Flawed knowledge circulation system

Abstract

To provide a method and a system capable of intelligently circulating defect knowledge and performing defect summarization on the basis of the circulated defect knowledge.SOLUTION: A method for performing defect summarization, the method comprising: receiving, by a processor, defect records associated with an operation; receiving, by the processor, work information associated with the operation; linking, by the processor, the defect records and the work information using a first artificial intelligence (AI) model to generate linked information; and performing, by the processor, summary generation using a second AI model to generate work summary using summarization keywords, the defect records, and the work information, as input to the second AI model.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure generally relates to methods and systems for performing defect summarization. [Background technology]

[0002] Factory workers regularly perform inspections during the manufacturing process, including assembly and final inspection before shipping. During these inspections, workers often find defects that need to be corrected. It is important to find defects at each manufacturing stage before shipping. It is also essential to avoid the same defects in subsequent manufacturing processes.

[0003] It is essential that the inspection results be reflected in subsequent work instructions for manufacturing and inspection tasks. Inspection results usually include several notes that explain the defects found. Although they are an important source of knowledge for process improvement to avoid future defects, these notes may be easily discarded because organizing the notes and reviewing the results is a significant burden for workers. Existing systems, such as MES (Manufacturing Execution Systems), can help workers automate and record inspection results. However, more technology is needed to organize the notes and the knowledge that can be extracted from them.

[0004] In the related art, a method for performing defect detection through images is disclosed. A polygon is applied to the image for defect pattern detection and collection. The defect detection helps an operator to fix the defect, but does not help an operator to understand which process may have caused the defect. Summary of the Invention [Problem to be solved by the invention]

[0005] A need exists for a method and system that can intelligently recycle defect knowledge and perform defect summarization based on the recycle defect knowledge. [Means for solving the problem]

[0006] Aspects of the present disclosure involve an innovative method for performing defect summarization. The method may include: receiving, by a processor, defect records associated with an operation; receiving, by the processor, work information associated with the operation; linking, by the processor, the defect records and the work information using a first artificial intelligence (AI) model to generate linked information; and performing, by the processor, summary generation using the second AI model to generate a work summary using the summarization keywords, the defect records, and the work information as inputs to the second AI model.

[0007] Aspects of the present disclosure involve an innovative non-transitory computer-readable medium storing instructions for performing defect summarization. The instructions may include receiving defect records associated with an operation, receiving work information associated with the operation, linking the defect records and the work information using a first artificial intelligence (AI) model to generate linked information, and performing summary generation using the second AI model to generate a work summary using the summarization keywords, the defect records, and the work information as inputs to the second AI model.

[0008] Aspects of the present disclosure involve an innovative server system for performing defect summarization. The system may include: receiving, by a processor, defect records associated with an operation; receiving, by a processor, work information associated with the operation; linking, by the processor, the defect records and the work information using a first AI model to generate linked information; and performing, by the processor, summary generation using a second AI model to generate a work summary using the summarization keywords, the defect records, and the work information as inputs to the second AI model.

[0009] Aspects of the present disclosure involve an innovative system for performing defect summarization, which may include means for receiving defect records associated with an operation, means for receiving work information associated with the operation, means for linking the defect records and the work information using a first artificial intelligence (AI) model to generate linked information, and means for performing summary generation using a second AI model to generate a work summary using the summarization keywords, the defect records, and the work information as inputs to the second AI model.

