Data management system and method based on industrial Internet of Things data center

Abstract

The invention relates to the field of data management, and provides a data management system and method based on an industrial Internet of Things data center, and the system comprises 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 sensing network platform, and an industrial Internet of Things sensing control platform. The industrial Internet of Things management platform is configured to determine future acquisition parameters of the sensing network sub-platform based on the residual storage space, the first calling feature and the future calling feature; determining a pre-increased storage amount based on the future acquisition parameters; determining a to-be-deleted group based on the pre-increased storage amount, the residual storage space and the group calling features and the group data amount corresponding to the plurality of data groups; generating a parameter updating instruction based on the future acquisition parameters; and generating a data deletion instruction based on the to-be-deleted group. According to the invention, the normalization and flexibility of data management can be improved, and the data management efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of data management, and in particular to a data management system and method based on an industrial Internet of Things data center. Background Art

[0002] With the continuous deepening of the application of industrial Internet of Things technology, enterprise-level sensor network platforms have become the core support for industrial automation and intelligence. In these platforms, the configuration of multiple sub-databases provides dedicated storage space for different business data, ensuring the flexibility and efficiency of data management. However, how to efficiently collect data and maintain storage space for each sub-platform has become the key to improving the overall performance of the system.

[0003] Therefore, it is hoped to provide a data management system and method based on an industrial Internet of Things data center, which can improve the standardization and flexibility of data management and improve the efficiency of data management. Summary of the invention

[0004] The invention content includes providing a data management system based on an industrial Internet of Things data center, the system 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 management platform includes a data center, the industrial Internet of Things sensor network platform includes multiple sensor network sub-platforms and multiple sensor network sub-databases, and the multiple sensor network sub-databases correspond to the multiple sensor network sub-platforms; the industrial Internet of Things management platform is configured to: every first preset period, for a single sensor network sub-platform among the multiple sensor network sub-platforms: based on the remaining storage space of the sensor network sub-database corresponding to the sensor network sub-platform, a first retrieval feature and future retrieval characteristics to determine future acquisition parameters of the sensor network sub-platform; based on the future acquisition parameters, determine the pre-increment storage capacity of the sensor network sub-database; divide the data items in the sensor network sub-database to obtain multiple data groups; determine the group to be deleted based on the pre-increment storage capacity, the remaining storage space, and the group retrieval characteristics and group data volume corresponding to the multiple data groups; based on the future acquisition parameters, generate a parameter update instruction and send it to the sensor network sub-platform to control the sensor network sub-platform to perform data acquisition based on the future acquisition parameters; and based on the group to be deleted, generate a data deletion instruction and send it to the sensor network sub-platform to control the sensor network sub-platform to delete the group to be deleted.

[0005] The invention content includes a data management method based on an industrial Internet of Things data center, which is executed by an industrial Internet of Things management platform in a data management system based on the industrial Internet of Things data center. The method includes: every first preset period, for a single sensor network sub-platform among multiple sensor network sub-platforms: based on the remaining storage space, first retrieval characteristics and future retrieval characteristics of the sensor network sub-platform, determining the future acquisition parameters of the sensor network sub-database corresponding to the sensor network sub-platform; based on the future acquisition parameters, determining the pre-increment storage capacity of the sensor network sub-database; dividing the data items in the sensor network sub-database to obtain multiple data groups; based on the pre-increment storage capacity, the remaining storage space, and the group retrieval characteristics and group data amounts corresponding to the multiple data groups, determining a group to be deleted; based on the future acquisition parameters, generating a parameter update instruction and sending it to the sensor network sub-platform to control the sensor network sub-platform to perform data acquisition based on the future acquisition parameters; and based on the group to be deleted, generating a data deletion instruction and sending it to the sensor network sub-platform to control the sensor network sub-platform to delete the group to be deleted.

[0006] The beneficial effects of the present invention include but are not limited to: (1) Through the data management system based on the industrial Internet of Things data center, an information operation closed loop can be formed between various functional platforms, and coordinated and regularly operated under the unified management of the industrial Internet of Things management platform, so as to realize the informatization and intelligence of data management. (2) Based on the heartbeat parameters between the sensor network sub-database and the data center, the communication bandwidth can be adjusted to allocate appropriate communication bandwidth to each sensor network sub-platform, avoiding low data transmission efficiency due to too small communication bandwidth or waste of resources due to too large communication bandwidth. (3) Based on the historical retrieval of the sensor network sub-database, multiple associated platform groups and the corresponding degree of association within the group can be determined. Considering the different degrees of influence of different associated sub-platforms on the sensor network sub-platform, the weights of different associated sub-platforms are adjusted to make the future retrieval characteristics of the sensor network sub-database corresponding to the obtained sensor network sub-platform more accurate. 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: Figure 1 It is a schematic diagram of a platform structure of a data management system based on an industrial Internet of Things data center according to some embodiments of this specification; Figure 2 is an exemplary flow chart of a data management method based on an industrial Internet of Things data center according to some embodiments of this specification; Figure 3 is an exemplary flow chart of determining future call features according to some embodiments of this specification; Figure 4 is an exemplary schematic diagram of a prediction model according to some embodiments of this specification; Figure 5 This is an exemplary flowchart of adjusting the groups to be deleted according to some embodiments of this specification. DETAILED DESCRIPTION

[0008] 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, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0009] It should be understood that the "system" used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0010] Figure 1 This is a platform structure diagram of a data management system based on an industrial Internet of Things data center as shown in some embodiments of this specification.

[0011] In some embodiments, Figure 1 As shown, the data management system 100 based on the industrial Internet of Things data center includes an industrial Internet of Things user platform 110, an industrial Internet of Things service platform 120, an industrial Internet of Things management platform 130, an industrial Internet of Things sensor network platform 140, and an industrial Internet of Things perception control platform 150.

[0012] The industrial Internet of Things user platform 110 refers to a platform for interacting with users. In some embodiments, the industrial Internet of Things user platform can be configured as a terminal device. Among them, the terminal device includes a mobile device, a laptop computer, etc.

