Remote fault detection method for intelligent terminal ticket machine

Abstract

The present invention discloses a remote fault detection method for a smart terminal ticket machine, and relates to the field of data processing technology. The method includes: configuring an edge computing node for the smart terminal device, the node includes a sensor monitoring module and a fault analysis module; collecting short-term user operation records and external environment interference data through the sensor monitoring module, and performing abnormality identification and fault prediction in combination with user ticket purchase feedback information through the fault analysis module, generating real-time prediction results and uploading them to the cloud; the cloud computing center calibrates the prediction results in combination with historical fault records, and finally obtains remote fault detection results. The present invention solves the technical problems in the prior art that traditional fault detection relies on manual inspections and post-maintenance, has poor real-time performance, low accuracy, and high maintenance costs, and achieves the technical effect of achieving real-time response and early warning through the coordinated cooperation of edge computing and cloud computing, improving fault detection accuracy, and reducing maintenance costs.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a remote fault detection method for an intelligent terminal ticket vending machine. Background Art

[0002] In modern society, smart terminal ticket machines are widely used in public places such as stations, cinemas, and transportation hubs to provide convenient self-service ticket purchase services. However, with the increase in frequency of use, smart terminal devices are prone to failure during long-term operation, which not only affects the user experience but may also cause business stagnation. Therefore, how to perform real-time fault detection and prediction on smart terminal ticket machines to ensure the stable operation of the equipment has become an urgent problem to be solved.

[0003] Traditional ticket machine maintenance methods rely on regular manual inspections or passive repairs after equipment failures. This method is not only lagging, but may also increase the cost of equipment maintenance and cannot provide early warning of potential equipment failures. Summary of the invention

[0004] The present application provides a remote fault detection method for an intelligent terminal ticket machine, which is used to solve the technical problems in the prior art that traditional fault detection relies on manual inspection and post-maintenance, has poor real-time performance, low accuracy and high maintenance cost.

[0005] The present application provides a remote fault detection method for a smart terminal ticket machine, the method comprising: configuring an edge computing node for the smart terminal device, the edge computing node comprising a sensor monitoring module and a fault analysis module, and the edge computing node is configured with a remote fault detection cycle; according to the sensor monitoring module, in accordance with the remote fault detection cycle, short-term user operation records and external environmental interference data are collected; through the fault analysis module, the short-term user operation records are received to identify operation anomalies, and in combination with user ticket purchase feedback information and the external environmental interference data, equipment fault prediction is performed to obtain real-time equipment fault prediction results and upload them to a cloud computing center; the cloud computing center calibrates the real-time equipment fault prediction results in combination with the historical fault records of the smart terminal device to obtain remote fault detection results.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The remote fault detection method for a smart terminal ticket machine provided in the present application relates to the field of data processing technology. By configuring edge computing nodes for smart terminal devices, and collecting operation records and external environment data periodically through a sensor monitoring module, a fault analysis module performs abnormality identification and fault prediction, generates real-time prediction results and uploads them to the cloud, and the cloud is calibrated in combination with historical fault records to obtain remote fault detection results. This solves the technical problems in the prior art that traditional fault detection relies on manual inspections and post-maintenance, has poor real-time performance, low accuracy and high maintenance costs, and achieves the technical effect of achieving real-time response and early warning through the coordinated cooperation of edge computing and cloud computing, improving fault detection accuracy and reducing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A flow chart of a remote fault detection method for an intelligent terminal ticket machine provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of the process of performing equipment fault prediction in the remote fault detection method for the intelligent terminal ticket machine provided in the embodiment of the present application. DETAILED DESCRIPTION

[0011] The present application provides a remote fault detection method for an intelligent terminal ticket machine, which is used to solve the technical problems in the prior art that traditional fault detection relies on manual inspection and post-maintenance, has poor real-time performance, low accuracy and high maintenance cost.

[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0013] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0014] Examples, such as Figure 1 As shown, the present application provides a remote fault detection method for an intelligent terminal ticket machine, the method comprising:

[0015] P10: Configure an edge computing node for the smart terminal device, wherein the edge computing node includes a sensor monitoring module and a fault analysis module, and the edge computing node is configured with a remote fault detection cycle.

