An RFID fixed asset inventory system and method based on the Internet of Things

Abstract

The present invention relates to an RFID fixed asset inventory system and method based on the Internet of Things, and relates to the technical field of asset inventory. The system comprises: an RFID module, comprising a plurality of RFID readers and a plurality of RFID tags arranged in a fixed asset inventory area, wherein each fixed asset is provided with an RFID tag, and the RFID tag is used to upload a heartbeat data packet to an RFID reader corresponding to a reading sub-area where the fixed asset is located; a status acquisition module, comprising a plurality of sound monitoring devices and a plurality of status acquisition devices; a status determination module, comprising a plurality of edge determination devices, wherein the plurality of edge determination devices are used to determine the real-time status of the fixed assets based on the sound information collected by the plurality of sound monitoring devices and the status information of the fixed assets collected by the plurality of status acquisition devices; and a digital twin module, which is used to establish a digital twin model of a fixed asset inventory area, and based on the real-time status of the fixed assets, update the digital twin model in real time, and has the advantage of improving the inventory quality of the fixed assets.

Description

Technical Field

[0001] The present invention relates to the technical field of asset inventory counting, and in particular to an RFID fixed asset inventory counting system and method based on the Internet of Things. Background Art

[0002] Fixed assets of enterprises are characterized by high value, long life cycle, scattered locations, and difficulty in inventory. Asset status is often not updated in time, and there is no record after loss, resulting in unknown whereabouts of assets. Most existing fixed asset inventory systems use paper coding or QR code coding, which has problems such as cumbersome fixed asset entry and exit procedures, chaotic fixed asset life cycle inventory procedures, heavy asset inventory workload, and lack of asset anti-theft functions.

[0003] Therefore, it is necessary to provide an RFID fixed asset inventory system and method based on the Internet of Things to improve the inventory quality of fixed assets. Summary of the invention

[0004] The present invention provides an RFID fixed asset inventory system based on the Internet of Things, comprising: an RFID module, comprising a plurality of RFID readers and a plurality of RFID tags arranged in a fixed asset inventory area, wherein each fixed asset is provided with the RFID tag, and at least one RFID tag is arranged in a reading sub-area corresponding to each of the RFID readers, and the RFID tag is used to upload a heartbeat data packet to the RFID reader corresponding to the reading sub-area where it is located; a status acquisition module, comprising a plurality of sound monitoring devices and a plurality of status acquisition devices, wherein the plurality of sound monitoring devices are respectively arranged at a plurality of positions in the fixed asset inventory area, and each of the fixed assets is provided with a status acquisition device, and the status acquisition device is used to collect status information of the fixed assets; a status determination module, comprising a plurality of edge determination devices, and the plurality of edge determination devices are used to determine the real-time status of the fixed assets based on the sound information collected by the plurality of sound monitoring devices and the status information of the fixed assets collected by the plurality of status acquisition devices; a digital twin module, used to establish a digital twin model of the fixed asset inventory area, and based on the real-time status of the fixed assets uploaded by the plurality of edge determination devices, update the digital twin model of the fixed asset inventory area in real time.

[0005] Furthermore, the state acquisition device also includes a vibration sensor, an inertial sensor and a pressure sensor.

[0006] Furthermore, the multiple edge determination devices include a first edge determination device and multiple second edge determination devices, wherein the first edge determination device is used to adjust the data collection frequency of the multiple status acquisition devices based on the sound information collected by the multiple sound monitoring devices; each of the second edge determination devices corresponds to at least one status acquisition device, and the second edge determination device is used to collect the status information of the fixed assets based on the corresponding status acquisition device, and determine the real-time status of the fixed assets corresponding to the status acquisition device.

