An AI-based intelligent sourcing and order optimization system

Abstract

The present invention is applicable to the technical field of intelligent order management, and provides an AI-based intelligent sourcing and order optimization system. The system includes: a data acquisition module, a new equipment determination module, a specified defective product ratio determination module, and a parameter correction module. Among them: The data acquisition module is used to determine the delivery stability parameter of the order to be executed after determining that the product of the order to be executed is a new model product, and obtain the production history data set of the production unit to which the order to be executed belongs. The present invention calculates the specified defective product ratio of the target production process based on the production history data set, and calculates the deviation amount in combination with the benchmark defective product ratio of the reference production process, so as to construct a correction factor to realize the dynamic correction of the delivery stability parameter.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent order management, and particularly relates to an AI-based intelligent sourcing and order optimization system. Background Art

[0002] In the prior art, order management systems are widely used in fields such as manufacturing and supply chain management, aiming to improve production efficiency, shorten delivery cycles, and reduce production costs through the analysis and optimization of order data. In the process of order management, production prediction methods based on historical data are usually adopted to optimize material procurement, production scheduling, and order delivery plans. Some technical solutions combine the operating status of production equipment, historical production efficiency, and inventory data, and use algorithm analysis to allocate optimal production resources for orders. However, in the process of order management for new model products, due to the adjustment of production processes, the update of production equipment, and the change of process parameters, the delivery stability parameters calculated by traditional order management systems based on existing model product data or fixed models often cannot accurately predict the production stability of new model products, resulting in a deviation between the order optimization strategy and the actual production conditions.

[0003] To solve the order optimization problem for new model products, some existing technologies introduce machine learning or artificial intelligence algorithms to improve the intelligence level of order optimization by analyzing historical production data, equipment operation and maintenance records, and order execution situations. However, these solutions mainly establish prediction models based on existing production data and cannot dynamically correct the production stability changes caused by the introduction of new dedicated equipment. In addition, although some technical solutions consider the process differences between different model products, their analysis methods are usually based on fixed classification rules or empirical parameter settings, lacking the ability to make real-time adjustments during the production process of new model products, resulting in low prediction accuracy and being unable to effectively guide the implementation of order optimization strategies. Summary of the Invention

[0004] The purpose of the present invention is to provide an AI-based intelligent sourcing and order optimization system, aiming to solve the problems raised in the background art.

[0005] The present invention is implemented as follows. An AI-based intelligent sourcing and order optimization system includes: a data acquisition module, a new equipment determination module, a specified defective product ratio determination module, and a parameter correction module, where:

[0006] The data acquisition module is used to determine the delivery stability parameter of a to-be-executed order and obtain the production historical data set of the production unit to which the to-be-executed order belongs after determining that the product of the to-be-executed order is a new model product;

[0007] A new equipment determination module, which is used to determine the existing model products corresponding to the new model products in the production unit, obtain the production process flows of the new model products and the existing model products, and determine the newly added dedicated equipment introduced for producing the new model products according to the differences between the two production process flows;

[0008] A specified defective product ratio determination module, which is used to screen out several production process flows containing the newly added dedicated equipment from the production history dataset, match the production process flow that matches the production background of the production process flow of the new model products as the target production process, and determine the specified defective product ratio caused by the newly added dedicated equipment during the preset operation time of the target production process;

[0009] A parameter correction module, which is used to calculate the baseline defective product ratio caused by the equipment of the same category as the newly added dedicated equipment among the products of the same category as the new model products based on the production history dataset, and correct the delivery stability parameter based on the deviation between the specified defective product ratio and the baseline defective product ratio.

[0010] As a further limitation of the technical solution of the embodiment of the present invention, the new equipment determination module specifically includes:

[0011] An existing model determination unit, which is used to determine the improved product with the closest production process flow corresponding to the new model products in the production unit, and use this product as the existing model product;

[0012] A new process determination unit, which is used to obtain the production process flows of the new model products and the existing model products, and analyze the newly added key process links of the production process flow of the new model products compared with the production process flow of the existing model products;

[0013] A new equipment determination unit, which is used to identify the production equipment involved in the newly added key process links, and set this production equipment as the newly added dedicated equipment.