[0010] A general architecture embodying various features of the present disclosure is described below with reference to the drawings. The drawings and related description are provided to illustrate example embodiments of the present disclosure and are not intended to limit the scope of the disclosure. Throughout the drawings, reference numbers are also used again to indicate correspondence between referenced elements. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 illustrates an exemplary defect knowledge circulation system 100, according to one exemplary embodiment. [Figure 2] FIG. 2 illustrates an exemplary process flow 200 for performing data acquisition steps, according to one exemplary implementation. [Figure 3] FIG. 3 illustrates an exemplary process flow 300 for performing link function processing steps, according to one exemplary implementation. [Figure 4] FIG. 4 illustrates an exemplary process flow 400 for performing summarization function processing steps, according to one exemplary implementation. [Figure 5] FIG. 5 illustrates an exemplary process flow 500 for performing knowledge provider processing steps, according to one exemplary implementation. [Figure 6] FIG. 2 illustrates an exemplary architecture of a link function 140a, according to one exemplary implementation. [Figure 7] FIG. 2 illustrates an exemplary architecture of a summarization function 140b, according to one exemplary implementation. [Figure 8] FIG. 8 illustrates an exemplary work instruction 800, according to one exemplary implementation. [Figure 9] FIG. 9 illustrates an exemplary defect record 900, according to one exemplary embodiment. [Figure 10] FIG. 10 illustrates an exemplary text file 1000 aggregated by data aggregator 140a-1, according to one exemplary implementation. [Figure 11] FIG. 11 illustrates an exemplary output 1100 of a link function 140a, according to one exemplary implementation. [Figure 12] FIG. 12 illustrates an example output 1200 of summarization function 140b using "customer" as a summarization keyword, according to one example implementation. [Figure 13] FIG. 1 illustrates an exemplary computing environment having an exemplary computer device suitable for use in some exemplary implementations. DETAILED DESCRIPTION OF THE INVENTION

[0012] The following detailed description provides details of the figures and exemplary embodiments of the present application. Reference numbers and descriptions of elements that are duplicated between figures are omitted for clarity. Terms used throughout the description are provided by way of example and are not intended to be limiting. For example, use of the term "automatic" can include fully automatic or semi-automatic implementations, including user or administrator control over certain aspects of the implementation, depending on the desired implementation of one skilled in the art practicing the embodiments of the present application. Selection can be performed by a user via a user interface or other input means, or can be implemented via a desired algorithm. The exemplary implementations as described herein can be used either alone or in combination, and the functionality of the exemplary implementations can be implemented via any means according to the desired implementation.

[0013] The exemplary embodiments relate to methods and systems for effectively associating / linking inspection results, particularly defect records, to work instructions and other work-related information. The exemplary embodiments summarize defect records for easy review and provide associated information and summarized defect records for work information requested by a user. In some exemplary embodiments, the work information is information related to industrial systems and related operations. Information formats include, but are not limited to, document files, images, videos, HyperText Markup Language (HTML) files, uniform resource locators (URLs) that point to data locations, etc. Target users are workers in industrial facilities / systems, such as factories, distribution centers, etc. Workers may include, but are not limited to, shop floor operators / workers, operations managers, etc.

[0014] 1 illustrates an exemplary defect knowledge circulation system 100, according to one exemplary embodiment. The defect knowledge circulation system 100 may include components such as, but not limited to, a data acquisition function 110, a knowledge provision function 120, a data store 130, and a reasoning function 140.

[0015] For the defect knowledge circulation system 100, there are two types of users: data acquisition function users 150 and knowledge contribution function users 160. The data acquisition function users 150 and knowledge contribution function users 160 may be the same person / worker if the title only represents the job function. The data acquisition function users 150 operate from a computing device 170, and the knowledge contribution function users 160 operate from a computing device 180. The computing device 170 has a result recording function 172 for recording and transmitting defect-related record data to the defect knowledge circulation system 100. The computing device 170 may be any computing device, such as, but not limited to, a mobile phone, a smart device, a tablet computer, a desktop computer, a laptop computer, a virtual / augmented reality device, an Internet of Things (IoT) device, etc.

[0016] The computing device 180 has a request acquisition and display function 182 for receiving a work information retrieval request from the knowledge provider user 160. In response to receiving the work information retrieval request, the request acquisition and display function 182 retrieves defect-related data for review by the knowledge provider user 160. The computing device 180 may be any computing device, such as, but not limited to, a mobile phone, a smart device, a tablet computer, a desktop computer, a laptop computer, a virtual / augmented reality device, an Internet of Things (IoT) device, etc.

[0017] The data store 130 may include components such as, but not limited to, a summarized keywords data store 130a, a defect-related records data store 130b, a work information data store 130c, and a summary and links data store 130d. The data store 130 may be one or more storage media, such as, but not limited to, a non-volatile memory device, a volatile memory device, a removable disk, a hard disk drive, an optical disk, etc. In some exemplary implementations, the data store 130 resides external to the defect knowledge circulation system 100.