[0016] Furthermore, step P10 of the embodiment of the present application further includes:

[0017] P11: The sensor monitoring module includes a hardware monitoring sub-module and an environmental monitoring sub-module; P12: Based on the smart terminal device, the hardware modules are divided to obtain multiple hardware functional modules; P13: According to the user operation instruction set, the multiple hardware functional modules are associated and mapped to generate corresponding multiple operation data collection loops; P14: According to the multiple operation data collection loops, the hardware monitoring sub-module is configured; P15: According to the environmental monitoring indicators, the environmental monitoring sub-module is configured.

[0018] It should be understood that an efficient edge computing node is configured for the smart terminal device. The edge computing node not only integrates the sensor monitoring module and the fault analysis module, but also the sensor monitoring module is responsible for monitoring the operating status of the device. The fault analysis module includes anomaly detection and fault prediction functions, which is responsible for identifying faults and performing remote fault detection tasks within the configured cycle. At the same time, the edge computing node also specially sets a remote fault detection cycle to ensure continuous monitoring and timely response to the device status, which means that the system will automatically perform monitoring and detection tasks within a preset time interval.

[0019] Among them, the sensor monitoring module is further refined into a hardware monitoring submodule and an environmental monitoring submodule. This subdivision design aims to capture the operating status of smart terminal devices and changes in their external environment in all directions. Among them, the hardware monitoring submodule focuses on the health status of the hardware components inside the device, and is mainly responsible for collecting the operating data of each hardware inside the smart terminal device, including real-time status information of key components such as printers, barcode scanners, and touch screens. The environmental monitoring submodule is responsible for monitoring the physical environment in which the device is located, such as temperature, humidity, electromagnetic fields, and other external factors that may affect the performance of the device.

[0020] Based on the specific structure of the smart terminal device, it is divided into hardware modules. The purpose of this step is to classify the functional units in the device and generate multiple hardware functional modules. Each module has a specific function. For example, the printing module is responsible for printing tickets, the payment module is responsible for processing user payment requests, and the code scanning module is used to read QR codes.

[0021] In order for the sensor monitoring module to accurately collect operation data, it is necessary to associate and map the user operation instruction set with the aforementioned hardware function module. Through the mapping relationship, a corresponding operation data collection loop is generated for each hardware module to ensure that each module can independently collect operation data through its own loop, which is convenient for subsequent monitoring and analysis. The corresponding hardware function module can be found for each user instruction. For example, when the user selects the payment operation on the screen, this instruction will be mapped to the payment module, thereby generating the operation data of the module.

[0022] According to the generated operation data collection loop, the hardware monitoring submodule is configured to enable real-time monitoring of the operating status of each hardware functional module. For example, by monitoring the status of the printing module, it is possible to detect abnormal situations such as paper jams and printing failures in the printer. The configuration of the hardware monitoring submodule ensures the accuracy and comprehensiveness of fault detection.

[0023] According to the environmental monitoring indicators in the equipment operating environment, the environmental monitoring submodule is configured to ensure that external factors, such as high temperature, humidity, or network instability, can be captured in real time and combined with the equipment's hardware monitoring data to provide more accurate fault prediction. For example, when the temperature is too high, it may cause the hardware to overheat, thereby increasing the probability of equipment failure. The configuration of the environmental monitoring submodule helps the system better cope with potential risks brought about by changes in the external environment.

[0024] P20: According to the sensor monitoring module, collect short-term user operation records and external environment interference data according to the remote fault detection cycle.

[0025] Optionally, during the operation of the intelligent terminal device, the sensor monitoring module starts the data collection task according to a preset remote fault detection cycle. The cycle can be dynamically adjusted according to the frequency of use of the device or the complexity of the environment to ensure that the detection frequency can adapt to the actual use situation.

