Structure Maintenance Mapper

Abstract

The present application discloses a structure maintenance mapper. A system and method are provided herein for enabling a computing system to search for and interact with service records containing natural language text to facilitate analysis of those records by: clustering terms in a corpus of natural language service records related to complex systems based on term definitions in a knowledge base; associating the clustered terms with a coordinate system of the complex system based on a definition of a complex system including a coordinate system describing the complex system; generating a question map for a given natural language service record in the corpus, wherein the question map identifies the clustered terms and associated positions of the clustered terms in the given natural language service record according to the coordinate system of the complex system; and associating the question map with the given natural language service record in the corpus.

Description

Technical Field

[0001] Aspects of the present disclosure provide improved computational efficiency when analyzing natural language text documents. Background Art

[0002] The present disclosure relates to natural language text documents, and more specifically, to service records containing natural language text. A service record includes a service request, a solution to the service request, and intermediate communications related to the service. For example, an end user may send a service request to a technician, who may then converse with the end user to diagnose and resolve the root cause of the service request before providing a solution to the service request.

[0003] In some embodiments, these communications are processed in a structured form, where various fields hold various data (e.g., a part number field holds a value identifying a part by part number), which can be unwieldy for end users, may require a specialized application for submitting the communication, can cause confusion and errors when data is mislabeled, and is only partially effective because many forms include a "notes" field containing natural language text. In other embodiments, natural language text documents, such as email messages, are used for service records without (or with minimal) formatting of the data fields. It will be appreciated that while free-form text is generally easier for human users to process than structured data, the free-form nature of natural language text presents difficulties for computing systems to analyze the data. Summary of the Invention

[0004] In one embodiment, the present disclosure provides a method for providing a structure maintenance mapper, comprising: clustering terms in a natural language service record of a corpus of natural language service records related to a complex system based on term definitions in a knowledge base; associating the clustered terms with the coordinate system of the complex system based on a definition of a complex system including a coordinate system describing the complex system; generating an issue map for a given natural language service record of the corpus, wherein the issue map identifies the clustered terms and associated positions of the clustered terms in the given natural language service record according to the coordinate system of the complex system; and associating the issue map with the given natural language service record of the corpus.

[0005] In one aspect, in combination with any of the above or below examples, when providing a structure maintenance mapper, a given natural language service record is associated with a question map, and in response to receiving a subsequent message for the given natural language service record, a question map is updated.

[0006] In one aspect, in combination with any of the above or below examples, a method for providing a structure maintenance mapper further includes: receiving a query request indicating a criterion from an operator device; querying a corpus based on the criterion; and sending a question mapping including the criterion as a term or a location to the operator device.

[0007] In one aspect, in conjunction with any of the above or below examples, when providing a structure maintenance mapper, the term includes components of a complex system.

[0008] In one aspect, in combination with any of the above or below examples, when providing a structure maintenance mapper, clustering the terms further comprises expanding the terms to include implicit terms, and including the implicit terms in the question map.

[0009] In one aspect, in combination with any of the above or below examples, when providing a structure maintenance mapper, the implicit term includes: an intermediate position to a first position explicitly listed in a given natural language service record and an intermediate position to a second position explicitly listed in the given natural language service record.

[0010] In one aspect, in conjunction with any of the above or below examples, when providing a structure maintenance mapper, the term includes locations listed according to a coordinate system of a complex system.

[0011] In one aspect, in combination with any of the above or below examples, when a structure maintenance mapper is provided, the definition of the complex system includes multiple coordinate systems for the complex system, and wherein associating clustered terms with the coordinate systems of the complex system based on the definition of the complex system also includes associating clustered terms with the multiple coordinate systems.

[0012] In one aspect, in combination with any of the above or below examples, when providing a structure maintenance mapper, the term includes: a client identifier, a date identifier, and an issue type identifier.

[0013] The present disclosure, in another embodiment, provides a method for providing a structure maintenance mapper, comprising: displaying an image of a complex system in a user interface; receiving a high-level selection of criteria for the complex system from the user interface; based on the high-level selection, querying a question mapping associated with an individual natural language service record of a corpus of natural language service records, wherein the natural language service record of the corpus is uniquely associated with a question mapping, wherein the question mapping specifies at least one term related to the complex system and a location on the complex system associated with the at least one term; and returning at least one question mapping, wherein the at least one question mapping returned specifies a term or location related to the criteria for the complex system indicated by the high-level selection.

[0014] In one aspect, in combination with any of the above or below examples, when providing a structure maintenance mapper, returning at least one problem map further comprises: overlaying a chart onto an image of the complex system, wherein the chart displays data from the at least one problem map at a location associated with the image of the complex system.

[0015] In one aspect, in combination with any of the above or below examples, when providing a structure maintenance mapper, at least one problem map includes a location associated with the complex system in a first coordinate system and in a second coordinate system related to the first coordinate system.

[0016] In one aspect, in combination with any of the above or below examples, when a structural maintenance mapper is provided, the method further includes: displaying a second image of the complex system associated with a second coordinate system; overlaying a second chart onto the second image of the complex system, wherein the second chart displays data from at least one problem map at a location relative to the second image of the complex system according to the second coordinate system; wherein the image of the complex system is associated with the first coordinate system; and wherein the chart is overlaid on the image of the complex system according to the first coordinate system.

[0017] In one aspect, in combination with any of the above or below examples, when a structure maintenance mapper is provided, the method further includes: receiving a filter input specifying additional criteria; removing any problem mappings that do not include the additional criteria from the at least one problem mapping returned; and in response to removing any problem mappings that do not include the additional criteria from the at least one problem mapping returned, updating the graph based on the filter input.

[0018] In one aspect, in combination with any of the above or below examples, when providing a structure maintenance mapper, the filtering input specifies one of: a client identifier for which the service record was created; a time range within which the service record was created; and a problem type for which the service record was created.

[0019] In one aspect, in combination with any of the above or below examples, when providing a structure maintenance mapper, the advanced option specifies a range of locations.