[0014] As a further limitation of the technical solution of the embodiment of the present invention, the specified defective product ratio determination module specifically includes:

[0015] A target production process determination unit, which is used to screen out several production process flows containing the newly added dedicated equipment from the production history dataset, and match the production process flow that is closest to the production process flow of the new model products in terms of process complexity and production environment conditions, and set this production process flow as the target production process;

[0016] A defective product statistics unit, which is used to count all the defective products generated by the target production process during the preset operation time based on the production history dataset, and identify the specific equipment that causes each defective product;

[0017] A specified defective product ratio determination unit is used to calculate the ratio of specified defective products caused by newly added dedicated equipment among all defective products in the target production process.

[0018] As a further limitation of the technical solution of the embodiment of the present invention, the parameter correction module specifically includes:

[0019] A reference production process acquisition unit is used to screen out several reference production processes of products of the same category as the new model product based on the production history data set, and analyze the process complexity of each reference production process;

[0020] A process complexity analysis unit is used to determine the process complexity of the target production process, and calculate the process complexity adjustment factor corresponding to each reference production process based on the process complexity of the target production process and the process complexity of each reference production process;

[0021] A reference defective product ratio calculation unit is used to count the ratio of defective products caused by equipment of the same category as the newly added dedicated equipment in each reference production process within a preset time period, and calculate the reference defective product ratio based on the process complexity adjustment factors and corresponding defective product ratios of all reference production processes;

[0022] A parameter correction execution unit is used to correct the delivery stability parameter based on the deviation between the specified defective product ratio of the target production process and the reference defective product ratio.

[0023] As a further limitation of the technical solution of the embodiment of the present invention, in the process of calculating the reference defective product ratio based on the process complexity adjustment factors and corresponding defective product ratios of all reference production processes, a preset reference defective product ratio calculation formula is adopted;

[0024] The reference defective product ratio calculation formula is: , where refers to the reference defective product ratio, refers to the total number of reference production processes, refers to the process complexity adjustment factor corresponding to the th reference production process, refers to the ratio of defective products caused by equipment of the same category as the newly added dedicated equipment in the

[0025] th reference production process within a preset time period; , where refers to the process complexity of the th reference production process,

[0026] As a further limitation of the technical solution of the embodiment of the present invention, the parameter correction execution unit specifically includes:

[0027] A correction factor setting sub-unit, configured to calculate the deviation amount between the specified defective product ratio and the reference defective product ratio of the target production process, and set it as the correction factor;

[0028] A parameter adjustment sub-unit, configured to retrieve a preset parameter correction formula, and adjust the delivery stability parameter based on the correction factor, and apply the corrected delivery stability parameter to the optimization of the order to be executed.

[0029] As a further limitation of the technical solution of the embodiment of the present invention, the parameter correction formula is: , where refers to the corrected delivery stability parameter, refers to the uncorrected delivery stability parameter, refers to the specified defective product ratio of the target production process, refers to the reference defective product ratio, refers to the correction factor, that is, the deviation amount between the specified defective product ratio and the reference defective product ratio of the target production process, refers to the adjustment coefficient corresponding to the correction factor.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] The present invention calculates the specified defective product ratio of the target production process based on the production history data set, and calculates the deviation amount in combination with the reference defective product ratio of the reference production process to construct a correction factor, so as to realize the dynamic correction of the delivery stability parameter. Compared with the prior art, the method of calculating the delivery stability parameter only relying on the historical data of existing model products or a fixed model cannot accurately reflect the production stability change caused by the introduction of new special equipment for new model products. However, the present invention makes the delivery stability parameter dynamically adapt to the production characteristics of new model products through the comparison and correction based on actual production data, improving the accuracy and reliability of order optimization.