[0026] Specifically, the hardware monitoring submodule within the sensor monitoring module is divided according to the established hardware module categories, focusing precisely on each hardware functional module. These modules are the core components of intelligent terminal devices, and their operating status is directly related to the overall performance and stability of the device. Through the hardware monitoring submodule, short-term user operation records of these hardware modules are collected regularly (i.e., according to the remote fault detection cycle). These records not only include the execution of user instructions, but also cover the real-time parameter changes of the hardware modules during the execution process, such as response time, load rate, etc. User operation data is classified and stored according to the hardware module category. For example, the user's payment behavior will be classified as payment module data, and the printing behavior will belong to the printing module. This classified storage method can effectively avoid data confusion and help to more accurately locate the module where the problem is located.

[0027] At the same time, the environmental monitoring submodule is also working continuously. It is responsible for monitoring the external environmental conditions of the smart terminal device. These environmental conditions, such as temperature, humidity, electromagnetic field strength, etc., may interfere with the normal operation of the device. Through the environmental monitoring submodule, the system can collect and record these external environmental interference data in real time. These data complement the hardware monitoring data and together form a comprehensive portrait of the operating status of the smart terminal device.

[0028] In order to ensure the accuracy and timeliness of data collection, a variety of technical means can be used to support it. For example, high-precision sensors are used to monitor hardware parameters and environmental conditions in real time; data compression and encryption technologies are used to ensure the security and integrity of data transmission; and efficient data storage solutions are designed to facilitate rapid retrieval and analysis of massive data.

[0029] P30: Through the fault analysis module, the short-term user operation records are received to identify abnormal operations, and the equipment failure prediction is performed in combination with the user ticket purchase feedback information and the external environment interference data, and the real-time equipment failure prediction results are obtained and uploaded to the cloud computing center.

[0030] Specifically, during each remote fault detection cycle, the fault analysis module receives short-term user operation records previously collected by the sensor monitoring module. These operation records contain the operation data of each hardware module when the user interacts with the ticket machine. According to the different hardware module classifications, their operation behaviors are analyzed one by one to detect whether there are any abnormalities.

[0031] The abnormal identification unit of the fault analysis module analyzes the operation data of each hardware module to identify whether there are abnormal operations that deviate from the normal range. For example, if the printing module has abnormal behaviors such as operation timeout and printing interruption, the system will mark it as a potential fault. At the same time, abnormal identification is not limited to hardware, but also combines the user's operation behavior pattern to detect whether there are abnormal operations by comparing with the normal user operation process.

[0032] Based on the identification of abnormal operation, the fault analysis module combines the user's ticket purchase feedback information to further verify whether the operation is in line with expectations. Ticket purchase feedback information may include whether the user's payment is successful, whether the ticket is printed smoothly, whether the code is scanned correctly, etc. If the user feedback has an abnormality, such as payment is successful but the ticket is not printed, this is regarded as a key fault prompt signal.

[0033] In addition to user operations and feedback, external environmental interference data is also included in the analysis. External environments (such as high temperatures, network fluctuations, etc.) often have a significant impact on device operation. By combining environmental data, the system can more accurately determine the cause and scope of the failure. For example, if the ambient temperature is too high and the printer frequently jams, it can be predicted that the printer is about to fail due to overheating.

[0034] After comprehensively considering the results of abnormal operation identification, user feedback information and environmental interference data, real-time equipment fault prediction results are generated and uploaded to the cloud computing center in real time. The cloud computing center can combine historical data and real-time data of more devices for in-depth analysis, thereby further verifying and optimizing the fault prediction results and ensuring the accuracy and reliability of the prediction.

[0035] Furthermore, step P30 of the embodiment of the present application further includes:

[0036] P31: The fault analysis module includes an abnormality identification unit and a fault prediction unit; P32: The short-term user operation record is received through the abnormality identification unit, and the operation abnormality of each hardware module is identified in turn according to the hardware module classification to obtain the abnormal operation identification result.

[0037] Furthermore, step P32 of the embodiment of the present application also includes:

[0038] P32-1: Based on the short-term user operation records, according to the hardware module classification, the operation evaluation index set of each hardware module is extracted, and the operation evaluation index set includes but is not limited to the response time of the terminal device after the user issues an operation instruction, the number of repeated operations, the number of operation failures, the ticket waiting time, and the ticket success rate; P32-2: Using the operation evaluation index set as input, the operation anomaly identification is performed through the anomaly identification unit to obtain the operation anomaly identification results of each hardware module.

