Computing system for evaluating product demand
Through the computing system, the missing information and errors in product requirements are automatically identified and output, and the problem of low efficiency of auditing complex product requirements in the existing technology is solved, automated audit is realized, and product development efficiency and quality are improved.
Patent Information
- Application Number
- CN202411061246.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-09-01
- Filing Date
- 2024-08-05
- Publication Date
- 2025-03-07
AI Technical Summary
The existing technology is difficult to effectively review and identify missing information and errors in product requirements, resulting in high cost of design, manufacturing and testing of complex products, long construction periods and high performance risks.
Provides a computing system that processes input product demand text through a processor, identifies demand types, determines required elements using predefined requirements criteria, applies natural language processing and predefined feature recognition rules, and automatically recognizes and outputs the presence or absence indications of required elements.
The system can automatically identify missing information and errors in product requirements, reduce the time and cost of manual review, and improve the efficiency and quality of product development.
Smart Images
Figure CN119577141A_ABST
Abstract
Description
Technical Field
[0001] The field of the invention relates generally to requirements for products and services, and more particularly to tools for assisting writers of product requirements in evaluating product requirements. Background Art
[0002] Written product requirements are used to establish and communicate the various characteristics of an item. For example, a purchaser may establish requirements to communicate the characteristics of a purchased item to a supplier. The supplier may use these requirements to design, develop, and manufacture the item, or otherwise provide the item to the purchaser. For less complex products, such as consumer products, the product requirements may only need to define the performance or other characteristics of a relatively small number of parts and components of the product. However, more complex products, such as aerospace vehicles, may include millions of parts and components. Drafting high-quality product requirements for such complex products can be much more complex. For more complex products, poorly drafted requirements can result in higher costs, longer schedules, and greater performance risks.
[0003] Incorrect, incomplete, or ambiguous product requirements can adversely affect the design, manufacture, and testing of items. For example, these requirements may result in items that do not meet expectations or needs. These items may need to be redesigned and remanufactured at great cost. This is evidenced by the cancellation of many commercial and military aviation and space vehicle development programs in the past decade. Therefore, it is critical to effectively review and identify missing information and errors in product requirements. Summary of the invention
[0004] In view of these problems, a computing system for evaluating product requirements is provided. According to one aspect, the computing system includes a processor coupled to a memory storing instructions, which, when executed by the processor, cause the processor to store input text of product requirements. The processor is further configured to identify a requirement type for the input text from a plurality of candidate requirement types. The processor is further configured to determine a plurality of required elements for the identified requirement type from a plurality of candidate elements using predefined requirement criteria. The processor is further configured to perform natural language processing on the input text using a natural language processing model, thereby applying one or more tags from a predefined tag set to corresponding portions of the input text to generate a labeled input text. The processor is further configured to apply one or more predefined element recognition rules to the labeled input text, thereby identifying the presence or absence of each of the plurality of required elements in the input text for the product requirements. The processor is further configured to output an indication of the identified presence or absence of each of the plurality of required elements in the product requirements.
[0005] This summary is provided to introduce a selection of concepts in a simplified form, which are further described in the detailed description below. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. Furthermore, the claimed subject matter is not limited to implementations that solve any or all disadvantages noted in any part of this disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0006] Figure 1 A schematic diagram illustrating an example computing system for evaluating product demand according to an example implementation of the present disclosure.
[0007] Figure 2 A schematic diagram showing an example GUI including input text for a product requirement and an identified requirement type.
[0008] Figure 3 Example predefined requirement criteria are shown.
[0009] Figure 4 An example predefined label set and example labeled input text are shown.
[0010] Figure 5 A schematic diagram of an example GUI including an identified requirement type, an indication of the presence or absence of each required element in the product requirement, and a score for the input text is shown.
[0011] Figure 6 A schematic diagram is shown of an example GUI including an indication of a report with a chart indicating an identified presence or absence in a product requirement and non-compliance of one or more predefined element identification rules for each of a plurality of required elements.
[0012] Figure 7 A flow chart illustrating a computerized method for assessing product demand according to one example configuration of the present disclosure.
