An unattended metro ticket processing method, device and equipment and storage medium

Abstract

The application discloses an unattended metro ticket processing method, which comprises the following steps: receiving a ticket service request input by a passenger; the terminal side system analyzes the request and performs local data verification; if the request is a basic request such as ticket purchase or recharge, the local transaction logic is directly called to process and generate a first result feedback to the passenger, and the first result is synchronously transmitted to the edge side data processing platform; if the request is an abnormal request such as ticket card invalidation or free certificate verification, the request is uploaded to the edge side for intelligent preliminary examination; if the edge side cannot process the request, the request is forwarded to a cloud side remote processing system; after remote examination and identity verification are performed on the cloud side, an authorization instruction is issued; the terminal side receives the instruction, executes the business, generates a second result feedback to the passenger, and synchronously transmits the second result to the edge side and the cloud side in sequence. The application can reduce network dependence and cloud computing power consumption, significantly improve the abnormal ticket processing efficiency, and realize closed-loop tracing of all-scene business.

Description

Technical Field

[0001] This application relates to the field of urban rail transit technology, and more specifically, to an unmanned subway ticketing processing method, device, equipment, and storage medium. Background Technology

[0002] With the continuous expansion of urban rail transit networks and the ever-increasing passenger flow, automatic fare collection (AFC) systems have become a core support for subway operations. Traditional ticketing services primarily rely on manual ticket booths and basic self-service terminals. While these methods have achieved some degree of ticket automation, they are no longer adequate for the demands of modern rail transit in terms of comprehensive service coverage, peak-hour traffic efficiency, and refined operational management. In recent years, the maturity of artificial intelligence, cloud computing, and biometric technologies has provided a technological foundation for the intelligent upgrading of ticketing systems. The industry is gradually exploring unmanned service models, aiming to reduce costs and increase efficiency through technological integration, thereby enhancing the passenger travel experience. Consequently, the research and application of smart ticketing terminals have become an important direction for the iteration of AFC systems.

[0003] However, existing unmanned or semi-self-service ticketing terminals still have significant shortcomings. On the one hand, traditional devices mostly adopt a centralized architecture, heavily relying on network connectivity. Once the network is down, transactions cannot be completed. Furthermore, the devices have fixed functions and poor scalability, making it difficult to handle complex and abnormal scenarios such as expired tickets, verification of free identification documents, and free tickets for children, still requiring significant manual intervention. On the other hand, the interaction method is limited to touchscreen operation, which is not user-friendly for special groups, and there is a lack of a unified cloud-based remote customer service system, resulting in delayed response times for handling anomalies. In addition, existing payment modules lack compatibility, biometric recognition is slow, and transaction data security and anti-tampering mechanisms are inadequate, making it difficult to balance payment convenience with fund security. These problems prevent existing technical solutions from truly achieving 24 / 7, all-scenario unmanned operation, hindering further improvements in the operational efficiency of rail transit. Summary of the Invention

[0004] In view of at least one defect or improvement need of the prior art, this application provides an unattended subway ticketing processing method, apparatus, equipment and storage medium, which can solve at least one of the problems existing in the background art.

[0005] To achieve the above objectives, according to the first aspect of this application, an unmanned subway ticketing processing method is provided, the method comprising: Receive ticketing service requests from passengers; The ticketing service request is parsed by the terminal system and then local data is verified. When it is determined to be a basic request, the terminal system directly calls the local transaction logic to execute the processing and generates a first processing result to be fed back to the passenger. The first processing result is then synchronized to the edge data processing platform. When a request is determined to be abnormal, the endpoint system uploads the abnormal request to the edge data processing platform for intelligent preliminary review. When the edge data processing platform is unable to process the abnormal request, it forwards the abnormal request to the cloud-side remote processing system. After receiving the abnormal request, the cloud-side remote processing system performs remote review and identity verification, and issues a remote authorization instruction to the terminal system. After receiving the remote authorization instruction, the terminal system executes the corresponding ticketing business processing, generates a second processing result and feeds it back to the passenger, and then synchronizes the second processing result to the edge data processing platform and the cloud remote processing system in sequence.

