Fault single processing method and device, storage medium and electronic equipment

Abstract

The application discloses a kind of fault single processing method, device, storage medium and electronic equipment.It relates to the field of departure control, which comprises: collecting the text in target maintenance fault single, to obtain target fault single text, wherein the target maintenance fault single includes: the fault seat on target aircraft contains the description information of to-be-processed fault single;The target fault information is obtained by inputting the target fault single text into the target language model, wherein the target language model is used for semantic recognition and information extraction on the target fault single text;Based on the target fault information, the fault type of the fault seat is determined;Based on the fault type of the fault seat, seat operation is carried out on the fault seat in the departure system, wherein the seat operation includes one of the following: seat locking, seat fault marking.The application solves the technical problem of low processing efficiency of manual analysis and processing of seat fault single data.

Description

Technical Field

[0001] This invention relates to the field of departure control, and more specifically, to a method, apparatus, storage medium, and electronic device for processing fault reports. Background Technology

[0002] Currently, aircraft fault reports are geared towards aircraft maintenance, describing only problems with aircraft components. The causes of these faults are presented in unstructured, free-form text. For example, fault reports are often filled out by maintenance personnel in free-form text, resulting in a mix of languages, diverse descriptions, and a lack of standardized structure. When a fault report is sent to the departure terminal, service staff must manually screen it to determine if it relates to a faulty seat, manually parse the seat malfunction information, input it into a structured system, and then synchronize it to the departure system. This process has the following drawbacks:

[0003] (1) Manual analysis is inefficient, with an average analysis time of 1-2 minutes per fault, which cannot meet the real-time requirements of the departure system.

[0004] (2) Manual analysis is prone to errors, especially the splitting of multi-seat combination labels and the understanding of professional fault terms, which can easily lead to errors in the entry of fault seat information.

[0005] (3) Fault information cannot be synchronized with the departure system in real time, which may cause passengers to select faulty seats at check-in, leading to passenger complaints and affecting the quality of civil aviation services.

[0006] There is currently no effective solution to the above problems. Summary of the Invention

[0007] This invention provides a method, apparatus, storage medium, and electronic device for processing fault reports, in order to at least solve the technical problem of low processing efficiency in the manual analysis and processing of data in seat fault reports in related technologies.

[0008] According to one aspect of the present invention, a method for processing fault reports is provided, comprising: acquiring text from a target aircraft maintenance fault report to obtain target fault report text, wherein the target aircraft maintenance fault report includes a fault report to be processed containing descriptive information of a faulty seat on a target aircraft; inputting the target fault report text into a target language model to obtain target fault information, wherein the target language model is used to perform semantic recognition and information extraction on the target fault report text; determining the fault type of the faulty seat based on the target fault information; and performing seat operations on the faulty seat in a departure system based on the fault type of the faulty seat, wherein the seat operations include one of the following: seat locking and seat fault marking.

[0009] Further, the fault type includes one of the following: a first fault type and a second fault type. The first fault type includes seats that are unusable, and the second fault type includes seats whose fault does not affect occupancy. Based on the fault type of the faulty seat, seat operation is performed on the faulty seat in the departure system, including: performing structured processing on the fault type of the faulty seat and the target fault information to obtain structured fault information; if the fault type of the faulty seat is a first type of fault, locking the seat of the faulty seat in the departure system based on the structured fault information; if the fault type of the faulty seat is a second type of fault, marking the seat as faulty in the departure system based on the structured fault information.

[0010] Furthermore, if the faulty seat is classified as a Type II fault, after performing seat operation on the faulty seat in the departure system based on the faulty seat type, the process further includes: generating a fault prompt message when the target person selects the faulty seat during check-in for the target aircraft, wherein the fault prompt message includes: the cause of the fault and an informed consent form; visually displaying the fault prompt message; and processing check-in for the target person if the target person signs the informed consent form.

[0011] Further, the target fault information includes at least one of the following: the seat identification of the faulty seat, the faulty component, and the fault phenomenon. Based on the target fault information, determining the fault type of the faulty seat includes: obtaining a preset judgment rule, wherein the preset judgment rule includes: a mapping relationship between the fault information of the aircraft seat and the fault type; and determining the fault type of the faulty seat based on the target fault information and the preset judgment rule.

[0012] Further, the target language model is obtained by: acquiring corpus samples from a fault corpus, wherein the fault corpus includes: aircraft seat fault reports with fault labeling information; training an initial language model based on the corpus samples until a preset convergence condition is met, and determining the initial language model trained in the last training as the target language model, wherein the type of the initial language model includes: a large language model to be trained.

[0013] Furthermore, after performing a seating operation on the faulty seat in the departure system based on the fault type of the faulty seat, the method further includes: collecting feedback correction data from the departure system, wherein the feedback correction data includes at least one of the following: data on the seating operation result of the faulty seat and data on the target object; and adding the feedback correction data to the fault corpus.

[0014] Furthermore, the process of training the initial language model based on the corpus samples also includes: initializing the model parameters of the initial language model to obtain an initialized language model; and training the initialized language model using a low-rank adaptation strategy based on the corpus samples.

[0015] According to another aspect of the present invention, a fault report processing apparatus is also provided, comprising: a first acquisition unit, configured to acquire text from a target aircraft maintenance fault report to obtain target fault report text, wherein the target aircraft maintenance fault report includes: a fault report to be processed containing descriptive information of a faulty seat on a target aircraft; a processing unit, configured to input the target fault report text into a target language model to obtain target fault information, wherein the target language model is used to perform semantic recognition and information extraction on the target fault report text; a determination unit, configured to determine the fault type of the faulty seat based on the target fault information; and an operation unit, configured to perform seat operation on the faulty seat in a departure system based on the fault type of the faulty seat, wherein the seat operation includes one of the following: seat locking, seat fault marking.

