Industrial Internet of Things service information processing system and method based on service cloud platform

Abstract

The present invention provides an industrial Internet of Things service information processing system and method based on a service cloud platform, the system includes an industrial Internet of Things subsystem and a service cloud platform. The industrial Internet of Things subsystem includes an industrial Internet of Things user platform, an industrial Internet of Things service platform, an industrial Internet of Things management platform, an industrial Internet of Things sensor network platform, and an industrial Internet of Things perception control platform; the industrial Internet of Things user platform is configured to receive application data and upload it to the industrial Internet of Things service platform; the industrial Internet of Things service platform is configured to generate second data and upload it to the service cloud platform; the industrial Internet of Things management platform is configured to determine monitoring operation instructions and send them to the industrial Internet of Things perception control platform; the industrial Internet of Things perception control platform is configured to obtain and upload first data to the industrial Internet of Things service platform; the service cloud platform is configured to determine service data and recommend operation data. The above system and method can provide users with more accurate service data.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial Internet of Things, and in particular to an industrial Internet of Things service information processing system and method based on a service cloud platform. Background Art

[0002] The Industrial Internet of Things has become a key force in promoting the intelligent transformation of the manufacturing industry. In the production line based on the Industrial Internet of Things, various sensors, intelligent devices and control systems are interconnected to form a highly integrated, data-driven production system. However, how to extract and classify user features; how to prioritize and process different users and different service information; how to obtain service data from different Industrial Internet of Things, classify, extract features, and apply them to ensure the stable operation and global scheduling of the production line have become important challenges faced in the actual application of the Industrial Internet of Things.

[0003] In view of this, it is hoped to provide an industrial Internet of Things service information processing system and method based on a service cloud platform, which can provide users with more accurate service data as a reference. Summary of the invention

[0004] One or more embodiments of the present specification provide an industrial Internet of Things service information processing system based on a service cloud platform, including an industrial Internet of Things subsystem and a service cloud platform; the industrial Internet of Things subsystem includes an industrial Internet of Things user platform, an industrial Internet of Things service platform, an industrial Internet of Things management platform, an industrial Internet of Things sensor network platform, and an industrial Internet of Things perception control platform; the industrial Internet of Things user platform is configured to receive user application data, upload the application data to the industrial Internet of Things service platform, and display the service data to the user in response to receiving the service data; the industrial Internet of Things service platform is configured to perform desensitization processing based on first data to generate second data, and upload the second data and the application data to the service cloud platform, the first data being data generated during the production process; the service cloud platform includes edge devices, central devices, a service database, and a control center, the control center is configured to: determine calculation parameters based on the application data, the calculation parameters include at least one of edge computing and central computing The target computing terminal is controlled to execute, based on the target database, the computing parameters: determining the service data based on the second data and the application data, the service data being data of at least one data type provided to the user; determining the recommended operation data based on the service data and the application data, the recommended operation data including the operation parameters of the monitoring device, the operation parameters including at least one of the data upload frequency and the data accuracy; sending the recommended operation data and the service data to the industrial Internet of Things service platform; the industrial Internet of Things management platform is configured to determine the monitoring operation instruction based on the recommended operation data in response to receiving the operation execution instruction sent by the industrial Internet of Things user platform, and send the monitoring operation instruction to the industrial Internet of Things perception control platform; the industrial Internet of Things perception control platform includes the monitoring device, the monitoring device is deployed in the production line, and is configured to monitor the production process based on the monitoring operation instruction to obtain and upload the first data to the industrial Internet of Things service platform.

[0005] One or more embodiments of the present specification provide an industrial Internet of Things service information processing method based on a service cloud platform, the method being executed by an industrial Internet of Things service information processing system, including: an industrial Internet of Things user platform receiving user application data, uploading the application data to the industrial Internet of Things service platform, and displaying the service data to the user in response to receiving the service data; the industrial Internet of Things service platform performing desensitization processing based on first data to generate second data, and uploading the second data and the application data to the service cloud platform, the first data being data generated during the production process; a control center of the service cloud platform determining calculation parameters based on the application data, the calculation parameters including at least one of edge calculation and center calculation; the control center controlling a target calculation terminal to execute, based on a target database, the following based on the second data: According to the service data and the application data, the service data is determined, and the service data is data of at least one data type provided to the user; based on the service data and the application data, the recommended operation data is determined, and the recommended operation data includes the operation parameters of the monitoring device, and the operation parameters include at least one of data upload frequency and data accuracy; the recommended operation data and the service data are sent to the industrial Internet of Things service platform; in response to receiving the operation execution instruction sent by the industrial Internet of Things user platform, the industrial Internet of Things management platform determines the monitoring operation instruction based on the recommended operation data, and sends the monitoring operation instruction to the industrial Internet of Things perception control platform; the monitoring device of the industrial Internet of Things perception control platform monitors the production process based on the monitoring operation instruction to obtain and upload the first data to the industrial Internet of Things service platform.

[0006] In some embodiments of the present specification, by determining the corresponding service data based on the application data, second data, etc. of different users, combined with the user's permissions and the importance of the data, and then pushing the service data based on the user's priority, the permissions and preferences of different users can be taken into account to determine service data that better meets actual needs, and further determine more reasonable recommended operating data, so as to facilitate more targeted monitoring of the production process later. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0008] Figure 1 It is a system structure diagram of an industrial Internet of Things service information processing system based on a service cloud platform according to some embodiments of this specification;

[0009] Figure 2is an exemplary flow chart of an industrial Internet of Things service information processing method based on a service cloud platform according to some embodiments of this specification;

[0010] Figure 3 is an exemplary flow chart of determining service data according to some embodiments of this specification;

[0011] Figure 4 is an exemplary schematic diagram of determining user priority according to some embodiments of this specification;

[0012] Figure 5 It is an exemplary schematic diagram of determining recommended operating data according to some embodiments of this specification. DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, without paying creative work, this specification can also be applied to other similar scenarios based on these drawings.