[0006] Furthermore, the aforementioned unmanned subway ticketing processing method, after receiving the ticketing service request input by the passenger and before the terminal system parses it, further includes: The facial recognition module is invoked to perform liveness detection and identity verification on passengers. When the verification is successful and the ticketing service request includes a payment requirement, the payment module is triggered to call the facial payment interface to complete the payment.

[0007] Furthermore, in the above-mentioned unattended subway ticketing processing method, if a network communication interruption is detected during the execution of the corresponding ticketing business by the terminal system, a local offline transaction mode is activated, and the transaction data is temporarily stored in a local encrypted database. After the network is restored, the transaction data is uploaded to the edge data processing platform and the cloud-side remote processing system.

[0008] Furthermore, in the aforementioned unattended subway ticketing processing method, the handling of abnormal requests specifically includes: The terminal system controls the document scanning module to collect image information of free documents; The side data processing platform calls the OCR algorithm to perform intelligent preliminary review of the document image information; If recognition fails, the document image information is forwarded to the cloud-based remote processing system for verification. Once the verification is successful, an authorization execution command is issued.

[0009] Furthermore, in the aforementioned unattended subway ticketing processing method, the handling of abnormal requests also includes: The terminal system uses a high-definition camera to collect data on the child's height and facial features. The side data processing platform performs intelligent preliminary review based on a preset height threshold; If the height is determined to be below the preset height, the passage is directly authorized. If the height cannot be determined, the remote identification module is activated, and the cloud-based remote processing system performs remote review before authorizing passage.

[0010] Furthermore, in the aforementioned unmanned subway ticketing processing method, the cloud-side remote processing system simultaneously records operation logs and audio / video stream data while issuing remote authorization instructions. The data is encapsulated into unalterable transaction data packets through an encrypted transmission protocol and stored in the terminal system, the edge data processing platform, and the cloud-side remote processing system, respectively.

[0011] Furthermore, in the aforementioned unmanned subway ticketing processing method, after receiving the first processing result or the second processing result uploaded by the terminal system, the edge data processing platform cleans and aggregates the data, filters out invalid data, and then uploads it to the big data analysis system of the cloud-side remote processing system.

[0012] According to a second aspect of this application, an unmanned subway ticketing processing device is also provided, comprising: The request receiving module is used to receive ticketing service requests input by passengers. The terminal-side processing module is used to perform local data verification after the ticketing service request is parsed by the terminal-side system. When it is determined to be a basic request, the terminal-side system directly calls the local transaction logic to perform processing and generates a first processing result to be fed back to the passenger. The first processing result is then synchronized to the edge data processing platform. The initial review module is used so that when a request is determined to be abnormal, the end-side system uploads the abnormal request to the edge-side data processing platform for intelligent initial review. The forwarding module is used to forward the abnormal request to the cloud-side remote processing system when the edge data processing platform is unable to process the abnormal request. The cloud-side review module is used by the cloud-side remote processing system to perform remote review and identity verification after receiving the abnormal request, and to issue a remote authorization instruction to the terminal system. The result feedback module is used to execute the corresponding ticketing business processing after the terminal system receives the remote authorization instruction, generate a second processing result and feed it back to the passenger, and then synchronize the second processing result to the edge data processing platform and the cloud remote processing system in sequence.

[0013] According to a third aspect of this application, an unmanned subway ticketing processing device is also provided, which includes at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program that, when executed by the processing unit, causes the processing unit to perform the steps of any of the methods described above.

[0014] According to a fourth aspect of this application, a storage medium is also provided, which stores a computer program executable by an unattended subway ticketing processing device, which, when run on the unattended subway ticketing processing device, causes the unattended subway ticketing processing device to perform the steps of any of the methods described above.

[0015] Overall, compared with the prior art, the above-described technical solutions conceived in this application can achieve the following beneficial effects: The unmanned subway ticketing processing method provided in this application constructs a hierarchical collaborative processing architecture of "real-time response on the terminal side - intelligent pre-review on the edge side - centralized review on the cloud side". This architecture decentralizes basic ticketing operations to the local terminal to ensure service continuity in offline environments. At the same time, it utilizes the edge side to perform rule-based initial screening of complex abnormal requests and achieves automatic synchronization and closed-loop flow of cross-level data throughout the entire business lifecycle. This significantly reduces the dependence of a single transaction on cloud computing power and network bandwidth. While effectively reducing the frequency of manual intervention, it ensures the compliance and traceability of ticketing operations across all scenarios, systematically solving the problems of delayed transaction response, low efficiency in abnormal handling, and high operation and maintenance costs under the traditional centralized architecture. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating an unattended subway ticketing processing method provided in an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. Furthermore, the technical features involved in the various embodiments described below can be combined with each other as long as they do not conflict with each other.