[0016] Further, the fault type includes one of the following: a first fault type and a second fault type. The first fault type includes seats that are unusable, and the second fault type includes seats whose fault does not affect occupancy. The operation unit includes: a processing subunit for performing structured processing on the fault type of the faulty seat and the target fault information to obtain structured fault information; a locking subunit for locking the seat of the faulty seat in the departure system based on the structured fault information when the fault type of the faulty seat is a first type of fault; and a marking subunit for marking the seat of the faulty seat in the departure system based on the structured fault information when the fault type of the faulty seat is a second type of fault.

[0017] Furthermore, the fault ticket processing device also includes: a generation unit, used to generate fault prompt information when the fault seat's fault type is a second type of fault, after performing seating operations on the fault seat based on the fault seat's fault type, and when the target object selects the fault seat during check-in for the target aircraft, wherein the fault prompt information includes: the cause of the fault and an informed consent form; and a processing unit, used to visualize the fault prompt information and process the check-in procedures for the target object when the target object signs the informed consent form.

[0018] Further, the target fault information includes at least one of the following: the seat identification of the faulty seat, the faulty component, and the fault phenomenon. The determining unit includes: a first acquisition subunit, used to acquire a preset judgment rule, wherein the preset judgment rule includes: a mapping relationship between the fault information of the aircraft seat and the fault type; and a determining subunit, used to determine the fault type of the faulty seat based on the target fault information and the preset judgment rule.

[0019] Further, the target language model is obtained through the following sub-units: a second acquisition sub-unit, used to acquire corpus samples in a fault corpus, wherein the fault corpus includes: aircraft seat fault reports with fault labeling information; and a training sub-unit, used to train an initial language model based on the corpus samples until a preset convergence condition is met, and to determine the initial language model trained in the last training as the target language model, wherein the type of the initial language model includes: a large language model to be trained.

[0020] Furthermore, the fault ticket processing device further includes: a collection unit, used to collect feedback correction data of the departure system after performing a seating operation on the faulty seat in the departure system based on the fault type of the faulty seat, wherein the feedback correction data includes at least one of the following: data on the seating operation result of the faulty seat and the data on the target object that are corrected; and an adding unit, used to add the feedback correction data to the fault corpus.

[0021] Furthermore, the training subunit also includes: an initialization module, used to initialize the model parameters of the initial language model during the model training process based on the corpus samples, to obtain an initialized language model; and a training module, used to train the initialized language model based on the corpus samples using a low-rank adaptation strategy.

[0022] According to another aspect of the present invention, an electronic device is also provided, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform a fault ticket processing method of any of the above-mentioned methods by executing the executable instructions.

[0023] According to another aspect of the present invention, a computer-readable storage medium is also provided, which stores a computer program, wherein the computer program controls the device where the computer-readable storage medium is located to execute the fault report processing method described above when the computer program is running.

[0024] In this invention, the following method is adopted: Text is collected from the target aircraft fault report to obtain the target fault report text, wherein the target aircraft fault report includes a fault report to be processed containing descriptive information of a faulty seat on the target aircraft; the target fault report text is input into a target language model to obtain target fault information, wherein the target language model is used for semantic recognition and information extraction of the target fault report text; based on the target fault information, the fault type of the faulty seat is determined; based on the fault type of the faulty seat, seat operations are performed on the faulty seat in the departure system, wherein the seat operations include one of the following: seat locking, seat fault marking. This solves the technical problem of low processing efficiency caused by manual parsing and processing of data in seat fault reports in related technologies. In this invention, fault information is extracted from the aircraft seat fault report using a language model, and seat operations are performed in the departure system based on the extraction results. This avoids the low efficiency of manual parsing of seat fault report information, which can lead to passengers selecting faulty seats during check-in, affecting passenger experience. Therefore, this invention achieves the technical effects of improving the processing efficiency of seat fault reports and improving passenger experience. Attached Figure Description

[0025] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0026] Figure 1 This is a flowchart of an optional fault ticket processing method according to an embodiment of the present invention;

[0027] Figure 2 This is a schematic diagram of an optional fault ticket processing system according to an embodiment of the present invention;

[0028] Figure 3 This is a schematic diagram of an optional fault ticket processing device according to an embodiment of the present invention;

[0029] Figure 4 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] It should be noted that the user information (including but not limited to user device information, user personal information, etc.), the collected information and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws and standards of the relevant regions, have taken necessary measures, do not violate public order and good morals, and provide corresponding operation portals for users to choose to authorize or refuse.

[0033] Example 1

[0034] According to an embodiment of the present invention, an optional method embodiment for processing fault tickets is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] Figure 1 This is a flowchart of an optional fault ticket processing method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0036] Step S101: Collect the text from the target aircraft maintenance fault report to obtain the target fault report text. The target aircraft maintenance fault report includes: a fault report to be processed containing descriptive information of the faulty seats on the target aircraft.

[0037] The aforementioned target maintenance fault report can refer to a document that records aircraft seat malfunctions. In this embodiment, the target maintenance fault report can be selected from all maintenance fault reports (documents that record malfunctions of various aircraft components).

[0038] For example, free text data (corresponding to the target fault report text) of aircraft maintenance fault reports (corresponding to the target fault report text) can be collected in real time from the aircraft maintenance system. The free text data includes various descriptive forms such as mixed Chinese and English, single / multiple seat faults, and whole aircraft faults.

[0039] Step S102: Input the target fault single text into the target language model to obtain the target fault information. The target language model is used to perform semantic recognition and information extraction on the target fault single text.

[0040] The aforementioned target language model can refer to a large language model fine-tuned using a civil aviation seat malfunction corpus, or a deep learning model.

[0041] By inputting free text data into the target language model for semantic recognition, core information related to seat malfunctions is automatically extracted to obtain target malfunction information. Core information may include, but is not limited to, seat identification, faulty components, and malfunction phenomena. This avoids the need for manual analysis of seat malfunction information, and achieves automated and high-precision extraction of seat malfunction features. It provides a standardized and structured data foundation for subsequent malfunction type determination and departure system linkage, improving analysis efficiency and accuracy.