[0014] It should be understood that the "system" and / or "device" used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. If other words can achieve the same purpose, the words can be replaced by other expressions.

[0015] Generally speaking, the terms "include" and "comprises" only indicate the inclusion of explicitly identified steps and elements, and these steps and elements do not constitute an exclusive list, and the method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0017] Some embodiments of the present specification provide an industrial Internet of Things service information processing system and method based on a service cloud platform, which can classify data from different production lines and different users according to data from multiple industrial physical network subsystems, balance the needs of different users, and use limited computing resources to provide more targeted services.

[0018] Figure 1 It is a system structure diagram of an industrial Internet of Things service information processing system based on a service cloud platform as shown in some embodiments of this specification.

[0019] In some embodiments, the industrial Internet of Things service information processing system 100 based on the service cloud platform may include at least one industrial Internet of Things subsystem 120 and a service cloud platform 110. The industrial Internet of Things subsystem 120 is a system for receiving recommended operation data, service data and generating transmission application data and second data. In some embodiments, the industrial Internet of Things subsystem 120 includes an industrial Internet of Things user platform 121, an industrial Internet of Things service platform 122, an industrial Internet of Things management platform 123, an industrial Internet of Things sensor network platform 124, and an industrial Internet of Things perception control platform 125.

[0020] The IIoT user platform 121 is a platform for interacting with users. In some embodiments, the IIoT user platform 121 is configured to receive application data from users, upload the application data to the IIoT service platform 122, and display the service data to the users in response to receiving the service data.

[0021] In some embodiments, the industrial Internet of Things user platform 121 can be a platform based on electronic devices such as computers and mobile phones.

[0022] The industrial Internet of Things service platform 122 is a platform for communicating with the service cloud platform 110. In some embodiments, the industrial Internet of Things service platform 122 is configured to perform desensitization processing based on the first data, generate second data, and upload the second data to the service cloud platform.

[0023] The IIoT management platform 123 is a platform for managing and controlling the IIoT subsystem 120. In some embodiments, the IIoT management platform 123 is configured to, in response to receiving an operation execution instruction from the IIoT user platform, determine a monitoring operation instruction based on the recommended operation data, and send the monitoring operation instruction to the IIoT perception control platform.

[0024] The IIoT sensor network platform 124 is a network used for data transmission in the IIoT subsystem 120. In some embodiments, the IIoT sensor network platform 124 is configured with a communication device or a server.

[0025] The industrial Internet of Things perception control platform 125 is a platform for monitoring and controlling the production process. In some embodiments, the industrial Internet of Things perception control platform 125 includes a monitoring device. The monitoring device is a device for monitoring the production process, for example, it may include a current sensor, a gas metering device, etc. In some embodiments, the monitoring device is deployed in the production line and is configured to monitor the production process based on the monitoring operation instruction to obtain and upload the first data to the industrial Internet of Things service platform.

[0026] In some embodiments, any platform in the industrial Internet of Things subsystem 120 may be configured with a processor configured to execute program instructions to perform one or more functions described in this specification. In some embodiments, the processor may include one or more sub-processing devices. As an example only, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction processor (ASIP), a graphics processing unit (GPU), etc., or any combination thereof.

[0027] The service cloud platform 110 can be used to manage resources and process data and / or information from at least one of its own components or external data sources (e.g., cloud data centers). In some embodiments, the service cloud platform 110 can be configured with a single server or a server group, and the server group can be centralized or distributed. In some embodiments, the service cloud platform 110 can be implemented on a cloud platform or provided in a virtual manner. By way of example only, the service cloud platform 110 can include a private cloud, a public cloud, a hybrid cloud, etc., or any combination thereof.

[0028] In some embodiments, the service cloud platform 110 may include edge devices, central devices, a service database, and a control center.

[0029] Edge devices refer to data processing devices deployed in production lines. Central devices refer to data processing devices deployed in the center of a system that communicates with production lines. In some embodiments, edge devices and central devices may include computer devices that servers rely on. In some embodiments, central devices may communicate with terminal devices in production lines.

[0030] The service database is a database for storing relevant data of the industrial Internet of Things subsystem. In some embodiments, the service cloud platform 110 may include multiple service databases, which are respectively deployed in edge devices and / or central devices.

[0031] The control center is a component used to control the target computing terminal to perform data calculation and processing. In some embodiments, the control center is configured to determine the calculation parameters based on the application data; control the target computing terminal to perform the following based on the target database with the calculation parameters: determine the service data based on the second data and the application data; determine the recommended operation data based on the service data and the application data; and send the recommended operation data and service data to the industrial Internet of Things service platform. Among them, the target computing terminal is an edge device or a central device for performing edge computing or remote computing.

[0032] In some embodiments, the edge devices, central devices, and control centers may be configured with processors.

[0033] In some embodiments of this specification, enterprises can realize the interaction of multiple different industrial Internet of Things subsystems through the service cloud platform, realize conditional sharing of data from different industrial Internet of Things, and improve the overall production effect. The service cloud platform pushes service data to users based on different application data, which can improve service quality.

