Digital structure impairment decision support

Abstract

The invention relates to digital structure impairment decision support. Aspects herein use a digital SRM (DSRM) with a maintenance user interface. In one embodiment, DSRM is a knowledge graph (KG) that uses natural language processing (NLP) and image processing to retrieve nodes and edges of related information derived from an SRM PDF document. In the KG, entity descriptions contribute to each other, forming a network, where each entity represents a portion of the description of the entity to which each entity is associated. The entities have attributes describing each entity, and each entity is interconnected via a relationship such as admissible impairment limits (ADL).

Description

Technical Field

[0001] This disclosure relates to the use of knowledge graphs (KG) to digitize structural repair manuals and provide rapid lookup of permissible damage / repair limits for aircraft damage. Background Technology

[0002] The first two hours after a flight lands are crucial for an airline's timely operations. Aircraft Maintenance Engineers (AMEs) typically inspect the aircraft for structural damage and, if damage is detected, check if it falls within the Allowable Damage Limit (ADL) / Repairable Damage Limit (RDL) and take necessary actions. To perform this task, engineers need to consult the Structural Repair Manual (SRM) of the ADL / RDL and perform specific actions based on that information. As aircraft have become increasingly complex, SRMs have become massive documents spanning thousands of pages, making finding the ADL and specific repairs a tedious task.

[0003] SRM is a portable document format (PDF) file that can be considered "modern paper." SRM includes bookmarks for finding the larger structure to which the damaged section might belong. AME needs to search hundreds of pages of a section to find relevant information using tables and figures. This information is often not present in a single PDF file, so AME may move back and forth between different chapters and sections of the SRM to obtain applicable data. AME must then check a series of conditions to ensure the correct conclusions are reached. This entire manual process is time-consuming and requires considerable effort to integrate the necessary data. Summary of the Invention

[0004] This disclosure provides a method or computer-readable storage medium comprising: plotting damage locations on a 3D model of a vehicle corresponding to damage on a physical version of the vehicle; identifying allowable damage limits (ADL) corresponding to the damage by traversing a knowledge graph using the damage locations on the 3D model, wherein the knowledge graph contains multiple nodes interconnected by relationships to represent information in the vehicle's structural repair manual (SRM); and sending (606) a prompt indicating whether the damage is within the ADL.

[0005] In one aspect, in conjunction with any of the above or below examples, a first node in the knowledge graph indicates a damaged portion of a vehicle, wherein a second node in the knowledge graph indicates a first type of damage, and wherein the connection between the first node and the second node indicates a first ADL corresponding to the first type of damage.

[0006] On the one hand, referring to the above example, the third node in the knowledge graph is positioned between the first and second nodes, where the third node represents the location of damage on a part of the vehicle.

[0007] On one hand, in conjunction with the above example, the third node in the knowledge graph indicates a second type of damage that is different from the first type of damage, wherein the connection between the first node and the third node indicates a second ADL corresponding to the second type of damage, which is different from the first ADL.

[0008] On the one hand, in conjunction with the above example, the third node in the knowledge graph indicates an annotation for that part of the vehicle, wherein the annotation contains at least one of proximity information between two instances of damage on that part or proximity information between damage and a specific location on that part.

[0009] In one aspect, in conjunction with any of the examples above or below, a maintenance user interface (108) implemented in a graphical user interface (GUI) is used to generate 3D models and prompts.

[0010] On the one hand, in conjunction with the above example, the maintenance user interface is responsible for performing recommended maintenance tasks based on damage outputs exceeding the ADL.

[0011] This disclosure provides a method or computer-readable storage medium, comprising: receiving a repair manual of a vehicle; extracting data from the repair manual using natural language processing; determining nodes of a knowledge graph based on the extracted data; determining connections between nodes based on the extracted data; and connecting nodes to create a knowledge graph.

[0012] In one aspect, in conjunction with any of the above or below instances, a first node in the knowledge graph indicates a damaged portion of a vehicle, a second node in the knowledge graph indicates a first type of damage, and a connection between the first node and the second node indicates a first ADL corresponding to the first type of damage.

[0013] On the one hand, in conjunction with the above example, the third node in the knowledge graph is set between the first and second nodes, where the third node represents the location of the damage on that part of the vehicle.