[0042] In one alternative example, extracting seat identifiers can include multi-seat splitting logic. For example, when the target fault report text contains a combination of seat identifiers such as numbers + consecutive letters, single numbers, numbers - numbers, numbers - numbers + consecutive letters, or numbers + (letters - letters), it is split into multiple independent seat numbers. The splitting rule is "numbers + single letters", and the association between the original fault information and each seat number after splitting is preserved.

[0043] Step S103: Based on the target fault information, determine the fault type of the faulty seat.

[0044] The types of failures may include, but are not limited to: Type 1 failure (i.e., Class A failure) and Type 2 failure (i.e., Class C failure). Type 1 failure seats include: seats that cannot be sat on. Specifically, the criteria for determining Type 1 failure seats can be: the failure phenomenon is that the seat is completely unusable, the core function is completely failed, and there is no temporary repair solution. This includes, but is not limited to, the seat armrests / backrests being completely stuck and unable to be adjusted, and the seat structure being damaged.

[0045] The second type of seat malfunction includes seats whose malfunction does not affect occupancy (i.e., seats are usable by passengers). Specifically, the criteria for determining the second type of seat malfunction can be as follows: when the malfunction is that part of the seat is not functioning properly, but can meet basic occupancy needs after temporary repair, or the malfunction can be retained and passengers need to sign an exemption (i.e., informed consent), it is determined to be the second type of malfunction, including but not limited to entertainment screen malfunction, tray table tilting and fixing, and seat back adjustment malfunction but fixed in a usable position.

[0046] In this embodiment, the target fault information can be judged by the fault type based on the preset fault judgment rule base. The fault types are divided into Class A faults (passengers are not available and cannot take the ride) and Class C faults (passengers are available, that is, there is a fault but it does not affect the ride).

[0047] Step S104: Based on the fault type of the faulty seat, perform seat operation on the faulty seat in the departure system, wherein the seat operation includes one of the following: seat locking, seat fault marking.

[0048] In this embodiment, the external passenger version of the fault cause and the internal detailed fault cause can be separated according to the preset expression rules. Combined with the target fault information and fault type, standardized structured fault seat data can be generated. The structured fault information can be pushed to the departure system in real time through a preset interface. The departure system performs the corresponding seat operation according to the fault type. For example, the seat locking operation is directly performed for the first fault type seat, and the fault marking operation is performed for the second fault type seat, so as to avoid the situation where passengers select unavailable seats during the check-in process.

[0049] Through the above steps, in this embodiment, fault information in the aircraft seat fault report is extracted using a language model, and seat operations are performed in the departure system based on the extraction results. This avoids the inefficiency of manually parsing seat fault report information, which could lead to passengers selecting faulty seats during check-in, thus affecting their experience. Therefore, this method improves the efficiency of seat fault report processing and enhances the passenger experience. It also solves the technical problem of low processing efficiency caused by manual parsing and processing of data in seat fault reports in related technologies.

[0050] Optionally, in the fault ticket processing method provided in this embodiment of the invention, the fault type includes one of the following: a first fault type and a second fault type. The first fault type includes seats that cannot be sat on, and the second fault type includes seats whose fault does not affect occupancy. Based on the fault type of the faulty seat, seat operation is performed on the faulty seat in the departure system, including: performing structured processing on the fault type and target fault information of the faulty seat to obtain structured fault information; if the fault type of the faulty seat is a first type of fault, locking the seat of the faulty seat in the departure system based on the structured fault information; if the fault type of the faulty seat is a second type of fault, marking the seat fault in the departure system based on the structured fault information.

[0051] The structured faulty seat information mentioned above can be in JSON format and can include fields such as: seat number, fault type, fault cause for external passengers, and detailed fault cause for internal passengers. When the free text data is related to faults of seats throughout the entire aircraft, structured data covering the corresponding seat type of the entire aircraft is generated and marked as faults of the entire aircraft.

[0052] In this embodiment, structured fault information can be pushed to the departure system in real time through a preset interface. The departure system performs corresponding seat operations according to the fault type: for the faulty seat of the first fault type, a locking operation can be directly performed; for the faulty seat of the second fault type, a fault marking operation can be performed. The preset interface can be an API (Application Programming Interface) based on HTTP (Hypertext Transfer Protocol) / HTTPS (Hypertext Transfer Protocol Secure). After receiving the structured fault information data, the departure system can visually mark the faulty seat in the seat resource list and prohibit passengers from selecting the first faulty seat at check-in. When passengers check in for the second faulty seat, a fault prompt can be displayed and passengers can be asked to confirm the exemption (i.e., sign an informed consent form). If the passenger does not confirm the exemption, the passenger can choose other seats.

[0053] Optionally, in the fault ticket processing method provided in this embodiment of the invention, when the fault type of the faulty seat is a second type of fault, after performing seat operation on the faulty seat in the departure system based on the fault type of the faulty seat, the method further includes: generating fault prompt information when the target object selects the faulty seat during the check-in process of the target aircraft, wherein the fault prompt information includes: the cause of the fault and an informed consent form; visually displaying the fault prompt information; and processing the check-in procedures for the target object after the target object signs the informed consent form.

[0054] If a passenger actively selects or is assigned to the faulty seat during the check-in process, a fault message can be generated immediately. This message can include two parts: ① the cause of the fault (a concise and easy-to-understand external version, such as "Entertainment system unavailable"); ② informed consent form (i.e., signing a waiver).

[0055] The aforementioned fault information can be displayed as a visual pop-up on check-in terminals (such as self-service machines or counter screens) to ensure that the target passenger is fully aware of the seat condition. After the target passenger reads and signs the informed consent form (electronic confirmation exempts them from liability), check-in for that seat can continue. If the target passenger refuses to sign, they can be guided to reselect a seat or manual intervention can be provided. This ensures that passengers voluntarily bear some inconvenience with full knowledge, avoiding passenger complaints due to seat malfunctions, reducing seat waste through differentiated handling, improving the flexibility of flight operations, and enhancing the passenger service experience.