[0034] The above description of the industrial Internet of Things service information processing system 100 based on the service cloud platform is only for the convenience of description and cannot limit this specification to the scope of the embodiments. For those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the various platforms of the industrial Internet of Things subsystem 120 without deviating from this principle, or to form a subsystem connected with other platforms.

[0035] Figure 2 This is an exemplary flow chart of an industrial Internet of Things service information processing method based on a service cloud platform according to some embodiments of this specification.

[0036] In some embodiments, the Industrial Internet of Things user platform receives the user's application data, uploads the application data to the Industrial Internet of Things service platform, and displays the service data to the user in response to receiving the service data; the Industrial Internet of Things service platform performs desensitization processing based on the first data to generate second data, and uploads the second data and the application data to the service cloud platform; the control center of the service cloud platform determines the calculation parameters based on the application data; the control center controls the target computing terminal to execute based on the target database with the calculation parameters: determine the service data based on the second data and the application data; determine the recommended operation data based on the service data and the application data; send the recommended operation data and the service data to the Industrial Internet of Things service platform; the Industrial Internet of Things management platform determines the monitoring operation instruction based on the recommended operation data in response to receiving the operation execution instruction sent by the Industrial Internet of Things user platform, and sends the monitoring operation instruction to the Industrial Internet of Things perception control platform; the monitoring device of the Industrial Internet of Things perception control platform monitors the production process based on the monitoring operation instruction to obtain and upload the first data to the Industrial Internet of Things service platform.

[0037] like Figure 2 As shown, process 200 includes the following steps. In some embodiments, process 200 can be performed by an industrial Internet of Things service information processing system. Steps S210, S220, S250, and S260 are performed by the industrial Internet of Things subsystem, and steps S230 to S240 are performed by the service cloud platform.

[0038] Step S210: the industrial Internet of Things user platform receives the user's application data, uploads the application data to the industrial Internet of Things service platform, and displays the service data to the user in response to receiving the service data.

[0039] Application data refers to data that a user applies to view. In some embodiments, the application data may include the user who made the application, the type of data applied for by the user, etc. The data type may be at least one of the name of the production line product, the production line output, the operation status of the production line, etc. The operation status of the production line may include operation, pause, shutdown, etc.

[0040] In some embodiments, the industrial Internet of Things user platform can receive the user's application data through a terminal or server used by the user, and upload the received user's application data to the industrial Internet of Things service platform through the network.

[0041] Service data refers to data provided to the user based on the application data. In some embodiments, the service data may include data of at least one data type provided to the user. In some embodiments, the service cloud platform may send the service data determined based on the application data to the industrial Internet of Things service platform, and the industrial Internet of Things service platform may then send the service data to the industrial Internet of Things user platform.

[0042] In some embodiments, the industrial Internet of Things user platform can display the service data to the user in response to receiving the service data. In some embodiments, the industrial Internet of Things user platform can push service data to the user based on the user priority, see Figure 4 Related description.

[0043] In some embodiments, the service data may also include a data priority of a data type. In some embodiments, the industrial Internet of Things user platform may determine a data display order of data in the service data according to the data priority in the service data; and display the service data to the user based on the data display order.

[0044] Data priority refers to an indicator that characterizes the importance of a data type. The larger the value, the more important the data type. Data priority can be preset by a technician. In some embodiments, data priority can also be determined based on data level scoring, see Figure 3 Related description.

[0045] The data display order refers to the order in which data is displayed to the user.

[0046] In some embodiments, the industrial Internet of Things user platform can sort data of different data types in the service data from high to low according to the data priority in the service data as the data display order.

[0047] In some embodiments, the industrial Internet of Things user platform may display the data in the service data to the user in a data display order.

[0048] In some embodiments of the present specification, by setting corresponding data priorities for different data types, a more reasonable data display order can be determined, so that the service data is displayed to the user in a more organized manner, thereby improving the user experience.

[0049] Step S220: The industrial Internet of Things service platform performs desensitization processing based on the first data to generate second data, and uploads the second data and the application data to the service cloud platform.

[0050] The first data is data generated during the production process. In some embodiments, the first data may include data of at least one data type.

[0051] The second data refers to the first data after desensitization. Desensitization is a data processing process to prevent data leakage. In some embodiments, desensitization can be implemented based on a desensitization function. For example, the industrial Internet of Things service platform can use a desensitization function to truncate, encrypt or hide data in certain fields of the first data to implement desensitization.

[0052] In some embodiments, the industrial Internet of Things service platform responds to receiving the application data uploaded by the industrial Internet of Things user platform and sends the application data to the service cloud platform for subsequent processing, see steps S241 and Figure 3 Related instructions.

[0053] In some embodiments, the industrial Internet of Things service platform may send the recommended operating data and service data to the industrial Internet of Things user platform in response to receiving the recommended operating data and service data sent by the service cloud platform.

[0054] Step S230: The control center of the service cloud platform determines the calculation parameters based on the application data.

[0055] The computing parameters are parameters that characterize the selected computing method. In some embodiments, the computing parameters may include at least one of edge computing and central computing. Edge computing refers to computing performed at or near the physical location of the user or data source, away from the center of the system. Central computing refers to computing performed by computer equipment based on a communication center.

[0056] In some embodiments, the control center can determine the calculation parameters in a variety of ways based on the application data. For example, the control center can determine the calculation complexity based on the type of data requested by the user in the application data, determine the average response time based on historical data, and then determine the calculation parameters based on the calculation complexity and the average response time. For example, the more complex the complexity, the longer the average response time, and the central calculation is used, otherwise the edge calculation is used.

