Remote diagnosis and maintenance method and system for public transport intelligent integrated machine and medium

Abstract

The application provides a remote diagnosis and maintenance method and system for a bus intelligent integrated machine and a medium, and relates to the technical field of electric digital data processing. The method is based on historical data in a historical time period, and each bus section of a specified bus is pre-marked. In the actual driving process, the vehicle parameter is collected in real time by the sensing collection module of the vehicle-mounted integrated machine and uploaded to the cloud for remote diagnosis. Whether to execute the remote control preprocessing strategy is determined in combination with the pre-marking result. If the remote control preprocessing strategy is executed, the actual network condition of the bus section and the historical remote diagnosis condition are combined and analyzed to select a network diagnosis preprocessing measure. If it is determined that the remote control preprocessing strategy is not executed, remote maintenance is directly performed based on the remote diagnosis analysis result of the cloud. After the remote diagnosis and maintenance are completed, remote maintenance quality evaluation is performed to update the remote diagnosis condition of the corresponding bus section in the historical data, thereby solving the problems of long diagnosis response time, invalid remote maintenance operation and the influence on the reliability and safety of the system.

Description

Technical Field

[0001] This invention relates to the field of electronic digital data processing technology, and in particular to a method, system and medium for remote diagnosis and maintenance of intelligent integrated machines for public transportation. Background Technology

[0002] Remote diagnostics and maintenance of integrated bus terminals refers to the monitoring, analysis, and control of equipment operation status through collaboration between the onboard terminal and the back-end system. This includes diagnosing factors such as online status, frequency of disconnections, and power supply status. Remote maintenance is based on these diagnostics and involves actions such as remote parameter configuration (e.g., communication parameters, sampling frequency), issuing maintenance commands (e.g., entering maintenance mode), and generating maintenance work orders to guide manual repairs. To improve the operational efficiency of bus companies, extend equipment lifespan, and build a smart transportation system, remote diagnostics and maintenance of integrated bus terminals not only enhances the intelligence, automation, and predictability of equipment operation and maintenance but also significantly reduces labor and time costs, enabling a shift from passive maintenance to proactive prediction, from decentralized maintenance to centralized management, and from manual experience to data-driven approaches.

[0003] For example, Chinese invention patent CN117908922A discloses a system and method for OTA upgrades based on remote diagnostics, including: a web client, a cloud server, an intelligent vehicle terminal, and an ECU; the system software includes corresponding software; the method is as follows: establishing a connection between the IOBU and the cloud server; the IOBU monitors data collection and transmission, the cloud server analyzes vehicle status and fault information, and performs remote diagnostics on ECU faults; the ECU upgrade decision submodule selects a matching upgrade and maintenance plan; the ECU and the cloud server work together to complete the OTA upgrade.

[0004] Through the aforementioned vehicle-cloud-device communication, functions such as remote monitoring, remote diagnosis, and maintenance services are integrated, achieving seamless connection between fault diagnosis and maintenance. Based on this mechanism, it is also applicable to remote diagnosis and maintenance of intelligent integrated machines for buses. Through two-way communication between the cloud and the on-board equipment, real-time monitoring of equipment operating status, intelligent fault diagnosis, remote command issuance, and adaptive maintenance are achieved. The entire process is divided into three major stages: data collection and transmission (from vehicle to cloud), remote diagnosis and decision-making (in the cloud), and maintenance command and execution (from cloud to vehicle).

[0005] The implementation process first involves real-time collection of vehicle operating status and integrated device operating parameters, such as memory temperature and occupancy, communication module signal strength, storage space, logs, and sensor data. Next, the data undergoes preprocessing and local preliminary diagnosis. The collected data is then uploaded to the cloud via a secure channel. The cloud classifies, cleans, and persistently stores the uploaded data. Then, based on big data and algorithm models, remote intelligent diagnosis is achieved. Maintenance strategies are automatically generated or manually confirmed based on the diagnostic results. Finally, maintenance instructions are distributed to the vehicle-mounted integrated device via the network, forming a complete diagnosis-maintenance-feedback closed loop. Key technologies employed in this process include multi-source heterogeneous data fusion, MQTT (Message Queuing Telemetry Transport) / TLS (Transport Layer Security) encrypted transmission, rule-based and machine learning hybrid models, command signing and authorization authentication, and self-learning models and knowledge base accumulation. This enables the evolution of the public transport intelligent integrated device from passive alarm to proactive diagnosis and then to intelligent maintenance.

[0006] The above-mentioned technology still has at least the following problems: Because buses are in a moving environment while traveling along their routes, 4G / 5G network signals may become unstable or be completely lost when passing through areas such as underpasses, suburbs, and tunnels. Network connections may be frequently interrupted due to weak network signals, signal obstruction, and bandwidth limitations. This leads to increased latency in uploading sensor data, poor real-time performance, data buffer overflow or packet loss, and even failure to issue remote commands. This further results in long diagnostic response times, failure of remote maintenance operations, and impacts the reliability and security of the system. Summary of the Invention

[0007] Therefore, embodiments of the present invention provide a method, system, and medium for remote diagnosis and maintenance of smart public transport terminals, which can improve the success rate of remote diagnosis and maintenance of smart public transport terminals.

[0008] The technical solution of this invention is implemented as follows: Based on historical data within a historical time period, pre-marking is performed on each bus route of a specified bus to reflect the stability of remote diagnosis and maintenance. The historical data represents the characteristics of remote diagnosis and maintenance of the bus integrated machine. During the actual operation of the specified bus, vehicle parameters are collected in real time by the sensor acquisition module of the on-board integrated machine and uploaded to the cloud for remote diagnosis. At the same time, the pre-marking results are combined to determine whether to execute a remote control preprocessing strategy. If the remote control preprocessing strategy is executed, the actual network situation of the corresponding bus route is combined with the historical remote diagnosis situation for analysis to select the corresponding network diagnosis preprocessing measures. If it is determined that the remote control preprocessing strategy is not executed, remote maintenance is performed directly based on the remote diagnosis analysis results in the cloud. After the remote diagnosis and maintenance are completed, a remote maintenance quality assessment is performed to update the remote diagnosis situation of the corresponding bus route in the historical data.