[0032] The present invention matches the target production process that is closest to the process complexity and production environment conditions of the new model product, ensuring that the reference data is more in line with the actual production situation of the new model product, and avoiding optimization errors caused by data deviation. By calculating the process complexity adjustment factor to optimize the calculation of the reference defective product ratio, the reference comparison is made more scientific and reasonable, ensuring the stability and applicability of order optimization, improving the accuracy of production scheduling, reducing the delivery risk caused by production fluctuations, and enhancing the reliability and intelligent level of order execution. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1It is the application architecture diagram of the system provided by the embodiment of the present invention;

[0034] Figure 2 It is the structural block diagram of the new device determination module in the system provided by the embodiment of the present invention;

[0035] Figure 3 It is the structural block diagram of the specified defective product ratio determination module in the system provided by the embodiment of the present invention;

[0036] Figure 4 It is the structural block diagram of the parameter correction module in the system provided by the embodiment of the present invention;

[0037] Figure 5 It is the structural block diagram of the parameter correction execution unit in the system provided by the embodiment of the present invention. Detailed implementation manners

[0038] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0039] Furthermore, Figure 1 It shows the application architecture diagram of the system provided by the embodiment of the present invention.

[0040] Among them, in another preferred embodiment provided by the present invention, an AI-based intelligent sourcing and order optimization system includes:

[0041] A data acquisition module 100, configured to determine the delivery stability parameters of a to-be-executed order and obtain the production history dataset of the production unit to which the to-be-executed order belongs after determining that the product of the to-be-executed order is a new model product.

[0042] In the embodiment of the present invention, determining that the product of the to-be-executed order is a new model product can be achieved by comparing the product information of the to-be-executed order with the historical production dataset of the production unit. Specifically, obtain the product model information specified in the to-be-executed order, and extract the product model information involved in the historical production records from the production history dataset of the production unit. If the product model specified in the to-be-executed order does not exist in the production history dataset or exists but there are significant changes such as process adjustments, material changes, production equipment updates, etc., then the product is identified as a new model product. This method can effectively identify the production characteristic differences caused by factors such as product upgrades, material replacements or production equipment changes, and ensure that appropriate optimization strategies can be adopted for the characteristics of new model products in the subsequent optimization process.

[0043] The delivery stability parameter is used to characterize the stability of the to-be-executed order during the production process and reflects the delivery reliability of the order product within the planned delivery period. The delivery stability parameter can be generated based on the mature stability evaluation model in the existing technology. The specific generation method includes obtaining the historical production data set of the production unit to which the to-be-executed order belongs, combining the data such as the defective rate, equipment failure rate, production rhythm stability, process parameter fluctuation, and raw material supply stability recorded in the historical production data set, using the data analysis model to quantitatively analyze the above parameters, and generating a parameter value that can comprehensively reflect the production stability of the to-be-executed order. The delivery stability parameter plays an important role in the order optimization process. Based on this parameter, dynamic adjustments can be made to aspects such as the order production plan, material supply plan, and personnel scheduling plan to reduce the risk of delayed delivery caused by unstable production factors and improve the reliability and production efficiency of order execution.

[0044] The production historical data set of the production unit to which the to-be-executed order belongs can be extracted from the production management system of the production unit. The content of the production historical data set includes the production records of previous orders within the production unit, specifically including information such as order number, product model, production batch, production time, production cycle, output, quality inspection results, defective rate, production anomaly records and their handling measures; the records of previous production process flows within the production unit, including the production process flows, process steps, process parameter settings, equipment configurations, processing materials, production environmental conditions, quality control standards, and process adjustment history of each product; the records of previous equipment usage within the production unit, including information such as equipment number, equipment type, equipment operation status, equipment maintenance records, equipment failure records, equipment replacement and upgrade records, equipment operation parameter fluctuation data, and correlation analysis data between equipment and defective rate.

[0045] The extraction and sorting method of the production historical data set can perform data query based on the production management system, or can perform batch data mining through the database interface or big data analysis system. In practical applications, the content of the production historical data set is the basic data source for subsequent module analysis. By comprehensively obtaining this data set, it can ensure that each module has sufficient reference information during the analysis process and avoid calculation deviations or inaccurate optimizations caused by incomplete data or data missing.

[0046] Furthermore, the AI-based intelligent sourcing and order optimization system further includes:

[0047] A new equipment determination module 200, which is used to determine the existing model products corresponding to the new model products in the production unit, obtain the production process flows of the new model products and the existing model products, and determine the new dedicated equipment introduced for the production of the new model products according to the differences between the two production process flows.

