An experimental equipment management system of internet of things RFID association

Abstract

The application relates to the field of intelligent Internet of Things and equipment management systems, and discloses an experimental equipment management system associated with an Internet of Things RFID, which comprises a collection module for collecting source data; the source data comprises spatial attribute data, function association data, equipment association data and equipment co-occurrence data of experimental equipment in an experimental equipment set deployed in a laboratory; a graph construction module for constructing a dynamic heterogeneous graph based on the source data; a fusion module for performing spatio-temporal fusion on data respectively carried by spatial mutual exclusion edges, function cooperation edges, equipment proximity edges and equipment co-occurrence edges in the dynamic heterogeneous graph to obtain a fusion result; and an equipment management module for determining an expected equipment state of the experimental equipment set in at least one time period based on the fusion result and managing at least part of the experimental equipment set based on the expected equipment state. The scheme can meet diversified experimental equipment management requirements.

Description

Technical Field

[0001] This application relates to the field of intelligent Internet of Things and equipment management systems, specifically to, but not limited to, an experimental equipment management system associated with Internet of Things radio frequency identification (RFID). Background Technology

[0002] In laboratories equipped with the Internet of Things (IoT), experimental equipment is typically equipped with RFID modules. Laboratory management systems can acquire the RFID signals emitted by these modules and use positioning algorithms to determine the location of each device based on the signal strength. The relative positions of the devices are then determined, and management is based on these relative positions. However, this method of managing experimental equipment cannot meet the diverse needs of laboratory equipment management. Summary of the Invention

[0003] Based on the above technical issues, this application provides an IoT RFID-linked experimental equipment management system, which can improve the accuracy and intelligence of managing experimental equipment in a set of experimental equipment, thereby meeting diverse experimental equipment management needs.

[0004] To achieve the above objectives, the technical solution of the present invention is as follows:

[0005] An IoT RFID-linked experimental equipment management system includes:

[0006] The data acquisition module is used to collect source data, which includes spatial attribute data, functional association data, device association data, and device co-occurrence data of the experimental equipment deployed in the laboratory. Spatial attribute data includes at least the layout data of the experimental equipment in the laboratory. Functional association data characterizes the experimental functions of the equipment. Device association data includes the relative positional relationships between the experimental equipment and other equipment. Device co-occurrence data includes descriptive data of at least two experimental devices appearing together in historical experiments. Other equipment includes equipment in the experimental equipment set other than the experimental equipment. The laboratory is also linked to the Internet of Things (IoT) and RFID.

[0007] The graph construction module is used to construct a dynamic heterogeneous graph based on the source data. The dynamic heterogeneous graph includes spatially exclusive edges corresponding to spatial attribute data, functional collaboration edges corresponding to functional association data, device proximity edges corresponding to device association data, and device co-occurrence edges corresponding to device co-occurrence data.

[0008] The fusion module is used to perform spatiotemporal fusion on the data carried by spatially exclusive edges, functional collaborative edges, device proximity edges, and device co-occurrence edges in the dynamic heterogeneous graph to obtain the fusion result.

[0009] The device management module is used to determine the expected device status of the experimental device set within at least one time period based on the fusion results, and to manage at least a portion of the experimental devices in the experimental device set based on the expected device status.

[0010] Furthermore, the acquisition module is also used to obtain the set of device locations corresponding to the experimental equipment;

[0011] The fusion module is also used to integrate the set of device positions to obtain the displacement pattern of the experimental device;

[0012] The device management module is used to determine the expected device status based on the displacement pattern and fusion results.

[0013] Furthermore, the fusion module is used to determine a weight set based on the data carried by spatially exclusive edges, functionally cooperative edges, device proximity edges, and device co-occurrence edges respectively, and to perform fusion processing on the data carried by the spatially exclusive edges, functionally cooperative edges, device proximity edges, and device co-occurrence edges respectively based on the weight set to obtain the fusion result.

[0014] Furthermore, the fusion module is used to process the mutual exclusion state of the nodes associated with the spatial mutual exclusion edge through a logical negation function to obtain a spatial mutual exclusion score, process the functional state of the nodes associated with the functional cooperation edge through a first averaging function to obtain a functional cooperation score, process the co-occurrence state of the nodes associated with the device co-occurrence edge through a second averaging function to obtain a device co-occurrence score, and process the spatial state associated with the device neighbor edge based on the signal strength corresponding to the device neighbor edge to obtain a spatial neighbor score.

[0015] The fusion module is also used to fuse spatial mutual exclusion scores, functional collaboration scores, device co-occurrence scores, and spatial proximity scores based on a weight set to obtain the fusion result.

[0016] Furthermore, the expected equipment status includes at least one of the following: equipment abnormal status, equipment cooperation status, and equipment load status at a future time.

[0017] The equipment management module is used to perform equipment maintenance operations associated with the target equipment and / or related equipment if the expected equipment status includes abnormal equipment status.

[0018] And / or,

[0019] The equipment management module is used to identify and output equipment maintenance prompts if the expected equipment status includes an abnormal equipment status; wherein, the target equipment includes experimental equipment that will be in an abnormal equipment status at a future time; and the associated equipment includes at least one device associated with the target equipment.

[0020] Furthermore, the spatial attribute data includes the equipment dimensions and safety distances of the experimental equipment; the graph construction module is used to process the equipment dimensions, safety distances, and layout data using a geometric collision detection algorithm to obtain the spatial overlap rate between the experimental equipment and other equipment, and to construct mutually exclusive edges based on the spatial overlap rate;

[0021] Functional association data includes the association between device identifiers and function identifiers; the graph construction module is used to construct functional collaboration edges based on the association relationships; among them, device identifiers include the identifiers of experimental equipment; function identifiers include the identifiers of experimental functions.

[0022] Furthermore, the acquisition module is used to acquire the initial signal strength associated with the experimental equipment in the experimental equipment set. If the initial signal strength is greater than or equal to the strength threshold, the initial signal strength is corrected to obtain the corrected strength, and the relative positional relationship is determined based on the corrected strength.

[0023] The graph construction module is used to construct the device proximity edges between experimental devices and other devices if the relative positional relationship characterizes that the experimental device is in an adjacent state with other devices.

[0024] Furthermore, the acquisition module is used to generate and send a graph update indication to the graph construction module if the initial signal strength is less than the strength threshold;

[0025] The graph construction module is used to remove at least some of the device proximity edges from the dynamic heterogeneous graph if the current dynamic heterogeneous graph contains device proximity edges, based on the graph update instruction.

[0026] Furthermore, the acquisition module is used to obtain historical experimental logs associated with the set of experimental equipment, and to determine the co-occurrence data of the equipment based on the historical experimental logs.

[0027] Furthermore, the fusion result is calculated in the following manner:

[0028] Based on the weights in the weight set, the data carried by spatial mutually exclusive edges, functional cooperation edges, device proximity edges, and device co-occurrence edges are respectively weighted and fused to obtain the fusion result; as shown in Equation (1):

[0029] (1)

[0030] Where t is an integer greater than or equal to 0, used to represent time t or the current time. The fusion result at time t is... Let be the mutual exclusion weights at time t, and be... The functional weight at time t Let the nearest neighbor weights be at time t. Let be the co-occurrence weight at time t. The data carried by the spatially mutually exclusive edge at time t. The data carried by the functional cooperation edge at time t. The data carried by the co-occurrence edge of the devices at time t. The data carried by the device's nearest edge at time t.