[0039] In a possible embodiment of the present application, the fault analysis module includes an abnormality identification unit and a fault prediction unit, and the abnormality identification unit and the fault prediction unit are used to realize operation abnormality identification and fault prediction. The abnormality identification unit is responsible for receiving short-term user operation records, and according to the hardware module classification, the operation abnormality identification is performed on each hardware module one by one. The fault prediction unit is responsible for predicting possible faults of the device based on the abnormality identification results and external data, so as to provide early warning and take measures.

[0040] Before identifying abnormal operation, firstly, based on the short-term user operation records and according to the classification of hardware modules, the operation evaluation index set of each hardware module is extracted. The operation evaluation index set is used to quantify the operation status of the device and provide input data for abnormal identification. The index set includes but is not limited to the response time of the terminal device after the user issues an operation instruction, the number of repeated operations, the number of operation failures, the waiting time for ticket issuance, and the success rate of ticket issuance. Among them, the response time refers to the response speed of the terminal device to the instruction after the user issues the operation instruction. A long response time may indicate that the device performance is degraded or the network is delayed. The number of repeated operations refers to the number of repeated operations performed by the user due to the failure of the device to respond in time. Too many repeated operations may mean that the device is unstable. The number of operation failures refers to the number of times the user's operation fails, such as payment failure or ticket issuance failure. A high operation failure rate may be a sign of hardware or software failure. The waiting time for ticket issuance refers to the time the user waits for the ticket to be printed after completing the payment. If the ticket issuance time is too long, it may indicate that there is a problem with the printing module. The ticket issuance success rate refers to the proportion of the number of successful ticket issuances to the total ticket issuance operations. A low ticket issuance success rate usually indicates that there may be a hardware failure in the ticket issuance device. These operation evaluation indicator sets provide the basis for anomaly identification. By quantitatively analyzing these data, potential abnormal behaviors of devices can be quickly identified.

[0041] Taking the extracted operation evaluation index set as input, the abnormality identification unit analyzes the operation status of each hardware module and identifies operation abnormalities based on these data. Exemplarily, based on statistical threshold comparison, classification and regression in machine learning models, etc., the data changes in the operation evaluation index set are automatically analyzed to identify abnormal behaviors that deviate significantly from the normal operation mode. For example, if the response time of a hardware module increases significantly, or the ticket issuance success rate decreases, the module will be marked as having an operation abnormality. Finally, the operation abnormality identification results of each hardware module are output. These results not only reveal potential operation abnormalities, but also provide an important basis for subsequent fault prediction.

[0042] Further, such as Figure 2As shown, based on the abnormal operation identification result, combined with the user's ticket purchase feedback information and the external environment interference data, equipment failure prediction is performed. Step P30 of the embodiment of the present application also includes:

[0043] P33: Read user ticket purchase feedback information, and obtain multiple feedback abnormality indicator sets based on the analysis of the user ticket purchase feedback information; P34: Extract multiple analysis abnormality indicator sets of each hardware module based on the operation abnormality identification result, and construct an abnormality indicator matrix by combining the multiple feedback abnormality indicator sets; P35: Generate an environmental interference coefficient through the external environment interference data, correct the abnormality indicator matrix, and obtain a corrected abnormality indicator matrix; P36: Normalize the corrected abnormality indicator matrix, and calculate and obtain the ideal solution and negative ideal solution of each abnormal indicator; P37: According to the ideal solution and negative ideal solution, combined with the normalized corrected abnormality indicator matrix, perform equipment failure risk prediction to obtain real-time equipment failure prediction results.

[0044] It should be understood that by integrating the results of abnormal operation identification, user ticket purchase feedback information, and external environment interference data, a more accurate prediction of equipment failure can be achieved. First, read the user ticket purchase feedback information, which is an important data source that directly reflects the user experience and the operating status of the device. Through natural language processing or text mining technology, analyze the key information in the user feedback information, such as payment failure, ticket issuance problems, system freezes, etc., and convert this information into multiple feedback abnormality indicator sets. These indicator sets are directly related to the specific problems encountered by users when purchasing tickets using smart terminal devices.

