms can be used to self-optimize AI-driven intelligent data cleaning models as data flows change, ensuring that efficient preprocessing capabilities are maintained when the production environment changes.

[0075] In some embodiments, it is possible to analyze and determine whether the data is abnormal based on different time intervals. For example, the abnormal data in the acquired indicator data can be removed based on the indicator threshold corresponding to the time interval to which the time point of the collected indicator data belongs. For example, the exemplary implementation method can refer to Figures 3 to 5 .

[0076] In some embodiments, the pre-processed indicator data can be encrypted and transmitted to the analysis layer through the network layer. For example, advanced quantum encryption technology can be combined to ensure the security of data during transmission, which is more forward-looking than traditional encryption methods and can resist future network security threats. Figure 6 .

[0077] In some embodiments, blockchain technology can be integrated into the network architecture to generate a unique hash value for each data transmission to ensure the immutability, traceability and integrity of the data. Figure 7 .

[0078] In step S206, the preprocessed indicator data is analyzed to provide production decisions for the IoT device based on the analysis results.

[0079] In some embodiments, ensemble learning and transfer learning techniques can be used to learn and transfer knowledge from different production scenarios to build a more accurate production prediction model to analyze indicator data. For example, see Fig. 9 and Fig.10 .

[0080] In some embodiments, a dynamically updated knowledge base may be established to acquire and store data features under different production environments in real time, continuously optimize the analysis model, and improve the accuracy of the model prediction.

[0081] In some embodiments, an adaptive decision-making system can be introduced to provide production decisions for IoT devices based on analysis results, and automatically adjust production scheduling, resource allocation, and quality control strategies based on real-time data streams. This dynamic response capability will significantly improve production efficiency. Through data visualization and interactive dashboards, operators can quickly understand the production status and provide intuitive decision support.

[0082] In some embodiments, a closed-loop feedback system can be built to monitor production results in real time and feed the results back to the AI ​​analysis layer to continuously optimize the analysis model and production process. Combined with industrial Internet technology, a real-time flow of production data and analysis results is formed, realizing full-link closed-loop management from data collection to decision execution.

[0083] According to the data processing method provided by the embodiment of the present disclosure, by acquiring the index data of the IoT device collected at multiple time points belonging to at least two time intervals, the abnormal data in the acquired index data is removed according to the index threshold corresponding to the time interval to which the time point of the collected index data belongs, and the pre-processed index data is obtained, and then the pre-processed index data is encrypted and transmitted, and the encrypted pre-processed index data is decrypted and analyzed to provide production decisions for the IoT device according to the analysis results, so that it can be analyzed and judged whether it is abnormal data for different time intervals, and the judgment accuracy of abnormal data of target parameters affected by temperature is improved, and the abnormal data in the collected index data of the IoT device is more accurately removed, and the quality of the analysis data is guaranteed. Since data quality is very important in the AIoT-driven intelligent manufacturing scenario, high-quality analysis data is the basis for more accurate and efficient analysis. The method provided by the present disclosure can effectively remove abnormal data and achieve better use of AIoT technology to enhance the function and efficiency of IoT devices.

[0084] Figure 3 FIG. 1 is a flow chart of another data processing method according to an exemplary embodiment. Figure 3 The method shown can be used, for example, in Figure 2 Executed before step S204, used to obtain the indicator threshold of a certain parameter in a certain time interval.

[0085] refer to Figure 3 The method 30 provided in the embodiment of the present disclosure may include the following steps S302 to S304.

[0086] In step S302, a data set of target parameters corresponding to the target time interval is obtained.

[0087] In some embodiments, the data set of the target parameter corresponding to the target time interval can be a data set of the same IoT device in the time period corresponding to the target time interval. For example, if the target time interval is the [t_p, t_p+1) (p∈[1,i]) time interval in a day as mentioned above, then the data of the target parameters of the IoT device in the [t_p, t_p+1) time interval of each day in the past several days (for example, one month, two months, half a year, etc.) can be obtained.

[0088] In some embodiments, the data set corresponding to the target parameter and the target time interval may be a data set of all IoT devices having the target parameter in the target time interval. For example, if the target time interval is the [t_p', t_p+1')(p∈[1,j]) time interval in a year as described above, then the data of the target parameters of all IoT devices having the target parameters for which data has been collected in the [t_p', t_p+1') time interval may be obtained.