[0013] Figure 8 Schematically showing the Figure 1 An example computing environment instantiated by a computing system. DETAILED DESCRIPTION
[0014] As described above, identifying missing information and errors in product requirements contributes to the successful development of complex products. However, current systems and methods for reviewing product requirements and identifying missing information have a manual process whereby a human reviewer checks for missing information in product requirements. These manual reviews are time consuming and often fail to effectively identify missing information.
[0015] To solve the above problems, a computing system and a computerized method for evaluating product demand are disclosed herein. Figure 1 A computing system 100 for evaluating product requirements is shown, the computing system 100 including a processor 12 coupled to a memory 14 storing instructions, which when executed by the processor cause the processor 12 to perform certain functions as described below. In the depicted configuration, the computing system 100 may include a processor 12, a memory 14, and a storage device 20, which may be operably coupled to each other via a communication bus. The processor 12, the memory 14, and the storage device 20 may each be configured as one or more physical components, such as one or more processor cores and / or one or more physical memory modules. The storage device stores instructions for various software components described herein as being executed by the processor 12, and also stores data sets 22 used by these software components in a non-volatile manner. The computing system 100 may further include an input device 16, which may be a keyboard, a mouse, a touch screen, a touchpad, an accelerometer, a microphone, or some other suitable type of input device. In addition, the computing system 100 may further include an output device 18, which may be a display, a speaker, or some other suitable type of output device. The computing system 100 may be any of various types of computing devices, such as a laptop, a desktop, or a server. In addition, the computing system 100 may be one of a plurality of server devices in a data center, and the processor 12 may be a processor of a single server device, or a plurality of processors of a plurality of server devices.
[0016] When executed by the processor 12, the instructions stored in the memory 14 cause the processor 12 to store the input text 24 of the product requirement in the storage device 20. The product requirement 26 can be a written description of mandatory or other (e.g., optional) characteristics of a system, service, or other product or item. The product requirement 26 can be a product requirement for a target aerospace component, and the product requirement can be selected from a group consisting of government rules, regulations, and contract requirements. Product requirements typically include natural language text. Therefore, the input text 24 of the product requirement 26 can be generated by an operator in a natural language. For example, but not limiting, the input text 24 can be in the form of a natural language statement, which is a language used by humans to communicate with each other. The processor 12 is configured to display the input text 24 of the product requirement 26 on the GUI 36. In the depicted example, the input text 24 includes and is displayed on the GUI 36 "The system should display the aircraft altitude when in an operational state."
[0017] Continue to refer Figure 1, the processor 12 is further configured to identify a requirement type 50 for the input text 24 from a plurality of candidate requirement types via the requirement type classifier 40. The requirement type 50 describes a characteristic of a product requirement. There may be a plurality of requirement types 50, examples of which are shown in the accompanying drawings as requirement type 1, requirement type 2, requirement type 3, and requirement type 4. In one example configuration, the plurality of candidate requirement types may be selected from the group consisting of functional requirements, design requirements, environmental requirements, and applicability requirements. It will be appreciated that this list is not exhaustive and other requirement types may be used in addition or in lieu thereof.
[0018] Functional requirements describe the functional and performance behaviors that perform the required actions or functions at the boundaries of an item. Functional requirements define input / output transitions at the boundaries of an item. Functional requirements define output responses to some input trigger or system state condition, both of which can be observed at the boundaries of an item. Design requirements describe how an item or its elements are designed or manufactured. Design requirements express mandatory features about how a product or service is manufactured, thereby constraining the design or manufacture of an item or its elements. Design requirements can summarize lessons learned and achieve the desired performance by using mature design solutions. Design requirements can address non-boundary items (such as parts, materials, and processes) and can provide alternatives to more complex performance requirements. When developers want to add specific features to a design solution, design requirements may come from previous experience with similar systems. Design requirements can include authorization to use specific legacy parts or other non-development items.
[0019] Environmental requirements describe the exposure or generated environment through which the item must survive or function during all or part of its life cycle. Suitability requirements describe the safety, security, reliability, availability, maintainability, or other health characteristics of the item. Suitability requirements may also specify the permissible impacts that the item may have on the external environment. Suitability requirements may describe the degree to which a system or end item can be used satisfactorily in the field, taking into account availability, compatibility, transportability, interoperability, reliability, utilization, maintainability, full-scale protection, operational safety, human factors, building and infrastructure compliance, manpower supportability, logistics supportability, natural environmental effects and impacts, documentation and training requirements, and / or any other factors considered individually or together in any combination.
