Automated forward train control event data extraction and analysis engine and method thereof
Through automated train control event data extraction and analysis engine, machine learning and natural language processing technology can be used to quickly and accurately identify the root causes of train events, solving the problems of low efficiency and poor accuracy of event analysis in the existing technology, significantly reducing downtime time.
Patent Information
- Application Number
- CN202380034093.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-04-14
- Filing Date
- 2023-03-30
- Publication Date
- 2024-12-06
AI Technical Summary
The prior art is difficult to quickly and accurately extract and analyze the root causes of train downtime from a large number of train event logs, resulting in extended downtime and increased errors.
An automated train-controlled event data extraction and analysis engine is used to identify event data through machine learning algorithms and natural language processing, generate detailed reports and notify relevant personnel.
Identifying and analyzing the root causes of train events in minutes reduces downtime, improves analysis efficiency and accuracy, and reduces the possibility of manual inspection errors.
Smart Images

Figure CN119095757A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates generally to management of positive train control events, and more particularly to an automated positive train control event data extraction and analysis engine and methods thereof. Background Art
[0002] Managing a fleet of trains is a complex system. Determining the root cause of an incident that brings a train to a complete stop can be a time-consuming and laborious task. The array of components involved in the system makes it nearly impossible to rely on a single source of data to identify and resolve issues. Organizations managing a fleet of trains can quickly become overwhelmed by the sheer volume of incidents occurring on the train network, not to mention the time required to identify the root cause of an incident, record the highlights of the incident, and notify the appropriate personnel. Manual analysis of a train incident can take hours to identify the root cause and days to resolve the issue. Further adding to the complexity is the fact that the Positive Train Control (PTC) system can generate countless braking events associated with a single train operation. For example, when a train is in danger of exceeding its posted speed, it initiates the application of a PTC penalty that affects the train's speed - known as a PTC or braking event.
[0003] While organizational approaches and personnel are useful in identifying and managing root cause analysis of train incidents, the inspection process is often still a manual operation. Railroad personnel are still required to inspect these fleets and make the final judgment on the cause of the train incident. These personnel may misclassify incidents, record train system logs incorrectly, and require regular training. Most incidents typically require about an hour of manual analysis for root cause analysis, and some can take more than a full day. In addition, the root cause can be caused by a variety of factors, such as signal loss, train problems, hardware or software problems, or human error. If the root cause of an enforcement is a signal or field problem, the railroad may conduct multiple enforcements at the same location when other trains attempt to pass. Faced with such a complex system, it is not enough to manually inspect a fleet of trains. Summary of the invention
[0004] The present disclosure achieves technical advantages as a system and method for automating workflow and performing root cause analysis of positive train control (PTC) enforcement events using an automated positive train control event data extraction and analysis engine. The system can accurately detect enforcement events and find the root causes of such events. The system can provide users with an interface for monitoring enforcement events by collecting a list of data that characterizes the enforcement events, and analyzing the data to evaluate and determine the root causes of the enforcement events. The system can also use an extraction model to extract key information from the train system log of the train to generate an activity window, providing a comprehensive scope for the analysis model to analyze the enforcement events. In addition, the system can also provide users with reliable and accurate information about the root causes of enforcement events.
[0005] The present disclosure solves the following technical problems: Provide an automated tool for identifying train events that can provide the root cause of enforcement events in a shorter time than manual inspection by extracting relevant data from a large amount of data, without having to consider a large amount of data from multiple different sources. For example, enforcement actions can include events that cause locomotives to stop completely based on various safety policy violations. In contrast, traditional systems rely solely on manual inspection techniques, which may generate a large number of errors, thereby increasing the pressure on trains to stop on the track. Since trains and events on the railway network generate a large amount of log information every day, identifying the relevant data that needs to be processed is a major obstacle that needs to be overcome.
[0006] The present disclosure provides a technical solution that is lacking in traditional systems through an extraction and analysis engine that can identify train events, retrieve train system logs, translate and convert structured and unstructured data into predefined standard formats, perform root cause analysis of PTC events, and notify subscribers of solutions. The extraction and analysis engine can implement one or more extraction models to identify relevant data. The present disclosure provides improved system performance through an extraction and analysis engine (and corresponding models) that can parse multiple PTC event-related files to retrieve only relevant details related to a specific PTC event and implement user-defined operations and scenario-based implementations. Advantageously, an automated positive train control event data extraction and analysis engine and method are provided that can perform root cause analysis to determine the cause of a PTC brake event without user interaction to alleviate the repetitive tasks involved in brake event reporting. In another embodiment, the automatic extraction model and the automatic analysis model can automatically (without user interaction) extract relevant log data and analyze the brake event data using a machine learning algorithm. For example, the PTC event automated extraction / analysis engine can implement a natural language processing keyword detection algorithm to identify relevant information. Once the root cause is determined, the system can generate a detailed report to transmit to all event subscribers and end the event. In addition, the system can also classify braking events for reporting, escalate events for review, and provide in-depth braking event analysis. The system can also provide at least the following functions: On-site or historical analysis; Multiple onboard software versions that can be processed in parallel; Tracking problem resolution; ·alarm; User subscription; Extensive classification models; Continuous improvement; System reports; Advanced classification; and Data retention.
[0007] The present disclosure technically goes beyond the traditional manual analysis of train events by providing an automated data extraction and analysis engine to effectively identify relevant data in countless log data and process the data using data analysis techniques within minutes or even seconds to determine the root cause, thereby minimizing train downtime. Therefore, the present disclosure discloses concepts that are inseparable from computer technology, so that the present disclosure provides a technical advantage of simplifying the data extraction and data analysis process by providing only the relevant information required to identify and analyze a specific train event. Using this analysis, manual inspection issues can be resolved faster, minimizing delays in train functions, while optimizing train event investigation time.
[0008] As events occur, the system can identify new events and download the necessary logs. Once the logs are downloaded, unzipped, and stored in a directory for the system to begin processing, the event can be stored in a queue for execution at the next instantiation to begin processing and analyzing the event. The system can implement control logic, machine learning, and / or system services to verify event times, identify the primary CPU during execution, verify that the event occurred, determine the appropriate system component software versions, and initiate advanced system health scans to ensure that the data is reliable to perform event analysis. Once completed and the event is cleared for processing, the system can select the appropriate extraction model to obtain the appropriate data point. As software versions change and adapt, additional extraction models are developed and presented to allow system selection based on at least part of the event analysis. When the extraction model begins, all logs can be moved into a dictionary to provide a unique identifier for each line of log data. The extraction model can implement pre-built regular expressions or data manipulation practices (such as splitting) when compiling delimited (structured) lines to obtain insights and valuable information. The logs can be processed according to a unified data structure to normalize the data. The system also allows for the extraction of data points, calculation of variables, and the creation of event time windows for the data.
[0009] In another embodiment, when prioritizing data points in the logs, the system can generate data points around how the event occurred and when the event occurred compared to the execution time. These time windows can simulate how manual analysis is performed. For example, the time window can be seconds, minutes, or hours, and can be positive or negative relative to the execution time (occurring before or after).
[0010] The data can then be transformed and processed by one or more analytical models instantiated on one or more devices. In another embodiment, the analytical models can be created using a variety of data science methods, including decision trees, classification, and clustering, among others. Once the model is developed, the system can convert the model into a custom algorithm that can be implemented by control logic, servers, processors, or other suitable devices. The analytical mode can be software-specific and have a hierarchical structure. In another embodiment, defect analysis can be completed first. If a defect is found, a conclusion can be drawn because the defect is determined to be the cause of the main problem - rather than a response to the defect. Second, the incident can be processed based on the model created over time about engineer interactions, system component responses, situational behaviors, etc. The model can then be exited and a second (or subsequent) model can be instantiated with the data. If the second model is inconsistent with the first model, the system can determine the correct model and close the incident. For each model endpoint (for example, in two models), a unique identifier can be created. The unique identifier allows the system to track and dynamically update the model endpoint from the back end by updating the database value of the specific unique identifier. In another embodiment, if a root cause is not determined, the analytical model can create a high-level classification for the incident by combining the target type, target description, and the last banner displayed to the engineer before execution, as well as other parameters and values, thereby providing the user with a level of detail about the incident without the need for manual investigation.
[0011] In another embodiment, using the data retrieved from the extraction and analysis model, the system can create a detailed summary of the events that led to the execution along with the assigned root causes. These events include: the time the train started, the speed of the train at the time of the execution, location details, warnings that may have occurred, train configuration details, PTC component information, execution type, braking type, etc. These data points combined together can provide the end user with an understanding of what happened and how the system made its decision.
[0012] When a root cause (or high-level classification) is determined, the system can use parameters from AES to determine who needs to be notified of the incident and the severity of the notification. If an alert is assigned to an analytical model identifier, the appropriate rail team can receive an email notifying them to take additional immediate steps to reduce the chance of a repeat violation.
[0013] It is an object of the present invention to provide a system for automating a workflow and performing root cause analysis of a data structure. It is another object of the present invention to provide a method for automating a workflow and performing root cause analysis of a data structure. It is another object of the present invention to provide a computer-implemented method for automating a workflow and performing root cause analysis of a data structure. It is another object of the present invention to provide a method for determining the cause of a PTC brake event without user interaction. These and other objects are provided by at least the following embodiments.
