Rail transit toilet system release state data processing method and system

Abstract

The present application relates to the technical field of data processing, and discloses a rail transit toilet system release state data processing method and system, comprising: obtaining maintenance behavior records and working condition sensor data streams and outputting time-stamped multi-source basic data sets; adopting asymmetric semantic field membership degree competition to bind and output a bound comprehensive data set; determining an output interface reassembly integrity state value through dynamic temperature difference recovery; combining transient tolerance and liquid level response slope deviation joint determination to output a risk state combination value; and outputting a release decision encapsulation object according to a preset release result combination logic matrix. The present application aims at the problem that the artificial maintenance record and the sensor fixed sampling time accuracy are inconsistent, and the absolute time stamp splicing is easy to cause reassembly and risk misjudgment, aligns the event semantics, determines the interface integrity, identifies the freezing and leakage risk, and continuously connects the release decision encapsulation, thereby improving the reliability and traceability of the preparation release state determination.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for processing release status data of a rail transit toilet system. Background Technology

[0002] Currently, during the maintenance and repair of rail transit vehicles, to prevent pipe leaks, freezing, and other malfunctions in the toilet system during subsequent operation, maintenance personnel need to periodically disassemble, inspect, and reassemble the interfaces, recording these actions via handheld terminals or information systems. Simultaneously, temperature sensors, level sensors, and other equipment distributed on the water tank and drainage pipes automatically collect operational data at fixed 5-minute intervals. To automatically assess the integrity of the interface reassembly and make release decisions after maintenance, it is typically necessary to temporally correlate discrete records of manual maintenance actions with equally spaced sensor data streams to form a sequence that can be used for temperature difference recovery and leakage risk assessment. Existing processing paths mostly employ an alignment method based on absolute timestamps, directly splicing together event-data pairs based on the temporal relationship between manually recorded times and sensor sampling times.

[0003] For example, in this application scenario, maintenance records are often entered by personnel after the fact, with time accuracy only reaching the minute level, and there are significant input delays and individual biases. Meanwhile, sensors such as those for pipeline temperature are collected strictly at 5-minute intervals. When the disassembly operation actually occurs at 10:08:30, the manually recorded timestamp might only be 10:08, while the corresponding temperature data points are sampled at 10:05 and 10:10. Traditional absolute timestamp alignment methods would directly associate this disassembly event with the 10:05 sampling point, causing the temperature decrease trend that should appear after disassembly to be replaced by the higher temperature value before disassembly. More seriously, after reassembly, integrity needs to be determined based on the temperature recovery amount and the timing of changes. Misaligned data points will disrupt the temperature sequences before, after, and after disassembly, causing the logical consistency of the event timing relationship on which the temperature difference recovery determination depends to be lost, resulting in misjudgments of the reassembly integrity status and ultimately affecting the reliability of the release decision.

[0004] Therefore, there is an urgent need for a data processing method that can tolerate the time accuracy difference between maintenance behavior records and sensor data streams without the need for additional deployment of high-precision time synchronization devices. This method should be based on event semantics rather than simple absolute time points to achieve the attribution and binding of multi-source data events with unequal intervals. This would ensure that, under the premise that disassembly events, reassembly events and their corresponding temperature change sequences are logically valid, the integrity status of interface reassembly can still be accurately determined, thereby improving the accuracy of release decisions and the safety and reliability of rail transit toilet system operation. Summary of the Invention

[0005] To address the aforementioned technical shortcomings, the present invention aims to propose a method and system for processing release status data in a rail transit toilet system. This method and system are intended to solve the technical problem in the prior art where maintenance records and sensor data are spliced ​​together using absolute timestamps, especially under the conditions of parking and maintenance where both manual coarse-grained timestamps and fixed-cycle fine-grained sensing coexist. This problem results in the inability to correctly align and bind multi-source time-series data with unequal intervals, which in turn leads to misjudgments of interface reassembly integrity.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides a method and system for processing release status data of a rail transit toilet system.

[0007] The method for processing release status data of a rail transit toilet system includes:

[0008] Step S10: Obtain maintenance behavior records and operating condition sensor data streams associated with the unique identifier of the overall toilet system of rail transit. Based on the maintenance behavior records, perform time-stamped association processing on the operating condition sensor data streams using an event time window mirror back projection method, and output time-stamped multi-source basic datasets.

[0009] Step S20: Based on the timestamped multi-source basic dataset, perform the event attribution binding task using the asymmetric semantic field membership degree competition binding method, and output a comprehensive binding dataset arranged by time axis and labeled with event attribution type;

[0010] Step S30: Based on the bound comprehensive dataset, perform the interface reassembly integrity status determination task using the dynamic temperature difference recovery determination method, and output the interface reassembly integrity status value;

[0011] Step S40: Based on the interface reassembly integrity status value, the event-driven transient tolerance and liquid level response slope deviation joint judgment method is used to perform the freezing and leakage risk judgment task, and output a risk status combination value including freezing risk status value and leakage risk status value;

[0012] Step S50: Encapsulate the release decision based on the risk status combination value and the preset release result combination logic matrix, and output the release decision encapsulation object.

[0013] Preferably, step S10, which involves acquiring maintenance behavior records and operational sensor data streams associated with the unique identifier of the overall rail transit toilet system, performing time-stamped association processing on the operational sensor data streams based on the maintenance behavior records using an event time window mirroring back projection method, and outputting a time-stamped multi-source basic dataset, specifically includes:

[0014] Step S101: Using the unique identifier of the rail transit integrated toilet system as an index, read the maintenance behavior record corresponding to the rail transit integrated toilet system from the maintenance database, and read the corresponding working condition sensor data stream from the working condition sensor database;

[0015] Step S102: Parse the operation timestamp and behavior event type for each maintenance behavior record to form a behavior event record with operation timestamp and behavior event type;

[0016] Step S103: Write a collection timestamp to each data point in the working condition sensor data stream, and generate associated event labels for the data points according to the behavior event records, forming a timestamped multi-source basic dataset containing the behavior event records and data points with associated event labels.

[0017] Preferably, step S20, which involves performing the event attribution binding task based on the timestamped multi-source basic dataset using an asymmetric semantic field membership competition binding method, and outputting a comprehensive binding dataset arranged along the time axis and labeled with event attribution types, specifically includes:

[0018] Step S201: Extract behavioral event records and sensor data points from the timestamped multi-source basic dataset. For each behavioral event type, preset the time window radius, the weight of the first period, and the weight of the second period. The sum of the weight of the first period and the weight of the second period is 1. The weight of the first period of the interface disassembly event is greater than the weight of the second period, and the weight of the second period of the interface reassembly event is greater than the weight of the first period.

