Order delivery optimization scheduling method and system based on machine learning

Abstract

The invention discloses an order delivery optimization scheduling method and system based on machine learning, and relates to the technical field of monitoring analysis, and the system comprises a data collection system which is used for collecting corresponding order data and assembly line data in a target factory; the analysis processing module is used for carrying out analysis processing on the corresponding order data and assembly line data in the target factory, carrying out risk analysis on each order in the target factory according to an analysis processing result, and formulating an optimization strategy based on a risk analysis result; the response module is used for responding to the optimization strategy and scheduling the corresponding orders in the target factory; and the notification module is used for outputting an early warning signal to a manager and outputting notification information. The method and the device have the effect of improving order delivery scheduling efficiency.

Description

Technical Field

[0001] The present application relates to the field of monitoring and analysis technology, and in particular to an order delivery optimization scheduling method and system based on machine learning. Background Art

[0002] Order delivery optimization scheduling plays a vital role in modern supply chain management. It aims to optimize every link from order generation to final delivery through intelligent algorithms and data analysis. Through automated and intelligent decision support, enterprises can effectively reduce delivery time and cost and improve customer satisfaction. In addition, optimized scheduling can enhance the company's ability to respond to market changes and improve the flexibility and reliability of the overall supply chain.

[0003] In the related technology, in response to customer demand orders in factories, traditional order delivery optimization scheduling methods often rely on static rules and experience, which makes it difficult to deal with abnormal situations in the assembly line, and to analyze whether the order delivery is on time from multiple angles, thereby effectively reducing the efficiency of order delivery, and there is room for improvement. Summary of the invention

[0004] In response to the deficiencies in the prior art, the present application provides an order delivery optimization scheduling method and system based on machine learning.

[0005] In a first aspect, the present application provides an order delivery optimization scheduling system based on machine learning, comprising: Data collection system, used to collect corresponding order data and assembly line data in the target factory; The analysis and processing module is used to analyze and process the corresponding order data and assembly line data in the target factory, conduct risk analysis on each order in the target factory according to the analysis and processing results, and formulate optimization strategies based on the results of the risk analysis; A response module, used to respond to the optimization strategy and schedule the corresponding orders in the target factory; The notification module is used to output warning signals and notification information to management personnel.

[0006] Preferably, the data acquisition system includes a data recognition unit, a data analysis unit and a marking unit; The data identification unit is used to identify the order type data, order remaining delivery time data and order mark data corresponding to each order in the target factory according to the corresponding order data in the target factory; The data analysis unit is used to comprehensively analyze the order type data, order remaining delivery time data, order marking data and assembly line data corresponding to each order in the target factory; The marking unit is used to analyze the completion status of each order in the target factory and mark each order based on the analysis result.

[0007] Preferably, a comprehensive analysis is performed on the order type data, order remaining delivery time data, order marking data and assembly line data corresponding to each order in the target factory, specifically including: Analyze the delay risk of each order in the target factory based on the order type data, order remaining delivery time data, order tag data and assembly line data corresponding to each order in the target factory; By formula , confirm the delay risk assessment coefficient corresponding to each order in the target factory ; in, Indicates the number corresponding to each order. Indicated as number The order type coefficient corresponding to the order of Indicated as number The remaining delivery time of the order corresponding to the order, Indicated as number The number of marks corresponding to the order; The delay risk assessment coefficient corresponding to each order in the target factory The delay risk assessment threshold range is Make a comparison; If there is a delay risk assessment coefficient corresponding to the order in the target factory , then there is no need to conduct risk analysis on the order of the target factory; If there is a delay risk assessment coefficient corresponding to the order in the target factory In When the target factory has a certain order, the order is set as a target order, and a risk analysis is performed on the target order in the target factory; If there is a delay risk assessment coefficient corresponding to the order in the target factory , then the orders of the target factory need to be scheduled and managed according to the preset first-level optimization strategy.

[0008] Preferably, the process of performing risk analysis on the target order in the target factory specifically includes: Confirm the assembly line corresponding to the target order, and set the assembly line as the target assembly line, and then extract assembly line data corresponding to the target assembly line from the corresponding assembly line data in the target factory, wherein the assembly line data includes assembly line equipment data and assembly line product data, wherein the assembly line equipment data includes an assembly line equipment state assessment coefficient and an assembly line equipment operation time assessment coefficient, and wherein the assembly line product data includes a product qualification coefficient and a product rework coefficient; By formula , confirm the assembly line equipment evaluation coefficient corresponding to the target assembly line in the target factory ; in, They are respectively represented as the pipeline equipment status evaluation coefficient and the pipeline equipment running time evaluation coefficient corresponding to the target pipeline. They are respectively represented by the preset standard assembly line equipment status evaluation coefficient and the preset standard assembly line equipment running time evaluation coefficient corresponding to the target assembly line. are respectively expressed as weight coefficients, and e is a natural constant.