[0007] Furthermore, the first edge determination device adjusts the data collection frequency of the multiple status collection devices based on the sound information collected by the multiple sound monitoring devices, including: the status collection device collects the status information of the fixed assets based on a first preset collection frequency; determines a sound abnormal sub-region based on the sound information collected by the multiple sound monitoring devices; determines an abnormal reading sub-region from multiple reading sub-regions based on the sound abnormal sub-region; and adjusts the data collection frequency of the status collection device in the abnormal reading sub-region to a second preset collection frequency, wherein the second preset collection frequency is greater than the first preset collection frequency.

[0008] Furthermore, the first edge determination device determines the abnormal sound sub-area based on the sound information collected by the multiple sound monitoring devices, including: for each of the sound monitoring devices, determining the induced sound intensity of the sound monitoring device at multiple time points based on the sound information collected by the sound monitoring device; and determining the abnormal sound sub-area based on the sound intensity of each of the sound monitoring devices at multiple sound collection time points.

[0009] Furthermore, the second edge determination device determines the real-time status of the fixed asset corresponding to the state acquisition device based on the status information of the fixed asset collected by the corresponding state acquisition device, including: for each of the state acquisition devices, the second edge determination device corresponding to the state acquisition device performs data denoising on the vibration information, inertia information and pressure information collected by the state acquisition device at multiple time points, and the second edge determination device corresponding to the state acquisition device determines the risk value of the fixed asset corresponding to the state acquisition device based on the denoised vibration information, inertia information and pressure information collected by the state acquisition device at multiple time points; when the risk value of the fixed asset corresponding to the state acquisition device is greater than a preset risk value threshold, the real-time position of the fixed asset is determined based on the RFID tag set on the fixed asset corresponding to the state acquisition device, and the real-time status of the fixed asset corresponding to the state acquisition device is determined based on the real-time position of the fixed asset.

[0010] Furthermore, the second edge determination device corresponding to the state acquisition device performs data denoising on the vibration information, inertia information and pressure information collected by the state acquisition device at multiple time points, including: extracting vibration frequency domain features and vibration time domain features based on the vibration information collected by the state acquisition device at multiple time points; extracting inertia frequency domain features and inertia time domain features based on the inertia information collected by the state acquisition device at multiple time points; extracting pressure frequency domain features and pressure time domain features based on the pressure information collected by the state acquisition device at multiple time points; performing data denoising on the vibration information, inertia information and pressure information collected by the state acquisition device at multiple time points based on the vibration frequency domain features, vibration time domain features, inertia frequency domain features, inertia time domain features, pressure frequency domain features and pressure time domain features through a multimodal denoising model.

[0011] Furthermore, the state determination module also includes a computing power scheduling device, which is used to adjust the real-time correspondence between the multiple second edge determination devices and the multiple state acquisition devices based on the data acquisition frequency of each of the state acquisition devices.

[0012] Furthermore, the computing power scheduling device adjusts the real-time correspondence between the multiple second edge determination devices and the multiple state acquisition devices based on the data acquisition frequency of each of the state acquisition devices, including: taking the fixed assets where the RFID tags in the abnormal reading sub-area are located as abnormal fixed assets, taking the state acquisition devices corresponding to the abnormal fixed assets as abnormal state acquisition devices, and taking the second edge determination devices corresponding to the state acquisition devices as the second edge determination devices to be scheduled; based on the abnormal state acquisition devices and the second edge determination devices to be scheduled, adjusting the real-time correspondence between the multiple second edge determination devices and the multiple state acquisition devices.

[0013] The present invention provides an RFID fixed asset inventory method based on the Internet of Things, comprising: uploading a heartbeat data packet by an RFID tag set on a fixed asset stored in a fixed asset inventory area to an RFID reader corresponding to the reading sub-area where the RFID tag is located; determining the real-time status of the fixed asset based on sound information at multiple locations in the fixed asset inventory area and status information of the fixed asset; establishing a digital twin model of the fixed asset inventory area; and updating the digital twin model of the fixed asset inventory area in real time based on the real-time status of the fixed asset.

