Inspection service management system based on artificial intelligence and Internet of Things

Abstract

The invention relates to the technical field of artificial intelligence and Internet of Things, in particular to an inspection service management system based on artificial intelligence and Internet of Things, which comprises a data acquisition module, an edge calculation module, a task allocation module, a path planning module, an early warning module and a user interaction module. Wherein the data acquisition module is used for acquiring multi-dimensional data of environment and equipment in real time; the edge calculation module is used for carrying out preliminary analysis and processing on the multi-dimensional data; the task distribution module is used for generating inspection tasks according to inspection rules; the path planning module is used for generating an optimal path of the inspection equipment; the early warning module is used for generating an early warning signal when the potential risk is detected; and the user interaction module is used for displaying the state of the system through a visual interface. According to the invention, by realizing real-time data processing, dynamic task scheduling and path optimization, the response speed and efficiency of the system are improved, and meanwhile, the equipment fault prevention and decision-making capabilities of operators are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence and the Internet of Things, and in particular to an inspection service management system based on artificial intelligence and the Internet of Things. Background Art

[0002] In modern industry and urban management, it has become a common practice to use artificial intelligence and Internet of Things technologies to dynamically monitor and maintain various facilities. These technologies make it possible to remotely monitor equipment status, optimize operation and maintenance processes, and prevent potential equipment failures in advance, especially in vast or difficult to directly access areas such as pipelines, power lines, and large mechanical equipment. The efficient operation of the inspection service management system is crucial to ensuring the stability and safety of facilities. However, although existing systems are able to collect large amounts of data and perform basic processing, they often lack the ability to effectively schedule tasks, optimize paths, and respond to risks in real time.

[0003] The main problem with existing technologies is that, although they can perform basic data collection and monitoring, they often lack effective data integration, intelligent task allocation and early warning mechanisms, which limits the application efficiency of inspection systems in complex environments, especially in the response speed and accuracy when facing emergencies and complex task priority adjustments. In addition, existing systems usually do not provide sufficient user interaction functions, making it difficult for operators to make quick decisions and adjust inspection strategies based on real-time data.

[0004] Therefore, it is necessary to develop a new inspection service management system that can integrate advanced artificial intelligence algorithms and Internet of Things technologies to achieve more advanced data processing, task scheduling, and early warning response to improve the overall performance and adaptability of the system. Summary of the invention

[0005] Based on the above objectives, the present invention provides an inspection service management system based on artificial intelligence and the Internet of Things.

[0006] The inspection service management system based on artificial intelligence and the Internet of Things includes a data acquisition module, an edge computing module, a task allocation module, a path planning module, an early warning module, and a user interaction module; among which:

[0007] Data acquisition module: Various sensors and mobile nodes deployed in the inspection area are used to collect multi-dimensional data of the environment and equipment in real time, and transmit the data to the edge computing module through the Internet of Things protocol;

[0008] Edge computing module: receives multi-dimensional data from the data acquisition module, and performs preliminary analysis and processing on the multi-dimensional data, including noise filtering and anomaly detection. The processed relevant information will be transmitted to the task allocation module and path planning module;

[0009] Task allocation module: Based on the relevant information processed by the edge computing module, it generates inspection tasks according to the preset inspection rules, dynamically optimizes the priority and execution order of tasks, and sends the optimized task instructions to the path planning module for path generation;

[0010] Path planning module: Based on the task instructions provided by the task assignment module and the environmental data processed by the edge computing module, the algorithm is used to generate the optimal path for the inspection equipment, and the planning results are sent to the inspection equipment for executing the inspection task;

[0011] Early warning module: Receives data processed by the edge computing module and combines historical data to predict and analyze equipment status. When potential risks are detected, the early warning module generates an early warning signal and feeds the early warning information back to the task allocation module to adjust the task plan.

[0012] User interaction module: used to display the system's operating status, task progress and equipment status through an intuitive interface, allowing users to view inspection data and adjust inspection strategies. The user's adjusted instructions are transmitted to the task allocation module through the user interaction module, and the task allocation module updates the task execution strategy based on the adjustments.

[0013] Optionally, the data acquisition module includes a sensor unit, a mobile node unit and a data transmission unit; wherein:

[0014] Sensor unit: multiple sensors fixedly deployed in the inspection area, used to continuously monitor environmental parameters and equipment status. The multiple sensors include temperature sensors, humidity sensors, vibration sensors and image sensors. The temperature sensor is used to measure the temperature change data of the environment and equipment, the humidity sensor is used to monitor the air humidity data, the vibration sensor is used to detect the mechanical vibration data of the equipment, and the image sensor is used to obtain image information of the equipment and the environment;

[0015] Mobile node unit: Multiple mobile nodes are deployed in the inspection area to autonomously adjust their positions according to the requirements of the inspection task to cover various monitoring points in the inspection area. The mobile node unit is equipped with an autonomous mobile device to dynamically monitor the predetermined key areas;

[0016] Data transmission unit: transmits the multi-dimensional data collected by the sensor unit and the mobile node unit to the edge computing module through the Internet of Things protocol.

[0017] Optionally, the edge computing module includes a data receiving unit and a data processing unit; wherein:

[0018] Data receiving unit: receives multi-dimensional data from the data acquisition module through a high-speed wireless communication interface, performs synchronous processing on the real-time data, performs normalization processing after synchronous processing, and stores it in a local cache in a standardized format;

[0019] Data processing unit: used for preliminary analysis and processing of the data transmitted by the data receiving unit, the data processing unit includes a noise filtering subunit and an abnormality detection subunit;

[0020] Noise filtering subunit: adopts a multi-level filtering algorithm to dynamically adjust the filtering strength according to the preset filtering parameters while receiving data to remove interference signals in the environment and equipment status data;

[0021] Anomaly detection subunit: It is used to detect anomalies in data in real time, judge the validity of data and filter out abnormal data by analyzing mutations, over-limits and unexpected changes.