[0009] This invention also provides a remote diagnostic and maintenance system for a smart bus terminal, including: a remote diagnostic pre-marking module, a remote control preprocessing module, a network diagnostic preprocessing module, and a remote maintenance quality assessment module. The remote diagnostic pre-marking module is used to pre-mark each bus route of a specified bus based on historical data within a historical time period, reflecting the stability of remote diagnostic and maintenance. The historical data represents the characteristics of remote diagnostic and maintenance of the bus terminal. The remote control preprocessing module is used to collect vehicle parameters in real time through the sensor acquisition module of the onboard unit during the actual operation of the specified bus and upload them to the cloud for remote diagnostics, while simultaneously combining pre-marking... The marking results determine whether to implement a remote control preprocessing strategy to intervene in the stability of remote maintenance in advance. The network diagnostic preprocessing module analyzes the actual network conditions of the corresponding bus route segment with historical remote diagnostic data if the remote control preprocessing strategy is implemented, and selects the appropriate network diagnostic preprocessing measures. If it is determined that the remote control preprocessing strategy is not implemented, remote maintenance is performed directly based on the cloud-based remote diagnostic analysis results. The remote maintenance quality assessment module performs a remote maintenance quality assessment after the remote diagnosis and maintenance are completed to update the remote diagnosis status of the corresponding bus route segment in historical data, thereby achieving closed-loop control of remote diagnosis and maintenance.

[0010] According to another aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute a remote diagnostic and maintenance method for a public transport intelligent integrated machine.

[0011] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: 1. During the remote diagnostics and maintenance of the bus-mounted integrated unit, historical data within a given time period is used to pre-mark each bus route segment of the designated bus, reflecting the stability of remote diagnostics and maintenance. This not only compensates for the current technology's lack of a quantitative assessment mechanism for the stability of remote diagnostics on different route segments and its inability to predict potential communication risks in advance, but also transforms remote maintenance from "post-event repair" to "pre-event prevention," improving the initiative and reliability of operation and maintenance. Then, during the actual operation of the designated bus, the sensor acquisition module of the onboard integrated unit collects vehicle parameters in real time and uploads them to the cloud for remote diagnostics. Simultaneously, the pre-marking results are combined to determine whether to execute remote control pre-processing strategies, allowing for early intervention in the stability of remote maintenance execution. This solves the problem of existing remote diagnostic systems lacking "on-the-fly decision-making" capabilities and only being able to execute fixed diagnostic procedures, resulting in a high task failure rate in weak network environments, thus improving the efficiency of remote diagnostics. The success rate and data integrity of remote maintenance are ensured by combining the actual network conditions of the corresponding bus route with historical remote diagnostic data if a remote control preprocessing strategy is implemented. This allows for the selection of appropriate network diagnostic preprocessing measures. If the remote control preprocessing strategy is not implemented, remote maintenance is performed directly based on the cloud-based remote diagnostic analysis results. This solves the problem that traditional technologies cannot combine real-time and historical network characteristics for personalized optimization. It enables the maintenance of basic communication and control functions even under poor network conditions, reducing "disconnection, reconnection, and interruption" phenomena. Finally, after the remote diagnostics and maintenance are completed, a remote maintenance quality assessment is performed to update the remote diagnostic data of the corresponding bus route in the historical data. This not only achieves closed-loop control of remote diagnostics and maintenance but also feeds back the results of each diagnostic task to update the historical database, making subsequent predictions more accurate and improving the system's long-term adaptability and decision-making accuracy.

[0012] 2. The remote control failure probability is compared with the extracted maximum failure probability. If the remote control failure probability is greater than the maximum failure probability, the remote control preprocessing strategy is executed. Otherwise, remote maintenance continues based on the cloud-based remote diagnostic analysis results. This compensates for the shortcomings of existing systems that often directly execute remote diagnostic commands without predicting failure risks based on actual communication conditions. It also prevents command issuance failures or system freezes caused by network fluctuations or abnormal device status. This realizes the transformation of remote tasks from "fixed execution" to "risk probability-based self-decision execution", ensuring that remote tasks are executed within the safety threshold and improving the success rate of remote maintenance and system reliability.

[0013] 3. The aforementioned remote control preprocessing strategy first acquires real-time remote control analysis data of the current bus route to provide more comprehensive environmental context information, making the preprocessing strategy more accurate. This solves the problem that existing systems rely solely on a single indicator (such as signal strength) to determine whether to perform preprocessing, lacking a comprehensive decision-making basis. Then, based on the remote control analysis data, quantitative analysis is performed to obtain the corresponding remote control stability index. This enables the selection of network diagnostic preprocessing measures in conjunction with remote diagnostic conditions, filling the gap in traditional remote control systems where judgments on network conditions often rely on experience or a single threshold (such as signal strength), lacking a comprehensive quantitative standard. This allows the system to maintain communication stability even in weak network environments, significantly reducing the remote control failure rate.

[0014] 4. Based on the current designated bus speed and maintenance delay distance, the remote maintenance waiting time is calculated. This prevents the previous system from forcibly executing maintenance commands when poor network conditions were detected, which could lead to task failure, command loss, or communication interruption. This gives remote maintenance tasks the ability to "delay execution," allowing operations to be performed when the network is better, thereby improving the task success rate. Then, a suggestion request to perform remote maintenance after the waiting time is sent to the cloud. This compensates for the lack of a collaborative judgment mechanism between the cloud and the terminal in traditional systems, improving the consistency and coordination of system decisions. If a permission command is received from the cloud, remote maintenance is performed after the waiting time; if a rejection command is received from the cloud, bandwidth limit adjustments are made to perform remote maintenance. This not only solves the problem that traditional solutions cannot automatically adjust task transmission strategies when bandwidth is insufficient, but also ensures that remote maintenance tasks can still be completed under low bandwidth conditions, improving system robustness. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating the remote diagnostic and maintenance method for a smart integrated machine for public transportation provided in an embodiment of the present invention. Figure 2 This is a flowchart illustrating the selection of network diagnostic preprocessing measures provided in an embodiment of the present invention; Figure 3 This is a flowchart illustrating the feasibility assessment of remote control delay provided in an embodiment of the present invention; Figure 4 This is a comparative diagram of remote maintenance optimization provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the remote diagnostic and maintenance system for intelligent integrated machines for public transportation provided in an embodiment of the present invention. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0017] In this application, the terms "first," "second," "third," etc., are used to distinguish identical or similar items with substantially the same function and purpose. It should be understood that there is no logical or temporal dependency between "first," "second," and "nth," nor does it limit the quantity or execution order. It should also be understood that although the following description uses the terms "first," "second," etc., to describe various elements, these elements should not be limited by the terms. These terms are merely used to distinguish one element from another. For example, "first device," "second device," "third device," etc., are only used to distinguish devices. Similarly, "first sample data," "second sample data," and "third sample data," etc., are only used to distinguish sample data. Without departing from the scope of the various examples, a first device can be referred to as a second device, and similarly, a second device can be referred to as a first device. Both the first device and the second device are devices, and in some cases, they can be separate and distinct devices.

