An IoT asset positioning system based on identification resolution system

Abstract

The present invention discloses an Internet of Things asset positioning system based on an identification resolution system, which relates to the field of network communication and positioning technology, and solves the problem that the existing system does not support accurate positioning and management of Internet of Things assets during the flow and exchange process across enterprises and regions; the asset positioning system includes a device communication end and an asset positioning end; the device communication end includes an active identification carrier module and an information transmission module; the asset positioning end includes an identification resolution docking module, a data analysis and processing module, an asset positioning service module and a display and early warning module; the real-time data of the equipment collected is detected and backed up through an anomaly detection model, and all equipment is positioned through the asset positioning service module; the real-time data of the equipment is collected and the equipment identification code is generated through the active identification carrier module; the data calculation load of the identification resolution server is reduced, the efficient and stable operation of the asset positioning system is ensured, and the security and reliability of all equipment data in the enterprise are guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of network communication and positioning technology, and in particular to an Internet of Things asset positioning system based on an identification resolution system. Background Art

[0002] With the rapid development of enterprise production supply chains, inter-enterprise asset exchange is becoming increasingly frequent. Existing IoT asset positioning systems face technical and data interoperability challenges, hindering effective IoT asset positioning. Currently, mainstream IoT asset positioning systems are dominated by foreign companies (such as Google and IBM) and lack the in-depth application of my country's own, controllable identification resolution system. To meet the needs of cross-enterprise and cross-regional IoT asset positioning and security management, while promoting the application of identification resolution systems in the field of positioning systems, it is necessary to develop an IoT asset positioning system based on identification resolution systems.

[0003] Patent No. CN202110060408.8 discloses an electronic identification plate for automatic positioning equipment based on Internet of Things technology and its use method. The former includes a hardware device and a software processing system. The hardware device includes an RFID module or an Internet of Things card module, a power module, a display device and an ARM processing unit. The power module is connected to the ARM processing unit, and the RFID module or the Internet of Things card module is connected to the ARM processing unit. The use of the electronic identification plate described in the above invention can quickly read the electronic tag information on the equipment during the inventory of power assets, and send the read tag information to the background server for processing through 3G, 4G and other networks; when encountering an emergency, the RFID handheld device will promptly send an abnormal condition signal to the background according to the equipment positioning information, so that it can respond quickly and handle it in time.

[0004] Patent No. CN202411031122.7 discloses a high-precision IoT positioning method and device based on the Beidou satellite system. The method includes: receiving a positioning request from an IoT terminal to obtain information such as the terminal identification, request accuracy, and request frequency; querying a preset terminal configuration database based on the terminal identification to determine the positioning policy template corresponding to the IoT terminal, providing a basis for customized IoT positioning; determining the positioning algorithm and parameter configuration based on the positioning policy template to achieve customized positioning of the IoT terminal, improving flexibility and practicality; and performing customized positioning for the IoT terminal based on the request accuracy, request frequency, and the selected positioning algorithm and parameter configuration. This method can improve the problem of IoT terminal positioning, which occurs during the positioning process, where different IoT terminals have different requirements for positioning accuracy and frequency, resulting in the positioning service being unable to accurately match actual needs and low positioning flexibility.

[0005] However, the above patents and existing systems do not support accurate positioning and management of IoT assets during the flow and exchange process across enterprises and regions, cannot realize the flow and sharing of IoT assets, cannot achieve traceability and transparency of the supply chain, and the management efficiency of IoT assets is low. Enterprises cannot know the location and status of IoT assets in detail at any time, and cannot achieve fine monitoring and scheduling of IoT assets, resulting in obvious idleness and waste of assets, which is not conducive to cooperation and collaboration between enterprises. Summary of the Invention

[0006] The purpose of the present invention is to provide an Internet of Things asset positioning system based on an identification resolution system, which can carry identification codes for different types of devices and actively establish communication connection capabilities and active information sharing through an active identification carrier module and an asset positioning service module, and collect real-time data of the devices and locate abnormalities, so as to reduce the data computing load of the identification resolution server, ensure the efficient and stable operation of the asset positioning system, and protect the security and reliability of all device data in the enterprise.

[0007] The present invention utilizes the following technical solutions:

[0008] An IoT asset positioning system based on an identification resolution system includes a device communication terminal and an asset positioning terminal; wherein,

[0009] The device communication terminal is used to collect real-time data of the device and generate device identification codes through the active identification carrier module, and to connect and transmit data with the asset positioning terminal and several devices using different communication protocols through the information transmission module;

[0010] The asset positioning end is used to resolve the device identification code through the identification resolution docking module combined with the identification resolution system, detect and back up the collected real-time data of the device using the anomaly detection model through the data analysis and processing module, locate all devices through the asset positioning service module, and display the device status and abnormal alarm notification through the display warning module.