[0022] Optionally, the noise filtering subunit includes a primary filtering process, a secondary filtering process and a tertiary filtering process; the primary filtering process outputs D1(t), the secondary filtering process outputs D2(t), and a dynamic intensity adjustment mechanism is provided between the secondary filtering process and the tertiary filtering process, and the dynamic intensity adjustment mechanism is used to dynamically adjust the intensity of the filtering according to the change of the real-time collected data and the preset filtering parameter P(t), and the adjusted filtering intensity is expressed as: Among them, S(t) is the initial filter strength, α and β are the filter strength adjustment coefficients, S A (t) is the adjusted filter strength, It represents the rate of change of the data D2(t) after secondary filtering at time t; after the dynamic intensity adjustment mechanism is adjusted, the third-level filtering processing output D3(t) is performed, which is the final filtered output data.

[0023] Optionally, the anomaly detection subunit specifically includes:

[0024] Mutation analysis: Perform mutation analysis on the final filtered output data D3(t) to detect rapid change patterns in the data and calculate the rate of change V(t) of each data point compared to the previous time point;

[0025] Out-of-limit analysis: Check whether the data exceeds the normal range by comparing the purified data D3(t) with the preset upper limit U L and the lower limit L L Threshold, to determine whether the data exceeds the limit, specifically when D3(t)>U L or D3(t) <L L When , it is marked as an out-of-limit data point;

[0026] Expected deviation analysis: The validity of the data is determined by analyzing the deviation ΔD(t) between the purified data and the expected model output, and the purified data D3(t) and the expected value D are calculated. exp The deviation between (t) is: ΔD(t) = D3(t)-D exp (t), if the deviation ΔD(t) exceeds the set deviation threshold T Δ , it is marked as a data point that does not meet expectations;

[0027] Anomaly score calculation and determination: The results of mutation analysis, over-limit analysis, and expected deviation analysis are combined to calculate the final anomaly score E. f (t), the formula is: E f (t) = w1×V(t)+w2×overlimit judgment+w3×ΔD(t), where w1, w2 and w3 are weight coefficients of each analysis method. f (t) exceeds the preset abnormal threshold T E When , it is determined as abnormal data and filtered;

[0028] Filter abnormal data: For data points that are determined to be abnormal, remove them from the data set and output the filtered data D f (t).

[0029] Optionally, the task allocation module includes a task generation unit, a priority evaluation unit, a sequence optimization unit and a task output unit; wherein:

[0030] Task generation unit: used to receive data processed by the edge computing module D f (t), and generate specific inspection tasks according to the preset inspection rules R, which include equipment inspection frequency, environmental monitoring standards and safety requirements. By analyzing the rules R and combining the data D f (t), the task generation unit outputs the inspection task list T;

[0031] Priority evaluation unit: performs priority evaluation on each task in the inspection task list T output by the task generation unit. The priority evaluation is based on multiple factors, including the importance of the task I(T i ), urgency level U(T i ) and the device status S(T i ), each task T i The priority P(T i ) is calculated as: P(T i )=w1×I(T i )+w2×U(T i )+w3×S(T i ), where w1, w2, w3 are evaluation weight coefficients, P(T i) is the priority score of the i-th task;

[0032] Sequential optimization unit: According to the task priority P(T i ), sort the task list T, and the order optimization unit specifically uses the sorting function Sort(T, P(T i )) is used to calculate the task priority P(T i ) to sort the tasks, which can be expressed as: Among them, O(T) is the task execution order list arranged in descending order of priority, and the task with higher priority is executed first;

[0033] Task output unit: transmits the optimized task execution sequence O(T) to the path planning module and the user interaction module.

[0034] Optionally, the path planning module includes a path calculation unit, an obstacle detection unit and a path optimization unit; wherein:

[0035] Path calculation unit: first parse the inspection target points and sequence in the task instructions, and combine them with the environmental data D f (t) and the location of the equipment, and preliminarily calculate the path set P of the inspection equipment init ;

[0036] Obstacle detection unit: the preliminary path set P generated by the path calculation unit init Obstacle detection is performed, and the environmental data provided by the edge computing module is combined to identify the location of obstacles on the inspection equipment path and exclude them from the preliminary path to form an adjusted path set P adj ;

[0037] Path optimization unit: adjust the path set P adj Optimize and use the path optimization strategy based on heuristic algorithm to calculate the optimal path P of the inspection equipment opt , the optimal path calculation takes into account multiple factors, including the path length L(P j )、Energy consumption E(P j ) and time T(P j ), the formula of the optimal path is: opt =min P (w1×L(P)+w2×E(P)+w3×T(P)), where w1, w2 and w3 are weight coefficients for path optimization, min P It means that the path that minimizes the objective function value among all paths P is the optimal path, P opt is the optimal path;

[0038] Path output unit: The optimized optimal path P opt Transmitted to the inspection equipment to ensure that the equipment performs inspection tasks along the optimal path.

[0039] Optionally, the warning module includes a historical data comparison unit, a state prediction unit, a warning signal generation unit and a warning information feedback unit; wherein:

[0040] Historical data comparison unit: receives the current data D processed by the edge computing module f (t) and the historical operation data of the equipment D h (t), and compare the two to identify abnormal trends. The comparison is completed by calculating the deviation ΔD(t) between the current data and the historical data. The formula is: ΔD(t) = D f (t)-D h (t), when ΔD(t) exceeds the set deviation threshold T D When , it is recorded as an abnormal trend;

[0041] State prediction unit: predicts the future operation state of the equipment based on the regression algorithm. p (t+Δt) is the predicted state result of the equipment. When S p (t+Δt) exceeds the preset safety threshold S safe When , it is marked as a potential risk state;

[0042] Warning signal generation unit: used to immediately generate a warning signal when the state prediction unit detects that there is a potential risk in the future state of the equipment. The warning signal includes the risk level, risk type and recommended operation;

[0043] Early warning information feedback unit: After the early warning signal is generated, the early warning information feedback unit will feed back the information in the early warning signal to the task allocation module. The task allocation module will adjust the task plan according to the risk level and type in the early warning signal, including giving priority to high-risk equipment or rearranging the inspection route.