[0057] For example, the control center can calculate the total number of data types of application data. The greater the number, the higher the calculation complexity. For all users with the same data type of application data, the control center can calculate the average response time based on the historical response time from the submission of application data to the delivery of service data, and then perform weighted average of the calculation complexity and average response time. When the result exceeds the preset calculation threshold, the central calculation is used, otherwise the edge calculation is used. The weight of the weighted average can be preset by the technician.

[0058] Step S240, the control center controls the target computing terminal to execute steps S241 to S243 based on the target database and the calculation parameters.

[0059] The target computing terminal refers to a terminal that performs computing processing. In some embodiments, the target computing terminal can be selected based on computing parameters. For example, if the computing parameter is edge computing, the control center selects the edge device closest to the target computing database (physical distance) for computing; if the computing parameter is central computing, the control center selects the central device for computing.

[0060] The target database is a database composed of historical data related to the application data. In some embodiments, the control center can filter out historical data corresponding to the data type contained in the application data from the historical application service data, and use the set of corresponding historical data with user satisfaction meeting the standard as the target database. If the user's satisfaction exceeds the satisfaction threshold, it is determined that the user's satisfaction meets the standard. In some embodiments, the user's satisfaction can be obtained based on the user's feedback, or it can be determined based on the number of subsequent similar applications. For details, see Figure 5 Related instructions.

[0061] Step S241, determining service data based on the second data and the application data.

[0062] In some embodiments, the control center can determine the service data in a variety of ways based on the second data and the application data. For example, the control center can check the data types that the user has checked in the past based on the user who made the application in the application data, determine the intersection of the data types in the application data and the data types that the user has checked in the past as the data types included in the service data of the user, and then check the value of the corresponding data type in the second data, and use the value as the data of the corresponding data type of the service data.

[0063] Step S242, determining recommended operation data based on the service data and application data.

[0064] Recommended operating data refers to the relevant parameters of the monitoring device that are recommended to be set. In some embodiments, the recommended operating data may include at least one operating parameter of the monitoring device.

[0065] In some embodiments, the recommended operating data includes at least one operating parameter of the monitoring device. In some embodiments, the operating parameter of the monitoring device may include at least one of data upload frequency and data accuracy. The data accuracy may be represented by the number of digits after the decimal point.

[0066] In some embodiments, before the user sends an operation execution instruction, the operation parameters of the monitoring device may be preset default values.

[0067] In some embodiments, the control center can determine the recommended operation data based on the service data and the application data in a variety of ways. For example, if the data types of the service data and the application data are quite different, such as the data types in the application data have little intersection with the data types that the user has viewed in the past, the control center can increase the data upload frequency and data accuracy of each data type provided to the user based on a preset range.

[0068] For example, the user's application data includes data types A, B, and C. Data type A is the data of the upstream production line, and the user has no access authority. The data types of the service data include B and C, which are the data of the downstream production line. The user can infer the value of data type A based on the data of the downstream production line. At this time, the control center improves the data accuracy and data upload frequency of the monitoring device, so that the user can make a more accurate calculation.

[0069] Step S243: Send the recommended operation data and service data to the industrial Internet of Things service platform.

[0070] Step S250, the industrial Internet of Things management platform determines a monitoring operation instruction based on the recommended operation data in response to receiving the operation execution instruction sent by the industrial Internet of Things user platform, and sends the monitoring operation instruction to the industrial Internet of Things perception control platform.

[0071] The operation execution instruction is an instruction that allows the recommended operation data to be adopted. In some embodiments, after obtaining the recommended operation data and service data, the user can send the operation execution instruction through the industrial Internet of Things user platform.

[0072] The monitoring operation instruction is an instruction used to guide the operation of the monitoring device.

[0073] In some embodiments, the IIoT management platform may determine the monitoring operation instruction in a variety of ways based on the recommended operation data in response to receiving the operation execution instruction from the IIoT user platform. For example, after receiving the operation execution instruction, the IIoT management platform may obtain the recommended operation data from the IIoT service platform, and based on the operation parameters included in the recommended operation data, determine the operation parameters of the monitoring device in the currently managed IIoT subsystem as the monitoring operation instruction, and send it to the IIoT perception control platform.

[0074] In step S260, the monitoring device of the industrial Internet of Things perception control platform monitors the production process based on the monitoring operation instruction to obtain and upload the first data to the industrial Internet of Things service platform.

[0075] In some embodiments, the monitoring device of the industrial Internet of Things perception control platform applies the operating parameters of the monitoring device to the corresponding monitoring device based on the monitoring operation instructions to monitor the production process.

[0076] In some embodiments, the industrial Internet of Things perception control platform can monitor the production process based on a monitoring device, obtain first data, and upload it to the industrial Internet of Things service platform.

[0077] In some embodiments of the present specification, interaction with multiple different industrial Internet of Things systems can be achieved through a service cloud platform, so as to improve the overall production effect. At the same time, by determining the service data based on different second data and application data, and then determining the recommended operation data, the user experience can be improved by improving the overall data quality.

[0078] Figure 3 is an exemplary flow chart of determining service data according to some embodiments of this specification. Figure 3 As shown, the process 300 includes the following steps. In some embodiments, the process 300 can be executed by a control center.

[0079] In some embodiments, the control center is further configured to: determine a user authority score based on user characteristics of the user; determine a data level score of the second data; determine a target data pool based on the user authority score, application data, and data level score; determine service data based on the target data pool, user characteristics, user authority score, and data level score.

[0080] Step S310, determining a user authority score based on the user characteristics of the user.