[0011] Preferably, the information transmission module uses different communication protocols to connect with the asset positioning end and several devices; the active identification carrier module applies for the enterprise node prefix according to the enterprise authentication information; the enterprise authentication information includes the company organization code, enterprise name, enterprise address, enterprise type and legal representative; at the same time, a list of factories of all enterprises is obtained based on the enterprise name and enterprise address combined with the enterprise type; and the equipment in all factories of the enterprise is clustered to obtain a list of equipment of all factories; the equipment is parsed to obtain all parts of each equipment and obtain an equipment part table; at the same time, the operating data of the equipment is collected by using the sensor network to obtain real-time data of the equipment; and the real-time data of the equipment is asymmetricly encrypted and decrypted, and then loaded into the information transmission module for transmission to the asset positioning end; the equipment includes Internet of Things devices and positioning devices; the real-time data of the equipment includes deployment location, security status, operation log and remote control data.

[0012] Preferably, the identification resolution docking module generates a factory code based on the identification resolution system using the enterprise node combined with the factory list and the enterprise node prefix; at the same time, it generates the equipment category code and the equipment code in sequence based on the equipment list combined with the factory code; at the same time, it obtains the code point code in each part of the equipment based on the equipment location table combined with the real-time data of the equipment; finally, the enterprise node prefix, company organization code, factory code, equipment category code, equipment code, location code and code point code are combined to obtain the equipment identification code, and then the identification code is completed for all equipment; then the identification resolution docking module aggregates the real-time data of the equipment of the same company according to the equipment identification code to obtain the equipment operation overview table, and at the same time, the equipment operation overview table is further divided and aggregated according to the factory code in combination with the real-time data of the equipment to obtain the equipment management table, and at the same time, the equipment management table of the same equipment is expanded according to the equipment attributes combined with the equipment code to obtain the equipment details list, thereby completing the identification resolution of the equipment real-time data; finally, the equipment operation overview table, equipment management table and equipment details list are hierarchically nested using the knowledge graph to obtain the identification coding map, thereby completing the identification registration of all equipment and transmitting it to the recursive resolution node.

[0013] Preferably, the identity resolution system includes a top-level node, a secondary node, an enterprise node, and a recursive resolution node; the operating mechanism of the identity resolution system is:

[0014] According to the enterprise node prefix in the recursive parsing node and the enterprise address, all device identification codes in the enterprise node are associated and allocated to obtain a regional identification list, and are classified as comprehensive secondary nodes in the secondary nodes;

[0015] Divide the regional identifier list according to the industry to which the enterprise belongs and the enterprise scale to obtain an industry identifier sublist, and classify it into industry-type secondary nodes in the secondary nodes;

[0016] The top-level node connects and parses the secondary node based on the docking application information and the access application protocol to obtain identification statistics, metadata, and master data;

[0017] The top-level node divides the metadata and master data of comprehensive and industry-specific secondary nodes into several batches of synchronized data sets based on identification statistical data and data synchronization channels.

[0018] The top-level node synchronizes and expands the metadata in each batch of synchronized data sets based on data attributes and updates feedback. At the same time, the master data is reported in a preset format based on the data type, and synchronized in full and incremental ways.

[0019] The top-level node sends monitoring requests to all enterprise nodes and secondary nodes according to the preset resolution port, and receives the security status and operation logs of all enterprise nodes and secondary nodes at the same time.

[0020] Preferably, the data analysis and processing module hierarchically expands the real-time data of all devices according to the device identification code and in combination with the device management table to obtain a device part associated data set;

[0021] At the same time, based on the preset device location threshold set and the device deployment environment information, the real-time data of the device is detected, judged, stored and backed up:

[0022] If the collection interval of the real-time data of adjacent devices is equal to the preset collection time difference, the real-time data of the current device is determined to be valid data, and the data quality is checked by inputting the anomaly detection model and combining it with the device operation overview table to obtain the abnormal device data set and the normal device data set;

[0023] If the collection interval of the real-time data of adjacent devices is not equal to the preset collection time difference, the real-time data of the current device is determined to be suspicious data, and the operating status of the device is checked at the same time:

[0024] If the device is in shutdown or standby mode, the current suspicious data will be marked and converted into valid data, and added to the normal device data set;

[0025] If the device is in normal operation, the current suspicious data will be marked and converted into invalid data. At the same time, the invalid data will be cleaned using a data cleaning algorithm, and a suspicious data set will be constructed based on the collection time.

[0026] If the operating status of the device is abnormal, the current suspicious data will be marked and converted into invalid data, and added to the abnormal device data set.

[0027] Preferably, the workflow of the anomaly detection model is:

[0028] A: The environmental analysis layer of the anomaly detection model uses a reflection mapping algorithm to decompose and sample the device deployment environment information to obtain an environmental stress map.

[0029] B: The feature extraction layer of the anomaly detection model uses an improved ant colony algorithm to extract features from the abnormal device dataset and the normal device dataset according to a preset information extraction mechanism, obtaining the abnormal feature matrix and the normal feature matrix;

[0030] C: The feature association layer of the anomaly detection model uses the frequent pattern growth algorithm and the environmental stress map to associate the abnormal feature matrix with the normal feature matrix to obtain the environment-device feature matrix.