[0018] The inference function 140 may include components such as, but not limited to, a linking function 140a, a summarization function 140b, and a triggering function 140c. The inference function 140 associates reported defect-related records with work information (e.g., work orders) to help users / operators discover potential causes of defects. The linking function 140a imports data from the data stores 130, infers links between data in the defect-related record data store 130b and data in the work information data store 130c, and stores the inference results in the summaries and links data store 130d. The inference function 140 also includes a summarization function 140b that summarizes defect-related records according to the inferred links between the defect-related record data store 130b and the work information data store 130c and stores the summarization results in the summaries and links data store 130d. The summarization keyword data store 130a stores summarization keywords used by the summarization function 140b when generating summaries, as described in detail below.

[0019] The data acquisition function 110 receives defect-related records from the computing device 170 and stores the data in the defect-related record data store 130b. The knowledge provision function 120 retrieves work information based on work information requests entered by the knowledge provision function user 160. The knowledge provision function 120 then retrieves the associated defect-related records and summaries and provides / transmits them to the computing device 180 for review by the knowledge provision function user 160.

[0020] 2 shows an example process flow 200 for performing a data capture step, according to one example embodiment. Process flow 200 begins at step S202, where a defect record is provided / entered by data capture function user 150. This defect record is provided as an inspection result using result recording function 172 of computing device 170. The defect record may include metadata such as notes about the defect, photos / video, who reported it, the time of reporting, and the process ID of the inspection task. Data capture function user 150 may be an operator at the shop floor where the inspection is performed. Defect record entry may occur at each inspection task throughout various processes in the factory.

[0021] In step S204, the defect record is sent to the defect knowledge circulation system 100. The defect record is sent / transmitted by the computing device 170 to the data acquisition function 110 of the defect knowledge circulation system 100. In step S206, the data acquisition function 110 stores the defect record in the defect-related record data store 130b in the data store 130.

[0022] 3 shows an example process flow 300 for performing link function processing steps, according to one example implementation. In step S302, trigger function 140c detects a trigger event (e.g., the addition of a defect record in defect-related record data store 130b) to initiate link function 140a. The trigger event may include, but is not limited to, the addition of a defect record in defect-related record data store 130b, a user request to initiate link function 140a, the number of recently added defect records since the last execution of link function 140a, or a time threshold since the last execution of link function 140a.

[0023] The process then continues to step S304, where linking function 140a imports defect records from defect-related records data store 130b and work information, such as work instructions, from work information data store 130c. In step S306, linking function 140a infers and generates relationships between the defect records and the work information and stores the inference results in summary and link data store 130d. Linking function 140a is described in more detail below.

[0024] 4 shows an example process flow 400 for performing summarization function processing steps, according to one example implementation. Process flow 400 begins in step S402, where trigger function 140c detects a trigger event to initiate summarization function 140b. The trigger event may include, but is not limited to, the addition of a defect record in defect-related record data store 130b, a user request to initiate summarization function 140b, the number of recently added defect records since the last execution of summarization function 140b, or a time threshold since the last execution of summarization function 140b.

[0025] The process then continues at step S404, where the summarization function 140b imports a summarization keyboard from the summarization keyword data store 130a, defect records from the defect-related records data store 130b, work information such as work instructions and customer information from the work information data store 130c, and current link data and summary records from the summary and link data store 130d. In step S406, the summarization function 140b uses the imported keywords to generate a summary of the links between the retrieved defect records and work information and stores the inference results in the summary and link data store 130d. The summarization function 140b is described in more detail below. The output of the summarization function 140b may be based on one or more imported keywords / classifications. For example, if the keywords are: "Process": A defect summary is generated for each process. "Worker Job": A summary of defects is generated for each worker job. "Machine": A defect summary is generated for each machine in the factory. "Customer": A defect summary is generated for each customer of the factory. "Product": A summary of defects is generated for each type of product.

[0026] 5 illustrates an exemplary process flow 500 for performing knowledge provider processing steps according to one exemplary implementation. In step S502, knowledge provider user 160 inputs a work information request through request acquisition and display function 182 of computing device 180. In some exemplary implementations, the work information request may be, but is not limited to, an identification number / identifier associated with the work information.

[0027] In step S504, the request acquisition and display function 182 of the computing device 180 transmits / sends the work information request to the knowledge providing function 120 of the defect knowledge circulation system 100. In step S506, the knowledge providing function 120 uses the work information request to retrieve work information.

[0028] The process then proceeds to step S508, where the knowledge providing function 120 retrieves the link data and summary records associated with the work information request. In step S510, the knowledge providing function 120 retrieves defect records from the defect-related record data store 130b according to the retrieved link data.