[0019] The terms "first," "second," "third," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0020] Figure 1 This application provides a flowchart illustrating an unattended subway ticketing processing method as an embodiment of the present application. Figure 1 As shown in the figure, an unmanned subway ticketing processing method provided in this application includes the following steps: Receive ticketing service requests from passengers; The ticketing service request is parsed by the terminal system and then local data is verified. When it is determined to be a basic request, the terminal system directly calls the local transaction logic to execute the processing and generates a first processing result to be fed back to the passenger. The first processing result is then synchronized to the edge data processing platform. When a request is determined to be abnormal, the endpoint system uploads the abnormal request to the edge data processing platform for intelligent preliminary review. When the edge data processing platform is unable to process the abnormal request, it forwards the abnormal request to the cloud-side remote processing system. After receiving the abnormal request, the cloud-side remote processing system performs remote review and identity verification, and issues a remote authorization instruction to the terminal system. After receiving the remote authorization instruction, the terminal system executes the corresponding ticketing business processing, generates a second processing result and feeds it back to the passenger, and then synchronizes the second processing result to the edge data processing platform and the cloud remote processing system in sequence.

[0021] Specifically, before arriving at the unmanned smart ticketing terminal in the subway station, passengers can input ticketing service requests through the terminal's interaction layer. Specifically, passengers can click the corresponding service icon on the dual touchscreens, or directly state their service needs through the far-field voice interaction module, such as "buy a single-journey ticket" or "process expired tickets." They can also trigger the request by scanning a ticket, QR code, or presenting their ID. After the terminal's request receiving module captures the request, it is immediately transmitted to the edge system, which is the edge computing engine deployed locally on the terminal.

[0022] Upon receiving a request, the edge system first parses the request content, extracting key fields such as business type, associated amount, and identity information, and then performs local data verification. Verification includes checking the validity of the request format, the functionality of required hardware modules such as ticket readers and printers, and the adequacy of the local account balance. If the parsing determines the request is a basic request, such as a regular ticket purchase, top-up, balance inquiry, or transaction history query, the edge system directly calls the pre-defined local transaction logic for processing, as this type of business logic is simple and requires no manual intervention. For example, when processing a ticket purchase request, the system calls the ticket issuance module to write the card and control ticket issuance. After processing, a first processing result is generated. This result is displayed on the touchscreen or announced to the passenger via voice, and the result data, including transaction time, amount, and type, is synchronized in real-time to the edge data processing platform for regional data aggregation and monitoring.

[0023] If the client-side system determines that the request is an abnormal request after parsing, such as complex scenarios involving ticket expiration, timeout or over-distance ticket supplementation, free document verification, or children's free ticket application, the client-side system will upload the abnormal request, which includes the original request information and related image data such as document photos and on-site video streams, to the edge data processing platform due to the lack of corresponding authorization permissions or complex comparison databases on the local machine.

[0024] Upon receiving an abnormal request, the edge data processing platform initiates an intelligent preliminary review. This review typically utilizes a built-in rule engine or lightweight AI model for preprocessing, such as using OCR technology to identify document validity periods, image recognition to preliminarily determine a child's height, or checking locally cached blacklist information. If the abnormal request falls within the edge's authorized scope and is a simple rule-based task that can be automatically processed, such as a simple overtime fee calculation, it is processed directly. However, if the edge encounters a document type it cannot recognize, a failed facial recognition comparison, or a complex situation requiring manual subjective judgment, the edge data processing platform will forward the abnormal request to the cloud-based remote processing system, which is the same as the central platform's remote processing system.