[0013] The industrial Internet of Things service platform 120 refers to a platform for providing users with data management services based on the industrial Internet of Things. In some embodiments, the industrial Internet of Things service platform is configured as a communication network or a server, etc. The industrial Internet of Things service platform can interact with the industrial Internet of Things management platform and the industrial Internet of Things user platform.

[0014] The industrial Internet of Things management platform 130 refers to a comprehensive management platform for multiple data. In some embodiments, the industrial Internet of Things management platform is configured as a server. In some embodiments, the industrial Internet of Things management platform may also include a processor and / or a memory, etc.

[0015] In some embodiments, the industrial Internet of Things management platform includes a data center 131. The data center is configured as a platform for storing information and / or data related to the data management system 100 based on the industrial Internet of Things data center.

[0016] The IIoT sensor network platform 140 is a platform for integrated management of sensor information. In some embodiments, the IIoT sensor network platform is configured as a communication network or a gateway, etc. The IIoT sensor network platform can interact with the IIoT management platform and the IIoT perception control platform.

[0017] In some embodiments, the industrial Internet of Things sensor network platform includes multiple sensor network sub-databases and multiple sensor network sub-platforms.

[0018] like Figure 1 As shown, the industrial Internet of Things sensor network platform 140 includes a first sensor network sub-database 141-1, a second sensor network sub-database 141-2, etc., as well as a first sensor network sub-platform 142-1, a second sensor network sub-platform 142-2, etc.

[0019] The sensor network sub-database refers to a database that stores and manages the sensor information obtained by the sensor network sub-platform. The number of sensor network sub-databases is the same as the number of sensor network sub-platforms, and one sensor network sub-database corresponds to one sensor network sub-platform.

[0020] The industrial Internet of Things perception control platform 150 refers to a functional platform for generating sensor information and executing control information. In some embodiments, the industrial Internet of Things perception control platform includes a variety of manufacturing equipment terminals and sensors. For example, the manufacturing terminals include automated production equipment, quality inspection equipment, etc., and the sensors include pressure sensors, image sensors, temperature sensors, etc.

[0021] The sensor network sub-platform refers to a platform that collects sensor information based on business needs. For example, business needs include production monitoring, energy management, etc. Correspondingly, the sensor network sub-platform includes a production monitoring platform, an energy management platform, etc. Among them, the production monitoring platform refers to a platform used to monitor the operating status of the factory production line in real time. The energy management platform refers to a platform used to collect and analyze the energy consumption data of a factory or facility.

[0022] In some embodiments, the sensor network sub-platform collects sensor information corresponding to business needs through multiple sensor devices in the industrial Internet of Things perception control platform, and uploads the sensor information to the industrial Internet of Things management platform. The sensor network sub-platform stores the acquired sensor information in the corresponding sensor network sub-database.

[0023] In some embodiments, the IIoT management platform can retrieve data in the sensor network sub-database based on the retrieval demand, and upload the data to the IIoT user platform through the IIoT service platform. The retrieval demand refers to the type of sensor network sub-database that the user of the IIoT management platform wants to retrieve. The retrieval demand corresponds to the business demand. For example, the retrieval demand includes retrieval of data in the sensor network sub-database corresponding to the energy management platform.

[0024] It is understandable that business needs may only require the sensor information of a part of the sensor equipment, so the sensor information of the sensor equipment related to the business needs can be collected through the sensor network sub-platform. At the same time, if all the data collected by the sensor network sub-platform is stored in the data center, the load of the data center will be large. Therefore, by storing the data obtained by the sensor network sub-platform through the sensor network sub-database, the load of the data center can be effectively reduced, and the data corresponding to different sensor network sub-platforms can be clearly divided.

[0025] In some embodiments, the data management system 100 based on the industrial Internet of Things data center further includes a processor and a memory. The processor is configured to process information and / or data related to the data management system 100 based on the industrial Internet of Things data center. The processor includes a central processing unit (CPU), an application specific instruction processor (ASIP), a graphics processing unit (GPU), etc. or any combination thereof.

[0026] For detailed description of the above, please refer to Figures 2 to 5 Related description.

[0027] Through the data management system based on the industrial Internet of Things data center, a closed loop of information operation can be formed between various functional platforms, and coordinated and regularly operated under the unified management of the industrial Internet of Things management platform, realizing the informatization and intelligence of data management.

[0028] Figure 2 is an exemplary flow chart of a data management method based on an industrial Internet of Things data center according to some embodiments of this specification. Figure 2 As shown, the process 200 of the data management method based on the industrial Internet of Things data center includes the following steps. In some embodiments, the process 200 of the data management method based on the industrial Internet of Things data center can be executed by an industrial Internet of Things management platform (hereinafter referred to as the management platform).

[0029] In some embodiments, every first preset period, for a single sensor network sub-platform among the multiple sensor network sub-platforms, the management platform may respectively execute steps 210 to 260 to generate parameter update instructions and / or data deletion instructions, etc. The first preset period is preset based on historical experience.

[0030] For information about the data management system and platforms based on the Industrial Internet of Things data center, see Figure 1 and its related description.

[0031] Step 210, determining future acquisition parameters of the sensor network sub-platform based on the remaining storage space of the sensor network sub-database corresponding to the sensor network sub-platform, the first retrieved feature, and the future retrieved feature.

[0032] The remaining storage space refers to the remaining storage space size in the sensor network sub-database. The storage space size is represented by the amount of data that can be stored. In some embodiments, the management platform obtains the remaining storage space from the sensor network sub-database.

[0033] The first retrieval feature refers to the retrieval feature of the sensor network sub-database within a preset historical period. The retrieval feature refers to data used to characterize the retrieval situation of the sensor network sub-database. For example, the retrieval feature includes at least one of the number of times the sensor network sub-database is retrieved, the data items retrieved each time, and the average amount of data retrieved multiple times. The preset historical period refers to a period of time past the current time point. The preset historical period is pre-set based on historical experience. The data item refers to the data of the sensor network sub-platform stored in the sensor network sub-database.

[0034] In some embodiments, the management platform obtains the first retrieval feature by counting the historical retrieval process of the sensor network sub-database within a preset historical period.