[0020] In one aspect, in combination with any of the above or below examples, when providing a structure maintenance mapper, the advanced option specifies a component identifier.

[0021] In a further embodiment, the present disclosure provides a system for a structure maintenance mapper, comprising: a processor; and a non-transitory storage device comprising instructions that, when executed by the processor, enable the system to: receive a definition of a complex system, including a coordinate system for the complex system; cluster terms in a natural language service record of a corpus of natural language service records related to the complex system based on term definitions in a knowledge base; associate the clustered terms with the coordinate system of the complex system based on the definition of the complex system; associate a question mapping to a given natural language service record of the corpus, wherein the question mapping identifies the clustered terms and associated positions of the clustered terms in the given natural language service record according to the coordinate system of the complex system; receive a new service request; parse the new service request for request terms; query the corpus based on the request terms; and return at least one natural language service record of the corpus having a question mapping, wherein the question mapping specifies at least one position of the complex system related to at least one of the request terms.

[0022] In one aspect, in combination with any of the above or below examples, the system is further configured to: display an image of the complex system in a user interface; receive a selection of a portion of the complex system; determine a request term based on the selection; and wherein in response to determining the request term, query the corpus based on completing the request term.

[0023] In one aspect, in combination with any of the above or below examples, a graphical user interface is used to return at least one natural language service record of the corpus as a term graph with identified locations in a question map, the graph overlaying an image of the complex system at the corresponding locations. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] So that the manner in which the above recited features of the disclosure can be understood in detail, a more particular description of the disclosure, briefly summarized above, may be had by reference to various aspects, some of which are illustrated in the accompanying drawings.

[0025] Figure 1 An example architecture for a structural maintenance system is illustrated.

[0026] Figure 2 is a flow chart illustrating general operations in one example method for structure maintenance mapping.

[0027] Figure 3 is a flow chart illustrating general operations in one example method for structure maintenance mapping.

[0028] Figure 4A and Figure 4B An example graphical user interface for structure maintenance mapping is illustrated. DETAILED DESCRIPTION

[0029] Manufacturers and service providers are dealing with increasing amounts of service records and other data related to the lifecycle of complex systems (e.g., aircraft, ships, factories). Typically, these service records consist of natural language text, and traditional computer-based search solutions are insufficient to address the needs of complex system manufacturers and service providers due to the size of the corpus of data records and the difficulty in generating optimized search queries for discovering data related to a specific problem with a particular complex system or group of such systems.

[0030] Finding and presenting relevant service records is increasingly important because a solution to a given problem may have been described in a previous service record, or a service record may indicate a trend of problems affecting a given component of a complex system. The variations found in natural language complicate the analysis of natural language text. For example, a first customer may describe a problem as a "gouge" at a given component, and a second customer may describe the same problem as a "score" or "scratch" at a given location where the component is located. Although service records can be queried using synonyms, each query must individually account for variations in how the underlying system is described because traditional technical solutions do not allow for aggregate analysis and require repeated queries to repeatedly expend computing resources to account for differences in terminology.

[0031] The present disclosure relates to systems and methods for enabling a computing system to search for and interact with service records containing natural language text to aid in analyzing those records. The processing efficiency of a computing device is improved, and when the present disclosure is applied, fewer computing resources are expended in analyzing service records. By parsing the natural language text in a service record for terms, and normalizing those terms according to a knowledge base, a computing device can relate those terms to the coordinate space of a complex system for which a service is sought. These normalized terms and associated locations are stored with the service record as a question map so that subsequent queries (either for a single record or for aggregated records) can quickly and efficiently return analysis results.

[0032] Although several examples of complex systems are given in this disclosure as specific complex systems (such as aircraft), it will be understood by those skilled in the art that other complex systems are also contemplated for purposes of this disclosure (e.g., cars, ships, factories, rockets, buildings, bridges). Similarly, although several examples of natural language text provided in email messages are given in this disclosure, it will be understood that documents having portions of natural language text include, but are not limited to, text messages, in-application messages, voice transcriptions, word processing documents, and the like.

[0033] Now turn Figure 1, provides an example architecture of a structural maintenance system 100. The structural maintenance system 100 is a computing device that includes a processor 110 and a memory 120. The processor 110 retrieves and executes programming instructions stored in the memory 120, and stores and retrieves application data residing in the memory 120. A bus is used to transmit programming instructions and application data between the processor 110, the memory 120, I / O devices, and a network interface (not shown) to communicate with client devices and operator devices. A client device is a computing device used by a third party that operates or maintains the entity for which the service request is generated, and an operator device is a computing device used by the parties that respond to the service request (which may be the same party that maintains the structural maintenance system 100).

[0034] Processor 110 generally represents any computer hardware capable of processing information (e.g., such as data, computer programs, and / or other suitable electronic information). Processor 110 is composed of a set of electronic circuits, some of which may be packaged as an integrated circuit or multiple interconnected integrated circuits (sometimes more commonly referred to as a "chip"). Processor 110 is configured to execute a computer program, which may be stored on the processor or otherwise stored in memory 120 (of the same or another device). Depending on the specific implementation, processor 110 may represent multiple processors, a multi-processor core, or some other type of processor. Furthermore, processor 110 may be implemented using multiple heterogeneous processor systems, in which a primary processor is present along with one or more secondary processors on a single chip. As another illustrative example, processor 110 may be a symmetric multiprocessor system comprising multiple processors of the same type. In yet another example, processor 110 may be embodied as or otherwise include one or more application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), etc. Thus, while processor 110 is capable of executing a computer program to perform one or more functions, the various examples of processors may be capable of performing one or more functions without the aid of a computer program.