[0031] The IoT RFID-linked experimental equipment management system provided in this application embodiment has at least the following beneficial effects:

[0032] In the IoT RFID-linked experimental equipment management system provided in this application embodiment, the acquisition module is used to collect source data. The source data includes spatial attribute data, functional association data, equipment association data, and equipment co-occurrence data of the experimental equipment in the set of experimental equipment deployed in the laboratory. The spatial attribute data includes at least the layout data of the experimental equipment in the laboratory; the functional association data includes the experimental functions of the experimental equipment; the equipment association data includes the relative positional relationship between the experimental equipment and other equipment; and the equipment co-occurrence data includes the probability of at least two experimental equipment in the set of experimental equipment appearing together in historical experiments. In this way, the acquisition module realizes the comprehensive collection of data associated with the set of experimental equipment deployed in the laboratory. Moreover, the source data can finely characterize and describe the dependency and constraint relationships between experimental equipment in the set of experimental equipment from the spatial dimension, the equipment function dimension, and the co-occurrence dimension of experimental equipment. At the same time, the graph construction module is used to construct a dynamic heterogeneous graph based on the source data. The dynamic heterogeneous graph includes spatial mutually exclusive edges corresponding to spatial attribute data, functional cooperative edges corresponding to functional association data, equipment proximity edges corresponding to equipment association data, and equipment co-occurrence data pairs. The corresponding co-occurrence edges of the devices enable a comprehensive, intuitive, and dynamic representation of the spatial and functional dependencies among the experimental devices in the experimental equipment set, achieving full integration of these dependencies. Based on this, the fusion module performs spatiotemporal fusion on the data carried by the spatially exclusive edges, functionally collaborative edges, device proximity edges, and device co-occurrence edges in the dynamic heterogeneous graph, obtaining a fusion result. This fusion result comprehensively, diversely, and multi-layeredly reflects the device relationships among the experimental devices included in the dynamic heterogeneous graph. On the other hand, the device management module determines the expected device state of the experimental equipment set within at least one time period based on the fusion result, managing the experimental equipment set based on the expected device state, enabling comprehensive, refined, dynamic, and intelligent management of the experimental devices within the set. Furthermore, since the laboratory is connected to the Internet of Things (IoT) and RFID, this solution leverages the advantages of IoT and RFID in data synchronization and efficient processing, further improving the accuracy and intelligence of the management of the experimental equipment in the set, thereby meeting diverse experimental equipment management needs. Attached Figure Description

[0033] Figure 1 A schematic diagram of the structure of the IoT RFID-linked experimental equipment management system provided in this application embodiment;

[0034] Figure 2 A schematic diagram illustrating the process of obtaining the expected state of the device provided in an embodiment of this application;

[0035] Figure 3A schematic diagram illustrating the construction process of a dynamic heterogeneous graph provided in an embodiment of this application;

[0036] Figure 4 A flowchart illustrating the management of experimental equipment provided in this application embodiment. Detailed Implementation

[0037] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0038] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0039] In laboratories equipped with the Internet of Things (IoT), positioning algorithms are typically used to analyze RFID signal strength to determine the location of various experimental devices. These devices are then managed based on their locations. However, this method cannot meet the diverse management needs of experimental equipment.

[0040] Based on the above technical problems, this application provides an IoT RFID-linked experimental equipment management system. Figure 1 This is a schematic diagram of the structure of the IoT RFID-linked experimental equipment management system provided in the embodiments of this application, as shown below. Figure 1 As shown, the experimental equipment management system 100 may include:

[0041] The acquisition module 101 is used to acquire source data; wherein, the source data includes spatial attribute data, functional association data, device association data, and device co-occurrence data of the experimental equipment in the set of experimental equipment deployed in the laboratory; the spatial attribute data includes at least the layout data of the experimental equipment in the laboratory; the functional association data is used to characterize the experimental functions of the experimental equipment; the device association data includes the relative positional relationship between the experimental equipment and other equipment; the device co-occurrence data includes descriptive data of at least two experimental equipment in the set of experimental equipment appearing together in historical experiments; other equipment includes equipment in the set of experimental equipment other than the experimental equipment.

[0042] Graph construction module 102 is used to construct a dynamic heterogeneous graph based on source data; wherein, the dynamic heterogeneous graph includes spatial mutually exclusive edges corresponding to spatial attribute data, functional collaboration edges corresponding to functional association data, device proximity edges corresponding to device association data, and device co-occurrence edges corresponding to device co-occurrence data;

[0043] The fusion module 103 is used to perform spatiotemporal fusion on the data carried by the spatially exclusive edges, functional collaborative edges, device proximity edges, and device co-occurrence edges in the dynamic heterogeneous graph to obtain the fusion result.

[0044] The equipment management module 104 is used to determine the expected equipment status of the experimental equipment set in at least one time period based on the fusion results, and to manage at least a portion of the experimental equipment in the laboratory equipment set based on the expected equipment status.

[0045] In some embodiments, the laboratory is associated with the Internet of Things (IoT) and RFID, which may include the deployment of IoT in the laboratory and the communication between the IoT and RFID signal systems deployed in the laboratory and the experimental equipment set, respectively; wherein the RFID signal system may include RFID electronic tags, readers, RFID antennas and data processing units.

[0046] In some embodiments, the layout data may include the location of the experimental equipment in the laboratory, a first area occupied by the experimental equipment in the laboratory, and a second area occupied by the laboratory; exemplarily, the spatial attribute data may also include orientation data of the first area in the second area; correspondingly, the spatial attribute data may be obtained in the following ways:

[0047] The data acquisition module collects image and / or video data from a set of experimental equipment in the laboratory using data acquisition devices deployed in the laboratory. It then performs feature extraction, object recognition, and distance calculation on the image and / or video data to determine spatial attribute data. In this case, the acquisition module may include data acquisition devices, which may include cameras or video cameras.

[0048] In some embodiments, the function association data may include the device identifier of the experimental equipment, the type of the experimental function, and / or function condition data; exemplarily, the function condition data may include data such as the electrical energy, network, input data type, input data format, storage space capacity, and environmental requirements required for the experimental equipment to perform its experimental function; exemplarily, the device identifier may include the name and / or number of the experimental equipment; exemplarily, the function association data may be obtained in the following ways:

[0049] The system acquires equipment manuals describing the attributes of the experimental equipment set and parses the manuals to obtain functional association data. The equipment manuals may include instruction manuals or product manuals for the experimental equipment. For example, the equipment manuals can be input into the acquisition module by a user or a technical professional, or the acquisition module can connect to the experimental equipment via an experimental network to receive the equipment manuals sent by the experimental equipment. In this case, the acquisition module may include a data input module or an experimental network. The data input module may include a display screen, keyboard, and mouse, while the experimental network may include an Internet of Things (IoT) deployed in the laboratory.

[0050] In some embodiments, the relative positional relationship may include the distance and / or orientation between the experimental device and other devices in two-dimensional or three-dimensional space; for example, the distance between other devices and the experimental device may be less than or equal to a distance threshold; accordingly, the device association data can be obtained in the following ways:

[0051] The relative positional relationship between the experimental equipment and other equipment is determined by detecting the signal attenuation state of the RFID signal between the experimental equipment and other equipment. For example, the signal attenuation state can be associated with at least one of the equipment distance between the experimental equipment and other equipment and the obstruction state of obstacles between the experimental equipment and other equipment. Accordingly, the acquisition module may include a signal detection module or signal detection equipment deployed in the laboratory.