[0014] On one hand, in conjunction with the above example, the third node in the knowledge graph indicates a second type of damage that is different from the first type of damage, wherein the connection between the first node and the third node indicates a second ADL corresponding to the second type of damage, which is different from the first ADL.

[0015] On the one hand, in conjunction with the above example, the third node in the knowledge graph indicates an annotation for that part of the vehicle, wherein the annotation contains at least one of proximity information between two instances of damage on the part or proximity information between the damage and a specific location of the part.

[0016] In one aspect, in conjunction with any instance above or below, a maintenance user interface (108) implemented as a graphical user interface (GUI) is used to generate 3D models and prompts.

[0017] On the one hand, in conjunction with the above example, the maintenance user interface is responsible for performing recommended maintenance tasks based on damage outputs exceeding the ADL. Attached Figure Description

[0018] To understand the features described above in detail, a more specific description of the above brief overview can be obtained by referring to the exemplary aspects, some of which are shown in the accompanying drawings. However, it should be noted that the drawings illustrate typical aspects and are therefore not intended to be limiting; other equally valid aspects are contemplated.

[0019] Figure 1 A system is described that is a computing device configured to perform various aspects of this disclosure, according to one aspect.

[0020] Figure 2 It is a flowchart of a method for processing information about damage, based on one aspect.

[0021] Figure 3 An example maintenance user interface is described, which is configured to perform various aspects of this disclosure according to one aspect.

[0022] Figure 4 This illustrates a knowledge graph pattern based on one aspect.

[0023] Figure 5 An example knowledge graph is depicted that is configured to perform the various aspects of this disclosure according to one aspect.

[0024] Figure 6 It is a flowchart of a method for indicating permissible damage limits based on one aspect.

[0025] Figure 7 It is a flowchart of a method for processing information about damage, based on one aspect.

[0026] Figure 8 It is a flowchart for creating a knowledge graph based on one aspect.

[0027] For ease of understanding, where possible, the same reference numerals are used to refer to the same elements common to the accompanying drawings. Elements disclosed in one aspect are intended to be usefully applied to other aspects without specific description. Detailed Implementation

[0028] This paper describes various aspects of a digital SRM (DSRM) integrated with a web-based application that maintains a user interface. In one aspect, a DSRM is a knowledge graph (KG) of nodes and edges that uses natural language processing (NLP) and image processing to retrieve relevant information derived from SRM PDF documents. A KG is a collection of interconnected entities where entity descriptions are clear enough for both humans and computers to understand. Entity descriptions contribute to each other, forming a network where each entity represents a portion of the description of entities related to it. These entities have characteristics that describe each entity, and each entity is interconnected via "relationships" such as allowable impairment limits (ADL).

[0029] The technical advantage of this disclosure is the ability to use plotted locations associated with damage instances, where the plotted locations are linked to a 3D model of the aircraft. The system and method can display the required input values ​​and process the input to search for digital SRMs, thereby making it easier, faster, and potentially more efficient to retrieve all relevant information.

[0030] Another technical advantage of this disclosure is that it enables crew members, mechanics, and engineers to inspect the aircraft for structural damage after each flight to determine if new damage exists and efficiently ensure that damage is within acceptable limits (ADL). For example, the systems and methods disclosed herein can include zones and areas associated with permissible damage / repair limits. By automatically identifying maintenance conditions based on input data, 3D models, and KG (Keeper Gauge), the systems and methods disclosed herein can efficiently generate damage treatments based on input data and damage limits retrieved from a digital SRM (Statistical Management Responsibility System) without having to examine thousands of pages of the SRM.

[0031] The accompanying drawings and the following description illustrate specific exemplary aspects. It should be understood that those skilled in the art will be able to conceive of various arrangements, which are not explicitly described or shown herein, but which embody the principles described herein and are included within the scope of the claims following this description. Furthermore, any examples described herein are intended to aid in understanding the principles of this disclosure and are to be construed as not limiting. Therefore, this disclosure is not limited to the specific aspects or examples described below, but is defined by the claims and their equivalents.

[0032] Figure 1 A system 100 is depicted that is configured to perform various aspects of this disclosure, according to one aspect. The computing device 102 is also configured to communicate with one or more devices. Although depicted as a physical device, in this aspect, the computing device may be implemented using a virtual device, and / or across multiple devices (e.g., in a cloud environment).