[0035] The future retrieved features refer to the retrieved features of the sensor network sub-database in a preset future period. The preset future period is pre-set based on historical experience.

[0036] In some embodiments, the management platform determines the future call features by various methods. For example, the management platform obtains the future call features by manual input.

[0037] In some embodiments, the management platform may also obtain multiple associated sub-platforms of the sensor network sub-platform; and determine future retrieval features based on the first stored data corresponding to the multiple associated sub-platforms.

[0038] The associated sub-platform refers to other sensor network sub-platforms that are associated with the current sensor network sub-platform.

[0039] In some embodiments, the management platform obtains the associated sub-platforms through various methods. For example, the management platform obtains the associated sub-platforms through manual input.

[0040] In some embodiments, the management platform can also determine multiple associated sub-platforms based on multiple associated platform groups. For more information, see Figure 3 and its related description.

[0041] The first storage data refers to data related to the data storage of the sensor network sub-database corresponding to the associated sub-platform. In some embodiments, the first storage data includes a historical storage sequence of the associated sub-platform, etc. The historical storage sequence refers to a sequence composed of data storage rates of multiple sampling points of the sensor network sub-database corresponding to the associated sub-platform within a preset historical period. The multiple sampling points are pre-set based on historical experience.

[0042] In some embodiments, the data storage rate is represented by the amount of data stored per unit time.

[0043] In some embodiments, for a single associated sub-platform among multiple associated sub-platforms, the management platform constructs a first target vector based on the first stored data of the sensor network sub-database corresponding to the associated sub-platform, matches the first target vector in the first vector database, obtains multiple first feature vectors that meet the first similarity condition, and determines the mean of the labels of the multiple first feature vectors as the candidate extraction feature of the sensor network sub-database corresponding to the associated sub-platform. The first similarity condition includes that the similarity with the first target vector is greater than a first similarity threshold, and the first similarity threshold is set based on experience. The similarity between vectors is negatively correlated to the vector distance. The vector distance includes the Euclidean distance, etc.

[0044] In some embodiments, the first vector database is constructed based on historical data. For example, the management platform constructs multiple first feature vectors based on multiple historical first storage data corresponding to the sensor network sub-database corresponding to the associated sub-platform in the historical data at the first historical time, and determines the actual retrieved features of the sensor network sub-database corresponding to the associated sub-platform at the second historical time as the label corresponding to the first feature vector. The first historical time is earlier than the second historical time.

[0045] In some embodiments, the management platform determines the candidate call features of the sensor network sub-database corresponding to the multiple associated sub-platforms through the above method, performs weighted summation on the number of call times in the multiple candidate call features, and uses the sum result as the number of call times in the future call features of the sensor network sub-database corresponding to the sensor network sub-platform. The management platform can also use the data items called in the multiple candidate call features as the data items called in the future call features, and count the total amount of data of the called data items as the amount of data in the future call features. The weights of different associated sub-platforms are set based on experience.

[0046] In some embodiments, the management platform determines the future retrieval feature based on the intra-group association degree corresponding to the multiple associated sub-platforms and the first stored data. For more information, see Figure 3 And related instructions.

[0047] By referring to the retrieved features of other sensor network sub-platforms with greater correlation, the future retrieved features of the current sensor network sub-platform can be determined more accurately.

[0048] The future acquisition parameters refer to the acquisition parameters of the sensor network sub-platform in the preset future period. The acquisition parameters include acquisition frequency and acquisition accuracy. Among them, the acquisition accuracy refers to the accuracy of the collected sensor information. For example, the pixel value of image sensor information.

[0049] In some embodiments, the management platform determines the future acquisition parameters by a variety of methods. For example, the management platform constructs a vector to be clustered based on the remaining storage space, the first retrieved feature, and the future retrieved feature, and constructs a clustering vector based on the historical remaining storage space, the historical first retrieved feature, and the historical future retrieved feature in the historical data. The management platform clusters the vector to be clustered and multiple clustering vectors to obtain multiple clustering clusters, determines the clustering cluster containing the vector to be clustered as the target cluster, and uses the future acquisition parameters corresponding to all clustering vectors in the target cluster with the best acquisition effect as the future acquisition parameters of the sensor network sub-platform. The acquisition effect is positively correlated to the success rate of the management platform to retrieve data items in the sensor network sub-database after the sensor network sub-platform collects data based on the future acquisition parameters. The higher the retrieval success rate, the better the acquisition effect. The retrieval success rate refers to the ratio of the number of data items actually retrieved by the management platform from the sensor network sub-database to the number of data items that need to be retrieved. If the sensor network sub-database includes all the data items that the management platform needs to retrieve, the retrieval success rate is 100%.

[0050] The future acquisition parameters corresponding to the clustering vector can be predetermined based on historical data. For example, the actual acquisition parameters of the sensor network sub-platform corresponding to the clustering vector at the third historical time are determined as the future acquisition parameters of the fourth historical time corresponding to the clustering vector. The third historical time is earlier than the fourth historical time.

[0051] In some embodiments, the management platform can adjust the future collection parameters of the target sub-platform based on the future collection parameters of multiple associated sub-platforms corresponding to the target sub-platform. For more information, see Figure 4 And related instructions.

[0052] Step 220: Determine the pre-incremental storage capacity of the sensor network sub-database based on the future acquisition parameters.

[0053] The pre-incremental storage capacity refers to the amount of data storage that will be added to the sensor network sub-database within a preset future period.

[0054] In some embodiments, the management platform determines the pre-increment storage amount based on the future collection parameters of the sensor network sub-platform. For example, the management platform multiplies the collection frequency in a preset future period by the amount of data collected by the sensor device at a single time as the pre-increment storage amount. The amount of data collected by the sensor device at a single time is a fixed amount.