[0089] In step S304, an indicator threshold of the target parameter in the target time interval is obtained according to the median of the data in the data set and the adjustment constant corresponding to the target time interval.

[0090] In some embodiments, taking a data set of a target parameter data (an indicator data, such as vibration frequency) collected in a time interval [t_p, t_p+1) as {X_m}, m∈1,2,3...n, as an example (the data set contains n data in total), the method for obtaining the median of the data set {X_m} can be:

[0091] Sort the data set {X_m} from small to large. (a) If the number of data points n is an odd number, the median is the middle number, denoted by: mid = X_mid; (b) If the number of data points n is an even number, the median is the average of the two middle numbers, denoted by: mid = (X_mid + X_mid) * 1 / 2.

[0092] In some embodiments, the average value of the absolute deviation of each data in the data set from the median can be obtained, and the index threshold of the target parameter in the target time interval can be obtained according to the average value and the adjustment constant corresponding to the target time interval. For example, see Figures 4 to 5 .

[0093] According to the method provided in the embodiment of the present disclosure, by obtaining a data set of the target parameter corresponding to the target time interval, the index threshold of the target parameter in the target time interval is obtained according to the median of the data in the data set and the adjustment constant corresponding to the target time interval. It is possible to determine the index threshold for judging abnormal data based on the statistical average of a large amount of data of the target parameter collected in the target time interval, thereby improving the accuracy of the determined index threshold, so that abnormal data can be removed more accurately in the preprocessing stage, thereby improving the quality of data used for analysis.

[0094] In other embodiments, other statistics of the data in the data set, such as arithmetic mean, weighted arithmetic mean, geometric mean, etc., can be selected based on the characteristics of the target parameter itself, thereby obtaining the index threshold of the target parameter in the target time interval. In the embodiments disclosed herein, the median is used as an example for description, but is not limited thereto.

[0095] Figure 4 Shows Figure 3 The processing process of step S304 in one embodiment is shown in FIG. Figure 4 As shown, in the embodiment of the present disclosure, the above step S304 may further include the following steps S402 to S404.

[0096] Step S402, obtaining the average value of the deviation between each data in the data set and the median.

[0097] Still taking the above data set {X_m} as an example, we can obtain the average value AD of the absolute deviation of each data point in the data set {X_m} from the median mid:

[0098]

[0099] Step S404: obtaining an index threshold of the target parameter in the target time interval according to the average value and the adjustment constant corresponding to the target time interval.

[0100] In some embodiments, an adjustment constant corresponding to the target interval can be obtained, and an index threshold of the target parameter in the target time interval can be obtained according to the adjustment constant and the average absolute deviation. For example, see Figure 5 .

[0101] According to the method provided in the embodiment of the present disclosure, by obtaining the average value of the absolute deviations of each data in the data set from the median, the indicator threshold of the target parameter in the target time interval is obtained according to the average value of the absolute deviations and the adjustment constant corresponding to the target time interval, thereby improving the accuracy of the determined indicator threshold, thereby more accurately removing abnormal data in the preprocessing stage and improving the quality of data used for analysis.

[0102] Figure 5 Shows Figure 4 The processing process of step S404 in one embodiment is shown in FIG. Figure 5 As shown, in the embodiment of the present disclosure, the above step S404 may further include the following steps.

[0103] Step S502, obtaining an adjustment constant corresponding to the target time interval.

[0104] In some embodiments, different adjustment constants may be set for different time intervals according to the characteristics of the target parameter in the target time interval. For example, in the case where the value of the target parameter may fluctuate due to the influence of temperature, since the temperature difference in summer is small and the temperature difference in winter is large, the value of the adjustment constant in the summer time interval may be set to be smaller than the value of the adjustment constant in the winter time interval.

[0105] In some embodiments, the value of the adjustment constant can be dynamically adjusted according to different data types and other actual situations, or can be set according to empirical values, and continuously iterated and optimized in actual work. For example, when the target parameter is the vibration data of the equipment, the adjustment constant K1 is initially set. After a period of actual work, it is found that the prediction effect of failures caused by vibration is poor and the accuracy is low. By increasing the adjustment constant to K2, it is found that the prediction accuracy is improved after working for a period of time again, which indicates that a suitable optimization scheme has been adopted.

[0106] Step S504, obtaining the index threshold of the target parameter in the target time interval according to the product of the median and the average value and the adjustment constant.

