A Multi-Device Behavior Interoperability Verification System and Method Based on an IoT Platform

Abstract

This invention discloses a multi-device behavior interoperability verification system and method based on an Internet of Things (IoT) platform, relating to the field of IoT technology. The system includes: real-time collection of operational status data and interaction behavior data of each device according to the device interoperability requirements of the IoT platform; establishment of a device behavior prediction model and construction of device state transition equations; verification of interoperability consistency indicators of multi-device behavior based on device operational status data and interaction behavior data, and calculation of device behavior deviation coefficients; generation of device interoperability anomaly alarms and location of abnormal interaction nodes when the behavior deviation coefficients exceed a preset threshold; and establishment of a three-dimensional dynamic model of the IoT devices using digital twin technology to display the multi-device behavior interoperability verification results and anomaly warning information in real time. The advantage of this invention is that by constructing a dynamic matching mechanism between device state transition equations and an operational status feature library, it effectively solves the problem of state transition consistency verification in multi-device behavior collaboration.

Description

Technical Field

[0001] This invention relates to the field of networking technology, and more specifically to a multi-device behavior interoperability verification system and method based on an Internet of Things (IoT) platform. Background Technology

[0002] With the rapid development of IoT technology, multi-device collaboration scenarios in smart cities, industrial internet, and other fields are becoming increasingly complex. Issues such as heterogeneous device types, diverse communication protocols, and highly dynamic interaction behaviors lead to frequent interoperability vulnerabilities. Traditional methods rely on manual rule configuration or offline log analysis, making it difficult to capture anomalies in device state matching in real time. Especially in cross-protocol interactions and high-concurrency scenarios, deviations from standard logic by device behavior can easily trigger cascading failures. Furthermore, existing technologies lack the ability to dynamically model the spatiotemporal correlation behavior of multiple devices, making it difficult to accurately quantify interoperability consistency.

[0003] Current IoT interoperability verification primarily focuses on protocol compatibility testing, failing to adequately consider the dynamic evolution of device operating states. Anomaly detection mechanisms based on single thresholds cannot adapt to the non-linear changes in device group behavior, and existing visualization solutions often employ two-dimensional planar displays, making it difficult to intuitively reflect the behavioral correlations between devices and anomaly propagation paths. Furthermore, traditional early warning systems frequently suffer from high false alarm rates due to asynchronous data acquisition and a lack of state reliability assessment. Therefore, a verification method integrating dynamic modeling, collaborative weight allocation, and three-dimensional spatial positioning is urgently needed to achieve full lifecycle monitoring of multi-device behavioral interoperability and accurate anomaly tracing. Summary of the Invention

[0004] To address the aforementioned technical issues, this paper provides a multi-device behavior interoperability verification system and method based on an IoT platform. This technical solution solves the problem that the existing technologies lack the ability to dynamically model the spatiotemporal correlation behavior of multiple devices, making it difficult to accurately quantify interoperability consistency.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A multi-device behavior interoperability verification method based on an IoT platform includes:

[0007] Data acquisition steps: Based on the device interoperability requirements of the IoT platform, set up a multi-device behavior data acquisition group to collect the operating status data and interaction behavior data of each device in real time;

[0008] Behavioral modeling steps: Establish a device behavior prediction model and construct the device's state transition equations based on the device's operating status data;

[0009] Interoperability verification steps: Based on the device operating status data and interaction behavior data, verify the interoperability consistency index of multiple device behaviors, and calculate the device behavior deviation coefficient by combining the interoperability consistency index of multiple device behaviors.

[0010] Anomaly warning steps: When the behavior deviation coefficient exceeds the preset threshold, generate a device interoperability anomaly alarm and locate the abnormal interaction node;

[0011] Dynamic visualization steps: Establish a 3D dynamic model of IoT devices using digital twin technology, and display the interoperability verification results of multi-device behavior and anomaly warning information in real time.

[0012] Preferably, the step of setting up a multi-device behavior data collection group according to the device interoperability requirements of the IoT platform, and collecting real-time operating status data and interaction behavior data of each device specifically includes:

[0013] Embed identifiable behavior tags in the device interaction protocol, and extract device interaction behavior sequences through tag parsing;

[0014] Monitoring groups are formed according to equipment type to collect equipment operating parameters, communication protocol data, and interaction response latency.