[0033] In some embodiments, the device may be included in, correspond to, or be included within a smartphone, tablet, or other handheld electronic device used by an aircraft maintenance crew. For example, an aircraft maintenance crew in an airport gate environment may use a camera-equipped smartphone to take pictures of external damage to an aircraft in the gate environment, record and / or input information about the aircraft itself, the type of damage, the size of the damage, etc.

[0034] As shown, computing device 102 includes a processor 104, a memory 106, and damage information 114. In the aspect shown, memory 106 includes a maintenance user interface 108, a vehicle 3D model 110, and KG 112. The user inputs damage information 114 onto vehicle 3D model 110 in maintenance user interface 108. An example of maintenance user interface 108 (e.g., a graphical user interface (GUI)) will be described in Figure 3 A vehicle 3D model 110 with typical structural components of an aircraft is generated on maintenance user interface 108.

[0035] In one aspect, maintenance user interface 108 displays detailed structural information based on the plotted damage information 114. Damage information 114 may include data associated with the type of damage, the degree of damage, or some combination thereof. For example, damage information 114 may indicate whether a particular instance of damage to a particular aircraft is a surface damage (e.g., a notch, scratch, scuff, etc.), a pit, a crack (e.g., a broken fiber), a hole, delamination, thermal damage, lightning strike away from a fastener, lightning strike at a fastener, etc. Damage information 114 may also indicate one or more physical dimensions associated with the damage (e.g., depth, length, width, area, etc.).

[0036] The structural information displayed in maintenance user interface 108 includes repair instructions that include aircraft data and aircraft location data. The aircraft data may include information identifying a particular aircraft type, manufacturer, model, tail number, etc. The aircraft location data may include data associated with the location on the particular aircraft where the damage is located. For example, the aircraft location data may indicate a part number, location coordinates, one or more other identifiers associated with the location on the particular aircraft, or some combination thereof, which is further explained in Figure 3 In

[0037] Digital SRM (DSRM) uses the extracted PDF document used to create KG 112 to generate repair instructions. DSRM may include, correspond to, or be included in an electronic device that includes memory storing one or more damage limits. Damage limits may include one or more values ​​indicating whether a particular instance of damage can be corrected in a particular environment when certain conditions are met. For example, damage limits(one or more) may indicate permissible damage limits(one or more) indicating whether the aircraft can continue to operate without correcting the instance of damage. Damage limits(one or more) may also indicate repairable damage limits(one or more) indicating whether the instance of damage can be repaired within certain parameters (e.g., within a certain time frame, within a gate environment, etc.).

[0038] In some respects, damage limits(s) may be associated with broader information about a specific aircraft type for a particular DSRM. For example, a digital maintenance manual may include information about damage limits and various conditions that must be met to apply those limits. KG 112 is a diagram of the nodes of an aircraft structure. The nodes each have relationships to create KG 112, which... Figure 4 The text provides further explanation.

[0039] The computing device 102 can also be configured to enable improved inventory management for aircraft operators. For example, an operator can analyze maintenance deployments associated with one or more aircraft over a period of time to determine whether a particular type of damage is more common than others. To illustrate, an aircraft operator can determine that lightning strikes on specific parts of an aircraft are more common for some aircraft flying a particular route than for others. The operator can then adjust material inventory levels to address the more common type of damage. For example, the operator can maintain higher inventory levels of specific fasteners, specific materials, etc., required to repair damage caused by lightning strikes. The computing device 102 can also be configured to enable other analytical tools, for example, to analyze fleet-wide damage statistics to improve aircraft construction or design. One or more components performing such operations can be incorporated into system 100, part of another system, or some combination thereof.

[0040] In addition, although Figure 1 Some operations that occur within computing device 102 are shown, but these operations can be performed by other components of system 100 without departing from the scope of this subject matter disclosure.

[0041] Figure 2This is a flowchart of a method 200 for processing information about damage, based on one aspect. After the aircraft lands, the user or maintenance personnel inspect the aircraft for any damage that may have occurred during flight. If the user finds any damage, the user determines whether the found damage is within the Allowable Damage Limits (ADL). Compared to previous methods using SRM, the user uses KG, for example... Figure 1 KG 112.