[0019] Step S202: Generate a mirrored event time window for each behavior event record:

[0020]

[0021] In the formula, Represents behavioral events The corresponding mirror event time window, Represents behavioral events The operation timestamp Indicates the radius of the time window. This indicates the weight over a certain period of time. Indicates the weight of the later period;

[0022] Step S203: When the acquisition timestamp of any sensor data point falls within one or more mirror event time windows, calculate the semantic field membership degree of that sensor data point to each corresponding behavioral event:

[0023]

[0024]

[0025] In the formula, Represents sensor data points behavioral events semantic field membership degree Represents sensor data points The collection timestamp, This represents the normalized time offset. This represents the membership attenuation width parameter;

[0026] Step S204: Compare the semantic field membership values ​​corresponding to the same sensor data point, bind the sensor data point to the behavior event with the largest semantic field membership value, bind the sensor data points that do not fall into any mirror event time window to the background state event, and form a bound comprehensive dataset arranged by time axis and labeled with the event belonging type.

[0027] Preferably, in step S202, when generating a mirror event time window for each behavior event record, the preceding time weight and the following time weight are configured according to the interface disassembly event, the interface reassembly event, and the electric heat tracing test completion event, respectively. This causes the mirror event time window corresponding to the interface disassembly event to shift to the time period before the operation timestamp, the mirror event time window corresponding to the interface reassembly event to shift to the time period after the operation timestamp, and the mirror event time window corresponding to the electric heat tracing test completion event to maintain symmetry with respect to the operation timestamp.

[0028] Preferably, step S30, which involves performing an interface reassembly integrity status determination task based on the bound comprehensive dataset using a dynamic temperature difference recovery determination method, and outputting the interface reassembly integrity status value, specifically includes:

[0029] Step S301: Extract the following sets of temperature data points after interface disassembly event, interface reassembly event, electric heat tracing temperature data points after electric heat tracing test completion event, background state temperature data point sequence corresponding to background state event, liquid level change analysis unit, final inspection leak detection value, and mirror event time window range corresponding to electric heat tracing test completion event from the binding comprehensive dataset to form event chain segments.

[0030] Step S302: Calculate the average temperature after disassembly, the average temperature after reassembly, and the temperature recovery amount:

[0031]

[0032]

[0033]

[0034] In the formula, This indicates the average temperature after disassembly. This indicates the average temperature after reassembly. Indicates the amount of temperature recovery. This indicates the number of temperature data points after disassembly. This indicates the number of temperature data points after reassembly. Indicates the first Temperature values ​​collected after disassembly Indicates the first Temperature values ​​collected after reassembly;

[0035] Step S303: Calculate the dynamic recovery judgment threshold:

[0036]

[0037] In the formula, This indicates the threshold for dynamic recovery determination. Indicates the baseline recovery temperature difference threshold. Indicates the reference ambient temperature. This indicates the current ambient temperature obtained from the vehicle's environmental sensors. This represents the ambient temperature compensation coefficient. This indicates the actual operation time for interface reinstallation, calculated from the timestamp intervals of the maintenance behavior records. Indicates the standard operation time. This represents the operation time compensation coefficient;

[0038] Step S304: When the temperature recovery amount is greater than or equal to the dynamic recovery judgment threshold, the event sequence in the event chain segment includes the complete sequence from the interface disassembly event to the interface reassembly event to the final inspection leakage detection event, and the final inspection leakage detection value is lower than the preset leakage threshold, the interface reassembly integrity judgment result is assigned the value of complete.

[0039] Step S305: When the temperature recovery amount is less than the dynamic recovery judgment threshold, or the event sequence in the event chain segment does not contain the complete sequence from the interface disassembly event to the interface reassembly event to the final inspection leakage detection event, or the final inspection leakage detection value is greater than or equal to the preset leakage threshold, the interface reassembly integrity judgment result is assigned as pending re-inspection.

[0040] Step S306: Encapsulate the interface reassembly integrity judgment result, the event chain fragment, the background state temperature data point sequence, the liquid level change analysis unit, and the mirror event time window range corresponding to the electric heat tracing test completion event into an interface reassembly integrity status value output.

[0041] Preferably, in step S40, the step of performing the freezing and leakage risk determination task based on the interface reassembly integrity status value using an event-driven transient tolerance and liquid level response slope deviation joint determination method, and outputting a risk status combination value including freezing risk status value and leakage risk status value, specifically includes:

[0042] Step S401: Extract the background state temperature data point sequence from the interface reassembly integrity state value. When the background state temperature data point sequence is in continuous... When the temperature shows a monotonically decreasing trend within a single data collection cycle, the cumulative temperature drop exceeds a preset cumulative temperature drop threshold, and the current temperature is below a preset warning temperature threshold, a freezing risk warning is triggered, and a freezing risk status value is generated. This indicates the number of descent cycles, and the preset cumulative cooling threshold indicates continuous... The maximum cumulative temperature drop allowed within a collection cycle, wherein the preset warning temperature threshold represents the temperature boundary value that triggers a freezing risk warning;

[0043] Step S402: Enter transient tolerance mode within the mirror event time window corresponding to the electric heat tracing test completion event in the interface reassembly integrity status value, and temporarily increase the continuous descent cycle number requirement, increase the cumulative cooling judgment boundary, and lower the warning temperature boundary in the transient tolerance mode. After the mirror event time window ends, restore the corresponding original triggering conditions.

[0044] Step S403: Extract the liquid level change analysis unit from the interface reassembly integrity status value, and calculate the actual liquid level change slope and slope deviation rate:

[0045]

[0046]

[0047] In the formula, This represents the slope of the actual liquid level change. This indicates the actual change in liquid level. This indicates the time span of the liquid level change analysis unit. Indicates the slope deviation rate. This indicates the ideal liquid level change slope corresponding to the preset valve operation type.

[0048] Step S404: When the slope deviation rate is greater than the preset deviation tolerance threshold and no other valve action event occurs in the liquid level change analysis unit, it is determined to be an unexpected liquid level change including the independent labels of the gray water tank and the black water tank, and a leakage risk status value is generated; the freezing risk status value and the leakage risk status value are encapsulated into a risk status combination value and output.

[0049] Preferably, step S50, which involves encapsulating the release decision based on the risk status combination value and the preset release result combination logic matrix, and outputting the release decision encapsulation object, specifically includes:

[0050] Step S501: Using the risk status combination value as input, query the preset release result combination logic matrix, and output a release result including allow release, restrict release, or prohibit release;

[0051] Step S502: Encapsulate the release result, the risk status combination value, and the processing data generated in steps S10 to S40 into a risk encapsulation object;

[0052] Step S503: Encapsulate the release result and the risk encapsulation object into a release decision encapsulation object, and associate and store the release decision encapsulation object with the unique identifier of the rail transit overall toilet system.