[0035] Memory 120 generally represents any computer hardware capable of temporarily and / or permanently storing information such as data, computer programs (e.g., computer-readable program code), and / or other suitable information. Memory 120 may include volatile and / or non-volatile memory and may be fixed or removable. Examples of suitable memory include random access memory (RAM), read-only memory (ROM), a hard drive, flash memory, a thumb drive, a removable computer disk, an optical disk, magnetic tape, or some combination thereof. Optical disks may include compact disc-read-only memory (CD-ROM), compact disc-read / write (CD-R / W), digital versatile discs (DVD), and the like. Although shown as a single unit, memory 120 may be a combination of fixed and / or removable storage devices, such as a fixed disk drive, removable memory cards or optical storage, network attached storage (NAS), or storage area network (SAN). Additionally, although shown as a component of structured maintenance system 100, memory may also include computer hardware located remotely from the structured maintenance system, such as, for example, an external hard drive, network storage, distributed systems and databases, cloud storage, and the like.

[0036] In various cases, memory 120 may be referred to as a computer-readable storage medium. A computer-readable storage medium is a non-transitory device capable of storing information and can be distinguished from a computer-readable transmission medium, such as an electronic transitory signal capable of transmitting information from one location to another. Computer-readable media, as described herein, may generally refer to either computer-readable storage media or computer-readable transmission media.

[0037] In addition to the memory 120, the processor 110 may also be connected to one or more interfaces for displaying, sending and / or receiving information. The interface may include: a communication interface (e.g., a communication unit) and / or one or more user interfaces, an example of which may be a network interface. The network interface may be configured to send and / or receive information, such as sending information to other (one or more) devices, (one or more) networks, etc. and / or receiving information from other (one or more) devices, (one or more) networks, etc. The network interface may be configured to send and / or receive information via a physical (wired) and / or wireless communication link. Examples of suitable communication interfaces include: a network interface controller (NIC), a wireless NIC (WNIC), etc.

[0038] The user interface may include: a display and / or one or more user input interfaces (e.g., input / output units). The display may be configured to present or otherwise display information to the user, suitable examples of which include a liquid crystal display (LCD), a light emitting diode display (LED), a plasma display panel (PDP), etc. The user input interface may be wired or wireless and may be configured to receive information from the user into the device, such as for processing, storage, and / or display. Suitable examples of user input interfaces include: a microphone, an image or video capture device, a keyboard or keypad, a joystick, a touch-sensitive surface (separate from or integrated into the touch screen), a biometric sensor, etc. The user interface may also include: one or more interfaces for communicating with peripheral devices such as printers, scanners, etc. In some embodiments, the user interface is omitted and / or the visual and audio output from the structured maintenance system 100 is transmitted to a client device and / or an operator device for consumption.

[0039] The memory 120 contains a knowledge base 130, a corpus 140 consisting of a plurality of service records 150 and associated problem maps 160, an information extraction engine 170, an analysis interface 180, and an operating system 190. Generally, the operating system 190 represents software configured to manage computing hardware and software resources on the structured maintenance system 100. The operating system 190 may also provide computing services for software applications executing on the structured maintenance system 100.

[0040] The knowledge base 130 identifies terms and associations between terms, locations associated with terms, and terms associated with locations that can be found in service records. These terms include, but are not limited to: component names, part numbers, client identifiers, operator identifiers, complex system identifiers, problem identifiers, and location identifiers. Associations include known synonyms, acronyms, locations of components, components at locations, locations according to a first coordinate system based on a second coordinate system, alternative names, negations (e.g., "not," "no," "none"), implicit definitions (e.g., pronouns, "through," "from X to Y"). The knowledge base 130 can be curated by an operator who is a subject matter expert (SME) to add or remove terms and associations, or automatically added or removed by a machine learning process evaluated by the SME. The information extraction engine 170 uses the knowledge base 130 to identify terms in the service records 150 to build a problem map 160 for those service records 150.

[0041] An individual service record 150 includes: an initial service request received from a client (e.g., via a client device) and intermediate communications made in response to the service request (e.g., via the client device and an operator device). Each communication in a service record includes natural language text, but each communication may also include structured data, metadata, and non-text data. For example, an email communication within a service record 150 may include natural language text from a client or operator regarding a question formatted or marked up as natural language text, such as may be formatted via structured data tags in HTML (e.g., <subject> X< / subject> and Y) to call the contents of the subject and body fields of the email. Additional formatting may also be included in the natural language text, such as, for example, tags indicating the font style or typeface to be applied to the natural language text (e.g., "bold," "italic," "Arial," "size 12," "heading 1"). Additionally, documents including natural language text may also include various metadata or non-text data, such as the time of transmission or the attachment of an image.

[0042] Several communications may be included in a service record 150, and the service record 150 will grow as communications are sent between the client and the operator. These communications may be stored together or linked across one or more corpora 140, which are repositories of service records 150. In some embodiments, a corpus 140 may contain all or a subset of service records 150. In one example, a first corpus 140 contains service records 150 from year X to year Y, and a second corpus 140 contains service records 150 from year Y to year Z. In a second example, the first corpus 140 contains service records 150 for a first client, and the second corpus 140 contains service records 150 for a second client. In a third example, the first corpus 140 contains service records 150 for a first complex system (e.g., aircraft of model A, building A), and the second corpus 140 contains service records 150 for a second complex system (e.g., aircraft of model B, building B). As will be appreciated, the corpus 140 may be divided into sub-corpora by various terms or identifiers found in the service records 150, when a communication was received, from whom the communication was received or by whom the communication was received, whether the service record 150 was designated as unconfirmed / in progress / resolved, and combinations thereof.

[0043] Communications within service records 150 are parsed by information extraction engine 170 in conjunction with knowledge base 130 to identify terms within the natural language text used in analysis corpus 140 to construct a problem map 160 for each given service record 150. Because communications comprise natural language text, the precise terminology used in a given communication may differ from one communication to another, even within a single service record 150. For example, a customer may refer to a given component as "Part X," while a carrier may refer to the same component as "Part Y," or a client may refer to the same problem in a communication as various synonyms (e.g., gouge, scratch, scar). Accordingly, information extraction engine 170 clusters the various terms found in the communications into standardized terms found in knowledge base 130. For example, instances of gouges / scratches / scars may be clustered into a standardized term, such as "surface damage," or instances of lightning / hail / thunderstorms may be clustered into a standardized term, such as "storm damage."