[0045] Next, based on the operation anomaly identification results obtained in the previous step, multiple analysis anomaly indicator sets of each hardware module are further extracted. These indicator sets include extended response time, excessive load, resource conflicts, etc., which reflect the operating status of the hardware modules from different angles. Subsequently, these analysis anomaly indicator sets are combined with the user ticket purchase feedback anomaly indicator set to construct an anomaly indicator matrix. This matrix contains possible abnormal conditions of the device in different dimensions, including both abnormal user operation feedback and abnormal performance of the device hardware performance. By constructing an anomaly indicator matrix, the system can integrate multi-source data and provide more comprehensive fault prediction input.

[0046] Exemplarily, the abnormal indicator matrix may be: ;in, is the abnormal indicator matrix, n is the number of samples, m is the number of abnormal indicators, Indicates the value of the i-th sample on the j-th index.

[0047] At the same time, considering the impact of external environmental factors on equipment performance, the concept of environmental interference coefficient is introduced. By real-time monitoring and analysis of external environmental interference data (such as temperature, humidity, electromagnetic field strength, etc.), the corresponding environmental interference coefficient is calculated. Exemplarily, it is first necessary to obtain real-time external environmental data from the environmental monitoring module and set weights for different environmental variables. The weight setting is based on the degree of influence of environmental variables on the equipment. For example, temperature and humidity are usually the main influencing factors, especially electronic equipment is susceptible to excessively high or low temperatures. Therefore, the weights of temperature and humidity will be relatively high. These weights can be adjusted through historical data analysis or domain expert experience. Then, for each environmental variable, a single environmental interference value is calculated based on the current collected real-time data, and the obtained single environmental interference value is weighted to generate the final environmental interference coefficient. These coefficients are used to correct the abnormal indicator matrix to eliminate or weaken the impact of the external environment on the fault prediction results. The corrected abnormal indicator matrix more accurately reflects the actual operating status of the equipment in a specific environment.

[0048] In order to eliminate the differences in dimensions and magnitudes between different abnormal indicators, the modified abnormal indicator matrix is ​​normalized, that is, standardized, so that all abnormal indicators can be compared and analyzed on the same scale. For example, the formula for the standardization process can be: ;in, is the standardized value. Then, the ideal solution and negative ideal solution of each abnormal indicator are calculated. The ideal solution represents the optimal state of each abnormal indicator, that is, the ideal value of each indicator when the device is in the best state, while the negative ideal solution represents the worst state, that is, the indicator value of the device under the worst condition. The ideal solution represents the target state when the device is operating normally, while the negative ideal solution represents the extreme case of device failure. Exemplarily, the calculation formula of the ideal solution and the negative ideal solution can be: The ideal solution is: ; Ideal solution It represents the value of each indicator in the best state, corresponding to the maximum or minimum value, depending on the nature of the indicator. The negative ideal solution is: ; Indicates the value of each indicator in the worst state.

[0049] Finally, the normalized modified abnormal index matrix and the calculated ideal solution and negative ideal solution are used to predict the equipment failure risk. This process may use methods such as multi-attribute decision analysis, fuzzy comprehensive evaluation or machine learning models. By comparing the proximity or distance relationship between each abnormal index and the ideal solution and negative ideal solution, the current failure risk level of the equipment is evaluated and real-time equipment failure prediction results are generated. These results can not only help users understand the equipment status in a timely manner and take corresponding measures to prevent failures, but also provide valuable reference information for equipment maintenance personnel to conduct more accurate fault diagnosis and repair work.

[0050] Furthermore, step P37 of the embodiment of the present application also includes:

[0051] P37-1: Based on the corrected abnormal indicator matrix, calculate the distance between each corrected abnormal indicator and the ideal solution and the negative ideal solution to obtain the sample relative distance; P37-2: According to the sample relative distance, calculate the sample relative proximity, and use it to predict the eating risk to obtain the real-time equipment failure prediction result.