[0052] In some embodiments, historical experiments may include experiments conducted in a laboratory within at least one historical period and requiring the use of at least two experimental devices.

[0053] In some embodiments, the descriptive data may include at least one of the following: the device identifier of the experimental equipment that co-occurs in the experimental stages included in the historical experiment, the order of occurrence among the co-occurring experimental equipment, and the frequency of occurrence of the experimental equipment; accordingly, the device co-occurrence data can be obtained in the following ways:

[0054] By analyzing the descriptions of experimental procedures in the historical experimental logs associated with historical experiments, device co-occurrence data can be obtained; at this time, the acquisition module may include a code module with historical experimental log acquisition function and / or a network transmission unit.

[0055] In some embodiments, the acquisition module can acquire source data at preset time intervals, and can also monitor the changes in spatial attribute data, functional association data, device association data, and device co-occurrence data in real time. When at least one of the spatial attribute data, functional association data, device association data, and device co-occurrence data changes, the acquisition module can acquire the changed data to obtain source data.

[0056] In some embodiments, spatial mutual exclusion edges can be used to describe the mutual exclusion state between the experimental equipment represented by the spatial attribute data and the configuration device in the laboratory; wherein, the configuration device may include hardware devices required for supporting, maintaining and configuring experimental conditions, such as walls, load-bearing columns, light sources, power supplies, network cables and network ports, etc.

[0057] In some embodiments, spatially mutually exclusive edges can also characterize whether experimental devices are mutually exclusive, whether experimental devices are mutually exclusive with configuration devices, and whether configuration devices are mutually exclusive with each other, as well as the strength of the mutual exclusion. The first set of nodes associated with a spatially mutually exclusive edge can include device nodes corresponding to experimental devices and device nodes corresponding to configuration devices. Accordingly, spatially mutually exclusive edges can be constructed in the following ways:

[0058] Based on the conflict probability between the experimental equipment size, the experimental equipment location, the configuration device size, and the configuration device location, construct spatial mutually exclusive edges.

[0059] For example, if the size of the experimental equipment is larger than the area enclosed by part of the walls in the laboratory, or if the size of the experimental equipment is smaller than the area enclosed by the walls, but the distance between the outer shell of the experimental equipment and the walls is less than or equal to the safe distance of the experimental equipment when the experimental equipment is deployed in the area, then a spatial mutually exclusive edge can be constructed between the experimental equipment and the area. Furthermore, if the overlap rate of the projected areas of two large-sized experimental devices in the laboratory is greater than or equal to the overlap rate threshold, then a spatial mutually exclusive edge can be constructed between the two large-sized experimental devices.

[0060] In some embodiments, a functional collaboration edge can characterize the relationship of mutual dependence or cooperation between the experimental functions of at least two experimental devices; for example, the second set of nodes associated with the functional collaboration edge may include device nodes and functional nodes corresponding to the experimental functions; accordingly, the functional collaboration edge can be constructed in the following manner:

[0061] By jointly analyzing the functional association data of each experimental device in the experimental equipment set, a mapping relationship between function and device is established. Then, the mapping relationship is sorted out to construct a functional collaboration edge. For example, if the functional association data of the microscope is analyzed and it is found that its function depends on the slide placed on the stage, then the second node set associated with the functional collaboration edge can include the node corresponding to the slide, the node corresponding to the microscope, the microscope's microscopic function, and the sample carrying function corresponding to the slide.

[0062] In some embodiments, a device proximity edge can represent the spatial adjacency relationship between the experimental device and other devices; correspondingly, the set of third nodes corresponding to the device proximity edge can include the device nodes corresponding to the experimental device and other devices respectively; for example, a device proximity edge can be constructed in the following way:

[0063] If the distance between the experimental device and other devices is less than or equal to the distance threshold, then the device proximity edge is constructed based on the device distance.

[0064] In some embodiments, device co-occurrence edges can characterize the probability of different experimental devices appearing together during an experiment; correspondingly, the set of fourth nodes corresponding to the device co-occurrence edges can include device nodes and scene nodes corresponding to the experimental scenario, wherein the experimental scenario can include a scenario that requires at least two experimental devices to cooperate in completing the experiment; accordingly, device co-occurrence edges can be constructed in the following ways:

[0065] If the probability of the first device and the second device appearing together is greater than or equal to the probability threshold, then a device co-occurrence edge is constructed based on the experimental scenarios corresponding to the first device, the second device, and the first device and the second device appearing together.

[0066] In some embodiments, the fusion result may include high-order semantic features characterizing the interrelationships among the experimental devices included in the dynamic heterogeneous graph. For example, these interrelationships can characterize the mutual influence, interdependence, and mutual constraints among the experimental devices included in the dynamic heterogeneous graph from spatial, temporal, and experimental functional dimensions. Accordingly, the fusion result can be obtained in the following ways:

[0067] The spatial constraints represented by mutually exclusive edges and adjacent edges of devices are sorted out by the fusion module to obtain spatial relationships. The dependencies between experimental functions contained in functional cooperation edges and co-occurrence edges of devices, as well as the probability of the occurrence of the above dependencies, are analyzed by the fusion module to obtain functional relationships. The changes in spatial relationships and functional relationships are fused in the time dimension by the fusion module to obtain fusion results.

[0068] In some embodiments, the expected device state may include the device state of the experimental devices included in the dynamic heterogeneity graph during at least one time period; for example, at least one time period may include a future time period of the current moment.

[0069] In some embodiments, the expected device state can be determined in the following ways:

[0070] The spatial relationships in the fusion results are predicted by the device management module to obtain the first prediction result. Based on the first prediction result, the possible conflict states of the experimental equipment in the dimension of position change are determined. The functional relationships are predicted by combining the experimental scenario in the laboratory to obtain the second prediction result. Based on the second prediction result, the possible configuration state of the experimental equipment at future moments is determined. The conflict state and the configuration state are then integrated to obtain the expected equipment state.

[0071] In some embodiments, the device management module may be deployed on an edge computing node.

[0072] In some implementation sets, the device management module can manage at least a portion of the experimental devices in the experimental device set in the following ways:

[0073] Based on the first prediction result, the constraints of the experimental equipment configuration are determined, and based on the second prediction result, the target conditions of the experimental equipment configuration are determined. Then, based on the constraints and target conditions, at least one of the following is adjusted: the setting method, placement location, data transmission method between different experimental equipment, energy supply method, and load state of at least some of the experimental equipment, in order to reduce the probability of equipment collision, functional mismatch, energy failure, and load overload between at least some of the experimental equipment. The energy may include at least one of light energy, electrical energy, magnetic energy, and wind energy.

[0074] For example, the device management module may include a classifier, a predictor, and a regressor; wherein, the classifier can analyze the data carried by spatially exclusive edges and device-adjacent edges contained in the fusion result to determine whether the data carried by spatially exclusive edges and device-adjacent edges correspond to an abnormal state; the predictor can predict the data carried by functional cooperation edges and device co-occurrence edges respectively to determine the functional correlation coefficient between experimental devices; and the regressor can predict the future location and future load of the experimental device at future times based on the data carried by spatially exclusive edges and device-adjacent edges respectively, if it is determined that the data carried by spatially exclusive edges and device-adjacent edges do not correspond to an abnormal state.