[0081] User characteristics are data that reflect the identity or habit characteristics of a user.

[0082] In some embodiments, user characteristics may include job title level, historical decision-making characteristics, managed production line type, etc. The job title level may be represented by an integer, and the larger the value, the higher the job title level.

[0083] The historical decision feature can be represented by the average number of data types that the user has made in the past. For example, when a user makes a decision in the past, he or she can generally make a decision by looking at data of two data types, so the historical decision feature of the user is 2.

[0084] The types of production lines managed can include automatic, non-automatic, semi-automatic, etc.

[0085] The user authority score is data that represents the user's authority level. The higher the user authority score, the more data types the user can access.

[0086] In some embodiments, the control center can determine the user authority score based on the user's user characteristics in a variety of ways. For example, the control center can use the professional title level in the user characteristics as the basic value. If the professional title level is the highest level, the professional title level can be directly used as the user authority score of the user. If the professional title level is not the highest level, the basic value can be increased based on historical decision-making characteristics, the type of production line managed, etc. The larger the value of the historical decision-making characteristics and the more non-automatic the type of production line managed, the higher the increase.

[0087] Step S320: determine the data grade score of the second data.

[0088] The data level score is data that reflects the importance of a data type. The higher the data level score corresponding to a data type, the higher the required user authority level.

[0089] In some embodiments, the data level score includes a level corresponding to at least one data type in the second data. In some embodiments, the granularity of the data level score and the user authority score needs to be aligned.

[0090] In some embodiments, the control center can determine the data grade score of the second data in a variety of ways. For example, for a data type of the second data, the control center can use the production line grade of the second data as the base value. If the production line grade is the highest, the base value can be directly used as the data grade score of the data type. If the production line grade is not the highest, the base value is increased according to the relative importance of the data type. The greater the value of the relative importance, the greater the increase. Among them, the production line grade can be preset manually to represent the importance of the production line.

[0091] In some embodiments, the relative importance can be determined based on the number of times the data type is viewed and the average user authority score of users who view the data type. For example, the control center can determine the production line based on the following formula (1): The following data types The relative importance of :

[0092]

[0093] in, Indicates the data type, Represents the production line, Indicates production line Medium data type Number of data accesses, Indicates production line Data Types The average user permission score of users.

[0094] Step S330, determining the target data pool based on the user authority score, application data, and data level score.

[0095] The target data pool refers to a collection of data that can be consulted by the user. In some embodiments, for the same data type, multiple copies of data with different data upload frequencies and data precisions may be stored, and the target data pool may be a database containing data of all data precisions and data upload frequencies.

[0096] In some embodiments, the control center can determine the target data pool in a variety of ways based on the user authority score, application data, and data level score. For example, the control center can determine the data that matches the data level score of the second data according to the user authority score of the user, and use the intersection of the data type of the part of the data and the application data as the data set corresponding to the user, and the data set corresponding to all users who are currently applying as the target data pool.

[0097] The data that matches the data level score of the second data is determined according to the user authority score of the user, and refers to the data in the second data whose data level score is less than or equal to the user authority score.

[0098] Step S340, determining service data based on the target data pool, user characteristics, user authority score, and data level score.

[0099] In some embodiments, the control center can determine the service data in a variety of ways based on the target data pool, user characteristics, user authority score, and data level score. For example, for each data type of the data set corresponding to the user in the target data pool, the control center can count the number of times that the data type appears in the historical service data, and use the top N data types with the highest number of times as the relevant data types of the data type, and count the data types with a data level score less than the user authority score among the relevant data types of all data types of the data set corresponding to the user into the relevant data set of the user, and determine the data of the data set corresponding to the user in the target data pool and the data of the relevant data set of the user as the service data corresponding to the user, and N can be positively correlated to the difference between the historical decision-making features in the user characteristics and the number of data types in the target data pool.

[0100] In some embodiments, the control center is further configured to determine the service data through the service data model based on the target data pool, user characteristics, user authority score, data level score, and application data.

[0101] The service data model is a model for determining service data. In some embodiments, the service data model may be a machine learning model. For example, the service data model may be a neural network model (NN). In some embodiments, the input of the service data model may include a target data pool, user characteristics, user authority rating, data level rating, and application data, and the output may be service data.

[0102] In some embodiments, the service data model may be obtained based on a large number of training samples with training labels.

[0103] The training samples may be the preferred historical data in the historical data, including the sample target data pool, sample user characteristics corresponding to the sample users, sample user authority scores and sample application data, and sample data grade scores corresponding to the sample second data. The preferred historical data refers to the historical data corresponding to the time when the user feedback satisfaction is high and the production line has no abnormality.

[0104] The training labels may be historical actual service data corresponding to the sample users, and may be automatically labeled by the control center based on the historical data.

[0105] In some embodiments, the control center may input a large number of training samples into the initial service data model, construct a loss function based on the output of the initial service data model and the training labels corresponding to the training samples, and iteratively update the initial service data model based on the loss function; when the value of the loss function meets the iteration completion condition, the training is completed. The iteration completion condition may include the convergence of the loss function, the number of iterations reaching a threshold, etc.

[0106] In some embodiments of the present specification, by training a service data model using preferred historical data in historical data, a more accurate service data model can be obtained. By determining the service data through the service data model, the service data can be determined more efficiently and accurately, thereby improving the user experience.

[0107] In some embodiments, the input to the service data model may also include production data sequences.

[0108] The production data sequence is a sequence of second data uploaded to the service cloud platform within a preset time period. The preset time period refers to a period of time before the current time, which can be preset manually.