[0056] Optionally, in the fault report processing method provided in this embodiment of the invention, the target fault information includes at least one of the following: seat identification of the faulty seat, faulty component, and fault phenomenon. Based on the target fault information, the fault type of the faulty seat is determined, including: obtaining a preset judgment rule, wherein the preset judgment rule includes: a mapping relationship between the fault information of the aircraft seat and the fault type; and determining the fault type of the faulty seat based on the target fault information and the preset judgment rule.

[0057] The criteria for determining the first type of seat malfunction are as follows: A seat is considered to be completely unusable, with its core functions utterly disabled, and no temporary repair solution is available. This includes, but is not limited to, seats with armrests / backrests completely stuck and unable to be adjusted, or seats with structural damage. The criteria for determining the second type of seat malfunction are as follows: A seat is considered to be in the second type of malfunction if some functions are disabled, but basic seating needs can be met after temporary repair, or if the malfunction can be retained and a waiver (i.e., informed consent) is required from the passenger. This includes, but is not limited to, entertainment screen malfunctions, tray tables that are tilted and fixed, and seat back adjustment malfunctions that are fixed in a usable position.

[0058] In this embodiment, the target fault information can be matched with preset judgment rules. The system extracts component and phenomenon keywords from the target fault information, searches for corresponding mapping relationships in the rule base, and thus automatically determines whether the seat belongs to the first fault type or the second fault type. This achieves automation and standardization of fault classification, providing a basis for differentiated seat locking or marking operations in the subsequent departure system.

[0059] Optionally, in the fault report processing method provided in this embodiment of the invention, the target language model is obtained in the following way: acquiring corpus samples in the fault corpus, wherein the fault corpus includes: aircraft seat fault reports with fault labeling information; training the initial language model based on the corpus samples until a preset convergence condition is met, and determining the initial language model trained in the last training as the target language model, wherein the type of the initial language model includes: a large language model to be trained.

[0060] The fault corpus can be constructed through the following process: collecting free text of historical seat fault reports from civil aviation maintenance personnel, annotating the core information of seat faults, classifying faults into A / C categories, breaking down internal and external fault causes, and adding knowledge corpora such as civil aviation seat terminology, seat numbering rules, and fault type definitions.

[0061] Large language models can be: deep neural network models based on the Transformer architecture, such as the Deep Search model.

[0062] In this embodiment, a general initial language model (i.e., the large language model to be trained) is used as the base, and fine-tuning training is performed using the aforementioned fault corpus samples. The training process can employ efficient parameter fine-tuning techniques (such as LoRA low-rank adaptation). By calculating the loss function and backpropagating to update the model parameters, the model gradually acquires the ability to extract core information and determine fault types from unstructured text. Training stops when the loss function during training decreases to a preset threshold or reaches a specified number of rounds, i.e., when the preset convergence condition is met. The output model at this point is the target language model. The target language model obtained through training can accurately handle complex scenarios such as multilingual mixing and multi-seat splitting, providing technical support for automatic fault ticket parsing.

[0063] Optionally, in the fault ticket processing method provided in the embodiments of the present invention, after performing seat operation on the faulty seat in the departure system based on the fault type of the faulty seat, the method further includes: collecting feedback correction data of the departure system, wherein the feedback correction data includes at least one of the following: data on the seat operation result of the faulty seat and the target object for correction; and adding the feedback correction data to the fault corpus.

[0064] After the departure system completes the locking or marking operation, the following data can be collected: the success / failure status of the locking / marking operation of the departure system, the manually corrected error parsing results (such as incorrect seat number splitting, incorrect fault type determination), and the description text of newly added fault types. After the data is cleaned and labeled, it is added to the "fault corpus" as new training samples. The incremental training method is used to optimize the dedicated large language model and correct the historical misconceptions of the model.

[0065] In one alternative example, the target language model can be retrained periodically or incrementally by re-feeding the updated fault corpus. This allows it to absorb new fault description patterns and correct recognition biases, thereby continuously improving its generalization ability and recognition accuracy for complex scenarios (such as novel seat faults and special expression habits). Simultaneously, manually corrected data can also be used to optimize preset judgment rules. This achieves a shift from "passive execution" to "active evolution," ensuring the target language model adapts to changes in civil aviation operations over the long term, reducing maintenance costs, and guaranteeing the accuracy and timeliness of faulty seat management.

[0066] Optionally, in the fault ticket processing method provided in the embodiments of the present invention, during the process of training the initial language model based on corpus samples, the method further includes: initializing the model parameters of the initial language model to obtain the initialized language model; and training the initialized language model based on corpus samples using a low-rank adaptation strategy.

[0067] At the start of training, the parameters of the initial language model can be initialized, such as loading pre-trained weights and configuring hyperparameters such as optimizer, learning rate, and batch size. This prepares the model for entering the training state and ensures that the model has a stable initial state to begin learning. Secondly, a low-rank adaptation strategy can be used for training, updating only a small number of adapter parameters, so that the model can efficiently learn specific knowledge in the field of civil aviation seat faults (such as professional terminology, multi-seat splitting logic, and fault determination rules).

[0068] For example, the initial language model can be fine-tuned using the low-rank adaptation LoRA method, with fine-tuning parameters including a learning rate of 2e-4 to 5e-4 and 3 to 5 training epochs, freezing the backbone parameters of the model and training only the adapter layer.

[0069] It should be noted that the processing method provided in this embodiment is not only applicable to seat fault identification of civil aircraft, but can also be extended to fault single semantic identification of other cabin components of civil aircraft (such as overhead bins, lavatories, and entertainment systems). It only requires expanding the aircraft maintenance fault corpus and supplementing the fault corpus of the corresponding components, without the need for large-scale modification of the model and system.

