Method and system for selecting manufacturing process control points

Abstract

The application provides a manufacturing process control point selection method suitable for a reactor, and the method comprises the following steps: obtaining control point original data, and converting the control point original data into control point structured data; confirming control point standardized information based on the control point structured data, wherein the control point standardized information comprises a standard control point type corresponding to the control point structured data; confirming control point historical information based on the control point structured data, wherein the control point historical information comprises a historical control point type corresponding to the control point structured data; and confirming a control point selection decision based on the standard control point type and the historical control point type. The manufacturing process control point selection method and system provided by the application can intelligently select and set the control points of the manufacturing process, and further improve the effectiveness of reactor quality supervision and manufacture.

Description

Technical Field

[0001] This application relates primarily to the field of reactor technology, and in particular to a method and system for selecting control points in a manufacturing process. Background Technology

[0002] In nuclear power plant construction, the quality of nuclear-grade equipment directly affects the safe and stable operation of the reactor. The Quality Planning (QCP) is a core quality control document in the equipment manufacturing process, its core content being the establishment of reasonable control points for each manufacturing process. Whether the control points are set scientifically, reasonably, and comprehensively directly determines the effectiveness of quality supervision and the accuracy of resource allocation. Currently, control point work mainly relies on the supervision engineer's understanding of domestic and international standards and regulations, such as the American Society of Mechanical Engineers (ASME) and the National Standards of the People's Republic of China (GB), as well as management procedures. Due to the vast and frequently updated standard system, different engineers have different understandings of the same process, leading to room for optimization in the setting of control points for similar equipment in different projects, and even in different packages within the same project. Furthermore, the current method of setting control points mostly involves manual database queries, which is time-consuming, labor-intensive, and prone to errors, reducing the efficiency of control point management. Summary of the Invention

[0003] The technical problem to be solved by this application is to provide a system for selecting and setting control points in manufacturing processes, which can intelligently select and set control points in manufacturing processes, thereby improving the effectiveness of reactor quality supervision.

[0004] To address the aforementioned technical problems, this application provides a method for selecting control points in a manufacturing process, applicable to reactors. The method includes the following steps: acquiring raw control point data and converting the raw control point data into structured control point data; based on the structured control point data, confirming standardized control point information, wherein the standardized control point information includes a standard control point type corresponding to the structured control point data; based on the structured control point data, confirming historical control point information, wherein the historical control point information includes a historical control point type corresponding to the structured control point data; and confirming a control point selection decision based on the standard control point type and the historical control point type.

[0005] Optionally, obtaining the raw control point data and converting it into structured control point data includes: extracting control point statements from the raw control point data; obtaining standard control point terms based on the control point statements; and obtaining the structured control point data based on the standard control point terms.

[0006] Optionally, confirming the standardized information of the control points based on the structured control point data includes the following steps: performing feature vectorization on the structured control point data to obtain control point semantic vectors; calculating the similarity of the structured control point data based on the control point semantic vectors; and confirming the standardized information of the control points based on the similarity.

[0007] Optionally, this includes calculating the similarity of the structured data of the control points using the following formula: S=w1 S_{edit}+w2 S_{seq}+w3 S_{jaccard}+w4 S_{semantic}, where S is the similarity, S_{edit} is the edit distance similarity, S_{seq} is the sequence matching similarity, S_{jaccard} is the set overlap similarity, S_{semantic} is the deep semantic similarity, w1 is the weight corresponding to the edit distance similarity, w2 is the weight corresponding to the sequence matching similarity, w3 is the weight corresponding to the set overlap similarity, and w4 is the weight corresponding to the deep semantic similarity. Optionally, the step of confirming the historical information of the control points based on the structured control point data, wherein the historical control point information includes the historical control point type corresponding to the structured control point data, includes: determining whether the standard control point type has a mandatory description; if the determination is negative, then obtaining historical biased control points and historical abnormal control points based on the historical control point information; confirming the weight of the historical biased control points based on the historical biased control points; confirming the weight of the historical abnormal control points based on the historical abnormal control points; and confirming the historical control point type based on the weight of the historical biased control points and the weight of the historical abnormal control points.