[0018] Example 1: This embodiment of the invention provides a remote diagnostic and maintenance method for intelligent integrated machines used in public transportation. For example... Figure 1 The diagram shown is a flowchart illustrating a remote diagnostic and maintenance method for a smart integrated machine for public transportation provided by an embodiment of the present invention. The processing flow of this method may include the following steps: Based on historical data representing the characteristics of remote diagnosis and maintenance of the bus integrated machine within a historical time period, pre-marking is performed on each bus segment of the specified bus to reflect the stability of remote diagnosis and maintenance. The historical data is obtained from the historical database, such as bus operation timestamps, bus maintenance records, and bus operation data (e.g., in-vehicle temperature, bus speed, etc.).

[0019] Among them, bus routes are divided according to the fixed routes of designated buses, and the section between two adjacent bus stops is a bus route.

[0020] During the actual operation of the designated bus, the vehicle parameters are collected in real time by the sensor acquisition module of the on-board integrated machine and uploaded to the cloud for remote diagnosis. At the same time, the pre-labeling results are combined to determine whether to execute the remote control pre-processing strategy, so as to intervene in the stability of the remote maintenance in advance.

[0021] It should be explained that the sensor acquisition module of the in-vehicle integrated machine typically integrates multiple types of sensor units, such as vehicle operation status sensors, environmental monitoring sensors, network communication monitoring modules, and positioning modules. The vehicle parameters it collects include, but are not limited to, vehicle operation status data (speed, acceleration, engine speed, fuel consumption, battery charge, braking status, door status), vehicle environmental monitoring data (indoor and outdoor temperature, humidity, noise, light intensity, air pressure), communication and network status data (signal strength, network type, latency, bandwidth, packet loss rate, jitter rate, upload / download rate, etc.), as well as positioning and route data (GPS - Global Positioning System - location information, road segment number, latitude and longitude, elevation, road segment length, driving direction, bus stop signs, etc.) and system operation and diagnostic data (CPU - Central Processing Unit - CPU utilization, memory usage, storage space, I / O load, sensor status, device temperature, system logs).

[0022] If the remote control preprocessing strategy is implemented, the actual network conditions of the corresponding bus route segment will be analyzed in combination with historical remote diagnostic results to select the appropriate network diagnostic preprocessing measures. If it is determined that the remote control preprocessing strategy will not be implemented, remote maintenance will be performed directly based on the remote diagnostic analysis results in the cloud.

[0023] After remote diagnostics and maintenance are completed, a remote maintenance quality assessment is performed to update the remote diagnostic status of the corresponding bus route in the historical data, thereby achieving closed-loop control of remote diagnostics and maintenance.

[0024] In this embodiment, by introducing a technical solution that combines historical data pre-labeling, real-time acquisition, and dynamic decision-making, intelligent and highly stable control of the remote diagnosis and maintenance process of the bus integrated machine is achieved. By pre-labeling the remote diagnosis and maintenance feature data based on historical time periods, the system can model and quantify the network stability, data transmission quality, and maintenance success rate of different bus routes, forming a "stability label" that reflects the reliability of remote diagnosis and maintenance. This approach allows the system to perceive potential risks before performing remote operations, enabling prior assessment of network conditions and avoiding problems such as remote control failure, data loss, or task interruption caused by network fluctuations in traditional solutions, thereby improving the accuracy and success rate of remote maintenance.

[0025] Secondly, during the actual operation of the bus, the on-board integrated unit collects vehicle operation, communication network and environmental parameters in real time through the sensor acquisition module, and uploads the data to the cloud for analysis. By combining the real-time collected information with the pre-marking results, the system can dynamically determine whether the current road segment needs to implement the remote control pre-processing strategy, realizing adaptive control of the remote maintenance process. When the network conditions of the current road segment are detected to be poor or there is a high probability of failure, the system can actively trigger the pre-processing strategy, thereby realizing the pre-optimization of remote operation and ensuring that the maintenance task is executed under better communication conditions.

[0026] Furthermore, through joint analysis of historical diagnostic data and current network status, the system can intelligently select the most appropriate network diagnostic preprocessing measures, such as bandwidth regulation, data compression, and transmission priority adjustment, to improve the stability and timeliness of data interaction. This data-driven dynamic optimization approach helps to enhance the robustness and flexibility of the system in complex traffic and communication environments.

[0027] Finally, after the remote diagnostic and maintenance tasks are completed, the system will conduct real-time evaluation of the maintenance quality and update the historical database, so that the historical stability label of each bus route is dynamically optimized, forming a closed-loop mechanism of self-learning and self-evolution. This mechanism enables the system to continuously optimize in long-term operation, making the remote diagnostic model gradually more accurate, thereby continuously improving the success rate and efficiency of subsequent remote maintenance tasks.

[0028] It should be noted that before designing remote diagnostic and maintenance methods for intelligent public transport terminals, technical personnel typically pre-build a preset database to support the operation of various control strategies. This database integrates several key control parameters, including maximum failure probability, remote control stability assessment interval, network bandwidth lockout duration mapping set, preset weights, and reliability score thresholds. All parameters are pre-set by technical personnel based on the selected analysis method and on-site hardware configuration. This preset database provides the core data foundation for subsequent data uploading, storage optimization, and automated filtering and judgment processes.