[0048] Specifically, Figure 2 The structural block diagram of the new device determination module 200 in the system provided by the embodiment of the present invention is shown.

[0049] Among them, in the preferred embodiment provided by the present invention, the new device determination module 200 specifically includes:

[0050] The existing model determination unit 201 is used to determine the product in the production unit that is improved and has the closest process flow corresponding to the new model product, and use this product as the existing model product;

[0051] The new process determination unit 202 is used to obtain the production process flows of the new model product and the existing model product, and analyze the new key process links in the production process flow of the new model product compared with the production process flow of the existing model product;

[0052] The new device determination unit 203 is used to identify the production equipment involved in the new key process links, and set this production equipment as the new dedicated equipment.

[0053] In the embodiment of the present invention, determining the product in the production unit that is improved and has the closest process flow corresponding to the new model product can be achieved by analyzing the production history data set of the production unit. Specifically, first, obtain the design specifications, material compositions, target production processes, and manufacturing requirements of the new model product, then screen out the mass-produced products of the same or similar categories as the new model product from the production history data set, and further analyze the production process flows, processing steps, equipment configurations, quality control standards, etc. of these products. Next, calculate the process flow complexity and production process similarity of each candidate product, and combine the design change points of the new model product to determine the existing product of the new model product that is closest in terms of process flow, production environment, processing steps, etc., and use it as the existing model product.

[0054] The reason for selecting this product as the existing model product is that new model products are usually optimized, improved, or functionally upgraded based on the original products. Therefore, the existing model product with the closest process flow to the new model product can provide the most reference-worthy historical production data, facilitate the analysis of the impact of process changes on the production process, and provide a basis for the identification of new equipment. In addition, the production data of the existing model product can be used for calculating the production stability prediction, equipment adaptability evaluation, process optimization parameter setting, etc. of the new model product, ensuring that the production of the new model product can be optimized and adjusted based on the existing mature processes, improving production efficiency and reducing the uncertainty brought by process adjustments.

[0055] Obtain the production process flows of new model products and existing model products, and analyze the new key process links in the production process flow of new model products compared with that of existing model products. Specifically, it can be achieved through the production process flow comparison method. First, extract the complete production process flow of existing model products from the production historical dataset, including each processing step, process parameter setting, production equipment configuration, processing materials, and quality inspection standards, and establish a standard process flow model. Then, obtain the design process flow of new model products, and compare the production process flow of new model products with the standard process flow of existing model products according to dimensions such as processing sequence, process characteristics, and equipment adaptability, identify information such as newly added processing steps, process adjustment points, equipment requirement change points, and material replacement points in the production process of new model products, and finally extract the new key process links of new model products. This method can effectively identify the process improvement parts of new model products compared with existing model products, and ensure the pertinence of production adjustment.

[0056] Identify the production equipment involved in the new key process links, and set this production equipment as the newly added dedicated equipment. Specifically, it can be achieved through the process equipment association analysis method. First, based on the equipment usage records in the production historical dataset, analyze the production equipment used in each process step of existing model products, and establish the mapping relationship between the process flow and the equipment. Then, based on the new key process links of new model products obtained from the above comparison analysis, determine the production steps, process parameter adjustment situations, and material change situations involved in this process link, and combine the mapping relationship between the process flow and the equipment to determine the equipment category that can execute this process link. If the equipment type involved in this process link has not been used in the production process of existing model products, or equipment upgrade and transformation are required to meet the new process requirements, then this equipment is identified as the newly added dedicated equipment. Through this method, the newly added production equipment required for new model products can be accurately identified, and it is ensured that the production equipment configuration meets the process requirements of new model products.

[0057] Furthermore, the AI-based intelligent sourcing and order optimization system further includes:

[0058] A specified defective product ratio determination module 300, which is used to screen out several production process flows containing newly added dedicated equipment from the production historical dataset, match the production process flow that matches the production background of the production process flow of new model products as the target production process, and determine the specified defective product ratio caused by the newly added dedicated equipment during the preset operation time of the target production process.