[0053] The present invention also provides a data processing system for the release status of a rail transit toilet system, comprising:

[0054] The multi-source data acquisition module is used to acquire maintenance behavior records and operating condition sensor data streams associated with the unique identifier of the overall toilet system of rail transit. Based on the maintenance behavior records, the operating condition sensor data streams are processed by time-stamping association using an event time window mirroring back projection method, and the time-stamped multi-source basic dataset is output.

[0055] The event attribution binding module is used to perform the event attribution binding task based on the timestamped multi-source basic dataset using an asymmetric semantic field membership degree competitive binding method, and outputs a binding comprehensive dataset arranged by time axis and labeled with event attribution type;

[0056] The interface reassembly integrity determination module is used to perform an interface reassembly integrity status determination task based on the bound comprehensive dataset using a dynamic temperature difference recovery determination method, and output the interface reassembly integrity status value.

[0057] The freezing and leakage risk assessment module is used to perform freezing and leakage risk assessment tasks based on the integrity status value of the interface and adopt an event-driven transient tolerance and liquid level response slope deviation joint assessment method, and output a risk status combination value including freezing risk status value and leakage risk status value.

[0058] The release decision encapsulation module is used to encapsulate the release decision based on the risk status combination value and the preset release result combination logic matrix, and output the release decision encapsulation object.

[0059] The present invention also provides a data processing device for the release status of a rail transit toilet system. The data processing device includes: a memory, a processor, and a data processing program for the release status of a rail transit toilet system stored in the memory and executable on the processor. When the data processing program for the release status of a rail transit toilet system is executed by the processor, it implements the above-mentioned method.

[0060] The present invention also provides a computer program product, which includes a rail transit toilet system release status data processing program, which implements the above-described method when executed by a processor.

[0061] The beneficial effects of this invention are as follows:

[0062] This invention maps maintenance behavior records to asymmetrical time windows on the sensor data time axis through an event time window mirroring and back-projection mechanism. It assigns pre-labeled associations based on event type and, together with an asymmetric semantic field membership degree competitive binding mechanism, uses the weights of the earlier and later time periods to control the effective range of event influence. This allows sensor data points to compete to bind to the most matching event based on the membership degree of the semantic field, overcoming the problems of timestamp misalignment caused by rough manual recording and fixed sensor sampling. It ensures that the bound dataset truly reflects the actual temporal relationship of physical events and provides accurate input for interface reassembly integrity and other risk assessments.

[0063] The dynamic temperature difference recovery judgment mechanism constructed in this invention introduces compensation coefficients for ambient temperature and operation time, automatically adjusting the dynamic recovery threshold in the reassembly integrity judgment, avoiding misjudgments caused by fixed thresholds under different seasons and operating conditions. At the same time, the event-driven transient tolerance and liquid level response slope deviation joint mechanism can temporarily relax the freezing warning conditions under specific working conditions such as electric heat tracing tests, suppressing false alarms caused by test disturbances. By analyzing the deviation between the liquid level change slope of the grey water and black water tanks and the ideal operating model, the interference of normal valve actions is eliminated, enabling accurate identification and independent labeling of unexpected leaks. This makes the entire release status data processing process more robust and environmentally adaptable, improving the accuracy and traceability of release decisions. Attached Figure Description

[0064] Figure 1 This is a flowchart illustrating the first embodiment of a method and system for processing release status data of a rail transit toilet system according to the present invention. Detailed Implementation

[0065] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0066] Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0067] Example 1: As Figure 1 The diagram shown is a flowchart of the first embodiment of a method and system for processing release status data of a rail transit toilet system according to the present invention.

[0068] In the first embodiment, the method and system for processing release status data of a rail transit toilet system includes:

[0069] Step S10: Obtain maintenance behavior records and operating condition sensor data streams associated with the unique identifier of the overall toilet system of rail transit. Based on the maintenance behavior records, perform time-stamped association processing on the operating condition sensor data streams using an event time window mirror back projection method, and output time-stamped multi-source basic datasets.

[0070] In this step, the maintenance behavior record refers to the operation action record filled out by maintenance personnel during the parking and preparation period via handheld terminal or information management system, which is associated with the unique identifier of the overall rail transit toilet system. It includes at least interface disassembly, interface reassembly, electric heat tracing test, valve operation, etc., along with their corresponding operation timestamps, with time accuracy typically at the minute level. The operating condition sensor data stream refers to the time-series data automatically collected at fixed intervals by temperature sensors, level sensors, etc., distributed on the toilet pipes and water tanks. For example, the pipe temperature sensor collects data every 5 minutes, and the level sensor sampling period is 10 seconds. Each data point has its own collection timestamp. The event time window mirroring and back-projection mechanism uses the operation timestamp of each maintenance behavior record as the center. Based on the behavior event type corresponding to the record, it generates an asymmetric or symmetric candidate time window on the time axis of the sensor data stream. Sensor data points falling within this window are marked as potential associated candidates for the corresponding event, but are not hard-bound, while retaining the original collection timestamp. After this step, the maintenance behavior records are standardized into behavior event records with operation timestamps, and the sensor data points are accompanied by associated event annotation information. The two constitute a structured multi-source data input, providing a basic dataset with event candidate attributes and computable association strength for the subsequent asymmetric semantic field membership degree competition binding task.

[0071] By employing an event time window mirroring back-projection mechanism, this step does not forcibly map manually entered coarse-grained timestamps to fixed sensor sampling times. Instead, it generates a soft candidate region on the sensor timeline whose direction and span are determined by the event type. Each sensor data point thus acquires potential association labels with one or more maintenance events. Two types of data streams that were initially mismatched in the time dimension are preliminarily coupled, narrowing the search range for subsequent membership calculations. This processing ensures that the binding task deals with a set of already identified candidate relationships, rather than an exhaustive combination of all global events and data points. This reduces the computational complexity of subsequent asymmetric semantic field membership competition binding and provides a buffer to avoid irreversible misbinding due to timestamp discrepancies. The data set output by this step is no longer an isolated discrete record but a structured sequence with event context information, laying the foundation for constructing a logically correct time-series sequence.

[0072] Traditional approaches typically assume that the timestamps of manual maintenance records and sensor sampling timestamps are identical in precision, directly constructing event-data pairs using nearest neighbor matching or by concatenating absolute timestamps. However, in the scenario of restroom maintenance in rail transit, maintenance records suffer from input delays and rounding errors, often resulting in timestamps deviating from the actual operation time by tens of seconds or even minutes. Meanwhile, the sensor sampling period is fixed and inconsistent with the manual recording time base. This alignment method based on precise time points is highly susceptible to incorrectly associating disassembly events with sensor sampling points that physically belong to the period before disassembly. For example, marking a higher pipe temperature value before disassembly as data after disassembly could reverse the temporal sequence of events. This step, through event time window mirroring and back-projection, no longer pursues precise single-point matching. Instead, it establishes a candidate window for each event that tolerates time deviations, transforming the forced one-to-one correspondence into a probabilistic candidate association. This avoids irreversible misbinding caused by hard alignment and preserves the opportunity to correct deviations for subsequent membership competition binding.