[0075] As can be seen from the above, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, the acquisition module is used to collect source data. The source data includes spatial attribute data, functional association data, equipment association data, and equipment co-occurrence data of the experimental equipment in the set of experimental equipment deployed in the laboratory. The spatial attribute data includes at least the layout data of the experimental equipment in the laboratory; the functional association data includes the experimental functions of the experimental equipment; the equipment association data includes the relative positional relationship between the experimental equipment and other equipment; and the equipment co-occurrence data includes the probability of at least two experimental equipment in the set of experimental equipment appearing together in historical experiments. In this way, the acquisition module realizes the comprehensive collection of data associated with the set of experimental equipment deployed in the laboratory. Moreover, the source data can finely characterize and describe the dependency and constraint relationships between experimental equipment in the set of experimental equipment from the spatial dimension, the equipment function dimension, and the co-occurrence dimension of experimental equipment. At the same time, the graph construction module is used to construct a dynamic heterogeneous graph based on the source data. The dynamic heterogeneous graph includes spatial mutually exclusive edges corresponding to the spatial attribute data, functional cooperative edges corresponding to the functional association data, equipment proximity edges corresponding to the equipment association data, and equipment co-occurrence edges. The data corresponds to device co-occurrence edges. Thus, through a dynamic heterogeneous graph, the dependencies between experimental devices in the experimental equipment set across spatial and functional dimensions can be displayed comprehensively, intuitively, and dynamically, achieving a complete integration of these dependencies. Based on this, the fusion module performs spatiotemporal fusion on the data carried by the spatially exclusive edges, functionally collaborative edges, device proximity edges, and device co-occurrence edges in the dynamic heterogeneous graph, obtaining a fusion result. This fusion result comprehensively, diversely, and multi-layeredly reflects the device relationships between the experimental devices included in the dynamic heterogeneous graph. On the other hand, the device management module determines the expected device state of the experimental equipment set within at least one time period based on the fusion result. Managing the experimental equipment set based on the expected device state enables comprehensive, refined, dynamic, and intelligent management of the experimental devices within the set. Furthermore, since the laboratory is linked to the Internet of Things (IoT) and RFID, this solution leverages the advantages of IoT and RFID in data synchronization and efficient processing to further improve the accuracy and intelligence of managing the experimental devices in the set, thereby meeting diverse experimental equipment management needs.

[0076] Based on the foregoing embodiments, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, the acquisition module is also used to acquire the set of equipment locations corresponding to the experimental equipment;

[0077] The fusion module is also used to integrate the set of device locations and determine the displacement pattern of the experimental equipment;

[0078] The equipment management module is also used to determine the expected equipment status based on displacement patterns and fusion results.

[0079] In some embodiments, the device location set can characterize the set of real-time spatial locations of experimental devices; for example, the device location set can be obtained in the following ways:

[0080] The signal strength of RFID signals emitted by experimental devices in the experimental equipment set is continuously monitored by a signal detection module or signal detection equipment in the laboratory. The signal strength sequence is obtained, and the signal strength sequence is processed to determine the set of device locations.

[0081] In some embodiments, the displacement mode may include the relative motion mode of the experimental device relative to other devices; exemplarily, the relative motion mode may include the motion mode of different experimental devices moving closer to or further away from each other; accordingly, the displacement mode may be determined in the following ways:

[0082] Features are extracted from the set of device locations using a one-dimensional convolutional neural network (1DCNN) to obtain displacement patterns that characterize the changing patterns of device locations. For example, the 1DCNN may include multiple convolutional kernels with a stride of 1 and an activation function ReLU. The activation function is used to capture valid features in the set of device locations and remove invalid data.

[0083] In some embodiments, the expected device state can be predicted in the following ways:

[0084] Based on the displacement patterns of each experimental device in the experimental equipment set, the spatial dimension of the data carried by the spatially mutually exclusive edges and the adjacent edges of the devices in the fusion result is predicted to obtain the future relative positions of the experimental devices contained in the feature heterogeneous graph in the future time period. Based on the experimental scenario of the laboratory, the data carried by the functional cooperation edges and the co-occurrence edges of the devices in the fusion result are predicted to obtain the future experimental state. Then, the device requirements corresponding to the future relative positions and the future experimental states are determined as the expected device state. Among them, the device requirements may include at least one of the types, quantities, and experimental functions of the experimental devices required by the future experimental state.

[0085] As can be seen from the above, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, the acquisition module is used to acquire the set of equipment locations corresponding to the experimental equipment, and the fusion module is used to integrate the set of equipment locations to obtain the displacement pattern of the experimental equipment. In this way, the displacement pattern of the experimental equipment is tracked and determined, and the displacement pattern can reflect the displacement state of the experimental equipment in the laboratory. Furthermore, the equipment management module is used to determine the expected equipment state based on the displacement pattern and the fusion result. In this way, the expected equipment state is simultaneously associated with the fusion result and the displacement pattern, so that the expected equipment state can dynamically and flexibly reflect the equipment state of the experimental equipment set within at least one time period.

[0086] Based on the foregoing embodiments, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, the fusion module is used to determine a weight set based on the data carried by the spatially mutually exclusive edges, functionally cooperative edges, device proximity edges, and device co-occurrence edges respectively, and to perform fusion processing on the data carried by the spatially mutually exclusive edges, functionally cooperative edges, device proximity edges, and device co-occurrence edges respectively based on the weight set to obtain the fusion result.

[0087] In some embodiments, the fusion module can analyze the data carried by spatially mutually exclusive edges, functionally cooperative edges, device proximity edges, and device co-occurrence edges respectively through a multi-head attention mechanism to determine the weight set.

[0088] For example, the multi-head attention mechanism can be implemented through a multi-head attention network, which may include eight attention heads. The first to fourth attention heads can be used to analyze the data carried by the functional cooperation edge and the device co-occurrence edge, respectively, to obtain the functional weight and co-occurrence weight. The fifth and sixth attention heads can analyze the data carried by the device proximity edge to obtain the proximity weight. The remaining attention heads can be used to analyze the data carried by the spatially mutually exclusive edge to obtain the mutual exclusion weight. For example, the functional weight, co-occurrence weight, proximity weight, and mutual exclusion weight can be normalized to obtain a weight set.

[0089] It should be noted that the weight set can change dynamically with the change of the dynamic heterogeneous graph. When the dynamic heterogeneous graph changes over time, the weight set can also change dynamically over time; correspondingly, the fusion result can also change dynamically over time.

[0090] In some embodiments, the fusion result can be calculated in the following manner:

[0091] Based on the weights in the weight set, the data carried by spatial mutually exclusive edges, functional cooperation edges, device proximity edges, and device co-occurrence edges are respectively weighted and fused to obtain the fusion result; specifically, it can be shown in equation (1):

[0092] (1)

[0093] Where t is an integer greater than or equal to 0, used to represent time t or the current time. The fusion result at time t is... Let be the mutual exclusion weights at time t, and be... The functional weight at time t Let the nearest neighbor weights be at time t. Let be the co-occurrence weight at time t. The data carried by the spatially mutually exclusive edge at time t. The data carried by the functional cooperation edge at time t. The data carried by the co-occurrence edge of the devices at time t. The data carried by the device's nearest edge at time t.