[0014] In one embodiment, a system for automating workflows and performing root cause analysis on data structures includes a memory having a database with a train system log; and a networked computer processor operably coupled to the memory and capable of executing machine-readable instructions to perform program steps, the program steps including receiving a message including information about a train event; retrieving a train system log corresponding to the message to identify at least one feature corresponding to the train event, such as the event time, the main central processing unit (CPU) during the execution of the train event, the appropriate component software version, and a high-level system health scan; verifying the actual occurrence of the train event based on the at least one feature; identifying an extraction model to generate data, such as a time window of the train event corresponding to the train system log; transforming the data to generate extracted data; analyzing the extracted data using an analysis model to generate an analysis result; if the analysis result does not include a root cause, creating a high-level classification for the train event through the analysis model and assigning a unique identifier (ID) to the analysis result; if the analysis result includes a root cause, assigning an alert ID to the analysis result through the analysis model; and sending a summary of the corresponding unique ID or alert ID to a user using an automatic email system (AES). Wherein, the summary includes multiple events, such as the time of train activities, the speed of the train during the execution of the train event, the location details of the train, warnings to the train, the configuration details of the train, positive train control (PTC) component information, execution type and braking type. Wherein the high-level classification includes target type, target description and banner. Wherein, the program steps also include: analyzing the extracted data using a defect detection analysis model; if a defect is detected, classifying the root cause as a defect; if no defect is detected, analyzing the extracted data using a historical analysis model. Wherein the historical analysis model can be based on historical data such as previous engineer interactions, system component responses and situational behaviors. Wherein, the train system log includes structured data or unstructured data. Wherein the extraction model uses regular expressions or data manipulation practices. Wherein, the analysis model includes a decision tree model, a classification model, or a clustering model.
[0015] In another embodiment, a method for automating a workflow and performing root cause analysis on a data structure includes receiving a message including information about a train event; retrieving a train system log corresponding to the message to identify at least one feature corresponding to the train event, such as event time, main CPU during execution of the train event, appropriate component software version, and high-level system health scan; verifying the occurrence of the train event based on at least one feature by a processor; instantiating an extraction model by a processor to generate data, such as a time window of the train event corresponding to the train system log; transforming the data by a processor to generate extracted data; analyzing the extracted data using an analysis model to generate an analysis result; if the analysis result does not include a root cause, generating a high-level classification of the train event by the analysis model and assigning a unique ID to the analysis result; if the analysis result includes a root cause, assigning an alarm ID to the analysis result by the analysis model; and generating and transmitting a summary (e.g., corresponding to a unique ID or an alarm ID) to a user using, for example, AES. The detailed summary includes multiple events such as time of train activity, train speed during execution of the train event, location details of the train, warnings to the train, configuration details of the train, PTC component information, execution type, and brake type. The high-level classification includes target type, target description, and banner. Wherein, the program steps further include: analyzing the extracted data using a defect detection analysis model; if a defect is detected, classifying the root cause as a defect; if no defect is detected, analyzing the extracted data using a historical analysis model. Wherein the historical analysis model can be based on historical data such as previous engineer interactions, system component responses, and situational behaviors. Wherein, the train system log includes structured data or unstructured data. Wherein, the extraction model uses regular expressions or data manipulation practices. Wherein, the analysis model includes a decision tree model, a classification model, or a clustering model.
[0016] In another embodiment, a computer-implemented method for automating a workflow and performing root cause analysis of a data structure includes receiving a message including information about a train event; retrieving a train system log corresponding to the message to identify at least one feature corresponding to the train event, such as event time, main CPU during execution of the train event, appropriate component software version, and high-level system health scan; verifying the actual occurrence of the train event based on at least one feature; identifying an extraction model to generate data, such as a time window of the train event corresponding to the train system log; transforming the data to generate extracted data; analyzing the extracted data using an analysis model to generate an analysis result; if the analysis result does not include a root cause, creating a high-level classification for the train event through the analysis model and assigning a unique ID to the analysis result; if the analysis result includes a root cause, assigning an alarm ID to the analysis result through the analysis model; and sending a detailed summary corresponding to the unique ID or the alarm ID to a user using AES. The detailed summary includes multiple events such as time of train activity, train speed during execution of the train event, location details of the train, warnings to the train, configuration details of the train, PTC component information, execution type, and brake type. The high-level classification includes target type, target description, and banner. Wherein, the program steps further include: analyzing the extracted data using a defect detection analysis model; if a defect is detected, classifying the root cause as a defect; if no defect is detected, analyzing the extracted data using a historical analysis model. Wherein the historical analysis model can be based on historical data such as previous engineer interactions, system component responses, and situational behaviors. Wherein, the train system log includes structured data or unstructured data. Wherein, the extraction model uses regular expressions or data manipulation practices. Wherein, the analysis model includes a decision tree model, a classification model, or a clustering model.
[0017] In another embodiment, a method for determining the cause of a PTC brake event without user interaction is provided, comprising: receiving a brake event from a PTC system; extracting data from the brake event; converting the extracted data into one or more dictionaries; analyzing the dictionaries through a machine learning module to identify the cause of the event using a training data model; and assigning a unique analysis code to each dictionary to control the model output. Wherein the dictionary converts the data into a predetermined format. Wherein the training data parameters include real-time or historical data. Wherein the training data model includes user-based parameters. Wherein the method also includes sending a notification to all event subscribers. Wherein the method also includes classifying the brake event into one or more predetermined categories. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] The present disclosure will be easily understood by the following detailed description in combination with the accompanying drawings, which illustrate the principles of the present disclosure by way of example. The accompanying drawings show the design and practicality of one or more exemplary embodiments of the present disclosure, wherein the same elements are represented by the same reference numerals or symbols. The objects and elements in the accompanying drawings are not necessarily drawn in proportion, ratio or precise positional relationship. Instead, the focus is on illustrating the principles of the present disclosure.
[0019] Figure 1 An automated workflow system according to one or more embodiments of the present disclosure is shown;
[0020] Figure 2 A block diagram of an automated workflow system according to one or more embodiments of the present disclosure is shown;
[0021] Figure 3 A flowchart illustrating example message processing control logic according to one or more embodiments of the present disclosure is shown;
[0022] Figure 4 A flowchart illustrating example message processing control logic according to one or more embodiments of the present disclosure is shown;
[0023] Figure 5 A flow chart illustrating an example watchdog control logic according to one or more embodiments of the present disclosure is shown;
[0024] Figure 6 A flowchart illustrating example data extraction control logic according to one or more embodiments of the present disclosure is shown;
[0025] Figure 7 A block diagram showing an automated workflow system interface according to one or more embodiments of the present disclosure;
[0026] Figure 8 An embodiment of an automated workflow system interface according to one or more embodiments of the present disclosure is shown;
[0027] Fig. 9 A flowchart illustrating example termination control logic according to one or more embodiments of the present disclosure; and
[0028] Fig.10 A flow chart illustrating example braking event handling control logic according to one or more embodiments of the present disclosure is shown. DETAILED DESCRIPTION
[0029] The disclosure and its various features and advantageous details set forth in the following written description will be more fully explained with reference to the non-limiting examples included in the accompanying drawings and the contents detailed in the specification. Descriptions of well-known components are omitted herein so as not to unnecessarily obscure the main features described herein. The following examples are intended to facilitate understanding of the implementation and practice of the disclosure. One of ordinary skill in the art will understand the disclosure as meaning that any suitable combination of the following functions or exemplary embodiments can be combined to achieve the claimed subject matter. The disclosure includes the number of representative species within the genus, or structural features common to members of the genus, so that one of ordinary skill in the art can identify members of the genus. Therefore, these examples should not be construed as limiting the scope of the claims.
[0030] A person of ordinary skill in the art will understand that any system claim set forth herein encompasses all elements and limitations disclosed therein, and therefore requires that each system claim be considered as a whole. Any reasonably foreseeable item that has a functional relationship with a claim also falls within the relevant scope. Pursuant to MPEP §904, the examiner searches for prior art disclosed in patents and other published documents (i.e., non-patent literature) after thoroughly understanding the invention disclosed and claimed in the non-provisional application. Therefore, as evidenced by the issuance of this patent, the prior art fails to disclose or teach the elements and limitations set forth in the claims supported by the specification and drawings, and therefore the set forth claims are patentable under 35 U.S.C. §§101, 102, 103, and 112.
[0031] Figure 1 A schematic diagram of an automated workflow system 100 according to one or more embodiments of the present disclosure is shown. The system 100 may include one or more servers 102 having one or more processors 104, a memory 134, machine-readable instructions 106, including a file collection module 108, a message identification module 110, a log collection module 112, an information parsing module 114, a log download module 116, an automated initialization module 118, an automated workflow module 120, an extraction module 122, an analysis module 124, an event monitoring module 126, an automated production module 128, and other related modules. The server 102 may be operably coupled to one or more clients via a network 140. The client may be a physical device (e.g., a mobile phone 150, a laptop 152, an external sensor 154, a desktop computer, a wearable device, or other suitable device), a program, or an application. In another embodiment, the client may include a mobile phone 150 having a mobile application configured to communicate with the server 102 via the network 140.
[0032] The aforementioned system components (e.g., server 102 and client 150, 152, 154, 156, etc.) can be coupled to each other in a communication manner through network 140, so that data can be transmitted. Network 140 can be the Internet, an intranet, or other suitable networks. Data transmission can be encrypted, unencrypted, through a virtual private network (VPN) tunnel, or other suitable communication methods. Network 140 can be a wide area network (WAN), a local area network (LAN), a personal area network (PAN), or other suitable network types. Network communications between clients, server 102, or any other system components can be encrypted using Very Good Privacy (PGP), Blowfish, Twofish, Triple Data Encryption Standard (3DES), Hypertext Transfer Protocol Security (HTTPS), or other suitable encryption. System 100 can be configured to provide communication via an application programming interface (API), a peripheral component interface (PCI), PCI-Express, an American National Standards Institute (ANSI)-X12, Ethernet, Wi-Fi, Bluetooth, or other suitable communication protocols or media through various systems, components, and modules disclosed herein. Additionally, third party systems and databases may be operatively coupled to the system components via the network 140 .