[0031] D: The iterative training layer of the anomaly detection model uses the inertial compression particle swarm algorithm and a preset device location threshold set to iterate the environment-device feature matrix several times to obtain a comprehensive monitoring weight matrix.

[0032] E: The prediction update layer of the anomaly detection model uses the energy-non-saturation loss function to combine the device historical data and the device operation overview table to feedback optimize the comprehensive monitoring weight matrix, and then predict and output abnormal device data and normal device data.

[0033] Preferably, the asset positioning service module performs hierarchical splitting of abnormal equipment data sets and normal equipment data sets according to the equipment identification code in accordance with the identification resolution coding rules and in combination with the equipment deployment environment information, thereby determining the abnormal parts of all equipment, and simultaneously synchronously updating the metadata and master data in the enterprise node in combination with the equipment management table and the equipment detailed list, and filling the abnormal equipment data sets and normal equipment data sets in the equipment management table and the equipment detailed list to obtain the equipment status table, and then completes the deployment position positioning and abnormal part positioning of all equipment in combination with the positioning correction model.

[0034] Preferably, the workflow of the positioning correction model is:

[0035] The communication parsing layer of the positioning correction model analyzes the communication protocols of all devices based on the device identification code and security status, combined with the device distance and signal attenuation value, to obtain a protocol-environment-distance communication table;

[0036] The positioning analysis layer of the positioning correction model analyzes the deployment locations of all devices based on the preset positioning accuracy threshold and signal anti-interference value to obtain a device deployment accuracy table;

[0037] The data judgment layer of the positioning correction model expands and judges the comprehensive monitoring weight matrix based on the protocol-environment-distance communication table and the equipment deployment accuracy table to obtain the positioning data expansion matrix;

[0038] The positioning correction layer of the positioning correction model corrects the deployment position and abnormal parts of the equipment based on the positioning data expansion matrix and abnormal equipment data set, combined with the identification coding map and environmental influencing factors, to obtain the positioning data of the optimal deployment position and abnormal parts.

[0039] Preferably, the display warning module uses a web page to display the completed equipment management table and equipment details to the administrator in real time, and uses notifications to alarm abnormal equipment parts combined with abnormal equipment data, and stores them in the asset positioning database in combination with the equipment status table.

[0040] The present invention detects and backs up the collected real-time data of devices through an anomaly detection model, and locates all devices through the asset positioning service module; collects real-time data of devices and generates device identification codes through the active identification carrier module; and resolves device identification codes through the identification resolution docking module combined with the identification resolution system; reduces the data computing load of the identification resolution server, ensures the efficient and stable operation of the asset positioning system, and guarantees the security and reliability of all device data in the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0042] Figure 1 Schematic diagram of the asset positioning system;

[0043] Figure 2 Schematic diagram of the anomaly detection model principle;

[0044] Figure 3 Provide a flow chart for the asset location system;

[0045] Figure 4 This is the principle diagram of the identity resolution system docking module;

[0046] Figure 5 This is an example diagram of identity resolution encoding rules. DETAILED DESCRIPTION

[0047] The present invention is described in detail below with reference to the accompanying drawings and embodiments:

[0048] like Figures 1 to 5 As shown, the IoT asset positioning system based on the identification resolution system of the present invention includes a device communication terminal and an asset positioning terminal; wherein,

[0049] The device communication terminal is used to collect real-time data of the device and generate device identification codes through the active identification carrier module, and to connect and transmit data with the asset positioning terminal and several devices using different communication protocols through the information transmission module;

[0050] The asset positioning end is used to resolve the device identification code through the identification resolution docking module combined with the identification resolution system, detect and back up the collected real-time data of the device using the anomaly detection model through the data analysis and processing module, locate all devices through the asset positioning service module, and display the device status and abnormal alarm notification through the display warning module.

[0051] In this embodiment, the asset positioning terminal processes and stores the information actively sent by the device in real time. The collected device data is stored in the Greenplum database using message queues or real-time data processing technology. By real-time monitoring and analysis of the device's location and status information, the operating status of the IoT device can be promptly understood:

[0052] By deploying sensors and data collection devices on devices, data is sent to the Greenplum database through real-time streaming processing technologies (such as Apache Kafka and Apache Flink) to achieve real-time data writing and storage.

[0053] Use real-time streaming technology to process and analyze device data in real time. By setting up a real-time monitoring system, data can be aggregated, calculated, and analyzed in real time to promptly detect changes in device status and abnormalities.

[0054] Through data visualization technology, the real-time monitored equipment location and status information is presented to relevant personnel in an intuitive manner. At the same time, an alarm system is established to send alarm notifications to relevant personnel in a timely manner when abnormal equipment status is detected, so that timely action can be taken;

[0055] Ensure real-time synchronization and backup of device data. Utilizing the Greenplum database's multi-copy replication mechanism, data can be synchronized and backed up in real time across a distributed environment, ensuring high data availability and reliability.