[0008] Optionally, confirming the control point selection decision based on the standard control point type and the historical control point type includes: determining abnormal control point risk cases based on the historical abnormal control points, and generating an abnormal control point traceability card based on the abnormal control point risk cases; if the standard control point type is the same as the historical control point type, generating a control point recommendation traceability card based on the standard control point type and the historical control point type; and determining the control point selection decision based on the abnormal control point traceability card and the control point recommendation traceability card.

[0009] Optionally, both the standard control point type and the historical control point type include one of the following: stop-work inspection point, witness point, document review point, and point not requiring supervision, or any combination thereof.

[0010] To address the aforementioned technical problems, this application provides a manufacturing process control point selection system, applied to the manufacturing process control point selection method described above, comprising: a data and processing module configured to acquire raw control point data and convert the raw control point data into structured control point data; an intelligent matching engine module configured to confirm standardized control point information based on the structured control point data, wherein the standardized control point information includes a standard control point type corresponding to the structured control point data; a historical data analysis module configured to confirm historical control point information based on the structured control point data, wherein the historical control point information includes a historical control point type corresponding to the structured control point data; and a decision fusion center module configured to confirm a control point selection decision based on the standard control point type and the historical control point type.

[0011] To address the aforementioned technical problems, this application provides a manufacturing process control point selection system, characterized in that it further includes: a memory for storing instructions executable by a processor; and a processor for executing the instructions to implement the method described above.

[0012] To address the aforementioned technical problems, this application provides a computer-readable medium storing computer program code, which, when executed by a processor, implements the method described above.

[0013] Compared with existing technologies, this application confirms standardized control point information and historical control point information based on structured control point data, and then obtains the final control point selection decision based on the standardized control point information and historical control point information. This enables automated and intelligent selection of control points in the manufacturing process. Furthermore, by integrating and combining standardized control point information and historical control point information, the accuracy and reliability of control point selection can be further guaranteed, thereby further improving the effectiveness of reactor quality supervision. Attached Figure Description

[0014] The accompanying drawings are included to provide a further understanding of this application; they are incorporated into and constitute a part of this application. The drawings illustrate embodiments of this application and, together with this specification, serve to explain the principles of this application. In the drawings: Figures 1-3 This is a schematic flowchart of a method for selecting control points in a manufacturing process according to an embodiment of this application; Figure 4 This is a schematic diagram of the module structure of a manufacturing process control point selection system according to an embodiment of this application; Figure 5 This is a schematic diagram of a manufacturing process control point selection system according to an embodiment of this application. Detailed Implementation

[0015] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this application. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0016] As indicated in this application and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" are not specifically singular and may include plural forms. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0017] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of this application. It should also be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale. Techniques, methods, and devices known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters in the following drawings denote similar items; therefore, once an item is defined in one drawing, it need not be further discussed in subsequent drawings.

[0018] This application refers to Figure 1 A manufacturing process control point selection method 10 (hereinafter referred to as "control point method 10") is proposed, which can intelligently select and set control points for manufacturing processes, further improving the effectiveness of reactor quality supervision. Flowcharts are used in this application to illustrate the operations performed by the system according to embodiments of this application. It should be understood that preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously. At the same time, other operations may be added to these processes, or one or more steps may be removed from these processes.

[0019] Specifically, refer to Figure 1The control point selection method 10 mainly includes steps S1-S4. Step S1 may include acquiring raw control point data and converting it into structured control point data. Step S2 may include confirming standardized control point information based on the structured control point data. Standardized control point information includes the standard control point type corresponding to the structured control point data. For example, standardized control point information can be obtained from a standard database, which mainly includes domestic and international standards and regulations, such as ASME and GB, for manufacturing processes. Step S3 may include confirming historical control point information based on the structured control point data. Historical control point information includes the historical control point type corresponding to the structured control point data. Historical control point information can be obtained from a historical database, which stores relevant information for all control point types corresponding to the manufacturing process. Step S4 may include confirming the control point selection decision based on the standard control point type and the historical control point type. By integrating standardized information from comprehensive control points with historical information from control points, a dual-driven mechanism is employed, combining standard specifications from the standard database with historical control point information from the historical database. This ensures both regulatory compliance (bottom-line thinking) and incorporates best engineering practices (optimization thinking). It effectively avoids the rigidity caused by relying solely on standards or the arbitrariness caused by relying solely on experience, further guaranteeing the accuracy and reliability of control points and thus improving the effectiveness of reactor quality supervision. In some embodiments, control point types may include one or any combination of shutdown inspection points (H points), witness points (W points), document review points (R points), and points not requiring supervision (N / A points).