[0107] In some embodiments, the average value of the absolute deviation can be multiplied by the adjustment constant, and then the median of the data set can be subtracted and added to obtain the lower limit and upper limit of the indicator threshold of the target parameter in the target time interval. Still taking the data set {X_m} of the target parameter in the above time interval [t_p, t_p+1) as an example, its average value of absolute deviation is AD, and the adjustment constant k corresponding to the time interval [t_p, t_p+1) is obtained. It can be defined that if the absolute deviation of a data point of a certain target parameter collected in the time interval [t_p, t_p+1) from its median mid is greater than k*AD, then the data point is considered to be an outlier, which can be expressed as:

[0108] (a) If |X_m-AD|>k*AD, then X_m is an outlier;

[0109] (b) If |X_m-AD|≤k*AD, then X_m is a normal value.

[0110] In other embodiments, based on the statistical distribution of the data set, other mathematical methods can be used to calculate the indicator threshold according to the average value of the absolute deviation and the adjustment constant. For example, the average value of the absolute deviation can be multiplied by the adjustment constant raised to the power of the natural constant e, and then divided or multiplied by the median of the data set to obtain the lower limit and upper limit of the indicator threshold of the target parameter in the target time interval.

[0111] According to the method provided in the embodiment of the present disclosure, by obtaining the indicator threshold of the target parameter in the target time interval based on the average value and the adjustment constant corresponding to the target time interval, it is possible to analyze and determine whether it is abnormal data for different time intervals, thereby improving the accuracy of judging abnormal data of the target parameter affected by temperature, so that abnormal data can be removed more accurately in the preprocessing stage, thereby improving the quality of data used for analysis.

[0112] Figure 6 according to Figure 2 FIG. 2 shows a schematic diagram of a data transmission process in an embodiment. Figure 6As shown, in the embodiment of the present disclosure, referring to steps S602 to S606, the pre-processed indicator data may be encrypted and transmitted, and step S208 may further include the following step S608.

[0113] Step S602, determining whether the pre-processed indicator data is sensitive data.

[0114] In some embodiments, sensitive data may be, for example, indicator data related to user privacy, indicator data marked as non-public by the user, etc. Whether the indicator data is sensitive data may be determined by using labels of IoT devices, labels of indicator data, and the like.

[0115] Step S604: If it is determined that the preprocessed indicator data is sensitive data, the preprocessed indicator data is encrypted and transmitted using quantum encryption technology.

[0116] In some embodiments, quantum encryption communication uses quantum mechanical phenomena such as quantum superposition, measurement collapse, and quantum entanglement to theoretically provide unbreakable information security. If traditional electromagnetic wave information is encrypted based on quantum entangled states, coupled entangled particles can be sent to the receiver and sender of the information at the same time. In this way, any eavesdropping will cause the quantum state to collapse, and the receiver and sender will immediately know that the transmitted information has been eavesdropped. Only when there is no quantum state collapse is the information transmission considered safe.

[0117] Step S606: If it is determined that the pre-processed indicator data is non-sensitive data, the pre-processed indicator data is encrypted and transmitted using conventional encryption technology.

[0118] In some embodiments, conventional encryption technology may be, for example, traditional symmetric encryption technology, asymmetric encryption technology, and the like.

[0119] Step S608, decrypting the encrypted transmitted pre-processed indicator data and analyzing it to provide production decisions for the IoT device based on the analysis results.

[0120] According to the method provided in the embodiment of the present disclosure, by adopting different encryption technologies for sensitive data and non-sensitive data, the security of sensitive data transmission can be enhanced while controlling the cost of data transmission.

[0121] Figure 7 according to Figure 2 FIG. 2 shows a schematic diagram of a data transmission process in another embodiment. Figure 7 As shown, in the embodiment of the present disclosure, referring to step S702 to step S708, the integrity of data transmission can be ensured by storing the preprocessed indicator data on the blockchain.

[0122] Step S702, uploading the summary of the preprocessed indicator data to the blockchain network.

[0123] In some embodiments, the data summary may be a unique hash value of the data, which may be stored by uploading the hash value of the data to the blockchain network.

[0124] Step S704: encrypt and transmit the preprocessed index data.

[0125] Step S706, uploading a summary of the transmission result data to the blockchain network.

[0126] Step S708, comparing the summary of the pre-transmission pre-processed indicator data stored in the blockchain network with the summary of the transmission result data to see if they are consistent.