[0014] Compared with the prior art, the RFID fixed asset inventory system and method based on the Internet of Things provided in this specification has at least the following beneficial effects:

[0015] 1. By setting RFID tags, multiple sound monitoring devices and multiple status collection devices on fixed assets, the location, quantity and status of assets can be understood in real time, achieving comprehensive control over fixed assets and helping to prevent asset loss and theft;

[0016] It can collect and analyze relevant data of assets, such as usage, maintenance records, etc. These data help enterprises make better decisions, improve asset utilization and maintenance effects. At the same time, data analysis and mining can also provide decision-making support for enterprises and optimize the configuration and use of assets. It reduces the time and effort of finding assets. This improves work efficiency and reduces labor costs. The ability to monitor and track assets in real time reduces the risk of asset loss and theft, further reducing the cost of the enterprise. RFID technology has the characteristics of high precision and high reliability, and can accurately record the information and location of assets. This improves the accuracy of asset inventory and avoids errors and omissions in traditional manual inventory methods. In addition, the entire life cycle of assets can be counted, including purchase, procurement, allocation, collection, inventory, repair, maintenance, depreciation, scrapping and other links. This helps enterprises fully understand the usage and value changes of assets and provide enterprises with better asset inventory services. When the real-time status of fixed assets changes, the digital twin model of the fixed asset inventory area can be updated in real time.

[0017] 2. Based on the sound information collected by multiple sound monitoring devices, the data collection frequency of multiple status acquisition devices is adjusted to detect potential problems or abnormal conditions earlier, so that timely measures can be taken to avoid the occurrence or expansion of failures. When the collection frequency of the status acquisition device is too high, a large amount of data will be generated, which will increase the cost of data storage, transmission and processing. By reducing the data collection frequency, the amount of data can be reduced and the data processing cost can be reduced while maintaining adequate monitoring of the status of fixed assets. Too frequent data collection may cause a certain burden on the second edge judgment device, such as sensor wear and shortened battery life. By adjusting the data collection frequency, the burden on the second edge judgment device can be reduced and the service life of the second edge judgment device can be extended.

[0018] 3. Through the multimodal denoising model, based on vibration frequency domain characteristics, vibration time domain characteristics, inertia frequency domain characteristics, inertia time domain characteristics, pressure frequency domain characteristics and pressure time domain characteristics, the vibration information, inertia information and pressure information collected by the state acquisition device at multiple time points are denoised from a higher dimension, thereby improving the accuracy of the vibration information, inertia information and pressure information collected by the state acquisition device at multiple time points after denoising.

[0019] 4. Based on the data collection frequency of each state acquisition device, the real-time correspondence between multiple second edge judgment devices and multiple state acquisition devices is dynamically adjusted. Flexible deployment can be performed according to the real-time computing power requirements of the state acquisition device to ensure that the analysis task of the data collected by the abnormal state acquisition device can be completed in the shortest time and meet the real-time requirements of the application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] 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:

[0021] Figure 1 It is a module diagram of an RFID fixed asset inventory system based on the Internet of Things shown in an embodiment of the present application;

[0022] Figure 2 is a flow chart of data denoising shown in one embodiment of the present application;

[0023] Figure 3 It is a flow chart of an RFID fixed asset inventory method based on the Internet of Things shown in one embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly introduces the drawings required for describing the embodiments.

[0025] Figure 1 FIG. 1 is a module diagram of an RFID fixed asset inventory system based on the Internet of Things shown in an embodiment of the present application, such as Figure 1 As shown, an RFID fixed asset inventory system based on the Internet of Things includes an RFID module, a status acquisition module, a status determination module and a digital twin module.

[0026] The RFID module may include multiple RFID readers and multiple RFID tags set in the fixed asset inventory area, wherein an RFID tag is set on each fixed asset, and at least one RFID tag is set in the reading sub-area corresponding to each RFID reader. The RFID tag is used to upload the heartbeat data packet to the RFID reader corresponding to the reading sub-area where it is located.