[0033] Data transmitted to and from components of the system 100 (e.g., server 102 and client) may include any format, including JavaScript Object Notation (JSON), Transmission Control Protocol (TCP) / Internet Protocol (IP), Extensible Markup Language (XML), Hypertext Markup Language (HTML), American Standard Code for Information Interchange (ASCII), Short Message Service (SMS), Comma Separated Values (CSV), Representational State Transfer (REST), or other suitable formats. Data transmissions may include messages, flags, headers, header attributes, metadata, and / or bodies, or be encapsulated and packaged in any suitable format therewith.
[0034] The server 102 may be implemented in hardware, software, or a suitable combination of hardware and software, and may include one or more software systems running on one or more servers, with one or more processors 104, and access to a memory 134. The server 102 may include electronic memory, one or more processors, and / or other components. The server 102 may include communication lines, connections, and / or ports to enable information to be exchanged through a network 140 and / or other computing platforms. The server 102 may also include multiple hardware, software, and / or firmware components that operate together to provide the functionality attributed to the server 102 herein. For example, the server 102 may be implemented by a computing platform cloud computing that operates together as the server 102, including software as a service (SaaS) and platform as a service (PaaS) functionality. In addition, the server 102 may include a memory 134.
[0035] The memory 134 may include electronic storage, which may include non-transitory storage media that electronically stores information. The electronic storage media of the electronic storage may include one or both of system storage and / or removable storage that may be provided integrally with the server 102 (e.g., substantially non-removable), wherein the removable storage may be removably connected to the server 102 via, for example, a port (e.g., a universal serial bus (USB) port, a firewire port, etc.) or a drive (e.g., a disk drive, etc.). The electronic storage may include one or more optically readable storage media (e.g., optical disks, etc.), magnetically readable storage media (e.g., magnetic tape, magnetic hard disk, floppy disk drive, etc.), charge-based storage media (e.g., erasable programmable read-only memory (EEPROM), random access memory (RAM), etc.), solid-state storage media (e.g., flash drives, etc.), and / or other electronically readable storage media. The electronic storage may include one or more virtual storage resources (e.g., cloud storage, virtual private networks, and / or other virtual storage resources). The electronic storage may include a database, or a public or private distributed ledger (e.g., blockchain). The electronic storage may store machine-readable instructions 106, software algorithms, control logic, data generated by a processor, data received from a server, data received from a computing platform, and / or other data that may enable a server to operate as described herein. The electronic storage may also include third-party databases accessible via the network 140.
[0036] The processor 104 may be configured to provide data processing capabilities in the server 102. Thus, the processor 104 may include one or more of a digital processor, an analog processor, a digital circuit designed to process information, an analog circuit designed to process information, a state machine, and / or other mechanisms for electronically processing information (e.g., a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC)). The processor 104 may be a single entity or may include multiple processing units. These processing units may be physically located within the same device, or the processor 104 may represent processing functionality of multiple devices or software functionality that operates separately or in conjunction. A networked computer processor may be a processor 104 that is operably coupled to a network 140. A networked computer processor may be operably coupled to other processors, databases, or components.
[0037] The processor 104 may be configured to execute the machine-readable instructions 106 or the machine learning module through software, hardware, firmware, some combination of software, hardware and / or firmware, and / or other mechanisms for configuring processing capabilities on the processor 104. As used herein, the term "machine-readable instructions" may refer to any component or set of components that perform the functionality attributed to the machine-readable instruction component 106. This may include one or more physical processors 104 during execution of processor-readable instructions, processor-readable instructions, circuitry, hardware, storage media, or any other component.
[0038] The server 102 may be configured with machine-readable instructions having one or more functional modules. The machine-readable instructions 106 may be implemented on one or more servers 102 having one or more processors 104 and access to a memory 130. The machine-readable instructions 106 may be a single networked node or a machine cluster, which may include a distributed architecture of multiple networked nodes. The machine-readable instructions 106 may include control logic for implementing various functions, as described in more detail below. The machine-readable instructions 106 may include certain functions related to the system 100. In addition, the machine-readable instructions 106 may include smart contracts or multi-signature contracts that may process, read, and write data to a database, a distributed ledger, or a blockchain.
[0039] Figure 2 A schematic diagram of an automated workflow system 200 according to one or more embodiments of the present disclosure is shown. The automated workflow system 200 may include a document retrieval management system 202, a watchdog system 204, and an automated production system 206. Although some embodiments may be directed to identifying the root cause of a PTC brake event, the automated workflow system 200 may be used to automate workflows to identify the root cause of various types of events and systems, such as policy enforcement events, repeat offender notifications, and permission notification systems.
[0040] In one embodiment, the document retrieval management system 202 may include a file collection module 108, a message identification module 110, a log collection module 112, and an information parsing module 114. The file collection module 108, the file parsing module 110, the log collection module 112, and the information parsing module 114 may implement one or more algorithms to facilitate the retrieval of files and railway event logs of various systems, including status, selection, and authentication algorithms. The algorithm and its associated thresholds and / or signatures may be programmable to suit specific railway events, applications, functions, facilities, or other requirements. The document retrieval management system 202 may be configured to retrieve and modify files and logs (sent to a client or obtained from a client or server) associated with one or more execution events or other appropriate activities. In another embodiment, the document retrieval management system 202 may generate one or more elements to be displayed on a user device. These elements may provide additional information related to the railway event management status. For example, the document retrieval management system 202 may generate a notification and display it on the client to indicate file collection, log parsing, automated workflow initialization, railway event processing, errors, or other appropriate information. In addition, system symbols may also be displayed on the client to indicate task, inspection, or analysis status.
[0041] The file collection module 108 may receive incoming messages regarding railroad event notifications. For example, railroad event notifications may include mandatory events, such as PTC brake events. In one embodiment, the file collection module 108 may receive incoming messages from a file retrieval manager (FRM). For example, the incoming message may correspond to one or more execution events. In another embodiment, the file collection module 108 may transmit outgoing messages to the FRM. For example, the outgoing message may request a train system log corresponding to one or more mandatory events. In another embodiment, the file collection module 108 may receive a notification indicating that a train system log is available.
[0042] In another embodiment, the file collection module 108 can generate an authentication token for a specific user, session, or request. In another embodiment, the file collection module 108 can access the network 140 without user credentials. In another embodiment, the file collection module 108 can use user data stored in the client to generate an authentication token. For example, a user can provide valid credentials (including username and password, biometrics, multi-factor authentication, or other suitable credentials) through a login page or screen to access the client and / or the automated workflow system 200, and these credentials and the user's information (such as name, username, employee number, etc.) can be stored in the client or server. In another embodiment, the file collection module 108 can process at least a portion of the credentials and / or user information to generate an authentication token. For example, the authentication token can be generated as a JSON Web Token (JWT), through a dongle or key card, new authentication tokens can be generated periodically according to a known algorithm, using an authenticator application on the client or sent on demand via SMS, by hashing at least a portion of the login credentials, or other suitable methods.
[0043] In another embodiment, the authentication token may allow for single sign-on authentication from the client to the server and / or memory. In another embodiment, the file collection module 108 may operate without a user interface. In another example, the file collection module 108 may provide a user interface for a user to access the file collection module 108. The automated workflow system 200 may utilize the file collection module 108 to provide a user interface for receiving relevant data.
[0044] The message identification module 110 can classify the received messages and notifications. In one embodiment, the message identification module 110 can receive information about execution events from incoming messages and notifications. For example, the message identification module 110 can classify incoming messages as mandatory messages or status requests and classify notifications as log status. In another embodiment, the message identification module 110 can identify train system logs for execution events. For example, the message identification module 110 can identify characteristics of the execution event. In another example, these characteristics can include event time, the main CPU that monitors the train during execution, appropriate component software versions, high-level system health scans, and other relevant characteristics. In another example, the message identification module 110 can verify the incoming message to identify whether the execution event actually occurred based on at least one characteristic.
[0045] The log collection module 112 may receive the train system log. In one embodiment, the train system log is sent by the FRM. In another embodiment, the log collection module 112 may download the train system log from an external memory. The train system log may correspond to a default onboard log set for at least one CPU on the train. The train system log may display characteristics of the brake event execution. In another embodiment, the log collection module 112 may store the train system log for future access.
[0046] The information parsing module 114 can parse incoming messages and notifications to obtain relevant information. For example, the relevant information can include information about the execution event. In another example, the incoming message can include information such as user ID, employee information on the train, the employee requesting the information, the train location, and other relevant information. In one embodiment, the information parsing module 114 can establish a connection with a database. For example, the information parsing module 114 can receive incoming messages from a database and transmit relevant information to the database.
[0047] In one embodiment, the watchdog system 204 may include a log download module 116, an automated initialization module 118, and an automated workflow module 120. The log download module 116, the automated initialization module 118, and the automated workflow module 120 may implement one or more algorithms to facilitate status monitoring of train system logs, including file acquisition, event monitoring, and service enablement algorithms. The algorithm and its associated thresholds and / or signatures may be programmable to suit a specific railway event monitoring system, application, function, facility, or other requirement. The watchdog system 204 may be configured to send and receive messages related to status monitoring or other appropriate activities to a client or server. In another embodiment, the watchdog system 204 may generate one or more elements to be displayed on the client. These elements may provide additional information related to workflow automation. For example, the watchdog system 204 may generate a notification and display it on the client to indicate a status update, a system component log status, the start of an automated service, or other appropriate information. In addition, a system symbol may be displayed on the client to indicate the management status.
[0048] In one embodiment, the log download module 116 may query the internal service queue. For example, the internal service queue may be located at an IP address. In another example, the log download module 116 may query the internal service queue at a specified frequency. In another example, the specified frequency may include a user-set value or a predetermined frequency. In another example, the scheduled frequency may include execution every six minutes. In another embodiment, the log download module 116 may determine whether the internal service queue includes a new execution message. For example, the control logic 500 may prompt the internal service queue to notify the log download module 116 of any updated execution messages. If the internal service queue lacks a new execution message, the control logic 500 does not perform any operation. If the internal service queue includes a new execution message, the log download module 116 continues to generate records. For example, the record may include a set of execution events based on the execution message from the internal service queue. In another example, the log download module 116 may store the record in a database. In another embodiment, the log download module 116 may parse a file retrieval system to obtain a train system log corresponding to a new mandatory execution event. For example, the file retrieval system may include an FRM. In another example, the train system log may include a downloadable file.