[0094] As can be seen from the above, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, the fusion module is used to determine the weight set based on the data carried by the spatially mutually exclusive edges, functionally cooperative edges, device proximity edges, and device co-occurrence edges respectively. In this way, when the data carried by the spatially mutually exclusive edges, functionally cooperative edges, device proximity edges, and device co-occurrence edges change dynamically, the weight set can also show a dynamic change state, thereby improving the dynamism, targeting, and accuracy of the weight set. On this basis, the data carried by the spatially mutually exclusive edges, functionally cooperative edges, device proximity edges, and device co-occurrence edges are fused based on the weight set to obtain the fusion result. This can achieve targeted fusion processing of the data carried by each edge in the dynamic heterogeneous graph. In this way, the comprehensiveness and completeness of the data in the fusion result can be improved, as well as the dynamic variability of the fusion result can be improved, so that the fusion result can accurately reflect the dynamic change process of the experimental equipment in the experimental equipment set.

[0095] Based on the foregoing embodiments, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, the fusion module is used to process the mutual exclusion state of the nodes associated with the spatial mutual exclusion edge through a logical negation function to obtain a spatial mutual exclusion score, process the functional state of the nodes associated with the functional cooperation edge through a first averaging function to obtain a functional cooperation score, process the co-occurrence state of the nodes associated with the device co-occurrence edge through a second averaging function to obtain a device co-occurrence score, and process the spatial state associated with the device neighboring edge based on the signal strength corresponding to the device neighboring edge to obtain a spatial neighboring score.

[0096] The fusion module is also used to fuse spatial mutual exclusion scores, functional collaboration scores, device co-occurrence scores, and spatial proximity scores based on a weight set to obtain the fusion result.

[0097] In some embodiments, the nodes associated with a spatially mutually exclusive edge may include a first set of nodes, and the mutual exclusion state may include the degree of mutual exclusion between nodes in the first set of nodes; correspondingly, the spatial mutual exclusion score can comprehensively characterize the level of mutual exclusion between any experimental device in the experimental device set and other experimental devices and configuration devices; for example, the spatial mutual exclusion score of any experimental device at time t may be the data carried by the spatially mutually exclusive edge at time t in the aforementioned embodiments, and the spatial mutual exclusion score of any experimental device at time t... It can be calculated using the logical negation function shown in equation (2):

[0098] (2)

[0099] in, Let represent the mutual exclusion state of the i-th node in the first node set at time t. The suppression coefficient, is the weight of the spatially mutually exclusive edge, and its value is negative; for example, if the value corresponding to the mutually exclusive state of the centrifuge in the experimental equipment set is 0.8, the value corresponding to the mutually exclusive state of the temperature control equipment is 0.7, and the mutual exclusion weight is -0.3, then the value corresponding to the spatial mutually exclusive score of the centrifuge calculated by formula (2) can be 0.905.

[0100] In some embodiments, the nodes associated with a functional collaboration edge may include a second set of nodes; exemplarily, the functional state may include the experimental functions possessed by the experimental equipment in the second set of nodes; correspondingly, the functional collaboration score may include a value representing the richness of the experimental functions possessed by the experimental equipment in the second set of nodes, which may be the data carried by the functional collaboration edge in the aforementioned embodiments; specifically, the functional collaboration score at time t... It can be calculated using the first average function shown in equation (3):

[0101] (3)

[0102] in, Let i be the functional score of the experimental function possessed by the i-th experimental device in the second node set, where i is an integer greater than or equal to 1. The statistical weights associated with the functional scores.

[0103] In some embodiments, the nodes associated with the device co-occurrence edge can be the third node set in the aforementioned embodiments; for example, the co-occurrence state can include the probability of experimental devices cooperating in experiments corresponding to the fourth node set, and the device co-occurrence score can include the scenario score of the experimental scenario corresponding to the experimental devices cooperating in experiments in the fourth node set, which can be the data carried by the device co-occurrence edge in the aforementioned embodiments; specifically, the device co-occurrence score at time t. It can be calculated using the second average function shown in equation (4):

[0104] (4)

[0105] in, Let be the value of the co-occurrence state corresponding to the i-th experimental device in the fourth node set. The weights are those corresponding to the co-occurrence states.

[0106] In some embodiments, the signal strength corresponding to the device proximity edge may include the RFID signal strength corresponding to the device in the third node set; for example, the spatial state associated with the device proximity edge may include the relative positional relationship between any experimental device and other adjacent experimental devices; correspondingly, the spatial proximity score may include the integrated value result of the above relative positional relationship, which may be the data carried by the device proximity edge in the foregoing embodiments.

[0107] Specifically, the spatial proximity score can be calculated in the following way:

[0108] The target weight is determined based on the signal strength corresponding to the device's nearest edge, and then the spatial state associated with the device's nearest edge is calculated based on the target weight to obtain the spatial proximity score; specifically, the above process can be implemented by equations (5) to (6):

[0109] (5)

[0110] (6)

[0111] in, Let t be the spatial proximity score. Let be the signal strength of the device's nearest edge at time t. This is the intensity threshold, which can take a value of -70 dBm. This represents the minimum signal strength, which can take a value of -80 dBm. The target weights are associated with the signal strength. Let represent the spatial state of the i-th experimental device among the adjacent edges of the device.

[0112] Figure 2This is a schematic diagram of the process for obtaining the expected state of the device provided in an embodiment of this application, such as... Figure 2 As shown, the process may include the following steps:

[0113] Step 201: Input the dynamic heterogeneity graph.

[0114] Step 202: Relationship-aware fusion.

[0115] For example, step 202 may include four sub-steps that can be executed in parallel: spatial mutual exclusion edge processing, functional cooperation edge processing, device proximity edge processing, and device co-occurrence edge processing, as well as a sub-step of multi-head attention fusion.

[0116] Specifically, spatial mutual exclusion edge processing can be achieved by processing the mutual exclusion state of the nodes associated with the spatial mutual exclusion edge using a logical negation function to obtain a spatial mutual exclusion score; functional cooperation edge processing can be achieved by processing the functional state of the nodes associated with the functional cooperation edge using a first averaging function to obtain a functional cooperation score; device co-occurrence edge processing can be achieved by processing the co-occurrence state of the nodes associated with the device co-occurrence edge using a second averaging function to obtain a device co-occurrence score; and device proximity edge processing can be achieved by processing the spatial state associated with the device proximity edge based on the signal strength corresponding to the device proximity edge to obtain a spatial proximity score.

[0117] Specifically, multi-head attention fusion can be achieved by determining a weight set using the methods provided in the aforementioned embodiments, and by weighting spatial mutual exclusion scores, functional collaboration scores, device co-occurrence scores, and spatial proximity scores based on the weight set to obtain the fusion result.

[0118] Step 203: Obtain the fusion result.

[0119] It should be noted that the first branch corresponding to steps 201 to 203 is executed in parallel with the second branch corresponding to steps 204 to 205. This application embodiment does not limit this.

[0120] Step 204: Timing coding processing.

[0121] For example, the set of device locations corresponding to the experimental equipment can be integrated to achieve time-series coding processing of the unknown set.

[0122] Step 205: Feature extraction processing.

[0123] For example, the displacement pattern of the experimental device can be obtained by performing feature extraction processing on the set of device locations using ID CNN.