[0020] The following details steps S1-S4. First, in step S1, raw control point data is acquired and converted into structured control point data. This is primarily achieved by extracting control point statements from the raw data. Standard control point terminology is then obtained based on these statements, and the structured control point data is derived from this standard terminology. Specifically, the raw control point data can be imported quality plans from historical procurement processes, including documents in formats such as Word and PDF. These documents contain technical standards and specifications (RCC-M / ASME / GB), management procedures, and manufacturing process libraries used in actual manufacturing scenarios. Next, deep learning-based document layout analysis technology can be used to accurately identify tables, hierarchical headings, and process descriptions within the document, extracting control point statements related to control points, such as "equipment code," "process name," "process parameters," and "control point type." After obtaining the control point statements, terminology normalization can be performed to extract standard control point terminology. Furthermore, steps such as entity extraction, attribute value matching, ambiguity resolution, and format output can be performed on the standard control point terminology to transform it into machine-readable structured control point data. For example, synonym mapping and entity linking techniques can be used to uniformly map different expressions such as "tensile test," "tensile strength test," and "tensiletest" to standard control point terminology, eliminating semantic ambiguity and realizing the transformation from standard control point terminology to structured control point data. Therefore, the final structured control point data includes machine-readable equipment codes, process names, process parameters, control point types, and standard clauses. Subsequently, a five-dimensional knowledge graph can be constructed based on the structured control point data, namely, a knowledge graph of equipment-component-process-standard clause-control point, thereby providing relevant information for subsequent control point recommendations.

[0021] In some specific embodiments, refer to Figure 2 Step S2 may further include steps S21-S23. Specifically, step S21 may include feature vectorization of the structured control point data to obtain control point semantic vectors; specifically, based on the content of the five-dimensional association knowledge graph obtained from the structured control point data, the description of the process to be controlled and the text in the control point standard database may be converted into control point semantic vectors respectively. The control point semantic vectors transform natural language semantic information into numerical expressions in a high-dimensional space, enabling the identification of semantically matched standard clauses without strict textual consistency, thus achieving intelligent matching of standard clauses under non-precise text conditions. Further, step S22 may be performed after obtaining the control point semantic vectors.

[0022] Furthermore, step S22 may include calculating the similarity of the structured data of control points based on the semantic vectors of the control points. The similarity can be calculated using the following formula: S = w1 S_{edit}+w2 S_{seq}+w3 S_{jaccard}+w4 S_{semantic}. Where S is the similarity, S_{edit} is the edit distance similarity, S_{seq} is the sequence matching similarity, S_{jaccard} is the set overlap similarity, S_{semantic} is the deep semantic similarity, w1 is the weight corresponding to edit distance similarity, w2 is the weight corresponding to sequence matching similarity, w3 is the weight corresponding to set overlap similarity, and w4 is the weight corresponding to deep semantic similarity. That is, in some specific embodiments, the four-dimensional similarity calculation includes edit distance similarity calculation, sequence matching similarity calculation, set overlap similarity (Jaccard similarity) calculation, and deep semantic similarity calculation (based on a Pre-trained Language Model, such as BERT / RoBERTa, RoFormer, SimCSE, Sentence-BERT (SBERT), or graph embedding similarity calculation using Graph Neural Networks (GNN)). Different weight coefficients can be matched to the four similarity calculations according to the actual situation, and the sum of the products of each weight and the corresponding similarity is the final similarity.

[0023] In some embodiments, step S23 may include confirming control point standardization information based on similarity. Specifically, the control point standardization information can be determined by judging the relationship between similarity and a first threshold, and the first threshold can also be dynamically adjusted according to the equipment level (nuclear safety level / non-nuclear level). If the similarity score exceeds the first threshold, the control point standardization information in the standard database (including multiple ASME and GB standards and management procedures for manufacturing processes) is automatically locked, and the mandatory descriptions (such as "must", "should", "should") regarding control point settings in the control point standardization information are extracted. For example, the national standard GB / T 228.2-2015 for high-temperature tensile testing methods stipulates that during the test, the temperature within the gauge length of the specimen should be maintained within the specified temperature allowable deviation range; after reaching the set temperature, it should be kept at that temperature for a sufficient time to ensure uniform specimen temperature before applying a tensile load. In this case, the clause includes the mandatory description "should", and this mandatory description is extracted. Furthermore, for example, in some practical application scenarios, the first threshold can be set to 0.9. If the calculation finds that the similarity between a certain process and the RCC-MM2123 clause after four-dimensional similarity calculation is as high as 0.92, then the content of the clause is parsed, and the "shall be witnessed" related content in the standardization information of the control point is identified. Then the standard control point type corresponding to the process is point W.