[0056] In the present invention, the information transmission module utilizes different communication protocols to connect with the asset positioning terminal and several devices; the active identification carrier module applies for the enterprise node prefix according to the enterprise authentication information; the enterprise authentication information includes the company organization code, enterprise name, enterprise address, enterprise type and legal representative; at the same time, a list of factories of all enterprises is obtained according to the enterprise name and enterprise address combined with the enterprise type; and the equipment in all factories of the enterprise is clustered to obtain a list of equipment of all factories; the equipment is parsed to obtain all parts of each equipment and obtain an equipment part table; at the same time, the operation data of the equipment is collected by using the sensor network to obtain real-time data of the equipment; and the real-time data of the equipment is subjected to asymmetric encryption and decryption operations, and then loaded into the information transmission module for transmission to the asset positioning terminal.

[0057] In this embodiment, the devices include IoT devices and positioning devices;

[0058] Real-time device data includes deployment location, security status, operation logs, and remote control data;

[0059] The deployment location includes geographic location information such as longitude and latitude to accurately understand the location of the device;

[0060] Safety status includes real-time monitoring data such as equipment operating status, working hours, output, temperature, pressure, humidity, etc., so as to timely understand the equipment's operating status and performance indicators;

[0061] The operation log includes the equipment's power on / off records, operation logs, alarm information, etc., in order to track the equipment's operation and abnormal conditions;

[0062] Remote control data includes remote control instructions and feedback information for equipment to facilitate remote operation and regulation;

[0063] The active identification carrier module also collects real-time data from equipment through sensors, PLCs (programmable logic controllers), SCADA systems (supervisory control and data acquisition systems), and other devices;

[0064] Communication protocols include RFID, BeiDou, 5G, WiFi, Bluetooth, and UWB;

[0065] In the present invention, the identification resolution docking module generates a factory code based on the identification resolution system using the enterprise node combined with the factory list and the enterprise node prefix; at the same time, the equipment category code and the equipment code are generated in sequence based on the equipment list combined with the factory code; at the same time, the code point code in each part of the equipment is obtained based on the equipment location table combined with the real-time data of the equipment; finally, the enterprise node prefix, company organization code, factory code, equipment category code, equipment code, location code and code point code are combined to obtain the equipment identification code, and then the identification code is completed for all equipment; then the identification resolution docking module aggregates the real-time data of the equipment of the same company according to the equipment identification code to obtain the equipment operation overview table, and at the same time, the equipment operation overview table is further divided and aggregated in combination with the real-time data of the equipment according to the factory code to obtain the equipment management table, and at the same time, the equipment management table of the same equipment is expanded according to the equipment attributes combined with the equipment code to obtain the equipment detailed list, thereby completing the identification resolution of the real-time data of the equipment; finally, the equipment operation overview table, the equipment management table and the equipment detailed list are hierarchically nested using the knowledge graph to obtain the identification coding graph, thereby completing the identification registration of all equipment and transmitting it to the recursive resolution node.

[0066] In this embodiment, the identity resolution system docking module abstracts and manages the unified identity of IoT assets, and provides services such as identity coding, identity resolution, and identity registration for various scenarios and industry applications.

[0067] In the present invention, the identity resolution system includes top-level nodes, secondary nodes, enterprise nodes, and recursive resolution nodes; the operating mechanism of the identity resolution system is:

[0068] According to the enterprise node prefix in the recursive parsing node and the enterprise address, all device identification codes in the enterprise node are associated and allocated to obtain a regional identification list, and are classified as comprehensive secondary nodes in the secondary nodes;

[0069] Divide the regional identifier list according to the industry to which the enterprise belongs and the enterprise scale to obtain an industry identifier sublist, and classify it into industry-type secondary nodes in the secondary nodes;

[0070] The top-level node connects and parses the secondary node based on the docking application information and the access application protocol to obtain identification statistics, metadata, and master data;

[0071] The top-level node divides the metadata and master data of comprehensive and industry-specific secondary nodes into several batches of synchronized data sets based on identification statistical data and data synchronization channels.

[0072] The top-level node synchronizes and expands the metadata in each batch of synchronized data sets based on data attributes and updates feedback. At the same time, the master data is reported in a preset format based on the data type, and synchronized in full and incremental ways.

[0073] The top-level node sends monitoring requests to all enterprise nodes and secondary nodes according to the preset resolution port, and receives the security status and operation logs of all enterprise nodes and secondary nodes at the same time.

[0074] In the present invention, the data analysis and processing module hierarchically expands the real-time data of all devices according to the device identification code and in combination with the device management table to obtain a device part associated data set;

[0075] In this embodiment, hierarchical expansion is to decompose complex information into logical levels or modules.