[0070] The processing method provided in this embodiment can be directly applied to the maintenance departments and departure operations departments of civil aviation airports and airlines to automate and lock faulty seats in real time. The system has low deployment cost, strong compatibility, and can be seamlessly integrated with existing civil aviation systems. It has high analysis efficiency and accuracy, can completely avoid passenger complaints caused by mis-selling faulty seats, improve the quality of civil aviation services and operational efficiency, and has industrial applicability.

[0071] In this embodiment, automated semantic recognition of free text in fault reports can be achieved through a large language model, with a single parsing time of less than 3 seconds, improving efficiency by over 95%. The model, finely tuned based on a civil aviation seat fault corpus, achieves over 99% accuracy in recognizing aviation terminology, mixed Chinese and English text, and multiple seat identifiers, completely avoiding manual parsing errors. Real-time linkage between structured data and the departure system is achieved through an API interface, enabling the locking / marking of faulty seats within seconds of fault report submission, completely preventing passenger complaints caused by mis-sold faulty seats and improving civil aviation service quality. A / C-class fault type judgment rules are designed to directly lock unusable seats and mark and display prompts for usable but exempted seats, balancing passenger right to know and the flexibility of civil aviation operations. A separate version of the fault cause is provided for external passengers and a detailed version for internal use, ensuring passengers clearly understand the fault situation while preserving original, professional fault information for maintenance personnel, meeting the information needs of different roles. Feedback data is continuously used to supplement the corpus and optimize the model, adapting to newly added seat fault description formats in civil aviation, achieving long-term model adaptability without frequent manual development. By integrating with existing aircraft maintenance and departure systems through standardized API interfaces, it eliminates the need for large-scale modifications to existing systems, resulting in low deployment costs and easy adoption. It can identify various descriptions of seat malfunctions, including single-seat, multi-seat, and aircraft-wide seat failures, covering all application scenarios of civil aviation aircraft seat malfunctions and demonstrating strong adaptability.

[0072] Example 2

[0073] Embodiment 2 of the present invention provides an optional fault ticket processing system, which can be used to execute the fault ticket processing method provided in Embodiment 1 of the present invention.

[0074] Figure 2 This is a schematic diagram of an optional fault ticket processing system according to an embodiment of the present invention, such as... Figure 2 As shown, it includes:

[0075] Data Acquisition Module: Used to collect fault report data from the aircraft maintenance system in real time. It supports the parsing and reception of mixed Chinese and English text and multiple text formats. For example, it can use distributed data acquisition technology to connect to the fault report publishing interface of the civil aviation aircraft maintenance system. It supports multiple methods of acquisition such as fax and electronic documents. The target aircraft maintenance fault report can be collected in real time at the second level. After collection, the text is cleaned (such as removing garbled characters and special symbols).

[0076] The LLM (Large Language Model) semantic recognition module has a built-in dedicated large language model (corresponding to the target language model in Example 1) that has been fine-tuned from the aircraft maintenance fault report corpus (corresponding to the fault corpus in Example 1). It performs semantic recognition on free text, extracts the core information of seat faults, and supports multi-seat splitting. The dedicated corpus can also include a civil aviation seat terminology dictionary and seat numbering rule base to achieve core information extraction and multi-seat splitting. The model inference latency is ≤3 seconds, and it supports high-concurrency processing (it can process more than 100 fault reports per second).

[0077] Fault Type Determination Module: It has a built-in preset fault determination rule library, which is used to determine the fault type of the extracted core information. In one optional example, maintenance personnel can also add, modify, and delete fault determination rules of type A (first type of fault) / type C (second type of fault) through the back-end interface. The rule modification takes effect in real time. The module receives the core information from the LLM semantic recognition module, automatically matches the rules and outputs the fault type.

[0078] Structured output module: Used to break down internal and external fault causes and generate standardized structured fault seat data in JSON format. For example, a JSON output template can be preset, and the external / internal fault causes can be automatically broken down. After filling the template, standardized structured data is generated, which supports local storage and cloud synchronization of data.

[0079] Departure Linkage Module: This module interfaces with the departure system via an API to enable real-time push of structured data and receive operational feedback data from the departure system. For example, a standardized HTTPS API interface is developed to interface with the departure system and enable real-time push of structured data. Simultaneously, it receives operational feedback data from the departure system and synchronizes it to the model optimization module.

[0080] Model optimization module: Used to collect feedback data and manually corrected data from the departure linkage module, supplement the corpus, and continuously optimize the dedicated large language model of the LLM semantic recognition module and the rule base of the fault type determination module. In one optional example, a data cleaning and annotation platform can be built to clean and annotate the feedback data and manually corrected data from the departure linkage module and supplement them to the special corpus of aircraft maintenance fault reports; incremental training is used to optimize the dedicated large language model, while the fault determination rule base is automatically updated (e.g., candidate rules are automatically generated when new fault types are added).

[0081] The LLM semantic recognition module can also include a built-in dictionary of civil aviation seat terminology and a seat numbering rule base, which are used to accurately match professional terms in free text and avoid semantic ambiguity; the fault type determination module supports manual visual editing of the rule base, and can add / modify / delete fault determination rules.

[0082] The system provided in this embodiment may also include a human-computer interaction module for displaying the free text of the fault report, semantic recognition results, structured data, and departure system lock status. It supports manual correction and review of the recognition results, and the corrected data is automatically synchronized to the model optimization module after review. In one optional example, a web-based and mobile backend interface can be designed to display the original text of the fault report, recognition results, structured data, and departure lock status. It supports maintenance personnel to review and correct the recognition results, and the corrected data is synchronized to the model optimization module with one click.

[0083] The processing system provided in this embodiment can be deployed on a civil aviation cloud server, supporting 24 / 7 uninterrupted operation, and can be connected to departure systems and multiple airline maintenance systems.