[0073] For example, during a winter maintenance stop, the maintenance personnel physically disassembled the grey water tank pipe connection at 10:08:20. However, because an electronic work order needed to be filled out item by item, the operation record was not entered until 10:09:10, with the timestamp being 10:08. The pipe temperature sensor has a data acquisition cycle of 5 minutes, with sampling times at 10:05:00 and 10:10:00. If the traditional nearest neighbor alignment is used, the system will record the temperature value at 10:05:00 (e.g., 32°C). The data was incorrectly bound to disassembly event data, while the temperature actually reflects the piping state before disassembly. By employing the event time window mirroring back-projection mechanism in this step, the system identifies the record as an interface disassembly event and generates a backward-sloping time window around its timestamp based on the characteristics of the disassembly event, for example, the interval from 1 minute before to 7 minutes after [10:07, 10:15]. 10:05:00, not being within this window, will not be marked as a candidate point, while 10:10:00 will be marked as a potential associated candidate point for the disassembly event, and sensor data points with this label will be output. Thus, the temperature point at 10:10:00 will enter the next stage of membership competition binding, providing a possibility for obtaining the correct post-disassembly temperature baseline.

[0074] Step S20: Based on the timestamped multi-source basic dataset, perform the event attribution binding task using the asymmetric semantic field membership degree competition binding method, and output a comprehensive binding dataset arranged by time axis and labeled with event attribution type;

[0075] The asymmetric semantic field membership competition binding method in this step refers to establishing a competitive binding relationship with event semantics between behavioral event records and sensor data points based on the different directions and durations of the impact of different maintenance events on the preceding and following time periods. The mirrored event time window is not simply expanded equidistantly around the operation timestamp, but rather configured with a time window radius, preceding time weight, and following time weight based on different event types such as interface disassembly events, interface reassembly events, and electric heat tracing test completion events. When a sensor data point falls into one or more mirrored event time windows, it is not immediately fixed to a particular event. Instead, a membership degree is formed based on its proximity to the corresponding behavioral event in terms of time location and event semantics. Finally, the behavioral event with the higher membership degree value acquires ownership of the data point.

[0076] After implementing asymmetric semantic field membership competition binding, sensor data points that might have been ambiguous due to coarse timestamps are now clearly assigned events with definite attributions consistent with the physical impact direction of the events through asymmetric time windows and membership competition. The asymmetric weighting configuration ensures that the time window for disassembly events primarily covers subsequent time periods, while the time window for reassembly events extends further back, aligning with the main distribution characteristics of temperature changes before and after operations in actual physical processes. The membership competition mechanism allows multiple events to simultaneously express their association intentions to the same data point, and quantifies the degree of membership using a Gaussian decay function. This transforms traditional deterministic time-point matching into soft-decision based on event semantics, thereby selecting the most probable attribution from multiple candidate associations. This processing effectively absorbs the uncertainty caused by small-range timestamp deviations, and the output binding dataset is more temporally consistent with the understanding process, providing more reliable data input for temperature difference calculation and event chain integrity verification in dynamic temperature difference recovery determination.

[0077] In traditional processing paths, due to the lack of directional modeling of event influence, sensor data points are typically rigidly correlated with the most recent event record, leading to numerous misalignments. For example, after a disassembly event, the temperature gradually decreases, but a rigid correlation might incorrectly treat the higher temperature value before disassembly as the data after disassembly. In the scenario of maintaining a subway toilet, the accuracy of manually recorded timestamps and the sensor sampling period make such misalignments even more frequent. This invention introduces event semantics into asymmetric weights and semantic field membership degrees, biasing the time window according to the event's influence distribution. Furthermore, it simulates the decay of event influence over time using a membership decay function. Thus, without requiring additional high-precision time synchronization equipment, it uses computational methods to compensate for the timestamp inconsistency problem, significantly improving the accuracy of unequal-interval multi-source data alignment and the logical consistency of the event's temporal sequence.

[0078] For example, during train maintenance, maintenance personnel first record the interface disassembly event, followed by reassembly. Temperature sensors have only a few sampling points between these two events. A particular temperature data point may fall within the candidate range corresponding to both the disassembly and reassembly events. In this step, the system does not directly bind the data point to the most recent event. Instead, it combines the asymmetric time window configurations of the disassembly and reassembly events to compare the semantic field membership of the data point to both events. If the data point better matches the time position and event semantics of the temperature recovery phase after reassembly, it is bound as interface reassembly event-related data; if it does not fall within the influence range of any maintenance event, it is classified as a background state event. The resulting bound comprehensive dataset more accurately reflects the real event chain during the maintenance operation.

[0079] Step S30: Based on the bound comprehensive dataset, perform the interface reassembly integrity status determination task using the dynamic temperature difference recovery determination method, and output the interface reassembly integrity status value;

[0080] The dynamic temperature difference recovery judgment method in step S30 refers to a data processing method in which the computing device takes the set of temperature data points after disassembly, the set of temperature data points after reassembly, the current ambient temperature, the actual operation time of interface reassembly, event chain fragments, and the final inspection leak detection value from the bound comprehensive dataset as input, calculates the temperature recovery amount and the dynamic recovery judgment threshold, and outputs the interface reassembly integrity status value. Here, interface reassembly integrity does not only indicate whether the maintenance personnel have entered the reassembly event, but also whether the interface after disassembly exhibits a temperature state consistent with the working condition recovery pattern, whether it has a complete sequence of events from disassembly to reassembly to final inspection leak detection, and whether the final inspection leak detection value supports the interface sealing state. The dynamic temperature difference recovery judgment does not use a fixed temperature difference boundary, but rather combines the temperature state after disassembly, the temperature state after reassembly, the current ambient temperature, the actual operation time of interface reassembly, and the final inspection leak detection results to form a judgment basis suitable for the current operating conditions. The interface reassembly integrity status value is a structured output, which includes the judgment result, event chain fragments, background state temperature data point sequence, liquid level change analysis unit, and the mirror event time window range corresponding to the electric heat tracing test completion event. This structured status object breaks down the reassembly conclusion into multiple traceable components. Subsequent steps read the reassembly status with context, rather than a simple pass / fail statement lacking data source.