[0029] In step S512, the knowledge providing function 120 sends the retrieved work information, the retrieved link data, the retrieved summary record, and the retrieved defect record to the request acquisition and display function 182. Then, in step S514, the request acquisition and display function 182 displays the received data.

[0030] 6 illustrates an exemplary architecture of linking functionality 140a according to one exemplary implementation. As illustrated in FIG. 6, linking functionality 140a may include components such as, but not limited to, a data aggregator 140a-1, a data converter 140a-2, a prompt generator 140a-3, prompt snippets 140a-4, a Retrieval Augmented Generation (RAG) functionality 140a-5, and a parser 140a-6.

[0031] Data aggregator 140a-1 aggregates the imported information into a single text file, which is then converted into chunks for embedding by data converter 140a-2 if the file size exceeds a predetermined size (e.g., if the file size exceeds the context window size of RAG function 140a-5). Prompt snippets 140a-4 are defined blocks of text or code that can be utilized by prompt generator 140a-3 when generating a prompt.

[0032] RAG function 140a-5 generates a response using the prompt derived from prompt generator 140a-3 and the converted chunk derived from data converter 140a-2. RAG function 140a-5 may utilize a machine learning (ML) / artificial intelligence (AI) model, an ontology-based reasoning function, or any other formal reasoning technique. The machine learning (ML) / artificial intelligence (AI) model may be a deep learning model such as a large-scale language model (LLM). The response generated by RAG function 140a-5 is then parsed and stored by parser 140a-6.

[0033] 7 illustrates an exemplary architecture of summarization functionality 140b according to one exemplary implementation. As shown in FIG. 7, summarization functionality 140b may include components similar to those of FIG. 6, such as, but not limited to, a data aggregator 140b-1, a data converter 140b-2, a prompt generator 140b-3, prompt snippets 140b-4, a Retrieval Augmented Generation (RAG) functionality 140b-5, and a parser 140b-6.

[0034] Data aggregator 140b-1 aggregates the imported information into a single text file, which is then converted into chunks for embedding by data converter 140b-2 if the file size exceeds a predetermined size (e.g., if the file size exceeds the context window size of RAG function 140b-5). Prompt snippets 140b-4 are defined blocks of text or code that can be utilized by prompt generator 140b-3 when generating a prompt.

[0035] The RAG function 140b-5 generates responses using the prompts derived from the prompt generator 140b-3 and the converted chunks derived from the data converter 140b-2. The RAG function 140b-5 may utilize a machine learning (ML) / artificial intelligence (AI) model, an ontology-based reasoning function, or any other formal reasoning technique. The machine learning (ML) / artificial intelligence (AI) model may be a deep learning model such as a large-scale language model (LLM). In some exemplary implementations, the input and output of the LLM may include a sequence of words (e.g., using a provided prompt as input). The LLM may include a module that takes a prompt as input, generates a single token (e.g., a word, space, etc.) as part of its output, and repeats this token generation process until the end of the sequence is reached. The LLM may be trained using different types of data depending on the model architecture (e.g., a large training set of text data, etc.). This set of text data may be tokenized to train the LLM to predict the next word in a sequence of text using either an unsupervised method, a semi-supervised method, a supervised method, or a reinforcement learning method. The response generated by RAG function 140b-5 is then parsed and stored by parser 140b-6.

[0036] 8 illustrates an exemplary work instruction 800 according to one exemplary implementation. As shown in FIG. 8, work instruction 800 may include a first work instruction 802 for TrainA and TrainB, and a second work instruction 804 for TrainA. The first work instruction is associated with customer CompanyA, and the second work instruction is associated with customer CompanyB. For parsing purposes, each instruction has a beginning tag and an end tag, such as "INSTRUCTION BEGIN" and "INSTRUCTION END."

[0037] 9 illustrates an exemplary defect record 900, according to one exemplary embodiment. The defect record 900 is a defect record for TrainA, which is associated with CompanyA. As shown in FIG. 9, the defect record 900 provides information about the defect described in the note and metadata associated with the defect (e.g., reporting date, location, product ID, reporting operator, product description, etc.). For parsing purposes, each defect record has a beginning tag and an end tag, such as "DEFECT NOTE BEGIN" and "DEFECT NOTE END."