[0076] At the same time, based on the preset device location threshold set and the device deployment environment information, the real-time data of the device is detected, judged, stored and backed up:

[0077] If the collection interval of the real-time data of adjacent devices is equal to the preset collection time difference, the real-time data of the current device is determined to be valid data, and the data quality is checked by inputting the anomaly detection model and combining it with the device operation overview table to obtain the abnormal device data set and the normal device data set;

[0078] If the collection interval of the real-time data of adjacent devices is not equal to the preset collection time difference, the real-time data of the current device is determined to be suspicious data, and the operating status of the device is checked at the same time:

[0079] If the device is in shutdown or standby mode, the current suspicious data will be marked and converted into valid data, and added to the normal device data set;

[0080] If the device is in normal operation, the current suspicious data will be marked and converted into invalid data. At the same time, the invalid data will be cleaned using a data cleaning algorithm, and a suspicious data set will be constructed based on the collection time.

[0081] If the operating status of the device is abnormal, the current suspicious data will be marked and converted into invalid data, and added to the abnormal device data set.

[0082] In the present invention, the workflow of the anomaly detection model is as follows:

[0083] A: The environmental analysis layer of the anomaly detection model uses a reflection mapping algorithm to decompose and sample the device deployment environment information to obtain an environmental stress map.

[0084] B: The feature extraction layer of the anomaly detection model uses an improved ant colony algorithm to extract features from the abnormal device dataset and the normal device dataset according to a preset information extraction mechanism, obtaining the abnormal feature matrix and the normal feature matrix;

[0085] C: The feature association layer of the anomaly detection model uses the frequent pattern growth algorithm and the environmental stress map to associate the abnormal feature matrix with the normal feature matrix to obtain the environment-device feature matrix.

[0086] D: The iterative training layer of the anomaly detection model uses the inertial compression particle swarm algorithm and a preset device location threshold set to iterate the environment-device feature matrix several times to obtain a comprehensive monitoring weight matrix.

[0087] E: The prediction update layer of the anomaly detection model uses the energy-non-saturation loss function to combine the device historical data and the device operation overview table to feedback optimize the comprehensive monitoring weight matrix, and then predict and output abnormal device data and normal device data.

[0088] In this embodiment, the energy-non-saturation loss function is:

[0089] Assume that the discriminator is an autoencoder and the energy function is defined as the reconstruction error E(x):

[0090] E(t)=||Dec(Enc(t))-t|| 2

[0091] Where t is the comprehensive monitoring weight matrix, Enc(·) is the encoder, and Dec(·) is the decoder;

[0092] Among them, the discriminator needs to meet the following requirements: r , minimize the energy E(t r ); for the generated data G(z), maximize the energy E(G(z)); the discriminator gradient function Generator gradient function E z []; Introduce the non-saturation idea and define the discriminator loss function L D :

[0093]

[0094] The first term minimizes the energy of the real data, and the second term achieves the non-saturated maximization of the energy of the generated data through the logistic function;

[0095] Minimize the energy of generated data and use the non-saturated form to obtain the generator loss function L G :

[0096] L G =-E z [log(1+e -E(G(z)) )

[0097] The gradient of this function is stronger when E(G(z)) is larger, avoiding the gradient vanishing problem of traditional EBGAN.

[0098] In the present invention, the asset positioning service module performs hierarchical splitting of abnormal equipment data sets and normal equipment data sets according to the equipment identification code in accordance with the identification resolution coding rules and in combination with the equipment deployment environment information, thereby determining the abnormal parts of all equipment. At the same time, the metadata and master data in the enterprise node are synchronously updated in combination with the equipment management table and the equipment detailed list. At the same time, the abnormal equipment data sets and the normal equipment data sets are filled in the equipment management table and the equipment detailed list to obtain the equipment status table, and then the deployment position positioning and abnormal part positioning of all equipment are completed in combination with the positioning correction model.

[0099] In this embodiment, the hierarchical splitting is to decompose the complex system / problem into smaller and more manageable sub-units step by step according to the logical level, forming a tree structure, ensuring that the information granularity of each level is consistent and there is no overlap.

[0100] In the present invention, the workflow of the positioning correction model is:

[0101] The communication parsing layer of the positioning correction model analyzes the communication protocols of all devices based on the device identification code and security status, combined with the device distance and signal attenuation value, to obtain a protocol-environment-distance communication table;

[0102] In this embodiment, the device set is i is the device serial number, n is the total number of devices; definition: Ci is the communication protocol characteristic vector of device di; Ei = α·||xi-xAP||+β·Ai, Ei is the environmental attenuation factor (α distance attenuation coefficient, β signal attenuation coefficient, Ai environmental absorption parameter); Si is the security state weight; then the protocol-environment-distance communication table Tcom is generated:

[0103] in, Represents the tensor product operation;

[0104] The positioning analysis layer of the positioning correction model analyzes the deployment locations of all devices based on the preset positioning accuracy threshold and signal anti-interference value to obtain a device deployment accuracy table;