[0055] In some embodiments, the management platform adjusts the pre-increment storage amount based on the average of the first compression amount and the second compression amount in multiple historical time intervals of the sensor network sub-database. For example, the management platform can use the sum of the average of the first compression amount and the second compression amount in multiple historical time intervals as the normal compression amount of the sensor network sub-database, and use the difference between the pre-increment storage amount and the normal compression amount as the final pre-increment storage amount. Among them, the first compression amount refers to the compression amount of repeated data compression performed by the sensor network sub-platform on the data collected by the sensor device. The second compression amount refers to the compression amount of data accuracy compression performed by the sensor network sub-platform on the data collected by the sensor device. Multiple historical time intervals are set based on experience.

[0056] Step 230, dividing the data items in the sensor network sub-database to obtain a plurality of data groups.

[0057] A data group refers to a group consisting of multiple data items. In some embodiments, the management platform divides the data items of the sensor network sub-database based on the retrieval time series to obtain multiple data groups. For example, the management platform clusters the multiple data items in the sensor network sub-database based on the retrieval time series corresponding to the data items, and uses the multiple clustering clusters obtained after clustering as multiple data groups. Among them, the retrieval time series refers to a sequence consisting of the time when the data item is retrieved multiple times in the historical data. The management platform counts the data items retrieved each time in the first retrieval feature, obtains the time when the data item is retrieved each time based on the historical data, obtains the time when each data item is retrieved multiple times and forms a retrieval time series.

[0058] Step 240 , determining the group to be deleted based on the pre-increment storage capacity, the remaining storage space, and the group retrieval features and group data volumes corresponding to the plurality of data groups.

[0059] The packet retrieval feature refers to the retrieval feature of the data packet in a preset future period. In some embodiments, the packet retrieval feature includes at least one of the total retrieval times and total retrieval amount of multiple data items in the data packet in the preset future period.

[0060] The group data volume refers to the total amount of data of multiple data items in the data group. The management platform uses the calculated sum of the data volumes of multiple data items in the data group as the group data volume.

[0061] In some embodiments, the management platform determines the group call feature corresponding to each data group based on the future call feature. For example, the management platform counts the number of data items in the data group that appear in the future call feature, and uses the product of the number and the number of calls in the future call feature as the total number of calls in the group call feature, and uses the product of the amount of data items that appear in the future call feature and the number of calls in the future call feature as the total call amount.

[0062] The group to be deleted refers to a data group to be deleted. The group to be deleted includes one or more data groups.

[0063] In some embodiments, when the remaining storage space meets the preset deletion condition, the management platform iteratively counts the data group with the least total number of retrievals into the group to be deleted based on multiple data groups, until the storage space of the sensor network sub-database after deleting the group to be deleted does not meet the preset deletion condition, and the group to be deleted is determined to be completed. Among them, the preset deletion condition includes that the storage space is less than the pre-increment storage amount or the difference between the storage space and the pre-increment storage amount is less than the storage amount threshold. The storage amount threshold is preset based on historical experience. The storage space of the sensor network sub-database after deleting the group to be deleted is represented by the sum of the remaining storage space before iteration and the group data amount of the group to be deleted.

[0064] In some embodiments, the management platform can adjust the group to be deleted based on the estimated retrieved features. Figure 5 And related instructions.

[0065] Step 250: Generate a parameter update instruction based on the future acquisition parameters and send it to the sensor network sub-platform to control the sensor network sub-platform to perform data acquisition based on the future acquisition parameters.

[0066] The parameter update instruction is an instruction for controlling the sensor network sub-platform to update the collection parameters. In some embodiments, the management platform converts the future collection parameters into machine instructions, and sends the machine instructions as parameter update instructions to the sensor network sub-platform to control the sensor network sub-platform to collect data based on the future collection parameters.

[0067] Step 260: Based on the group to be deleted, generate a data deletion instruction and send it to the sensor network sub-platform to control the sensor network sub-platform to delete the group to be deleted.

[0068] The data deletion instruction is an instruction for controlling the sensor network sub-platform to delete the group to be deleted. In some embodiments, the management platform converts the group to be deleted into a machine instruction, and sends the machine instruction as the data deletion instruction to the sensor network sub-platform to control the sensor network sub-platform to delete the group to be deleted.

[0069] By generating parameter update instructions based on future acquisition parameters, the sensor network sub-platform can be controlled to perform more comprehensive data acquisition to avoid the situation where the corresponding data items cannot be retrieved. By determining the group to be deleted and generating data deletion instructions, uncommon data can be deleted in a timely manner, improving the standardization and flexibility of data management and improving data management efficiency.

[0070] In some embodiments, every first preset period, the management platform can also determine the heartbeat parameters between the sensor network sub-database and the data center based on future collection parameters, determine the communication bandwidth between the sensor network sub-platform and the data center based on the heartbeat parameters, and adjust the communication parameters between the sensor network sub-platform and the data center based on the communication bandwidth.

[0071] In some embodiments, the heartbeat parameters include parameters related to data transmission between the sensor network sub-database and the data center. For example, the heartbeat parameters include at least one of a heartbeat cycle and a type of information transmitted by the heartbeat.

[0072] The heartbeat cycle refers to the time interval for the sensor network database to transmit heartbeat information to the data center.

[0073] The heartbeat transmission information refers to the information related to the data transmission between the sensor network sub-database and the data center. The type of the heartbeat transmission information includes at least one of the state information, storage information and the number of connections.

[0074] The status information is used to reflect the current status of the sensor network sub-database. For example, the sensor network sub-database is available or faulty. Storage information includes the total amount of data stored in the sensor network sub-database and the remaining storage space. The number of connections refers to the number of data centers or sensor network sub-platforms connected to the sensor network sub-database.

[0075] In some embodiments, the management platform queries the heartbeat parameters corresponding to the future acquisition parameters in the first preset table as the current heartbeat parameters based on the future acquisition parameters. The first preset table is constructed by technicians based on historical experience and includes multiple pairs of corresponding relationships between future acquisition parameters and heartbeat parameters.

[0076] In some embodiments, the management platform adjusts the heartbeat parameters every second preset period based on the current storage data of multiple associated sub-platforms corresponding to the sensor network sub-platforms in response to the load data of the communication links between the multiple sensor network sub-platforms and the data center not meeting the preset load conditions.