[0127] In some embodiments, when it is determined that the hash values ​​of the data before and after the transmission are consistent, it can be determined that the data has not been tampered with during the transmission process and that the transmitted data is complete.

[0128] According to the method provided by the embodiment of the present disclosure, by combining blockchain in the transmission network architecture, the data summary is stored in the blockchain, and then the hash value of the data before and after the transmission is compared to see if it is consistent, it can be determined whether the data has been tampered with during the transmission process and the data integrity, thereby ensuring the data's immutability, traceability and integrity.

[0129] Figure 8 FIG. 1 is a flowchart of another data processing method according to an exemplary embodiment. Figure 8 The method shown can be used, for example, to store preprocessed indicator data and apply Figure 1 The network layer 104 in.

[0130] refer to Figure 8 , the method 80 provided in the embodiment of the present disclosure may include the following steps.

[0131] In step S802, it is determined whether the pre-processed indicator data is sensitive data.

[0132] The implementation of step S802 in some exemplary embodiments may refer to step S702 .

[0133] In step S804, if it is determined that the preprocessed indicator data is sensitive data, the preprocessed indicator data is stored in the first cloud platform.

[0134] In step S806, if it is determined that the preprocessed indicator data is non-sensitive data, the preprocessed indicator data is stored in the second cloud platform.

[0135] In some embodiments, a hybrid storage architecture can be used to store sensitive data and non-sensitive data separately to improve the security and performance of the system. Smart contracts can be introduced to automatically manage data access permissions to ensure that only authorized users can access sensitive information.

[0136] According to the method provided in the embodiment of the present disclosure, a multi-cloud storage solution is used, and data is stored in a dispersed manner on different cloud platforms according to access frequency and security requirements, thereby enhancing the flexibility and reliability of the system.

[0137] Fig. 9 Shows Figure 2 The processing process of step S206 in one embodiment is shown in FIG. Fig. 9 As shown, in the embodiment of the present disclosure, the above step S206 may further include the following steps.

[0138] Step S902, based on the integrated learning technology, the preprocessed data of multiple parameters are input into the combined model to obtain the model prediction result, and the combined model integrates the production prediction model corresponding to each parameter of the multiple parameters.

[0139] In some embodiments, the data of multiple parameters may include multiple parameters of different dimensions such as temperature, pressure, vibration, flow, etc.

[0140] Step S904, obtaining analysis results based on the model prediction results to provide production decisions for the IoT devices.

[0141] According to the method provided in the embodiment of the present disclosure, production decisions are provided by combining the prediction results of multiple models, which utilizes the concept of "collective wisdom", that is, the collective judgment of multiple evaluators or models is often better than the judgment of a single evaluator, which can improve the overall prediction performance.

[0142] Fig.10 Shows Figure 2 FIG. 1 is a schematic diagram of the processing process of step S206 in another embodiment. Fig.10 As shown, in the embodiment of the present disclosure, the above step S206 may further include the following steps.

[0143] Step S1002, input the preprocessed indicator data into the production prediction model to obtain the model prediction result, and the production prediction model is obtained by training based on the transfer learning technology.

[0144] In some embodiments, most data or tasks are related, and transfer learning can be used to share the learned model parameters with the new model in some way to speed up and optimize the learning efficiency of the model. For example, in the production data prediction scenario of different parts such as wheels and engines, a prediction model can be generated based on transfer learning technology to improve efficiency.

[0145] Step S1004, obtaining analysis results based on the model prediction results to provide production decisions for the IoT devices.

[0146] According to the method provided in the embodiment of the present disclosure, the learned model parameters are shared with the new model in some way through transfer learning to speed up and optimize the learning efficiency of the model, which can effectively reduce the dependence on a large amount of labeled data and adapt to different production environments.

[0147] Taking the scenario in which an automobile parts manufacturing enterprise improves its overall production capacity through AIoT intelligent transformation as an example, some steps of the enterprise implementing the method provided by the embodiment of the present disclosure may be as follows:

[0148] 1) Data collection:

[0149] Smart sensors, including temperature, pressure, vibration and flow sensors, are installed at key nodes of the production line to monitor equipment status and production environment in real time. The sensors transmit data to edge computing devices for preliminary data processing and storage.

[0150] 2) Data preprocessing:

[0151] AI-driven data cleaning algorithms are used to remove abnormal data and noise in real time to ensure data accuracy. Deep learning models are used to extract features from the collected data to generate data sets that can be used for subsequent analysis.