[0044] Clustering also expands terms into implicit components and implicit location terms that are referenced but not directly named in the natural language text. In one example, when a client specifies in natural language text "from beam 1 to beam 6," the information extraction engine 170 clusters beams 1, 2, 3, 4, 5, and 6 because beams 2-5 are implicitly referenced (i.e., are implicit location terms) based on the natural language of "from beam 1 to beam 6." In another example, the information extraction engine 170 clusters pronouns within or across sentences to refer to various terms that are explicitly referenced elsewhere, such as in natural language text: "The surface damage is extensive. It goes from point A to point Z," where 'it' implicitly refers to 'surface damage.'

[0045] The information extraction engine 170 may also access a hierarchical list of complex systems for identifying parent and child components within the complex system. As will be appreciated, a complex system may be viewed as a "root" in a hierarchical list from which all other components and assemblies descend. In one example, when a client specifies in natural language text: "landing gear assembly," the information extraction engine 170 clusters the subcomponents of the landing gear (e.g., axle, shock strut, tire) with the referenced 'landing gear assembly' as implicit components based on the hierarchical list. In a second example, the information extraction engine 170 clusters supercomponents or assemblies identified in the hierarchical list that include explicitly referenced components, such as when axles, shock struts, or tires are referenced, the term is clustered with the landing gear assembly to which the explicitly referenced component belongs.

[0046] The clustering operation performed by the information extraction engine 170 also uses the sentence and paragraph structure of the natural language text to determine which explicitly referenced terms to ignore. For example, if the communication states "component X is not damaged," the information extraction engine 170 determines that the reference to component X uses the negation term "not" and can ignore the reference to component X, potentially excluding component X from the problem map 160.

[0047] Additionally, because structural elements of complex systems may be referenced as part of a service request as components affected by a problem or as reference points to other components, the information extraction engine 170 uses the sentence and paragraph structure of the natural language text to determine which explicit component references should be considered location references. For example, a customer may reference "surface damage from window 5 to window 9, one foot above the waterline," where "window 5 to window 8" would be considered a location reference indicating that the surface damage runs in the longitudinal direction rather than referring to windows 5-9 being affected by "surface damage."

[0048] A problem map 160 is generated from the clustered terms identified in the service transcript 150 that are relevant to the service request. As will be appreciated, individual service transcripts 150 progress (e.g., as further communications are exchanged), updating the service transcript 150 with new information. For example, as a customer and operator seek to find a solution to a problem, several potential solutions or root causes may be proposed that are subsequently discovered to be unrelated to the ultimate solution or actual root cause. Accordingly, the information extraction engine 170 analyzes the service transcripts 150 in order of earliest to most recent communications. The initially generated problem map 160 includes terms found in the initial service request, as well as terms that were implicitly referenced, but as analysis of the service transcript 150 continues, the information extraction engine 170 places greater or lesser weight on terms based on the term's position in the service transcript 150. The information extraction engine 170 may employ various machine learning techniques to determine whether to include new terms or retain existing terms, which are monitored by the SME for accuracy.

[0049] The problem map 160 is associated with the service record 150 from which the problem map 160 was generated to provide a searchable body of data to the analysis interface 180. In various embodiments, unresolved service records 150 have the associated problem map 160 marked as unsearchable until such time as the service record 150 is marked as resolved. The analysis interface 180 accepts queries for service records 150 having certain characteristics (e.g., relating to client X, referencing problem Y, and / or referencing component Z) and returns aggregated metrics related to those service records 150 and / or links for accessing those service records 150. For example, a user interface (examples of which are provided in relation to Figure 4A and Figure 4B ) can provide a count of various problems illustrated on an image of the affected complex system.

[0050] In some embodiments, the problem map 160 is stored in the corpus 140 along with the service record 150 associated with the problem map 160. In other embodiments, the problem map 160 is stored separately from the service record 150, but is linked to the service record 150. By storing the problem map 160 separately from the service record 150, computer security can be improved (e.g., via reduced access to the service record 150) and memory storage space requirements can be reduced compared to storing the problem map 160 and the service record 150 together. For example, the service record 150 can be stored in an archive and / or encrypted storage device, while the associated problem map 160 can be stored in an actively assessable storage device. However, it will be appreciated that storing the problem map 160 and the service record 150 together can provide faster access to the linked service record 150 from the associated problem map 160 than storing the data separately.

[0051] The user can specify various criteria by which the analysis interface 180 searches the problem maps 160 via selections in the user interface, via text input, or by submitting a service record 150 for use as a seed. For example, the user can make advanced selections of locations on an image of a complex system, filter selections of date ranges, problem types, client identifiers, etc., in the user interface to be used by the analysis interface 180 to return service records 150 (and their metrics) that have associated problem maps 160 that include the selected criteria. In another example, the user can enter various criteria as text that is normalized according to clusters defined in the knowledge base 130 to search the problem maps 160 for matches. In another example, the user can submit a service record 150 (resolved or unresolved) to search the corresponding problem maps 160 for service records 150 that contain the same or similar terms.

[0052] The question map 160 provides improved efficiency for the structured maintenance system 100 when searching a large corpus 140 of natural language text. By searching the question map 160 rather than individual service records 150, multiple instances or repetitions of terms in the service records 150 are not reflected as multiple hits for the query, thereby improving data accuracy and using fewer processing resources. Additionally, by standardizing and collecting (and cross-correlating) terms in the service records 150 in the question map 160 regardless of the query, query results are returned to the user more quickly and the service records 150 can be retained in their original format. Furthermore, by storing the question map 160 as associated with or linked to the related service records 150, fewer computations need to be processed, further reducing the processing resources consumed.

[0053] Figure 2 2 is a flow chart illustrating the general operations of an example method 200 for structured maintenance mapping. The method 200 begins at block 210, where a complex system definition is received. A complex system is an entity associated with at least one coordinate system for which a service request is issued. In one example, several types of aircraft may have complex system definitions associated with stringers, waterlines, fuselage longitudinal sections (also known as butt-lines), and fuselage stations within that type of aircraft. In another example, different classes of ships may have complex system definitions that use decks and bulkheads as coordinate systems.