[0015] The collected data is spatiotemporally aligned to generate a multi-device behavior dataset with timestamps.

[0016] Preferably, the establishment of the device behavior prediction model specifically includes:

[0017] Based on the standard operating data of the equipment, extract the operating status data feature library P when the equipment's operating status changes. , The data characteristics of the operating state when the device transitions from the i-th operating state to the j-th operating state, where n is the total number of operating state types of the device;

[0018] The device behavior prediction model takes the device's operating status data features as input and outputs the similarity between the device's operating status data features and each element in the operating status data feature library.

[0019] Preferably, the construction of the device's state transition equation based on the device's operating state data specifically includes:

[0020] Based on the input of the equipment's operating status data into the equipment behavior prediction model, the similarity between the current operating status data of the equipment and each element in the operating status data feature library is obtained.

[0021] Based on the similarity between the current operating status data of the device and each element in the operating status data feature library, the state transition equation of the device is constructed.

[0022] The state transition equation of the device is as follows:

[0023]

[0024] For the next The probability that the device is in the j-th operating state within a given time period. The current operating status data of the device and the elements in the operating status data feature library. Similarity between them This is the current operating status data of the device.

[0025] Preferably, the step of verifying the interoperability consistency index of multiple device behaviors based on device operating status data and interaction behavior data, and calculating the device behavior deviation coefficient by combining the interoperability consistency indexes of multiple device behaviors, specifically includes:

[0026] Based on the interaction behavior data of all devices connected to the IoT platform, the frequency of simultaneous occurrence of the states of the devices is statistically analyzed.

[0027] Based on the state transition equations of the devices, and combined with the frequency of simultaneous occurrence of states between devices, the interoperability consistency index is calculated using the behavioral consistency formula.

[0028] Based on the interoperability consistency index of the devices, a state credibility weight is added to each device, and the device behavior deviation coefficient is calculated by combining the state credibility weight of each device.

[0029] The formula for behavioral consistency is as follows:

[0030]

[0031] in, This is the interoperability consistency index for device k. Let U be the set of devices excluding device k, and o be an element in U. The number of elements in U. Let k be the set of operating states of device k. Let O be the set of operating states of device O. for The elements in for The elements in Let $ be the frequency at which device k is in state e and device o is in the c-th state simultaneously. For the next The probability that device o is in the c-th state within a given time period. For the next The probability that device k is in the c-th state within a given time period.

[0032] Preferably, the method of assigning state credibility weights to each device based on the device interoperability consistency index, and calculating the device behavior deviation coefficient by combining the state credibility weights of each device, specifically includes:

[0033] Based on the interoperability consistency index of the devices, the state trust weights of the devices are assigned from high to low in order of increasing value.

[0034] Based on the state credibility weight of each device, the behavior consistency formula is weighted and optimized to obtain the device behavior deviation formula, and the device behavior deviation coefficient is calculated based on the device behavior deviation formula.

[0035] The specific formula for the deviation of device behavior is as follows:

[0036]

[0037] Let $k$ be the deviation coefficient of the device behavior of device $k$. The state confidence weight of device o.

[0038] Preferably, the step of generating a device interoperability anomaly alarm and locating the abnormal interaction node when the behavior deviation coefficient exceeds a preset threshold specifically involves:

[0039] All IoT devices whose behavior deviation coefficient exceeds a preset threshold are collected and recorded as devices with abnormal behavior.

[0040] Based on the Internet of Things architecture, the hierarchical connectivity of devices exhibiting abnormal behavior is determined, and the behavior of these devices is investigated sequentially from high to low hierarchy.

[0041] Furthermore, a multi-device behavior interoperability verification system based on an IoT platform is proposed to implement the aforementioned multi-device behavior interoperability verification method based on an IoT platform, characterized by comprising:

[0042] The data acquisition module is configured to embed identifiable behavior tags in the device interaction protocol, extract the interaction behavior sequence through tag parsing, divide the monitoring group according to device type to synchronously collect operating parameters, communication protocol data and interaction response latency, and perform spatiotemporal alignment processing on the collected data to generate a multi-device behavior dataset with timestamps.