[0052] Optionally, after the construction of the corrected anomaly indicator matrix is ​​completed, based on the normalized corrected anomaly indicator matrix, an appropriate distance measurement method (such as Euclidean distance, Manhattan distance, etc.) is used to calculate the distance between each corrected anomaly indicator and the ideal solution and the negative ideal solution. These distances are called sample relative distances, which reflect the importance and contribution of each corrected anomaly indicator in fault risk prediction. The ideal solution represents the optimal set of indicator values ​​when the equipment is in a fault-free state, while the negative ideal solution represents the worst set of indicator values ​​when the equipment is in a complete fault state. By calculating the distance between each corrected anomaly indicator and these two extreme states, the degree of closeness between the current state of the equipment and the fault risk can be quantitatively evaluated. Exemplarily, the formula for the sample relative distance can be: ;in, is the relative distance of the positive samples, is the relative distance of negative samples.

[0053] Next, based on the calculated sample relative distance, the sample relative proximity is further calculated. The sample relative proximity is a comprehensive indicator that comprehensively considers the relative position relationship between the corrected anomaly indicator and the ideal solution and the negative ideal solution. Specifically, the sample relative proximity can be calculated by weighted summation, proportional calculation or more complex mathematical models. A higher sample relative proximity means that the current state of the device is closer to the ideal solution (i.e., a fault-free state), while a lower sample relative proximity indicates that the device is closer to the negative ideal solution (i.e., a state with a higher risk of failure). Exemplarily, the calculation formula for the sample relative proximity can be: ;in, is the relative proximity of the sample, between 0 and 1, and is used to measure how close the sample is to the ideal solution. The closer the value is to 1, the closer the sample is to the ideal state and the lower the risk of failure; the closer the value is to 0, the closer the sample is to the negative ideal state and the higher the risk of failure.

[0054] Finally, the equipment failure risk is predicted based on the calculated relative proximity of the samples to obtain real-time equipment failure prediction results. This result expresses the failure risk level or probability currently faced by the equipment in a quantitative form, providing users with intuitive reference information. Through this step, not only can potential failure risks be discovered in a timely manner, but also early warning information can be provided to users so that they can take corresponding measures to prevent failures or reduce the impact of failures.

[0055] P40: The cloud computing center calibrates the real-time device fault prediction result in combination with the historical fault records of the smart terminal device to obtain a remote fault detection result.

[0056] Furthermore, step P40 of the embodiment of the present application also includes:

[0057] P41: With reference to the external environment interference data, historical fault records under similar environmental conditions are extracted from the historical database through the cloud computing center; P42: Based on the historical fault records, the actual fault occurrence frequency is obtained, and a risk correction factor is generated based on this; P43: Based on the risk correction factor, the real-time equipment fault prediction result is calibrated to obtain the remote fault detection result.

[0058] Specifically, when the intelligent terminal device completes the real-time fault prediction, the system will upload the prediction results to the cloud computing center. The cloud computing center calibrates the real-time prediction results by calling the historical fault records of the device. This process utilizes a larger historical data set and in-depth analysis capabilities to ensure that the prediction results are more accurate and reliable, and ultimately generate remote fault detection results.

[0059] In order to calibrate the prediction results more accurately, the external environmental interference data is introduced. The cloud computing center first refers to these external environmental interference data, such as temperature, humidity, electromagnetic field strength, etc., and selects historical fault records similar to the current environmental conditions from the historical database. This step uses big data analysis and data mining technology to quickly locate the historical cases that are closest to the current situation, providing strong data support for subsequent calibration work.

[0060] Subsequently, the actual fault frequency is calculated based on the extracted historical fault records. This frequency reflects the probability of failure of the intelligent terminal device under similar environmental conditions. For example, the failure frequency of the printing module may be higher in a high temperature environment, while the failure frequency of the network module is also higher in an environment with large network delay. Through statistical analysis, a risk correction coefficient is generated, which reflects the gap between the actual failure rate and the current prediction result. The generation process can refer to the generation process of the above-mentioned environmental interference coefficient. For example, if historical data shows that the frequency of failures in similar environments is low, a smaller risk correction coefficient is generated to appropriately reduce the failure risk in the real-time prediction results, and vice versa. This risk correction coefficient is a key parameter for subsequent calibration work, which can help the system more accurately assess the failure risk of the current equipment.