[0109] In some embodiments, when the input of the service data model includes a production data sequence, the control center may add a sample production data sequence of a preset time period before the corresponding time of the sample second data to the training sample when training the service data model, and then train the service data model.

[0110] In some embodiments of the present specification, by adding a production data sequence to the input of the service data model, real-time change information of the production line can be provided, and more accurate service data can be provided for production lines with faster real-time changes.

[0111] In some embodiments, during the training process of the service data model, different training sample sets have different learning rates, and the learning rate of the training sample set is related to the historical accident rate of the training sample set.

[0112] The learning rate is a parameter used to control the magnitude of weight updates when training a model. In some embodiments, the learning rate is a parameter used in neural network training and can be 0.0 to 1.0. The weight is a parameter used to calculate the relationship between input samples and output samples when training a model.

[0113] The historical accident rate refers to the frequency of accidents in the history of the sample production line corresponding to the training sample. In some embodiments, accidents occurring on the production line may include empty production line, overflow of goods at the front end of the production line, etc.

[0114] In some embodiments, the control center may divide the training samples into multiple training sample sets based on the range of the historical accident rates of the training samples. For example, the control center may divide the historical accident rates into multiple ranges, and divide the training samples into corresponding training sample sets according to the ranges of the historical accident rates corresponding to them.

[0115] In some embodiments, the learning rate of the training sample set may be negatively correlated to the historical accident rate of the training sample set, for example, the greater the average historical accident rate of the training sample set, the smaller the corresponding learning rate. The greater the historical accident rate of the production line, the more potential impacts the production line involves in various aspects. It is more important to learn the implicit rules of such training samples, and the learning rate of such training samples can be appropriately reduced.

[0116] In some embodiments of the present specification, by mapping different training sample sets to different learning rates, the training of the service data model can be made more accurate, the ability of the service data model to handle complex problems can be improved, and the trained service data model can output more accurate service data.

[0117] In some embodiments of the present specification, by determining the user's user authority score and the data level score of the second data, combining the application data to determine the target data pool, and then determining the service data, it is possible to ensure the security of the entire system while enabling the service data to meet the user's data needs as much as possible within limited authority restrictions.

[0118] It should be noted that the above description of the process 200 and the process 300 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process 200 and the process 300 under the guidance of this specification. These modifications and changes are still within the scope of this specification.

[0119] Figure 4 This is an exemplary schematic diagram of determining user priority according to some embodiments of this specification.

[0120] In some embodiments, Figure 4 As shown, the industrial Internet of Things user platform is further configured to: determine a user push order 420 according to a user priority 410 in the service data; and push service data to a user 430 based on the user push order 420 .

[0121] User priority refers to the priority of information processing corresponding to a user. In some embodiments, a batch of applications in the same period includes application data of multiple users, and the user priority corresponding to each user needs to be determined.

[0122] User push order refers to the order in which service data is pushed to users.

[0123] In some embodiments, the control center can determine the user push order in a variety of ways according to the user priority in the service data. For example, the control center can sort the users from high to low according to the user priority as the user push order.

[0124] In some embodiments, the control center may push service data to users in sequence based on the user push order.

[0125] In some embodiments, the control center is further configured to: determine service urgency 460 based on user characteristics 440 and application data 450 of the user; and determine user priority 410 based on service urgency 460 and user authority score 470 .

[0126] Service urgency is an indicator that measures how eager users are to apply for services.

[0127] In some embodiments, the control center can determine the service urgency in a variety of ways based on the user's user characteristics and application data. For example, the control center can determine the service urgency based on the type of production line managed by the user, the number of data types included in the application data, and the relationship between the historical decision features in the user characteristics.

[0128] For example, the more automatic the type of production line managed by the user is, the faster the production line may change; the more the number of data types contained in the application data exceeds the user's historical decision-making characteristics, the more uncertain the user may be about how to make a decision. Therefore, the more automatic the managed production type is, and the more the number of data types contained in the application data exceeds the historical decision-making characteristics, the higher the service urgency.

[0129] In some embodiments, service urgency may also be positively correlated to service time cost.

[0130] Service time cost refers to the time cost of calling the data required to serve users.

[0131] In some embodiments, the control center can calculate the sum of the average call time of each data type based on the data type contained in the application data corresponding to the user and the historical data statistics of the average call time of each data type as the service time cost.

[0132] In some embodiments, the higher the service time cost, the higher the service urgency can be set.

[0133] In some embodiments of the present specification, by positively correlating service urgency with service time cost, the time cost of data calls can be taken into account, and applications with higher service time costs can be processed first to prevent reduced data processing efficiency due to insufficient computing resources.

[0134] In some embodiments, service urgency is also positively correlated to service time efficiency loss, which is determined based on historical service data.

[0135] Service time loss can reflect the expected loss caused by service delay.

[0136] The historical service data may include historical actual service delay time and production loss. The service delay time refers to the time difference between the time when the service data is determined and the time when the application data is received. The production loss can be represented by the product of the reduced output during the service delay and the value of the unit output.

[0137] In some embodiments, the control center can determine the service time loss based on historical service data in a variety of ways. For example, the control center can use the service delay time as an independent variable and the corresponding production loss as a dependent variable, select multiple pairs of data for fitting, determine the service loss function, and then substitute the historical average service delay time into the service loss function to obtain the service time loss.

[0138] In some embodiments, the higher the service time loss is, the higher the service urgency can be set.