[0029] Furthermore, the specific process of pre-marking designated bus routes to reflect the stability of remote diagnosis and maintenance is as follows: First, read the historical network diagnostic data for each bus route of the specified bus. The historical network diagnostic data includes the failure rate of remote command issuance, the network interruption rate, and the success rate of remote maintenance response.

[0030] Specifically, the remote command failure rate is the ratio of the number of failed remote commands to the total number of remote commands issued within a historical time period; the network outage rate is the frequency of network outages within a historical time period, i.e., the ratio of the number of network outages to the total duration of the historical time period; and the remote maintenance response success rate is the ratio of the number of successful remote maintenance operations to the total number of remote maintenance operations.

[0031] Next, the historical network diagnostic data is normalized (min-maximum data normalization) and then averaged to obtain historical remote diagnostic and maintenance parameters.

[0032] Finally, the corresponding remote control failure probability is obtained by mapping the historical remote diagnosis and maintenance parameters to the set historical average failure rate mapping table, and the remote control failure probability is marked on the corresponding bus route.

[0033] It should be added that historical remote diagnostic and maintenance parameters are input into a pre-trained historical average failure rate mapping table. The corresponding remote control failure probability is obtained by comparison. This mapping table is used to characterize the correlation between historical remote diagnostic and maintenance parameters and remote control failure probabilities. Its construction process is as follows: historical remote diagnostic and maintenance parameters collected within a historical time period, as well as remote control failure probabilities preset by professionals based on empirical rules, are input into an initial dataset constructed based on a logistic regression algorithm; subsequently, the cross-entropy loss function is used as the optimization criterion, and the model is trained using the scikit-learn framework to finally generate the historical average failure rate mapping table.

[0034] This invention realizes the process of extracting network features from historical data, quantifying fault risks, and spatially labeling them. By marking the probability of remote control failure on each road segment, the system can identify potential high-risk areas in advance, providing data support for subsequent remote diagnosis and maintenance strategies. This enables risk prediction, precise scheduling, and proactive optimization of maintenance tasks, significantly improving the stability of remote control and the success rate of tasks.

[0035] Furthermore, the specific steps for determining whether to execute the remote control preprocessing strategy based on the pre-labeling results are as follows: The remote control failure probability is compared with the maximum failure probability extracted from the preset database. If the remote control failure probability is greater than the maximum failure probability, the remote control preprocessing strategy is executed; otherwise, remote maintenance continues based on the remote diagnostic analysis results in the cloud. The maximum failure rate is preset by the staff based on historical data, standard rules and work experience and stored in the preset database. When needed, it can be read directly from the preset database.

[0036] The remote control preprocessing strategy is implemented as follows: Step 1: Obtain remote control analysis data of the current bus route in real time. The remote control analysis data includes network diagnostic data, the current bus route length and bus speed. The network diagnostic data includes signal strength, network latency, data transmission speed and data packet loss rate.

[0037] Specifically, signal strength can be directly read from the communication module. The communication module (4G / 5G / Wi-Fi module) usually provides signal strength values, such as RSSI (Received Signal Strength Indicator), RSRP (Reference Signal Received Power), or SINR (Signal to Interference plus Noise Ratio). Network latency is obtained by the all-in-one device by sending network probe packets (such as Ping commands or TCP handshake tests, Transmission Control Protocol) to a designated server and measuring the round-trip time (RTT). Data transmission speed is obtained by calculating the real-time bandwidth by measuring the amount of data transmitted per unit time (such as 1 second, 1 minute, 1 hour, etc.). The data packet loss rate is obtained by periodically sending test packets (such as Ping or UDP test packets, User Datagram Protocol), calculating the difference between the number of packets sent and the number of packets received, and then comparing it with the number of packets sent.

[0038] Step 2: Based on the remote control analysis data, perform quantitative analysis to obtain the corresponding remote control stability index, and select network diagnostic preprocessing measures in combination with the remote diagnostic situation.

[0039] Specifically, the network diagnostic data is first normalized using a minimum-maximum method. Then, each of these methods is multiplied by a pre-defined influencing factor, and the sum is obtained to obtain the first remote control stability factor. Next, the ratio of the current bus segment length to the bus speed is calculated, followed by Z-score standardization to obtain the second remote control stability factor. Finally, the first and second remote control stability factors are averaged to obtain the remote control stability index. The influencing factors include signal strength, network latency, data transmission speed, and packet loss rate, all of which sum to 1. These factors are pre-defined by experienced professionals based on established rules. Furthermore, the network diagnostic data is normalized using reference network diagnostic data set by pre-defined professionals, extracted from a pre-defined database. This reference data includes the minimum and maximum values ​​of signal strength, network latency, data transmission speed, and packet loss rate.

[0040] In this embodiment of the invention, by introducing a remote control failure probability determination mechanism and a remote control preprocessing strategy, intelligent risk assessment and adaptive control of the remote diagnosis and maintenance process of buses are realized. The system compares the remote control failure probability calculated in real time with the maximum failure probability threshold extracted from the preset database to quantitatively determine the risk of remote maintenance task execution. When the failure probability is detected to be too high, the system actively triggers the preprocessing strategy, which helps to avoid remote maintenance failures caused by network instability or signal abnormalities, thereby improving the task success rate and system security.

[0041] Secondly, the preprocessing strategy achieves multi-dimensional perception of the communication environment and vehicle dynamic status by collecting remote control analysis data of bus routes in real time, including network diagnostic data (signal strength, latency, speed, packet loss rate), route length, and vehicle speed. Based on this data, the system performs quantitative analysis, calculates the remote control stability index, and selects the optimal network diagnostic preprocessing measures, such as data compression, delayed execution, or speed-limited transmission. This ensures stable execution of remote maintenance even in weak network environments, thereby improving the success rate of remote control of the vehicle-mounted integrated unit from the cloud.