[0061] Finally, the generated risk correction coefficient is used to calibrate the real-time equipment failure prediction results. According to the risk correction coefficient of each hardware module, the real-time fault prediction results of the module are adjusted. If a module has a low frequency of failure in the historical records, the system will reduce the risk factor of the module, and vice versa. This calibration process fully considers the impact of external environmental interference factors on the risk of equipment failure, and adjusts the failure probability or risk level in the prediction results to make it closer to the actual situation. The calibrated remote fault detection results are not only more accurate and reliable, but also can provide users with more timely and effective fault warnings and maintenance suggestions, effectively reduce the false alarm rate, and promptly discover potential problems, and provide targeted fault prevention and maintenance solutions.

[0062] Furthermore, the embodiment of the present application further includes step P50, and step P50 further includes:

[0063] P51: Generate a fault detection compensation coefficient based on the real-time equipment fault prediction result and the actual fault occurrence frequency; P52: Correct the remote fault detection period through the fault detection compensation coefficient.

[0064] In a possible embodiment of the present application, in order to further optimize the efficiency and accuracy of remote fault detection, the remote fault detection cycle can be dynamically adjusted by comprehensively considering the real-time equipment fault prediction results and the actual fault occurrence frequency, thereby achieving reasonable allocation and efficient utilization of detection resources.

[0065] Specifically, first, a fault detection compensation coefficient is generated based on the two key indicators of real-time equipment fault prediction results and actual fault occurrence frequency. This coefficient is a dynamic adjustment factor that reflects the degree of deviation between the actual situation of the current equipment failure risk and the prediction result. This coefficient can be calculated through statistical analysis, machine learning algorithms or expert systems, so that it can be used to correct the remote fault detection cycle later. The calculation formula can be: Fault detection compensation coefficient = f (real-time fault prediction result) + g (actual fault occurrence frequency). Among them, f (real-time fault prediction result) is used to reflect the current prediction result. The higher the prediction risk, the larger the compensation coefficient. g (actual fault occurrence frequency) is used to refer to historical data. If a module has a high fault frequency in history, the compensation coefficient should also be increased accordingly.

[0066] Next, the generated fault detection compensation coefficient is used to correct the remote fault detection cycle. If the real-time device fault prediction results show that the current device is in a high-risk state and the actual fault frequency is also high, the detection cycle is shortened accordingly according to the fault detection compensation coefficient, so that the device status can be monitored more frequently and potential faults can be discovered and handled in a timely manner. On the contrary, if the prediction results show that the device is in good condition and the actual fault frequency is low, the detection cycle is appropriately extended to reduce unnecessary detection times and resource waste. This flexible fault detection cycle adjustment mechanism ensures the operational stability of smart terminal devices and improves overall detection efficiency.

[0067] In summary, the embodiments of the present application have at least the following technical effects:

[0068] This application configures edge computing nodes for smart terminal devices. The nodes include a sensor monitoring module and a fault analysis module. The sensor monitoring module collects short-term user operation records and external environment interference data, and the fault analysis module performs anomaly identification and fault prediction. Real-time prediction results are generated and uploaded to the cloud. Finally, the cloud computing center calibrates the prediction results based on historical fault records to obtain remote fault detection results.

[0069] The technical effect of achieving real-time response and early warning, improving fault detection accuracy, and reducing maintenance costs has been achieved through the coordinated cooperation of edge computing and cloud computing.