[0081] The dynamic temperature difference recovery judgment mechanism couples the assessment of reassembly integrity with the current ambient temperature and actual operation time, enabling the judgment threshold to be automatically adjusted according to operating conditions. When the ambient temperature is low, pipeline heat dissipation is accelerated, and the temperature recovery amount is naturally smaller. The dynamic threshold will be adjusted accordingly based on the ambient temperature compensation coefficient and the current ambient temperature to avoid misjudging incomplete reassembly due to insufficient temperature recovery. When the reassembly operation time is too long, resulting in additional heat loss, the dynamic threshold will be corrected based on the operation time compensation coefficient and the actual operation time of interface reassembly to ensure that the judgment takes into account the impact of the operation process. At the same time, the joint verification of event chain integrity and final inspection leakage value further constrains the operation process closure and physical sealing from two dimensions, avoiding misjudgments that may occur based on a single temperature difference indicator. The interface reassembly integrity status value output by this step not only includes the integrity conclusion but also encapsulates the temperature data and liquid level event units related to this judgment, so that these event-related data can be directly reused in subsequent freezing and leakage risk judgments.

[0082] Traditional methods for determining the integrity of interface reassembly typically use an empirically fixed temperature difference threshold. For example, a reassembled interface is considered to be in good condition if the temperature is higher than the disassembled interface by a fixed value. When rail transit vehicles operate across regions and seasons, ambient temperatures can vary by tens of degrees Celsius. In frigid environments, the fixed threshold is often too high, leading to intact interfaces being mistakenly judged as incomplete, requiring additional re-inspection. Conversely, in high-temperature environments, the threshold may be too low, overlooking cases of poor sealing. Furthermore, variations in reassembly time due to differences in operator skill are often ignored. This step introduces ambient temperature and operation time compensation through a dynamic threshold formula, automatically adjusting the judgment criteria according to objective conditions and reducing systemic biases caused by environmental and human factors. Simultaneously, the combined verification of event chain integrity and leak detection compensates for the shortcomings of traditional single temperature difference criteria, making the overall judgment more robust, especially maintaining high accuracy under extreme conditions.

[0083] For example, when a train enters the maintenance depot at night in winter, the interface of the target toilet system is disassembled and cleaned. After reassembly, although the pipe temperature begins to rise, the recovery is less than the experience value for normal temperature seasons due to the low temperature inside the depot. Traditional fixed thresholds may directly give a re-inspection prompt, requiring maintenance personnel to recheck the original records. Using step S30, the system extracts the set of temperature data points after disassembly and reassembly from the bound comprehensive dataset, while simultaneously reading the current ambient temperature, the actual reassembly operation time, and the final inspection leak detection value. If the event chain can form a complete sequence of interface disassembly, interface reassembly, and final inspection leak detection, and the final inspection leak detection value does not show any abnormalities, the system can output the interface reassembly integrity status value based on dynamic recovery judgment. Conversely, if the reassembly event exists but the final inspection leak detection is missing, or the liquid level change analysis unit shows abnormalities in subsequent risk entry points, this status value will also be retained as a basis for re-inspection, allowing step S40 to continue identifying leakage or freezing risks. In another scenario, the pipe temperature is high after the vehicle is parked in summer, and the temperature recovery after reassembly seems rapid, but the event chain lacks a final inspection leak detection record. Traditional methods might simply overlook an interface based solely on temperature recovery. Step S30, however, uses incomplete event timing as a basis for re-inspection, encapsulating the missing final inspection step along with the temperature data fragment into the interface reassembly integrity status value. Subsequent maintenance personnel can then directly identify the issue not as insufficient temperature recovery, but rather as a lack of final inspection closure in the event chain, providing a clearer direction for the review.

[0084] Step S40: Based on the interface reassembly integrity status value, the event-driven transient tolerance and liquid level response slope deviation joint judgment method is used to perform the freezing and leakage risk judgment task, and output a risk status combination value including freezing risk status value and leakage risk status value;

[0085] Step S40 addresses the freezing and leakage risks that are most likely to affect operational safety before release. Event-driven transient tolerance means that the system does not treat all cooling processes as freezing risks. Instead, it first identifies the mirrored event time window corresponding to the electric heat tracing test completion event in the interface reassembly integrity status value. Within this time window, a short-term temperature drop related to the test completion is allowed, and the triggering requirements for the continuous cooling cycle, cumulative cooling amplitude, and warning temperature boundary are temporarily adjusted. The joint determination of liquid level response slope deviation involves reading the liquid level change analysis unit, comparing the actual liquid level change trend with the ideal liquid level change trend under the corresponding valve operation type, and checking whether there are other valve action events during this time period. Only when the liquid level change deviates from the expectation and there is no normal valve action explanation is it considered an unexpected liquid level change and a leakage risk status value is generated. It is important to emphasize that freezing risk and leakage risk differ in data presentation, but both are easily affected by maintenance events. The risk of freezing depends on the continuous changes in the background temperature data point sequence; the temperature recovery phase after electric heat tracing testing cannot be mistaken for natural cooling. Similarly, the risk of leakage depends on the trend deviation of the liquid level change analysis unit; liquid level changes caused by normal valve operation cannot be mistaken for leakage. Therefore, this step uses event-driven mechanisms as a common constraint, placing the transient tolerance on the temperature side and the exclusion of valve operation on the liquid level side within the same risk assessment task, ensuring that the two risk state values ​​originate from the same source and are not isolated. This shared-source risk assessment method facilitates the subsequent unified reading of the two risk states using matrix rules. Thus, the two risk states share the same event basis.

[0086] By employing a combined event-driven transient tolerance and level response slope deviation mechanism, the assessment of freezing risk is no longer based solely on a single trigger of temperature drop. Instead, it incorporates the duration and cumulative magnitude of the drop, as well as comparisons with warning thresholds. Furthermore, it can identify special operating conditions such as electric heat tracing tests, temporarily relaxing conditions to tolerate normal temperature fluctuations. This reduces frequent false alarms triggered by brief temperature disturbances caused by testing operations, allowing freezing warnings to focus more on genuine pipeline freezing risks. For leak detection, an ideal level change slope model is introduced as a reference. By comparing the deviation between the actual slope and the ideal slope, it effectively distinguishes between expected level changes caused by normal valve actions and unexpected, continuous, slow level changes caused by pipeline leaks. Simultaneously, the absence of other valve action events serves as an exclusion condition, further reducing the possibility of misjudging normal flushing or water replenishment as leaks. The generation of independent tags allows for separate location of leakage risks in grey water and black water systems, making the information output to subsequent decision-making modules more targeted and facilitating rapid response by maintenance personnel.