[0042] like Figure 2The diagram shown is a flowchart illustrating the selection of network diagnostic preprocessing measures provided in an embodiment of the present invention. The specific process is as follows: The remote control stability index is compared with the extracted remote control stability evaluation interval. If the remote control stability index belongs to the first remote control stability interval, the corresponding remote control real-time performance evaluation value is recorded as the first set value; if the remote control stability index belongs to the second remote control stability interval, the corresponding remote control real-time performance evaluation value is recorded as the second set value; if the remote control stability index belongs to the third remote control stability interval, the corresponding remote control real-time performance evaluation value is recorded as the third set value; the deviation between the remote control failure probability and the maximum failure probability is calculated to obtain the... The corresponding remote control deviation value is calculated; the remote control real-time evaluation value and the remote control deviation value are weighted and summed with preset weights, and then inversely proportional to obtain the remote control diagnosis and maintenance reliability score; the remote control diagnosis and maintenance reliability score is compared with the reliability score threshold: if the remote control diagnosis and maintenance reliability score is higher than the reliability score threshold, network bandwidth locking preprocessing is performed; if the remote control diagnosis and maintenance reliability score is not higher than the reliability score threshold, the feasibility of remote control delay is judged to ensure the stability of remote maintenance; through the above process, the dynamic selection of network bandwidth locking or delay control strategy is realized, which helps to improve the stability of the cloud-based remote diagnosis and maintenance process.

[0043] Specifically, the methods for selecting network diagnostic preprocessing measures are as follows: The first step is to compare the remote control stability index with the remote control stability assessment interval extracted from the preset database. The remote control stability assessment interval includes the first remote control stability interval, the second remote control stability interval, and the third remote control stability interval. The stability represented has a decreasing characteristic and is usually set in advance by preset staff based on historical data and experience rules within a historical time period and stored in the preset database for later retrieval.

[0044] The second step involves determining the optimal remote control stability index. If the index falls within the first remote control stability interval (left-closed, right-open interval), the current bus route exhibits the highest remote control stability. The corresponding real-time remote control evaluation value is recorded as the first setpoint, typically 1. If the index falls within the second remote control stability interval (left-closed, right-open interval), the current bus route exhibits satisfactory remote control stability. The corresponding real-time remote control evaluation value is recorded as the second setpoint, typically 2. If the index falls within the third remote control stability interval (left-closed, right-open interval), the current bus route exhibits the lowest remote control stability. The corresponding real-time remote control evaluation value is recorded as the third setpoint, typically 3. Furthermore, as the first, second, and third setpoints increase, the corresponding remote control stability gradually decreases.

[0045] The third step is to calculate the deviation between the remote control failure probability and the maximum failure probability to obtain the corresponding remote control deviation value. This means that the remote control deviation value is obtained by calculating the difference between the remote control failure probability and the maximum failure probability, and then by calculating the ratio between the difference and the maximum failure probability.

[0046] The fourth step involves weighting the remote control real-time performance evaluation value and the remote control deviation value with preset weights, summing the results, and then performing an inverse proportional operation to obtain the remote control diagnostic and maintenance reliability score. The inverse proportional operation means performing an inverse proportional operation on the sum of the weighted remote control real-time performance evaluation value and the remote control deviation value with preset weights. The preset weights include the remote control real-time weight and the remote control weight, both of which are preset data by the staff, and their sum is 1.

[0047] The fifth step is to compare the remote control diagnostic and maintenance reliability score with the reliability score threshold used to classify the feasibility of remote diagnostics and maintenance: if the remote control diagnostic and maintenance reliability score is higher than the reliability score threshold, network bandwidth locking preprocessing is performed; if the remote control diagnostic and maintenance reliability score is not higher than the reliability score threshold, the feasibility of remote control delay is judged to ensure the stability of remote maintenance; the aforementioned reliability score thresholds are read from a preset database and are generally preset by preset staff based on historical data and experience rules.

[0048] By establishing a remote control stability grading and weighted reliability calculation model, the feasibility of remote maintenance can be accurately determined. At the same time, by weighting and summing the comprehensive stability index, real-time evaluation value and failure probability deviation, a quantitative reliability score is obtained, thereby dynamically selecting bandwidth locking or delay control strategies. This method helps to improve the adaptability, stability and decision-making accuracy of the cloud-based remote diagnosis and maintenance process.

[0049] It should be noted that the specific content of the network bandwidth lockout preprocessing is as follows: Based on the reliability score of remote control diagnosis and maintenance, the network bandwidth lockout duration is mapped in the network bandwidth lockout duration mapping set in the preset database to obtain the network bandwidth resource lockout duration. Within the network bandwidth resource lockout duration, the number of processes currently occupying network bandwidth is locked and awaits remote maintenance. If the remote diagnosis does not issue a remote maintenance command, the network bandwidth lockout is automatically released.

[0050] It should be added that by inputting the remote control diagnostic and maintenance reliability score into the network bandwidth lock-in duration mapping set, the corresponding network bandwidth resource lock-in duration can be obtained. This dataset is used to fit the mapping relationship between the remote control diagnostic and maintenance reliability score and the network bandwidth resource lock-in duration. The construction method is as follows: in the initial data sequence constructed based on the gradient boosting regression algorithm, the remote control diagnostic and maintenance reliability score collected in the historical time period and the network bandwidth resource lock-in duration set according to empirical rules are selected as training samples. The model is trained based on the XGBoost framework with the least squares error as the objective function, and finally the set network bandwidth lock-in duration mapping set is obtained.

[0051] like Figure 3 The diagram illustrates the process for determining the feasibility of remote control delay according to an embodiment of the present invention. The specific logic is as follows: Based on the current specified bus speed and maintenance delay distance, the remote maintenance waiting time is calculated; a suggestion request to perform remote maintenance after the waiting time is sent to the cloud; if a permission command is received from the cloud, remote maintenance is performed after the waiting time; if a rejection command is received from the cloud, the relationship between the remote control diagnostic maintenance reliability score and the reliability score threshold is queried based on the difference between the difference and the bandwidth optimization strength to obtain the data preemption bandwidth optimization strength value, which includes the reduction in data acquisition frequency and the increase in data compression ratio; the data acquisition frequency and data compression are adjusted based on the reduction in data acquisition frequency and the increase in data compression ratio, respectively; through the above process, not only is intelligent dynamic optimization of bandwidth resources achieved, but it also helps to improve the stability and reliability of the remote control process of the smart bus integrated machine by the cloud.