[0025] After receiving the forwarded request, the cloud-based remote processing system obtains the passenger's real-time audio and video streams and business data through the backend interface, and performs remote review and identity verification. For example, for free pass verification, it checks whether the pass is genuine and matches the holder; for disputes regarding free tickets for children, it remotely verifies whether the child's height falls within the free ticket range. After successful review, it confirms the verification in the system and issues a remote authorization command to the edge system. This command is an encrypted control signal containing an authorization code that allows passage or specific parameters for business execution.

[0026] After receiving and decrypting the remote authorization command, the edge system executes the corresponding ticketing business processing. For example, it controls the gate opening, deducts the difference in fare, or updates the ticket validity period, and generates a second processing result. This result is also immediately fed back to the passenger. At the same time, the complete transaction record, operation log, and audio / video recordings serve as the data source for the second processing result, and are sequentially synchronized to the edge data processing platform for backup, and finally converged to the cloud-side remote processing system, thereby realizing a closed-loop data system and traceability for the entire process from request initiation to business completion.

[0027] The unmanned subway ticketing processing method provided in this application constructs a hierarchical collaborative processing architecture of "real-time response on the terminal side - intelligent pre-review on the edge side - centralized review on the cloud side". This architecture decentralizes basic ticketing operations to the local terminal to ensure service continuity in offline environments. At the same time, it utilizes the edge side to perform rule-based initial screening of complex abnormal requests and achieves automatic synchronization and closed-loop flow of cross-level data throughout the entire business lifecycle. This significantly reduces the dependence of a single transaction on cloud computing power and network bandwidth. While effectively reducing the frequency of manual intervention, it ensures the compliance and traceability of ticketing operations across all scenarios, systematically solving the problems of delayed transaction response, low efficiency in abnormal handling, and high operation and maintenance costs under the traditional centralized architecture.

[0028] Optionally, the unmanned subway ticketing processing method provided in this application embodiment further includes, after receiving the ticketing service request input by the passenger and before the terminal system parses it: The facial recognition module is invoked to perform liveness detection and identity verification on passengers. When the verification is successful and the ticketing service request includes a payment requirement, the payment module is triggered to call the facial payment interface to complete the payment.

[0029] Specifically, in implementation, the facial recognition module employs a lightweight algorithm. When a passenger selects facial payment or triggers "identity verification" via camera, the client-side system first calls the facial recognition module to perform liveness detection, preventing photo or video attacks. After successful verification, if the ticketing service request includes payment, the client-side system automatically associates the payment module with the facial payment interface to directly deduct payment from the linked account.

[0030] Optionally, in the unmanned subway ticketing processing method provided in this application embodiment, if a network communication interruption is detected during the execution of the corresponding ticketing business by the terminal system, a local offline transaction mode is activated, and the transaction data is temporarily stored in a local encrypted database. After the network is restored, the transaction data is uploaded to the edge data processing platform and the cloud remote processing system.

[0031] Specifically, considering the fluctuating network conditions in the subway environment, the edge system monitors network connectivity in real time. During ticketing processing, if a network communication interruption is detected, the edge system immediately activates a local offline transaction mode, temporarily storing transaction data, including transaction time, amount, and transaction type, in a local encrypted database to ensure uninterrupted service. Once the network is restored, the edge system automatically wakes up the communication module, uploads the transaction data to the edge data processing platform, and then forwards it to the cloud-based remote processing system to complete the final data storage and clearing settlement.

[0032] Optionally, the unmanned subway ticketing processing method provided in this application embodiment includes the following specific steps for handling abnormal requests: The terminal system controls the document scanning module to collect image information of free documents; The side data processing platform calls the OCR algorithm to perform intelligent preliminary review of the document image information; If recognition fails, the document image information is forwarded to the cloud-based remote processing system for verification. Once the verification is successful, an authorization execution command is issued.

[0033] Specifically, for the particular exception scenario of free document verification, when the edge system determines that the request type is free document verification, it first controls the document scanning module to collect image information of free documents such as disability certificates and senior citizen certificates. After receiving the image information, the edge data processing platform calls the OCR algorithm to extract the document number, validity period, and certificate holder information, and compares it with the locally cached valid document database to complete the intelligent preliminary review. If the recognition fails or the comparison is inconsistent, the edge data processing platform packages the document image information and forwards it to the cloud-based remote processing system for review. After the review is successful, an authorization execution command is issued.