[0020] Continue to refer Figure 1, a requirement type 50 can be identified using a requirement type classifier 40 (i.e., a trained machine learning model) that has been trained using a training data set that includes input text from historical product requirements and ground truth data indicating the requirement type 50 for each input text. The trained machine learning model can be a category classification model that can identify text entries with labels. It will be appreciated that the requirement type 50 can also be identified by the user based on the user's own knowledge and experience. In the described example, the identified requirement type 50 is "Requirement Type 1", as shown in the GUI 36. Turning temporarily to Figure 2 , which shows a schematic diagram of an example GUI 36 including input text 24 of a product requirement 26 and an identified requirement type 50. Figure 2 As shown therein, a requirement type 50 is identified for each input text 24. As discussed above, the requirement type 50 may be, for example, a functional requirement, a design requirement, an environmental requirement, a serviceability requirement, or other requirement type.
[0021] Return to Figure 1 , the processor 12 is further configured to determine a plurality of required elements 60 for the identified requirement type 50 from the plurality of candidate elements using the predefined requirement criteria 48. Figure 3 , which illustrates example predefined requirement criteria 48 for determining required elements 60 for a required type 50. The predefined requirement criteria 48 illustrate one or more of the required elements 60 that are required for the required type 50. In the depicted example, elements 1, 4, and 5 are required for requirement type 1, element 1 is required for requirement type 2, elements 1, 2, and 5 are required for requirement type 3, and element 4 is required for requirement type 4. For example, but not limitation, the plurality of required elements 60 may be selected from the group consisting of agent elements, functional elements, output elements, performance elements, timing elements, and conditional elements. Thus, in the depicted example, element 1 may be an agent element, element 2 may be a functional element, element 3 may be an output element, element 4 may be a timing element, and element 5 may be a conditional element.
[0022] Agent elements identify items that perform required actions or functions or process required characteristics. Functional elements describe the actions or behaviors of agents. Functional elements refer to what an agent does that can be observed at its boundaries. Output elements are locations where functions can be observed and evaluated, as well as associated constraints. Performance elements are measurable attributes of functions or design properties that enable success or failure to be determined during verification of items against requirements. Performance elements are usually quantitative. Performance elements describe the extent to which an application, system, or component completes its designed functions under given constraints (such as speed, accuracy, or memory usage). Timing elements are statements of how fast or how long behaviors associated with state changes and triggering conditions need to take. Conditional elements describe situations in which agents are to perform actions or functions. Conditional elements can include states, modes, environments, restrictions, special conditions, configurations, or combinations thereof that affect or limit the applicability of requirements. A state or mode is a condition or combination of conditions that occurs under a defined situation.
[0023] Return to Figure 1 The processor 12 is further configured to perform natural language processing on the input text 24 using a natural language processing model via a natural language processing module 52, thereby applying one or more tags 56 from a predefined tag set 54 to corresponding portions of the input text 24 to generate a labeled input text 58. The natural language processing model can be one of the publicly available natural language processing models that performs part-of-speech (POS) tagging. Turning temporarily to Figure 4 , which shows an example predefined tag set 54 and labeled input text 58. The predefined tag set 54 is a collection of tags 56 used to classify words into parts of speech and label the input text 24 accordingly. As shown in the depicted example, NN (noun singular) and NNP (proper noun singular) are tags for singular nouns, ADJ (adjective) is a tag for adjectives, and VB and VBD are tags for verbs. The natural language processing module 52 applies one or more tags 56 from the predefined tag set 54 to each word of the input text 24 to generate labeled input text, such as Figure 4 As shown. For example, NNP (proper noun singular) is applied to "avionics" and "system" of the input text 24, and VB (verb, prototype) is applied to "comply" of the input text 24. The natural language processing performed by the natural language processing module 52 further includes keyword replacement and / or keyword recognition. Keyword recognition recognizes whether the input text 24 contains predetermined keywords. For example, "shall" can be one of the predetermined keywords, and the natural language processing module 52 recognizes whether the input text 24 contains "shall".