[0070] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0072] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A remote fault detection method for an intelligent terminal ticket machine, characterized in that: The method comprises: Configuring an edge computing node for the intelligent terminal device, wherein the edge computing node comprises a sensor monitoring module and a fault analysis module, and the edge computing node is configured with a remote fault detection cycle; According to the sensor monitoring module, collecting short-term user operation records and external environment interference data according to the remote fault detection cycle; The fault analysis module receives the short-term user operation records to identify abnormal operations, and combines the user's ticket purchase feedback information and the external environment interference data to predict equipment failures, obtain real-time equipment failure prediction results and upload them to the cloud computing center; The cloud computing center calibrates the real-time device fault prediction result in combination with the historical fault records of the smart terminal device to obtain a remote fault detection result; Among them, combining the user ticket purchase feedback information and the external environment interference data to predict equipment failures includes: Reading user ticket purchase feedback information, and obtaining multiple feedback abnormality indicator sets according to the user ticket purchase feedback information; Extract multiple analysis abnormality indicator sets of each hardware module according to the operation abnormality identification result, and construct an abnormality indicator matrix by combining the multiple feedback abnormality indicator sets; Generate an environmental interference coefficient through the external environmental interference data, and correct the abnormal index matrix to obtain a corrected abnormal index matrix; Normalizing the corrected abnormality indicator matrix, and calculating and obtaining an ideal solution and a negative ideal solution for each abnormality indicator; According to the ideal solution and the negative ideal solution, combined with the normalized modified abnormal indicator matrix, equipment failure risk prediction is performed to obtain a real-time equipment failure prediction result; According to the ideal solution and the negative ideal solution, combined with the normalized modified abnormal indicator matrix, equipment failure risk prediction is performed to obtain real-time equipment failure prediction results, including: Based on the modified anomaly indicator matrix, the distance between each modified anomaly indicator and the ideal solution and the negative ideal solution is calculated to obtain a sample relative distance; Calculate the relative proximity of the samples according to the relative distance of the samples, and use this to predict the risk of eating, and obtain the real-time equipment failure prediction result; The cloud computing center calibrates the real-time device fault prediction result in combination with the historical fault records of the smart terminal device, including: Referring to the external environment interference data, extracting historical fault records under similar environmental conditions from a historical database through the cloud computing center; Based on the historical fault records, the actual fault occurrence frequency is obtained, and a risk correction factor is generated based on the actual fault occurrence frequency. Calibrate the real-time equipment fault prediction result according to the risk correction coefficient to obtain the remote fault detection result; generating a fault detection compensation coefficient according to the real-time equipment fault prediction result and the actual fault occurrence frequency; The remote fault detection period is corrected by the fault detection compensation coefficient.

2. The remote fault detection method of the intelligent terminal ticket machine according to claim 1, characterized in that: Configure edge computing nodes, including: The sensor monitoring module includes a hardware monitoring submodule and an environment monitoring submodule; Based on the intelligent terminal device, hardware module division is performed to obtain multiple hardware function modules; According to the user operation instruction set, the plurality of hardware function modules are associated and mapped to generate a plurality of corresponding operation data collection loops; configuring the hardware monitoring submodule according to the plurality of operation data collection loops; The environmental monitoring submodule is configured according to the environmental monitoring indicators.

3. The remote fault detection method for an intelligent terminal ticket machine according to claim 1, characterized in that: Receiving the short-term user operation record to identify abnormal operation through the fault analysis module includes: The fault analysis module includes an abnormality identification unit and a fault prediction unit; The short-term user operation record is received by the abnormality identification unit, and the operation abnormality of each hardware module is identified in turn according to the hardware module classification to obtain the abnormal operation identification result.

4. The remote fault detection method of the intelligent terminal ticket machine according to claim 3, characterized in that: The abnormality identification unit receives the short-term user operation record and classifies the hardware modules to identify the abnormality of the operation of each hardware module in turn, including: Based on the short-term user operation records, according to the hardware module classification, an operation evaluation index set of each hardware module is extracted, wherein the operation evaluation index set includes but is not limited to the response time of the terminal device after the user issues an operation instruction, the number of repeated operations, the number of operation failures, the ticket issuance waiting time, and the ticket issuance success rate; The operation evaluation index set is used as input, and operation anomaly identification is performed by the anomaly identification unit to obtain operation anomaly identification results of each hardware module.

Images