[0124] Step 206: Obtain the expected status of the equipment.

[0125] For example, the expected device state can be predicted based on the displacement pattern and fusion result using the method provided in the foregoing embodiments.

[0126] Through the above process, the processing of each edge in the dynamic heterogeneous graph, as well as the temporal coding and feature extraction processes, are integrated into a unified whole, thereby improving the efficiency and accuracy of determining the expected state of the device.

[0127] As can be seen from the above, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, the fusion module is used to process the state of the nodes associated with spatially mutually exclusive edges, functionally cooperative edges, and device co-occurrence edges through a logical negation function, a first averaging function, and a second averaging function, respectively, to obtain spatially mutually exclusive scores, functionally cooperative scores, and device co-occurrence scores. In this way, the state of the nodes associated with spatially mutually exclusive edges, functionally cooperative edges, and device co-occurrence edges can be accurately and meticulously quantified. Furthermore, the spatial state associated with the device's neighboring edge is processed based on the signal strength corresponding to the device's neighboring edge to obtain a spatial proximity score, thereby realizing the dynamic quantification of the spatial state associated with the device's neighboring edge. On this basis, the spatially mutually exclusive scores, functionally cooperative scores, device co-occurrence scores, and spatial proximity scores are fused based on a weight set to obtain a fusion result, which enables the fusion result to more comprehensively, intuitively, and meticulously represent the state of the experimental equipment set in the dynamic heterogeneous graph.

[0128] Based on the foregoing embodiments, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, the expected equipment status includes at least one of the following: future equipment abnormal status, equipment cooperation status, and equipment load status.

[0129] The device management module is used to perform device maintenance operations on the target device and / or associated devices if the expected device status includes an abnormal device status, and / or to determine and output a device maintenance prompt if the expected device status includes an abnormal device status.

[0130] The target device includes experimental equipment that will be in an abnormal state at a future time; the associated device includes at least one device associated with the target device.

[0131] Accordingly, if the expected equipment status does not include abnormal equipment status, then equipment maintenance operations for the target equipment and / or associated equipment may not be performed, and equipment maintenance prompts may not be output.

[0132] In some embodiments, an abnormal equipment state may include a state in which the experimental equipment is unable to maintain its experimental functions.

[0133] In some embodiments, the device collaboration state may include a state in which at least two experimental devices work together to achieve at least one or more experimental steps.

[0134] In some embodiments, the equipment load status may include at least one of the following: load rate, runtime percentage, resource availability, failure rate, and task saturation of the experimental equipment during at least one time period.

[0135] In some embodiments, the associated device may include at least one experimental device that is in a collaborative experimental state with the target device, and may also include a configuration device for providing energy support to the target device; for example, the associated device can be identified by the device co-occurrence edge and the identifier of the target device.

[0136] In some embodiments, the types and procedures of operations included in equipment maintenance operations can be determined by the equipment management module through analysis of the equipment manuals of the target equipment and / or associated equipment.

[0137] In some embodiments, device maintenance prompts may be output via images, videos, text, vibration, flashing lights, and alarm sounds; for example, device maintenance prompts may include the operation types and operation procedures involved in the device maintenance operation.

[0138] As can be seen from the above, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, the expected equipment status includes at least one of the following: future equipment abnormal status, equipment cooperation status, and equipment load status. This improves the comprehensiveness and richness of the expected equipment status. Furthermore, the equipment management module is used to perform equipment maintenance operations associated with the target equipment and / or associated equipment, and / or output equipment maintenance prompts if the expected equipment status includes an abnormal equipment status. This enables intelligent and targeted equipment maintenance of the target equipment and / or associated equipment, thereby reducing the probability that the experimental equipment will be in an abnormal equipment status for a long time in the future.

[0139] Based on the foregoing embodiments, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, the spatial attribute data includes the equipment size and equipment safety distance of the experimental equipment; the graph construction module is used to process the equipment size, equipment safety distance and layout data through a geometric collision detection algorithm to obtain the spatial overlap rate between the experimental equipment and other equipment, and construct spatial mutually exclusive edges based on the spatial overlap rate.

[0140] In some embodiments, the device dimensions may include the length, width, height, and other geometric dimensions of the experimental device housing.

[0141] In some embodiments, the safe distance between devices may include the minimum distance that should be maintained between experimental devices or between experimental devices and configuration devices while the experimental device is maintaining its experimental function.

[0142] In some embodiments, the spatial overlap rate may include the overlap rate of the projections of the experimental device and other devices in any direction; for example, the spatial overlap rate can be obtained in the following manner:

[0143] The device size is calculated based on the layout data using a geometric collision detection algorithm to obtain the device area occupied by the experimental device in the laboratory. Then, the device area is expanded based on the device safety distance to obtain the expanded device area. Finally, the spatial overlap rate is determined based on the overlap state between the projections of the expanded device areas corresponding to different experimental devices in a specified direction.

[0144] In some embodiments, spatial mutual exclusion edges can be constructed in the following way:

[0145] Based on the relationship between spatial overlap rate and overlap rate threshold, the device mutual exclusion risk corresponding to the spatial overlap rate is determined, and then spatial mutual exclusion edges are constructed according to the device mutual exclusion risk. Among them, the device mutual exclusion risk can increase with the increase of spatial overlap rate, and the data carried by the spatial mutual exclusion edge can include spatial overlap rate, device mutual exclusion risk, and the size of the overlapping area between the expanded device areas corresponding to different experimental devices.

[0146] As can be seen from the above, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, the spatial attribute data includes the equipment size and equipment safety distance of the experimental equipment. The graph construction module is used to process the equipment size, equipment safety distance and layout data through set detection algorithm to obtain the spatial overlap rate between the experimental equipment and other equipment. In this way, the accuracy of the spatial overlap rate can be improved. On this basis, spatial mutual exclusion edges are constructed based on the spatial overlap rate, which can improve the diversity and accuracy of the data carried by the spatial mutual exclusion edges.

[0147] Based on the foregoing embodiments, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, the functional association data includes the association relationship between equipment identifiers and functional identifiers; the graph construction module is used to construct functional collaborative edges based on the association relationship.

[0148] Among them, equipment identification includes the identification of experimental equipment; function identification includes the identification of experimental functions.

[0149] In some embodiments, the function identifier includes the name and / or number of the experimental function.

[0150] In some embodiments, the association can be obtained by analyzing the equipment manual of the experimental equipment.

[0151] In some embodiments, functional collaborative edges can be constructed in the following ways:

[0152] Obtain the association relationships corresponding to each experimental device in the experimental equipment set. If the nth function identifier in the mth association relationship corresponding to the mth experimental device matches the sth function identifier in the pth association relationship corresponding to the pth experimental device, then construct a functional collaboration edge between the mth experimental device and the pth experimental device. By traversing the association relationships corresponding to each experimental device in the experimental equipment set in the above manner, functional collaboration edges corresponding to each experimental device can be constructed. Here, m, n, p, and s are all integers greater than or equal to 1.

[0153] As can be seen from the above, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, the functional association module includes the association relationship between device identifiers and functional identifiers, and the graph construction module is used to construct functional collaboration edges based on the association relationship. This not only improves the efficiency of constructing functional collaboration edges but also enhances the accuracy and comprehensiveness of the data carried by the functional collaboration edges.