[0042] Method 200 begins at box 202, where the user maintenance interface receives input about the damage, such as... Figure 1 Damage information 114. At box 204, KG determines whether the damage is within the Allowable Damage Limit (ADL). If KG determines that the damage is not within the ADL, method 200 proceeds to box 206. At box 206, the user interface (such as...) is maintained. Figure 1 The maintenance user interface 108 outputs prompts for scheduling maintenance tasks. If KG determines that the damage is within ADL, then method 200 proceeds to box 208, where the damage is added to KG's annotation and the structure is allowed to run.

[0043] Users save time by using KG to determine whether any discovered damage is within the ADL. KG allows users to use multi-layered vehicle 3D models (e.g., Figure 1 The 3D model of the vehicle (110) allows for quick retrieval of ADL information for damaged structures on the maintenance user interface, such as... Figure 3 This will be discussed further. For example, at least six 3D layers may exist, displaying different structural details. Layers can be turned on and off by the user based on preferences. A seamless process is created from the ADL information displayed in the KG to complete the aircraft damage analysis.

[0044] Figure 3 An example maintenance user interface 300 (e.g., a GUI) configured to perform various aspects of this disclosure is depicted. The maintenance user interface 300 displays selectable virtual buttons 302 for MEL status, 304 for dents and buckling, 306 for cases, 308 for defects, 310 for structural delays, 312 for flight plans, 314 for view details, 316 for filter views, 318 for orientation, and 320 for viewing the overall aircraft. Such as... Figure 1 The maintenance user interface 108 and maintenance user interface 300 automate the user's role in accelerating aircraft turnaround (restoration to operation). Maintenance user interface 300 has features for locating 3D models of vehicles (such as...) Figure 1 A visual representation of damage, damage recording, and aircraft event management on a 3D model of a vehicle (110).

[0045] As the user walks around the aircraft to look for damage (lightning strikes, cracks, scratches, debris, etc.), the user marks damage information on the maintenance user interface 108, such as... Figure 1 Damage information 114. More specifically, damage points derived from the damage information are plotted on, for example,... Figure 1 The damage is applied to the 3D model of the vehicle (model 110). Each damage point has a personalized ADL (Application Programming Language) displayed on the 3D model of the vehicle, allowing the user to draw the damage point. As shown in the figure... Figure 3 The spheres or damage points on the 3D model of the aircraft are depictions of damage areas specific to the aircraft's structure.

[0046] For example, a user draws damage point 322, a 2-inch scratch, on the side of an aircraft on a 3D model of a vehicle. KG calculates the ADL (Advanced Design Principle) for the specific structure where damage point 322 is located. The maintenance user interface fills the ADL from the KG of damage point 322. Based on the ADL of this specific location, the user avoids navigating hundreds of pages trying to find the ADL for damage point 322 on the structure. The user reads the ADL associated with damage point 322 and determines whether the 2-inch scratch is within the ADL. Depending on the ADL, the user knows whether the damage to damage point 322 is repairable or whether the damage needs to be marked. The user makes this determination by considering annotations found in the virtual button 314 where viewing details is available. For example, an annotation might indicate that damage point 322 must be less than 6 inches from any other damage for damage limits to apply.

[0047] The vehicle 3D model can have at least six layers for drawing damage points. Each of the at least six layers can be turned on and off for simultaneous viewing. Based on the drawn damage, the user has the option on the maintenance user interface to select which vehicle 3D model is best suited for drawing damage points. The user draws damage points on the vehicle 3D model, and the system automatically uses the KG (Knowledge Group) to determine whether a given damage falls within the ADL (Application Limits). Furthermore, the maintenance user interface can suggest or display specific repair solutions for the damage on the same screen as the vehicle 3D model.

[0048] Figure 4The diagram illustrates a KG architecture 400 according to one aspect. The KG architecture 400 includes multiple nodes, including part 402, location 404, damage type 406, and annotation 408. In this example, the information for part 402 includes at least name, section, part, station, longitudinal beam, line number, major model number, and minor model number. Each part 402 contains location 404 information. The location 404 information may include at least the area, region, and feature of part 402. Each location 404 of each part 402 has an ADL for each damage type 406. The ADL may include at least length, width, and annotation. The damage type 406 may include at least damage type and measurement type.

[0049] In addition, each section 402 has one or more notes 408. The notes 408 for each section 402 may include at least information about the damage under consideration and other factors. Notes 408 describe the relationships between damage types 406. Other factors may include previously plotted damage points.