[0054] At block 220, a corpus 140 of natural language service records 150 is accessed. In various embodiments, the corpus 140 is selected (or filtered from the large corpus 140) based on the complex system definition accessed in block 210. In other embodiments, the corpus 140 is selected using additional or different criteria, including: the status of the service record 150 (e.g., resolved vs. unresolved), when the service record 150 was received, from / by whom the service record 150 was received, etc. The corpus 140 includes a plurality of service records 150 that include natural language text related to the problem for which service is sought.

[0055] Proceeding to box 230, the information extraction engine 170 utilizes the knowledge base 130 to parse the natural language text to identify and cluster terms found in the natural language service record 150. These terms include: various names or identifiers for components of a complex system, locations in a complex system, questions for services, customers, operators, and date identification. These terms are clustered into a standardized form and expanded to include any implicit terms based on the relationships set in the knowledge base 130. The knowledge base 130 defines terms that are related to each other (e.g., synonyms, parent components, child components), spelling errors and typos of known terms, and term tags that specify additional implicit terms, such as "through", "-", "both", "all", etc. As will be understood, implicit terms include internal terms that are related to the listed terms, for example, such as an intermediate position in a range of positions, a child component of a listed component, a super component of a listed component, a parent company of a listed customer, a date within a range, etc.

[0056] In addition to positive clustering, the information extraction engine 170 performs negative clustering and reference clustering to remove mentions of terms that are not relevant to the issue for which service is being requested. For example, the terms "not," "no," "none," and similar terms may be used in natural language to indicate that the indicated term is not affected by the issue for which service is being requested and should be ignored by the information extraction engine. Similarly, terms such as "near," "below," "above," "beside," and the like may be used in natural language to indicate a location relative to a referenced component, but are not necessarily intended to indicate that the referenced component is affected by the issue for which service is being requested, and are treated as location terms by the information extraction engine 170. For example, a service request may indicate that surface damage occurred below an access hatch, which the information extraction engine 170 interprets to determine the location of the surface damage that occurred (i.e., "below" the access hatch).

[0057] At box 240, the information extraction engine 170 utilizes the knowledge base 130 and the complex system definition to associate the clustered terms with a coordinate system of the complex system. This association is bidirectional for components and locations referenced in the communication. For example, a location listed in the communication is cross-referenced with components located at or around that location and associated with the listed location. In a second example, a component listed in the communication is cross-referenced with the location where that component is located in the complex system. In a third example, a component that is implicitly referenced as a child of a listed component is associated with a location associated with the listed parent component. When more than one coordinate system is available in the complex system definition, each of the coordinate systems is associated with a clustered term from the service record 150.

[0058] Proceeding to block 250, a problem map 160 is generated for the natural language service transcript 150. Each problem map 160 is associated with a service transcript 150 and includes terms found in the service transcript 150, including both implicitly referenced and explicitly referenced terms. In service transcripts 150 determined to include negated terms, such terms may be removed from the problem map 160 or included as negated terms for later reference. These terms are listed in the problem map 160 in association with any location on the complex system with which the terms are associated. For example, a client's term (e.g., "Acme, Inc.") is stored in the problem map 160 without reference to a location on the complex system, but a term for a component affected by the problem for which service is requested (e.g., "fuselage skin") is stored in the problem map 160 with respect to the location on the complex system. Similarly, in some embodiments, terms for a location found in the service transcript 150 are stored with respect to the component at that location. In embodiments where multiple coordinate systems are used for a complex system, terms are stored in the problem map 160 in association with each of the available coordinate systems that can be used to describe the position of the term as part of the complex system.

[0059] At block 260, the question map 160 is associated with a given service record 150 of the corpus 140. The question maps 160 of all service records 150 in the corpus 140 are searchable by an operator who can access the corpus 140 via any term stored in the question map 160. When queried, the question map 160 provides a link to the associated service record 150 (e.g., for user analysis of natural language text) and counts of various terms found therein (e.g., for analysis of the frequency of components, locations, and / or question types).

[0060] The method 200 may then end or repeat (updating the problem map 160) when a new communication is received as part of a new or existing service record.

[0061] Figure 3 3 is a flow chart illustrating the general operations of an example method 300 for structured maintenance mapping. Method 300 begins at block 310, where an image of a complex system is displayed in a user interface. In various embodiments, one or more images of the complex system are presented in different views, such as images of a front view and a side view of the complex system, or as an isometric view of the complex system. Each image of the complex system is associated with at least one coordinate system of the complex system, such that metrics associated with various locations according to the coordinate system can be displayed in association with the image for visual analysis.

[0062] Proceeding to block 320, an advanced selection of one or more criteria related to the complex system is received. In some embodiments, the advanced selection includes: a location selected from the displayed image; a range of locations selected from the displayed image; a location or range of locations selected via text input; a client, service record age range, component and problem type, or complex system age range selected from a user interface control (e.g., a drop-down menu); a client, service record age range, component and problem type, or complex system age range selected via text input; and selection of various criteria matched against criteria found in the problem map 160 of the selected service record 150.

[0063] In various embodiments, depending on how the requested term is selected, analysis interface 180 interprets the user's input to determine what the requested term is. For example, selecting a portion of an image of a complex system will cause analysis interface 180 to identify the location indicated on the image and determine the term for the component and / or location on the complex system that corresponds to the image selection. In another example, inputting a text selection will cause analysis interface 180 to cluster the input term into a standardized form, which can then be compared to the terms in question map 160.

[0064] At block 330, the analysis interface 180 proceeds to query the corpus 140 of the natural language service transcript 150 based on the selection(s) received from the user. The analysis interface 180 employs the criteria of the terms and / or positions indicated in the selection(s) and locates the question mappings 160 that contain the criteria indicated by the selections. At block 340, the question mappings 160 that match the selection criteria are returned from the corpus 140 to the analysis interface 180.