[0077] In some embodiments, the management platform can adjust the heartbeat parameters between the sensor network sub-database and the data center corresponding to each sensor network sub-platform based on the current storage data of multiple associated sub-platforms corresponding to each sensor network sub-platform. The following is an example of a single sensor network sub-platform.

[0078] The second preset period refers to the period during which the management platform adjusts the heartbeat parameters. The second preset period is set based on experience. The second preset period is shorter than the first preset period.

[0079] Load data refers to the data flow on the communication link between the data center and multiple sensor network sub-platforms. Among them, multiple sensor network sub-platforms share a communication link to transmit information to the data center.

[0080] In some embodiments, the management platform obtains load data by monitoring data traffic on the communication link in real time.

[0081] The preset load condition refers to a condition for determining whether the heartbeat parameter needs to be adjusted. In some embodiments, the preset load condition includes that the load data is less than a preset flow threshold, etc. The preset flow threshold is set based on experience.

[0082] The currently stored data refers to data related to the data storage of the sensor network sub-database corresponding to the associated sub-platform corresponding to the sensor network sub-platform at the current moment. In some embodiments, the currently stored data includes the data storage rate of the sensor network sub-database at the current moment, etc. For more information about the data storage rate, see step 210 and its related description.

[0083] In some embodiments, the management platform calculates the weighted sum of the currently stored data of the multiple associated sub-platforms corresponding to the sensor network sub-platform, queries the heartbeat cycle adjustment amount and the type of heartbeat transmission information corresponding to the weighted sum in the second preset table based on the weighted sum, adjusts the heartbeat cycle based on the heartbeat cycle adjustment amount, and forms a new adjustment parameter with the adjusted heartbeat cycle and the type of heartbeat transmission information. The weights of different associated sub-platforms are set based on experience.

[0084] The second preset table is constructed by technicians based on historical experience, and includes a plurality of corresponding relationships between weighted sums and heartbeat cycle adjustment amounts and types of heartbeat transmission information.

[0085] When the load data exceeds the preset flow threshold, the heartbeat parameters are adjusted based on the data storage rate of the sensor network database at the current moment. When the load of the communication link is large, the heartbeat parameters can be adjusted in time to reduce the data flow on the communication link and ensure the normal transmission of data in the communication link.

[0086] In some embodiments, the management platform allocates the communication bandwidth of each sensor network sub-platform based on the ratio of the heartbeat parameters between the sensor network sub-databases and the data center corresponding to the multiple sensor network sub-platforms. For example, the management platform allocates the same proportion of communication bandwidth to each sensor network sub-platform based on the ratio of the heartbeat parameters. The ratio of the heartbeat parameters is represented by the ratio of the weighted sum of the heartbeat cycle and the amount of data of the heartbeat transmission information. The weights of the heartbeat cycle and the heartbeat transmission information are set based on experience. The weight of the heartbeat cycle can be a negative number.

[0087] Communication parameters refer to parameters related to the communication between the sensor network sub-platform and the data center. In some embodiments, the communication parameters include routing parameters of routers on the communication link between the sensor network sub-platform and the data center. The routing parameters include the IP addresses of the sensor network sub-platform and the data center and the corresponding bandwidth limits.

[0088] In some embodiments, the management platform uses the communication bandwidth corresponding to the sensor network sub-platform as the bandwidth limit in the routing parameters.

[0089] By adjusting the communication bandwidth based on the heartbeat parameters between the sensor network sub-database and the data center, appropriate communication bandwidth can be allocated to each sensor network sub-platform to avoid low data transmission efficiency due to too small communication bandwidth or waste of resources due to too large communication bandwidth.

[0090] It should be noted that the above description of the process 200 of the data management method based on the industrial Internet of Things data center 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 of the data management method based on the industrial Internet of Things data center under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0091] Figure 3 FIG. 1 is an exemplary flow chart of determining future call features according to some embodiments of this specification. Figure 3 As shown, the process 300 of determining future call features includes the following steps.

[0092] Step 310: Determine a plurality of associated platform groups and intra-group association degrees corresponding to the plurality of associated platform groups based on the second retrieved features corresponding to the plurality of sensor network sub-platforms.

[0093] The second retrieval feature refers to data related to the retrieval time of the sensor network sub-database corresponding to the sensor network sub-platform. In some embodiments, the second retrieval feature includes the time when the sensor network sub-database is retrieved each time in the historical data. The second retrieval feature is obtained based on the historical data.

[0094] The associated platform group refers to a combination of mutually associated sensor network sub-platforms. Each associated platform group includes two mutually associated sensor network sub-platforms.

[0095] In some embodiments, the management platform calculates explicit association values ​​and implicit association values ​​corresponding to any two sensor network sub-platforms based on the second retrieved features corresponding to the plurality of sensor network sub-platforms, and in response to the sum of the explicit association value and the implicit association value being greater than an association value threshold, the management platform determines the two sensor network sub-platforms as a group of associated platforms. The association value threshold is set based on experience.

[0096] The explicit correlation value is positively correlated with the number of occurrences of positive events in multiple historical time intervals. A positive event refers to the number of times that the sensor network sub-databases corresponding to the two sensor network sub-platforms are simultaneously retrieved within a single historical time interval, which is greater than a preset explicit threshold. The preset explicit threshold is set based on experience. Among them, being retrieved simultaneously means that a single retrieval instruction issued by the data center requires the data of the sensor network sub-databases corresponding to the two sensor network sub-platforms to be retrieved simultaneously. For an explanation of multiple historical time intervals, see step 220 and its related description.

[0097] In some embodiments, the preset explicit threshold may be positively correlated to an average value of the number of sensor network sub-databases required to be retrieved in the plurality of retrieval instructions.

[0098] The greater the average number of sensor network sub-databases required to be retrieved in multiple retrieval instructions, the lower the correlation between the two sensor network sub-platforms that are retrieved at the same time. At this time, the preset explicit threshold needs to be appropriately increased to ensure the accuracy of the explicit correlation value.

[0099] The implicit correlation value is positively correlated with the number of negative events in multiple historical time intervals. A negative event refers to the number of times that the sensor network sub-databases corresponding to the two sensor network sub-platforms are individually retrieved in two or more consecutive historical time intervals, which is less than the preset implicit threshold. The preset implicit threshold is set based on experience.