[0050] For example, suppose a previous damage point is plotted, indicating a 3-inch scratch, again assuming it's within a 4-inch ADL (Advanced Limiting Distance). Then, a new damage point is plotted in the same area as the previous one. However, this new damage point is 5 inches, which is outside the 4-inch ADL, as shown below. Figure 3 Viewing details can be done via virtual button 314. Note 408 displays details of the ADL and how a 5-inch scratch is not within the 4-inch ADL. KG 400 can provide this information to the maintenance user interface, which then outputs a prompt to the user to schedule a maintenance task. This output and the ability to schedule maintenance tasks can be provided by [the relevant authority / component]. Figure 3 The maintenance user interface 300 shown is provided.

[0051] Figure 5 A system 500 for a KG 504 is described, configured to perform different aspects of this disclosure according to one aspect. System 500 allows the KG 504 (such as...) Figure 1 KG 112) in maintaining user interface (such as Figure 1 It is constructed and updated within the context of maintaining the user interface 108. KG 504 is a collection of information in a graphical format, in which different entities and their relationships (with parameters) can be easily learned, defined, and queried. It includes 3D models of vehicles (such as...) Figure 1 The maintenance user interface of the vehicle 3D model (110) allows users to draw damage points and input damage dimensions. The interface between the maintenance user interface and the vehicle 3D model allows them to interact with each other.

[0052] KG 504 is an implementation of DSRM. KG 504 is created from information extracted from the SRM organizational structure 502. The extracted PDF document from organizational structure 502 refers to the aircraft's structural information. KG 504 includes multiple nodes. For example... Figure 7 and Figure 8 As discussed in more detail below, the extracted PDF document of the organizational structure 502 is used to create multiple nodes forming KG 504. Information from the PDF document of the organizational structure 502 can also be used to populate the ADL information 506 for each of the multiple nodes.

[0053] System 500 can be organized according to an exemplary organizational structure 502, which narrows down from a part number of a particular aircraft to subsequent segments of the part number to one or more sub-segments of the segment. Content associated with a sub-segment may include ADL information 506 indicating permissible damage limits for a particular part of the aircraft, wherein the permissible damage limits are based on damage type, the specific part of the aircraft, and the area of ​​damage.

[0054] exist Figure 5 In a specific instance, ADL information 506 describes multiple permissible damage limits for the corner seal clamping device (exemplary part) of the passenger boarding door peristructure (exemplary section 208) of the fuselage section (part number) (exemplary section 208), specifically the passenger boarding door peristructure (composite material) (exemplary sub-section). ADL information 506 specifies permissible damage limits for a pit (e.g., damage type) in a specific part (in this example, the corner seal clamping device), indicating the maximum size of the pit corresponding to the values ​​of the length damage limit, width damage limit, and depth damage limit. The KG may also include a damage figure showing the damage type, the dimensions of the damage limit, etc. The KG may further include one or more annotations associated with a specific maintenance issue. Annotations may indicate additional information associated with the KG, as described above. Figure 3 More detailed descriptions are possible. For example, a note might indicate that a particular instance of damage must be less than 6 inches from any other damage for the damage limit to apply. That is, two instances of damage may each be within the ADL (Advanced Limits). However, when considered together, they may exceed the ADL because they violate the proximity requirements of the ADL (e.g., two damaged areas are too close together). In another instance, a instance of damage may have dimensions that meet the ADL (e.g., width, length, and depth) but have a location on the aircraft that is too close to a particular component (e.g., a door handle or seal) and therefore does not meet the ADL. Variations in the ADL can be stored in the notes section of the KG (Keeper Gauge).

[0055] although Figure 5A specific exemplary system 500 for SRM is shown, but other configurations, contents, etc., of the SRM may exist without departing from the scope of the subject matter disclosure. For example, the SRM may illustrate maintenance conditions for different types of aircraft, another part of the same type of aircraft, or aircraft organized in different ways. Furthermore, although in Figure 5 No specific number is used to illustrate the exemplary permissible damage limit for this part of the SRM, but the permissible damage limit may be different for another type of aircraft, for different parts of the same aircraft, for different materials used in the same part of the same aircraft, and the permissible damage limit may change over time, etc.

[0056] In KG 504, a node can be connected to one or more additional nodes through connections that describe the relationships between nodes. These relationships can be directional, as they indicate the direction in which data flows from one node to another.