[0059] Specifically, Figure 3 The structural block diagram of the specified defective product ratio determination module 300 in the system provided by the embodiment of the present invention is shown.

[0060] Among them, in the preferred embodiment provided by the present invention, the specified defective product ratio determination module 300 specifically includes:

[0061] A target production process determination unit 301, configured to screen out several production process flows including newly added dedicated equipment from the production history dataset, and match the production process flow that is closest to the production process flow of the new model product in terms of process complexity and production environment conditions, and set this production process flow as the target production process;

[0062] A defective product statistics unit 302, configured to count all defective products generated by the target production process within a preset operation time based on the production history dataset, and identify the specific equipment that causes each defective product;

[0063] A specified defective product ratio determination unit 303, configured to calculate the ratio of specified defective products caused by the newly added dedicated equipment among all defective products within the target production process.

[0064] In the embodiment of the present invention, the preset operation time refers to the shortest time required for order delivery, that is, the shortest production duration required for this target production process under the premise of meeting the order delivery time constraint. The main purpose of setting this time range is to ensure that the counted defective product data can truly reflect the production stability within the order delivery cycle, and at the same time avoid introducing historical data unrelated to order execution due to too long a statistical cycle, thereby affecting the accuracy of the evaluation. By limiting the statistical time range within the shortest time required for order delivery, the impact of the newly added dedicated equipment on the production stability of the order in the actual production process can be more accurately identified, ensuring that the calculated ratio of specified defective products can be directly used for correcting the delivery stability parameter, enabling the order optimization to be adjusted based on a more accurate production stability evaluation result, and improving the predictability of order execution and the rationality of production scheduling.

[0065] The acquisition of process complexity can be calculated based on the quantification methods used in the prior art to measure the complexity of production processes. Specifically, the process complexity usually consists of data in multiple dimensions, including the number of processing steps, the fineness of process parameter control, the automation level of equipment, the stability of the production beat, the technical requirements of operators, etc. By analyzing the production process flows recorded in the production history dataset, feature data related to process complexity can be extracted, and through weighted calculation with weights, the process complexity value of each production process flow can be obtained. Common methods in the prior art include process complexity calculation based on a rule model, complexity modeling based on statistical regression, and process complexity prediction based on machine learning. These methods can be used to calculate the process complexity of the target production process and the reference production process to provide basic data for production process matching and optimization.

[0066] Match the production process flow that is closest to the new model product in terms of process complexity and production environment conditions, and set this production process flow as the target production process, which can be specifically achieved through the production process flow feature matching method. First, screen out all production process flows containing new dedicated equipment from the production history dataset, and obtain their corresponding process complexity, production environment parameters, and equipment configuration. Then, based on the production process flow of the new model product, calculate its process complexity value, and analyze the production environment conditions involved in this production process flow, including indicators such as temperature and humidity control requirements, cleanliness standards, equipment types, and production rhythm stability. Next, compare the process complexity value of each candidate production process flow with the process complexity value of the new model product, calculate the complexity deviation between the two, and at the same time match the production environment parameters of the candidate production process flow with the production environment requirements of the new model product, and calculate the environmental fitness score. Finally, based on the comprehensive evaluation results of the complexity deviation and the environmental fitness score, select the production process flow with the highest comprehensive matching degree as the target production process. The significance of formulating the target production process is that this production process can best reflect the production conditions of the new model product, and provide a reasonable production stability assessment based on the existing production data, ensuring that subsequent production optimization and stability correction can be analyzed based on historical data with high similarity, improving prediction accuracy and reducing the risk of production adjustment.

[0067] Based on the production history dataset, count all defective products produced by the target production process within the preset running time, and identify the specific equipment that caused each defective product, which can be specifically achieved through the defective product traceability analysis method. First, extract production data from the historical production log corresponding to the target production process, including product batches, production times, process parameter settings, equipment operation records, quality inspection results, and defective product statistics. Then, screen out all products recorded as defective from the production log, and analyze the production time points, production steps, and process parameter status corresponding to the defective products, further extract the production equipment and process links involved when the defective products occur, and establish the association between defective products and equipment. Next, according to the equipment operation status, fault records, and process adjustment conditions in the production log, determine whether each defective product is caused by the new dedicated equipment, count the number of defective products caused by the new dedicated equipment among all defective products within the target production process, and calculate the specified defective product ratio.