[0049] In another embodiment, the log download module 116 can determine whether the train system log is available. For example, the log download module 116 can determine whether the train system log is available in the file retrieval system. In another example, because the train system log may lag behind, the train system log may not be generated when the log download module 116 checks. If the train system log is not available, the log download module 116 repeats the inspection process after a period of time. For example, the time period can be 49 hours. If the train system log is available, the log download module 116 continues to receive the train system log. For example, the log download module 116 can receive the train system log from the file retrieval system. In another example, the log download module 116 can receive the train system log in a downloadable manner. In another example, the log download module 116 can receive the train system log in a virtual manner (e.g., a cloud environment).
[0050] In another embodiment, the log download module 116 may update the status of the train system log in the record. For example, the log download module 116 may update the record to indicate whether the train system log is available. In one example, the log download module 116 may determine whether the train system log includes information about multiple CPUs on the train.
[0051] In one embodiment, the automation initialization module 118 can identify whether the automation service is being executed. For example, the automation initialization module 118 can determine whether the automation service is being executed on a specified server. In another example, the specified server can include a specified IP address. In another example, the automation initialization module 118 can determine whether the automation service is being executed based on network traffic on the specified IP address, network traffic on the specified server, or other methods. If the automation service is not currently being executed, the automation initialization module 118 can continue to execute the automation service. For example, the automation initialization module 118 can execute the automation service by executing the initialization instruction of the automation service. If the automation service is currently being executed, the automation initialization module 118 can continue to execute the automation process. For example, the automation process can include algorithms, applications, and functions from the automation production system 206. In another example, the algorithms, applications, and functions can include one or more of the extraction module 122, the analysis module 124, the event monitoring module 126, and the automation production module 128. In another example, the automation initialization module 118 can execute the automation process by executing the initialization instruction of the automation process.
[0052] The automated workflow module 120 may receive processed events. For example, the processed events may include results from an automated process. In another example, the processed events may include a root cause for executing the event. In another example, the automated workflow module 120 may receive processed events from a specified server. In another example, the automated workflow module 120 may store the processed events to an automated production server. In one embodiment, the automated workflow module 120 may generate a notification when the automated process is completed. For example, the notification may correspond to the results of the processed event. In another example, the automated workflow module 120 generates a notification for a set of stakeholders of the processed event. In another example, the automated workflow module 120 sends the notification to the stakeholders via email. In one embodiment, the automated workflow module 120 may transfer the event file to a completed directory. For example, the event file may include information about the processed event. In another example, the completed directory may include a file server specific to the processed event.
[0053] In one embodiment, the automated production system 206 may include an extraction module 122, an analysis module 124, an event monitoring module 126, and an automated production module 128. The extraction module 122, the analysis module 124, the event monitoring module 126, and the automated production module 128 may implement one or more algorithms to facilitate automated workflows and identify the root causes of train events, including extraction, analysis monitoring, and event monitoring algorithms. The algorithm and its associated thresholds and / or signatures may be programmable to suit a specific railway event monitoring system, application, function, facility, or other requirement. The automated production system 206 may be configured to send and receive messages related to workflow automation or other suitable activities to a client or server. In another embodiment, the automated production system 206 may generate one or more elements to be displayed on a user device. These elements may provide additional information related to the root cause analysis. For example, the automated production system 206 may generate a notification and display it on the client to indicate that the root cause has been identified, the train system log, event monitoring, or other suitable information has been extracted. In addition, system symbols may be displayed on the client to indicate the event status, analysis completion, or identified root cause.
[0054] In one embodiment, the extraction module 122 may receive data from a file server. For example, the data may correspond to a train system log that includes features of an enforcement event. In another example, the file server may include a training system log from multiple enforcement events. In another embodiment, the extraction module 122 may collect data before and after the enforcement event to generate a time window. For example, the data may correspond to a train system log. In another example, the time window may include time measurements before the enforcement event, after the enforcement event, or before and after the enforcement event. In another example, the time window may include seconds, minutes, or hours associated with the enforcement event. In another example, the extraction module 122 may compare the time of enforcement with the data to verify whether the enforcement event actually occurred.
[0055] In another embodiment, the extraction module 122 may tag the data with a unique identifier. For example, the extraction module 122 may tag the train system log according to the features. In another embodiment, the extraction module 122 may determine whether the data is structured. For example, when the information in the data is classified in a predetermined manner, the data may be structured. In another example, when the information in the data may be classified in a manner different from the predetermined manner or is not classified at all, the data may be unstructured. In another embodiment, when the data is unstructured data, the extraction module 122 may identify patterns in the unstructured data to convert the data into structured data and extract the data. In another embodiment, the extraction module 122 may convert the unstructured data into structured data by organizing the unstructured data according to a predetermined data structure. The extraction module 122 may convert the unstructured data by assigning elements of the unstructured data to one or more categories, fields, or metadata. In another embodiment, when the data is structured, the extraction module 122 may extract the data. In another example, the extraction module 122 may extract the data using a regular expression. In another example, a regular expression may include a sequence of characters that defines a search pattern. In another example, the extraction module 122 may use data manipulation techniques to extract data. In another example, the data manipulation techniques may include using commercial software tools, such as Or a custom data tool. In another embodiment, the extraction module 122 transmits the extracted data to the analysis module 124.
[0056] In one embodiment, the analysis module 124 may analyze the extracted data to generate an analysis result. For example, the analysis result may include whether the analysis module 124 has determined the root cause. In another example, the analysis module 124 may include multiple decision steps to determine whether the root cause is established. In another embodiment, the analysis module 124 may use a defect detection analysis model to analyze the extracted data. For example, the defect detection analysis model identifies the time when the defect occurs during the analysis process. In another example, when a defect occurs, the analysis module 124 classifies the defect as a root cause. In another example, when no defect occurs, the analysis module 124 may use a historical analysis model to analyze the extracted data. In another example, the historical analysis model may be based on historical data, such as previous engineer interactions, system component responses, and situational behaviors. In another example, the analysis module 124 may use a decision tree model, a classification model, or a clustering model to analyze the extracted data. In one embodiment, the analysis module 124, the event monitoring module 126, and the automated production module 128 may form an analysis model.
[0057] In one embodiment, one or more analysis thresholds can determine whether the automated workflow system 206 executes a single analysis model or multiple analysis models. Such adaptive analysis thresholds can change one or more features of the database. In addition, the analysis thresholds are adaptive because the thresholds can change based on historical data, data types, timestamps, or other relevant data. For example, the system can compare the first accuracy of the output of the first analysis model with a preset analysis threshold. The preset analysis threshold can include a user-defined accuracy value. Therefore, when the first analysis model outputs the first root cause of the penalty event, the system can verify whether the first root cause is the cause of the penalty event. In one example, when the first accuracy of the first root cause is lower than the preset analysis threshold, the system can continue with the second analysis model.
[0058] By further example, when the second analysis model is executed, the second analysis model compares the historical data to the penalty event. The historical data may include data about a particular locomotive, a fleet of locomotives, user-defined inputs, or other data related to the penalty event. If the system identifies that the historical data matches the penalty event, the system outputs a second root cause of the penalty event based on the historical data. The second root cause corresponds to a second accuracy. The system may compare the first accuracy of the first root cause with the second root cause to determine whether the two root causes are the same or different.
[0059] In another exemplary embodiment, the system may provide a threshold when comparing the first accuracy and the second accuracy. For example, the system may compare the two accuracies based on subsequent accuracy measurements. The system may initially compare the similarity of the two root causes, and when the two root causes are the same, the system may conclude that the similar root cause is the cause of the penalty event. At the time of the initial measurement, when one of the accuracies is above the analysis threshold, the accuracy above the analysis threshold may correspond to the root cause of the penalty event. When both accuracies are above the analysis threshold, the system may compare the similarity of the two root causes. If the two root causes are the same, the system determines that the similar root cause is the cause of the penalty event. If the two root causes are different, the system may perform another round of comparison. The second round of comparison may include various forms of tiebreakers, such as higher accuracy measurements, user intervention, re-running the analysis, or other forms of determining the root cause.
[0060] In one embodiment, the event monitoring module 126 may receive analysis results from the analysis module 124. In one embodiment, when the analysis results do not include a root cause, the event monitoring module 126 may generate a high-level classification for the execution event and assign a unique ID to the analysis results. For example, the high-level classification may include a message type, a message description, and a banner. In another example, the message type may be a warning to a train before enforcing an event. In another example, the message description may include a description of the warning, including information such as the enforcing event. In another example, the banner may be the last banner displayed to the engineer before enforcing the event. In another embodiment, when the analysis results include a root cause, the event monitoring module 126 may assign an alarm ID to the analysis results.
[0061] In one embodiment, the automated production module 128 can transmit a detailed summary to the user. For example, the detailed summary can include multiple events, such as the time of train operation, the speed of the train during the execution of the train event, the location details of the train, the warning to the train, the configuration details of the train, the PTC component information, the execution type, and the type of braking event. In another example, the detailed summary can correspond to a unique ID or an alarm ID. In another example, the automated production module 128 can transmit the detailed summary via AES. In another example, AES can include a list service of applicable users to be notified. In another embodiment, the automated production module 128 can generate output based on the user list and distribute notifications to users.
[0062] Figure 3 A flow chart of an example message processing control logic 300 according to one or more embodiments of the present disclosure is shown. The message processing control logic 300 can be implemented as an algorithm on the server 102, a machine learning module, a client, a database, or other suitable system. In addition, the message processing control logic 300 can implement or include one or more features of the file retrieval system 202, including the file collection module 108, the message identification module 110, the log collection module 112, and the information parsing module 114. The data lifecycle management control logic 300 can be implemented by software, hardware, an application programming interface (API), a network connection, a network transmission protocol, HTML, DHTML, JavaScript, Dojo, Ruby, Rails, other suitable applications, or a suitable combination thereof.