[0139] In some embodiments of the present specification, the service urgency of users with higher service time loss is increased, so that applications of users who may cause greater losses can be processed preferentially, thereby improving user satisfaction.

[0140] In some embodiments, the control center can determine the user priority in a variety of ways based on the service urgency and the user authority score. For example, the control center can set a higher user priority for a user with a higher service urgency and a higher user authority score.

[0141] In some embodiments of the present specification, by dividing user priorities, tasks with high service urgency can be given priority. The decisions of users with high user priorities are often more important. Giving priority to the application data of such users can maintain the reliability of the overall decision-making of the system.

[0142] Figure 5 It is an exemplary schematic diagram of determining recommended operating data according to some embodiments of this specification.

[0143] In some embodiments, Figure 5 As shown, the control center is further configured to: determine the user's expected satisfaction 530 based on the service data 510 and the application data 450; and determine the recommended operating data 550 based on the expected satisfaction 530 and the current operating parameters 540 of the monitoring device.

[0144] Expected satisfaction is the estimated user satisfaction with the service data.

[0145] In some embodiments, the control center can determine the expected satisfaction of the user based on the service data and application data in a variety of ways. For example, the control center can construct a feature vector based on the service data and application data of the user, match the feature vector in a standard database, use the standard vector with the highest similarity as the target vector, and determine the expected satisfaction of the user based on the label corresponding to the target vector. The similarity can be calculated based on cosine distance, Euclidean distance, etc.

[0146] The standard database includes standard vectors and their corresponding labels. The standard vectors are constructed based on historical data. For example, the service data, application data, and subsequent actual satisfaction in the historical data are constructed into vectors for clustering to form a preset number of cluster centers. The service data and application data corresponding to each cluster center are constructed into standard vectors, and the subsequent actual satisfaction corresponding to the standard vector is used as the label corresponding to the standard vector.

[0147] In some embodiments, the subsequent actual satisfaction can be determined by the number of similar applications made by the user. The more similar applications are made, the less the actual satisfaction is. For example, the control center can use the inverse of the number of similar applications + 1 as the subsequent actual satisfaction. Similar applications refer to applications in which the overlap of data types in the application data is greater than the overlap threshold.

[0148] In some embodiments, the control center is further configured to determine expected satisfaction 530 through a satisfaction prediction model 520 based on the service data 510 and the application data 450 .

[0149] The satisfaction prediction model is a model for determining expected satisfaction. In some embodiments, the satisfaction prediction model may be a machine learning model. For example, the satisfaction prediction model may be a neural network model. In some embodiments, the input of the satisfaction prediction model may include service data and application data, and the output may be expected satisfaction.

[0150] In some embodiments, the satisfaction prediction model can be obtained based on a large number of feature training samples with feature labels. The feature training samples can be sample service data and sample application data of sample users in historical data, and the feature labels can be the historical actual satisfaction of the sample users. The method for determining the historical actual satisfaction is similar to the method for determining the subsequent actual satisfaction described above.

[0151] The training method of the satisfaction prediction model is similar to that of the service data model. Figure 3 Related description.

[0152] In some embodiments of the present specification, by using a satisfaction prediction model to determine the user's expected satisfaction, the user's satisfaction can be more accurately predicted, so that the recommended operating data of the monitoring device can be adjusted more reasonably in the future to improve the user experience.

[0153] In some embodiments, the input of the satisfaction prediction model may also include user characteristics. For a description of user characteristics, see Figure 3 The corresponding description.

[0154] In some embodiments, when the input of the satisfaction prediction model includes user features, the control center may add sample user features of sample users to feature training samples when training the satisfaction prediction model, and then perform training.

[0155] In some embodiments of the present specification, by adding user characteristics as input to the satisfaction prediction model, the user characteristics can be taken into account to determine a more accurate expected satisfaction, so as to subsequently determine more accurate recommended operation data.

[0156] In some embodiments, the control center can determine the recommended operating data in a variety of ways based on the expected satisfaction and the current operating parameters of the monitoring device. For example, if the user's expected satisfaction is less than a preset threshold, the control center can adjust the monitoring device corresponding to the current data type. For example, based on the current operating parameters of the corresponding monitoring device, the data upload frequency can be appropriately increased and the data accuracy can be improved. The greater the gap between the expected satisfaction and the preset threshold, the greater the adjustment range. Among them, the current data type refers to the data type contained in the current service data, and the corresponding monitoring device refers to the monitoring device used to obtain data of these data types.

[0157] When the user's expected satisfaction is low, the monitoring device can be adjusted to improve the accuracy of the data. In some embodiments of this specification, by estimating the expected satisfaction corresponding to the service data and appropriately adjusting the corresponding monitoring device, more and more accurate data can be provided to improve user satisfaction.

[0158] The basic concepts have been described above. For those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation of this specification. Those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, and such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0159] At the same time, this specification uses specific words to describe the embodiments of this specification. "Some embodiments" means a feature related to at least one embodiment of this specification. Certain features in one or more embodiments of this specification can be appropriately combined.

[0160] Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification.

[0161] In order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. This disclosure method does not mean that the features required by the subject of this specification are more than the features mentioned in the claims.

[0162] In some embodiments, the numerical parameters used in the specification are approximate values, which may vary depending on the desired characteristics of individual embodiments.

[0163] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification.