[0043] The behavior modeling module includes a feature extraction unit and a prediction engine unit. The feature extraction unit extracts multi-dimensional feature vectors during state transitions from standard operating data to construct an operating state feature library. The prediction engine unit generates the device's state transition equation based on the similarity matching between real-time data and the feature library.

[0044] The interoperability verification module is configured to construct a state correlation matrix by statistically analyzing the co-occurrence frequency of states between devices, and to calculate the device behavior deviation coefficient by combining a weighted consistency algorithm with dynamically allocated state credibility weights. The weight allocation is dynamically adjusted based on the interoperability consistency index ranking.

[0045] The anomaly warning module includes a threshold comparison unit, a topology analysis unit, and a root cause localization unit. It is configured to trace the anomaly propagation path in reverse according to the hierarchical connectivity relationship. When the behavior deviation coefficient exceeds the dynamic threshold, an alarm is triggered and the faulty node is marked.

[0046] The dynamic visualization module integrates a digital twin engine to build a 3D device model with adjustable parameters. It displays the distribution of deviation coefficients in real time through heatmap gradient rendering and generates a multi-view interactive interface that includes an anomaly location topology map.

[0047] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0048] This invention addresses the issue of state transition consistency verification in multi-device behavioral collaboration by constructing a dynamic matching mechanism between device state transition equations and an operational state feature library. It extracts state transition features from historical device operational data and generates probabilistic state transition paths using real-time similarity calculations, enabling continuous monitoring of the compliance of device behavioral logic. Simultaneously, it establishes state transition correlation constraints among device groups through cross-device state co-occurrence frequency analysis and interoperability consistency index fusion calculation, effectively identifying interoperability conflicts caused by abnormal state migrations of single devices. This overcomes the blind spots of traditional static rule verification in covering the evolutionary patterns of temporal behavior, significantly improving the state synchronization and behavioral logic consistency of multi-device collaborative operation in complex IoT scenarios. Attached Figure Description

[0049] Figure 1 This is a flowchart of the multi-device behavior interoperability verification method based on an Internet of Things platform proposed in this invention;

[0050] Figure 2 This is a flowchart of the method for constructing the state transition equation of a device in this invention;

[0051] Figure 3 This is a flowchart of the method for calculating the deviation coefficient of device behavior in this invention;

[0052] Figure 4 This is a flowchart of the method for calculating the deviation coefficient of device behavior by combining the state credibility weights of each device in this invention;

[0053] Figure 5 This is a flowchart of the method for generating device interoperability anomaly alarms and locating abnormal interaction nodes in this invention;

[0054] Figure 6This is an architecture diagram of the electronic devices in this solution;

[0055] Figure 7 This is a schematic diagram of the computer-readable storage medium structure in this scheme.

[0056] The numbers on the map are:

[0057] 500 - Electronic device; 501 - Bus; 502 - CPU; 503 - ROM; 504 - RAM; 505 - Communication port; 506 - Input / output component; 507 - Hard disk; 508 - User interface; 600 - Computer-readable storage medium. Detailed Implementation

[0058] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0059] Reference Figure 1 As shown, the multi-device behavior interoperability verification method based on an IoT platform includes:

[0060] Data acquisition steps: Based on the device interoperability requirements of the IoT platform, set up a multi-device behavior data acquisition group to collect real-time operating status data and interaction behavior data of each device, specifically as follows:

[0061] Embed identifiable behavior tags in the device interaction protocol, and extract device interaction behavior sequences through tag parsing;

[0062] Monitoring groups are formed according to equipment type to collect equipment operating parameters, communication protocol data, and interaction response latency.

[0063] The collected data is spatiotemporally aligned to generate a multi-device behavior dataset with timestamps.

[0064] By establishing a behavior labeling system for pre-defined device interoperability scenarios, such as protocol field extensions or metadata injection, the semantic parsing of device interaction behavior is ensured. Monitoring groups based on device type use distributed data acquisition agents to synchronously capture device operating parameters, such as CPU load, sensor readings, and communication protocol messages, such as MQTT topics, CoAP commands, and interaction latency data. Clock synchronization protocols and spatial coordinate calibration techniques are used to eliminate spatiotemporal deviations of multi-source data, forming a high-precision spatiotemporally aligned multidimensional dataset, providing fine-grained input for subsequent behavior modeling.