[0063] The message processing control logic 300 can take advantage of the capabilities of the computer platform to generate multiple processes and threads by processing data simultaneously. By instantiating multiple processes to implement data lifecycle management, the speed and efficiency of the message processing control logic 300 can be greatly improved. However, those skilled in the art of programming will recognize that a single processing thread may also be used and this is within the scope of the present disclosure.
[0064] In step 302, in one embodiment, the control logic 300 may receive an enforcement detection message. For example, the control logic 300 may receive an enforcement detection message from the FRM. In another example, the enforcement detection message may correspond to the enforcement of a braking event applied to the train. In another example, the enforcement detection message may include information such as message length, message payload, employee name, employee ID, employee role on the train, enforcement type, train location, and other relevant information. The control logic 300 proceeds to step 304.
[0065] In step 304, in one embodiment, the control logic 300 may identify whether the execution detection message is written to the disk. For example, the disk may be a local disk of the system executing the control logic 300. If the execution detection message is not written to the disk, the control logic 300 does not perform any operation. If the execution detection message is written to the disk, the control logic 300 proceeds to step 306.
[0066] In step 306, in one embodiment, the control logic 300 may update the internal service queue. For example, the control logic 300 may generate an internal service queue to prioritize the services to be performed. In another example, the control logic 300 may perform the services based on the order of the queue (e.g., first-in, first-out). The control logic 300 proceeds to step 308.
[0067] In step 308, in one embodiment, the control logic 300 may parse the enforcement detection message. For example, the control logic 300 may classify the enforcement detection message. In another example, the control logic 300 may classify the enforcement detection message according to the railway enforcement policy. In another example, the control logic 300 may classify the enforcement detection message as an enforcement event. In one embodiment, the control logic 300 may identify the train system log of the enforcement detection message. For example, the message control logic 300 may identify the characteristics of the enforcement event corresponding to the enforcement detection message. The control logic 300 proceeds to step 310.
[0068] At step 310, in one embodiment, the control logic 300 may identify whether the execution event of the execution detection message is of the first type. For example, the control logic 300 may classify the execution event based on at least one feature. In another example, the first type may be a PTC braking event. If the force detection message is of the first type, the control logic 300 proceeds to step 312. If the force detection message is not of the first type, the control logic 300 proceeds to step 316.
[0069] In step 312 , in one embodiment, the control logic 300 may generate a globally unique identifier (GUID). For example, the control logic 300 may generate a globally unique identifier (GUID) for an execution event. The control logic 300 proceeds to step 314 .
[0070] In step 314, in one embodiment, control logic 300 may send a request message. For example, control logic 300 may transmit the request message to the FRM. In another example, the request message may include a globally unique identifier (GUID) of the execution event. Control logic 300 proceeds to step 316.
[0071] In step 316, in one embodiment, the control logic 300 may write an automation service address. For example, the automation service address may include an IP address to receive multiple automation logs. In another example, the automation log may include a globally unique identifier (GUID) of the execution event and the execution event. The control logic 300 proceeds to step 318.
[0072] In step 318, in one embodiment, the control logic 300 may determine whether an exception occurs when writing the automation service address. For example, the exception may be a network connection error, insufficient storage, an incorrect IP address, and other related exceptions. If an exception occurs, the control logic 300 proceeds to step 320. If no exception occurs, the control logic 300 proceeds to step 322.
[0073] In step 320, in one embodiment, the control logic 300 may write to disk. For example, the control logic 300 may write an execution message to disk. In another example, the control logic 300 may write an exception to disk. In another example, the control logic 300 may write a globally unique identifier (GUID) of the execution event to disk. In another example, the control logic 300 may write all of the foregoing items to disk.
[0074] At step 322, in one embodiment, the control logic 300 may identify whether the execution event of the execution detection message is of the first type. For example, the control logic 300 may classify the execution event based on at least one feature. In another example, the first type may be a PTC braking event. If the mandatory message is of the first type, the control logic proceeds to step 324. If the mandatory message is not of the first type, the control logic 300 proceeds to step 326.
[0075] In step 324, in one embodiment, the control logic 300 may update the execution log. For example, the execution log may include a first-class message log, a first-class information log, an asset status log, and a personnel information log.
[0076] In step 326, in one embodiment, the control logic 300 may update the alternate log. For example, the alternate log may include a second type message log and a second type information log. In another example, the second type may include an alternate execution message.
[0077] Figure 4 A flow chart of an example message processing control logic 400 according to one or more embodiments of the present disclosure is shown. The message processing control logic 400 can be implemented as an algorithm on the server 102, a machine learning module, a client, a database, or other suitable system. In addition, the message processing control logic 400 can implement or include one or more features of the file retrieval management system 202, including the file collection module 108, the message identification module 110, the log collection module 112, and the information parsing module 114. The message processing control logic 400 can be implemented by software, hardware, API, network connection, network transmission protocol, HTML, DHTML, JavaScript, Dojo, Ruby, Rails, other suitable applications, or a suitable combination thereof.
[0078] The message processing control logic 400 can take advantage of the computer platform's capabilities to generate multiple processes and threads by processing data simultaneously. By instantiating multiple processes to implement appending partitioned data to a table in a database, the speed and efficiency of the message processing control logic 400 can be greatly improved. However, those skilled in the art of programming will recognize that a single processing thread may also be used and this is within the scope of the present disclosure.
[0079] In one embodiment, the command or data may be received via user input generated on the client or server, such as a screen click, a slide, a mouse click, a key, a voice command, or other suitable mechanism. In another exemplary embodiment, the inspection command or data may include inspection data having one or more fields, parameters, characteristics, or metadata related to the inspection. Then, the message processing control logic 400 proceeds to step 402.
[0080] In step 402, in one embodiment, the control logic 400 may receive a verification message. For example, the control logic 400 may receive a verification message from the FRM. In another example, the verification message may inform the control logic 400 of the available train system logs. In another example, the verification message may include information such as a globally unique identifier (GUID) of the execution event, the asset type, status, number of available files, file path length of the train system log, and other relevant information. The control logic 400 proceeds to step 404.
[0081] In step 404, in one embodiment, the control logic 400 may identify whether the verification message is written to the disk. For example, the disk may be a local disk of the system executing the control logic 400. If the verification message is not written to the disk, the control logic 400 does not perform any operation. If the verification message is written to the disk, the control logic 400 proceeds to step 406.
[0082] In step 406, in one embodiment, the control logic 400 may update the internal service queue. For example, the control logic 400 may generate an internal service queue to prioritize the services to be performed. In another example, the control logic 400 may perform services based on the order of the queue (e.g., first-in, first-out). The control logic 400 proceeds to step 408.
[0083] In step 408, in one embodiment, the control logic 400 may parse the verification message. For example, the control logic 400 may receive information from the verification message. In another example, the control logic 400 may classify the verification message according to the railway enforcement policy. In another example, the control logic 400 may classify the verification message as a status notification of the availability of the train system log. In one embodiment, the control logic 400 may identify the location of the train system log from the verification message. For example, the message control logic 400 may identify the characteristics of the execution event corresponding to the verification message. The control logic 400 proceeds to step 410.
[0084] In step 410, in one embodiment, the control logic 400 may write an automation service address. For example, the automation service address may include an IP address to receive multiple automation logs. In another example, the automation log may include a globally unique identifier (GUID) of the execution event and the execution event. The control logic 400 proceeds to step 412.
[0085] In step 412, in one embodiment, the control logic 400 may determine whether an exception occurs when writing the automation service address. For example, the exception may be a network connection error, insufficient storage, an incorrect IP address, and other related exceptions. If an exception occurs, the control logic 400 proceeds to step 414. If no exception occurs, the control logic 400 proceeds to step 416.
[0086] In step 414, in one embodiment, the control logic 400 may write to disk. For example, the control logic 400 may write the exception to disk. In another example, the control logic 400 may write a globally unique identifier (GUID) of the execution event to disk. In another example, the control logic 400 may write any, all, or none of the above to disk.
[0087] In step 416, in one embodiment, the control logic 400 may update the execution log. For example, the execution log may include a request message log, a request information log, an asset response log, asset request details and asset files, and other related logs.
[0088] Figure 5 A flow chart of an exemplary watchdog control logic 500 according to one or more embodiments of the present disclosure is shown. The watchdog control logic 500 can be implemented as an algorithm on the server 102, a machine learning module, a client, a database, or other suitable system. In addition, the watchdog control logic 500 can implement or include one or more features of the watchdog system 204, including the log download module 116, the automated initialization module 118, and the automated workflow module 120. The watchdog control logic 500 can be implemented by software, hardware, API, network connection, network transmission protocol, HTML, DHTML, JavaScript, Dojo, Ruby, Rails, other suitable applications, or a suitable combination thereof.
[0089] The watchdog control logic 500 can take advantage of the capabilities of the computer platform to generate multiple processes and threads by processing data simultaneously. By instantiating multiple processes to separate partitioned data, the speed and efficiency of the watchdog control logic 500 can be greatly improved. However, those skilled in the art of programming will recognize that a single processing thread may also be used and this is within the scope of the present disclosure.
[0090] In one embodiment, the command or data may be received via user input generated on a client or server, such as a screen click, a slide, a mouse click, a key, a voice command, or other suitable mechanism. In another exemplary embodiment, the inspection command or data may include inspection data having one or more fields, parameters, characteristics, or metadata related to the inspection. Then, the watchdog control logic 500 proceeds to step 502.