[0044] Optionally, the warning information feedback unit specifically includes:

[0045] Risk analysis: Receive the warning signal transmitted by the warning signal generation unit and analyze the risk level R in the signal l and risk type R t ;

[0046] Task priority adjustment: According to the risk level R l Adjust the priority of the task. The adjustment process is to recalculate the priority score P(T i ) is completed, the adjusted priority score formula is: P′(T i )=P(T i )+α×Rl , where P′(T i ) is the adjusted task priority, P(T i ) is the original task priority, α is the risk adjustment coefficient;

[0047] Task reallocation: After the task priority adjustment unit recalculates the priorities, the task reallocation unit reorders the tasks according to the new priority scores and reallocates resources.

[0048] Optionally, the user interaction module includes a status display unit, a task progress monitoring unit, a device status display unit and a strategy adjustment unit; wherein:

[0049] Status display unit: used to receive the operation data from each module in real time and present it in a visual way, including dashboards, charts and real-time updated status indicators;

[0050] Task progress monitoring unit: displays the progress of the current inspection task in real time, including the execution status of the task, the list of completed tasks, ongoing tasks, and tasks to be started. The task progress monitoring unit also displays the execution order of the tasks in the form of a timeline or Gantt chart, and distinguishes different task states with color coding;

[0051] Equipment status display unit: used to display the current status information of the inspection equipment, including the equipment's geographic location, operating status, battery power, sensor readings, and health status;

[0052] Policy adjustment unit: allows users to adjust inspection policies based on real-time information on system operation status, task progress, and device status. The policy adjustment unit provides an intuitive operation interface, where users can adjust task priorities, modify the execution order of tasks, or add new inspection tasks by dragging and dropping, clicking, or entering commands.

[0053] Beneficial effects of the present invention:

[0054] The present invention greatly improves the dynamic monitoring capability of equipment and environmental status by integrating advanced artificial intelligence and Internet of Things technologies. The core advantage of the system is that it can process and analyze complex data collected from inspection equipment in real time, and effectively perform data fusion and anomaly detection. This advanced analysis capability allows the system to not only identify current equipment problems in a timely manner, but also actively predict possible future failures or risks through the status prediction module. Such an early warning mechanism can significantly reduce the equipment failure rate and avoid unexpected downtime, thereby improving the operating efficiency of the equipment and extending its service life.

[0055] The present invention automatically adjusts the priority and sequence of inspection tasks through real-time data and risk assessment, and can also optimize the inspection path in real time according to environmental changes and equipment status. This dynamic adjustment mechanism ensures the optimal utilization and time management of system resources, and greatly reduces operating costs. At the same time, the intuitive interface provided by the user interaction module enables operators to receive early warning information and task updates in real time, allowing them to quickly adjust inspection strategies when necessary, thereby enhancing the system's response capabilities to emergencies and ensuring the continuous and stable operation of key facilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 A schematic diagram of an inspection service management system according to an embodiment of the present invention;

[0058] Figure 2 Schematic diagram of an edge computing module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0059] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0060] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0061] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0062] like Figure 1-Figure 2 As shown, the inspection service management system based on artificial intelligence and the Internet of Things includes a data acquisition module, an edge computing module, a task allocation module, a path planning module, an early warning module, and a user interaction module; among which:

[0063] Data acquisition module: Various sensors (such as temperature sensors, humidity sensors, vibration sensors, image sensors) and mobile nodes deployed in the inspection area are used to collect multi-dimensional data of the environment and equipment in real time, and transmit the data to the edge computing module through the Internet of Things protocol for preliminary processing and analysis;

[0064] Edge computing module: Receives multi-dimensional data from the data acquisition module and performs preliminary analysis and processing on the multi-dimensional data, including noise filtering and anomaly detection. The processed relevant information will be transmitted to the task allocation module and the path planning module for subsequent task generation and path optimization. At the same time, it continues to perform data processing tasks when the network is unstable to ensure the continuity of inspections.

[0065] Task assignment module: Based on the relevant information processed by the edge computing module, it generates inspection tasks according to the preset inspection rules, dynamically optimizes the priority and execution order of tasks, sends the optimized task instructions to the path planning module for path generation, and conveys them to users through the user interaction module for reference and adjustment;

[0066] Path planning module: Based on the task instructions provided by the task assignment module and the environmental data processed by the edge computing module, the algorithm is used to generate the optimal path for the inspection equipment, and the planning results are sent to the inspection equipment for executing the inspection task;

[0067] Early warning module: Receives data processed by the edge computing module and combines historical data to predict and analyze equipment status. When potential risks are detected, the early warning module generates an early warning signal and feeds the early warning information back to the task allocation module to adjust the task plan.

[0068] User interaction module: used to display the system's operating status, task progress and equipment status through an intuitive interface, allowing users to view inspection data and adjust inspection strategies. The user's adjusted instructions are transmitted to the task allocation module through the user interaction module, and the task allocation module updates the task execution strategy based on the adjustments.