[0068] The generation of the specified defective product ratio is of great significance, mainly used to quantify the impact of newly added special equipment on production stability. Since newly added special equipment may introduce new process uncertainties during the production process of new model products, leading to a decline in production stability, it is necessary to calculate the specified defective product ratio of the target production process to evaluate the stability performance of this equipment in the actual production environment. This parameter can not only be used to judge whether there is a high risk of failure or defective products in the newly added special equipment, but also provide reference data for subsequent delivery stability correction, enabling the final order optimization to be adjusted based on more accurate production stability evaluation results, and improving the delivery reliability of new model products.

[0069] Furthermore, the AI-based intelligent sourcing and order optimization system further includes:

[0070] A parameter correction module 400, configured to calculate the benchmark defective product ratio caused by equipment of the same category as the newly added special equipment in products of the same category as the new model product based on the production history data set, and correct the delivery stability parameter based on the deviation between the specified defective product ratio and the benchmark defective product ratio.

[0071] Specifically, Figure 4 FIG. shows the structural block diagram of the parameter correction module 400 in the system provided by the embodiment of the present invention.

[0072] Among them, in the preferred embodiment provided by the present invention, the parameter correction module 400 specifically includes:

[0073] A reference production process acquisition unit 401, configured to screen out several reference production processes of products of the same category as the new model product based on the production history data set, and analyze the process complexity of each reference production process;

[0074] A process complexity analysis unit 402, configured to determine the process complexity of the target production process, and calculate the process complexity adjustment factor corresponding to each reference production process based on the process complexity of the target production process and the process complexity of each reference production process;

[0075] A benchmark defective product ratio calculation unit 403, configured to count the defective product ratio caused by equipment of the same category as the newly added special equipment in each reference production process within a preset period, and calculate the benchmark defective product ratio based on the process complexity adjustment factors and the corresponding defective product ratios of all reference production processes;

[0076] A parameter correction execution unit 404, configured to correct the delivery stability parameter based on the deviation between the specified defective product ratio and the benchmark defective product ratio of the target production process.

[0077] In the process of calculating the baseline defective product ratio based on the process complexity adjustment factors of all reference production processes and the corresponding defective product ratios, a preset calculation formula for the baseline defective product ratio is adopted;

[0078] The calculation formula for the baseline defective product ratio is: , where refers to the baseline defective product ratio, refers to the total number of reference production processes, refers to the th process complexity adjustment factor corresponding to the reference production process, refers to the th defective product ratio caused by equipment of the same category as the newly added dedicated equipment during the preset period for the reference production process;

[0079] In the calculation formula for the baseline defective product ratio: , where refers to the process complexity of the th reference production process, refers to the process complexity of the target production process.

[0080] In the embodiments of the present invention, the same category generally refers to products belonging to the same product category in the product classification system. Specifically, these products have high similarities in aspects such as production process, processing materials, equipment configuration, and process parameter control range. For example, in the field of electronic manufacturing, the same category may refer to circuit board products of the same size or the same function, and in the field of machining, the same category may refer to parts using the same processing method or the same material. In the implementation process of the present invention, selecting products of the same category as the new model product as the basis for the reference production process is to ensure that the selected reference production process has high consistency with the production environment and process requirements of the new model product, making the calculation of the baseline defective product ratio more valuable for reference.

[0081] The process complexity adjustment factor is used to measure the impact of the process complexity of each reference production process on the target production process. If the process complexity adjustment factor is greater than 1, it means that the process complexity of this reference production process is higher than that of the target production process. If the process complexity adjustment factor is less than 1, it means that the process complexity of this reference production process is lower than that of the target production process. Through the calculation of this factor, in the process of calculating the baseline defective product ratio, reasonable weighting can be performed on reference production processes with different process complexities to ensure that the calculated baseline defective product ratio can accurately reflect the production environment characteristics of the target production process.