[0065] Behavioral modeling steps: Establish a device behavior prediction model and construct the device's state transition equations based on the device's operating status data;

[0066] A state transition feature library is constructed based on historical operating data, and the implicit patterns of equipment state transitions are extracted using the feature vectorization method. The state transition equation generates probabilistic transition paths by calculating the similarity between real-time data and the feature library, quantifying the possibility of equipment migration from the current state to the next state, thereby dynamically reflecting the compliance of equipment behavior logic and overcoming the limitations of traditional state machine models in modeling nonlinear behavior.

[0067] Interoperability verification steps: Based on the device operating status data and interaction behavior data, verify the interoperability consistency index of multiple device behaviors, and calculate the device behavior deviation coefficient by combining the interoperability consistency index of multiple device behaviors.

[0068] By statistically analyzing the frequency of cross-device state co-occurrence, a behavioral correlation matrix between devices is constructed. Combined with the expected state matching degree predicted by the state transition equation, the deviation between the actual interaction and the theoretical model is calculated. The device behavior deviation coefficient is aggregated using a weighted fusion algorithm to aggregate the consistency index of multiple devices, with a focus on strengthening the weight contribution of abnormal devices, so as to achieve accurate quantification of the intensity of abnormal group behavior.

[0069] Anomaly warning steps: When the behavior deviation coefficient exceeds the preset threshold, generate a device interoperability anomaly alarm and locate the abnormal interaction node;

[0070] The preset threshold is dynamically adjusted according to the device type. For example, strict thresholds are used for industrial equipment and flexible thresholds are used for consumer devices. When an abnormal alarm is generated, the hierarchical topology of the IoT architecture is combined, such as edge layer-gateway layer-cloud layer, to analyze the abnormal propagation path. By tracing back the device interaction logs and parsing the protocol stack, the root node of the abnormal can be located, avoiding false alarms or missed alarms caused by a single threshold.

[0071] Dynamic visualization steps: Establish a 3D dynamic model of IoT devices using digital twin technology, and display the interoperability verification results of multi-device behavior and anomaly warning information in real time.

[0072] Based on a digital twin engine, physical devices are mapped into interactive virtual entities. The spatial distribution of device behavior deviation coefficients is dynamically rendered through heatmaps, and the topological connections of anomaly propagation paths are superimposed. The interactive interface supports multi-dimensional view switching and real-time synchronization of verification results and alarm information, providing operation and maintenance personnel with intuitive global situational awareness and precise local anomaly location capabilities.

[0073] Specifically, establishing a device behavior prediction model includes:

[0074] Based on the standard operating data of the equipment, extract the operating status data feature library P when the equipment's operating status changes. , The data characteristics of the operating state when the device transitions from the i-th operating state to the j-th operating state, where n is the total number of operating state types of the device;

[0075] The equipment behavior prediction model takes the equipment's operating status data features as input and outputs the similarity between the equipment's operating status data features and each element in the operating status data feature library.

[0076] By constructing a standard operating state feature library P and a dynamic similarity matching mechanism, the accuracy and real-time performance of equipment behavior prediction are significantly improved. Based on state transition features, such as the multi-dimensional data patterns of equipment transitioning from state i to state j, the feature library accurately characterizes the spatiotemporal correlation of legitimate state transitions. This allows the behavior prediction model to effectively identify abnormal state transition behaviors that deviate from standard logic by calculating the similarity between real-time data features and the feature library, such as cosine similarity. Compared to traditional static rule bases or fixed threshold detection methods, this technology not only supports dynamic coverage of all equipment state types but also adapts to the differences in operating characteristics of different equipment through a similarity quantification mechanism.

[0077] Reference Figure 2 As shown, constructing the state transition equation of a device based on its operating status data specifically includes:

[0078] Based on the input of the equipment's operating status data into the equipment behavior prediction model, the similarity between the current operating status data of the equipment and each element in the operating status data feature library is obtained.

[0079] Based on the similarity between the current operating status data of the device and each element in the operating status data feature library, the state transition equation of the device is constructed.