[0052] To further explain, the specific process for determining the feasibility of remote control delay is as follows: Based on the current designated bus speed and maintenance delay distance, the remote maintenance waiting time is calculated. The maintenance delay distance represents the distance between the current designated bus and the next bus segment with a remote control failure probability no greater than the maximum failure probability. A suggestion request to perform remote maintenance after the remote maintenance waiting time is sent to the cloud. If a permission command is received from the cloud, remote maintenance is performed after the remote maintenance waiting time. If a rejection command is received from the cloud, bandwidth limit adjustment measures are implemented to perform remote maintenance.

[0053] The remote maintenance waiting time is obtained by dividing the maintenance delay distance by the specified bus speed.

[0054] It is important to understand that the specific methods for implementing bandwidth limit adjustments are as follows: S1. Based on the difference between the remote control diagnostic and maintenance reliability score and the reliability score threshold, query the relationship between the difference and the bandwidth optimization intensity to obtain the data preemption bandwidth optimization intensity value. The data preemption bandwidth optimization intensity value includes the reduction of data acquisition frequency and the increase of data compression ratio.

[0055] It should be added that the difference between the remote control diagnostic and maintenance reliability score and the reliability score threshold is recorded as the remote control diagnostic and maintenance difference. The remote control diagnostic and maintenance difference is input into the remote control diagnostic and maintenance sequence to obtain the corresponding data preemption bandwidth optimization strength value. This sequence is used to fit the mapping relationship between the remote control diagnostic and maintenance difference and the data preemption bandwidth optimization strength value. The construction method is as follows: in the initial data sequence constructed based on the linear regression algorithm, the remote control diagnostic and maintenance difference collected in the historical time period and the data preemption bandwidth optimization strength value set according to the empirical rules are selected as training samples. The least squares method criterion is used and the model is trained based on the statsmodels framework to finally obtain the set remote control diagnostic and maintenance sequence.

[0056] S2, based on the reduction of data acquisition frequency and the increase of data compression ratio, adjust the data acquisition frequency and data compression respectively for remote maintenance, which means multiplying the reduction of data acquisition frequency and the increase of data compression ratio with the data acquisition frequency and data compression respectively.

[0057] In this embodiment of the invention, by introducing a difference mapping mechanism between the reliability score and the reliability score threshold for remote control diagnostics and maintenance, intelligent dynamic optimization of bandwidth resources is achieved. When the system detects a low reliability score, it automatically determines the bandwidth optimization intensity value based on the difference mapping result, including the reduction in data acquisition frequency and the increase in data compression ratio. Through adaptive adjustment of data acquisition frequency and compression ratio, the system can effectively reduce data transmission pressure and improve bandwidth utilization in weak network or high load environments, preventing communication congestion and command delays during remote maintenance. At the same time, this method achieves fine-grained control of bandwidth resources, enabling remote diagnostics and maintenance tasks to achieve the optimal balance of network performance while ensuring data integrity and real-time response, thereby significantly improving the stability and reliability of the remote control process.

[0058] Furthermore, a remote maintenance quality assessment is conducted to update the remote diagnostic data for the corresponding bus routes in the historical data. The specific process is as follows: The remote maintenance quality coefficient is obtained by quantifying the quality characteristics of the current remote maintenance process using the acquired remote maintenance data. The remote maintenance data corresponding to the remote maintenance quality coefficient is then used to replace the first-stored remote maintenance data in the historical data within the historical time period. Based on the historical network diagnostic data of the bus route corresponding to the replaced historical data, the data is re-pre-labeled. The remote maintenance data includes the remote maintenance control duration, the number of vehicle-cloud interactions, and the maintenance status (success is recorded as 1, failure as 0).

[0059] It should be explained that after performing minimum-maximum data normalization on the remote maintenance control duration and the number of vehicle-cloud interactions, the mean is calculated, and then summed with the value corresponding to the maintenance status (1 for successful maintenance status and 0 for failure) to obtain the remote maintenance quality coefficient. The minimum-maximum data normalization is mainly performed on the maximum and minimum values ​​of remote maintenance control duration and the maximum and minimum values ​​of vehicle-cloud interactions in historical data.

[0060] By introducing a dynamic calculation mechanism for remote maintenance quality coefficients and a historical data replacement mechanism, the remote diagnostic system achieves self-learning and continuous optimization. Furthermore, the system quantifies the quality characteristics of the maintenance process based on real-time collected remote maintenance data, obtaining a remote maintenance quality coefficient, which is then used to update the maintenance data stored for the first time in the historical database. This method enables historical network diagnostic data to dynamically reflect the latest operating status, avoiding model lag and data distortion caused by long-term accumulation. Moreover, by re-labeling based on updated historical data, the system can continuously optimize the remote control reliability modeling of each bus route, achieving adaptive adjustment and accuracy improvement of remote maintenance strategies, thereby significantly improving the timeliness, accuracy, and overall intelligence level of remote diagnostics and maintenance.

[0061] like Figure 4 The diagram illustrates a comparison of remote maintenance optimization provided in this embodiment of the invention. The test conditions are as follows: two test buses with identical configurations depart simultaneously on designated bus routes during multiple test time periods. Remote maintenance command packets are simultaneously sent via the cloud to the integrated bus terminals of both test buses at preset time intervals. The remote maintenance results (success or failure) for each bus route are statistically analyzed. One test bus uses a traditional remote maintenance method (such as delayed maintenance), representing "before optimization," while the other test bus uses the method provided in this embodiment for remote maintenance, representing "after optimization." The bar chart in the diagram shows the changes in the failure rate during remote maintenance for 20 bus routes, comparing the remote maintenance failure rates (unit: %) before and after optimization. Orange bars represent "before optimization," and green bars represent "after optimization." After optimization, the green bars were generally lower than the orange bars across all 20 bus routes, indicating that the overall remote maintenance failure rate decreased. This demonstrates that the optimization measures improved the reliability of remote maintenance on most routes. Before optimization, the failure rate ranged from 10% to 40%, with some routes (such as routes 3, 5, 15, and 17) peaking at over 40%. This indicated unstable network conditions or weak signals on these routes, leading to frequent interruptions in data transmission and reception, thus increasing the probability of remote maintenance failure. After optimization, the remote maintenance failure rate decreased significantly, dropping to 10% to 25% on most routes, with an average reduction of approximately 30% to 40%. The improvement was even greater on some routes (such as routes 5, 15, and 17). As shown in the figure, the optimization measures significantly reduced the remote maintenance failure rate and improved the stability of the system's remote maintenance.