[0100] In some embodiments, the preset implicit threshold value may be positively correlated with the weighted sum of the access frequencies of the sensor network sub-databases corresponding to the two sensor network sub-platforms. The access frequency refers to the ratio of the average number of times the sensor network sub-database is accessed in multiple historical time intervals to the duration of a single historical time interval. The weights corresponding to the two sensor network sub-platforms are set based on experience.

[0101] When the access frequency is low, it means that the two sensor network sub-databases are accessed less frequently. At this time, the preset implicit threshold can be appropriately lowered to avoid the situation where the two sensor network sub-databases are individually accessed less frequently than the preset implicit threshold.

[0102] The intra-group correlation degree refers to the correlation degree between two sensor network sub-platforms in the associated platform group. Each sensor network sub-platform in the associated platform group corresponds to an intra-group correlation degree.

[0103] In some embodiments, the management platform counts the number of times that the sensor network sub-databases corresponding to two sensor network sub-platforms in the associated platform group are called individually and simultaneously within multiple historical time intervals based on the second call features corresponding to multiple sensor network sub-platforms, and takes the ratio of the number of times each sensor network sub-database is called simultaneously to the number of times it is called individually as the degree of intra-group association of the sensor network sub-platform corresponding to the sensor network sub-database.

[0104] Step 320: Determine multiple associated sub-platforms based on the multiple associated platform groups.

[0105] In some embodiments, the two sensor network sub-platforms in each associated platform group are associated sub-platforms with each other. The management platform can count all associated platform groups that include the current sensor network sub-platform, and determine other sensor network sub-platforms in these associated platform groups as associated sub-platforms of the current sensor network sub-platform. For more information about associated sub-platforms, see Figure 2 The management platform can determine the associated sub-platforms of all sensor network sub-platforms through the above method. Step 330 , determining future retrieved features based on the intra-group association levels corresponding to the multiple associated sub-platforms and the first stored data.

[0106] For more information about first stored data and future retrieval features, see Figure 2 And related instructions.

[0107] In some embodiments, the management platform assigns weights to multiple associated sub-platforms when determining future features to be retrieved based on the ratio of the intra-group association levels corresponding to multiple associated sub-platforms of the current sensor network sub-platform. For example, the management platform assigns the same proportion of weights to each associated sub-platform based on the ratio of the intra-group association levels.

[0108] The management platform obtains the future extraction features of the sensor network sub-database corresponding to the current sensor network sub-platform by weighted summation based on multiple candidate extraction features of the sensor network sub-database corresponding to the multiple associated sub-platforms. For instructions on obtaining the future extraction features by weighted summation based on multiple candidate extraction features, see Figure 2 and related descriptions.

[0109] In some embodiments, the management platform constructs a data retrieval map based on multiple associated platform groups, the degree of association within the group, and the second storage data corresponding to multiple sensor network sub-platforms; based on the data retrieval map, the future retrieval characteristics are determined through a prediction model. For more information, see Figure 4 And related instructions.

[0110] Based on the historical retrieval of the sensor network sub-database, it is possible to determine multiple associated platform groups and the corresponding degree of association within the group. Taking into account the different degrees of influence of different associated sub-platforms on the sensor network sub-platform, the weights of different associated sub-platforms are adjusted to make the future retrieval characteristics of the sensor network sub-database corresponding to the obtained sensor network sub-platform more accurate.

[0111] It should be noted that the above description of the process 300 for determining the future call feature is only for example and illustration, 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 300 for determining the future call feature under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0112] Figure 4 is an exemplary schematic diagram of a prediction model according to some embodiments of the present specification.

[0113] In some embodiments, Figure 4 As shown, the management platform constructs a data retrieval map 440 based on multiple associated platform groups 410, the intra-group correlation levels 420 corresponding to multiple associated sub-platforms, and the second storage data 430 corresponding to multiple sensor network sub-platforms, and determines future retrieval features 460 through a prediction model 450 based on the data retrieval map 440.

[0114] For more information on related platform groups, future feature extraction, and the degree of association within groups, see Figure 2 and Figure 3 And related instructions.

[0115] The second stored data refers to data related to the data storage of the sensor network sub-database corresponding to the sensor network sub-platform. In some embodiments, the second stored data includes the historical storage sequence of the sensor network sub-database corresponding to the sensor network sub-platform, etc. For an explanation of the historical storage sequence, see step 210 and its related description.

[0116] The data retrieval graph refers to a graph structure that can reflect the data retrieval status of sensor network sub-databases corresponding to multiple sensor network sub-platforms. The graph structure is a data structure composed of nodes and edges, where edges connect nodes and nodes and edges can have features.

[0117] In some embodiments, the management platform constructs a data retrieval graph based on multiple associated platform groups, the intra-group association degrees corresponding to multiple associated sub-platforms, and the second storage data corresponding to multiple sensor network sub-platforms. For example, the nodes (such as node 441, etc.) of the data retrieval graph include sensor network sub-platforms, and the node features include the second storage data of the sensor network sub-database corresponding to the sensor network sub-platform.

[0118] The edges in the data retrieval graph can represent the association relationship between nodes. For example, if two sensor network sub-platforms belong to an associated platform group, there are two directed edges in opposite directions (such as edge 442, etc.) between the two sensor network sub-platforms. The edge features of the directed edges include the group association degree of the sensor network sub-platform corresponding to the node at the starting point of the directed edge in the associated platform group.

[0119] The prediction model is a model used to determine the future features to be retrieved. In some embodiments, the prediction model is a machine learning model. For example, the prediction model is any one or combination of a graph neural network (GNN) model or other custom model structures.

[0120] In some embodiments, the input of the prediction model includes a data retrieval graph. The output of the prediction model includes future retrieval features of the sensor network sub-database corresponding to each node in the data retrieval graph.