[0082] The significance of the benchmark defective product ratio lies in that it provides a reference standard for evaluating the production stability of the target production process in the production environment of products of the same category, and is used to correct the delivery stability parameters. By calculating the benchmark defective product ratio, the calculation deviation caused by the abnormality of individual production processes can be reduced, the evaluation accuracy of the production stability of the target production process can be improved, and more reliable data support can be provided for the order optimization of new model products.

[0083] Specifically, Figure 5 FIG. shows a structural block diagram of a parameter correction execution unit 404 in the system provided by an embodiment of the present invention.

[0084] Among them, in the preferred embodiment provided by the present invention, the parameter correction execution unit 404 specifically includes:

[0085] A correction factor setting sub-unit 4041, configured to calculate the deviation amount between the specified defective product ratio of the target production process and the benchmark defective product ratio, and set it as the correction factor;

[0086] A parameter adjustment sub-unit 4042, configured to retrieve a preset parameter correction formula, and adjust the delivery stability parameter based on the correction factor, and apply the corrected delivery stability parameter to the optimization of the order to be executed.

[0087] The parameter correction formula is: , where refers to the corrected delivery stability parameter, refers to the uncorrected delivery stability parameter, refers to the specified defective product ratio of the target production process, refers to the benchmark defective product ratio, refers to the correction factor, that is, the deviation amount between the specified defective product ratio of the target production process and the benchmark defective product ratio, refers to the adjustment coefficient corresponding to the correction factor.

[0088] In the embodiment of the present invention, the main purpose of calculating the deviation amount between the specified defective product ratio of the target production process and the benchmark defective product ratio and setting it as the correction factor is to ensure that the delivery stability parameter can accurately reflect the actual impact of the newly added dedicated equipment on the production stability of new model products. Since the production process flow of new model products may be adjusted compared with that of existing model products, especially the introduction of newly added dedicated equipment may cause changes in production stability. Therefore, the delivery stability parameter calculated only based on historical data or the benchmark model may not be able to truly reflect the production status of new model products. By calculating the specified defective product ratio of the target production process and comparing it with the benchmark defective product ratio, the influence degree of the newly added dedicated equipment on the defective product rate can be quantified, so that the correction of the delivery stability parameter has clear data support.

[0089] Adjust the delivery stability parameter based on the correction factor and apply the corrected delivery stability parameter to the optimization of the order to be executed, which can improve the accuracy and stability of order execution. The delivery stability parameter directly affects production scheduling, material supply, quality control and delivery time prediction during the order production process. If the parameter is calculated inaccurately, it may lead to misjudgment of the production plan, resulting in production capacity fluctuations, quality problems or delivery delays during the order execution process. The present invention ensures that the calculation of the delivery stability parameter is not only based on historical data but can also adaptively correct the stability performance of new model products in the actual production environment through a correction method based on the deviation amount, making the order optimization more in line with the actual production situation and improving the scientific nature of overall production management.

[0090] The core innovation of the present invention is to calculate the specified defective product ratio of the target production process and calculate the deviation amount in combination with the benchmark defective product ratio, and construct a correction factor in a data-driven manner, so that the correction of the delivery stability parameter not only depends on static historical data but can also dynamically adapt to the production characteristic changes of new model products. This method breaks through the limitation of the prior art that only relies on historical data of existing model products or fixed models to calculate the delivery stability parameter, enabling the delivery stability parameter to more accurately predict the production stability of new model products, thereby improving the reliability and execution effect of order optimization.

[0091] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order limit for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment but can be executed at different moments, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0092] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in this application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or an external cache. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0093] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0094] The above embodiments only represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

[0095] The above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An AI-based intelligent sourcing and order optimization system, characterized by: The system includes: a data acquisition module, a new equipment determination module, a designated defective product ratio determination module, and a parameter correction module, wherein: A data acquisition module is used to determine the delivery stability parameters of the pending order after determining that the product of the pending order is a new model product, and obtain the production history data set of the production unit to which the pending order belongs; A new equipment determination module is used to determine the existing product models corresponding to the new product models in the production unit, obtain the production process flows of the new product models and the existing product models, and determine the new special equipment introduced for the production of the new product models based on the differences between the two production process flows; The module for determining the proportion of designated defective products is used to select several production process flows that include newly added special equipment from the production history data set, match the production process flow that matches the production background of the production process flow of the new model product as the target production process flow, and determine the proportion of designated defective products caused by the newly added special equipment in the target production process flow within a preset operating time; The parameter correction module is used to calculate the baseline defective product ratio caused by the same category of equipment as the newly added special equipment in the same category of products as the new model product based on the production history data set, and to correct the delivery stability parameters based on the deviation between the specified defective product ratio and the baseline defective product ratio.