[0027] The heartbeat data packet of the RFID tag may include:

[0028] Asset unique identification (ID): Each RFID tag has a unique ID that is used to uniquely identify and track fixed assets;

[0029] Asset name and description: Tags can store the name and a brief description of an asset so that people can quickly identify and understand the type and purpose of the asset;

[0030] Asset type: such as office equipment, production equipment, vehicles, etc., for classification and inventory;

[0031] Asset location: The preset location information for storing assets in the fixed asset inventory area can be used;

[0032] Asset status: such as in use, idle, under repair, scrapped, etc., to facilitate understanding of asset usage;

[0033] Supplier information: information about the manufacturer or supplier of the asset for subsequent purchase or repair;

[0034] Purchase date and cost: The purchase date and original cost of the asset, used for asset inventory and financial analysis;

[0035] Using department and user: record the information of the current using department and user of the asset to facilitate asset allocation and tracking;

[0036] Depreciation information: the asset's depreciation status, depreciation method, depreciated amount, etc., for financial and tax reporting;

[0037] Maintenance history: record the maintenance history of assets, including maintenance date, maintenance content, maintenance cost, etc., to facilitate asset maintenance and cost analysis;

[0038] Security attributes: can include information such as the security level and access rights of assets to ensure the safe and compliant use of assets.

[0039] The RFID reader can realize group reading of RFID tags, with the group reading quantity >200 per second, and quickly read the electronic tag information on the equipment in batches to achieve efficient inventory.

[0040] The status acquisition module may include multiple sound monitoring devices and multiple status acquisition devices, wherein the multiple sound monitoring devices are respectively arranged at multiple locations in the fixed asset inventory area, and a status acquisition device is arranged on each fixed asset, and the status acquisition device is used to collect status information of the fixed asset.

[0041] In some embodiments, the state acquisition device further includes a vibration sensor, an inertial sensor, and a pressure sensor.

[0042] The status determination module may include multiple edge determination devices, where the multiple edge determination devices are used to determine the real-time status of the fixed assets based on the sound information collected by multiple sound monitoring devices and the status information of the fixed assets collected by multiple status collection devices.

[0043] In some embodiments, the plurality of edge determination devices include a first edge determination device and a plurality of second edge determination devices, wherein the first edge determination device is used to adjust the data collection frequency of the plurality of state collection devices based on the sound information collected by the plurality of sound monitoring devices. Each second edge determination device corresponds to at least one state collection device, and the second edge determination device is used to collect the state information of the fixed asset based on the corresponding state collection device, and determine the real-time state of the fixed asset corresponding to the state collection device.

[0044] In some embodiments, the first edge determination device adjusts the data collection frequency of the plurality of state collection devices based on the sound information collected by the plurality of sound monitoring devices, including:

[0045] The status collection device collects status information of the fixed assets based on a first preset collection frequency;

[0046] Determine the abnormal sound sub-area based on the sound information collected by multiple sound monitoring devices;

[0047] determining an abnormal reading subregion from among a plurality of reading subregions based on the abnormal sound subregion;

[0048] The data collection frequency of the status collection device in the abnormal reading sub-area is adjusted to a second preset collection frequency, wherein the second preset collection frequency is greater than the first preset collection frequency.

[0049] In some embodiments, the first edge determination device determines the abnormal sound sub-region based on the sound information collected by the plurality of sound monitoring devices, including:

[0050] For each sound monitoring device, determining the intensity of the induced sound of the sound monitoring device at multiple time points based on the sound information collected by the sound monitoring device;

[0051] Based on the sound intensity of each sound monitoring device at multiple sound collection time points, the sound abnormal sub-area is determined.

[0052] Specifically, for each sound monitoring device, the sound change parameter of the sound monitoring device may be determined based on the sensed sound intensity of the sound monitoring device at multiple time points according to the following formula:

[0053] ;

[0054] in, is the sound change parameter of the i-th sound monitoring device, is the induced sound intensity of the i-th sound monitoring device at the t-th time point, is the total number of time points.