[0121] In some embodiments, the management platform trains a prediction model based on multiple labeled training samples. For example, the management platform can input multiple training samples into the initial prediction model, construct a loss function based on the output of the initial prediction model and the labels of the training samples, iteratively update the parameters of the initial prediction model based on the loss function, and terminate the iteration when the iteration completion condition is met to obtain a trained prediction model. Among them, the iterative update method includes but is not limited to the gradient descent method, etc. The iteration completion condition includes the convergence of the loss function or the number of iterations reaching a threshold, etc.

[0122] The training sample includes a sample data retrieval graph, and the sample data retrieval graph includes a historical data retrieval graph determined based on historical data of a fifth historical time. The nodes and features, and the edges and features of the historical data retrieval graph are similar to the above description.

[0123] The label of the training sample refers to the actual retrieved features of each sample node in the sample data retrieval graph at the sixth historical time. The sixth historical time is later than the fifth historical time.

[0124] Based on the data retrieval graph, the future retrieval features are determined through the prediction model, and the future retrieval features of the sensor network sub-databases corresponding to multiple sensor network sub-platforms can be determined at the same time, thereby realizing the unified management of multiple sensor network sub-platforms. Determining future retrieval features through machine learning models can improve the efficiency and accuracy of determining future retrieval features.

[0125] In some embodiments, the management platform determines the update priorities corresponding to multiple sensor network sub-platforms through a data retrieval map; based on the update priorities, determines multiple future acquisition parameters corresponding to the multiple sensor network sub-platforms, wherein, for a target sub-platform whose update priority meets a preset adjustment condition, the future acquisition parameters of the target sub-platform are adjusted based on the future acquisition parameters of multiple associated sub-platforms corresponding to the target sub-platform.

[0126] The update priority is the order of adjusting future acquisition parameters. In some embodiments, the management platform sorts the out-degree of each node in the data retrieval graph from large to small, and uses the sorting result as the update priority of the sensor network sub-platform corresponding to each node. The smaller the value corresponding to the sorting result, the higher the ranking, and the higher the corresponding update priority. Among them, the out-degree of each node refers to the number of directed edges from the node to other nodes.

[0127] In some embodiments, the management platform determines the sensor network sub-platform whose update priority meets the preset adjustment condition as the target sub-platform, and adjusts the future acquisition parameters of the target sub-platform based on the future acquisition parameters of multiple associated sub-platforms corresponding to the target sub-platform. The preset adjustment condition is that the update priority is lower than the priority threshold. The priority threshold is set based on experience.

[0128] In some embodiments, the management platform screens multiple associated platform groups including the target sub-platform, and uses multiple associated platform groups whose intra-group association degree is greater than an association threshold as multiple target associated platform groups. In response to future acquisition parameters of other sensor network sub-platforms in the multiple target associated platform groups satisfying a second preset condition, the management platform adjusts (e.g., reduces a preset adjustment amount, etc.) the future acquisition parameters of the target sub-platform based on a preset adjustment amount. The association threshold and the preset adjustment amount are set based on experience.

[0129] The second preset condition includes that the weighted sum of future acquisition parameters of multiple other sensor network sub-platforms is greater than a preset acquisition threshold. The preset acquisition threshold and the weight of each sensor network sub-platform are set based on experience.

[0130] In some embodiments, the weight of the sensor network sub-platform is positively correlated to the intra-group association degree corresponding to the sensor network sub-platform in the associated platform group including the target sub-platform.

[0131] By adjusting the future acquisition parameters of the sensor network sub-platforms based on the update priority, the future acquisition parameters of the sensor network sub-platforms with higher importance can be adjusted preferentially, and the acquisition parameters of the sensor network sub-platforms with lower priority can be reduced by a preset adjustment amount, thereby giving priority to ensuring the normal acquisition and transmission of data of the sensor network sub-platforms with higher importance.

[0132] Figure 5 FIG. 1 is an exemplary flow chart of adjusting a group to be deleted according to some embodiments of this specification. Figure 5 As shown, the process 500 of adjusting the group to be deleted includes the following steps.

[0133] Step 510: Acquire multiple associated data groups of the data group.

[0134] An associated data group refers to a data group associated with the existence of a current data group. In some embodiments, the management platform clusters multiple data groups based on the time when they were retrieved in historical data and the retrieved data items to obtain multiple clusters, and determines the data group in the same cluster as the current data group as the associated data group of the current data group. For more information about data groups, see Figure 2 And related instructions.

[0135] Step 520, determining an estimated retrieved feature of the data group based on a plurality of associated data groups and the group retrieved features of the data group.

[0136] For more information about grouping features, see Figure 2 And related instructions.

[0137] The estimated retrieved features refer to the group retrieved features of the current data group within a preset future time period.

[0138] In some embodiments, the management platform constructs a feature vector based on multiple associated data groups and grouped call features of the data groups, and performs vector matching, determines the mean of the labels of the matched feature vector as the candidate grouped call features corresponding to the associated data group, and determines the weighted sum of the multiple candidate call features as the estimated call features based on the candidate call features corresponding to the multiple associated data groups. The weights of different associated data groups are set based on experience. Among them, the above method for determining the candidate grouped call features corresponding to the associated data group is similar to the method for determining the candidate call features corresponding to the associated sub-platform in step 210. Its implementation method refers to step 210 and its related description.

[0139] Step 530: Adjust the group to be deleted based on the estimated retrieved features.

[0140] In some embodiments, in response to the difference between the storage space of the sensor network sub-database after deleting the group to be deleted and the pre-increment storage capacity after deleting the group to be deleted being higher than the storage space threshold, the management platform determines the group to be deleted with the largest weighted sum of each parameter in the estimated retrieved feature among multiple groups to be deleted as the data group that does not need to be deleted. The management platform iteratively performs the above operations until the difference between the storage space of the sensor network sub-database after deleting the group to be deleted and the pre-increment storage capacity is not higher than the storage space threshold. The storage space threshold is set based on experience. For more information about groups to be deleted and pre-increment storage capacity, see Figure 2 And related instructions.

[0141] The groups to be deleted are adjusted in real time based on the estimated retrieval features. When the storage space of the sensor network database after deleting the groups to be deleted still has a certain amount of storage space excluding the pre-incremented storage capacity, the data groups that are more easily retrieved are retained as much as possible to maximize the integrity of the data.