[0069] The data acquisition module includes a sensor unit, a mobile node unit and a data transmission unit; wherein:

[0070] Sensor unit: Multiple sensors are fixedly deployed in the inspection area to continuously monitor environmental parameters and equipment status. The multiple sensors include temperature sensors, humidity sensors, vibration sensors and image sensors. The temperature sensor is used to measure the temperature change data of the environment and equipment, the humidity sensor is used to monitor the air humidity data, the vibration sensor is used to detect the mechanical vibration data of the equipment, and the image sensor is used to obtain the image information of the equipment and the environment. Each sensor collects and processes the monitoring data in real time through the internal integrated digital interface to ensure the accuracy and stability of the data;

[0071] Mobile node unit: multiple mobile nodes are arranged in the inspection area to autonomously adjust their positions according to the requirements of the inspection task to cover various monitoring points in the inspection area. The mobile node unit is equipped with an autonomous mobile device to dynamically monitor the predetermined key areas. The mobile node unit also includes a multi-sensor array for data collection to supplement the areas that cannot be covered by the fixed sensor unit;

[0072] Data transmission unit: The multi-dimensional data collected by the sensor unit and the mobile node unit are transmitted to the edge computing module through the Internet of Things protocol. The data transmission unit integrates a high-speed wireless communication sub-module, supports real-time data transmission, and has a built-in data caching function to prevent data loss when the network is unstable. The data transmission unit uses encryption technology to ensure the security and integrity of data transmission; through the design of the above structure, the data acquisition module can efficiently and accurately collect multi-dimensional data of the environment and equipment in the inspection area, ensuring the comprehensiveness and real-time nature of the data. The fixed deployment of the sensor unit and the dynamic adjustment of the mobile node unit are combined to achieve full coverage monitoring of the inspection area, and the data transmission unit ensures the safe transmission and timely processing of the data, thereby improving the overall performance and reliability of the system.

[0073] The edge computing module includes a data receiving unit and a data processing unit; wherein:

[0074] Data receiving unit: Receives multi-dimensional data from the data acquisition module through a high-speed wireless communication interface, and performs synchronous processing on real-time data to ensure that there is no delay or data loss during the transmission of multi-dimensional data. The received multi-dimensional data includes environmental parameters, equipment status information, and image data. After synchronous processing, it is normalized and stored in a local cache in a standardized format for subsequent processing;

[0075] Data processing unit: used for preliminary analysis and processing of the data transmitted by the data receiving unit, the data processing unit includes a noise filtering subunit and an abnormality detection subunit;

[0076] Noise filtering subunit: adopts a multi-level filtering algorithm to dynamically adjust the filtering strength according to the preset filtering parameters while receiving data to remove interference signals in the environment and equipment status data to ensure the purity and accuracy of the data;

[0077] Anomaly detection subunit: It is used to detect anomalies in data in real time. By analyzing mutations, over-limits and unexpected changes, it determines the validity of the data and filters out abnormal data to improve the accuracy of system judgment. Through the above design, the edge computing module can efficiently and accurately process the received multi-dimensional data in real time. The combination of the noise filtering subunit and the anomaly detection subunit ensures the reliability and purity of the data, provides a solid data foundation for subsequent task allocation and path planning, and improves the stability and response speed of the system as a whole.

[0078] The noise filtering subunit includes primary filtering, secondary filtering and tertiary filtering. The primary filtering outputs D1(t), the secondary filtering outputs D2(t), and a dynamic intensity adjustment mechanism is provided between the secondary filtering and the tertiary filtering. The dynamic intensity adjustment mechanism is used to dynamically adjust the intensity of the filter according to the changes in the real-time collected data and the preset filter parameters P(t). The adjusted filter intensity is expressed as: Among them, S(t) is the initial filter strength, α and β are the filter strength adjustment coefficients, S A (t) is the adjusted filter strength, It represents the rate of change of the data D2(t) after secondary filtering at time t; after the dynamic intensity adjustment mechanism is adjusted, the third-level filtering processing output D3(t) is performed, which is the final filtered output data.

[0079] The processing steps of noise filtering are as follows:

[0080] Data initialization: receiving the original data transmitted from the data receiving unit and preprocessing the data. The preprocessed data is represented as D(t), where D(t) represents the multidimensional data set received at time t;

[0081] Preset filter parameter loading: According to the operating environment and device status, load the applicable filter parameter P(t) from the preset filter parameter set, expressed as: P(t) = {P1(t), P2(t), ..., P n (t)}, where P i (t) represents the i-th filter parameter used at time t;

[0082] Primary filtering: Use low-pass filtering algorithm to filter the raw data preliminarily to remove high-frequency noise. The processed data is expressed as D1(t), and the formula is: D1(t) = D(t)-H(D(t), P L (t)), where (D(t), P L (t)) represents the low-pass filter parameter P L (t) is the filtering operation performed on the original data D(t), P L (t) is the low-pass filter parameter used at time t;

[0083] Secondary filtering: The data D1(t) after low-pass filtering is subjected to band-pass filtering to remove noise in a predetermined frequency band. The processed data is represented as D2(t), and the formula is: D2(t) = D1(t) - B(D1(t), P B (t)), where B(D1(t), P B (t)) represents the bandpass filter parameter P B (t) Bandpass filtering operation, P B (t) is the bandpass filter parameter used at time t;

[0084] Dynamic intensity adjustment: Dynamically adjust the intensity of the filter according to the changes in real-time collected data and the preset filter parameters P(t);

[0085] Three-stage filtering: Apply dynamically adjusted filter strength S A (t) The data is subjected to three-level filtering to remove subtle noise, and finally the purified data D3(t) is obtained, which is expressed as: D3(t) = D2(t) - S A (t)×G(D2(t)), where G(D2(t)) represents the filtering operation adjusted according to the dynamic strength, and D3(t) is the final filtering output data;

[0086] Output purified data: The final filtered data D3(t) is used as the output data for processing by the anomaly detection unit. Through the above steps, the noise filtering subunit can dynamically adjust the filtering strength according to the real-time situation while receiving the data, and remove the interference signals in the environment and equipment status data in stages and multiple levels, ensuring the high purity and accuracy of the output data, and providing a reliable data basis for subsequent anomaly detection and system judgment.