[0087] Traditional freeze warning systems often rely on temperatures falling below a fixed threshold or simple cooling rates, failing to distinguish between normal operating fluctuations and genuine freezing trends. For example, alarms are easily triggered during the natural temperature drop period after electric heat tracing testing, leading to alarm fatigue among maintenance personnel and causing them to overlook real risks. For leak detection, traditional methods often rely on alarms triggered by exceeding absolute liquid level limits, unable to identify whether changes are caused by planned operations or slow leaks; minor leaks are often masked by normal water usage fluctuations. This step introduces an event-driven transient tolerance mechanism that automatically relaxes criteria using known test event labels, reducing predictable false alarms. Furthermore, slope deviation analysis based on an ideal operating model focuses on the morphological characteristics of the process, moving beyond just the magnitude of changes, thus enhancing sensitivity to small but continuous abnormal liquid level changes. These improvements collectively make risk assessment more accurate, reduce false alarm rates, and provide separate leak risk information for gray and black water tanks, laying the foundation for differentiated release and maintenance decisions. For instance, after maintenance personnel complete the electric heat tracing test, the pipeline temperature gradually drops from the test heating state within a short period. If only the continuous temperature drop is considered, the system might immediately trigger a freeze warning. However, in step S40, this cooling process falls within the mirror event time window corresponding to the completion of the electric heat tracing test. The system enters transient tolerance mode, temporarily increasing the continuous drop period and cumulative cooling trigger requirements, and then returns to the original conditions after the time window ends. For example, if the grey water tank level changes slowly and continuously during a period without recorded flushing, drainage, or water replenishment valve actions, and the actual level change trend significantly deviates from the ideal level response expected during that period, the system will not simply classify this change as normal fluctuation, but will generate a grey water tank-related leakage risk status value. The combination of these two risk judgments can be expressed as a specific combination state such as normal freezing risk but abnormal leakage risk, providing fine-grained basis for release decisions. Furthermore, within the overall preparation process, step S40 can handle situations where risks overlap. For example, if the interface reassembly integrity status is "complete," but the background temperature continuously decreases within the non-test time window and is approaching the warning boundary, a freezing risk status value should still be generated. Similarly, if the interface integrity is pending re-inspection, but the liquid level change is as expected under the corresponding valve's action, the leakage risk status value can be distinguished from the reassembly integrity issue. Through this combined output, subsequent release decisions no longer lump all anomalies together, but rather can allocate different review focuses based on the source of risk. This combined expression provides step S50 with more granular decision input than a single alarm. The risk conclusion corresponds to a specific temperature or liquid level segment, facilitating verification. This status combination also facilitates the distinction between immediate action and continued observation.

[0088] Step S50: Encapsulate the release decision based on the risk status combination value and the preset release result combination logic matrix, and output the release decision encapsulation object.

[0089] This step receives the frozen risk status value, grey water tank leakage risk status value, and black water tank leakage risk status value output from step S40, and writes these values ​​into a risk status combination value according to a preset field order. The risk status combination value includes a frozen risk status field, a grey water tank leakage status field, and a black water tank leakage status field. Each status field is represented by a binary status code: 0 indicates that the corresponding risk has not been triggered, and 1 indicates that the corresponding risk has been triggered.

[0090] The preset release result combination logic matrix is ​​a state mapping data table pre-stored in the vehicle preparation and release system. The state mapping data table uses the risk state combination value as the input index and outputs a release status field, an interface status code, and a handling prompt field. The release status field includes an allowed release status field, a restricted release status field, and a prohibited release status field. Specifically, when the frozen risk status field, the grey water tank leakage status field, and the black water tank leakage status field are all 0, the allowed release status field is output; when the frozen risk status field is 0 and only the grey water tank leakage status field or the black water tank leakage status field is 1, the restricted release status field is output, and a handling prompt field corresponding to the water tank that triggered the leakage risk is generated simultaneously; when the frozen risk status field is 1, or both the grey water tank leakage status field and the black water tank leakage status field are 1, the prohibited release status field is output.

[0091] After obtaining the release status field, this step encapsulates the processing data generated in steps S10 to S40 into a structured history field set. The processing data includes original maintenance records, sensor data streams, bound integrated datasets, temperature data point sets, reassembly integrity status values, risk assessment parameters, and intermediate calculation results. The structured history field set is used to record the data sources, data binding relationships, integrity assessment results, and risk assessment criteria used in the formation of the release status field.

[0092] Finally, this step packages the release status field, interface status code, handling prompt field, and structured history field into a release decision encapsulation object, and associates and stores this release decision encapsulation object with the unique identifier of the rail transit toilet system. The release decision encapsulation object is a status object readable by the maintenance system, and can be output through the work order system interface, train control and management system interface, or vehicle maintenance system interface. This allows the work order system, train control and management system, or vehicle maintenance system to read the release status field, interface status code, and handling prompt field, and trigger a maintenance release process, a maintenance work order generation process, or a prohibition on release prompt process accordingly.

[0093] It should be noted that the preset release result combination logic matrix is ​​not obtained by maintenance personnel on an ad-hoc basis, but rather by converting the frozen risk status field, gray water tank leakage status field, and black water tank leakage status field into field-based output results that the vehicle preparation and release system can recognize. By converting multiple risk statuses into unified release status fields, interface status codes, and handling prompt fields, consistent status data can be read by different vehicles, different preparation sites, and different operation and maintenance terminals, reducing the problem of inconsistent status output caused by differences in human experience.

[0094] Understandably, during the preparation of rail transit toilet systems, abnormal temperatures, abnormal liquid levels, and abnormal reinstallation status typically originate from different data acquisition and processing links. If only manual release decisions are recorded, they are difficult for work order systems, train control and management systems, or vehicle maintenance systems to directly access. This step generates a release decision encapsulation object, enabling the release status, risk sources, handling prompts, and process history to be synchronously output in structured field format, thereby improving the consistency and traceability of data transmission between systems.

[0095] It should be understood that the release decision encapsulation object can be stored and transmitted in the form of a JSON object, XML object, binary protocol object, or database record object. The release decision encapsulation object includes at least the following fields: toilet system unique identifier field, freeze risk status field, grey water tank leakage status field, black water tank leakage status field, release status field, interface status code field, handling prompt field, history index field, and generation time field. Through these field settings, the vehicle preparation and release system can directly parse the release status field, the work order system can directly parse the handling prompt field, the train control and management system can directly parse the interface status code field, and the vehicle maintenance system can retrieve the corresponding structured history field set through the history index field.

[0096] For example, after a train completes toilet preparation, a status is generated. Step S40 outputs a freeze risk status value of 0, a grey water tank leakage risk status value of 1, and a black water tank leakage risk status value of 0, resulting in a combined risk status value of [0, 1, 0]. After querying the preset release result combination logic matrix, the vehicle preparation release system writes a restricted release status field, generates an interface status code for the work order system to read, and generates a handling prompt field for checking the grey water tank pipeline interface and related sealing parts. Subsequently, the system encapsulates the restricted release status field, interface status code, handling prompt field, and structured history field set into a release decision encapsulation object. The structured history field set includes disassembly and reassembly operation information obtained from maintenance record parsing, the binding comprehensive dataset generated in step S20, the reassembly integrity status value output in step S30, and the grey water tank level slope deviation rate obtained in step S40. After the encapsulated release decision object is associated with and stored as a unique identifier of the rail transit toilet system, the work order system, train control and management system, or vehicle operation and maintenance system can read the restricted release status field and generate a corresponding maintenance work order or operation and maintenance prompt based on the disposal prompt field.