[0142] It should be noted that the above description of the process 500 for adjusting the group to be deleted is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various amendments and changes can be made to the process 500 for adjusting the group to be deleted under the guidance of this specification. However, these amendments and changes are still within the scope of this specification.

[0143] Some embodiments of the present specification also provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the data management method based on the industrial Internet of Things data center described in any one of the above embodiments.

[0144] Furthermore, certain features, structures or characteristics in one or more embodiments of this specification may be appropriately combined.

[0145] In some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired characteristics of a particular embodiment.

[0146] If there is any inconsistency or conflict between the descriptions, definitions, and / or usage of terms in the materials cited in this specification and the contents described in this specification, the descriptions, definitions, and / or usage of terms in this specification shall prevail.

Claims

1. A data management system based on an industrial Internet of Things data center, characterized in that: The system 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 management platform includes a data center, the industrial Internet of Things sensor network platform includes a plurality of sensor network sub-platforms and a plurality of sensor network sub-databases, and the plurality of sensor network sub-databases correspond to the plurality of sensor network sub-platforms; The industrial Internet of Things management platform is configured to: At every first preset period, for a single sensor network sub-platform among the plurality of sensor network sub-platforms: Determining future acquisition parameters of the sensor network sub-platform based on the remaining storage space of the sensor network sub-database corresponding to the sensor network sub-platform, the first retrieved feature, and the future retrieved feature; Based on the future acquisition parameters, determining the pre-increment storage capacity of the sensor network sub-database; Dividing the data items in the sensor network sub-database to obtain a plurality of data groups; Determining a group to be deleted based on the pre-increment storage amount, the remaining storage space, and group retrieval features and group data amounts corresponding to the plurality of data groups; Based on the future acquisition parameters, a parameter update instruction is generated and sent to the sensor network sub-platform to control the sensor network sub-platform to perform data acquisition based on the future acquisition parameters; Based on the group to be deleted, a data deletion instruction is generated and sent to the sensor network sub-platform to control the sensor network sub-platform to delete the group to be deleted.

2. The system according to claim 1, characterized in that The industrial Internet of Things management platform is further configured to: Acquire multiple associated sub-platforms of the sensor network sub-platform; The future retrieval feature is determined based on the first stored data corresponding to the multiple associated sub-platforms.

3. The system according to claim 2, characterized in that The industrial Internet of Things management platform is further configured to: Determining a plurality of associated platform groups and intra-group association degrees corresponding to the plurality of associated platform groups based on the second retrieved features corresponding to the plurality of sensor network sub-platforms; Based on the multiple associated platform groups, determining the multiple associated sub-platforms; The future retrieval feature is determined based on the intra-group association levels corresponding to the multiple associated sub-platforms and the first stored data.

4. The system according to claim 3, characterized in that The industrial Internet of Things management platform is further configured to: constructing a data retrieval graph based on the multiple associated platform groups, the intra-group association degrees corresponding to the multiple associated sub-platforms, and the second stored data corresponding to the multiple sensor network sub-platforms, wherein the second stored data includes the first stored data; Based on the data retrieval map, the future retrieval features are determined by a prediction model, and the prediction model is a machine learning model.

5. The system according to claim 1, wherein: The industrial Internet of Things management platform is further configured to: For a single data packet among the plurality of data packets: Acquire multiple associated data groups of the data group; Determining an estimated call feature of the data group based on the plurality of associated data groups and the group call features of the data group; Based on the estimated retrieved features, the to-be-deleted group is adjusted.

6. A data management method based on an industrial Internet of Things data center, characterized in that: The method is performed by an industrial Internet of Things management platform in a data management system based on an industrial Internet of Things data center, and the method includes: Every first preset period, for a single sensor network sub-platform among the multiple sensor network sub-platforms: Determining future acquisition parameters of the sensor network sub-platform based on the remaining storage space of the sensor network sub-database corresponding to the sensor network sub-platform, the first retrieved feature, and the future retrieved feature; Based on the future acquisition parameters, determining the pre-increment storage capacity of the sensor network sub-database; Dividing the data items in the sensor network sub-database to obtain a plurality of data groups; Determining a group to be deleted based on the pre-increment storage amount, the remaining storage space, and group retrieval features and group data amounts corresponding to the plurality of data groups; Based on the future acquisition parameters, a parameter update instruction is generated and sent to the sensor network sub-platform to control the sensor network sub-platform to perform data acquisition based on the future acquisition parameters; Based on the group to be deleted, a data deletion instruction is generated and sent to the sensor network sub-platform to control the sensor network sub-platform to delete the group to be deleted.

7. The method according to claim 6, characterized in that The method further comprises: Acquire multiple associated sub-platforms of the sensor network sub-platform; The future retrieval feature is determined based on the first stored data corresponding to the multiple associated sub-platforms.

8. The method according to claim 7, characterized in that The determining the future retrieval feature based on the first stored data corresponding to the multiple associated sub-platforms includes: Determining a plurality of associated platform groups and intra-group association degrees corresponding to the plurality of associated platform groups based on the second retrieved features corresponding to the plurality of sensor network sub-platforms; Based on the multiple associated platform groups, determining the multiple associated sub-platforms; The future retrieval feature is determined based on the intra-group association levels corresponding to the multiple associated sub-platforms and the first stored data.

9. The method according to claim 8, characterized in that The method further comprises: constructing a data retrieval graph based on the multiple associated platform groups, the intra-group association degrees corresponding to the multiple associated sub-platforms, and the second stored data corresponding to the multiple sensor network sub-platforms, wherein the second stored data includes the first stored data; Based on the data retrieval map, the future retrieval features are determined by a prediction model, and the prediction model is a machine learning model.

10. The method according to claim 6, characterized in that The method further comprises: For a single data packet among the plurality of data packets: Acquire multiple associated data groups of the data group; Determining an estimated call feature of the data group based on the plurality of associated data groups and the group call features of the data group; Based on the estimated retrieved features, the to-be-deleted group is adjusted.

Images