[0087] The anomaly detection subunit specifically includes:

[0088] Mutation analysis: Perform mutation analysis on the final filtered output data D3(t) to detect the rapid change pattern in the data, calculate the change rate V(t) of each data point compared with the previous time point, and compare it with the preset mutation threshold T V For comparison, it is expressed as: Where Δt is the time interval. When V(t)>T V When , it is marked as a mutation data point;

[0089] Out-of-limit analysis: Check whether the data exceeds the normal range by comparing the purified data D3(t) with the preset upper limit U L and the lower limit L L Threshold, to determine whether the data exceeds the limit, specifically when D3(t)>U L or D3(t) <L L When , it is marked as an out-of-limit data point;

[0090] Expected deviation analysis: The validity of the data is determined by analyzing the deviation ΔD(t) between the purified data and the expected model output, and the purified data D3(t) and the expected value D are calculated. exp The deviation between (t) is: ΔD(t) = D3(t)-D exp (t), if the deviation ΔD(t) exceeds the set deviation threshold T Δ , it is marked as a data point that does not meet expectations;

[0091] Anomaly score calculation and determination: The results of mutation analysis, over-limit analysis, and expected deviation analysis are combined to calculate the final anomaly score E. f (t), the formula is: E f (t) = w1×V(t)+w2×overlimit judgment+w3×ΔD(t), where w1, w2 and w3 are weight coefficients of each analysis method. f (t) exceeds the preset abnormal threshold T E When , it is determined as abnormal data and filtered;

[0092] Filter abnormal data: For data points that are determined to be abnormal, remove them from the data set and output the filtered data D f (t) for subsequent processing by the system; through the above steps, the anomaly detection subunit can effectively identify sudden changes, over-limit and unexpected changes in the data, comprehensively calculate the anomaly score, and accurately filter the abnormal data. This multi-dimensional anomaly detection method ensures the validity and reliability of the system input data and provides a high-quality data foundation for further decision-making and control.

[0093] The task allocation module includes a task generation unit, a priority evaluation unit, a sequence optimization unit and a task output unit; wherein:

[0094] Task generation unit: used to receive data processed by the edge computing module D f (t) and generates specific inspection tasks according to the preset inspection rules R. The inspection rules R include equipment inspection frequency, environmental monitoring standards and safety requirements. By analyzing the rules R and combining them with data D f (t), the task generation unit outputs the inspection task list T, which is expressed as: T = {T1, T2, ..., T n}, where T i is the i-th inspection task generated according to rule R;

[0095] The rule parsing process includes the following steps:

[0096] Rule loading and initialization: First, load the preset secondary inspection rule R from the system configuration file or database. Rule R contains a series of parameters and conditions, which are used to describe the frequency of equipment inspection, environmental monitoring standards, safety requirements, etc.

[0097] Data matching and condition judgment: For each rule R i , the task generation unit receives the purified data D from the edge computing module f (t) extracts relevant data for matching. Specifically, the task generation unit compares the conditions in each rule with the real-time data to determine whether the current data meets the specific inspection conditions. The formula is: if D f (t)[k]≥R i [k] then satisfies the rule, where D f (t)[k] represents the purified data consistent with rule R i The relevant k-th data dimension;

[0098] Rule priority analysis: Rule R contains multiple conditions, and different conditions have priority relationships. The task generation unit analyzes the weight of each condition according to the rule priority and gives priority to satisfying the rules with higher priority. For example, if the priority of rule R1 is higher than that of rule R2, the condition satisfying R1 will be given priority when generating tasks.

[0099] Task generation: Based on the rule analysis results, the task generation unit creates an inspection task. If data D f (t) satisfies a rule R i , then the corresponding inspection task T is generated i .

[0100] Priority evaluation unit: performs priority evaluation on each task in the inspection task list T output by the task generation unit. The priority evaluation is based on multiple factors, including the importance of the task I(T i ), urgency level U(T i ) and the device status S(T i ), each task T i The priority P(T i ) is calculated as: P(T i )=w1×I(T i )+w2×U(T i )+w3×S(T i ), where w1, w2, w3 are evaluation weight coefficients, P(T i ) is the priority score of the i-th task;

[0101] Sequential optimization unit: According to the task priority P(T i ), sort the task list T, and the order optimization unit specifically uses the sorting function Sort(T, P(T i )) is used to calculate the task priority P(T i ) to sort the tasks, which can be expressed as: Among them, O(T) is the task execution order list arranged in descending order of priority, and the task with higher priority is executed first;

[0102] Task output unit: transmits the optimized task execution order O(T) to the path planning module and the user interaction module to ensure that the system executes the inspection tasks in the optimal order, and displays the task information to the user for monitoring and adjustment; through the above design, the task allocation module can automatically generate inspection tasks that meet the requirements based on the data processed by the edge computing module and the preset inspection rules, and dynamically optimize the task priority and execution order according to the importance, urgency and equipment status of the task. The multi-level optimization mechanism of this module ensures the efficient allocation and execution of inspection tasks and improves the response speed and overall performance of the system.

[0103] The path planning module includes a path calculation unit, an obstacle detection unit and a path optimization unit; wherein:

[0104] Path calculation unit: first parse the inspection target points and sequence in the task instructions, and combine them with the environmental data D f (t) and the location of the equipment, and preliminarily calculate the path set P of the inspection equipment init , expressed as: P init = {P1, P2, ..., P m}, where P iIt represents the i-th path that the inspection equipment needs to visit. The preliminary path is generated based on the geographical distribution of the equipment location and the task target point. The specific formula is:

[0105] P init = {P i |P i =Path(S, T i , D f (t)), i = 1, 2, ..., m}, where P i represents the i-th path that the inspection device needs to visit, S is the starting position of the device, T i is the target position in the task instruction, D f (t) is the environmental data at the current time t, and the function Path(S, T i , D f (t)) represents the distance from the starting position S to the target position T i The path calculation result of

[0106] Obstacle detection unit: the preliminary path set P generated by the path calculation unit init Obstacle detection is performed to ensure the safety and accessibility of the inspection path. The obstacle detection unit combines the environmental data provided by the edge computing module to identify the location of obstacles on the inspection device path and excludes them from the preliminary path to form an adjusted path set P. adj ;