[0024] Return to Figure 1 , the processor 12 is further configured to apply one or more predefined element identification rules 64 to the tagged input text 58 via the element identification module 62, thereby identifying the presence or absence of each of the multiple required elements 60 in the input text 24 for the product requirement 26. The element identification module 62 identifies whether each of the multiple required elements 60 (e.g., agents, functions, conditions) is present in the input text 24 according to the one or more predefined element identification rules 64. The one or more predefined element identification rules 64 may further include additional rules, such as but not limited to sorting rules, singularity rules, and keyword rules. For example, according to the singularity rule, the agent (element) discussed above must be singular. According to the sorting rule, "shall" must be after the agent (element). According to the keyword rule, "shall" must be present in the input text 24 as a predetermined keyword.
[0025] The processor 12 is further configured to output an indication 74 of the identified presence or absence of each of the plurality of required elements 60 in the product requirement 26. The processor 12 is further configured to output a score 76 along with the indication 74. The presence or absence of each of the plurality of required elements 60 is indicated by the score 76. In one example, a higher score may indicate the presence of each of the plurality of required elements 60, and a lower score may indicate the absence of each of the plurality of required elements 60. The score 76 may be a numerical value such as 1, 2, 3, 4, and 5, or a grade such as A, B, C, and D. In one example, the score may be a numerical value indicating a level of ambiguity as to whether the required element exists. In another example, the score may be a classification confidence value used to classify the presence (or absence) of the required element. Figure 1 As shown in the depicted example, the processor outputs feedback on the GUI 36, which includes an indication 74 of the identified presence or absence of each of the plurality of required elements 60 in the product requirement 26 and a score 76. For example, the feedback indicates that element 5 (e.g., a conditional element) requires a definition, such as "in an operating state as specified in Section XX," while the original input text only states "in an operating state." If the original text does not include "shall," which is one of the required predetermined keywords, the feedback may indicate that "shall" is missing. Additionally, if the original text does not place "shall" after the proxy element, the feedback may indicate that "shall" is not in the correct order. Additionally, in the depicted example, the score is shown as "1" out of 0-5, which indicates the absence of one or more of the required elements 60.
[0026] Temporary turn Figure 5 , which shows a schematic diagram of an example GUI 36 including an identified requirement type 50, an indication 74 of the presence or absence of each of the required elements 60 in the product requirement 26, and a score 76 for the input text 24. It will be appreciated that the presence or absence may take other forms, such as an icon, a code, an element in a computer data file, an audio indicator, etc.
[0027] Steering Figure 6 , which shows a schematic diagram of an example GUI 36 of output indications 74 including a report 81 having a chart 82 indicating the identified presence or absence of each of the plurality of required elements 60 in the product requirements 26 and non-compliance with one or more predefined element identification rules 64. This presentation of information enables a human operator to have a general understanding of the status of a set of product requirements. As depicted in this example, the first chart 82A of the report 81 for element 1 indicates that 1100 (44%) entries in the product requirement dataset have the presence of each of the plurality of required elements 60 and 1400 (800+600) entries have the absence of each of the plurality of required elements 60 in the input text 24 for the product requirement 26, wherein 800 of the 2500 entries (32%) do not comply with one of the predefined element identification rules 64 (e.g., the ordering rule, the singularity rule, and the keyword rule) and 600 of the 2500 entries (24%) do not comply with another of the predefined element identification rules 64. Similar charts 82 are shown for elements 2 and 5, which will not be described in detail.
[0028] Figure 7 is a flow chart of a computerized method 300 for evaluating product demand according to an example configuration of the present disclosure. The method 300 may be implemented using the computer hardware and software described above or using other suitable computer hardware and software.
[0029] At step 302, method 300 may include storing input text of product requirements. From step 302, method 300 may proceed to step 304, where method 300 may include identifying a requirement type for the input text from a plurality of candidate requirement types.
[0030] Proceeding from step 304 to step 306 , method 300 may include determining a plurality of required elements for the identified requirement type from a plurality of candidate elements using predefined requirement criteria.