[0055] The sound effective parameter is determined based on the sound change parameter corresponding to each sound monitoring device according to the following formula. When the sound effective parameter is greater than the preset sound effective parameter threshold, the sound abnormal sub-area is determined based on the sound intensity of each sound monitoring device at multiple sound collection time points:

[0056] ;

[0057] ;

[0058] in, is the effective parameter of the sound. is the total number of sound monitoring devices, is the difference between the sound change parameter of the i-th sound monitoring device and the sound change parameter of the i+1-th sound monitoring device, is a preset difference between the sound change parameter of the i-th sound monitoring device and the sound change parameter of the i+1-th sound monitoring device, is the sound change parameter of the i+1th sound monitoring device.

[0059] The preset difference between the sound change parameters of the ith sound monitoring device and the sound change parameters of the i+1th sound monitoring device can be calculated through test data. Specifically, multiple tests are performed, and the difference between the sound change parameters of the ith sound monitoring device and the sound change parameters of the i+1th sound monitoring device in each test is calculated. The average of the difference between the sound change parameters of the ith sound monitoring device and the sound change parameters of the i+1th sound monitoring device in each test is used as the preset difference between the sound change parameters of the ith sound monitoring device and the sound change parameters of the i+1th sound monitoring device.

[0060] The abnormal sound sub-area may be an area in the fixed asset inventory area where abnormal sounds occur.

[0061] The abnormal reading sub-region may be a reading sub-region that at least partially overlaps with the abnormal sound sub-region.

[0062] The sound abnormality sub-region can be determined based on the sound intensity of each sound monitoring device at multiple sound collection time points through a region determination model, wherein the region determination model can be a long short-term memory network (LSTM, Long Short-Term Memory) model.

[0063] In some embodiments, the second edge determination device collects status information of the fixed asset based on the corresponding status collection device, and determines the real-time status of the fixed asset corresponding to the status collection device, including:

[0064] For each state acquisition device, the second edge determination device corresponding to the state acquisition device performs data denoising on vibration information, inertia information and pressure information collected by the state acquisition device at multiple time points, and the second edge determination device corresponding to the state acquisition device determines the risk value of the fixed asset corresponding to the state acquisition device based on the denoised vibration information, inertia information and pressure information collected by the state acquisition device at multiple time points, wherein the inertia information may include at least acceleration;

[0065] When the risk value of the fixed assets corresponding to the status acquisition device is greater than the preset risk value threshold, the real-time location of the fixed assets is determined based on the RFID tags set on the fixed assets corresponding to the status acquisition device, and the real-time status of the fixed assets corresponding to the status acquisition device is determined based on the real-time location of the fixed assets.

[0066] Specifically, the risk value of the fixed assets corresponding to the state acquisition device can be determined according to the following formula based on the vibration information, inertia information and pressure information collected by the state acquisition device at multiple time points after denoising:

[0067] ;

[0068] in, For the The risk value of a fixed asset, For the The status collection device of the fixed asset is in the The vibration amplitude collected at each time point, is the preset vibration amplitude threshold, For the The status collection device of the fixed asset is in the The acceleration collected at each time point, is the preset acceleration threshold, For the The status collection device of the fixed asset is in the The pressure value collected at each time point, is the preset pressure threshold, , and is the preset weight, , and are greater than 0, and .

[0069] Figure 2 is a flow chart of performing data denoising shown in an embodiment of the present application, such as Figure 2As shown, in some embodiments, the second edge determination device corresponding to the state acquisition device performs data denoising on the vibration information, inertia information, and pressure information collected by the state acquisition device at multiple time points, including:

[0070] Extract vibration frequency domain features and vibration time domain features based on vibration information collected by the state acquisition device at multiple time points;

[0071] Based on the inertial information collected by the state acquisition device at multiple time points, extract the inertial frequency domain features and inertial time domain features;

[0072] Based on the pressure information collected by the state acquisition device at multiple time points, the pressure frequency domain characteristics and pressure time domain characteristics are extracted;

[0073] The vibration information, inertia information and pressure information collected by the state acquisition device at multiple time points are denoised based on the vibration frequency domain characteristics, vibration time domain characteristics, inertia frequency domain characteristics, inertia time domain characteristics, pressure frequency domain characteristics and pressure time domain characteristics through a multimodal denoising model, wherein the multimodal denoising model can be a convolutional neural network (CNN) model.