[0024] In some specific embodiments, in step S3, the control point settings of similar processes in the historical database can be aggregated and statistically analyzed according to dimensions such as equipment category (pump, valve, container, etc.), material type, and manufacturing process (casting, forging, welding, etc.) to obtain historical control point information. Further, the weights of the biased control points and the abnormal control points can be determined based on historical biased control points and historical abnormal control points, thus identifying abnormal settings in the historical control point information. For example, if a process is set as point W in 90% of projects, but as point N / A in some projects, then point W is a historical biased control point, and point N / A is a historical abnormal control point. Combining this with the project's quality feedback records (such as non-conformity records (NCR), experience feedback, etc.), the abnormal data is weighted down. Finally, the historical control point type can be determined based on the weights of the biased control points and the abnormal control points. For example, in the above example, point W has a weight of 90%, while point N / A has a weight of 10%. Since point W has a higher weight, it can be used as the historical control point type. In some embodiments, a recommended intensity heatmap can be generated based on process-control points, which can intuitively display the historical frequency distribution and confidence interval of each option H / W / R / N / A, and help to better select the type of historical control point.

[0025] In some embodiments, step S4 is to confirm the control point selection decision based on the standard control point type and the historical control point type. In some specific embodiments, a Bayesian inference model can be introduced to calculate the posterior probability of the control point type corresponding to the standard control point type and the historical control point type under a given device attribute, and the maximum probability can be selected as the recommendation result. Further, it can be referred to... Figure 3 The process can include step S31, determining whether the standard control point type has a mandatory description; step S32, if the determination is no, identifying abnormal point selection risk cases based on historical abnormal point selections, and generating an abnormal point selection traceability card based on the abnormal point selection risk cases; step S33, if the standard control point type is the same as the historical control point type, generating a point selection recommendation traceability card based on the standard control point type and the historical control point type; and step S34, determining the control point selection decision based on the abnormal point selection traceability card and the point selection recommendation traceability card. The control point selection decision mainly includes the original text and number of the cited standard clauses, the number of historical similar cases, the items and setting ratios, and the recommendation confidence score. In some embodiments, if the standard control point type has a mandatory description (e.g., regulations require it to be set as an H point), then even if the historical control point type is not an H point, the historical control point type can be ignored, and the mandatory requirements of the standard control point type can be directly used to select control points to ensure compliance. The traceability card can clearly show the regulatory source and historical data support for each recommendation, fully meeting the stringent requirements of the nuclear power industry for quality traceability, and greatly reducing the difficulty of quality review.

[0026] In some specific embodiments, the control point selection method 10 can also provide a visual interface for staff, push control point selection decisions, and allow staff to "adopt," "modify," or "reject" the recommended results of the control point selection decisions. For items that deviate from the control point selection decisions, staff are required to fill in the reasons for modification (such as "special process requirements"). In some embodiments, the final data after manual correction can be used as a high-quality labeled sample, updated in real time to the historical database of selected points, and trigger incremental training of the model, automatically adjusting the similarity algorithm weights and statistical cardinality to further improve the reliability of supervision.