[0031] From step 306 , method 300 may proceed to step 308 , where the method 300 may include performing natural language processing on the input text using a natural language processing model, thereby applying one or more tags from a predefined tag set to corresponding portions of the input text to generate labeled input text.
[0032] Continuing from step 308 to step 310 , method 300 may include applying one or more predefined element identification rules to the tagged input text to identify the presence or absence of each of the plurality of required elements in the input text for the product requirement.
[0033] At step 312 , the method 300 may further include outputting an indication of the identified presence or absence in the product requirements for each required element of the plurality of required elements.
[0034] The computing system 100 and method 300 described herein provide a mechanism for evaluating product requirements and identifying missing information. The computing system 100 and method 300 provide an automated process for checking each requirement for missing information and generating a report. This allows the requirement author to revise the requirement before manual review, which not only brings the requirement into compliance with quality standards, but also saves time by eliminating the need for manual review during the review.
[0035] Figure 8 A non-limiting embodiment of a computing system 200 is schematically shown, which can implement one or more of the above methods and processes. The computing system 200 is shown in simplified form. The computing system 200 can embody the above description and Figure 1 Components of computing system 200 are included, for example, in one or more personal computers, server computers, tablet computers, home entertainment computers, network computing devices, video game devices, mobile computing devices, mobile communication devices (e.g., smartphones), and / or other computing devices and wearable computing devices (such as smart watches and head-mounted augmented reality devices).
[0036] The computing system 200 includes a logic processor 202, a volatile memory 204, and a non-volatile storage device 206. The computing system 200 may optionally include a display subsystem 208, an input subsystem 210, a communication subsystem 212, and / or Figure 8 Other components not shown.
[0037] Logical processor 202 includes one or more physical devices configured to execute instructions. For example, logical processor 202 is configured to execute instructions that are part of one or more applications, programs, routines, libraries, objects, components, data structures, or other logical constructs. These instructions are implemented to perform tasks, implement data types, transform the state of one or more components, achieve technical effects, or otherwise achieve desired results.
[0038] The logical processor 202 includes one or more physical processors configured to execute software instructions. Additionally or alternatively, in some examples, the logical processor 202 includes one or more hardware logic circuits or firmware devices configured to execute hardware-implemented logic or firmware instructions. The processor of the logical processor 202 is a single core or multi-core, and the instructions executed thereon are configured for sequential, parallel and / or distributed processing. The individual components of the logical processor 202 are optionally distributed between two or more independent devices, which in some examples are located at a remote location and / or configured for coordinated processing. In some examples, certain aspects of the logical processor 202 are virtualized and executed by a remotely accessible networked computing device configured in a cloud computing configuration. In this case, these virtualized aspects run on different physical logical processors of various different machines.
[0039] The non-volatile storage device 206 includes one or more physical devices configured to hold instructions executable by a logical processor to implement the methods and processes described herein. When implementing these methods and processes, the state of the non-volatile storage device 206 is transformed, for example, to hold different data.
[0040] The non-volatile storage device 206 includes removable and / or built-in physical devices. The non-volatile storage device 206 may include optical storage, semiconductor storage and / or magnetic storage or other mass storage device technology. The non-volatile storage device 206 may include non-volatile, dynamic, static, read / write, read-only, sequential access, location addressable, file addressable and / or content addressable devices. It is understood that the non-volatile storage device 206 is configured to retain instructions even when the power to the non-volatile storage device 206 is cut off.
[0041] Volatile memory 204 includes physical devices that include random access memory. Volatile memory 204 is typically used by logical processor 202 to temporarily store information during processing of software instructions. It will be appreciated that when power to volatile memory 204 is removed, volatile memory 204 typically does not continue to store instructions.
[0042] In some examples, various aspects of logic processor 202, volatile memory 204, and non-volatile storage device 206 are integrated together in one or more hardware logic components. For example, examples of such hardware logic components include field programmable gate arrays (FPGAs), program and application specific integrated circuits (PASIC / ASIC), program and application specific standard products (PSSP / ASSP), systems on chips (SOCs), and complex programmable logic devices (CPLDs).