[0074] Specifically, the vibration feature extraction model can be used to extract vibration frequency domain features and vibration time domain features based on vibration information collected by the state acquisition device at multiple time points. The inertia feature extraction model can be used to extract inertia frequency domain features and inertia time domain features based on inertia information collected by the state acquisition device at multiple time points. The pressure feature extraction model can be used to extract pressure frequency domain features and pressure time domain features based on pressure information collected by the state acquisition device at multiple time points. Among them, the vibration feature extraction model, the inertia feature extraction model and the pressure feature extraction model can be generative adversarial network (GAN) models.

[0075] In some embodiments, the state determination module also includes a computing power scheduling device, which is used to adjust the real-time correspondence between multiple second edge determination devices and multiple state acquisition devices based on the data acquisition frequency of each state acquisition device.

[0076] In some embodiments, the computing power scheduling device adjusts the real-time correspondence between the plurality of second edge determination devices and the plurality of state acquisition devices based on the data acquisition frequency of each state acquisition device, including:

[0077] The fixed asset where the RFID tag in the abnormal reading sub-area is located is regarded as an abnormal fixed asset, the state acquisition device corresponding to the abnormal fixed asset is regarded as an abnormal state acquisition device, and the second edge determination device corresponding to the state acquisition device is regarded as the second edge determination device to be scheduled;

[0078] Based on the abnormal state collection device and the second edge determination device to be scheduled, the real-time correspondence between the plurality of second edge determination devices and the plurality of state collection devices is adjusted.

[0079] Specifically, the real-time correspondence between multiple second edge determination devices and multiple state acquisition devices can be adjusted through a computing power scheduling model based on the abnormal state acquisition device and the second edge determination device to be scheduled. The computing power scheduling model can be a convolutional neural network (CNN) model.

[0080] The digital twin module can be used to establish a digital twin model of the fixed asset inventory area, and based on the real-time status of fixed assets uploaded by multiple edge judgment devices, the digital twin model of the fixed asset inventory area is updated in real time. The real and virtual elements are connected and integrated with each other, and the real world and virtual world of asset inventory are seamlessly superimposed and twinned with each other.

[0081] Specifically, the digital twin model of the fixed asset inventory area can be established according to the following steps:

[0082] S11. Demand Analysis and Planning:

[0083] Identify specific needs and goals for fixed asset inventory areas, such as asset tracking, condition monitoring, maintenance inventory, etc. Plan the functions and features required for the digital twin model and determine the type of data that needs to be collected (such as location data, maintenance records, etc.).

[0084] S12. Data collection and integration:

[0085] Collect relevant data in the fixed asset inventory area, including asset lists, location information, maintenance records, etc.

[0086] Data from different systems (such as ERP, CMMS, etc.) can be integrated to ensure the accuracy and completeness of the data.

[0087] The collected data are cleaned, organized and standardized to facilitate subsequent modeling and analysis.

[0088] S13. Modeling and simulation:

[0089] Based on the collected data, use modeling tools and technologies (such as CAD, BIM, etc.) to build a 3D model of the fixed asset inventory area.

[0090] Integrate detailed information about assets, including asset type, location, etc., into the 3D model of the fixed asset inventory area.

[0091] Use simulation technology to simulate the operation of the fixed asset inventory area, including the movement of assets, maintenance operations, etc.

[0092] S14. Construction of digital twin model:

[0093] Based on the 3D model of the fixed asset inventory area, a digital twin model is constructed by combining simulation results and actual needs.

[0094] S15. Model verification and optimization:

[0095] Use real data to validate the digital twin model to ensure its accuracy and reliability.