[0097] Example 2: Furthermore, the present invention provides a rail transit toilet system release status data processing system, which employs the rail transit toilet system release status data processing method and system described in the above embodiments, and can solve a technical problem in rail transit toilet system release status data processing. The beneficial effects of the rail transit toilet system release status data processing system provided by the present invention are the same as those of the rail transit toilet system release status data processing method and system provided in the above embodiments, and other technical features of the rail transit toilet system release status data processing system are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0098] Example 3: This invention provides a data processing device for the release status of a rail transit toilet system. The device includes at least one processor and a memory communicatively connected to the processor. The memory stores instructions executable by the processor, which are then executed to enable the processor to perform the data processing method and system for the release status of a rail transit toilet system described in Example 1. The data processing device for the release status of a rail transit toilet system in this invention may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. This data processing device for the release status of a rail transit toilet system is merely an example and should not be construed as limiting the functionality or scope of the invention. A rail transit toilet system release status data processing device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory or a program loaded from a storage device into a random access memory. The random access memory also stores various programs and data required for the operation of the rail transit toilet system release status data processing device. The processing unit, the read-only memory, and the random access memory are interconnected via a bus. An I / O interface is also connected to the bus. Typically, the following systems can be connected to the I / O interface: input devices including touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices including liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices including magnetic tapes, hard disks, etc.; and communication devices. The communication device allows the rail transit toilet system release status data processing device to communicate wirelessly or wiredly with other devices to exchange data. Although a rail transit toilet system release status data processing device with various systems has been described, it should be understood that it is not required to implement or possess all the systems described. More or fewer systems may be implemented alternatively.

[0099] Example 4: This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method and system for processing release status data of a rail transit toilet system. The computer program product provided by this invention can solve a technical problem related to processing release status data of a rail transit toilet system. Compared with the prior art, the beneficial effects of the computer program product provided by this invention are the same as those of the method and system for processing release status data of a rail transit toilet system provided in the above embodiments, and will not be repeated here.

[0100] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a read-only memory. When the computer program is executed by a processing device, it performs the functions defined in the methods of the embodiments disclosed in this invention.

[0101] It should be understood that the various parts disclosed in this invention can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0102] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the present invention and its equivalents, the present invention also intends to include these modifications and variations.

Claims

1. A method for processing release status data of a rail transit toilet system, characterized in that, The methods include: Step S10: Obtain maintenance behavior records and operating condition sensor data streams associated with the unique identifier of the overall toilet system of rail transit. Based on the maintenance behavior records, perform time-stamped association processing on the operating condition sensor data streams using an event time window mirror back projection method, and output time-stamped multi-source basic datasets. Step S20: Based on the timestamped multi-source basic dataset, perform the event attribution binding task using the asymmetric semantic field membership degree competition binding method, and output a comprehensive binding dataset arranged by time axis and labeled with event attribution type; Step S30: Based on the bound comprehensive dataset, perform the interface reassembly integrity status determination task using the dynamic temperature difference recovery determination method, and output the interface reassembly integrity status value; Step S40: Based on the interface reassembly integrity status value, the event-driven transient tolerance and liquid level response slope deviation joint judgment method is used to perform the freezing and leakage risk judgment task, and output a risk status combination value including freezing risk status value and leakage risk status value; Step S50: Encapsulate the release decision based on the risk status combination value and the preset release result combination logic matrix, and output the release decision encapsulation object.

2. The method for processing release status data of a rail transit toilet system as described in claim 1, characterized in that, Step S10 involves acquiring maintenance behavior records and operational sensor data streams associated with the unique identifier of the overall rail transit toilet system. Based on the maintenance behavior records, a time-stamped association processing task is performed on the operational sensor data streams using an event time window mirroring method, outputting a time-stamped multi-source basic dataset. This step specifically includes: Step S101: Using the unique identifier of the rail transit integrated toilet system as an index, read the maintenance behavior record corresponding to the rail transit integrated toilet system from the maintenance database, and read the corresponding working condition sensor data stream from the working condition sensor database; Step S102: Parse the operation timestamp and behavior event type for each maintenance behavior record to form a behavior event record with operation timestamp and behavior event type; Step S103: Write a collection timestamp to each data point in the working condition sensor data stream, and generate associated event labels for the data points according to the behavior event records, forming a timestamped multi-source basic dataset containing the behavior event records and data points with associated event labels.

3. The method for processing release status data of a rail transit toilet system as described in claim 1, characterized in that, Step S20, which involves performing the event attribution binding task based on the timestamped multi-source basic dataset using an asymmetric semantic field membership competition binding method, and outputting a comprehensive binding dataset arranged along the time axis and labeled with event attribution types, specifically includes: Step S201: Extract behavioral event records and sensor data points from the timestamped multi-source basic dataset. For each behavioral event type, preset the time window radius, the weight of the first period, and the weight of the second period. The sum of the weight of the first period and the weight of the second period is 1. The weight of the first period of the interface disassembly event is greater than the weight of the second period, and the weight of the second period of the interface reassembly event is greater than the weight of the first period. Step S202: Generate a mirrored event time window for each behavior event record: In the formula, Represents behavioral events The corresponding mirror event time window, Represents behavioral events Operation timestamp Indicates the radius of the time window. This indicates the weight over a certain period of time. Indicates the weight of the later period; Step S203: When the acquisition timestamp of any sensor data point falls within one or more mirror event time windows, calculate the semantic field membership degree of that sensor data point to each corresponding behavioral event: In the formula, Represents sensor data points behavioral events semantic field membership degree Represents sensor data points The collection timestamp, This represents the normalized time offset. This represents the membership attenuation width parameter; Step S204: Compare the semantic field membership values ​​corresponding to the same sensor data point, bind the sensor data point to the behavior event with the largest semantic field membership value, bind the sensor data points that do not fall into any mirror event time window to the background state event, and form a bound comprehensive dataset arranged by time axis and labeled with the event belonging type.

4. The method for processing release status data of a rail transit toilet system as described in claim 3, characterized in that, In step S202, when generating a mirror event time window for each behavior event record, the preceding time weight and the following time weight are configured according to the interface disassembly event, the interface reassembly event, and the electric heat tracing test completion event, respectively. This causes the mirror event time window corresponding to the interface disassembly event to shift to the time period before the operation timestamp, the mirror event time window corresponding to the interface reassembly event to shift to the time period after the operation timestamp, and the mirror event time window corresponding to the electric heat tracing test completion event to maintain symmetry with respect to the operation timestamp.