[0034] Optionally, the unmanned subway ticketing processing method provided in this application embodiment further includes the processing of abnormal requests as follows: The terminal system uses a high-definition camera to collect data on the child's height and facial features. The side data processing platform performs intelligent preliminary review based on a preset height threshold; If the height is determined to be below the preset height, the passage is directly authorized. If the height cannot be determined, the remote identification module is activated, and the cloud-based remote processing system performs remote review before authorizing passage.

[0035] Specifically, for scenarios involving free admission for children, when the edge system determines that the request type is free admission for children, it calls a high-definition camera to collect the child's height data and facial features. The edge data processing platform performs intelligent preliminary review based on a preset height threshold. If the image recognition determines that the height is below the threshold, an authorization release command is directly generated. If the height cannot be accurately determined due to obstruction, angle issues, or if the height is determined to be at the critical value, the remote recognition module is activated. The cloud-based remote processing system remotely verifies the child's height and issues an authorization release command after confirmation, thus solving the problem of inaccurate traditional turnstiles relying solely on infrared detection.

[0036] Optionally, in the unmanned subway ticketing processing method provided in this application embodiment, the cloud-side remote processing system simultaneously records operation logs and audio / video stream data while issuing remote authorization instructions. The data is encapsulated into tamper-proof transaction data packets through an encrypted transmission protocol and stored in the terminal system, the edge data processing platform, and the cloud-side remote processing system, respectively.

[0037] Specifically, to ensure transaction security, the cloud-based remote processing system simultaneously records operation logs, reviewer IDs, and audio / video stream data at the time of issuing remote authorization commands. This data is encapsulated into an immutable transaction data packet using an encrypted transmission protocol, timestamped, and then stored in the local encrypted database of the endpoint system, the temporary storage area of ​​the edge data processing platform, and the persistent storage of the cloud-based remote processing system, forming a complete chain of evidence for subsequent auditing and dispute resolution.

[0038] Optionally, in the unmanned subway ticketing processing method provided in this application embodiment, after the edge data processing platform receives the first processing result or the second processing result uploaded by the end system, it cleans and aggregates the data, filters out invalid data, and then uploads it to the big data analysis system of the cloud-side remote processing system.

[0039] Specifically, after receiving the first or second processing result uploaded by the end-side system, the edge-side data processing platform does not simply transmit it, but performs data cleaning and aggregation operations. For example, it filters out duplicate or invalid test data and aggregates transaction data for the same train. The cleaned and valid data is then uploaded to the big data analysis system of the cloud-side remote processing system. Based on this aggregated data, the big data analysis system mines passenger flow patterns, equipment operating status, and ticketing business needs, thereby providing operators with decision support such as tidal passenger flow early warning and preventive equipment maintenance.

[0040] The unmanned subway ticketing processing method provided in this application will be specifically described below with a concrete embodiment. This embodiment proposes a modular, cloud-edge-device collaborative, AI multimodal interactive unmanned subway smart ticketing terminal, and designs a corresponding ticketing processing method. A complete technical solution is formed from three aspects: hardware architecture, software system, and business process, realizing a closed loop of fully self-service + remote assistance ticketing services. The specific technical solution is as follows: (1) Hardware modular architecture design The terminal adopts a three-tier modular hardware architecture consisting of an interaction layer, a processing layer, and an extension layer. Each module is designed independently and adapted through standard interfaces, facilitating disassembly, assembly, and functional expansion. The specific module composition is as follows: 1) Interaction layer: Equipped with high-definition dual touch screens, far-field voice interaction module, high-definition camera, document scanning module, ticket reader / writer, and thermal printer. Optional banknote / coin payment module is available to realize multi-mode human-computer interaction and basic ticketing operations; 2) Processing layer: integrates industrial-grade main control unit, multi-mode communication module (4G / 5G / Wi-Fi / wired), UPS uninterruptible power supply, security monitoring module, ticket issuance module, and ticket reader module to realize local data processing, offline transactions, and real-time monitoring of equipment status; 3) Extension layer: Equipped with a face recognition module (300ms kernel verification), identity verification module, QR code scanning module, NFC module, and remote audio and video intercom module to realize biometric recognition, contactless payment, and remote customer service audio and video interaction.