[0065] Proceeding to box 350, the analysis interface 180 compiles and displays the metrics indicated in the returned problem map 160 in association with the displayed image of the complex system. For example, a heat map of the locations of the problems in the problem map 160 is overlaid in association with the frame image of the complex system. In other embodiments, bubble charts, three-dimensional bar charts, and other visualizations are used to indicate the number or frequency of problems occurring for a given term at a given location on the image. For terms that are not associated with a location on the complex system (e.g., clients with problems with the complex system for which service is requested), visualizations independent of the image, such as bar charts, pie charts, bubble charts, scatter plots, line graphs, etc., are displayed separately from the image of the complex system in the user interface. Additionally, one or more links are displayed in the user interface for downloading or otherwise viewing natural language text of the associated service record 150.

[0066] At block 360, a determination is made as to whether a subsequent selection has been made. A subsequent selection may include selecting new or additional query criteria to refine or filter the results presented in response to the current or previous query. In response to determining that the user has made a subsequent selection, method 300 returns to block 330 to further query corpus 140. In response to determining that the user has not made a subsequent selection, method 300 may then end or wait to repeat until such time as a new query is made against question map 160 of corpus 140.

[0067] Figure 4A and Figure 4B An example graphical user interface (GUI) for structured maintenance mapping is described. Figure 4A and Figure 4B Each of the GUI 401 and GUI 402 illustrated in FIG may be displayed individually or in combination with one another depending on the screen space available for the user interface. Therefore, it will be understood that the examples shown are given for illustration purposes only.

[0068] exist Figure 4A In the GUI 401 illustrated in FIG, a first image 410 of a complex system is displayed above a line graph 420 of the frequency of service record submissions and above a first bar graph 430 of the age of entities that have submitted service records 150 (at the time of submission or at the time of analysis or at the time of analysis). Figure 4B In the illustrated GUI, a second image 440 of the complex system is displayed above a bar graph 450 of the number of clients that have submitted service requests, a bar graph 460 of the number of components involved in the service record 150, and a bar graph 470 of the number of problem types that resulted in the service request. It will be understood that the elements discussed as part of GUI 401 and GUI 402 may be displayed in an arrangement different from that shown in the illustrated example.

[0069] Each of the first image 410 and the second image 440 of the complex system is overlaid with data (in the form of bubbles belonging to a bubble chart, where the size of the bubble indicates the number of service requests linked to the specific location) indicating issues identified at the displayed location. The illustrated example provides the first image 410 as a front view of an aircraft, and the second image 440 as a side view of the same aircraft. It will therefore be understood that the data overlaid on the images is the same data presented according to different coordinate systems associated with various terms from the returned problem map 160. For example, the first image 410 presents data around a circular cross-section of the aircraft via stringer coordinates, and presents that data across the width of the aircraft at various fuselage longitudinal section coordinates. This same data is again presented in the second image 440 as waterline / stringer coordinates relative to the width and height of the aircraft, and as fuselage station coordinates relative to the length of the aircraft.

[0070] While the analysis interface 180 enables the user to interact with various display elements to further refine previous queries of the corpus 140, submit new queries to the corpus 140 (including queries for different entities), request that previous queries be rerun or re-rendered, and change the criteria used to analyze the data. In some embodiments, the analysis interface 180 sends the results to the operator device to display a user interface populated by the structured maintenance system 100, while in other embodiments, the analysis interface 180 sends data to the operator device to populate the user interface on the operator device. In some embodiments, the data sent to the operator device is the problem map 160, which provides the benefit of reducing the bandwidth required to analyze the corpus 140 compared to sending the service record 150 to the operator device.

[0071] The description of various embodiments of the present disclosure has been presented for illustrative purposes, but is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, practical applications, or technical improvements to the technology found in the marketplace, or to enable those skilled in the art to understand the embodiments disclosed herein.

[0072] As will be appreciated by those skilled in the art, aspects of the present disclosure may be embodied as a system, method, or computer program product. Accordingly, aspects of the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment (including firmware, resident software, microcode, etc.), or an embodiment of a combination of software and hardware, which may generally be referred to as a "circuit," "module," or "system." Additionally, aspects of the present disclosure may take the form of a computer program product embodied in one or more computer-readable media having a computer-readable program code embodied therein.

[0073] Any combination of one or more computer-readable media may be utilized. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer-readable storage media would include the following: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electronically erasable programmable memory (EEPROM) (such as flash memory, optical fiber), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium may be any tangible medium that can contain or store a program used by or in conjunction with an instruction execution system, apparatus, or device.

[0074] A computer-readable signal medium may include a propagated data signal with computer-readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electromagnetic, optical, or any suitable combination thereof. A computer-readable signal medium may be any computer-readable medium that is not a computer-readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0075] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0076] The computer program code for performing the operations of various aspects of the present disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, Smalltalk, C++, and traditional procedural programming languages, such as the "C" programming 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 separate 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 through 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).

[0077] Various aspects of the present disclosure are described with reference to flowchart illustrations and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams and the combination of blocks in the flowchart illustrations 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 device to produce a machine, so that instructions executed by the processor of the computer or other programmable data processing device create a device for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0078] These computer program instructions may also be stored in a computer-readable medium that can direct a computer, other programmable data processing apparatus, or other device to function in a specific manner so that the instructions stored in the computer-readable medium produce an article of manufacture that includes instructions for implementing the functions / actions specified in the flowchart and / or block diagram blocks.

[0079] The computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide a process for implementing the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0080] The present disclosure may be a system, method, and / or computer program product. The computer program product may include one or more computer-readable storage media having computer-readable program instructions thereon for causing a processor to perform various aspects of the present disclosure.