[0057] For example, node 508 can connect to multiple nodes, such as Figure 4 The nodes (part 402, location 404, damage type 406, and note 408) represent various maintenance areas on the aircraft associated with the physical location of the structural corner seal clamping device around the passenger boarding gate. In KG 504, each node is associated with all maintenance areas. In some aspects, the relationship between multiple nodes and node 508 is illustrated via connection 510. Figure 5 In the example, connection 510 shows that node 508 contains multiple nodes. In other respects, connection 510 can illustrate other kinds of relationships between multiple nodes and node 508.

[0058] In this example, ADL information 506 is dedicated to each node. When the user draws damage information (such as...) Figure 1 When damage information 114 is obtained, ADL information 506 associated with that specific damage area is used to determine whether the damage is within the ADL. The ADL information 506 (or whether the damage exceeds the ADL) is displayed using a user maintenance interface for user analysis. ADL information 506 may include location, damage type, area, depth, length, width, damage value (figure, indicator), and annotations. Each category of ADL information 506 has a value if applicable to a node. For user convenience, each node can be categorized by part, location, and damage type.

[0059] Figure 6 This is a flowchart of a method for indicating permissible damage limits according to one aspect. Method 600 begins at block 602. At block 602, the user displays a 3D model of the vehicle (such as...) Figure 1Damage (such as damage on the physical version of the vehicle) is drawn on the 3D model 110 of the vehicle. Figure 3 The location of the damage point (322). For example, a user sees a 3-inch scratch on an airplane door. The user... Figure 3 A 3-inch scratch is drawn on the 3D model of the vehicle displayed on the maintenance user interface 300.

[0060] At box 604, the user identifies the ADL corresponding to the damage by traversing the KG (such as KG 504) using the location of the damage in the 3D model. The KG contains multiple nodes, such as... Figure 4 The nodes (part 402, location 404, damage type 406, and annotation 408) are linked through multiple relationships (such as...). Figure 5 The connections 510 are interconnected to represent the SRM information of the vehicle. For example, after damage is drawn, the KG fills in the ADL for the drawn damage. The KG has nodes for the front of the aircraft (part 402), damage locations (more specific nodes for location 404), and even more specific nodes for 3-inch scratches (damage type 406). Each node is connected using relationships. The KG includes annotations related to the nose of the aircraft, such as... Figure 4 Note 408.

[0061] At box 606, a prompt is sent to indicate whether the damage is within the ADL (Advanced Management Principle). For example, KG cross-references a 3-inch scratch drawn on the 3D model with the ADL. If the 3-inch scratch is not within the ADL, the ADL displays a prompt to schedule a maintenance task. If the 3-inch scratch is within the ADL, the 3-inch scratch is added to KG's annotation. Compared to what could be determined using previous solutions, users can view the ADL on the maintenance user interface much faster.

[0062] Figure 7 This is a flowchart of a method 700 for processing information about damage, based on one aspect. Damage information is processed using a PDF document extracted from an SRM (e.g.,...). Figure 1 Damage information 114). The extracted information is processed and configured into the KG, such as... Figure 1 KG 112 or Figure 5 KG 504 in the data is used for post-landing aircraft analysis.

[0063] Method 700 begins at box 702. For ease of explanation, the box for method 700 is... Figure 8 Parallel discourse, Figure 8 This is a flowchart illustrating a method 800 for creating KG 812, based on one aspect.

[0064] At box 702, the processor (such as...) Figure 1The processor 104) receives the repair manual. In one aspect, the repair manual is an SRM, such as... Figure 8 As further described herein, method 800 begins with SRM document 802. To create KG 812, SRM document 802 is processed to use NLP to extract information from organizational structures (such as...). Figure 5 Extract key information from the organizational structure (502).

[0065] In box 704, the processor uses Natural Language Processing (NLP) to extract data from the repair manual to convert the PDF into machine-readable data. For example, in Figure 8 At box 804, NPL is used to extract key information from the SRM document (Repair Manual), which includes, but is not limited to, tables, text, graphics, and section numbering. The data extracted from the PDF document is stored in, for example,... Figure 1 The memory of memory 106.

[0066] At box 706, the processor uses the extracted data to determine the node of the KG. Figure 8 At box 806, a node (entity) is created based on the extracted key information. Nodes can include information such as the location of structural segments, parts, and regions, as well as the type of damage. In the above... Figure 4 and Figure 5 Various examples of nodes are discussed in the text.