[0096] The model is optimized based on the verification results to improve the model's prediction accuracy and response speed.

[0097] S16. System Integration and Deployment:

[0098] Integrate the digital twin model into the fixed asset inventory system or related platform.

[0099] Deploy the necessary hardware and software to ensure that the digital twin model can function properly and work with other systems.

[0100] The real-time status of the fixed assets determined by the status determination module can be displayed in the digital twin model of the fixed asset inventory area, and the digital twin model of the fixed asset inventory area can be updated in real time based on the update of the real-time status of the fixed assets.

[0101] Figure 3 FIG. 1 is a flowchart of an RFID fixed asset inventory method based on the Internet of Things shown in an embodiment of the present application, such as Figure 3 As shown, an RFID fixed asset inventory method based on the Internet of Things may include:

[0102] Step 310, the RFID tags set on the fixed assets stored in the fixed asset inventory area upload the heartbeat data packet to the RFID reader corresponding to the reading sub-area;

[0103] Step 320, determining the real-time status of the fixed assets based on the sound information of the multiple locations in the fixed asset inventory area and the status information of the fixed assets;

[0104] Step 330, establishing a digital twin model of the fixed asset inventory area;

[0105] Step 340, based on the real-time status of the fixed assets, update the digital twin model of the fixed asset inventory area in real time.

[0106] An RFID fixed asset inventory method based on the Internet of Things can be executed by an RFID fixed asset inventory system based on the Internet of Things. For more descriptions of an RFID fixed asset inventory method based on the Internet of Things, please refer to the relevant description of an RFID fixed asset inventory system based on the Internet of Things, which will not be repeated here.

[0107] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. An RFID fixed asset inventory system based on the Internet of Things, characterized in that: include: The RFID module includes a plurality of RFID readers and a plurality of RFID tags arranged in a fixed asset inventory area, wherein each fixed asset is provided with the RFID tag, and at least one RFID tag is arranged in a reading sub-area corresponding to each of the RFID readers, and the RFID tag is used to upload a heartbeat data packet to the RFID reader corresponding to the reading sub-area where the RFID tag is located; A status collection module, comprising a plurality of sound monitoring devices and a plurality of status collection devices, wherein the plurality of sound monitoring devices are respectively arranged at a plurality of locations in the fixed asset inventory area, and each of the fixed assets is provided with a status collection device, and the status collection device is used to collect status information of the fixed assets; A status determination module, comprising a plurality of edge determination devices, wherein the plurality of edge determination devices are used to determine the real-time status of the fixed asset based on the sound information collected by the plurality of sound monitoring devices and the status information of the fixed asset collected by the plurality of status collection devices; A digital twin module, used to establish a digital twin model of the fixed asset inventory area, and update the digital twin model of the fixed asset inventory area in real time based on the real-time status of the fixed assets uploaded by the multiple edge determination devices; The state acquisition device also includes a vibration sensor, an inertial sensor and a pressure sensor; The plurality of edge determination devices include a first edge determination device and a plurality of second edge determination devices, wherein the first edge determination device is used to adjust the data collection frequency of the plurality of state collection devices based on the sound information collected by the plurality of sound monitoring devices; Each of the second edge determination devices corresponds to at least one state acquisition device, and the second edge determination device is used to collect state information of the fixed asset based on the corresponding state acquisition device, and determine the real-time state of the fixed asset corresponding to the state acquisition device; The first edge determination device adjusts the data collection frequency of the multiple state collection devices based on the sound information collected by the multiple sound monitoring devices, including: The status collection device collects the status information of the fixed asset based on a first preset collection frequency; Determining an abnormal sound sub-region based on the sound information collected by the plurality of sound monitoring devices; Based on the abnormal sound sub-region, determining an abnormal reading sub-region from a plurality of reading sub-regions; The data collection frequency of the status collection device in the abnormal reading sub-area is adjusted to a second preset collection frequency, wherein the second preset collection frequency is greater than the first preset collection frequency.