[0081] A computer-readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer-readable storage media includes the following: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a DVD, a memory stick, a floppy disk, a mechanical encoding device (such as a punched card or raised structure in a groove on which instructions are recorded), and any suitable combination of the foregoing. As used herein, a computer-readable storage medium should not be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave transmitted through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0082] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a corresponding computing / processing device or downloaded to an external computer or external storage device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network). The network can include copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in a computer-readable storage medium within the corresponding computing / processing device.

[0083] The computer-readable program instructions for performing the operation of the present disclosure can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Java, Smalltalk, C++, and traditional procedural programming languages such as "C" programming language or similar programming languages. The computer-readable program instructions can be executed entirely on the user's computer, partially on the user's computer, as an independent 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 through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an internet service provider via the internet). In some embodiments, the electronic circuit system including, for example, a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA) can execute the computer-readable program instructions with personalized electronic circuit system by utilizing the state information of the computer-readable program instructions to perform various aspects of the present disclosure.

[0084] Various aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0085] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device create a device for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, which can direct the computer, programmable data processing device, and / or other equipment to function in a specific manner, so that the computer-readable storage medium having the instructions stored therein includes an article of manufacture, which includes instructions for implementing various aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0086] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0087] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functions and operations of possible implementations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, segment or part of an instruction, which includes one or more executable instructions for realizing (one or more) specified logical functions. In some alternative embodiments, the functions mentioned in the box may not occur in the order described in the figure. For example, the two boxes shown in succession can actually be performed substantially simultaneously, or these boxes can sometimes be performed in reverse order, depending on the functions involved. It should also be noted that each box of the block diagram and / or flowchart illustration and the combination of the boxes in the block diagram and / or flowchart illustration can be implemented by a system based on special-purpose hardware, which performs a specific function or action or performs a combination of special-purpose hardware and computer instructions.

[0088] Furthermore, the present disclosure includes embodiments according to the following embodiments:

[0089] Example 1. A method comprising:

[0090] Clustering terms in a corpus (140) of natural language service records (150) related to a complex system based on term definitions in a knowledge base (130); (230)

[0091] Based on the definition of complex systems, which includes a coordinate system for describing complex systems, the term clustering is associated with the coordinate system of complex systems; (240)

[0092] generating a question map (160) for a given natural language service transcript (150) of the corpus (140), wherein the question map (160) identifies clustered terms and associated positions of the clustered terms in the given natural language service transcript (150) according to a coordinate system of the complex system; (250) and

[0093] Associating a question map (160) with a given natural language service record (150) of a corpus (140). (260)

[0094] Embodiment 2. The method of embodiment 1, wherein a given natural language service record (150) is associated with a question mapping (160), and in response to receiving a subsequent message for the given natural language service record (150), a question mapping (160) is updated.

[0095] Embodiment 3. The method according to any one of embodiments 1-2, further comprising:

[0096] receiving a query request indicating a standard from an operator device;

[0097] querying the corpus (140) based on the criteria; and

[0098] The question map (160) including the criteria as terms or locations is sent to the operator equipment.

[0099] Embodiment 4. The method of any one of embodiments 1-3, wherein the term includes a component of a complex system.

[0100] Embodiment 5. The method of any one of embodiments 1-4, wherein clustering the terms further comprises expanding the terms to include implicit terms, and including the implicit terms in the question map (160).

[0101] Example 6. The method of Example 5, wherein the implicit term includes a position intermediate to a first position explicitly listed in a given natural language service record (150) and a second position explicitly listed in a given natural language service record (150).

[0102] Embodiment 7. The method of any one of embodiments 1-6, wherein the term includes a position listed according to a coordinate system of the complex system.

[0103] Example 8. A method according to any one of Examples 1-7, wherein the definition of the complex system includes multiple coordinate systems for the complex system, and wherein associating clustered terms with the coordinate systems of the complex system based on the definition of the complex system also includes associating clustered terms with multiple coordinate systems.

[0104] Embodiment 9. The method of any one of embodiments 1-8, wherein the term comprises: a client identifier, a date identifier, and a question type identifier.

[0105] Example 10. A method comprising:

[0106] Displaying an image of the complex system in a user interface (410); (310)

[0107] Receive high-level selection of standards for complex systems from a user interface; (320)

[0108] Based on the advanced selection, querying a question mapping (160) associated with an individual natural language service record (150) of the corpus (140) of natural language service records (150), wherein the question mapping (160) specifies at least one term related to a complex system and a location on the complex system associated with the at least one term; (330) and

[0109] At least one problem mapping (160) is returned, wherein the returned at least one problem mapping (160) specifies a term or location associated with a standard of the complex system indicated by the high-level selection. (340)

[0110] Example 11. The method of Example 10, wherein returning at least one problem map (160) further comprises overlaying a chart onto an image (410) of a complex system, wherein the chart displays data from at least one problem map (160) at a location relative to the image (410) of the complex system.

[0111] Embodiment 12. The method of embodiment 11, wherein at least one problem map (160) includes a location associated with the complex system in a first coordinate system and a second coordinate system associated with the first coordinate system.

[0112] Example 13. The method according to Example 12, further comprising:

[0113] displaying a second image of the complex system associated with the second coordinate system (440);

[0114] overlaying a second chart onto the second image (440) of the complex system, wherein the second chart displays data from the at least one problem map (160) at locations relative to the second image (440) of the complex system according to a second coordinate system;

[0115] wherein the image (410) of the complex system is associated with a first coordinate system; and

[0116] In this case, the diagram is overlaid on the image of the complex system according to the first coordinate system.

[0117] Embodiment 14. The method of any one of embodiments 11-13, further comprising: receiving a filter input specifying additional criteria;

[0118] removing any question mapping (160) from the returned at least one question mapping (160) that does not include the additional criteria; and

[0119] In response to removing any question mapping from the returned at least one question mapping that does not include the additional criteria, updating the graph based on the filter input. (350)

[0120] Embodiment 15. The method of embodiment 14, wherein the filter input specifies one of the following:

[0121] The client identifier for which the service record is created (150);

[0122] The timeframe in which the service record (150) was created; and

[0123] The type of problem for which a service record (150) is created.