[0062] Example 2: Because the bandwidth usage differs between data acquisition frequency and data compression, bandwidth limit adjustment measures are implemented, which also includes: If the decrease in data acquisition frequency is greater than the increase in data compression ratio, and the difference between the two is greater than the set maximum difference, then the data acquisition frequency will be adjusted based on the decrease in data acquisition frequency. Furthermore, if the reliability score of remote control diagnosis and maintenance is still not higher than the reliability score threshold after the adjustment, the data compression will be adjusted based on the increase in data compression ratio.

[0063] If the increase in data compression ratio is greater than the decrease in data acquisition frequency, and the difference between the two is greater than the set maximum difference, then the data compression will be adjusted based on the increase in data compression ratio. If the reliability score of remote control diagnosis and maintenance is still not higher than the reliability score threshold after the adjustment, then the data acquisition frequency will be adjusted based on the decrease in data acquisition frequency.

[0064] In this embodiment, by setting a difference judgment mechanism between the reduction in data acquisition frequency and the increase in data compression ratio, the priority of bandwidth optimization process is adaptively adjusted. When the difference between the two exceeds the maximum difference, the system automatically identifies the dominant optimization direction and prioritizes the parameter adjustment with greater influence to maximize bandwidth utilization efficiency and remote communication stability. At the same time, if the reliability score of remote control diagnosis and maintenance still does not reach the threshold after the priority adjustment, the system will automatically execute another supplementary adjustment, forming a two-layer optimization closed loop. This strategy avoids the limitations of single parameter adjustment and achieves dynamic balance control of acquisition frequency and data compression, thereby effectively reducing transmission delay and packet loss risk in complex network environments and improving the robustness, flexibility and execution reliability of remote maintenance process.

[0065] This application also provides a remote diagnostic and maintenance system for applications such as intelligent integrated machines for public transportation. Figure 5 The diagram shown is a schematic representation of a remote diagnostic and maintenance system for a smart integrated machine for public transportation provided in an embodiment of the present invention. The system includes: a remote diagnostic pre-marking module, a remote control pre-processing module, a network diagnostic pre-processing module, and a remote maintenance quality assessment module.

[0066] The remote diagnostic pre-labeling module is used to pre-label the specified bus routes for each bus based on historical data representing the characteristics of remote diagnostics and maintenance of the integrated bus system within a historical time period, reflecting the stability of remote diagnostics and maintenance.

[0067] The remote control preprocessing module is used to collect vehicle parameters in real time through the sensor acquisition module of the on-board integrated machine during the actual operation of the designated bus and upload them to the cloud for remote diagnosis. At the same time, it combines the pre-labeling results to determine whether to execute the remote control preprocessing strategy, so as to intervene in the stability of remote maintenance in advance.

[0068] The network diagnostic preprocessing module is used to combine and analyze the actual network conditions of the corresponding bus route with historical remote diagnostic data if the remote control preprocessing strategy is executed, in order to select the corresponding network diagnostic preprocessing measures. If it is determined that the remote control preprocessing strategy is not executed, remote maintenance is performed directly based on the remote diagnostic analysis results in the cloud.

[0069] The remote maintenance quality assessment module is used to perform remote maintenance quality assessment after remote diagnosis and maintenance are completed, so as to update the remote diagnosis status of the corresponding bus route in the historical data and realize closed-loop control of remote diagnosis and maintenance.

[0070] This application also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute a remote diagnostic and maintenance method for a public transport intelligent integrated machine.

[0071] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0072] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, and portable compact disc read-only memory (CD). ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0073] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0074] The above description is only an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for remote diagnosis and maintenance of intelligent integrated machines for public transportation, characterized in that, The method includes: Based on historical data within a historical time period, pre-marking is performed on each bus route of a specified bus to reflect the stability of remote diagnosis and maintenance. The historical data represents the characteristics of remote diagnosis and maintenance of the integrated bus system. During the actual operation of the designated bus, the vehicle parameters are collected in real time by the sensor acquisition module of the on-board integrated machine and uploaded to the cloud for remote diagnosis. At the same time, the pre-labeling results are combined to determine whether to execute the remote control preprocessing strategy. If the remote control preprocessing strategy is implemented, the actual network conditions of the corresponding bus route segment will be analyzed in combination with the historical remote diagnostic results to select the corresponding network diagnostic preprocessing measures. If it is determined that the remote control preprocessing strategy is not implemented, remote maintenance will be performed directly based on the remote diagnostic analysis results in the cloud. After remote diagnostics and maintenance are completed, a remote maintenance quality assessment is performed to update the remote diagnostic status of the corresponding bus route in the historical data.

2. The remote diagnostic and maintenance method for intelligent integrated machines in public transportation as described in claim 1, characterized in that, The specific process of pre-marking designated bus routes to reflect the stability of remote diagnosis and maintenance is as follows: Read historical network diagnostic data for each bus route of a specified bus, including remote command failure rate, network interruption rate, and remote maintenance response success rate. After normalizing the historical network diagnostic data, the mean value is then applied to obtain the historical remote diagnostic and maintenance parameters. Based on the historical remote diagnostic and maintenance parameters, the corresponding remote control failure probability is obtained by mapping them to the set historical average failure rate mapping table, and the remote control failure probability is marked on the corresponding bus segment.