[0027] The control point selection method 10 will now be described in conjunction with a specific implementation method. In the procurement quality plan for the main pump casing (equipment code: PUMP-001) of a nuclear power project, a key process is included: "SA-508Gr.3Cl.1 forging high-temperature tensile test". First, control point selection method 10 can automatically read the manufacturing process flow table of the equipment. Then, it identifies the process description "high-temperature tensile test". First, it needs to normalize "high-temperature tensile test" and map it to the standard control point term "HighTemperatureTensileTest". Then, it extracts the associated attributes: material grade "SA-508Gr.3Cl.1", equipment type "main pump casing", and safety level "nuclear level 1", and converts it into machine-readable structured control point data. Furthermore, searches can be conducted in the RCC-MM2000 and ASME Section III standard libraries, and the similarity of the process can be calculated using four-dimensional similarity. For example, if the similarity between this process and clause RCC-MM2123 is as high as 0.92, then the content of that clause can be analyzed to identify the selected point matching information "shall be witnessed," thus determining it as a mandatory W-point requirement. Next, the manufacturing data of the main pump casings for all nuclear power projects of the company over the past 10 years can be retrieved from the historical database. Statistical analysis of the historical database reveals that in 15 similar quality plans, this process was set as a W-point 13 times and as non-witnessed 2 times (N / A). At this point, further analysis of projects not involved in witnessing can be conducted. For example, if a subsequent experience feedback event record shows a quality problem, this abnormal case is automatically marked and its weight is reduced in the statistical analysis. Finally, a control point recommendation traceability card is generated, pointing to point W (weighted percentage 92.85%), and an abnormal control point traceability card is generated, pointing to the N / A point case. At this time, the control point selection decision is to select point W, but at the same time, a quality risk warning will be issued.

[0028] This application also refers to, in another respect, [the following text is missing from the original] Figure 4 A manufacturing process control point selection system 40 is proposed, mainly comprising: a data and processing module 41, configured to acquire raw control point data and convert the raw control point data into structured control point data; an intelligent matching engine module 42, configured to confirm standardized control point information based on the structured control point data, wherein the standardized control point information includes a standard control point type corresponding to the structured control point data; a historical data analysis module 43, configured to confirm historical control point information based on the structured control point data, wherein the historical control point information includes a historical control point type corresponding to the structured control point data; and a decision fusion center module 43, configured to confirm the control point selection decision based on the standard control point type and the historical control point type.

[0029] An embodiment of this application also proposes a method such as Figure 5 The manufacturing process control point selection system 50 is shown. According to... Figure 5 The manufacturing process control point selection system 50 may include an internal communication bus 51, a processor 52, a read-only memory (ROM) 53, a random access memory (RAM) 54, and a communication port 55. When applied to a personal computer, the manufacturing process control point selection system 50 may also include a hard disk 56.

[0030] The internal communication bus 51 enables data communication between components of the manufacturing process control point selection system 50. The processor 52 can perform judgments and issue prompts. In some embodiments, the processor 52 may consist of one or more processors. The communication port 55 enables data communication between the manufacturing process control point selection system 50 and external systems. In some embodiments, the manufacturing process control point selection system 50 can send and receive information and data from a network via the communication port 55.

[0031] The manufacturing process control point selection system 50 may also include different types of program storage units and data storage units, such as hard disk 56, read-only memory (ROM) 53, and random access memory (RAM) 54, capable of storing various data files used for computer processing and / or communication, as well as possible program instructions executed by processor 52. The processor executes these instructions to implement the main part of the method. The results of processor processing are transmitted to the user equipment via a communication port and displayed on the user interface.

[0032] In addition, this application also proposes a computer-readable medium storing computer program code, which implements the above-described voice interaction method when executed by a processor.

[0033] The basic concepts have been described above. Obviously, for those skilled in the art, the above disclosure is merely illustrative and does not constitute a limitation of this application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are suggested in this application, and therefore remain within the spirit and scope of the exemplary embodiments of this application.

[0034] Furthermore, this application uses specific terms to describe embodiments of the application. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic related to at least one embodiment of the application. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this specification do not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of the application can be appropriately combined.

[0035] Some aspects of this application can be executed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The aforementioned hardware or software may be referred to as a "data block," "module," "engine," "unit," "component," or "system." The processor may be one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or combinations thereof. Furthermore, aspects of this application may manifest as computer products residing in one or more computer-readable media, including computer-readable program code. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic tapes, etc.), optical discs (e.g., compressed CDs, digital multifunction DVDs, etc.), smart cards, and flash memory devices (e.g., cards, sticks, key drives, etc.).

[0036] A computer-readable medium may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and so on, or suitable combinations thereof. A computer-readable medium can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer-readable medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, radio frequency signals, or similar media, or any combination of the above media.

[0037] Similarly, it should be noted that, in order to simplify the description of the present application and thus aid in the understanding of one or more embodiments, the foregoing description of the embodiments of the present application sometimes combines multiple features into a single embodiment, drawing, or description thereof. However, this disclosure method does not imply that the subject matter of the present application requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of the single embodiments disclosed above.