[0154] Based on the foregoing embodiments, in the IoT RFID-associated experimental equipment management system provided in this application embodiment, the acquisition module is used to acquire the initial signal strength associated with the experimental equipment in the experimental equipment set. If the initial signal strength is greater than or equal to the strength threshold, the initial signal strength is corrected to obtain the corrected strength, and the relative positional relationship is determined based on the corrected strength.

[0155] The graph construction module is used to construct the device proximity edges between experimental devices and other devices if the relative positional relationship characterizes that the experimental device is in an adjacent state with other devices.

[0156] Accordingly, if the initial signal strength is less than the strength threshold, the initial signal strength does not need to be corrected.

[0157] Accordingly, if the relative positional relationship indicates that the experimental equipment is not in an adjacent state with other equipment, then it is not necessary to construct the adjacent edge of the equipment.

[0158] In some embodiments, the initial signal strength may be related to the antenna transmit power, transmit antenna gain, receive antenna gain of the experimental equipment, and the equipment distance between the experimental equipment and other equipment; specifically, the initial signal strength It can be calculated using equation (7):

[0159] (7)

[0160] in, For RFID transmitting antenna gain, For RFID receiving antenna gain, For RFID signal wavelength, For device distance, This refers to the RFID antenna transmission power of the experimental equipment.

[0161] In some embodiments, the correction strength may be less than the initial signal strength; for example, the correction strength may be calculated by determining an environmental correction factor based on the degree of signal obstruction between the experimental device and other devices, and then correcting the initial signal strength based on the environmental correction factor; for example, the environmental correction factor may characterize the degree or severity of signal obstruction.

[0162] In some embodiments, device proximity edges can be constructed in the following way:

[0163] The closeness of adjacent states is determined based on the distance between devices in the relative position relationship. Then, based on the closeness, the device identifier of the experimental device, the device identifier of other devices, and the device positions of the experimental device and other devices, the device proximity edges are constructed.

[0164] As can be seen from the above, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, if the initial signal strength between experimental devices is greater than or equal to the strength threshold, the initial signal strength is corrected to obtain the corrected strength. In this way, the operation of correcting the initial signal is controlled. Furthermore, determining the relative positional relationship based on the corrected strength can improve the dynamic variability and accuracy of the relative positional relationship. On this basis, if the relative positional relationship indicates that the experimental device is in an adjacent state with other devices, a device proximity edge is constructed between the experimental device and other devices. This not only controls the operation of constructing the device proximity edge, but also improves the consistency between the device proximity edge and the actual adjacent state, thereby improving the accuracy of the device proximity edge.

[0165] Based on the foregoing embodiments, in the IoT RFID-associated experimental equipment management system provided in this application embodiment, the acquisition module is used to generate and send a graph update instruction to the graph construction module if the initial signal strength is less than the strength threshold; the graph construction module is used to remove at least some of the device proximity edges from the dynamic heterogeneous graph based on the graph update instruction if the current dynamic heterogeneous graph contains device proximity edges.

[0166] Accordingly, if the initial signal strength is greater than or equal to the strength threshold, a graph update instruction can be left ungenerated and sent to the graph construction module. Alternatively, the initial signal strength can be corrected using the method provided in the aforementioned embodiments.

[0167] Accordingly, if the current dynamic heterogeneous graph does not contain device proximity edges, then the operation of removing device proximity edges from the dynamic heterogeneous graph can be omitted.

[0168] In some embodiments, the graph update indication may include the device identifiers of the experimental equipment and other equipment corresponding to the initial signal strength.

[0169] In some embodiments, at least some device proximity edges may include device proximity edges associated with the device identifiers of the experimental device and other devices corresponding to the initial signal strength, among all device proximity edges included in the dynamic heterogeneous graph.

[0170] Accordingly, device proximity edges can be removed from dynamic heterogeneous graphs in the following way:

[0171] Based on the graph update instructions, the device identifiers of the experimental equipment and other equipment are determined. Then, based on the matching relationship between the above device identifiers and the device identifiers corresponding to the device nodes associated with each device's adjacent edge in the dynamic heterogeneous graph, at least some of the device adjacent edges to be removed are determined from the dynamic heterogeneous graph, and at least some of the device adjacent edges to be removed are removed from the dynamic heterogeneous graph.

[0172] It should be noted that if a graph update instruction is received from the acquisition module before the graph construction module first constructs the dynamic heterogeneous graph, then when constructing the dynamic heterogeneous graph for the first time, it is not necessary to construct the device neighbor edges associated with the device identifiers of the experimental device and other devices corresponding to the initial signal strength.

[0173] As can be seen from the above, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, the acquisition module is used to generate and send a graph update instruction to the graph construction module if the initial signal strength is less than the previous threshold. The graph construction module is used to remove at least some of the device neighbor edges from the dynamic heterogeneous graph based on the graph update instruction if the current dynamic heterogeneous graph contains device neighbor edges. In this way, the automated dynamic update of device neighbor edges in the dynamic heterogeneous graph is realized. Furthermore, through the synchronization of the graph update instruction between the acquisition module and the graph construction module, precise control of the removal of device neighbor edges in the dynamic heterogeneous graph is achieved, thereby enabling targeted updates of at least some device neighbor edges in the dynamic heterogeneous graph, reducing the number of redundant device neighbor edges in the dynamic heterogeneous graph, and reducing the redundancy of the dynamic heterogeneous graph.

[0174] Based on the foregoing embodiments, in the IoT RFID-associated experimental equipment management system provided in this application embodiment, the acquisition module is used to acquire historical experimental logs associated with the set of experimental equipment, and determine the co-occurrence data of the equipment based on the historical experimental logs.

[0175] In some embodiments, the historical experiment log may include log data recording multiple historical experiments performed within a historical period.

[0176] In some embodiments, device co-occurrence data can be determined in the following ways:

[0177] The minimum support threshold and confidence threshold are set using the Apriori algorithm, and historical experimental logs are scanned to calculate the co-occurrence frequency of experimental devices. Based on the minimum support threshold and confidence threshold, the co-occurrence frequency is filtered to obtain the device combination with the highest co-occurrence frequency and strong correlation. The device identifier and experimental scenario corresponding to each experimental device in the device combination are determined as the device co-occurrence data.

[0178] Figure 3 This is a schematic diagram illustrating the construction process of the dynamic heterogeneous graph provided in the embodiments of this application; such as Figure 3 As shown, the construction process 300 of the dynamic heterogeneous graph may include the following steps:

[0179] Spatial mutually exclusive edges are constructed through geometric collision detection, functional cooperative edges are constructed through functional relationship mapping, device proximity edges are constructed by correcting the initial signal strength, and device co-occurrence edges are constructed by obtaining historical experimental logs. After constructing spatial mutually exclusive edges, functional cooperative edges, device proximity edges, and device co-occurrence edges, the operation of constructing a dynamic heterogeneous graph can be performed.

[0180] It should be noted that the operations of constructing spatially mutually exclusive edges, functionally collaborative edges, device proximity edges, and device co-occurrence edges can be executed in parallel, and this application embodiment does not limit this.

[0181] Through the above process, the efficient and accurate construction of spatially exclusive edges, functionally collaborative edges, device proximity edges, and device co-occurrence edges is achieved, thereby improving the timeliness and accuracy of dynamic heterogeneous graph construction.