[0038] 10 illustrates an exemplary text file 1000 aggregated by data aggregator 140a-1 according to one exemplary implementation. Work instructions 800 and defect records 900 are aggregated to form a single text file for chunking by data converter 140a-2 and subsequent processing by RAG function 140a-5.

[0039] FIG. 11 shows an example output 1100 of linking function 140a according to one example implementation. Linking function 140a infers links between work information and defect records and groups the inferred links by summary keywords (e.g., “train” and “customer”). In some example implementations, additional defect records may be derived using components such as RAG functions 140a-5 and 140b-5 and used for further processing. FIG. 12 shows an example output 1200 of summarization function 140b using “customer” as a summary keyword according to one example implementation.

[0040] The exemplary implementations described above may have various benefits and advantages, such as reducing the burden of organizing defect knowledge and improving the quality and efficiency of factory operations. By intelligently linking defect records with work instructions, the system provides users with unique operational insights that can be used in performing production or system optimization.

[0041] 13 illustrates an exemplary computing environment having an exemplary computing device suitable for use in some exemplary implementations. The computing device 1305 in the computing environment 1300 can include one or more processing units, cores, or processors 1310, memory 1315 (e.g., RAM, ROM, and / or the like), internal storage 1320 (e.g., magnetic, optical, solid-state storage, and / or organic), and / or IO interface 1325, any of which can be coupled over a communication mechanism or bus 1330 for communicating information or can be incorporated into the computing device 1305. The IO interface 1325 can be further configured to receive images from a camera or provide images to a projector or display, depending on the desired implementation.

[0042] The computing device 1305 may be communicatively coupled to an input / user interface 1335 and an output device / interface 1340. Either or both of the input / user interface 1335 and the output device / interface 1340 may be a wired or wireless interface and may be detachable. The input / user interface 1335 may include any device, component, sensor, or interface, physical or virtual, that can be used to provide input (e.g., buttons, touchscreen interface, keyboard, pointing / cursor control, microphone, camera, Braille, motion sensor, accelerometer, optical reader, and / or the like). The output device / interface 1340 may include a display, television, monitor, printer, speaker, Braille, or the like. In some exemplary implementations, the input / user interface 1335 and the output device / interface 1340 may be incorporated with or physically coupled to the computing device 1305. In other implementations, other computing devices may function as or provide the functionality of input / user interface 1335 and output device / interface 1340 for computing device 1305 .

[0043] Examples of computing devices 1305 may include, but are not limited to, highly mobile devices (e.g., smartphones, devices mounted on vehicles and other machines, devices carried by people or animals, and the like), mobile devices (e.g., tablets, notebooks, laptops, personal computers, portable televisions, radios, and the like), and devices not designed for mobility (e.g., desktop computers, other computers, information kiosks, televisions with one or more processors embedded and / or televisions with one or more processors coupled thereto, radios, and the like).

[0044] Computing device 1305 may be communicatively coupled (e.g., via IO interface 1325) to external storage 1345 and a network 1350 for communication with any number of networked components, devices, and systems, including one or more computing devices of the same or different configurations. Computing device 1305 or any connected computing device may function as, provide services to, or be referred to as a server, client, thin server, general-purpose machine, special-purpose machine, or otherwise.

[0045] IO interface 1325 may include, but is not limited to, wired and / or wireless interfaces using any communication or IO protocol or convention (e.g., Ethernet, 802.11x, Universal System Bus, WiMax, modem, cellular network protocols, and the like) for communicating information to and / or from at least all connected components, devices, and networks in computing environment 1300. Network 1350 may be any network or combination of networks (e.g., the Internet, a local area network, a wide area network, a telephone network, a cellular network, a satellite network, and the like).

[0046] The computing device 1305 can use and / or communicate using computer-usable or computer-readable media, including transitory and non-transitory media. Transitory media include transmission media (e.g., metallic cables, fiber optics), signals, carrier waves, and the like. Non-transitory media include magnetic media (e.g., disks and tape), optical media (e.g., CD-ROM, digital video disks, Blu-ray® disks), solid-state media (e.g., RAM, ROM, flash memory, solid-state storage), and other non-volatile storage or memory.