[0084] The following detailed description of this embodiment, using a specific example, will illustrate the concept in more detail:

[0085] This embodiment uses an open-source deep search model as the large language model, and fine-tunes it using the LoRA method. The specific steps are as follows:

[0086] S1. Construct a specialized corpus of aircraft fault reports and fine-tune the large language model:

[0087] 1. Corpus Construction: 10,000 free text entries of civil aviation aircraft seat malfunction reports from the past 3 years were collected, including single-seat, multi-seat, and whole-aircraft malfunctions, with mixed Chinese and English descriptions; each entry was annotated, including seat number, malfunction component, malfunction phenomenon, A / C type malfunction, external malfunction cause, and internal malfunction cause; at the same time, civil aviation seat professional terminology (such as PCU, AMM, backrest, armrest, entertainment screen, etc.), seat numbering rules (such as numbers + letters, consecutive letters indicate multiple seats), A / C type malfunction definitions, and other knowledge corpora were added to construct a dedicated corpus of aircraft malfunction reports with a total scale of 12,000 entries.

[0088] 2. Model fine-tuning: The LoRA low-rank adaptation method is adopted, with a learning rate of 3e-4, 4 training epochs, and a batch size of 8. The backbone parameters of the deepseek model are frozen, and only the adapter layer is trained. After training, a dedicated large language model (corresponding to the target language model) adapted for civil aviation seat fault identification is obtained. This model can achieve real-time inference on ordinary servers.

[0089] S2. Collect free text data of fault reports:

[0090] The data acquisition module collects free text of fault reports from the civil aviation maintenance system in real time. In this embodiment, five typical fault report texts are selected as the identification objects:

[0091] 1. Text 1: 7DH Entertainment Screen Malfunction 7DH ENTERTAINMENTMON FAULT;

[0092] 2. Text 2: 32J Seat Backrest Adjustment Fault;

[0093] 3. Text 3: The 35A seat back is faulty and fixed in an upright position.

[0094] 4. Text 4: 44AC Seat Armrest PCU No Power;

[0095] 5. Text 5: During a short stop, it was discovered that the small table on the 38C seat was tilted. According to AMM25-21-08-040-803, item M was completed. The small table was fixed in the storage position, and the seat was usable. Due to insufficient time, it was decided to keep it.

[0096] S3. Semantic recognition and extraction of core information:

[0097] The above five texts were input into a dedicated large language model. The model extracted the following core information through semantic recognition and multi-seat segmentation logic:

[0098] 1. Text 1: Seat label 7DH → split into 7D and 7H, faulty component: entertainment screen, fault symptom: screen malfunction;

[0099] 2. Text 2: Seat label 32J, faulty part: seat back, fault symptom: backrest adjustment failure;

[0100] 3. Text 3: Seat label 35A, faulty part: seat back, fault symptom: seat back is faulty and fixed in the upright position;

[0101] 4. Text 4: Seat label 44AC → split into 44A and 44C, faulty component is seat armrest PCU, fault symptom is PCU has no power;

[0102] 5. Text 5: Seat label 38C, faulty part: small table, fault symptoms: small table is tilted, it has been fixed in the storage position, the seat is usable.

[0103] S4. Fault Type Determination:

[0104] The fault determination rule base preset in this embodiment includes the rules described in claim 4. Based on this rule base, the fault type determination results for the above 5 texts are as follows:

[0105] 1. Text 1: Category C Fault (Entertainment screen malfunction, basic seat functions are available, waiver required by passenger's signature);

[0106] 2. Text 2: Class C fault (backrest adjustment fault, not clearly completely stuck, can be used temporarily);

[0107] 3. Text 3: Class C fault (backrest fixed in the upright position, basic seating functions available, waiver required by passenger's signature);

[0108] 4. Text 4: Class A fault (Handrail PCU is out of power, the core function of the handrail is completely disabled, and it is unusable for passengers).

[0109] 5. Text 5: Category C fault (the tray table is fixed, the seat is available, and the passenger needs to sign an exemption).

[0110] S5. Generate standardized, structured faulty seat data:

[0111] The data is generated in JSON format, separating the data into an external passenger version and a detailed internal fault cause version. Using text 1 and text 4 as examples, the generated structured data example is as follows:

[0112] Text 1 Structured Data:

[0113] {

[0114] "seatNo":"7D",

[0115] "seatType":"C",

[0116] "seatReason": "Entertainment system unavailable"

[0117] "seatInnerReason": "Entertainment screen malfunction 7DH ENTERTAINMENTMON FAULT"

[0118] },

[0119] {

[0120] "seatNo":"7H",

[0121] "seatType":"C",

[0122] "seatReason": "Entertainment system unavailable"

[0123] "seatInnerReason": "Entertainment screen malfunction 7DH ENTERTAINMENTMON FAULT"

[0124] }

[0125] Text 4 Structured Data

[0126] {

[0127] "seatNo":"44A",

[0128] "seatType":"A",

[0129] "seatReason": "The seat armrest function is disabled and unavailable".

[0130] "seatInnerReason":"44AC Seat Armrest PCU No Power 44AC SEAT ARMREST PCU NOPOWER"

[0131] },

[0132] {

[0133] "seatNo":"44C",

[0134] "seatType":"A",

[0135] "seatReason": "The seat armrest function is disabled and unavailable".

[0136] "seatInnerReason":"44AC Seat Armrest PCU No Power 44AC SEAT ARMREST PCU NOPOWER"

[0137] }

[0138] S6. Link the departure system to perform seat operations:

[0139] Structured data is pushed to the departure system in real time via an HTTPS API interface. The departure system then performs the following operations:

[0140] 1. For Class A faulty seats 44A and 44C: Immediately lock them, mark them as "Faulty and locked, seat selection not allowed" in the seat resource list, and prohibit passengers from selecting seats during check-in;

[0141] 2. For Class C fault seats 7D, 7H, 32J, 35A, and 38C: Perform a fault marking operation, marking "Fault requires exemption". When passengers check in and select seats, a fault prompt box will pop up, displaying the content of the external fault reason field. Passengers are required to click "Confirm Exemption" before they can complete the seat selection.