[0107] Path optimization unit: adjust the path set P adj Optimize and use the path optimization strategy based on heuristic algorithms (such as A* algorithm, Dijkstra algorithm) to calculate the optimal path P of the inspection equipment opt , the optimal path calculation takes into account multiple factors, including the path length L(P j )、Energy consumption E(P j ) and time T(P j ), the formula for the optimal path is: P opt =min P (w1×L(P)+w2×E(P)+w3×T(P)), where w1, w2 and w3 are weight coefficients for path optimization, min P It means that the path that minimizes the objective function value among all paths P is the optimal path, P opt For the optimal path, meet the task requirements and reduce the path cost as much as possible;

[0108] Path output unit: The optimized optimal path P optTransmitted to the inspection equipment to ensure that the equipment performs the inspection task according to the optimal path; through the above design, the path planning module can generate the optimal path most suitable for the inspection equipment according to the task instructions provided by the task assignment module and the environmental data processed by the edge computing module. This module ensures that the inspection equipment can complete the inspection task efficiently and safely in a complex environment through multi-level path calculation, obstacle detection and path optimization, while optimizing the path cost and improving the overall operation efficiency of the system.

[0109] The early warning module includes a historical data comparison unit, a state prediction unit, an early warning signal generation unit and an early warning information feedback unit; wherein:

[0110] Historical data comparison unit: receives the current data D processed by the edge computing module f (t) and the historical operation data of the equipment D h (t), and compare the two to identify abnormal trends. The comparison is completed by calculating the deviation ΔD(t) between the current data and the historical data. The formula is: ΔD(t) = D f (t)-D h (t), when ΔD(t) exceeds the set deviation threshold T D When it is detected, it is recorded as an abnormal trend for subsequent status prediction;

[0111] State prediction unit: predicts the future operation state of the equipment based on the regression algorithm. p (t+Δt) is the predicted state result of the equipment. When S p (t+Δt) exceeds the preset safety threshold S safe When , it is marked as a potential risk state;

[0112] The specific steps of prediction are as follows:

[0113] Step 1: Get current data D from the historical data comparison unit f (t), historical deviation data ΔD(t) and historical operation data D h (t), these data are standardized to ensure that the data input is in the same dimension. The standardization formula is: Among them, μ D and σ D are the mean and standard deviation of the data set D(t), D norm (t) is the standardized data;

[0114] Step 2: Standardize the data D norm (t) is input to the feature extraction submodule to extract the key feature vector X(t) as the input of the regression model. The features include historical trends, current status and deviation information;

[0115] Step 3: Use linear regression algorithm to establish the equipment status prediction model. The model training process is based on the historical data set D h (t) and the corresponding actual device state S(t), the trained model is used to predict the device state S at the future time t+Δt p (t+Δt), the regression prediction formula is: Among them, β0 is the intercept term of the model, β i is the regression coefficient of the model, X i (t) is the i-th feature in the input feature vector;

[0116] Step 4: Calculate the predicted device state S p (t+Δt) is used as the output for subsequent warning signal generation. If S p (t+Δt) exceeds the safety threshold S safe When it is detected, it is marked as a potential risk state.

[0117] Warning signal generation unit: used to generate a warning signal immediately when the state prediction unit detects that there is a potential risk in the future state of the equipment. The warning signal includes the risk level, risk type and recommended operation, and is sent to the user interaction module and the task allocation module through the communication interface so that corresponding measures can be taken in time;

[0118] Early warning information feedback unit: After generating the early warning signal, the early warning information feedback unit will feed back the information in the early warning signal to the task assignment module. The task assignment module will adjust the task plan according to the risk level and type in the early warning signal, including giving priority to high-risk equipment or rearranging the inspection route to ensure the safe operation of the system. Through the above design, the early warning module can effectively combine current data and historical data to predict the equipment status, and when potential risks are detected, it will generate early warning signals in time and feed back to the task assignment module to adjust the task plan, thereby improving the safety and response speed of the system and ensuring the reliable execution of inspection tasks.

[0119] The early warning information feedback unit specifically includes:

[0120] Risk analysis: Receive the warning signal transmitted by the warning signal generation unit and analyze the risk level R in the signal l and risk type R t , risk level R l It is a quantitative indicator in the early warning signal, used to indicate the severity of the risk, and the range is set to R l ∈[1, 5], where 1 represents low risk and 5 represents high risk, and the risk type R t It is a classification of specific risk types, including equipment failure and environmental abnormalities;

[0121] Task priority adjustment: According to the risk level R l Adjust the priority of the task. The adjustment process is to recalculate the priority score P(T i ) is completed, the adjusted priority score formula is: P′(T i )=P(T i )+α×R l , where P′(T i ) is the adjusted task priority, P(T i ) is the original task priority, α is the risk adjustment coefficient, which is used to quantify the impact of risk level on task priority. The higher the risk level, the greater the priority adjustment, ensuring that high-risk tasks are given priority.

[0122] Task reallocation: After the task priority adjustment unit recalculates the priority, the task reallocation unit reorders the tasks according to the new priority score and reallocates resources; through the above design, the early warning information feedback unit can effectively analyze the risk level and type in the early warning signal, and convert the risk information into the basis for adjusting the task priority. After receiving the adjusted priority information, the task allocation module dynamically adjusts the inspection plan through precise task reordering and resource allocation to ensure that the system can respond in time when dealing with high-risk events, optimize resource allocation, and improve the response speed of the inspection system and the efficiency of task execution.