[0067] In box 708, the processor uses the extracted data to determine the connections between nodes in the KG. In box 808, the extracted data is used to establish relationships that include at least ADL length, depth, and width, as well as proximity constraints between damaged or special components (e.g., seals).

[0068] In box 710, nodes are connected to build the KG. Figure 8 Box 810, by combining extracted key information, creates KG 812 to create nodes connected by the relationships identified in box 808.

[0069] According to one aspect, methods 700 and 800 describe techniques for creating KG 812. KG 812 (such as...) Figure 5 KG 504 allows for faster retrieval and question answering of ever-growing datasets. KG 812 further enables visual navigation, damage history recording, and drill-down analysis. KG 812 maximizes dispatch speed with minimal user input. Human error (human factor) is minimized. Users avoid reviewing previous SRMs, reducing the chance of errors. KG 812 is further capable of capturing 3D models of vehicles (such as...) Figure 1Detailed damage characteristics and locations were drawn on the 3D model 110 of the vehicle.

[0070] In this disclosure, references are made to various aspects. However, it should be understood that this disclosure is not limited to the aspects specifically described. Rather, any combination of the following features and elements (whether or not they relate to different aspects) is contemplated for the implementation and practice of the teachings provided herein. Furthermore, when elements of these aspects are described in the form of “at least one of A and B,” it will be understood that aspects including element A exclusively, including element B exclusively, and including elements A and B are each considered individually. Moreover, while some aspects may achieve advantages over other possible solutions and / or over the prior art, whether a particular advantage is achieved by a given aspect does not limit this disclosure. Therefore, the aspects, features, aspects, and advantages disclosed herein are merely illustrative and should not be considered as elements or limitations of the appended claims unless expressly stated in the claims. Similarly, references to “this disclosure” should not be construed as a generalization of any inventive subject matter disclosed herein and should not be considered as elements or limitations of the appended claims unless expressly stated in the claims.

[0071] As those skilled in the art will understand, the aspects described herein may be embodied as a system, method, or computer program product. Therefore, the aspects may take the form of a purely hardware aspect, a purely software aspect (including firmware, resident software, microcode, etc.), or a combination of software and hardware aspects, all of which are collectively referred to herein as “circuit,” “module,” or “system.” Furthermore, the aspects described herein may take the form of a computer program product embodied in one or more computer-readable storage media having computer-readable program code embodied thereon.

[0072] Program code implemented on a computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, or any suitable combination thereof.

[0073] Computer program code for performing the operations of the aspects of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0074] This document describes aspects of the present disclosure with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to these aspects. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to create a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, these computer program instructions create means for implementing the functions / actions specified in one or more blocks of the flowcharts and / or block diagrams.

[0075] These computer program instructions may also be stored in a computer-readable medium, which causes a computer, other programmable data processing apparatus, or other device to operate in a particular manner, such that the instructions stored in the computer-readable medium produce an article of writing including instructions that implement the functions / actions specified in the boxes of a flowchart and / or block diagram.

[0076] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, such that the instructions that execute on the computer, other programmable data processing apparatus, or other device provide for implementing the process for carrying out the functions / actions specified in the flowchart and / or block diagram (or blocks).

[0077] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various aspects of this disclosure. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative embodiments, the functions indicated in the blocks may occur in a different order than shown in the figures. For example, depending on the functions involved, two consecutively shown blocks may actually be executed substantially simultaneously, or these blocks may sometimes be executed in reverse order or out of order. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0078] While the foregoing addresses aspects of this disclosure, other and further aspects of this disclosure may be contemplated without departing from its essential scope, as defined by the appended claims.

Claims

1. A method for processing information about damage, comprising: Draw the location of the damage on the 3D model of the vehicle, corresponding to the damage on the physical version of the vehicle; The allowable damage limit (ADL) corresponding to the damage is identified by traversing a knowledge graph at the location of the damage on the 3D model, wherein the knowledge graph contains multiple nodes interconnected by relations to represent information from the structural repair manual (SRM) of the vehicle. as well as A prompt indicating whether the damage is within the permissible damage limit is sent for display.

2. The method according to claim 1, wherein, The first node in the knowledge graph indicates a portion of the vehicle that contains the damage, wherein the second node in the knowledge graph indicates a first type of damage, and wherein the connection between the first node and the second node indicates a first permissible damage limit corresponding to the first type of damage.