3. The remote diagnostic and maintenance method for intelligent integrated machines for public transportation as described in claim 1, characterized in that, The specific steps for determining whether to execute the remote control preprocessing strategy based on the pre-labeling results are as follows: The probability of remote control failure is compared with the maximum failure probability. If the probability of remote control failure is greater than the maximum failure probability, the remote control preprocessing strategy is executed; otherwise, remote maintenance continues based on the remote diagnostic analysis results in the cloud. The remote control preprocessing strategy is implemented as follows: The system acquires real-time remote control analysis data of the current bus route, including network diagnostic data, the current bus route length and bus speed. The network diagnostic data includes signal strength, network latency, data transmission speed and data packet loss rate. Based on the remote control analysis data, a quantitative analysis is performed to obtain the corresponding remote control stability index, which is then used to select network diagnostic preprocessing measures in conjunction with the remote diagnostic situation.

4. The remote diagnostic and maintenance method for intelligent integrated machines in public transportation as described in claim 3, characterized in that, The specific method for selecting network diagnostic preprocessing measures is as follows: The remote control stability index is compared with the extracted remote control stability evaluation interval, which includes a first remote control stability interval, a second remote control stability interval, and a third remote control stability interval. The stability represented has a decreasing characteristic. If the remote control stability index belongs to the first remote control stability range, it means that the remote control stability of the current bus route is the highest, and the corresponding remote control real-time evaluation value is recorded as the first set value. If the remote control stability index belongs to the second remote control stability range, it means that the remote control stability of the current bus route is qualified, and the corresponding remote control real-time evaluation value is recorded as the second set value. If the remote control stability index belongs to the third remote control stability range, it means that the remote control stability of the current bus route is the lowest. The corresponding remote control real-time performance evaluation value is recorded as the third set value. The remote control stability gradually decreases as the first set value, the second set value, and the third set value are reached. The deviation value of remote control is obtained by calculating the difference between the probability of remote control failure and the maximum probability of failure. The remote control real-time performance evaluation value and the remote control deviation value are weighted by preset weights, summed, and then inversely proportional to obtain the remote control diagnostic and maintenance reliability score. The reliability score for remote control diagnostics and maintenance is compared with a reliability score threshold used to classify the feasibility of remote diagnostics and maintenance: If the reliability score for remote control diagnostics and maintenance is higher than the reliability score threshold, then network bandwidth locking preprocessing is performed. If the reliability score for remote control diagnostics and maintenance is not higher than the reliability score threshold, a feasibility assessment of remote control delay will be conducted to ensure the stability of remote maintenance.

5. The remote diagnostic and maintenance method for intelligent integrated machines in public transportation as described in claim 4, characterized in that, The specific details of the network bandwidth locking preprocessing are as follows: Based on the reliability score of remote control diagnosis and maintenance, the network bandwidth resource lock-in duration is obtained by mapping it to the network bandwidth lock-in duration mapping set in the preset database. The number of processes currently occupying network bandwidth is locked during the network bandwidth resource lockout period. If no remote maintenance command is issued by remote diagnostics, the network bandwidth lockout will be automatically released.

6. The remote diagnostic and maintenance method for intelligent integrated machines in public transportation as described in claim 4, characterized in that, The specific process for determining the feasibility of remote control delay is as follows: Based on the current designated bus speed and maintenance delay distance, the remote maintenance waiting time is calculated. The maintenance delay distance represents the distance between the current designated bus and the next bus segment with a remote control failure probability not greater than the maximum failure probability. Send a request to the cloud suggesting that remote maintenance be performed after the remote maintenance waiting period. If the cloud grants permission, remote maintenance will be performed after the waiting period. If the cloud rejects the request, bandwidth limit adjustment measures will be implemented to perform remote maintenance.

7. The remote diagnostic and maintenance method for intelligent integrated machines in public transportation as described in claim 6, characterized in that, The specific methods for implementing bandwidth limit adjustments are as follows: Based on the difference between the remote control diagnostic and maintenance reliability score and the reliability score threshold, the relationship between the difference and the bandwidth optimization intensity is queried to obtain the data preemption bandwidth optimization intensity value, which includes the reduction of data acquisition frequency and the increase of data compression ratio; The data acquisition frequency and data compression were adjusted based on the reduction in data acquisition frequency and the increase in data compression ratio, respectively, in preparation for remote maintenance.

8. The remote diagnostic and maintenance method for intelligent integrated machines for public transportation as described in claim 1, characterized in that, The process of conducting remote maintenance quality assessment to update the remote diagnostic status of the corresponding bus route in historical data is as follows: The quality characteristics of the current remote maintenance process are quantified by acquiring remote maintenance data to obtain a remote maintenance quality coefficient. The remote maintenance data corresponding to the remote maintenance quality coefficient is then used to replace the first-stored remote maintenance data in the historical data within the historical time period. Based on the historical network diagnostic data of the bus route corresponding to the replaced historical data, the data is re-pre-labeled. The remote maintenance data includes remote maintenance control duration, number of vehicle-cloud interactions, and maintenance status.

9. A system applying the remote diagnostic and maintenance method for intelligent integrated machines for public transportation as described in any one of claims 1-8, wherein, include: Remote diagnostic pre-labeling module, remote control preprocessing module, network diagnostic preprocessing module, and remote maintenance quality assessment module; The remote diagnostic pre-marking module is used to pre-mark each bus route of a specified bus based on historical data within a historical time period, reflecting the stability of remote diagnostics and maintenance. The historical data represents the characteristics of remote diagnostics and maintenance of the integrated bus unit. The remote control preprocessing module is used to collect vehicle parameters in real time through the sensor acquisition module of the on-board integrated machine during the actual operation of the designated bus and upload them to the cloud for remote diagnosis. At the same time, it determines whether to execute the remote control preprocessing strategy based on the pre-marking results, so as to intervene in the stability of the remote maintenance in advance. The network diagnostic preprocessing module is used to combine and analyze the actual network situation of the corresponding bus route with the historical remote diagnostic situation if the remote control preprocessing strategy is executed, so as to select the corresponding network diagnostic preprocessing measures. If it is determined that the remote control preprocessing strategy is not executed, remote maintenance is performed directly based on the remote diagnostic analysis results in the cloud. The remote maintenance quality assessment module is used to perform a remote maintenance quality assessment after the remote diagnosis and maintenance are completed, so as to update the remote diagnosis status of the corresponding bus route in the historical data and realize closed-loop control of remote diagnosis and maintenance.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the remote diagnosis and maintenance method for a smart integrated machine for public transportation as described in any one of claims 1-8.

Images