[0043] The terms "module", "program", and "engine" are used to describe an aspect of the computing system 200, which is typically implemented in software by a processor to perform a specific function using some portions of volatile memory, which involves a transformation process that specifically configures the processor to perform the function. Therefore, a module, program, or engine can be instantiated by executing instructions maintained by the non-volatile storage device 206 via the logical processor 202 using some portions of the volatile memory 204. It will be understood that different modules, programs, and / or engines can be instantiated by the same application, service, code block, object, library, routine, API, function, etc. Similarly, the same module, program, and / or engine can be instantiated by different applications, services, code blocks, objects, routines, APIs, functions, etc. The terms "module", "program", and "engine" can cover individual or grouped executable files, data files, libraries, drivers, scripts, database records, etc.
[0044] In some examples, the display subsystem 208 is used to present a visual representation of the data held by the non-volatile storage device 206. For example, the visual representation takes the form of a graphical user interface (GUI). In such an example, when the methods and processes described herein change the data held by the non-volatile storage device and thus transform the state of the non-volatile storage device, the state of the display subsystem 208 will also be transformed to visually represent the changes in the underlying data. The display subsystem 208 includes one or more display devices using almost any type of display technology. In some examples, such display devices are combined with the logical processor 202, the volatile memory 204 and / or the non-volatile storage device 206 in a shared housing. In other examples, such display devices are peripheral display devices.
[0045] When included, input subsystem 210 includes or interfaces to one or more user input devices, such as a keyboard, mouse, touch screen, camera, or microphone.
[0046] When included, the communication subsystem 212 is configured to communicatively couple the various computing devices described herein to each other and to other devices. For example, the communication subsystem 212 includes one or more wired and / or wireless communication devices compatible with one or more different communication protocols. As non-limiting examples, the communication subsystem is configured to communicate via a wired or wireless local or wide area network, a broadband cellular network, or the like. In some embodiments, the communication subsystem allows the computing system 200 to send information to and / or receive information from other devices via a network (such as the Internet).
[0047] Furthermore, the present disclosure includes configurations according to the following clauses.
[0048] Item 1. A computing system for evaluating product requirements, comprising: a processor coupled to a memory storing instructions, which when executed by the processor causes the processor to: store input text of the product requirements; identify a requirement type for the input text from a plurality of candidate requirement types; determine a plurality of required elements for the identified requirement type from a plurality of candidate elements using predefined requirement criteria; perform natural language processing on the input text using a natural language processing model, thereby applying one or more tags from a predefined tag set to corresponding portions of the input text to generate labeled input text; apply one or more predefined element identification rules to the labeled input text, thereby identifying the presence or absence of each of the plurality of required elements in the input text for the product requirements; and output an indication of the identified presence or absence of each of the plurality of required elements in the product requirements.
[0049] Clause 2. The computing system of clause 1, wherein the product requirement is a product requirement for a target aerospace component, and wherein the product requirement is selected from the group consisting of a government rule, a regulation, and a contract requirement.
[0050] Clause 3. The computing system of any of clauses 1-2, wherein the presence or absence of each required element of the plurality of required elements is indicated by a score.
[0051] Clause 4. A computing system according to any one of clauses 1-3, wherein the requirement type is identified using a requirement type classifier, the requirement type classifier having been trained using a training data set comprising the input text from historical product requirements and ground truth data indicating the requirement type for each input text.
[0052] Clause 5. The computing system of any one of clauses 1-4, wherein the natural language processing further comprises keyword replacement and / or keyword identification.
[0053] Clause 6. The computing system of clause 5, wherein the keyword identification identifies whether the input text contains a predetermined keyword.
[0054] Clause 7. A computing system according to any of clauses 1-5, wherein the output indication includes a report having a chart indicating the identified presence or absence of each of the plurality of required elements in the product requirements and non-compliance with the one or more predefined element identification rules.
[0055] Clause 8. The computing system of any of clauses 1-7, wherein the plurality of candidate requirement types are selected from the group consisting of functional requirements, design requirements, environmental requirements, and serviceability requirements.
[0056] Clause 9. The computing system of any of clauses 1-8, wherein the plurality of required elements are selected from the group consisting of agent elements, functional elements, output elements, performance elements, timing elements, and conditional elements.
[0057] Clause 10. The computing system of any of Clauses 1-9, wherein the one or more predefined element identification rules include one or more of an ordering rule, a singularity rule, and / or a keyword rule.