[0080] The state transition equation of the device is as follows:

[0081]

[0082] For the next The probability that the device is in the j-th operating state within a given time period. The current operating status data of the device and the elements in the operating status data feature library. Similarity between them This is the current operating status data of the device.

[0083] By dynamically constructing probabilistic state transition equations through real-time similarity matching, the adaptability of the equipment behavior prediction model and the sensitivity of anomaly detection are significantly improved. Utilizing the similarity calculation between current operating data and historical state transition features in the feature library, the probability distribution of the equipment's next state is transformed into an aggregated result of multi-dimensional similarity, overcoming the limitations of fixed transition probabilities in traditional state machine models. This method not only dynamically adjusts the state transition logic according to the actual operating characteristics of the equipment, but also captures implicit state transition deviations caused by factors such as equipment aging and environmental disturbances through a similarity decay mechanism. In predictive maintenance scenarios for industrial equipment, it can identify abnormal state jumps caused by mechanical wear in advance, while avoiding misjudgments due to individual equipment differences.

[0084] Reference Figure 3 As shown, based on device operating status data and interaction behavior data, the interoperability consistency index of multiple device behaviors is verified, and the device behavior deviation coefficient is calculated by combining the interoperability consistency index of multiple device behaviors. Specifically, this includes:

[0085] Based on the interaction behavior data of all devices connected to the IoT platform, the frequency of simultaneous occurrence of the states of the devices is statistically analyzed.

[0086] Based on the state transition equations of the devices, and combined with the frequency of simultaneous occurrence of states between devices, the interoperability consistency index is calculated using the behavioral consistency formula.

[0087] Based on the interoperability consistency index of the devices, a state credibility weight is added to each device, and the device behavior deviation coefficient is calculated by combining the state credibility weight of each device.

[0088] The formula for behavioral consistency is as follows:

[0089]

[0090] in, This is the interoperability consistency index for device k. Let U be the set of devices excluding device k, and o be an element in U. The number of elements in U. Let k be the set of operating states of device k. Let O be the set of operating states of device O. for The elements in for The elements in Let $ be the frequency at which device k is in state e and device o is in the c-th state simultaneously. For the next The probability that device o is in the c-th state within a given time period. For the next The probability that device k is in the c-th state within a given time period.

[0091] By employing a multi-dimensional collaborative analysis of the co-occurrence frequency and state transition probability among devices, a dynamically weighted interoperability consistency evaluation system is constructed, significantly improving the comprehensiveness and reliability of anomaly detection in complex device groups. This system integrates real-time device interaction states, such as the co-occurrence frequency of device k and device o in state (e,c), with the future state prediction probability from the state transition equation, based on a behavior consistency formula. , By performing fitting analysis, not only can explicit behavioral conflicts between devices be captured, but potential temporal logical contradictions can also be identified through probability deviations. Dynamically allocating state reliability weights through interoperability consistency indices ensures that the deviation coefficients of high-risk anomalies contribute more significantly to group computation, effectively addressing the anomaly signal dilution problem caused by equalizing device weights in traditional methods. Simultaneously, adaptive weight adjustment reduces false alarm rates caused by environmental noise interference, providing accurate collaborative behavior health assessment and anomaly tracing capabilities for industrial IoT device clusters.

[0092] Reference Figure 4 As shown, based on the interoperability consistency index of the devices, a state credibility weight is added to each device, and the device behavior deviation coefficient is calculated by combining the state credibility weight of each device. Specifically, this includes:

[0093] Based on the interoperability consistency index of the devices, the state trust weights of the devices are assigned from high to low in order of increasing value.

[0094] The specific state credibility weight is determined using the following formula:

[0095]

[0096] in, Let k be the state confidence weight. This is the maximum value among all interoperability consistency metrics for all devices. This is the minimum value among all interoperability consistency metrics for all devices.

[0097] Based on the state credibility weight of each device, the behavior consistency formula is weighted and optimized to obtain the device behavior deviation formula, and the device behavior deviation coefficient is calculated based on the device behavior deviation formula.

[0098] The specific formula for equipment behavior deviation is as follows:

[0099]

[0100] Let $k$ be the deviation coefficient of the device behavior of device $k$. The state confidence weight of device o.