[0182] As can be seen from the above, in the IoT RFID-linked experimental equipment management system provided in this application embodiment, historical experimental logs associated with the experimental equipment set are obtained, and equipment co-occurrence data is determined based on the historical experimental logs. In this way, the correlation between equipment co-occurrence data and historical experimental logs is achieved, thereby improving the consistency between the equipment co-occurrence data and historical experimental logs, and improving the accuracy of the equipment co-occurrence data.

[0183] Figure 4 This is a flowchart illustrating the management of experimental equipment provided in an embodiment of this application. Figure 4 As shown, the process may include the following steps:

[0184] Step 401: Collect source data.

[0185] Step 402: Construct a dynamic heterogeneous graph.

[0186] Step 403: Obtain the expected status of the equipment.

[0187] Step 404: Manage devices and update the dynamic heterogeneity diagram.

[0188] For example, at least some of the experimental devices in the experimental device set can be managed by the method provided in the foregoing embodiments, and when at least one data update in the source data is detected, steps 401 to 402 can be executed recursively to dynamically update the dynamic heterogeneous graph based on the updated source data.

[0189] Through the above process, an integrated configuration for the management of experimental equipment and the closed-loop update of the dynamic heterogeneous graph is realized. This not only enables flexible and intelligent dynamic updates of the dynamic heterogeneous graph, but also enables dynamic updates that follow the expected state of the equipment, thereby improving the accuracy of experimental equipment management.

[0190] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0191] The methods disclosed in the various method embodiments provided in this application can be arbitrarily combined to obtain new method embodiments without conflict.

[0192] The features disclosed in the various product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0193] The features disclosed in the various method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0194] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware nodes. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0195] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0196] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0197] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0198] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. An experimental equipment management system of Internet of Things RFID association, characterized in that, include: The data acquisition module is used to collect source data, which includes spatial attribute data, functional association data, device association data, and device co-occurrence data of the experimental equipment deployed in the laboratory. Spatial attribute data includes at least the layout data of the experimental equipment in the laboratory. Functional association data characterizes the experimental functions of the equipment. Device association data includes the relative positional relationships between the experimental equipment and other equipment. Device co-occurrence data includes descriptive data of at least two experimental devices appearing together in historical experiments. Other equipment includes equipment in the experimental equipment set other than the experimental equipment. The laboratory is also linked to the Internet of Things (IoT) and RFID. The graph construction module is used to construct a dynamic heterogeneous graph based on the source data. The dynamic heterogeneous graph includes spatially mutually exclusive edges corresponding to spatial attribute data, functional collaboration edges corresponding to functional association data, device proximity edges corresponding to device association data, and device co-occurrence edges corresponding to device co-occurrence data. The fusion module is used to perform spatiotemporal fusion on the data carried by spatially exclusive edges, functional collaborative edges, device proximity edges, and device co-occurrence edges in the dynamic heterogeneous graph to obtain the fusion result. The equipment management module is used to determine the expected equipment status of the experimental equipment set within at least one time period based on the fusion results, and to manage at least a portion of the experimental equipment in the experimental equipment set based on the expected equipment status. The fusion module is also used to determine a weight set based on the data carried by spatially mutually exclusive edges, functionally cooperative edges, device proximity edges, and device co-occurrence edges respectively, and to perform fusion processing on the data carried by spatially mutually exclusive edges, functionally cooperative edges, device proximity edges, and device co-occurrence edges respectively based on the weight set to obtain the fusion result. The fusion module is also used to process the mutual exclusion state of the nodes associated with the spatial mutual exclusion edge through a logical negation function to obtain a spatial mutual exclusion score, process the functional state of the nodes associated with the functional cooperation edge through a first averaging function to obtain a functional cooperation score, process the co-occurrence state of the nodes associated with the device co-occurrence edge through a second averaging function to obtain a device co-occurrence score, and process the spatial state associated with the device neighbor edge based on the signal strength corresponding to the device neighbor edge to obtain a spatial neighbor score.

2. The IoT RFID correlated lab equipment management system according to claim 1, wherein, The data acquisition module is also used to obtain the set of device locations corresponding to the experimental equipment; The fusion module is also used to integrate the set of device positions to obtain the displacement pattern of the experimental device; The device management module is used to determine the expected device status based on the displacement pattern and fusion results.

3. The IoT RFID correlated lab equipment management system of claim 1, wherein, The expected equipment status includes at least one of the following: equipment abnormality status, equipment cooperation status, and equipment load status at a future time. The equipment management module is used to perform equipment maintenance operations associated with the target equipment and / or related equipment if the expected equipment status includes abnormal equipment status. And / or, The equipment management module is used to identify and output equipment maintenance prompts if the expected equipment status includes an abnormal equipment status; wherein, the target equipment includes experimental equipment that will be in an abnormal equipment status at a future time; and the associated equipment includes at least one device associated with the target equipment.

4. The IoT RFID correlated lab equipment management system of claim 1, wherein, Spatial attribute data includes the dimensions of the experimental equipment and the safe distance between the equipment; the graph construction module is used to process the equipment dimensions, safe distances, and layout data using a geometric collision detection algorithm to obtain the spatial overlap rate between the experimental equipment and other equipment, and to construct mutually exclusive edges based on the spatial overlap rate; Functional association data includes the association between device identifiers and function identifiers; the graph construction module is used to construct functional collaboration edges based on the association relationships; among them, device identifiers include the identifiers of experimental equipment; function identifiers include the identifiers of experimental functions.

5. A management system for IoT-enabled RFID-linked experimental equipment according to claim 1, characterized in that, The acquisition module is used to acquire the initial signal strength associated with the experimental equipment in the experimental equipment set. If the initial signal strength is greater than or equal to the strength threshold, the initial signal strength is corrected to obtain the corrected strength, and the relative positional relationship is determined based on the corrected strength. The graph construction module is used to construct the device proximity edges between experimental devices and other devices if the relative positional relationship characterizes that the experimental device is in an adjacent state with other devices.

6. The IoT RFID correlation based lab equipment management system as claimed in claim 5, wherein, The acquisition module is used to generate and send a graph update indication to the graph construction module if the initial signal strength is less than the strength threshold. The graph construction module is used to remove at least some of the device proximity edges from the dynamic heterogeneous graph if the current dynamic heterogeneous graph contains device proximity edges, based on the graph update instruction.

7. The IoT RFID correlated lab equipment management system of claim 1, wherein, The data acquisition module is used to obtain historical experimental logs associated with the set of experimental equipment, and to determine the co-occurrence data of the equipment based on the historical experimental logs.

8. The IoT RFID correlated lab equipment management system of claim 3, wherein, The fusion result is calculated in the following way: Based on the weights in the weight set, the data carried by spatial mutually exclusive edges, functional cooperation edges, device proximity edges, and device co-occurrence edges are weighted and fused respectively to obtain the fusion result. Specifically, as shown in equation (1): （1） Where t is an integer greater than or equal to 0, used to represent time t or the current time. The fusion result at time t is... Let be the mutual exclusion weights at time t, and be... The functional weight at time t Let the nearest neighbor weights be at time t. Let be the co-occurrence weight at time t. The data carried by the spatially mutually exclusive edge at time t. The data carried by the functional cooperation edge at time t. The data carried by the co-occurrence edge of the devices at time t. The data carried by the device's nearest edge at time t.

Images