5. The method for processing release status data of a rail transit toilet system as described in claim 1, characterized in that, Step S30, which involves performing an interface reassembly integrity status determination task based on the bound comprehensive dataset using a dynamic temperature difference recovery determination method and outputting the interface reassembly integrity status value, specifically includes: Step S301: Extract the following sets of temperature data points after interface disassembly event, interface reassembly event, electric heat tracing temperature data points after electric heat tracing test completion event, background state temperature data point sequence corresponding to background state event, liquid level change analysis unit, final inspection leak detection value, and mirror event time window range corresponding to electric heat tracing test completion event from the binding comprehensive dataset to form event chain segments. Step S302: Calculate the average temperature after disassembly, the average temperature after reassembly, and the temperature recovery amount: In the formula, This indicates the average temperature after disassembly. This indicates the average temperature after reassembly. Indicates the amount of temperature recovery. This indicates the number of temperature data points after disassembly. This indicates the number of temperature data points after reassembly. Indicates the first Temperature values ​​collected after disassembly Indicates the first Temperature values ​​collected after reassembly; Step S303: Calculate the dynamic recovery judgment threshold: In the formula, This indicates the threshold for dynamic recovery determination. Indicates the baseline recovery temperature difference threshold. Indicates the reference ambient temperature. This indicates the current ambient temperature obtained from the vehicle's environmental sensors. This represents the ambient temperature compensation coefficient. This indicates the actual operation time for interface reinstallation, calculated from the timestamp intervals of the maintenance behavior records. Indicates the standard operation time. This represents the operation time compensation coefficient; Step S304: When the temperature recovery amount is greater than or equal to the dynamic recovery judgment threshold, the event sequence in the event chain segment includes the complete sequence from the interface disassembly event to the interface reassembly event to the final inspection leakage detection event, and the final inspection leakage detection value is lower than the preset leakage threshold, the interface reassembly integrity judgment result is assigned the value of complete. Step S305: When the temperature recovery amount is less than the dynamic recovery judgment threshold, or the event sequence in the event chain segment does not contain the complete sequence from the interface disassembly event to the interface reassembly event to the final inspection leakage detection event, or the final inspection leakage detection value is greater than or equal to the preset leakage threshold, the interface reassembly integrity judgment result is assigned as pending re-inspection. Step S306: Encapsulate the interface reassembly integrity judgment result, the event chain fragment, the background state temperature data point sequence, the liquid level change analysis unit, and the mirror event time window range corresponding to the electric heat tracing test completion event into an interface reassembly integrity status value output.

6. The method for processing release status data of a rail transit toilet system as described in claim 1, characterized in that, In step S40, the step of performing the freezing and leakage risk assessment task based on the interface reassembly integrity status value using an event-driven transient tolerance and liquid level response slope deviation joint judgment method, and outputting a risk status combination value including freezing risk status value and leakage risk status value, specifically includes: Step S401: Extract the background state temperature data point sequence from the interface reassembly integrity state value. When the background state temperature data point sequence is in continuous... When the temperature shows a monotonically decreasing trend within a single data collection cycle, the cumulative temperature drop exceeds a preset cumulative temperature drop threshold, and the current temperature is below a preset warning temperature threshold, a freezing risk warning is triggered, and a freezing risk status value is generated. This indicates the number of descent cycles, and the preset cumulative cooling threshold indicates continuous... The maximum cumulative temperature drop allowed within a collection cycle, wherein the preset warning temperature threshold represents the temperature boundary value that triggers a freezing risk warning; Step S402: Enter transient tolerance mode within the mirror event time window corresponding to the electric heat tracing test completion event in the interface reassembly integrity status value, and temporarily increase the continuous descent cycle number requirement, increase the cumulative cooling judgment boundary, and lower the warning temperature boundary in the transient tolerance mode. After the mirror event time window ends, restore the corresponding original triggering conditions. Step S403: Extract the liquid level change analysis unit from the interface reassembly integrity status value, and calculate the actual liquid level change slope and slope deviation rate: In the formula, This represents the slope of the actual liquid level change. This indicates the actual change in liquid level. This indicates the time span of the liquid level change analysis unit. Indicates the slope deviation rate. This indicates the ideal liquid level change slope corresponding to the preset valve operation type. Step S404: When the slope deviation rate is greater than the preset deviation tolerance threshold and no other valve action event occurs in the liquid level change analysis unit, it is determined to be an unexpected liquid level change including the independent labels of the gray water tank and the black water tank, and a leakage risk status value is generated; the freezing risk status value and the leakage risk status value are encapsulated into a risk status combination value and output.

7. The method for processing release status data of a rail transit toilet system as described in claim 1, characterized in that, Step S50, which involves encapsulating the release decision based on the risk status combination value and the preset release result combination logic matrix, and outputting the release decision encapsulation object, specifically includes: Step S501: Using the risk status combination value as input, query the preset release result combination logic matrix, and output a release result including allow release, restrict release, or prohibit release; Step S502: Encapsulate the release result, the risk status combination value, and the processing data generated in steps S10 to S40 into a risk encapsulation object; Step S503: Encapsulate the release result and the risk encapsulation object into a release decision encapsulation object, and associate and store the release decision encapsulation object with the unique identifier of the rail transit overall toilet system.

8. A data processing system for the release status of a rail transit toilet system, applied to the data processing method for the release status of a rail transit toilet system as described in any one of claims 1 to 7, characterized in that, The rail transit toilet system release status data processing system includes: The multi-source data acquisition module is used to acquire maintenance behavior records and operating condition sensor data streams associated with the unique identifier of the overall toilet system of rail transit. Based on the maintenance behavior records, the operating condition sensor data streams are processed by time-stamping association using an event time window mirroring back projection method, and the time-stamped multi-source basic dataset is output. The event attribution binding module is used to perform the event attribution binding task based on the timestamped multi-source basic dataset using an asymmetric semantic field membership degree competitive binding method, and outputs a binding comprehensive dataset arranged by time axis and labeled with event attribution type; The interface reassembly integrity determination module is used to perform an interface reassembly integrity status determination task based on the bound comprehensive dataset using a dynamic temperature difference recovery determination method, and output the interface reassembly integrity status value. The freezing and leakage risk assessment module is used to perform freezing and leakage risk assessment tasks based on the integrity status value of the interface and adopt an event-driven transient tolerance and liquid level response slope deviation joint assessment method, and output a risk status combination value including freezing risk status value and leakage risk status value. The release decision encapsulation module is used to encapsulate the release decision based on the risk status combination value and the preset release result combination logic matrix, and output the release decision encapsulation object.

9. A data processing device for the release status of a rail transit toilet system, characterized in that, The rail transit toilet system release status data processing device includes: a memory, a processor, and a rail transit toilet system release status data processing program stored in the memory and executable on the processor. When the rail transit toilet system release status data processing program is executed by the processor, it implements a rail transit toilet system release status data processing method according to any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a rail transit toilet system release status data processing program, which, when executed by a processor, implements a rail transit toilet system release status data processing method according to any one of claims 1 to 7.

Images