3. The method according to claim 2, wherein, The third node in the knowledge graph is positioned between the first node and the second node, wherein the third node represents the location of the damage on the part of the vehicle.

4. The method according to claim 2, wherein, The third node in the knowledge graph indicates a second type of damage that is different from the first type of damage, wherein the connection between the first node and the third node indicates a second permissible damage limit corresponding to the second type of damage, which is different from the first permissible damage limit.

5. The method according to claim 2, wherein, The third node in the knowledge graph indicates an annotation for the portion of the vehicle, wherein the annotation contains at least one of proximity information between two instances of damage on the portion and proximity information between the damage and a specific location of the portion.

6. The method according to claim 1, wherein, The 3D model and the prompts are generated using a maintenance user interface implemented with a graphical user interface (GUI).

7. The method according to claim 6, wherein, The maintenance user interface outputs suggested maintenance tasks to be performed based on the damage exceeding the permissible damage limit.

8. A computer-readable storage medium having program instructions implemented thereon, the program instructions being executable by a processor to perform operations, the operations including: Draw the location of the damage on the 3D model of the vehicle, corresponding to the damage on the physical version of the vehicle; The allowable damage limit (ADL) corresponding to the damage is identified by traversing a knowledge graph at the location of the damage on the 3D model, wherein the knowledge graph contains multiple nodes interconnected by relations to represent information from the structural repair manual (SRM) of the vehicle. as well as A prompt indicating whether the damage is within the permissible damage limit is sent to display.

9. The computer-readable storage medium according to claim 8, wherein, The first node in the knowledge graph indicates a portion of the vehicle that contains the damage, wherein the second node in the knowledge graph indicates a first type of damage, and wherein the connection between the first node and the second node indicates a first permissible damage limit corresponding to the first type of damage.

10. The computer-readable storage medium according to claim 9, wherein, The third node in the knowledge graph is positioned between the first node and the second node, wherein the third node represents the location of the damage on the part of the vehicle.

11. The computer-readable storage medium according to claim 9, wherein, The third node in the knowledge graph indicates a second type of damage that is different from the first type of damage, wherein the connection between the first node and the third node indicates a second permissible damage limit corresponding to the second type of damage, which is different from the first permissible damage limit.

12. The computer-readable storage medium according to claim 9, wherein, The third node in the knowledge graph indicates an annotation for the portion of the vehicle, wherein the annotation contains at least one of proximity information between two instances of damage on the portion and proximity information between the damage and a specific location of the portion.

13. The computer-readable storage medium according to claim 8, wherein, The 3D model and the prompts are generated using a maintenance user interface implemented with a graphical user interface (GUI).

14. The computer-readable storage medium according to claim 13, wherein, The maintenance user interface outputs suggested maintenance tasks to be performed based on the damage exceeding the permissible damage limit.

15. A computer-readable storage medium having program instructions implemented thereon, the program instructions being executable by a processor to perform operations, the operations including: Repair manual for receiving transport vehicles; Data was extracted from the repair manual using natural language processing; The nodes of the knowledge graph are determined based on the extracted data; The connections between the nodes are determined based on the extracted data; as well as Connect the nodes to create the knowledge graph.

16. The computer-readable storage medium according to claim 15, wherein, The first node in the knowledge graph indicates a damaged portion of the vehicle, wherein the second node in the knowledge graph indicates a first type of damage, and wherein the connection between the first node and the second node indicates a first permissible damage limit corresponding to the first type of damage.

17. The computer-readable storage medium of claim 16, wherein, The third node in the knowledge graph is positioned between the first node and the second node, wherein the third node represents the location of the damage on the part of the vehicle.

18. The computer-readable storage medium according to claim 16, wherein, The third node in the knowledge graph indicates a second type of damage that is different from the first type of damage, wherein the connection between the first node and the third node indicates a second permissible damage limit corresponding to the second type of damage, which is different from the first permissible damage limit.

19. The computer-readable storage medium according to claim 16, wherein, The third node in the knowledge graph indicates an annotation for the portion of the vehicle, wherein the annotation contains at least one of proximity information between two instances of damage on the portion and proximity information between the damage and a specific location of the portion.

20. The computer-readable storage medium according to claim 16, wherein, The natural language processing includes converting the data in the portable document format (PDF) of the repair manual into computer-readable data.

Images