[0152] 3) AI analysis:

[0153] Build a predictive maintenance model to identify potential signs of equipment failure through historical equipment data analysis and issue maintenance warnings in advance. Implement real-time production scheduling optimization, adjust production plans based on real-time data, improve resource utilization, and reduce idle time.

[0154] 4) Decision support:

[0155] Provides a real-time data visualization platform, where operators can intuitively view production status, equipment operation and key performance indicators. The system automatically adjusts the production process based on the analysis results and provides optimization suggestions to operators to improve decision-making efficiency.

[0156] The system layered architecture provided by the embodiment of the present disclosure includes equipment, network and analysis layers, and a complete data link and analysis method are designed to provide an efficient solution for AIoT smart manufacturing. Through efficient data processing and secure data transmission and storage methods, full use of industrial equipment data in smart manufacturing is achieved, production efficiency and safety are improved, and strong support is provided for the intelligent transformation of enterprises. The main advantages also include:

[0157] 1) Efficient data processing: Use AIoT to quickly process and analyze massive amounts of data from devices, providing instant feedback and decision support;

[0158] 2) Autonomous decision-making capability: AIoT systems can make optimal decisions without human intervention, improving response speed and accuracy;

[0159] 3) Improved user experience: By learning user habits and preferences, AIoT can provide more personalized and convenient services;

[0160] 4) Reduce costs and increase efficiency: By optimizing resource allocation and preventive maintenance, AIoT helps reduce operating costs and maintenance expenses.

[0161] Fig.11 FIG. 1 is a block diagram of a data processing device according to an exemplary embodiment. Fig.11 The example shown can be applied to Figure 1 System architecture 10 is shown.

[0162] refer to Fig.11 The device 110 provided in the embodiment of the present disclosure may include an acquisition module 1102 , a preprocessing module 1104 , and an analysis module 1106 .

[0163] The acquisition module 1102 may be used to acquire indicator data of the IoT device collected at multiple time points, where the multiple time points belong to at least two time intervals.

[0164] The preprocessing module 1104 can be used to remove abnormal data in the acquired indicator data according to the indicator threshold corresponding to the time interval to which the time point of collecting the indicator data belongs, and obtain the preprocessed indicator data. The indicator threshold is obtained according to the statistical average of the indicator data collected in the corresponding time interval and the adjustment constant corresponding to the time interval.

[0165] The analysis module 1106 can be used to analyze the preprocessed indicator data to provide production decisions for the IoT device based on the analysis results.

[0166] Fig.12 FIG. 1 is a block diagram of another data processing device according to an exemplary embodiment. Fig.12 The device shown can be used, for example, Figure 1 System architecture 10 is shown.

[0167] refer to Fig.12 The device 120 provided in the embodiment of the present disclosure may include an acquisition module 1202, a preprocessing module 1204, a transmission module 1206, an analysis module 1208, an acquisition module 1210 and a storage module 1212.

[0168] The acquisition module 1202 may be used to acquire indicator data of the IoT device collected at multiple time points, where the multiple time points belong to at least two time intervals.

[0169] The indicator data of the IoT device may include data of target parameters of the IoT device, and the at least two time intervals may include a target time interval.

[0170] The indicator data of the IoT device may also include data of multiple parameters of the IoT device.

[0171] The acquisition module 1210 may be used to acquire a data set of the target parameter corresponding to the target time interval; and obtain an indicator threshold of the target parameter in the target time interval according to the median of the data in the data set.

[0172] The acquisition module 1210 can also be used to obtain the average value of the deviation between each data in the data set and the median; and obtain the indicator threshold of the target parameter in the target time interval according to the average value.

[0173] The acquisition module 1210 may also be used to obtain an adjustment constant corresponding to the target time interval; and obtain an indicator threshold of the target parameter in the target time interval according to the average value and the adjustment constant.

[0174] The preprocessing module 1204 may be used to remove abnormal data from the acquired indicator data according to an indicator threshold corresponding to a time interval to which a time point at which the indicator data is collected belongs, to obtain preprocessed indicator data.

[0175] The transmission module 1206 may be used to encrypt and transmit the pre-processed indicator data.

[0176] The transmission module 1206 can also be used to determine whether the preprocessed indicator data is sensitive data; if it is determined that the preprocessed indicator data is sensitive data, the preprocessed indicator data is encrypted and transmitted using quantum encryption technology.