[0041] (2) Cloud-edge-device collaborative software architecture design Construct a three-tiered collaborative software system encompassing the edge, cloud, and endpoint, breaking through the limitations of traditional centralized architectures to achieve offline availability, elastic scaling, and global scheduling. The functionalities and interaction logic at each level are as follows: 1) Edge side (local terminal): Deploy an edge computing engine to realize local self-service ticketing transactions, offline data storage, and device status collection. In the offline state, it supports core businesses such as ticket purchase, recharge, and ticket replacement. After reconnecting to the network, it automatically synchronizes data to the edge side. 2) Edge side (station / line edge nodes): Deploy a local data processing platform to achieve centralized monitoring of terminal equipment, fault isolation, regional data aggregation, real-time operation and maintenance of terminal equipment, and filter invalid data to reduce cloud side pressure; 3) Cloud side (central platform): Build a centralized cloud platform that integrates a remote customer service seat system, a clearing and settlement system, a big data analysis system, and a global operation and maintenance system to achieve 24 / 7 remote customer service dispatch, cross-line ticket clearing, equipment lifecycle management, and operation data mining.

[0042] (3) AI multimodal interaction technology design Integrating three major AI technologies—natural language interaction, facial recognition, and intelligent customer service—it lowers the operational threshold and enables intelligent self-service. 1) Voice interaction module: Equipped with far-field voice pickup and semantic understanding algorithms, it supports Chinese voice command recognition, enabling touchless operations such as ticket purchase, recharge, and information inquiry, while also supporting voice-guided operation; 2) Face recognition module: It adopts a lightweight face recognition algorithm to achieve fast verification within 300ms, supports face recognition for ticket purchase, face recognition for payment and face recognition for access, and works in conjunction with the identity verification module to achieve "identity verification". 3) Intelligent Customer Service Module: Construct a knowledge graph and FAQ knowledge base for rail transit ticketing to enable automatic answers to common questions. Unanswerable questions can be transferred to remote human customer service with one click, forming an interactive closed loop of "intelligent self-service - remote assistance".

[0043] (4) Design of remote customer service system and exception handling process Design a centralized remote customer service system with a standardized ticketing exception handling process to enable rapid remote processing of complex transactions: 1) Remote customer service function: Supports audio and video intercom, remote face-to-face review, remote authorization, and remote terminal operation. One agent can serve multiple stations and achieve 24 / 7 response. 2) Abnormal Handling Process: For scenarios such as ticket invalidation / loss, verification of free documents, free tickets for children, and ticket supplement for exceeding the distance / time limit, a standardized process of "self-service application - intelligent preliminary review - remote review - authorized execution" is designed. More than 40 types of free documents support scanning and uploading + remote verification. Children under 1.3 meters can support remote face review + gate opening authorization.

[0044] (5) Design of a comprehensive payment security system It integrates all types of payment modules and configures multi-layered security protection mechanisms to achieve a balance between convenient payment and secure transactions. 1) Full payment module: Supports multiple payment methods such as cash, WeChat / Alipay / UnionPay QR code scanning, NFC quick payment, facial recognition payment, and digital RMB. Each payment module is independently adapted and supports one-click switching. 2) Security protection mechanism: The transaction data is protected against tampering by an encrypted transmission protocol, a transaction traceability system is built to record data throughout the process, and anti-pry / anti-theft sensors and identity verification encryption modules are configured on the equipment. At the same time, the linkage verification of payment and biometric identification is realized to prevent malicious attacks and wrong charges.

[0045] (6) Ticketing processing method design Based on the above hardware and software architecture, a ticketing processing method for an unattended subway smart ticketing terminal is designed, including three major processes: basic ticketing processing, abnormal ticketing processing, and value-added service processing. The core steps are as follows: 1) Passengers initiate ticketing service requests via the interaction layer / AI voice; 2) The edge system receives requests and performs local data verification. Basic requests are executed directly and the results are returned. Complex / abnormal requests are pushed to the edge for review. 3) Requests that cannot be processed on the side are pushed to the cloud-side remote customer service agent, who completes the review and remote authorization through audio and video intercom; 4) The terminal executes the authorization command and completes the business processing, while synchronizing the transaction data to the edge and cloud sides to achieve full-process data traceability.