[0105] In this embodiment, the position accuracy threshold is set to ∈th and the anti-interference coefficient is γ, then the device deployment accuracy evaluation Pi is: in is the signal gradient at position xi, is the noise variance; generate the device deployment accuracy table Tpre:

[0106] The data judgment layer of the positioning correction model expands and judges the comprehensive monitoring weight matrix based on the protocol-environment-distance communication table and the equipment deployment accuracy table to obtain the positioning data expansion matrix;

[0107] In this embodiment, the comprehensive monitoring weight matrix W∈R is defined as n×m , through the double table joint expansion: W^=W⊙(Tcom T ·Tpre)+λ·diag(P1,...,Pn); where ⊙ is the Hadamard product and λ is the regularization coefficient; obtain the positioning data expansion matrix Mext: Mext=SVD(W^)·Σk; retain the first k principal components (Σk is the singular value truncation matrix);

[0108] The positioning correction layer of the positioning correction model corrects the deployment position and abnormal parts of the equipment based on the positioning data expansion matrix and abnormal equipment data set, combined with the identification coding map and environmental influencing factors, to obtain the positioning data of the optimal deployment position and abnormal parts;

[0109] In this embodiment, an optimization objective function is constructed, where X is the positioning data matrix of the original deployment position:

[0110]

[0111] Among them, Yobs is the observation data matrix, L is the graph Laplace matrix constructed based on the identification coding map, μ is the regularization parameter, F is the Frobenius norm; the positioning data X of the optimal deployment position * :

[0112] X * =(Mext T Mext+μL) -1 Mext T Yobs;

[0113] Abnormal part detection is done through residual analysis: Δ=||Yobs-MextX * ||>τ·σ env , (τ is the environmental factor threshold, σ env is the standard deviation of environmental impact factors);

[0114] In the present invention, the display warning module uses a web page to display the completed equipment management table and equipment details to the administrator in real time, and at the same time uses notifications to alarm abnormal equipment parts combined with abnormal equipment data, and stores them in the asset positioning database in combination with the equipment status table.

[0115] Example:

[0116] The hardware environment required for running the main program: server CPU 16 cores, memory 32G, hard disk 1TGB.

[0117] Software environment required for running the main program: Linux CentOS 7.9 operating system, JAVA JDK8, SpringBoot, SpringCloud, Flink, Kafka, Elasticsearch, MySQL, etc.

[0118] The main program Jar package is run in the mode of nohup java-jar xxx.jar;

[0119] The subroutine calls the Flink window to distribute the device data in Kafka and the Greenplum database to the display and warning module;

[0120] The device communication terminal uses different communication protocols to connect with the asset positioning terminal and several devices through the information transmission module;

[0121] Apply for an enterprise node prefix based on enterprise authentication information through the active identification carrier module; enterprise authentication information includes company organization code, enterprise name, enterprise address, enterprise type, and legal representative; obtain a list of all enterprises' factories based on the enterprise name and address combined with the enterprise type; cluster the equipment in all the enterprises' factories to obtain a list of all the equipment in the factories; parse the equipment to obtain all the parts of each device, and obtain a device part table;

[0122] At the same time, the sensor network is used to collect the operating data of the equipment to obtain real-time data of the equipment. The real-time data of the equipment is then asymmetric encrypted and decrypted, and then loaded into the information transmission module for transmission to the asset positioning end. The equipment includes IoT devices and positioning devices. The real-time data of the equipment includes deployment location, security status, operation log and remote control data.

[0123] The identity resolution docking module of the asset positioning terminal (IoT asset positioning system) generates a factory code based on the identity resolution system using the enterprise node combined with the factory list and the enterprise node prefix; at the same time, it generates the equipment category code and equipment code in sequence based on the equipment list combined with the factory code; at the same time, it obtains the code point code of each part of the equipment based on the equipment location table combined with the real-time data of the equipment; finally, the enterprise node prefix, company organization code, factory code, equipment category code, equipment code, location code and code point code are combined to obtain the equipment identification code, and then the identification code is issued for all equipment; then the identity resolution docking module aggregates the real-time data of the equipment of the same company according to the equipment identification code to obtain the equipment operation summary table, and at the same time, the equipment operation summary table is further divided and aggregated according to the factory code in combination with the real-time data of the equipment to obtain the equipment management table, and at the same time, the equipment management table of the same equipment is expanded according to the equipment attributes combined with the equipment code to obtain the equipment detailed list, thereby completing the identity resolution of the equipment real-time data; finally, the equipment operation summary table, equipment management table and equipment detailed list are hierarchically nested using the knowledge graph to obtain the identification coding map, thereby completing the identification registration of all equipment and transmitting it to the recursive resolution node;

[0124] The data analysis and processing module expands the real-time data of all devices hierarchically based on the device identification code and the device management table to obtain the device part-related data set;

[0125] At the same time, based on the preset device location threshold set and the device deployment environment information, the real-time data of the device is detected, judged, stored and backed up:

[0126] If the collection interval of the real-time data of adjacent devices is equal to the preset collection time difference, the real-time data of the current device is determined to be valid data, and the data quality is checked by inputting the anomaly detection model and combining it with the device operation overview table to obtain the abnormal device data set and the normal device data set;

[0127] If the collection interval of the real-time data of adjacent devices is not equal to the preset collection time difference, the real-time data of the current device is determined to be suspicious data, and the operating status of the device is checked at the same time:

[0128] If the device is in shutdown or standby mode, the current suspicious data will be marked and converted into valid data, and added to the normal device data set;

[0129] If the device is in normal operation, the current suspicious data will be marked and converted into invalid data. At the same time, the invalid data will be cleaned using a data cleaning algorithm, and a suspicious data set will be constructed based on the collection time.

[0130] If the operating status of the device is abnormal, the current suspicious data will be marked and converted into invalid data, and added to the abnormal device data set;

[0131] The asset positioning service module (IoT asset positioning service module) performs hierarchical splitting of abnormal device data sets and normal device data sets according to the device identification code and the identification resolution coding rules, combined with the device deployment environment information, and then determines the abnormal parts of all devices. At the same time, it synchronizes the metadata and master data in the enterprise node with the device management table and the device detailed list, and fills the abnormal device data sets and normal device data sets in the device management table and the device detailed list to obtain the device status table. Then, combined with the positioning correction model, it completes the deployment position positioning and abnormal part positioning of all devices.

[0132] The display warning module uses a web page to display the completed device management table and device details to the administrator in real time. At the same time, it uses notifications to alarm abnormal parts of the equipment combined with abnormal device data, and stores them in the asset positioning database (GreenPlum, the Internet of Things asset positioning system database) in combination with the device status table.

Claims

1. An IoT asset positioning system based on an identification resolution system, characterized by: Including equipment communication terminal and asset positioning terminal; among them, The device communication terminal is used to collect real-time data of the device and generate device identification codes through the active identification carrier module, and to connect and transmit data with the asset positioning terminal and several devices using different communication protocols through the information transmission module; The asset positioning terminal is used to resolve the device identification code through the identification resolution docking module combined with the identification resolution system, detect and back up the collected real-time data of the device using the anomaly detection model through the data analysis and processing module, and locate all devices using the positioning correction model through the asset positioning service module, while displaying the device status and abnormal alarm notification through the display warning module; The data analysis and processing module hierarchically expands the real-time data of all devices according to the device identification code and the device management table to obtain a device part associated data set; At the same time, based on the preset device location threshold set and the device deployment environment information, the real-time data of the device is detected, judged, stored and backed up: If the collection interval of the real-time data of adjacent devices is equal to the preset collection time difference, the real-time data of the current device is determined to be valid data, and the data quality is checked by inputting the anomaly detection model and combining it with the device operation overview table to obtain the abnormal device data set and the normal device data set; If the collection interval of the real-time data of adjacent devices is not equal to the preset collection time difference, the real-time data of the current device is determined to be suspicious data, and the operating status of the device is checked at the same time: If the device is in shutdown or standby mode, the current suspicious data will be marked and converted into valid data, and added to the normal device data set; If the device is in normal operation, the current suspicious data will be marked and converted into invalid data. The invalid data will be cleaned and a suspicious data set will be constructed based on the collection time. If the operating status of the device is abnormal, the current suspicious data will be marked and converted into invalid data, and added to the abnormal device data set; The workflow of the anomaly detection model is as follows: A: The environmental analysis layer of the anomaly detection model uses a reflection mapping algorithm to decompose and sample the device deployment environment information to obtain an environmental stress map. B: The feature extraction layer of the anomaly detection model uses an improved ant colony algorithm to extract features from the abnormal device dataset and the normal device dataset according to a preset information extraction mechanism, obtaining the abnormal feature matrix and the normal feature matrix; C: The feature association layer of the anomaly detection model uses the frequent pattern growth algorithm and the environmental stress map to associate the abnormal feature matrix with the normal feature matrix to obtain the environment-device feature matrix. D: The iterative training layer of the anomaly detection model uses the inertial compression particle swarm algorithm and a preset device location threshold set to iterate the environment-device feature matrix several times to obtain a comprehensive monitoring weight matrix. E: The prediction update layer of the anomaly detection model uses the energy-non-saturation loss function to combine the device historical data and the device operation overview table to feedback optimize the comprehensive monitoring weight matrix, and then predict and output abnormal device data and normal device data.

2. The IoT asset positioning system based on the identification resolution system according to claim 1 is characterized in that: The information transmission module uses different communication protocols to connect with the asset positioning terminal and several devices; the devices include Internet of Things devices and positioning devices.