[0091] In step 502, in one embodiment, the control logic 500 may query an internal service queue. For example, the internal service queue may be located at an IP address. In another example, the control logic 500 may query the internal service queue at a specified frequency. In another example, the specified frequency may include a value set by a user or a predetermined frequency. In another example, the planned frequency may include execution every six minutes. The control logic 500 proceeds to step 504.
[0092] In step 504, in one embodiment, control logic 500 may determine whether the internal service queue includes a new execution message. For example, the new execution message may correspond to a new execution event. In another example, control logic 500 may prompt the internal service queue to notify control logic 500 of any updated execution messages. If the internal service queue includes a new execution message, control logic 500 proceeds to step 506. If the internal service queue lacks a new execution message, control logic 500 does not perform any operation.
[0093] In step 506, in one embodiment, the control logic 500 may generate a record. For example, the record may include a set of execution events based on execution messages from an internal service queue. In another example, the control logic 500 may store the record in another database. The control logic 500 proceeds to step 508.
[0094] In step 508, in one embodiment, the control logic 500 may parse a file retrieval system to obtain a train system log corresponding to the new enforcement event. For example, the file retrieval system may include an FRM. In another example, the train system log may include a downloadable file. The control logic 500 proceeds to step 510.
[0095] In step 510, in one embodiment, the control logic 500 may determine whether the train system log is available. For example, the control logic 500 may determine whether the train system log is available in the file retrieval system. In another example, the train system log may not be generated when the control logic 500 checks because the train system log may be delayed. If the train system log is not available, the control logic 500 repeats step 510 after a period of time. For example, the period of time may be 49 hours. If the train system log is available, the control logic 500 continues to execute step 512.
[0096] In step 512, in one embodiment, the control logic 500 may receive the train system log. For example, the control logic 500 may receive the train system log from a file retrieval system. In another example, the control logic 500 may receive the train system log in a downloadable manner. In another example, the control logic 500 may receive the train system log in a virtual manner (e.g., a cloud environment). The control logic 500 proceeds to step 514.
[0097] In step 514, in one embodiment, the control logic 500 may update the status of the train system log in the record. For example, the control logic 500 may update the record to indicate whether the train system log is available. The control logic 500 proceeds to step 516.
[0098] In step 516, in one embodiment, the control logic 500 may determine whether a log is available. For example, the control logic 500 may determine whether the train system log includes information for multiple CPUs on the train. If the log is available, the control logic 500 proceeds to step 518. If the log is not available, the control logic 500 proceeds to step 528.
[0099] In step 518, in one embodiment, the control logic 500 may determine whether the automation service is currently executing. For example, the control logic 500 may determine whether the automation service is currently executing on a specified server. In another example, the specified server may include a specified IP address. If the automation service is not currently executing, the control logic 500 may proceed to step 520. If the automation service is currently executing, the control logic 500 may proceed to step 522.
[0100] In step 520 , in one embodiment, the control logic 500 may perform the automation service. For example, the control logic 500 may perform the automation service by executing an initialization instruction of the automation service. The control logic 500 proceeds to step 518 .
[0101] In step 522, in one embodiment, the control logic 500 may execute an automation process. For example, the automation process may include algorithms, applications, and functions from the automated production system 206. In another example, the algorithms, applications, and functions may include one or more of the extraction module 122, the analysis module 124, the event monitoring module 126, and the automated production module 128. In another example, the control logic 500 may execute the automation process by executing initialization instructions of the automation process. The control logic 500 proceeds to step 522.
[0102] At step 524, in one embodiment, the control logic 500 may receive the processed events. For example, the processed events may include results from an automated process. In another example, the processed events may include a root cause for executing the events. In another example, the control logic 500 may receive the processed events from a specified server. In another example, the control logic 500 may store the processed events to an automated production server. The control logic 500 proceeds to step 526.
[0103] In step 526, in one embodiment, the control logic 500 may generate a notification. For example, the notification may correspond to the result of the processed event. In another example, the control logic 500 may generate a notification for a set of stakeholders of the processed event. In another example, the control logic 500 sends the notification to the stakeholders via email. In one embodiment, the control logic 500 may transfer the event file to a completed directory. For example, the event file may include information about the processed event. In another example, the completed directory may include a file server specific to the processed event.
[0104] In step 528, in one embodiment, control logic 500 may determine whether a time limit has been reached. For example, the time limit may be 49 hours from the completion of step 516. If the time limit has not expired, control logic 500 continues to repeat step 526 until the time limit expires. If the time limit has expired, control logic 500 continues to proceed to step 528.
[0105] In step 530 , in one embodiment, the control logic 500 may update the status to indicate that the train system log is not available.
[0106] Figure 6A flow chart of an example data extraction control logic 600 according to one or more embodiments of the present disclosure is shown. The data extraction control logic 600 can be implemented as an algorithm on the server 102, a machine learning module, a client, a database, or other suitable system. In addition, the data extraction control logic 600 can implement or include one or more features of the automated production system 206, including the extraction module 122, the analysis module 124, the event monitoring module 126, and the automated production module 128. The data extraction control logic 600 can be implemented by software, hardware, API, network connection, network transmission protocol, HTML, DHTML, JavaScript, Dojo, Ruby, Rails, other suitable applications, or a suitable combination thereof.
[0107] The data extraction control logic 600 can take advantage of the capabilities of the computer platform to generate multiple processes and threads by processing data simultaneously. By instantiating multiple processes to implement the deletion of partitioned data, the speed and efficiency of the data extraction control logic 600 can be greatly improved. However, those skilled in the art of programming will recognize that a single processing thread may also be used and this is within the scope of the present disclosure.
[0108] In one embodiment, the command or data may be received via user input generated on a client or server, such as a screen click, a slide, a mouse click, a key press, a voice command, or other suitable mechanism. In another exemplary embodiment, the inspection command or data may include inspection data having one or more fields, parameters, characteristics, or metadata related to the inspection. The data extraction control logic 600 then proceeds to step 602.
[0109] In step 602, in one embodiment, the control logic 600 may receive data from a file server. For example, the data corresponds to a train system log of an enforcement event. In another example, the train system log may include features of the enforcement event, such as the event time, the main CPU of the train monitored during enforcement, the appropriate component software version, a high-level system health scan, and other relevant information. In another example, the control logic 600 may collect data around the time of one of the enforcement events to generate a time window. For example, the data may correspond to a train system log. In another example, the time window may include time measurements before, after, or before and after one or more enforcement events. In another example, the time window may include seconds, minutes, or hours around one or more enforcement events. In another example, the control logic 600 may compare the time of one of the enforcement events with the data to verify whether the enforcement event actually occurred. The control logic 600 proceeds to step 604.
[0110] In step 604 , in one embodiment, the control logic 600 may provide a unique identifier for the data. For example, the unique identifier may correspond to a feature of a train system log. The control logic 600 proceeds to step 606 .
[0111] In step 606, in one embodiment, control logic 600 may determine whether the data is structured. For example, when the information in the data can be classified in a predetermined manner, the data may be structured. In another example, when the information in the data can be classified in a manner different from the predetermined manner or is not classified at all, the data may be unstructured. If the data is unstructured, control logic 600 proceeds to step 608. If the data is structured, control logic 600 proceeds to step 610.
[0112] In step 608, in one embodiment, the control logic 600 can organize the unstructured data. For example, the control logic 600 can identify the pattern of the unstructured data to convert the data into structured data. In another example, the control logic 600 can use a data conversion software tool to convert the unstructured data into structured data. In another example, the control logic 600 can organize the unstructured data to convert the unstructured data into structured data based on various factors. In another example, these factors can include message length, message payload, employee name, employee ID, employee role on the train, law enforcement type, train location, and other relevant information. The control logic 600 proceeds to step 610.
[0113] At step 610, in one embodiment, the control logic 600 may organize the structured data. For example, the control logic 600 may organize the structured data based on various factors of the data. In another example, these factors may include message length, message payload, employee name, employee ID, employee role on the train, law enforcement type, train location, and other relevant information. The control logic proceeds to step 612.
[0114] In step 612, in one embodiment, the control logic 600 may extract data. For example, the control logic 600 may extract data using a regular expression. In another example, the regular expression may include a sequence of characters that defines a search pattern. In another example, the control logic 600 may extract data using a data manipulation technique. In another example, the data manipulation technique may include using a commercial software tool, such as Or a custom data tool. In another embodiment, the control logic 600 transmits the extracted data to an analysis model.
[0115] Figure 7An exemplary block diagram of an automated workflow system interface 700 according to one or more embodiments of the present disclosure is shown. In one embodiment, a user interface 702 may be displayed on a client. For example, a client may display one or more icons to select multiple operations, including event analysis, event statistics, event search for brake events, and other related operations. In another example, event analysis may include a brake event search function that may search for collected information about brake events to display any collected information. In another embodiment, the back end of the automated workflow system interface 700 may include an API 704, a WINUTIL API 706, a simple mail transfer protocol (SMTP) email interface 708, an automated product database 710, a service database 712, a service log database 714, a PTC operation database 716, a PTC configuration management database (CMDB) 718, an event classification database 720, and an automatic message database 722. In another embodiment, API 704 may communicate with WINUTIL API 706, SMTP email interface 708, automation product database 710, service database 712, service log database 714, PTC operation database 716, PTC CMDB 718, event classification database 720, and automatic message database 722 via a network. For example, the network may include Figure 1 Network 140 in.
[0116] Figure 8 An embodiment of an automated workflow system interface according to one or more embodiments of the present disclosure is shown. Figure 8 An automated workflow system (dashboard) screen 800 is shown. In one embodiment, the automated workflow system screen 800 may include one or more icons that may instantiate one or more processes or algorithms. Icons may include text, images, and / or software objects. For example, the automated workflow system screen 800 may include a homepage icon 802, an event analysis icon 804, a statistics icon 806, an event reclassification icon 808, a case closure dashboard icon 810, and an event profile icon 812, as well as other related icons. In another embodiment, the automated workflow system screen 800 may include a search function 814 to perform a search of event information collected in multiple databases based on an input. For example, the search function 814 may include a list of brake events that occurred within an identified date range and other related categories based on an input. In another example, the search function 814 may filter search results based on one or more segments corresponding to the event information. In another example, the search function 814 may display event information in a web-based interface.