[0101] By employing a dynamic and reliable weight allocation mechanism and weighted deviation coefficient calculation, the accuracy and sensitivity of multi-device collaborative anomaly detection are both significantly improved. The design, based on the inverse weight allocation of interoperability consistency indices (assigning higher weights to devices with low consistency), significantly amplifies the contribution of anomalous devices in group deviation calculation, effectively overcoming the deficiency of traditional weighted processing modes where anomalous signals are easily overwhelmed by normal device data. Combined with a weighted and optimized device behavior deviation formula, the co-occurrence deviation between device states and the difference in individual state transition probabilities are coupled for analysis. This not only captures explicit behavioral conflicts but also identifies implicit collaborative logic anomalies through weight gradient differences. In industrial IoT multi-device collaborative scenarios, this mechanism can prioritize the identification of anomalous devices and reduce environmental noise interference and false alarm rates through dynamic weight adjustment, providing highly reliable behavioral health assessment and root cause localization capabilities for device clusters.

[0102] Reference Figure 5 As shown, when the behavior deviation coefficient exceeds a preset threshold, a device interoperability anomaly alarm is generated, and the specific abnormal interaction node is located:

[0103] All IoT devices whose behavior deviation coefficient exceeds a preset threshold are collected and recorded as devices with abnormal behavior.

[0104] Based on the Internet of Things architecture, the hierarchical connectivity of devices exhibiting abnormal behavior is determined, and the behavior of these devices is investigated sequentially from high to low hierarchy.

[0105] By aggregating abnormal devices and employing a hierarchical troubleshooting mechanism, rapid and accurate location of interoperability faults in complex IoT systems can be achieved. After filtering devices exhibiting abnormal behavior based on dynamic thresholds, and combining this with hierarchical topology analysis of the IoT architecture, such as the physical connections and data flow dependencies between the edge layer, gateway layer, and cloud layer, behavior troubleshooting is initiated preferentially from higher-level nodes, such as core gateways or control centers. This allows for rapid identification of the root device causing cascading anomalies, avoiding the resource waste caused by traditional full-scale traversal detection. Simultaneously, through reverse tracing of hierarchical connectivity relationships, such as reverse analysis of abnormal signal propagation paths, critical paths of anomaly propagation and secondary affected nodes can be identified within the device cluster, significantly improving operational efficiency and reducing overall system diagnostic energy consumption.

[0106] Furthermore, based on the same inventive concept as the above method, this solution also proposes a multi-device behavior interoperability verification system based on an Internet of Things platform, comprising:

[0107] The data acquisition module is configured to embed identifiable behavior tags in the device interaction protocol, extract the interaction behavior sequence through tag parsing, divide the monitoring group according to device type to synchronously collect operating parameters, communication protocol data and interaction response latency, and perform spatiotemporal alignment processing on the collected data to generate a multi-device behavior dataset with timestamps.

[0108] The behavior modeling module includes a feature extraction unit and a prediction engine unit. The feature extraction unit extracts multi-dimensional feature vectors during state transitions from standard operating data to build an operating state feature library. The prediction engine unit generates the device's state transition equation based on the similarity matching between real-time data and the feature library.

[0109] The interoperability verification module is configured to construct a state association matrix by statistically analyzing the co-occurrence frequency of states between devices. It calculates the deviation coefficient of device behavior by combining a weighted consistency algorithm with dynamically allocated state credibility weights. The weight allocation is dynamically adjusted based on the interoperability consistency index ranking.

[0110] The anomaly warning module includes a threshold comparison unit, a topology analysis unit, and a root cause localization unit. It is configured to trace the anomaly propagation path in reverse according to the hierarchical connectivity relationship. When the behavior deviation coefficient exceeds the dynamic threshold, an alarm is triggered and the faulty node is marked.

[0111] The dynamic visualization module integrates a digital twin engine to build a 3D device model with adjustable parameters. It displays the distribution of deviation coefficients in real time through heatmap gradient rendering and generates a multi-view interactive interface that includes an anomaly location topology map.

[0112] Furthermore, the method according to the embodiments of this application can also be achieved by means of... Figure 6 The architecture of the electronic device shown is used to implement this. For example... Figure 6 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, ROM 503, RAM 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as ROM 503 or hard disk 507, may store a multi-device behavior interoperability verification method based on an IoT platform provided in this application. The electronic device 500 may also include a user interface 508. Of course, Figure 6 The architecture shown is merely exemplary and can be omitted as needed when implementing different devices. Figure 6 One or more components in the illustrated electronic device.