[0177] The transmission module 1206 can also be used to upload a summary of the preprocessed indicator data to the blockchain network; encrypt and transmit the preprocessed indicator data; upload a summary of the transmission result data to the blockchain network; the method also includes: comparing whether the summary of the preprocessed indicator data before transmission stored in the blockchain network is consistent with the summary of the transmission result data.

[0178] The storage module 1212 can be used to determine whether the preprocessed indicator data is sensitive data; if the preprocessed indicator data is determined to be sensitive data, the preprocessed indicator data is stored in the first cloud platform; if the preprocessed indicator data is determined to be non-sensitive data, the preprocessed indicator data is stored in the second cloud platform.

[0179] The analysis module 1208 can be used to decrypt the pre-processed indicator data transmitted in encrypted form and then analyze it to provide production decisions for the IoT device based on the analysis results.

[0180] The analysis module 1208 can also be used to decrypt the encrypted transmission of pre-processed data of multiple parameters; based on the integrated learning technology, the decrypted pre-processed data of multiple parameters is input into the combined model to obtain the model prediction result, and the combined model integrates the production prediction model corresponding to each parameter in the multiple parameters; the analysis result is obtained according to the model prediction result to provide production decisions for the Internet of Things device.

[0181] The analysis module 1208 can also be used to decrypt the pre-processed indicator data that is encrypted and transmitted; input the decrypted pre-processed indicator data into the production prediction model to obtain the model prediction results, and the production prediction model is obtained by training based on the transfer learning technology; obtain the analysis results based on the model prediction results to provide production decisions for the Internet of Things devices.

[0182] The specific implementation of each module in the device provided by the embodiment of the present disclosure can refer to the content of the above method, which will not be repeated here.

[0183] Fig.13 The following is a schematic diagram showing the structure of an electronic device in an embodiment of the present disclosure. It should be noted that: Fig.13 The device shown is only an example of a computer system, which should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0184] like Fig.13 As shown, the device 1300 includes a central processing unit (CPU) 1301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1302 or a program loaded from a storage part 1308 into a random access memory (RAM) 1303. In the RAM 1303, various programs and data required for the operation of the device 1300 are also stored. The CPU 1301, the ROM 1302, and the RAM 1303 are connected to each other via a bus 1304. An input / output (I / O) interface 1305 is also connected to the bus 1304.

[0185] The following components are connected to the I / O interface 1305: an input section 1306 including a keyboard, a mouse, etc.; an output section 1307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1308 including a hard disk, etc.; and a communication section 1309 including a network interface card such as a LAN card, a modem, etc. The communication section 1309 performs communication processing via a network such as the Internet. A drive 1310 is also connected to the I / O interface 1305 as needed. A removable medium 1311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1310 as needed, so that a computer program read therefrom is installed into the storage section 1308 as needed.

[0186] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part 1309, and / or installed from a removable medium 1311. When the computer program is executed by a central processing unit (CPU) 1301, the above-mentioned functions defined in the system of the present disclosure are executed.

[0187] It should be noted that the computer-readable medium shown in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0188] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0189] The modules involved in the embodiments described in the present disclosure may be implemented by software or by hardware. The modules described may also be set in a processor. For example, they may be described as: a processor includes an acquisition module, a preprocessing module, a transmission module, and an analysis module. The names of these modules do not, in some cases, constitute a limitation on the modules themselves. For example, the acquisition module may also be described as a "module for acquiring indicator data of IoT devices collected at multiple time points."

[0190] As another aspect, the present disclosure further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device implements:

[0191] Obtain indicator data of an IoT device collected at multiple time points, where the multiple time points belong to at least two time intervals; remove abnormal data in the acquired indicator data according to an indicator threshold corresponding to the time interval to which the time point of collecting the indicator data belongs, to obtain preprocessed indicator data; encrypt and transmit the preprocessed indicator data; decrypt the encrypted and transmitted preprocessed indicator data and perform analysis to provide production decisions for the IoT device based on the analysis results.

[0192] The embodiments of the present disclosure provide a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0193] The exemplary embodiments of the present disclosure are specifically shown and described above. It should be understood that the present disclosure is not limited to the detailed structures, configurations or implementations described herein; on the contrary, the present disclosure is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended claims.