[0142] S7. Model Optimization:

[0143] Collect operational feedback data from the departure system (such as successful locking / marking) and manually corrected data (no correction is needed if there are no errors). Add the above 5 texts and parsing results to the special corpus of aircraft maintenance fault reports. If new fault descriptions appear later (such as "56B seat belt buckle failure, temporary repair available"), mark them and add them to the corpus. Use incremental training to optimize the dedicated large language model and improve the model's ability to identify new fault types.

[0144] It should be noted that the processing system provided in this embodiment is not only applicable to seat fault identification of civil aircraft, but can also be extended to fault single semantic recognition of other cabin components of civil aircraft (such as overhead bins, lavatories, and entertainment systems). Only the aircraft maintenance fault corpus needs to be expanded and the fault corpus of the corresponding components needs to be supplemented. There is no need to make large-scale modifications to the model and system.

[0145] The processing system provided in this embodiment can be directly applied to the maintenance departments and departure operations departments of civil aviation airports and airlines to automate and lock faulty seats in real time. The system has low deployment cost, strong compatibility, and can be seamlessly integrated with existing civil aviation systems. It has high analysis efficiency and accuracy, can completely avoid passenger complaints caused by mis-selling faulty seats, improve the quality of civil aviation services and operational efficiency, and has industrial applicability.

[0146] Example 3

[0147] Embodiment 3 of the present invention provides an optional fault ticket processing device, wherein each implementation unit in the processing device corresponds to each implementation step in Embodiment 1.

[0148] Figure 3 This is a schematic diagram of an optional fault ticket processing device according to an embodiment of the present invention, such as... Figure 3 As shown, the fault report processing device includes: a first acquisition unit 31, a processing unit 32, a determination unit 33, and an operation unit 34.

[0149] The first acquisition unit 31 is used to acquire the text in the target aircraft maintenance fault report to obtain the target fault report text. The target aircraft maintenance fault report includes: a fault report to be processed containing descriptive information of the faulty seats on the target aircraft.

[0150] Processing unit 32 is used to input the target fault single text into the target language model to obtain target fault information, wherein the target language model is used to perform semantic recognition and information extraction on the target fault single text;

[0151] The determining unit 33 is used to determine the fault type of the faulty seat based on the target fault information;

[0152] The operation unit 34 is used to perform seat operation on the faulty seat in the departure system based on the fault type of the faulty seat, wherein the seat operation includes one of the following: seat locking, seat fault marking.

[0153] In the fault report processing device provided in this embodiment of the invention, the text of the target aircraft maintenance fault report can be collected by the first acquisition unit 31 to obtain the target fault report text. The target aircraft maintenance fault report includes a fault report to be processed containing descriptive information of a faulty seat on the target aircraft. The processing unit 32 inputs the target fault report text into a target language model to obtain target fault information. The target language model is used to perform semantic recognition and information extraction on the target fault report text. Based on the target fault information, the determination unit 33 determines the fault type of the faulty seat. Based on the fault type of the faulty seat, the operation unit 34 performs seat operations on the faulty seat in the departure system. The seat operations include one of the following: seat locking and seat fault marking. This solves the technical problem of low processing efficiency caused by manual parsing and processing of data in seat fault reports in related technologies. In this embodiment, a language model is used to extract fault information from the aircraft seat fault report, and the seat is operated in the departure system based on the extraction results. This avoids the need for manual parsing of seat fault report information, which is inefficient and can lead to passengers selecting faulty seats during check-in, thus affecting the passenger experience. This achieves the technical effect of improving the efficiency of seat fault report processing and improving the passenger experience.

[0154] Optionally, in the fault report processing device provided in this embodiment of the invention, the fault type includes one of the following: a first fault type and a second fault type. The first fault type includes seats that cannot be sat on, and the second fault type includes seats whose fault does not affect occupancy. The operation unit includes: a processing subunit for performing structured processing on the fault type and target fault information of the faulty seat to obtain structured fault information; a locking subunit for locking the seat of the faulty seat in the departure system based on the structured fault information when the fault type of the faulty seat is a first type of fault; and a marking subunit for marking the seat of the faulty seat in the departure system based on the structured fault information when the fault type of the faulty seat is a second type of fault.

[0155] Optionally, in the fault ticket processing device provided in this embodiment of the invention, the fault ticket processing device further includes: a generation unit, used to generate fault prompt information when the fault type of the fault seat is a second type of fault, after performing seat operation on the fault seat based on the fault type of the fault seat, and when the target object selects the fault seat during the check-in operation of the target aircraft, wherein the fault prompt information includes: the cause of the fault and an informed consent form; and a processing unit, used to visualize the fault prompt information and process the check-in procedures for the target object after the target object signs the informed consent form.

[0156] Optionally, in the fault report processing device provided in this embodiment of the invention, the target fault information includes at least one of the following: seat identification of the faulty seat, faulty component, and fault phenomenon. The determining unit includes: a first acquisition subunit, used to acquire a preset judgment rule, wherein the preset judgment rule includes: a mapping relationship between the fault information of the aircraft seat and the fault type; and a determining subunit, used to determine the fault type of the faulty seat based on the target fault information and the preset judgment rule.

[0157] Optionally, in the fault report processing device provided in this embodiment of the invention, the target language model is obtained through the following sub-units: a second acquisition sub-unit, used to acquire corpus samples in the fault corpus, wherein the fault corpus includes: aircraft seat fault reports with fault labeling information; and a training sub-unit, used to train the initial language model based on the corpus samples until a preset convergence condition is met, and to determine the initial language model trained in the last training as the target language model, wherein the type of the initial language model includes: a large language model to be trained.