[0123] The user interaction module includes a status display unit, a task progress monitoring unit, a device status display unit and a strategy adjustment unit; wherein:

[0124] Status display unit: used to receive real-time operation data from each module and present it in a visual way, including dashboards, charts and real-time updated status indicators. Users can view key parameters such as the current system's operating load, network connection status, data processing status, etc. through the interface, so as to fully understand the system's operating status;

[0125] Task progress monitoring unit: displays the progress of the current inspection task in real time, including the execution status of the task, the list of completed tasks, ongoing tasks, and tasks to be started. The task progress monitoring unit also displays the execution order of the tasks in the form of a timeline or Gantt chart, and distinguishes different task states (such as not started, in progress, completed, pending adjustment, etc.) with color coding to help users intuitively understand the progress of task execution;

[0126] Equipment status display unit: used to display the current status information of the inspection equipment, including the geographical location, operating status, battery power, sensor readings and health status of the equipment. The equipment status display unit also presents the location information and status of each device to the user in the form of maps and status icons. Users can click on specific equipment icons to view detailed information, such as sensor data, equipment historical operation records, etc.;

[0127] Policy adjustment unit: allows users to adjust the inspection strategy according to the real-time information of system operation status, task progress and equipment status. The policy adjustment unit provides an intuitive operation interface. Users can adjust the priority of tasks, modify the execution order of tasks or add new inspection tasks by dragging and dropping, clicking or entering commands. The policy adjustment unit will transmit the user's adjustment instructions to the task allocation module. The task allocation module will update the inspection plan in real time according to the user's instructions, and feed back the updated information to the user interaction module for display.

[0128] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0129] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. Inspection service management system based on artificial intelligence and Internet of Things, characterized by: It includes data acquisition module, edge computing module, task allocation module, path planning module, warning module and user interaction module; among which: Data acquisition module: Various sensors and mobile nodes deployed in the inspection area are used to collect multi-dimensional data of the environment and equipment in real time, and transmit the data to the edge computing module through the Internet of Things protocol; Edge computing module: receives multi-dimensional data from the data acquisition module, and performs preliminary analysis and processing on the multi-dimensional data, including noise filtering and anomaly detection. The processed relevant information will be transmitted to the task allocation module and path planning module; Task allocation module: Based on the relevant information processed by the edge computing module, it generates inspection tasks according to the preset inspection rules, dynamically optimizes the priority and execution order of tasks, and sends the optimized task instructions to the path planning module for path generation; Path planning module: Based on the task instructions provided by the task assignment module and the environmental data processed by the edge computing module, the algorithm is used to generate the optimal path for the inspection equipment, and the planning results are sent to the inspection equipment for executing the inspection task; Early warning module: Receives data processed by the edge computing module and combines historical data to predict and analyze equipment status. When potential risks are detected, the early warning module generates an early warning signal and feeds the early warning information back to the task allocation module to adjust the task plan. User interaction module: used to display the system's operating status, task progress and equipment status through an intuitive interface, allowing users to view inspection data and adjust inspection strategies. The user's adjusted instructions are transmitted to the task allocation module through the user interaction module, and the task allocation module updates the task execution strategy based on the adjustments.

2. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 1 is characterized in that: The data acquisition module includes a sensor unit, a mobile node unit and a data transmission unit; wherein: Sensor unit: multiple sensors fixedly deployed in the inspection area, used to continuously monitor environmental parameters and equipment status. The multiple sensors include temperature sensors, humidity sensors, vibration sensors and image sensors. The temperature sensor is used to measure the temperature change data of the environment and equipment, the humidity sensor is used to monitor the air humidity data, the vibration sensor is used to detect the mechanical vibration data of the equipment, and the image sensor is used to obtain image information of the equipment and the environment; Mobile node unit: Multiple mobile nodes are deployed in the inspection area to autonomously adjust their positions according to the requirements of the inspection task to cover various monitoring points in the inspection area. The mobile node unit is equipped with an autonomous mobile device to dynamically monitor the predetermined key areas; Data transmission unit: transmits the multi-dimensional data collected by the sensor unit and the mobile node unit to the edge computing module through the Internet of Things protocol.

3. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 1 is characterized in that: The edge computing module includes a data receiving unit and a data processing unit; wherein: Data receiving unit: receives multi-dimensional data from the data acquisition module through a high-speed wireless communication interface, performs synchronous processing on the real-time data, performs normalization processing after synchronous processing, and stores it in a local cache in a standardized format; Data processing unit: used for preliminary analysis and processing of the data transmitted by the data receiving unit, the data processing unit includes a noise filtering subunit and an abnormality detection subunit; Noise filtering subunit: adopts a multi-level filtering algorithm to dynamically adjust the filtering strength according to the preset filtering parameters while receiving data to remove interference signals in the environment and equipment status data; Anomaly detection subunit: It is used to detect anomalies in data in real time, judge the validity of data and filter out abnormal data by analyzing mutations, over-limits and unexpected changes.

4. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 3 is characterized in that: The noise filtering subunit includes a primary filtering process, a secondary filtering process and a tertiary filtering process; the primary filtering process outputs D1(t), the secondary filtering process outputs D2(t), and a dynamic intensity adjustment mechanism is provided between the secondary filtering process and the tertiary filtering process. The dynamic intensity adjustment mechanism is used to dynamically adjust the intensity of the filter according to the change of the real-time collected data and the preset filtering parameter P(t). The adjusted filter intensity is expressed as: Among them, S(t) is the initial filter strength, α and β are the filter strength adjustment coefficients, S A (t) is the adjusted filter strength, It represents the rate of change of the data D2(t) after secondary filtering at time t; after the dynamic intensity adjustment mechanism is adjusted, the third-level filtering processing output D3(t) is performed, which is the final filtered output data.

5. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 4 is characterized in that: The abnormality detection subunit specifically includes: Mutation analysis: Perform mutation analysis on the final filtered output data D3(t) to detect rapid change patterns in the data and calculate the rate of change V(t) of each data point compared to the previous time point; Out-of-limit analysis: Check whether the data exceeds the normal range by comparing the purified data D3(t) with the preset upper limit U L and the lower limit L L Threshold, to determine whether the data exceeds the limit, specifically when D3(t)>U L or D3(t) <L L When , it is marked as an out-of-limit data point; Expected deviation analysis: The validity of the data is determined by analyzing the deviation ΔD(t) between the purified data and the expected model output, and the purified data D3(t) and the expected value D are calculated. exp The deviation between (t) is: ΔD(t) = D3(t)-D exp (t), if the deviation ΔD(t) exceeds the set deviation threshold T Δ , it is marked as a data point that does not meet expectations; Anomaly score calculation and determination: The results of mutation analysis, over-limit analysis, and expected deviation analysis are combined to calculate the final anomaly score E. f (t), the formula is: E f (t) = w1×V(t)+w2×overlimit judgment+w3×ΔD(t), where w1, w2 and w3 are weight coefficients of each analysis method. f (t) exceeds the preset abnormal threshold T E When , it is determined as abnormal data and filtered; Filter abnormal data: For data points that are determined to be abnormal, remove them from the data set and output the filtered data D f (t).

6. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 5 is characterized in that: The task allocation module includes a task generation unit, a priority evaluation unit, a sequence optimization unit and a task output unit; wherein: Task generation unit: used to receive data processed by the edge computing module D f (t), and generate specific inspection tasks according to the preset inspection rules R, which include equipment inspection frequency, environmental monitoring standards and safety requirements. By analyzing the rules R and combining the data D f (t), the task generation unit outputs the inspection task list T; Priority evaluation unit: performs priority evaluation on each task in the inspection task list T output by the task generation unit. The priority evaluation is based on multiple factors, including the importance of the task I(T i ), urgency level U(T i ) and the device status S(T i ), each task T i The priority P(T i ) is calculated as: P(T i )=w1×I(T i )+w2×U(T i )+w3×S(T i ), where w1, w2, w3 are evaluation weight coefficients, P(T i ) is the priority score of the i-th task; Sequential optimization unit: According to the task priority P(T i ), sort the task list T, and the order optimization unit specifically uses the sorting function Sort(T, P(T i )) is used to calculate the task priority P(T i ) to sort the tasks, which can be expressed as: Among them, O(T) is the task execution order list arranged in descending order of priority, and the task with higher priority is executed first; Task output unit: transmits the optimized task execution order O(T) to the path planning module and the user interaction module.

7. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 1 is characterized in that: The path planning module includes a path calculation unit, an obstacle detection unit and a path optimization unit; wherein: Path calculation unit: first parse the inspection target points and sequence in the task instructions, and combine them with the environmental data D f (t) and the location of the equipment, and preliminarily calculate the path set P of the inspection equipment init ; Obstacle detection unit: the preliminary path set P generated by the path calculation unit init Obstacle detection is performed, and the environmental data provided by the edge computing module is combined to identify the location of obstacles on the inspection equipment path and exclude them from the preliminary path to form an adjusted path set P adj ; Path optimization unit: adjust the path set P adj Optimize and use the path optimization strategy based on heuristic algorithm to calculate the optimal path P of the inspection equipment opt , the optimal path calculation takes into account multiple factors, including the path length L(P j )、Energy consumption E(P j ) and time T(P j ), the formula of the optimal path is: opt =min P (w1×L(P)+w2×E(P)+w3×T(P)), where w1, w2 and w3 are weight coefficients for path optimization, min P It means that the path that minimizes the objective function value among all paths P is the optimal path, P opt is the optimal path; Path output unit: The optimized optimal path P opt Transmitted to the inspection equipment to ensure that the equipment performs inspection tasks along the optimal path.

8. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 1 is characterized in that: The warning module includes a historical data comparison unit, a state prediction unit, a warning signal generation unit and a warning information feedback unit; wherein: Historical data comparison unit: receives the current data D processed by the edge computing module f (t) and the historical operation data of the equipment D h (t), and compare the two to identify abnormal trends. The comparison is completed by calculating the deviation ΔD(t) between the current data and the historical data. The formula is: ΔD(t) = D f (t)-D h (t), when ΔD(t) exceeds the set deviation threshold T D When , it is recorded as an abnormal trend; State prediction unit: predicts the future operation state of the equipment based on the regression algorithm. p (t+Δt) is the predicted state result of the equipment. When S p (t+Δt) exceeds the preset safety threshold S safe When , it is marked as a potential risk state; Warning signal generation unit: used to immediately generate a warning signal when the state prediction unit detects that there is a potential risk in the future state of the equipment. The warning signal includes the risk level, risk type and recommended operation; Early warning information feedback unit: After the early warning signal is generated, the early warning information feedback unit will feed back the information in the early warning signal to the task allocation module. The task allocation module will adjust the task plan according to the risk level and type in the early warning signal, including giving priority to high-risk equipment or rearranging the inspection route.

9. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 8 is characterized in that: The early warning information feedback unit specifically includes: Risk analysis: Receive the warning signal transmitted by the warning signal generation unit and analyze the risk level R in the signal l and risk type R t ; Task priority adjustment: According to the risk level R l Adjust the priority of the task. The adjustment process is to recalculate the priority score P(T i ) is completed, the adjusted priority score formula is: P′(T i )=P(T i )+α×R l , where P′(T i ) is the adjusted task priority, P(T i ) is the original task priority, α is the risk adjustment coefficient; Task reallocation: After the task priority adjustment unit recalculates the priorities, the task reallocation unit reorders the tasks according to the new priority scores and reallocates resources.

10. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 1 is characterized in that: The user interaction module includes a status display unit, a task progress monitoring unit, a device status display unit and a strategy adjustment unit; wherein: Status display unit: used to receive the operation data from each module in real time and present it in a visual way, including dashboards, charts and real-time updated status indicators; Task progress monitoring unit: displays the progress of the current inspection task in real time, including the execution status of the task, the list of completed tasks, ongoing tasks, and tasks to be started. The task progress monitoring unit also displays the execution order of the tasks in the form of a timeline or Gantt chart, and distinguishes different task states with color coding; Equipment status display unit: used to display the current status information of the inspection equipment, including the equipment's geographic location, operating status, battery power, sensor readings, and health status; Policy adjustment unit: allows users to adjust inspection policies based on real-time information on system operation status, task progress, and device status. The policy adjustment unit provides an intuitive operation interface, where users can adjust task priorities, modify the execution order of tasks, or add new inspection tasks by dragging and dropping, clicking, or entering commands.

Images