3. The IoT asset positioning system based on the identification resolution system according to claim 1 is characterized in that: The active identification carrier module applies for an enterprise node prefix according to the enterprise authentication information; Enterprise certification information includes company organization code, enterprise name, enterprise address, enterprise type and legal representative; At the same time, the factory list of all enterprises is obtained according to the enterprise name, enterprise address and enterprise type; And cluster the equipment in all factories of the enterprise to obtain a list of equipment in all factories; The equipment is analyzed to obtain all parts of each equipment and obtain the equipment part table; at the same time, the equipment operation data is collected to obtain the equipment real-time data; and the equipment real-time data is asymmetric encrypted and decrypted, and then loaded into the information transmission module for transmission to the asset positioning end.

4. The IoT asset positioning system based on the identification resolution system according to claim 1 is characterized in that: The identity resolution docking module generates a factory code based on the identity resolution system using the enterprise node combined with the factory list and the enterprise node prefix; At the same time, the equipment category code and equipment code are generated in sequence according to the equipment list combined with the factory code; at the same time, the code point code of each part of the equipment is obtained according to the equipment location table combined with the real-time data of the equipment; finally, the enterprise node prefix, company organization code, factory code, equipment category code, equipment code, location code and code point code are combined to obtain the equipment identification code, and then the identification coding is completed for all equipment; then the identification resolution docking module aggregates the real-time data of the equipment of the same company according to the equipment identification code to obtain the equipment operation overview table, and at the same time, the equipment operation overview table is further divided and aggregated according to the factory code in combination with the real-time data of the equipment to obtain the equipment management table, and at the same time, the equipment management table of the same equipment is expanded according to the equipment attributes combined with the equipment code to obtain the equipment details list, and then the identification resolution of the real-time data of the equipment is completed; finally, the equipment operation overview table, equipment management table and equipment details list are hierarchically nested to obtain the identification coding map, and then the identification registration of all equipment is completed and transmitted to the recursive resolution node.

5. The IoT asset positioning system based on the identification resolution system according to claim 1 is characterized in that: The identity resolution system includes top-level nodes, secondary nodes, enterprise nodes, and recursive resolution nodes. The operating mechanism of the identity resolution system is as follows: According to the enterprise node prefix in the recursive parsing node and the enterprise address, all device identification codes in the enterprise node are associated and allocated to obtain a regional identification list, and are classified as comprehensive secondary nodes in the secondary nodes; The regional identifier list is divided according to the industry to which the enterprise belongs and the enterprise size to obtain an industry identifier sublist, which is classified into industry-type secondary nodes in the secondary nodes; The top-level node connects and parses the secondary node based on the docking application information and the access application protocol to obtain identification statistics, metadata, and master data; The top-level node divides the metadata and master data of comprehensive and industry-specific secondary nodes into several batches of synchronized data sets based on identification statistical data and data synchronization channels. The top-level node synchronizes and expands the metadata in each batch of synchronized data sets based on data attributes and updates feedback. At the same time, the master data is reported in a preset format based on the data type, and synchronized in full and incremental ways. The top-level node sends monitoring requests to all enterprise nodes and secondary nodes according to the preset resolution port, and receives the security status and operation logs of all enterprise nodes and secondary nodes at the same time.

6. The IoT asset positioning system based on the identification resolution system according to claim 1 is characterized in that: The asset positioning service module performs hierarchical splitting of abnormal equipment data sets and normal equipment data sets according to the equipment identification code and the identification resolution coding rules, combined with the equipment deployment environment information, and then determines the abnormal parts of all equipment. At the same time, combined with the equipment management table and the equipment detailed list, the metadata and master data in the enterprise node are synchronously updated, and the abnormal equipment data sets and normal equipment data sets are filled in the equipment management table and the equipment detailed list to obtain the equipment status table, and then combined with the positioning correction model to complete the deployment position positioning and abnormal part positioning of all equipment.

7. The IoT asset positioning system based on the identification resolution system according to claim 1, characterized in that: The workflow of the positioning correction model is as follows: The communication parsing layer of the positioning correction model analyzes the communication protocols of all devices based on the device identification code and security status, combined with the device distance and signal attenuation value, to obtain a protocol-environment-distance communication table; The positioning analysis layer of the positioning correction model analyzes the deployment locations of all devices based on the preset positioning accuracy threshold and signal anti-interference value to obtain a device deployment accuracy table; The data judgment layer of the positioning correction model expands and judges the comprehensive monitoring weight matrix based on the protocol-environment-distance communication table and the equipment deployment accuracy table to obtain the positioning data expansion matrix; The positioning correction layer of the positioning correction model corrects the deployment position and abnormal parts of the equipment based on the positioning data expansion matrix and abnormal equipment data set, combined with the identification coding map and environmental influencing factors, to obtain the positioning data of the optimal deployment position and abnormal parts.

8. The IoT asset positioning system based on the identification resolution system according to claim 1, characterized in that: The display warning module will display the completed equipment management table and equipment details to the administrator in real time, and at the same time, alarm the abnormal parts of the equipment in combination with the abnormal equipment data, and store them in the asset positioning database in combination with the equipment status table.

Images