[0117] Fig. 9A flow chart of an exemplary termination control logic 900 according to one or more embodiments of the present disclosure is shown. The termination control logic 900 can be implemented as an algorithm on the server 102, a machine learning module, a client, a database, or other suitable system. In addition, the termination control logic 900 can implement or include one or more features of the automated workflow system 200, including the document retrieval management system 202, the watchdog system 204, and the automated production system 206. The termination control logic 900 can be implemented by software, hardware, API, network connection, network transmission protocol, HTML, DHTML, JavaScript, Dojo, Ruby, Rails, other suitable applications, or a suitable combination thereof.
[0118] The termination control logic 900 can take advantage of the capabilities of the computer platform to generate multiple processes and threads by processing data simultaneously. By instantiating multiple processes to implement data lifecycle management, the speed and efficiency of the termination control logic 900 can be greatly improved. However, those skilled in the art of programming will recognize that a single processing thread may also be used and this is within the scope of the present disclosure.
[0119] In one embodiment, the command or data may be received via user input generated on a client or server, such as a screen click, a slide, a mouse click, a key, a voice command, or other suitable mechanism. In another exemplary embodiment, the inspection command or data may include inspection data having one or more fields, parameters, characteristics, or metadata related to the inspection. The control logic 900 then terminates and proceeds to step 902.
[0120] In step 902, in one embodiment, the control logic 900 may identify whether a root cause has been determined. For example, the control logic 900 may receive an analysis result to determine whether a root cause has been determined. In another example, the root cause is determined by an analysis model, such as the analysis module 124 described in the figure. 2. In another embodiment, when the analysis result includes a root cause, the control logic 900 may assign an alarm ID to the analysis result. If the root cause has not been determined, the control logic 900 proceeds to step 904. If the root cause has been determined, the control logic 900 proceeds to step 906.
[0121] In step 904, in one embodiment, the control logic 900 may generate a high-level classification. For example, the high-level classification may correspond to an execution event. In another example, when the analysis result does not include a root cause, the control logic 900 may generate a high-level classification for the execution event and assign a unique ID to the analysis result. For example, the high-level classification may include a message type, a message description, and a banner. In another example, the message type may be a warning to a train before a mandatory execution event. In another example, the message description may include a description of the warning, including information such as mandatory events. In another example, the banner may be the last banner displayed to an engineer before a mandatory execution event. The control logic 900 then proceeds to step 908.
[0122] In step 906, in one embodiment, the control logic 900 may generate a root cause classification. For example, the control logic 900 may generate a detailed summary. In another example, the detailed summary may include multiple events, such as the time of train operation, the speed of the train during the execution of the train event, the location details of the train, the warning to the train, the configuration details of the train, the PTC component information, the execution type, and the type of braking event. In another example, the detailed summary may correspond to a unique ID or an alarm ID. The control logic 900 then proceeds to step 908.
[0123] In step 908, in one embodiment, the control logic 900 may write an automation service address. For example, the automation service address may include an IP address to receive multiple automation logs. In another example, the automation log may include a globally unique identifier (GUID) of the execution event and the execution event. The control logic 900 proceeds to step 910.
[0124] At step 910, in one embodiment, control logic 900 may generate a message to be sent to at least one user. For example, the message may include information about the root cause of the execution event. Control logic 900 proceeds to step 912.
[0125] In step 912, in one embodiment, the control logic 900 may determine whether the at least one user has subscribed to a specific message type. For example, the control logic 900 may determine whether the at least one user has subscribed to a specific message type based on a user list service. In another example, the specific message type may be an email, a text message, a direct message, or another type of message type. If the at least one user has not subscribed to the specific message type, the control logic 900 does not perform any operation. If the at least one user has indeed subscribed to the specific message type, the control logic 900 proceeds to step 914.
[0126] In step 914, in one embodiment, control logic 900 may determine whether the message is an alarm message. If the message is not an alarm message, control logic 900 proceeds to step 916. If the message is an alarm message, control logic 900 proceeds to step 918.
[0127] In step 916 , in one embodiment, the control logic 900 may transmit the message as a regular notification. For example, the control logic 900 may transmit the message using a specific message type. The control logic 900 proceeds to step 920 .
[0128] In step 918 , in one embodiment, control logic 900 may transmit the message as a regular notification and alert message. Control logic 900 then proceeds to step 920 .
[0129] At step 920, in one embodiment, the control logic 900 may generate a log. For example, the log may contain a data history record of periodic notifications and alarm messages. In another example, the control logic 900 may send an email to generate a history record of the data in the log.
[0130] Fig.10 A flow chart of an example brake event processing control logic 1000 according to one or more embodiments of the present disclosure is shown. The brake event processing control logic 1000 can be implemented as an algorithm on a server 102, a machine learning module, a client, a database, or other suitable system. In addition, the brake event processing control logic 1000 can implement or include one or more features of the automated workflow system 200, including the file retrieval management system 202, the watchdog system 204, and the automated production system 206. The brake event processing control logic 1000 can be implemented by software, hardware, API, network connection, network transmission protocol, HTML, DHTML, JavaScript, Dojo, Ruby, Rails, other suitable applications, or a suitable combination thereof.
[0131] The brake event processing control logic 1000 can take advantage of the computer platform's capabilities to generate multiple processes and threads by processing data simultaneously. By instantiating multiple processes to implement brake event processing, the speed and efficiency of the brake event processing control logic 1000 can be greatly improved. However, those skilled in the art of programming will recognize that a single processing thread may also be used and this is within the scope of the present disclosure.
[0132] In one embodiment, the command or data may be received via user input generated on a client or server, such as a screen click, a swipe, a mouse click, a key press, a voice command, or other suitable mechanism. In another exemplary embodiment, the inspection command or data may include inspection data having one or more fields, parameters, characteristics, or metadata related to the inspection. The braking event processing control logic 1000 then proceeds to step 1002.
[0133] In step 1002, in one embodiment, the control logic 1000 may receive a braking event. For example, the control logic 1000 may receive a braking event from a PTC system. In another example, the control logic 1000 may receive an incoming message regarding a railway event notification (e.g., a PTC braking event). In another example, the control logic 1000 may receive an incoming message from an FRM. For example, the incoming message may correspond to the execution of a braking event implemented on a train. In another embodiment, the control logic 1000 may transmit an outgoing message to the FRM. For example, the message sent may request a train system log corresponding to the implementation of the braking event. In another embodiment, the file collection module 108 may receive a notification from the FRM indicating that a train system log is available. The control logic 1000 proceeds to step 1004.
[0134] In step 1004, in one embodiment, the control logic 1000 may extract data from the braking event. For example, the data may correspond to a train system log indicating characteristics of an enforcement event. In another example, a file server may include a training system log from multiple enforcement events. In another embodiment, the control logic 1000 may collect data before and after the enforcement event to generate a time window. For example, the data may correspond to a train system log. In another example, the time window may include a time measurement before the enforcement event, after the enforcement event, or before and after the enforcement event. In another example, the time window may include seconds, minutes, or hours before and after the enforcement event. In another example, the control logic 1000 may compare the time of enforcement with the data to verify whether the enforcement event actually occurred. The control logic 1000 proceeds to step 1006.
[0135] In step 1006, in one embodiment, the control logic 1000 may convert the extracted data into one or more dictionaries. For example, the dictionary may include a predetermined format. In another embodiment, the control logic 1000 may determine whether the data is structured. For example, when the information in the data can be classified in a predetermined manner, the data may be structured. In another example, when the information in the data can be classified in a manner different from the predetermined manner or is not classified at all, the data may be unstructured. In another embodiment, when the data is unstructured, the control logic 1000 may identify a pattern of the unstructured data to convert the data into structured data and extract the data. For example, the control logic 1000 may use a data conversion software tool to convert the unstructured data into structured data. In another embodiment, when the data is structured, the control logic 1000 may extract the data. In another example, the control logic 1000 may extract the data using a regular expression. In another example, a regular expression may include a sequence of characters that defines a search pattern. In another example, the control logic 1000 may extract the data using a data manipulation technique. In another example, the data manipulation technique may include using a commercial software tool, such as Or a custom data tool. Control logic 1000 proceeds to step 1008 .
[0136] In step 1008, in one embodiment, the control logic 1000 may analyze the dictionary. For example, the dictionary may include whether the control logic 1000 has determined the cause of the braking event. In another example, the control logic 1000 may include multiple decision steps to determine the cause. In another example, the control logic 1000 may use a training data model to identify the cause of the braking event. In another example, the training data model may include user-based parameters. In another example, the training data may include real-time data or historical data. In another example, the real-time data may include real-time information to monitor abnormal behavior. In another example, the historical data may include a data set of previous events that can be used to classify the braking event. In another embodiment, the control logic 1000 may use a defect detection analysis model to analyze the dictionary. In another example, the defect detection analysis model identifies the time when the defect occurs during the analysis process. In another example, when the defect occurs, the control logic 1000 classifies the defect as a root cause. In another example, when the defect does not occur, the control logic 1000 may use a historical analysis model to analyze the dictionary. In another example, the historical analysis model may be based on historical data, such as previous engineer interactions, system component responses, and situational behaviors. In another example, the control logic 1000 may use a decision tree model, a classification model, or a clustering model to analyze the extracted data. For example, the control logic 1000 may analyze the dictionary through a machine learning module. The control logic 1000 proceeds to step 1010.