2. The AI-based intelligent sourcing and order optimization system according to claim 1 is characterized in that: The newly added device determination module specifically includes: An existing model determination unit is used to determine the improved product in the production unit that corresponds to the new model product and has the closest process flow, and to treat this product as the existing model product; A new process determination unit is added to obtain the production process flow of new and existing models of products, and analyze the new key process links in the production process flow of new models compared with the production process flow of existing models; The newly added equipment determination unit is used to identify the production equipment involved in the newly added key process links and set the production equipment as newly added special equipment.

3. The AI-based intelligent sourcing and order optimization system according to claim 1 is characterized in that: The designated defective product ratio determination module specifically includes: The target production process determination unit is used to screen out several production process flows that include newly added special equipment from the production history data set, and match the production process flow that is closest to the production process flow of the new model product in terms of process complexity and production environment conditions, and set the production process flow as the target production process flow; The defective product statistics unit is used to count all defective products generated by the target production process within the preset running time based on the production history data set, and identify the specific equipment that causes each defective product; The designated defective product ratio determination unit is used to calculate the designated defective product ratio caused by the newly added special equipment among all defective products in the target production process.

4. The AI-based intelligent sourcing and order optimization system according to claim 3 is characterized in that: The parameter correction module specifically includes: A reference production process acquisition unit is used to screen out several reference production processes for products of the same category as the new model product based on the production history data set, and analyze the process complexity of each reference production process; a process complexity analysis unit, configured to determine the process complexity of the target production process and calculate a process complexity adjustment factor corresponding to each reference production process based on the process complexity of the target production process and the process complexity of each reference production process; A baseline defective product ratio calculation unit is used to count the defective product ratio caused by equipment of the same category as the newly added special equipment in each reference production process within a preset time period, and calculate the baseline defective product ratio based on the process complexity adjustment factors and corresponding defective product ratios of all reference production processes; The parameter correction execution unit is used to correct the delivery stability parameter based on the deviation between the specified defective product ratio of the target production process and the benchmark defective product ratio.

5. The AI-based intelligent sourcing and order optimization system according to claim 4 is characterized in that: In the process of calculating the baseline defective product ratio based on the process complexity adjustment factors and corresponding defective product ratios of all reference production processes, a preset baseline defective product ratio calculation formula is used; The calculation formula for the benchmark defective product ratio is: ,in Refers to the benchmark defective ratio, Refers to the total quantity of the reference production process, Refers to the A process complexity adjustment factor corresponding to a reference production process, Refers to the The percentage of defective products in a reference production process caused by equipment of the same type as the newly added specialized equipment within a preset period; In the formula for calculating the benchmark defective product ratio: ,in Refers to the A reference to the process complexity of the production process, Refers to the process complexity of the target production process.

6. The AI-based intelligent sourcing and order optimization system according to claim 4 is characterized in that: The parameter correction execution unit specifically includes: The correction factor setting subunit is used to calculate the deviation between the specified defective product ratio of the target production process and the benchmark defective product ratio, and set it as the correction factor; The parameter adjustment subunit is used to call a preset parameter correction formula, adjust the delivery stability parameter based on the correction factor, and apply the corrected delivery stability parameter to the optimization of the orders to be executed.

7. The AI-based intelligent sourcing and order optimization system according to claim 6, characterized in that: The parameter correction formula is: ,in refers to the modified delivery stability parameter, refers to the uncorrected delivery stability parameter, Refers to the specified defective proportion of the target production process, Refers to the benchmark defective ratio, Refers to the correction factor, which is the deviation between the specified defective percentage of the target production process and the benchmark defective percentage. Refers to the adjustment coefficient corresponding to the correction factor.

Images