[0038] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of scope in some embodiments of this application are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0039] Although this application has been described with reference to specific embodiments, those skilled in the art should recognize that the above embodiments are only used to illustrate this application, and various equivalent changes or substitutions can be made without departing from the spirit of this application. Therefore, any changes or modifications to the above embodiments within the essential spirit of this application will fall within the scope of the claims of this application.

Claims

1. A method for selecting control points in a manufacturing process, applicable to reactors, characterized in that, The method includes the following steps: Obtain raw control point data and convert it into structured control point data. Based on the structured data of the control points, the standardized information of the control points is confirmed, and the standardized information of the control points includes the standard control point type corresponding to the structured data of the control points; Based on the structured data of the control points, the historical information of the control points is confirmed, including the historical control point types corresponding to the structured data of the control points; The control point selection decision is confirmed based on the standard control point type and the historical control point type.

2. The manufacturing process control point selection method as described in claim 1, characterized in that, The step of obtaining the raw control point data and converting the raw control point data into structured control point data includes: Extract control point statements from the raw control point data; The standard terminology of the control point is obtained based on the control point statement, and the structured data of the control point is obtained based on the standard terminology of the control point.

3. The method for selecting control points in a manufacturing process as described in claim 1, characterized in that, The process of confirming the standardized information of the control points based on the structured data of the control points includes the following steps: The structured data of the control points is vectorized to obtain semantic vectors of the control points. The similarity of the structured data of the control points is calculated based on the semantic vectors of the control points. The control point standardization information is confirmed based on the similarity.

4. The method for selecting control points in a manufacturing process as described in claim 3, characterized in that, This includes calculating the similarity of the structured data of the control points using the following formula: S=w1 S_{edit}+w2 S_{seq}+w3 S_{jaccard}+w4 S_{semantic} Where S represents the similarity, S_{edit} represents the edit distance similarity, S_{seq} represents the sequence matching similarity, S_{jaccard} represents the set overlap similarity, and S_{semantic} represents the deep semantic similarity. w1 is the weight corresponding to the edit distance similarity, w2 is the weight corresponding to the sequence matching similarity, w3 is the weight corresponding to the set overlap similarity, and w4 is the weight corresponding to the deep semantic similarity.

5. The method for selecting control points in a manufacturing process as described in claim 1, characterized in that, Based on the structured control point data, the historical information of the control points is confirmed. This historical information includes the historical control point types corresponding to the structured control point data, including: Based on the historically favored control points, determine the weights of the historically favored control points. Based on historical abnormal control points, determine the weight of the historical abnormal control points; The type of historical control point is determined based on the weights of the historical biased control points and the weights of the historical abnormal control points.

6. The method for selecting control points in a manufacturing process as described in claim 5, characterized in that, The process of confirming the control point selection decision based on the standard control point type and the historical control point type includes: Determine whether the standard control point type has a mandatory description; If the judgment is negative, then an abnormal control point risk case is determined based on the historical abnormal control points, and an abnormal control point traceability card is generated based on the abnormal control point risk case. If the standard control point type is the same as the historical control point type, then a control point recommendation traceability card is generated based on the standard control point type and the historical control point type. The control point selection decision is determined based on the anomaly control point tracing card and the control point recommendation tracing card.

7. The method for selecting control points in a manufacturing process using intelligent control points as described in claim 1, characterized in that, Both the standard control point type and the historical control point type include one of the following: work stoppage pending inspection point, witness point, document review point, and point not requiring supervision, or any combination thereof.

8. A manufacturing process control point selection system, characterized in that, include: The data and processing module is configured to acquire raw control point data and convert the raw control point data into structured control point data. The intelligent matching engine module is configured to confirm the standardized information of control points based on the structured data of the control points, wherein the standardized information of the control points includes the standard control point type corresponding to the structured data of the control points; The historical data analysis module is configured to confirm the historical information of the control points based on the structured data of the control points, wherein the historical information of the control points includes the historical control point types corresponding to the structured data of the control points; The decision fusion center module is configured to confirm the control point selection decision based on the standard control point type and the historical control point type.

9. A manufacturing process control point selection system, characterized in that, Also includes: Memory is used to store instructions that can be executed by the processor; and a processor for executing the instructions to implement the method as described in any one of claims 1-7.

10. A computer-readable medium storing computer program code that, when executed by a processor, implements the method as claimed in any one of claims 1-7.

Images