[0113] Figure 7 This is a schematic diagram of a computer-readable storage medium structure provided in one embodiment of this application. Figure 7The diagram illustrates a computer-readable storage medium 600 according to one embodiment of this application. The computer-readable storage medium 600 stores computer-readable instructions. When executed by a processor, the computer-readable instructions can perform a multi-device behavior interoperability verification method based on an Internet of Things (IoT) platform, as described above with reference to the accompanying drawings. The storage medium 600 includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0114] In summary, the advantages of this invention are as follows: By constructing a dynamic matching mechanism between device state transition equations and an operational state feature library, it effectively addresses the problem of state transition consistency verification in multi-device behavioral collaboration. State transition features are extracted based on historical device operational data, and probabilistic state transition paths are generated through real-time similarity calculations, enabling continuous monitoring of the compliance of device behavioral logic. Simultaneously, by integrating cross-device state co-occurrence frequency analysis with interoperability consistency index calculations, state transition association constraints between device groups are established, effectively identifying interoperability conflicts caused by abnormal state migrations of single devices. This overcomes the blind spots in traditional static rule verification regarding the evolutionary patterns of temporal behavior, significantly improving the state synchronization and behavioral logic consistency of multi-device collaborative operation in complex IoT scenarios.

[0115] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A method for verifying the interoperability of multi-device behaviors based on an Internet of Things (IoT) platform, characterized in that: include: Data acquisition steps: Based on the device interoperability requirements of the IoT platform, set up a multi-device behavior data acquisition group to collect the operating status data and interaction behavior data of each device in real time; Behavioral modeling steps: Establish a device behavior prediction model and construct the device's state transition equations based on the device's operating status data; Interoperability verification steps: Based on the device operating status data and interaction behavior data, verify the interoperability consistency index of multiple device behaviors, and calculate the device behavior deviation coefficient by combining the interoperability consistency index of multiple device behaviors. Anomaly warning steps: When the behavior deviation coefficient exceeds the preset threshold, generate a device interoperability anomaly alarm and locate the abnormal interaction node; Dynamic visualization steps: Establish a 3D dynamic model of IoT devices using digital twin technology, and display the interoperability verification results of multi-device behavior and anomaly warning information in real time.

2. The multi-device behavior interoperability verification method based on an IoT platform according to claim 1, characterized in that, The step of setting up a multi-device behavior data collection group based on the device interoperability requirements of the IoT platform to collect real-time operating status data and interaction behavior data of each device specifically includes: Embed identifiable behavior tags in the device interaction protocol, and extract device interaction behavior sequences through tag parsing; Monitoring groups are formed according to equipment type to collect equipment operating parameters, communication protocol data, and interaction response latency. The collected data is spatiotemporally aligned to generate a multi-device behavior dataset with timestamps.

3. The multi-device behavior interoperability verification method based on an IoT platform according to claim 2, characterized in that, The establishment of the equipment behavior prediction model specifically includes: Based on the standard operating data of the equipment, extract the operating status data feature library P when the equipment's operating status changes. , The data characteristics of the operating state when the device transitions from the i-th operating state to the j-th operating state, where n is the total number of operating state types of the device; The device behavior prediction model takes the device's operating status data features as input and outputs the similarity between the device's operating status data features and each element in the operating status data feature library.

4. The multi-device behavior interoperability verification method based on an IoT platform according to claim 3, characterized in that, The construction of the device's state transition equation based on the device's operating status data specifically includes: Based on the input of the equipment's operating status data into the equipment behavior prediction model, the similarity between the current operating status data of the equipment and each element in the operating status data feature library is obtained. Based on the similarity between the current operating status data of the device and each element in the operating status data feature library, the state transition equation of the device is constructed. The state transition equation of the device is as follows: For the next The probability that the device is in the j-th operating state within a given time period. The current operating status data of the device and the elements in the operating status data feature library. Similarity between them This is the current operating status data of the device.