Claims

1. A data processing method, characterized in that: include: Obtaining indicator data of an IoT device collected at multiple time points, where the multiple time points belong to at least two time intervals; Removing abnormal data from the acquired indicator data according to an indicator threshold corresponding to a time interval to which the time point of collecting the indicator data belongs, to obtain preprocessed indicator data, wherein the indicator threshold is obtained according to a statistical average of the indicator data collected in the corresponding time interval and an adjustment constant corresponding to the time interval; The preprocessed indicator data is analyzed to provide production decisions for the Internet of Things device according to the analysis results.

2. The method according to claim 1, characterized in that The indicator data of the IoT device includes data of a target parameter of the IoT device, and the at least two time intervals include a target time interval; The method further comprises: Acquire a data set of the target parameter corresponding to the target time interval; The indicator threshold of the target parameter in the target time interval is obtained according to the median of the data in the data set and the adjustment constant corresponding to the target time interval.

3. The method according to claim 2, characterized in that Obtaining an index threshold of the target parameter in the target time interval according to the median of the data in the data set and an adjustment constant corresponding to the target time interval includes: Obtaining an average value of the deviations of each data in the data set from the median; An indicator threshold of the target parameter in the target time interval is obtained according to the average value and an adjustment constant corresponding to the target time interval.

4. The method according to claim 3, characterized in that Obtaining an index threshold of the target parameter in the target time interval according to the average value and an adjustment constant corresponding to the target time interval includes: Obtaining an adjustment constant corresponding to the target time interval; The index threshold of the target parameter in the target time interval is obtained according to the product of the median and the mean value and the adjustment constant.

5. The method according to any one of claims 1 to 4, characterized in that: The indicator data of the IoT device includes data of multiple parameters of the IoT device; Analyzing the preprocessed indicator data to provide a production decision for the IoT device according to the analysis result, including: Inputting the preprocessed data of the plurality of parameters into a combined model based on an integrated learning technology to obtain a model prediction result, wherein the combined model integrates production prediction models corresponding to each parameter of the plurality of parameters; The analysis result is obtained according to the prediction result of the model to provide production decision for the Internet of Things device.

6. The method according to any one of claims 1 to 4, characterized in that Analyzing the preprocessed indicator data to provide a production decision for the IoT device according to the analysis result, including: Inputting the preprocessed indicator data into the production prediction model to obtain the model prediction result, wherein the production prediction model is obtained by training based on the transfer learning technology; The analysis result is obtained according to the prediction result of the model to provide production decision for the Internet of Things device.

7. The method according to any one of claims 1 to 4, characterized in that Also includes: Determining whether the preprocessed indicator data is sensitive data; If it is determined that the pre-processed indicator data is sensitive data, the pre-processed indicator data is encrypted and transmitted using quantum encryption technology; Analyzing the preprocessed indicator data to provide a production decision for the IoT device according to the analysis result, including: The encrypted transmission of the pre-processed indicator data is decrypted and analyzed to provide production decisions for the Internet of Things device based on the analysis results.

8. The method according to any one of claims 1 to 4, characterized in that Also includes: Uploading a summary of the preprocessed indicator data to a blockchain network; Encrypting and transmitting the preprocessed index data; Uploading a summary of the transmission result data to the blockchain network; Compare whether the summary of the preprocessed indicator data before transmission stored in the blockchain network is consistent with the summary of the transmission result data.

9. The method according to any one of claims 1 to 4, characterized in that: Also includes: Determining whether the preprocessed indicator data is sensitive data; If it is determined that the preprocessed indicator data is sensitive data, storing the preprocessed indicator data in the first cloud platform; If it is determined that the preprocessed indicator data is non-sensitive data, the preprocessed indicator data is stored in the second cloud platform.

10. A data processing device, characterized in that: include: An acquisition module, used to acquire indicator data of IoT devices collected at multiple time points, where the multiple time points belong to at least two time intervals; A preprocessing module, used to remove abnormal data in the acquired indicator data according to an indicator threshold corresponding to the time interval to which the time point of collecting the indicator data belongs, to obtain the preprocessed indicator data, wherein the indicator threshold is obtained according to the statistical average of the indicator data collected in the corresponding time interval and the adjustment constant corresponding to the time interval; The analysis module is used to analyze the preprocessed indicator data to provide production decisions for the Internet of Things device according to the analysis results.

11. An electronic device, comprising: A memory, a processor, and executable instructions stored in the memory and executable in the processor, wherein the processor implements the method according to any one of claims 1 to 9 when executing the executable instructions.

12. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that: When the executable instructions are executed by a processor, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images