[0137] In step 1010, in one embodiment, the control logic 1000 may assign a unique analysis code to each dictionary. For example, when the dictionary does not contain the cause of the braking event, the control logic 1000 may generate a unique analysis code as a high-level classification of the cause of the braking event and assign a unique ID to the dictionary. For example, the high-level classification may include a message type, a message description, and a banner. In another example, the message type may be a warning to a train before enforcing an event. In another example, the message description may include a description of the warning, including information such as the enforcing event. In another example, the banner may be the last banner displayed to the engineer before enforcing the event. In another embodiment, when the dictionary contains the cause of the braking event, the control logic 1000 may assign an alarm ID to the dictionary. The control logic 1000 proceeds to step 1012.
[0138] In step 1012, in one embodiment, the control logic 1000 may send a notification to all event subscribers. For example, the control logic 1000 may transmit a detailed summary to the event subscribers. For example, the detailed summary may include multiple events, such as the time of train operation, the speed of the train during the execution of the train event, the location details of the train, the warning to the train, the configuration details of the train, the PTC component information, the execution type, and the type of braking event. In another example, the detailed summary may correspond to a unique ID or an alarm ID. In another example, the control logic 1000 may transmit the detailed summary via AES. In another example, AES may include a list service of all event subscribers to be notified. In another embodiment, the control logic 1000 may generate output based on the subscriber list and distribute notifications. The control logic 1000 proceeds to step 1014.
[0139] In step 1014, in one embodiment, the control logic 1000 may classify the braking event. For example, the control logic 1000 may classify the braking event as one of a plurality of events corresponding to the cause of the braking event. In another example, the control logic 1000 may classify the braking event based on the train system log and features. In another example, the control logic 1000 may classify the braking event based on the extracted data. In another embodiment, the control logic 1000 may classify the braking event and store the information corresponding to the braking event in a designated server.
[0140] The present disclosure achieves at least the following advantages:
[0141] 1. Perform data extraction and root cause analysis on various types of data structures using automation engines;
[0142] 2. Improve the efficiency of inspectors performing root cause analysis through automated workflows;
[0143] 3. Ability to accurately detect train events, such as PTC braking events, and identify the root causes of such events;
[0144] 4. Provide an analytical framework to perform root cause analysis using data extraction and analytical models.
[0145] Those skilled in the art will readily appreciate that without the specific combination of computer hardware and other structural components and mechanisms assembled in the system of the present invention and described herein, the above advantages and purposes will not be possible to achieve. In addition, the algorithms, methods and processes disclosed herein improve and convert any general-purpose computer or processor disclosed in this specification and the accompanying drawings into a special-purpose computer, which is programmed to execute the disclosed algorithms, methods and processes to achieve the above functions, advantages and goals. It should also be understood that for those who are proficient in this field, there are a variety of programming tools that can be used to generate and implement the functions and operations described above. In addition, the specific selection of programming tools may be subject to the specific goals and constraints selected to implement the concepts set forth in this article and the appended claims.
[0146] The description in this patent document should not be construed as implying that any particular element, step, or function is an essential or critical element that must be included within the scope of the claims. In addition, unless the exact words "means for..." or "step for..." are expressly used in a particular claim and followed by a participatory phrase identifying the function, no claim is intended to invoke 35 U.S.C. §112(f) for any additional claim or claim element. Terms used in the claims (such as (but not limited to) "mechanism", "module", "device", "unit", "component", "element", "member", "device", "machine", "system", "processor", "processing device", or "controller") should be understood and intended to refer to structures known to those skilled in the relevant art and are further modified or enhanced by the features of the claims themselves, and are not intended to invoke 35 U.S.C. §112(f). Even under the broadest reasonable interpretation, in accordance with this paragraph of the specification, the claims are not intended to invoke 35 U.S.C. §112(f) in the absence of the above specific language.
[0147] The present disclosure may be embodied in other specific forms without departing from its spirit or essential features. For example, each new structure described herein may be modified to accommodate specific local changes or requirements while retaining their basic configuration or structural relationship to each other, or while performing the same or similar functions described herein. Therefore, the present embodiments should be considered illustrative rather than restrictive in all respects. Therefore, the scope of the invention should be determined by the appended claims rather than by the foregoing description. Therefore, all changes within the meaning and equivalent scope of the claims should be included in the claims. In addition, the various elements in the claims are not well-known, conventional or traditional. Instead, the claims point to the non-traditional innovative concepts described in the specification.
Claims
1. A system for automating workflows and performing root cause analysis of data structures, comprising: A memory having a database storing a train system log; as well as A networked computer processor operatively coupled to a memory and capable of executing machine-readable instructions to perform program steps comprising: receiving a message containing information about a train event; retrieving a train system log corresponding to the message to identify at least one feature corresponding to a train event; verifying actual occurrence of a train event based on at least one characteristic; determining an extraction model to generate data corresponding to a train system log; transforming data to generate extracted data; Analyze the extracted data using analytical models to generate analytical results; If the analysis result does not contain the root cause, a high-level classification is created for the train event through the analysis model and a unique ID is assigned to the analysis result; If the analysis result includes a root cause, assigning an alert ID to the analysis result through the analysis model; and A summary corresponding to the unique ID or alert ID is sent to the user using an automated email system (AES).
2. The system as claimed in claim 1, wherein the summary includes a plurality of events such as time of train activity, speed of the train during execution of the train event, position details of the train, warnings to the train, configuration details of the train, Positive Train Control (PTC) component information, execution type, and braking type.
3. The system of claim 1, wherein the high-level classification includes target type, target description, and banner.
4. The system of claim 1, wherein the program steps further include: Analyze the extracted data using defect detection analysis models; If a defect is detected, the root cause is classified as the defect; and If no defects are detected, the extracted data is analyzed using a historical analysis model.
5. The system of claim 4, wherein the historical analysis model is based on historical data, such as previous engineer interactions, system component responses, and situational behaviors. The system according to claim 1 , wherein the train system log comprises structured data or unstructured data.
7. The system of claim 6, wherein the extraction model uses regular expressions or data manipulation practices.
8. The system of claim 1, wherein the analysis model comprises a decision tree model, a classification model, or a clustering model.
9. A method for automating a workflow and performing root cause analysis of a data structure, comprising: receiving a message containing information about a train event; retrieving a train system log corresponding to the message to identify at least one feature corresponding to the train event; verifying, by a processor, the occurrence of a train event based on at least one characteristic; Instantiating the extraction model to generate data corresponding to the train system logs; transforming the data by a processor to generate extracted data; Analyze the extracted data using analytical models to generate analytical results; If the analysis result does not contain the root cause, a high-level classification of the train event is generated through the analysis model and a unique ID is assigned to the analysis result; If the analysis result includes a root cause, an alert ID is assigned to the analysis result through the analysis model; as well as Generate an analysis summary.
10. The method according to claim 9, wherein the detailed summary includes multiple events, such as time of train activity, speed of the train during execution of the train event, location details of the train, warnings to the train, configuration details of the train, positive train control (PTC) component information, type of execution and type of braking.
11. The method of claim 9, wherein the high-level categories include target type, target description, and banner.
12. The method according to claim 9, wherein the program steps further include: Analyze the extracted data using defect detection analysis models; If a defect is detected, the root cause is classified as the defect; and If no defects are detected, the extracted data is analyzed using a historical analysis model.
13. The method of claim 12, wherein the historical analysis model is based on historical data, such as previous engineer interactions, system component responses, and situational behaviors.
14. The method according to claim 9, wherein the train system log comprises structured data or unstructured data.
15. The method according to claim 15, wherein the extraction model uses regular expressions or data manipulation practices.
16. The method according to claim 9, wherein the analysis model comprises a decision tree model, a classification model or a clustering model.
17. A computer-implemented method for automating workflows and performing root cause analysis of data structures, comprising: receiving a message containing information about a train event; retrieving a train system log corresponding to the message to identify at least one characteristic corresponding to the train event, such as a time of the event, a main CPU during execution of the train event, or an appropriate component software version; verifying actual occurrence of a train event based on at least one characteristic; determining an extraction model to generate data corresponding to a train system log, such as a time window of a train event; transforming data to generate extracted data; Analyze the extracted data using analytical models to generate analytical results; If the analysis result does not contain the root cause, a high-level classification is created for the train event through the analysis model and a unique ID is assigned to the analysis result; If the analysis result includes a root cause, an alert ID is assigned to the analysis result through the analysis model; as well as A detailed summary is sent to the user using an automated email system (AES) corresponding to the unique ID or alert ID.
18. The method according to claim 9, wherein the detailed summary includes multiple events such as time of train activity, speed of the train during execution of the train event, location details of the train, warnings to the train, configuration details of the train, positive train control (PTC) component information, type of execution and type of braking.
19. The method of claim 9, wherein the high-level categories include target type, target description, and banner.
20. The method according to claim 9, wherein the program steps further include: Analyze the extracted data using defect detection analysis models; as well as If a defect is detected, the root cause is classified as the defect; and If no defects are detected, the extracted data is analyzed using a historical analysis model.
21. The method of claim 12, wherein the historical analysis model is based on historical data, such as previous engineer interactions, system component responses, and situational behaviors.
22. The method of claim 9, wherein the train system log comprises structured data or unstructured data.
23. The method of claim 15, wherein the extraction model uses regular expressions or data manipulation practices.
24. The method according to claim 9, wherein the analysis model comprises a decision tree model, a classification model or a clustering model.
25. A method for determining the cause of a positive train control (PTC) braking event without user interaction, comprising: Receive braking events from the PTC system; Extract data from braking events; Convert the extracted data into one or more dictionaries; The machine learning module analyzes the dictionary and uses the training data model to identify the cause of the event; Assign a unique analysis code to each dictionary to control model output.
26. The method of claim 25, wherein the dictionary converts the data into a predetermined format.
27. The method of claim 25, wherein the training data parameters include real-time data or historical data.
28. The method of claim 25, wherein the training data model includes user-based parameters.
29. The method of claim 25, further comprising transmitting a notification to all event subscribers.
30. The method of claim 25, further comprising classifying braking events into one or more predetermined categories.