5. The multi-device behavior interoperability verification method based on an IoT platform according to claim 4, characterized in that, The step of verifying the interoperability consistency index of multiple device behaviors based on device operating status data and interaction behavior data, and calculating the device behavior deviation coefficient by combining the interoperability consistency index of multiple device behaviors, specifically includes: Based on the interaction behavior data of all devices connected to the IoT platform, the frequency of simultaneous occurrence of the states of the devices is statistically analyzed. Based on the state transition equations of the devices, and combined with the frequency of simultaneous occurrence of states between devices, the interoperability consistency index is calculated using the behavioral consistency formula. Based on the interoperability consistency index of the devices, a state credibility weight is added to each device, and the device behavior deviation coefficient is calculated by combining the state credibility weight of each device. The formula for behavioral consistency is as follows: in, This is the interoperability consistency index for device k. Let U be the set of devices excluding device k, and o be an element in U. The number of elements in U. Let k be the set of operating states of device k. Let O be the set of operating states of device O. for The elements in for The elements in Let $ be the frequency at which device k is in state e and device o is in the c-th state simultaneously. For the next The probability that device o is in the c-th state within a given time period. For the next The probability that device k is in the c-th state within a given time period.

6. The multi-device behavior interoperability verification method based on an IoT platform according to claim 5, characterized in that, The device-based interoperability consistency index, which assigns a state credibility weight to each device and calculates the device behavior deviation coefficient based on the state credibility weight of each device, specifically includes: Based on the interoperability consistency index of the devices, the state trust weights of the devices are assigned from high to low in order of increasing value. Based on the state credibility weight of each device, the behavior consistency formula is weighted and optimized to obtain the device behavior deviation formula, and the device behavior deviation coefficient is calculated based on the device behavior deviation formula. The specific formula for the deviation of device behavior is as follows: Let $k$ be the deviation coefficient of the device behavior of device $k$. The state confidence weight of device o.

7. The multi-device behavior interoperability verification method based on an IoT platform according to claim 6, characterized in that, The specific steps for generating a device interoperability anomaly alarm and locating the abnormal interaction node when the behavior deviation coefficient exceeds a preset threshold are as follows: All IoT devices whose behavior deviation coefficient exceeds a preset threshold are collected and recorded as devices with abnormal behavior. Based on the Internet of Things architecture, the hierarchical connectivity of devices exhibiting abnormal behavior is determined, and the behavior of these devices is investigated sequentially from high to low hierarchy.

8. A multi-device behavior interoperability verification system based on an Internet of Things (IoT) platform, used to implement the multi-device behavior interoperability verification method based on an IoT platform as described in any one of claims 1-7, characterized in that, include: The data acquisition module is configured to embed identifiable behavior tags in the device interaction protocol, extract the interaction behavior sequence through tag parsing, divide the monitoring group according to device type to synchronously collect operating parameters, communication protocol data and interaction response latency, and perform spatiotemporal alignment processing on the collected data to generate a multi-device behavior dataset with timestamps. The behavior modeling module includes a feature extraction unit and a prediction engine unit. The feature extraction unit extracts multi-dimensional feature vectors during state transitions from standard operating data to construct an operating state feature library. The prediction engine unit generates the device's state transition equation based on the similarity matching between real-time data and the feature library. The interoperability verification module is configured to construct a state correlation matrix by statistically analyzing the co-occurrence frequency of states between devices, and to calculate the deviation coefficient of device behavior by using a weighted consistency algorithm combined with dynamically allocated state credibility weights. The weight allocation is dynamically adjusted based on the interoperability consistency index ranking. The anomaly warning module includes a threshold comparison unit, a topology analysis unit, and a root cause localization unit. It is configured to trace the anomaly propagation path in reverse according to the hierarchical connectivity relationship. When the behavior deviation coefficient exceeds the dynamic threshold, an alarm is triggered and the faulty node is marked. The dynamic visualization module integrates a digital twin engine to build a 3D device model with adjustable parameters. It displays the distribution of deviation coefficients in real time through heatmap gradient rendering and generates a multi-view interactive interface that includes an anomaly location topology map.

9. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the multi-device behavior interoperability verification method based on an IoT platform as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the multi-device behavior interoperability verification method based on the Internet of Things platform as described in any one of claims 1-7.

Images