[0047] The computing device 1305 can be used to implement techniques, methods, applications, processes, or computer-executable instructions in some exemplary computing environments. The computer-executable instructions can be retrieved from transitory media and stored on and retrieved from non-transitory media. The executable instructions can be from one or more of any programming, scripting, and machine language (e.g., C, C++, C#, Java, Visual Basic, Python, Perl, JavaScript, etc.).

[0048] The processor 1310 can execute under any operating system (OS) (not shown) in a native or virtual environment. One or more applications can be deployed, including a logic unit 1360, an application programming interface (API) unit 1365, an input unit 1370, an output unit 1375, and an inter-unit communication mechanism 1395 for different units to communicate with each other, with the OS, and with other applications (not shown). The above-mentioned units and elements can vary in design, function, configuration, or implementation and are not limited to the above description. The processor 1310 can have the form of a hardware processor, such as a central processing unit (CPU), or can be a combination of hardware and software units.

[0049] In some exemplary implementations, when information or instructions to perform are received by API unit 1365, it may be communicated to one or more other units (e.g., logic unit 1360, input unit 1370, output unit 1375). In some examples, logic unit 1360 may be configured to control the flow of information between units and, in some exemplary implementations described above, direct the services provided by API unit 1365, input unit 1370, and output unit 1375. For example, the flow of one or more processes or implementations may be controlled by logic unit 1360 alone or in conjunction with API unit 1365. Input unit 1370 may be configured to obtain inputs for the calculations described in the exemplary implementations, and output unit 1375 may be configured to provide outputs based on the calculations described in the exemplary implementations.

[0050] The processor 1310 may be configured to receive defect records associated with the operation, receive work information associated with the operation, link the defect records and the work information using a first artificial intelligence (AI) model to generate linked information, and perform summary generation using a second AI model to generate a work summary using the summarization keywords, the defect records, and the work information as inputs to the second AI model, as shown in Figures 1-5. The processor 1310 may also be configured to receive a work information retrieval request from a user to retrieve work information from a database, and use the linked information to retrieve and display the defect records, work information, and work summary to the user, as shown in Figures 1-5.

[0051] Some portions of the detailed description are presented in terms of algorithms and symbolic representations of operations within a computer. These algorithmic descriptions and symbolic representations are the means used by those skilled in the data processing arts to convey the substance of their innovations to others skilled in the art. An algorithm is a series of defined steps leading to a desired end state or result. In exemplary implementations, the performed steps require physical manipulations of tangible quantities to achieve a tangible result.

[0052] Unless otherwise specified, and as will be apparent from the description, throughout this specification, descriptions utilizing words such as "processing," "calculating," "computing," "determining," "displaying," or the like, are understood to include the actions and processes of a computer system or other information processing device that manipulates and converts data represented as physical (electronic) quantities in the registers and memory of the computer system into other data similarly represented as physical quantities in the memory or registers of the computer system or other information storage, transmission, or display devices.

[0053] Exemplary embodiments may further relate to apparatuses for performing the operations herein. This apparatus may be specially constructed for the desired purposes, or may include one or more general-purpose computers selectively activated or reconfigured by one or more computer programs. Such computer programs may be stored on a computer-readable medium, such as a computer-readable storage medium or a computer-readable signal medium. Computer-readable storage media may include tangible media, such as, but not limited to, optical disks, magnetic disks, read-only memory, random-access memory, solid-state devices and drives, or any other type of tangible or non-transitory medium suitable for storing electronic information. Computer-readable signal media may include media such as carrier waves. The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. A computer program may include a pure software implementation containing instructions for performing the operations of a desired embodiment.

[0054] Various general-purpose systems may be used with the programs and modules according to the examples herein, or it may eventually be convenient to construct more specialized apparatus to perform the desired method steps. Moreover, the example embodiments are not described with reference to any particular programming language. It will be understood that a variety of programming languages ​​may be used to implement the teachings of the example embodiments as described herein. Instructions in the programming language may be executed by one or more processing devices, such as, for example, a central processing unit (CPU), processor, or controller.

[0055] As is known in the art, the operations described above may be performed by hardware, software, or some combination of software and hardware. Various aspects of the exemplary embodiments may be implemented using circuits and logic devices (hardware), while other aspects may be implemented using instructions stored on a machine-readable medium (software) that, when executed by a processor, cause the processor to perform methods that implement the present application. Furthermore, some exemplary embodiments of the present application may be implemented solely in hardware, while other exemplary embodiments may be implemented solely in software. Furthermore, the various functions described may be performed in a single unit or distributed across multiple components in any number of ways. When implemented by software, the methods may be executed by a processor, such as a general-purpose computer, based on instructions stored on a computer-readable medium. If desired, the instructions may be stored on the medium in compressed and / or encrypted format.