[0046] The unmanned smart ticketing terminal and processing method for subways proposed in this application have significant substantive features and remarkable technological advancements compared to existing manual ticket booths and traditional self-service ticketing terminals. Specific implementation benefits are reflected in efficiency, cost, user experience, data, and security. (1) Significantly improved passage efficiency: Covering all ticketing scenarios, including ticketing, top-up, ticket replenishment, exception handling, real-name registration, invoices, and consultation, it achieves 24 / 7 self-service, with no queues during peak hours, and complex ticketing exceptions can be resolved within 1 minute, improving passenger passage efficiency by more than 50%. (2) Significantly reduced operating costs: One terminal can replace the workload of 3-5 manual ticket booth staff, achieving staff reduction and efficiency improvement, saving millions of yuan in labor costs annually. At the same time, the modular hardware design reduces equipment maintenance costs, and the cloud-edge-device collaborative architecture reduces data center construction and operation costs. (3) Comprehensive optimization of passenger experience: AI multimodal interaction (voice + touch screen + face recognition) lowers the operation threshold, the full payment system adapts to different passenger needs, remote customer service realizes "one-click help", and free document verification, free tickets for children and other scenarios do not require human intervention, realizing zero-contact and zero-wait ticketing services; (4) Upgraded data management capabilities: The cloud-edge-device collaborative architecture enables the full-process digital collection and storage of ticketing data, equipment data, and operational data. The cloud-side big data analysis system can uncover passenger flow patterns, equipment operating status, and ticketing business needs, providing data support for rail transit operation decisions and solving the problems of scattered data and delayed statistics in traditional manual ticket booths. (5) Improved system security and reliability: Local offline transactions can be realized on the terminal side in the absence of network, which solves the network dependence problem of traditional centralized architecture; security mechanisms such as encrypted transmission, transaction traceability, and identity verification can prevent transaction data from being tampered with, equipment from being stolen, and payment from being maliciously attacked. At the same time, the fault isolation mechanism can prevent the failure of a single device from affecting the entire system. (6) Strong equipment scalability and adaptability: The modular hardware architecture enables flexible disassembly and upgrading of functional modules through standard interfaces, which can adapt to the ticketing needs of subways in different cities. At the same time, the cloud-edge-device collaborative architecture supports elastic expansion, which can realize rapid deployment from a single station to the entire network.

[0047] This application also provides an unattended subway ticketing processing device, including: The request receiving module is used to receive ticketing service requests input by passengers. The terminal-side processing module is used to perform local data verification after the ticketing service request is parsed by the terminal-side system. When it is determined to be a basic request, the terminal-side system directly calls the local transaction logic to perform processing and generates a first processing result to be fed back to the passenger. The first processing result is then synchronized to the edge data processing platform. The initial review module is used so that when a request is determined to be abnormal, the end-side system uploads the abnormal request to the edge-side data processing platform for intelligent initial review. The forwarding module is used to forward the abnormal request to the cloud-side remote processing system when the edge data processing platform is unable to process the abnormal request. The cloud-side review module is used by the cloud-side remote processing system to perform remote review and identity verification after receiving the abnormal request, and to issue a remote authorization instruction to the terminal system. The result feedback module is used to execute the corresponding ticketing business processing after the terminal system receives the remote authorization instruction, generate a second processing result and feed it back to the passenger, and then synchronize the second processing result to the edge data processing platform and the cloud remote processing system in sequence.

[0048] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0049] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0050] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0051] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0052] 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 network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0053] Furthermore, the functional units in the various embodiments of this application 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.

[0054] 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 device (CMD). Based on this understanding, the technical solution of this application, 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 memory 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 this application. The aforementioned memory 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.

[0055] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0056] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of embodiments of this disclosure upon considering the specification and practicing the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

[0057] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0058] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for unmanned subway ticketing processing, characterized in that, Includes the following steps: Receive ticketing service requests from passengers; The ticketing service request is parsed by the terminal system and then local data is verified. When it is determined to be a basic request, the terminal system directly calls the local transaction logic to execute the processing and generates a first processing result to be fed back to the passenger. The first processing result is then synchronized to the edge data processing platform. When a request is determined to be abnormal, the endpoint system uploads the abnormal request to the edge data processing platform for intelligent preliminary review. When the edge data processing platform is unable to process the abnormal request, it forwards the abnormal request to the cloud-side remote processing system. After receiving the abnormal request, the cloud-side remote processing system performs remote review and identity verification, and issues a remote authorization instruction to the terminal system. After receiving the remote authorization instruction, the terminal system executes the corresponding ticketing business processing, generates a second processing result and feeds it back to the passenger, and then synchronizes the second processing result to the edge data processing platform and the cloud remote processing system in sequence.