[0058] Clause 11. A computerized method for evaluating product requirements, comprising: storing input text of the product requirements; identifying a requirement type for the input text from a plurality of candidate requirement types; determining a plurality of required elements for the identified requirement type from a plurality of candidate elements using predefined requirement criteria; performing natural language processing on the input text using a natural language processing model, thereby applying one or more tags from a predefined tag set to corresponding portions of the input text to generate labeled input text; applying one or more predefined element identification rules to the labeled input text, thereby identifying the presence or absence of each of the plurality of required elements in the input text for the product requirements; and outputting an indication of the identified presence or absence of each of the plurality of required elements in the product requirements.
[0059] Clause 12. The computerized method of clause 11, wherein the product requirement is a product requirement for a target aerospace component, and wherein the product requirement is selected from the group consisting of a government rule, a regulation, and a contract requirement.
[0060] Clause 13. The computerized method of any one of clauses 11-12, wherein the presence or absence of each required element of the plurality of required elements is indicated by a score.
[0061] Clause 14. A computerized method according to any one of clauses 11-13, wherein the requirement type is identified using a requirement type classifier, the requirement type classifier having been trained using a training data set comprising the input text from historical product requirements and ground truth data indicating the requirement type for each input text.
[0062] Clause 15. The computerized method of any one of clauses 11-14, wherein the natural language processing further comprises keyword replacement and / or keyword identification.
[0063] Clause 16. The computerized method of Clause 15, wherein the keyword identification identifies whether the input text contains predetermined keywords.
[0064] Clause 17. A computerized method according to any one of clauses 11-16, wherein the output indication includes a report having a chart indicating the identified presence or absence of each of the plurality of required elements in the product requirements and non-compliance with the one or more predefined element identification rules.
[0065] Clause 18. The computerized method of any of Clauses 11-17, wherein the plurality of candidate requirement types are selected from the group consisting of functional requirements, design requirements, environmental requirements, and serviceability requirements.
[0066] Clause 19. The computerized method of any one of clauses 11-18, wherein the plurality of required elements are selected from the group consisting of agent elements, functional elements, output elements, performance elements, timing elements, and conditional elements.
[0067] Clause 20. The computerized method of any one of Clauses 11-19, wherein the one or more predefined element identification rules include one or more of an ordering rule, a singularity rule, and / or a keyword rule.
[0068] Parts List:
[0069] Processor 12
[0070] Memory 14
[0071] Input devices 16
[0072] Output Devices 18
[0073] Storage device 20
[0074] Dataset 22
[0075] Input text 24
[0076] Product Requirement 26
[0077] GUI 36
[0078] Requirement Type Classifier 40
[0079] Predefined Requirements Criteria48
[0080] Requirement Type 50
[0081] Natural Language Processing Module 52
[0082] Predefined tag sets 54
[0083] Tag 56
[0084] Input text with label 58
[0085] Required elements 60
[0086] Element recognition module 62
[0087] Predefined element identification rules 64 instructions 74
[0088] Rating 76
[0089] Report 81
[0090] Chart 82
[0091] First Chart 82A
[0092] Computing system 100
[0093] Computing system 200
[0094] Logical processor 202
[0095] Volatile memory 204
[0096] Non-volatile storage device 206
[0097] Display subsystem 208
[0098] Input subsystem 210
[0099] Communication subsystem 212
[0100] Method 300
Claims
1. A computing system (100, 200) for evaluating product demand (26), comprising: A processor (12) coupled to a memory (14) storing instructions which, when executed by the processor (12), cause the processor (12) to: storing input text (24) of said product requirement (26); identifying a requirement type (50) for the input text (24) from a plurality of candidate requirement types; determining a plurality of required elements (60) for the identified requirement type (50) from a plurality of candidate elements using predefined requirement criteria (48); performing natural language processing on the input text (24) using a natural language processing model, thereby applying one or more tags (56) from a predefined tag set (54) to corresponding portions of the input text (24) to generate labeled input text (58); applying one or more predefined element identification rules (64) to the tagged input text (58) to identify the presence or absence of each of the plurality of required elements (60) in the input text (24) for the product requirement (26); and An indication (74) of the identified presence or absence of each required element in the plurality of required elements (60) in the product requirement (26) is output.