[0056] Additionally, other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the teachings herein. Various aspects and / or components of the described exemplary embodiments may be used singly or in any combination. It is intended that the specification and exemplary embodiments be considered exemplary only, with the true scope and spirit of the present application being indicated by the following claims. [Explanation of symbols]

[0057] 100 Flawed Knowledge Circulation System 140 Inference Function 140a Link Function 140b Summarization function 140c trigger function 130 Datastores 130a Summarized Keyword Data Store 130b Defect-related records data store 130c Work Information Data Store 130d Summary and Linked Data Store 110 Data Acquisition Function 120 Knowledge provision function 170 Computing Devices 172 Result recording function 182 Request Retrieval and Display Function 150 Data Acquisition Function Users 160 Knowledge Contribution Function Users 1305 Computer Devices 1310 processor 1315 memory 1320 Internal Storage 1325 IO interface 1335 Input / User Interface 1340 Output Device / Interface 1345 External Storage 1350 Network 1360 logical units 1365 API units 1370 Input Unit 1375 output unit

Claims

1. 1. A method for performing defect summarization, the method comprising: receiving, by a processor, a defect record associated with the operation; receiving, by the processor, task information associated with the operation; linking, by the processor, the defect records and the work information using a first artificial intelligence (AI) model to generate linked information; and performing, by the processor, summary generation using a second AI model to generate a job summary using summarization keywords, the defect records, and the job information as inputs to the second AI model.

2. 2. The method of claim 1, wherein the first AI model and the second AI model are large language models (LLMs).

3. receiving, by the processor, a task information retrieval request from a user to retrieve the task information from a database; 10. The method of claim 1, further comprising: retrieving, by the processor, the defect record, the work information, and the work summary using the linked information to retrieve and display to the user.

4. 2. The method of claim 1, wherein using the first AI model to link the defect record and the work information is triggered by receipt of the defect record.

5. the processor:

2. The method of claim 1 , further comprising: configuring to link the defect record and the work information using the first AI model to generate the linked information by using the first AI model to infer and generate a relationship between the defect record and the work information, the relationship being the linked information.

6. The method of claim 5 , wherein the job summary includes a summary of the relationships between the defect records and the job information grouped by the summarization keywords.

7. The method of claim 6 , wherein the summaries of the relationships include one or more of a process defect summary, a job defect summary, a machine defect summary, a customer defect summary, or a product defect summary.

8. The method of claim 1 , wherein the work information includes work instructions and process information associated with the operation.

9. 1. A system for performing defect summarization, the system comprising: Data storage; a processor in communication with the data storage, the processor comprising: receiving a defect record associated with the operation and storing the defect record in the data storage; receiving task information associated with the operation and storing the task information in the data storage; linking the defect records and the work information using a first artificial intelligence (AI) model to generate linked information and store the linked information in the data storage; and performing summary generation using a second AI model, wherein the second AI model generates a work summary using summarization keywords, the defect records, and the work information as inputs to the second AI model, and records the work summary in the data storage.

10. 10. The system of claim 9, wherein the first AI model and the second AI model are large language models (LLMs).

11. the processor: receiving a task information retrieval request from a user to retrieve the task information from a database; 10. The system of claim 9, further configured to use the linked information to retrieve and display to the user the defect record, the work information, and the work summary.

12. 10. The system of claim 9, wherein linking the defect record and the work information using the first AI model is triggered by receipt of the defect record.

13. the processor:

10. The system of claim 9, wherein the system is configured to link the defect record and the work information using the first AI model to generate the linked information by using the first AI model to infer and generate a relationship between the defect record and the work information, the relationship being the linked information.

14. The system of claim 13 , wherein the job summary includes a summary of the relationships between the defect records and the job information grouped by the summarization keywords.

15. The system of claim 14 , wherein the summaries of the relationships include one or more of a process defect summary, a job defect summary, a machine defect summary, a customer defect summary, or a product defect summary.

16. The system of claim 9 , wherein the work information includes work instructions and process information associated with the operation.

Images