2. The unmanned subway ticketing processing method as described in claim 1, characterized in that, After receiving the ticketing service request input by the passenger, and before the terminal system parses it, the following is also included: The facial recognition module is invoked to perform liveness detection and identity verification on passengers. When the verification is successful and the ticketing service request includes a payment requirement, the payment module is triggered to call the facial payment interface to complete the payment.

3. The unmanned subway ticketing processing method as described in claim 1, characterized in that, If a network communication interruption is detected during the execution of the corresponding ticketing business by the terminal system, a local offline transaction mode is activated, and the transaction data is temporarily stored in a local encrypted database. After the network is restored, the transaction data is uploaded to the edge data processing platform and the cloud remote processing system.

4. The unmanned subway ticketing processing method as described in claim 1, characterized in that, The handling of the abnormal request specifically includes: The terminal system controls the document scanning module to collect image information of free documents; The side data processing platform calls the OCR algorithm to perform intelligent preliminary review of the document image information; If recognition fails, the document image information is forwarded to the cloud-based remote processing system for verification. Once the verification is successful, an authorization execution command is issued.

5. The unmanned subway ticketing processing method as described in claim 4, characterized in that, The handling of abnormal requests also includes: The terminal system uses a high-definition camera to collect data on the child's height and facial features. The side data processing platform performs intelligent preliminary review based on a preset height threshold; If the height is determined to be below the preset height, the passage is directly authorized. If the height cannot be determined, the remote identification module is activated, and the cloud-based remote processing system performs remote review before authorizing passage.

6. The unmanned subway ticketing processing method as described in claim 1, characterized in that, While issuing remote authorization commands, the cloud-side remote processing system simultaneously records operation logs and audio / video stream data. The data is encapsulated into tamper-proof transaction data packets through an encrypted transmission protocol and stored in the terminal system, the edge data processing platform, and the cloud-side remote processing system, respectively.

7. The unmanned subway ticketing processing method as described in claim 1, characterized in that, After receiving the first processing result or the second processing result uploaded by the end-side system, the edge-side data processing platform cleans and aggregates the data, filters out invalid data, and then uploads it to the big data analysis system of the cloud-side remote processing system.

8. An unmanned subway ticketing processing device, characterized in that, include: The request receiving module is used to receive ticketing service requests input by passengers. The terminal-side processing module is used to perform local data verification after the ticketing service request is parsed by the terminal-side system. When it is determined to be a basic request, the terminal-side system directly calls the local transaction logic to perform processing and generates a first processing result to be fed back to the passenger. The first processing result is then synchronized to the edge data processing platform. The initial review module is used so that when a request is determined to be abnormal, the end-side system uploads the abnormal request to the edge-side data processing platform for intelligent initial review. The forwarding module is used to forward the abnormal request to the cloud-side remote processing system when the edge data processing platform is unable to process the abnormal request. The cloud-side review module is used by the cloud-side remote processing system to perform remote review and identity verification after receiving the abnormal request, and to issue a remote authorization instruction to the terminal system. The result feedback module is used to execute the corresponding ticketing business processing after the terminal system receives the remote authorization instruction, generate a second processing result and feed it back to the passenger, and then synchronize the second processing result to the edge data processing platform and the cloud remote processing system in sequence.

9. An unmanned subway ticketing processing device, characterized in that, The method includes at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program that, when executed by the processing unit, causes the processing unit to perform the steps of the method according to any one of claims 1 to 7.

10. A storage medium, characterized in that, It stores a computer program that can be executed by an unattended subway ticketing processing device. When the computer program is run on the unattended subway ticketing processing device, it causes the unattended subway ticketing processing device to perform the steps of the method described in any one of claims 1 to 7.

Images