2. The computing system (100, 200) of claim 1, wherein: The product requirement (26) is a product requirement (26) for a target aerospace component, and The product requirement (26) is selected from the group consisting of government rules, regulations and contract requirements.
3. The computing system (100, 200) of claim 1, wherein the presence or absence of each required element in the plurality of required elements (60) is indicated by a score (76).
4. A computing system (100, 200) according to claim 1, wherein a requirement type classifier (40) is used to identify the requirement type (50), and the requirement type classifier (40) has been trained using a training data set, and the training data set includes the input text (24) from historical product requirements and ground truth data indicating the requirement type (50) for each input text (24).
5. The computing system (100, 200) of claim 1, wherein the natural language processing further comprises keyword replacement and / or keyword identification.
6. The computing system (100, 200) of claim 5, wherein the keyword recognition recognizes whether the input text (24) contains a predetermined keyword.
7. A computing system (100, 200) according to claim 1, wherein the output indication includes a report (81) having a chart (82), wherein the chart (82) indicates the identified presence or absence of each required element in the plurality of required elements (60) in the product requirements (26) and the non-compliance of the one or more predefined element identification rules (64).
8. The computing system (100, 200) of claim 1, wherein the plurality of candidate requirement types (50) are selected from the group consisting of functional requirements, design requirements, environmental requirements, and applicability requirements.
9. The computing system (100, 200) of claim 1, wherein the plurality of required elements (60) are selected from the group consisting of agent elements, functional elements, output elements, performance elements, timing elements, and conditional elements.
10. The computing system (100, 200) of claim 1, wherein the one or more predefined element identification rules (64) include one or more of an ordering rule, a singularity rule, and / or a keyword rule.
11. A computerized method (300) for evaluating product demand (26), comprising: storing (302) input text (24) of the product requirement (26); identifying (304) a requirement type (50) for the input text (24) from a plurality of candidate requirement types; determining (306) a plurality of required elements (60) for the identified requirement type (50) from a plurality of candidate elements using predefined requirement criteria (48); performing (308) natural language processing on the input text (24) using a natural language processing model to apply one or more tags (56) from a predefined tag set (54) to corresponding portions of the input text (24) to generate labeled input text (58); applying (310) one or more predefined element identification rules (64) to the tagged input text (58) to identify the presence or absence of each of the plurality of required elements (60) in the input text (24) for the product requirement (26); and An indication (74) of the identified presence or absence in the product requirement (26) of each required element in the plurality of required elements (60) is output (312).
12. The computerized method (300) of claim 11, wherein: The product requirement (26) is a product requirement (26) for a target aerospace component, and The product requirement (26) is selected from the group consisting of government rules, regulations and contract requirements.
13. The computerized method (300) of claim 11, wherein the presence or absence of each desired element in the plurality of desired elements (60) is indicated by a score (76).
14. A computerized method (300) according to claim 11, wherein the requirement type (50) is identified using a requirement type classifier (40), the requirement type classifier (40) having been trained using a training data set, the training data set comprising the input text (24) from historical product requirements and ground truth data indicating the requirement type (50) for each input text (24).
15. The computerized method (300) of claim 11, wherein the natural language processing further comprises keyword replacement and / or keyword identification.
16. The computerized method (300) of claim 15, wherein the keyword identification identifies whether the input text (24) contains predetermined keywords.
17. A computerized method (300) according to claim 11, wherein the output indication includes a report (81) having a chart (82), wherein the chart (82) indicates the identified presence or absence of each of the plurality of required elements (60) in the product requirements (26) and the non-compliance of the one or more predefined element identification rules (64).
18. The computerized method (300) of claim 11, wherein the plurality of candidate requirement types (50) are selected from the group consisting of functional requirements, design requirements, environmental requirements, and serviceability requirements.
19. The computerized method (300) of claim 11, wherein the plurality of required elements (60) are selected from the group consisting of agent elements, functional elements, output elements, performance elements, timing elements, and conditional elements.
20. The computerized method (300) of claim 11, wherein the one or more predefined element identification rules (64) include one or more of an ordering rule, a singularity rule, and / or a keyword rule.