Claims

1. An industrial Internet of Things service information processing system based on a service cloud platform, characterized in that: It includes an industrial Internet of Things subsystem and a service cloud platform; the industrial Internet of Things subsystem includes an industrial Internet of Things user platform, an industrial Internet of Things service platform, an industrial Internet of Things management platform, an industrial Internet of Things sensor network platform, and an industrial Internet of Things perception control platform; The industrial Internet of Things user platform is configured to receive application data of a user, upload the application data to the industrial Internet of Things service platform, and display the service data to the user in response to receiving the service data; the industrial Internet of Things service platform is configured to perform desensitization processing based on the first data to generate second data, and upload the second data and the application data to the service cloud platform, wherein the first data is data generated during the production process; The service cloud platform includes edge devices, central devices, a service database and a control center, and the control center is configured as follows: Determine a computing parameter based on the application data, wherein the computing parameter includes at least one of edge computing and central computing; The target computing terminal is controlled to execute the following based on the target database and the computing parameters: Determine the service data based on the second data and the application data, where the service data is data of at least one data type provided to the user; Determine recommended operating data based on the service data and the application data, wherein the recommended operating data includes operating parameters of the monitoring device, and the operating parameters include at least one of data upload frequency and data accuracy; Sending the recommended operation data and the service data to the industrial Internet of Things service platform; The industrial Internet of Things management platform is configured to, in response to receiving the operation execution instruction sent by the industrial Internet of Things user platform, determine the monitoring operation instruction based on the recommended operation data, and send the monitoring operation instruction to the industrial Internet of Things perception control platform; the industrial Internet of Things perception control platform includes the monitoring device, which is deployed in the production line and is configured to monitor the production process based on the monitoring operation instruction to obtain and upload the first data to the industrial Internet of Things service platform; The industrial Internet of Things user platform is further configured to: determining a data display order of the data in the service data according to the data priority in the service data; and displaying the service data to the user based on the data display order; The control center is further configured to: Determining a user authority score based on the user characteristics of the user; Determining a data grade score of the second data; Determining a target data pool based on the user authority score, the application data, and the data level score; The service data is determined based on the target data pool, the user characteristics, the user authority score, and the data level score.

2. The industrial Internet of Things service information processing system according to claim 1, characterized in that: The service data also includes the user priority of the user, and the industrial Internet of Things user platform is further configured as follows: Determine the user push order according to the user priority in the service data; Pushing the service data to the user based on the user push order; The control center is further configured to: Determining service urgency based on the user characteristics of the user and the application data; The user priority is determined based on the service urgency and the user authority score.

3. The industrial Internet of Things service information processing system according to claim 1, characterized in that: The control center is further configured to: Determining the expected satisfaction of the user based on the service data and the application data; The recommended operating data is determined based on the expected satisfaction level and current operating parameters of the monitoring device.

4. The industrial Internet of Things service information processing system according to claim 3, characterized in that: The control center is further configured to determine the expected satisfaction through a satisfaction prediction model based on the service data and the application data, and the satisfaction prediction model is a machine learning model.

5. A method for processing industrial Internet of Things service information based on a service cloud platform, characterized in that: The method is performed by an industrial Internet of Things service information processing system, and includes: The industrial Internet of Things user platform receives application data of the user, uploads the application data to the industrial Internet of Things service platform, and displays the service data to the user in response to receiving the service data; The industrial Internet of Things service platform performs desensitization processing based on the first data to generate second data, and uploads the second data and the application data to the service cloud platform, wherein the first data is data generated during the production process; The control center of the service cloud platform determines a computing parameter based on the application data, where the computing parameter includes at least one of edge computing and center computing; The control center controls the target computing terminal to execute the following based on the target database and the computing parameters: Determine the service data based on the second data and the application data, where the service data is data of at least one data type provided to the user; Determine recommended operating data based on the service data and the application data, wherein the recommended operating data includes operating parameters of the monitoring device, and the operating parameters include at least one of data upload frequency and data accuracy; Sending the recommended operation data and the service data to the industrial Internet of Things service platform; The industrial Internet of Things management platform, in response to receiving the operation execution instruction sent by the industrial Internet of Things user platform, determines a monitoring operation instruction based on the recommended operation data, and sends the monitoring operation instruction to the industrial Internet of Things perception control platform; The monitoring device of the industrial Internet of Things perception control platform monitors the production process based on the monitoring operation instruction to obtain and upload the first data to the industrial Internet of Things service platform; In response to receiving the service data, presenting the service data to the user comprises: Determining a data display order of the data in the service data according to the data priority in the service data; Based on the data display order, display the service data to the user; The determining of the service data based on the second data and the application data includes: Determining a user authority score based on the user characteristics of the user; Determining a data grade score of the second data; Determining a target data pool based on the user authority score, the application data, and the data level score; The service data is determined based on the target data pool, the user characteristics, the user authority score, and the data level score.

6. The industrial Internet of Things service information processing method according to claim 5, characterized in that: The service data further includes a user priority of the user, and the method further includes: The industrial Internet of Things user platform determines the user push order according to the user priority in the service data; The industrial Internet of Things user platform pushes the service data to the user based on the user push order; The control center determines the service urgency based on the user characteristics and the application data of the user; The control center determines the user priority based on the service urgency and the user authority score.

7. The industrial Internet of Things service information processing method according to claim 5, characterized in that: The determining the recommended operation data based on the service data and the application data includes: Determining the expected satisfaction of the user based on the service data and the application data; The recommended operating data is determined based on the expected satisfaction level and current operating parameters of the monitoring device.

8. The industrial Internet of Things service information processing method according to claim 7, characterized in that: The determining the expected satisfaction of the user based on the service data and the application data includes: Based on the service data and the application data, the expected satisfaction is determined by a satisfaction prediction model, and the satisfaction prediction model is a machine learning model.

Images