2. The RFID fixed asset inventory system based on the Internet of Things according to claim 1 is characterized in that: The first edge determination device determines the abnormal sound sub-area based on the sound information collected by the multiple sound monitoring devices, including: For each of the sound monitoring devices, determining the induced sound intensity of the sound monitoring device at multiple time points based on the sound information collected by the sound monitoring device; The abnormal sound sub-region is determined based on the sound intensity of each of the sound monitoring devices at a plurality of sound collection time points.

3. The RFID fixed asset inventory system based on the Internet of Things according to claim 1 is characterized in that: The second edge determination device collects the status information of the fixed asset based on the corresponding status collection device, and determines the real-time status of the fixed asset corresponding to the status collection device, including: For each of the state acquisition devices, the second edge determination device corresponding to the state acquisition device performs data denoising on the vibration information, inertia information and pressure information collected by the state acquisition device at multiple time points, and the second edge determination device corresponding to the state acquisition device determines the risk value of the fixed asset corresponding to the state acquisition device based on the denoised vibration information, inertia information and pressure information collected by the state acquisition device at multiple time points; When the risk value of the fixed assets corresponding to the status acquisition device is greater than a preset risk value threshold, the real-time location of the fixed assets is determined based on the RFID tags set on the fixed assets corresponding to the status acquisition device, and the real-time status of the fixed assets corresponding to the status acquisition device is determined based on the real-time location of the fixed assets.

4. The RFID fixed asset inventory system based on the Internet of Things according to claim 3 is characterized in that: The second edge determination device corresponding to the state acquisition device performs data denoising on the vibration information, inertia information and pressure information collected by the state acquisition device at multiple time points, including: Extracting vibration frequency domain features and vibration time domain features based on the vibration information collected by the state acquisition device at multiple time points; Extracting inertial frequency domain features and inertial time domain features based on inertial information collected by the state acquisition device at multiple time points; Extracting pressure frequency domain features and pressure time domain features based on the pressure information collected by the state acquisition device at multiple time points; The vibration information, inertia information and pressure information collected by the state acquisition device at multiple time points are denoised by a multimodal denoising model based on the vibration frequency domain characteristics, vibration time domain characteristics, inertia frequency domain characteristics, inertia time domain characteristics, pressure frequency domain characteristics and pressure time domain characteristics.

5. The RFID fixed asset inventory system based on the Internet of Things according to claim 4 is characterized in that: The state determination module also includes a computing power scheduling device, which is used to adjust the real-time correspondence between the multiple second edge determination devices and the multiple state acquisition devices based on the data acquisition frequency of each of the state acquisition devices.

6. The RFID fixed asset inventory system based on the Internet of Things according to claim 5 is characterized in that: The computing power scheduling device adjusts the real-time correspondence between the plurality of second edge determination devices and the plurality of state acquisition devices based on the data acquisition frequency of each of the state acquisition devices, including: The fixed asset where the RFID tag in the abnormal reading sub-area is located is regarded as an abnormal fixed asset, the state acquisition device corresponding to the abnormal fixed asset is regarded as an abnormal state acquisition device, and the second edge determination device corresponding to the state acquisition device is regarded as a second edge determination device to be scheduled; Based on the abnormal state collection device and the second edge determination device to be scheduled, the real-time correspondence between the plurality of second edge determination devices and the plurality of state collection devices is adjusted.

7. An RFID fixed asset inventory method based on the Internet of Things, applied to an RFID fixed asset inventory system based on the Internet of Things as claimed in any one of claims 1 to 6, characterized in that: include: The RFID tags set on the fixed assets stored in the fixed asset inventory area upload the heartbeat data packet to the RFID reader corresponding to the reading sub-area; Determine the real-time status of the fixed assets based on the sound information of multiple locations in the fixed asset inventory area and the status information of the fixed assets; Establishing a digital twin model of the fixed asset inventory area; Based on the real-time status of the fixed assets, the digital twin model of the fixed asset inventory area is updated in real time.

Images