[0158] Optionally, in the fault ticket processing device provided in the embodiments of the present invention, the fault ticket processing device further includes: a collection unit, used to collect feedback correction data of the departure system after performing a seating operation on the fault seat in the departure system based on the fault type of the fault seat, wherein the feedback correction data includes at least one of the following: data on the seating operation result of the fault seat and the target object; and an adding unit, used to add the feedback correction data to the fault corpus.

[0159] Optionally, in the fault ticket processing device provided in this embodiment of the invention, the training subunit further includes: an initialization module, used to initialize the model parameters of the initial language model during the model training process based on corpus samples, to obtain an initialized language model; and a training module, used to train the initialized language model based on corpus samples using a low-rank adaptation strategy.

[0160] The aforementioned fault report processing device may also include a processor and a memory. The first acquisition unit 31, processing unit 32, determination unit 33 and operation unit 34 are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0161] The aforementioned processor contains a kernel that retrieves the corresponding program units from memory. One or more kernels can be configured. By adjusting kernel parameters, information is extracted from aircraft seat fault reports using a language model. Based on the extraction results, seat operations are performed in the departure system. This avoids the inefficiency of manually parsing seat fault report information, which can lead to passengers selecting faulty seats during check-in, negatively impacting their experience. Therefore, this processor improves both the efficiency of seat fault report processing and the passenger experience.

[0162] The aforementioned memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0163] According to another aspect of the present invention, an electronic device is also provided, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform a fault ticket processing method of any of the above-mentioned methods by executing the executable instructions.

[0164] According to another aspect of the present invention, a computer-readable storage medium is also provided, which stores a computer program, wherein the computer program controls the device where the computer-readable storage medium is located to execute the fault report processing method described above when the computer program is running.

[0165] Figure 4 This is a schematic diagram of an electronic device according to an embodiment of the present invention, such as... Figure 4 As shown, an embodiment of the present invention provides an electronic device 40, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements a fault report processing method for any of the above-mentioned items.

[0166] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0167] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0168] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0169] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0170] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0171] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0172] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for processing fault reports, characterized in that, include: Collect the text from the target aircraft maintenance fault report to obtain the target fault report text, wherein the target aircraft maintenance fault report includes: a fault report to be processed containing descriptive information of the faulty seats on the target aircraft; The target fault single text is input into the target language model to obtain target fault information, wherein the target language model is used to perform semantic recognition and information extraction on the target fault single text; Based on the target fault information, determine the fault type of the faulty seat; Based on the fault type of the faulty seat, a seat operation is performed on the faulty seat in the departure system, wherein the seat operation includes one of the following: seat locking, seat fault marking.

2. The processing method according to claim 1, characterized in that, The fault type includes one of the following: a first fault type and a second fault type. The first fault type includes seats that are unusable. The second fault type includes seats whose fault does not affect occupancy. Based on the fault type of the faulty seat, seating operations are performed on the faulty seat in the departure system, including: The fault type of the faulty seat and the target fault information are processed in a structured manner to obtain structured fault information; If the fault type of the faulty seat is a Type I fault, the seat of the faulty seat is locked in the departure system based on the structured fault information. If the faulty seat is classified as a Type II fault, the faulty seat is marked as faulty in the departure system based on the structured fault information.

3. The processing method according to claim 1, characterized in that, If the faulty seat is classified as a Type II fault, after performing a seating operation on the faulty seat in the departure system based on the fault type, the process further includes: If the target person selects the faulty seat during the check-in process of the target aircraft, a fault prompt message is generated, which includes: the cause of the fault and the informed consent form; The fault message is displayed visually, and check-in procedures are processed for the target object after the target object signs the informed consent form.

4. The processing method according to claim 1, characterized in that, The target fault information includes at least one of the following: the seat identification of the faulty seat, the faulty component, and the fault phenomenon. Based on the target fault information, the fault type of the faulty seat is determined, including: Obtain preset judgment rules, wherein the preset judgment rules include: the mapping relationship between aircraft seat fault information and fault type; Based on the target fault information and the preset judgment rules, the fault type of the faulty seat is determined.

5. The processing method according to claim 1, characterized in that, The target language model is obtained in the following way: Obtain corpus samples from a fault corpus, wherein the fault corpus includes: aircraft seat fault reports with fault labeling information; The initial language model is trained based on the corpus samples until a preset convergence condition is met. The initial language model trained in the last training session is then identified as the target language model. The type of the initial language model includes: a large language model to be trained.

6. The processing method according to claim 5, characterized in that, After performing seating operations on the faulty seat in the departure system based on the fault type of the faulty seat, the process further includes: The system collects feedback correction data from the departure system, wherein the feedback correction data includes at least one of the following: data on the seat operation results of the faulty seat and the data on the target object for correction; The feedback correction data is added to the fault corpus.

7. The processing method according to claim 5, characterized in that, The process of training the initial language model based on the corpus samples also includes: The model parameters of the initial language model are initialized to obtain the initialized language model; Based on the corpus samples, a low-rank adaptation strategy is used to train the initialized language model.

8. A fault report processing device, characterized in that, include: The first acquisition unit is used to acquire the text in the target aircraft maintenance fault report to obtain the target fault report text, wherein the target aircraft maintenance fault report includes: a fault report to be processed containing descriptive information of the faulty seats on the target aircraft; The processing unit is used to input the target fault single text into the target language model to obtain target fault information, wherein the target language model is used to perform semantic recognition and information extraction on the target fault single text; The determining unit is configured to determine the fault type of the faulty seat based on the target fault information; An operating unit is configured to perform seat operations on the faulty seat in the departure system based on the fault type of the faulty seat, wherein the seat operations include one of the following: seat locking, seat fault marking.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the fault ticket processing method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the fault ticket processing method according to any one of claims 1 to 7.

Images