[0124] Embodiment 16. The method of any one of embodiments 10-15, wherein the advanced selection specifies a range of locations.

[0125] Embodiment 17. The method of any one of embodiments 10-16, wherein the advanced selection specifies a component identifier.

[0126] Example 18. A system comprising:

[0127] a processor (110); and

[0128] A non-transitory storage device comprising instructions that, when executed by a processor (110), enable the system to:

[0129] receiving a definition of a complex system, including a coordinate system for the complex system;

[0130] clustering terms in a corpus (140) of natural language service records (150) related to a complex system based on definitions of the terms in the knowledge base (130);

[0131] Based on the definition of complex systems, the terminology of clustering is associated with the coordinate system of complex systems;

[0132] associating a question map (160) to a given natural language service transcript (150) of the corpus (140), wherein the question map (160) identifies clustered terms and associated positions of the clustered terms in the given natural language service transcript (150) according to a coordinate system of the complex system;

[0133] Receive new service requests;

[0134] Resolve new service requests for request terms;

[0135] querying the corpus (140) based on the request terms; and

[0136] At least one natural language service record (150) of the corpus (140) having a question mapping (160) is returned, the question mapping (160) specifying at least one location of the complex system related to at least one of the request terms.

[0137] Embodiment 19. The system of embodiment 18, wherein the instructions further enable the system to:

[0138] Displaying images of complex systems in user interfaces;

[0139] the choice to receive a portion of a complex system;

[0140] determining a request term based on the selection; and

[0141] Wherein in response to determining the request term, a corpus is queried based on the request term being completed (140).

[0142] Example 20. A system according to any one of claims 18-19, wherein the graphical user interface (401) is used to return at least one natural language service record (150) of the corpus (140) as a term graph with the identified positions in the problem map (160), the graph overlaying an image of the complex system at the corresponding positions.

[0143] While the foregoing is directed to embodiments of the present disclosure, other and further embodiments of the disclosure may be devised without departing from the basic scope thereof, and the scope of the disclosure is determined by the claims that follow.

Claims

1. A method comprising: clustering terms in a corpus (140) of natural language service records (150) related to a complex system based on definitions of the terms in the knowledge base (130); Based on a definition of the complex system including a coordinate system describing the complex system, associating clustered terms with the coordinate system of the complex system; generating a question map (160) for a given natural language service record (150) of the corpus (140), wherein the question map (160) identifies the terms of the cluster and the associated positions of the terms of the cluster in the given natural language service record (150) according to the coordinate system of the complex system, wherein the question map is associated with a single natural language service record and reduces multiple instances of a given term in the given natural language service record to a single cluster associated with the given term; as well as The question map (160) is associated with the given natural language service record (150) of the corpus (140).

2. The method of claim 1 , wherein the given natural language service record (150) is associated with a question map (160), and in response to receiving a subsequent message of the given natural language service record (150), the question map (160) is updated.

3. The method according to any one of claims 1 to 2, further comprising: receiving a query request indicating a standard from an operator device; querying the corpus based on the criteria (140); as well as A question map (160) including the criteria as terms or locations is sent to the operator device.

4. The method according to claim 1, wherein Clustering the terms further includes expanding the terms to include implicit terms, and including the implicit terms in the question map (160).

5. The method according to claim 1, wherein The definition of the complex system includes a plurality of coordinate systems for the complex system, and wherein associating terms of the cluster with the coordinate systems of the complex system based on the definition of the complex system further comprises associating terms of the cluster with the plurality of coordinate systems.

6. A method comprising: displaying an image of the complex system in a user interface (410); receiving a high-level selection of criteria for the complex system from the user interface; querying, based on the high-level selection, question mappings (160) associated with individual natural language service records (150) of the corpus (140) of natural language service records (150), wherein the question mappings (160) specify terms of at least one cluster related to the complex system and locations on the complex system associated with the terms of the at least one cluster, and, based on a definition of the complex system, the terms of the clusters are associated with a coordinate system of the complex system, and wherein each question mapping is associated with a single natural language service record and reduces multiple instances of a given term in the associated natural language service record to a single cluster associated with the given term; as well as At least one question map (160) is returned, wherein the at least one question map (160) returned specifies a term or location related to the standard of the complex system indicated by the high-level selection.

7. The method according to claim 6, wherein: Returning the at least one question map (160) further comprises: A chart is overlaid onto the image (410) of the complex system, wherein the chart displays data from the at least one problem map (160) at a location relative to the image (410) of the complex system.

8. The method according to claim 7, wherein: The at least one problem map (160) includes a position associated with the complex system in a first coordinate system and a second coordinate system associated with the first coordinate system.

9. The method according to claim 8, further comprising: displaying a second image of the complex system associated with the second coordinate system (440); overlaying a second chart onto the second image (440) of the complex system, wherein the second chart displays the data in the at least one problem map (160) at locations relative to the second image (440) of the complex system according to the second coordinate system; wherein the image (410) of the complex system is associated with the first coordinate system; and The diagram is overlaid on the image of the complex system according to the first coordinate system.

10. A system comprising: Processor (110); as well as A non-transitory storage device comprising instructions that, when executed by the processor (110), enable the system to: receiving a definition of a complex system including a coordinate system for the complex system; clustering terms in a natural language service record (150) of a corpus (140) of natural language service records (150) related to the complex system based on the term definitions in the knowledge base (130); Associating clustered terms with the coordinate system of the complex system based on the definition of the complex system; associating a question map (160) to a given natural language service record (150) of the corpus (140), wherein the question map (160) identifies the terms of the cluster and the associated positions of the terms of the cluster in the given natural language service record (150) according to the coordinate system for the complex system, wherein the question map is associated with a single natural language service record and reduces multiple instances of a given term in the given natural language service record to a single cluster associated with the given term; Receive new service requests; parsing the new service request for request terms; querying the corpus based on the request terms (140); as well as At least one natural language service record (150) of the corpus (140) having a question mapping (160) that specifies at least one location of the complex system associated with at least one of the request terms is returned.

Images