[0009] Preferably, the process of performing risk analysis on the target order in the target factory specifically includes: Acquire assembly line product data corresponding to a target assembly line in a target factory, and extract a product qualification coefficient and a product rework coefficient corresponding to the target assembly line from the assembly line product data; By formula , confirm the production line product evaluation coefficient corresponding to the target production line in the target factory ; in, They are respectively expressed as the product qualification coefficient and product rework coefficient corresponding to the target production line. They are respectively represented as the preset standard product qualification coefficient and the preset standard product rework coefficient corresponding to the target assembly line; By formula , confirm the comprehensive evaluation coefficient of the target production line in the target factory ,in, They are respectively represented as weight coefficients corresponding to the preset assembly line equipment evaluation coefficient and assembly line product evaluation coefficient; The comprehensive evaluation coefficient of the target assembly line in the target factory Comprehensive evaluation threshold with preset pipeline Make a comparison; If the comprehensive evaluation coefficient of the target assembly line in the target factory corresponds to , then there is no need to formulate an optimization strategy; If the comprehensive evaluation coefficient of the target assembly line in the target factory corresponds to , an optimization strategy needs to be formulated for the target order.

[0010] Preferably, the process of formulating an optimization strategy for the target order specifically includes: The above formula is used to calculate the comprehensive reference value of the delay risk of the target order in the target factory. ; in, It is expressed as the delay risk assessment coefficient corresponding to the target order, Represented as a preset correlation function; The comprehensive reference value of the target factory's target order delay risk With the preset comprehensive reference threshold Make a comparison; Comprehensive reference value if there is a risk of delay in the target order in the target factory , the target orders in the target factory need to be scheduled and managed according to the preset secondary optimization strategy; Comprehensive reference value if there is a risk of delay in the target order in the target factory , the target orders in the target factory need to be scheduled and managed according to the preset three-level optimization strategy, and the warning signal and notification information are output to the management personnel through the notification module.

[0011] Preferably, the process of analyzing the completion status of each order in the target factory and marking each order based on the analysis result specifically includes: Within a preset time period, each timestamp is obtained, and based on each timestamp, the completion coefficient corresponding to each order in the target factory is obtained, and the completion coefficient corresponding to each order is compared with the preset completion coefficient range. If there is an order whose corresponding completion coefficient is not in the preset completion coefficient range, the order is marked once, and then the number of markings corresponding to each order in the target factory is confirmed.

[0012] In a second aspect, the present application provides an order delivery optimization scheduling method based on machine learning, comprising the following steps: Collect the corresponding order data and assembly line data in the target factory; Analyze and process the corresponding order data and assembly line data in the target factory, conduct risk analysis on each order in the target factory based on the results of the analysis and processing, and formulate optimization strategies based on the results of the risk analysis; Responding to the optimization strategy, and scheduling corresponding orders in the target factory; Output warning signals to management personnel and output notification information.

[0013] In a third aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute any one of the above-mentioned machine learning-based order delivery optimization scheduling systems.

[0014] In summary, this application includes the following beneficial technical effects: The present application provides an order delivery optimization scheduling system based on machine learning, which analyzes and processes the corresponding order data and assembly line data in the target factory, conducts risk analysis on each order in the target factory according to the results of the analysis and processing, and formulates an optimization strategy based on the results of the risk analysis; then responds to the optimization strategy and schedules the corresponding orders in the target factory, thereby effectively dealing with abnormal situations in the assembly line and effectively analyzing whether the order is delivered on time, thereby effectively improving the efficiency of order delivery. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0016] Figure 1 It is a system diagram of order delivery optimization scheduling based on machine learning in an embodiment of the present application.

[0017] Figure 2 This is a flow chart of a method for optimizing order delivery scheduling based on machine learning in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The following is combined with Figure 1-2 This application is described in further detail. Example

[0019] The embodiments of the present application disclose an order delivery optimization scheduling system based on machine learning.

[0020] Reference Figure 1 , an order delivery optimization scheduling system based on machine learning, including: Data collection system, used to collect corresponding order data and assembly line data in the target factory; The analysis and processing module is used to analyze and process the corresponding order data and assembly line data in the target factory, conduct risk analysis on each order in the target factory according to the analysis and processing results, and formulate optimization strategies based on the results of the risk analysis; A response module, used to respond to the optimization strategy and schedule the corresponding orders in the target factory; The notification module is used to output warning signals and notification information to management personnel.

[0021] Further, the data acquisition system includes a data recognition unit, a data analysis unit and a marking unit; The data identification unit is used to identify the order type data, order remaining delivery time data and order mark data corresponding to each order in the target factory according to the corresponding order data in the target factory; The data analysis unit is used to comprehensively analyze the order type data, order remaining delivery time data, order marking data and assembly line data corresponding to each order in the target factory; The marking unit is used to analyze the completion status of each order in the target factory and mark each order based on the analysis result.

[0022] It should be noted that a comprehensive analysis is conducted on the order type data, order remaining delivery time data, order marking data and assembly line data corresponding to each order in the target factory, including: Analyze the delay risk of each order in the target factory based on the order type data, order remaining delivery time data, order tag data and assembly line data corresponding to each order in the target factory; By formula , confirm the delay risk assessment coefficient corresponding to each order in the target factory ; in, Indicates the number corresponding to each order. Indicated as number The order type coefficient corresponding to the order of Indicated as number The remaining delivery time of the order corresponding to the order, Indicated as number The number of marks corresponding to the order; The delay risk assessment coefficient corresponding to each order in the target factory The delay risk assessment threshold range is Make a comparison; If there is a delay risk assessment coefficient corresponding to the order in the target factory , then there is no need to conduct risk analysis on the order of the target factory; If there is a delay risk assessment coefficient corresponding to the order in the target factory In When the target factory has a certain order, the order is set as a target order, and a risk analysis is performed on the target order in the target factory; If there is a delay risk assessment coefficient corresponding to the order in the target factory , then the orders of the target factory need to be scheduled and managed according to the preset first-level optimization strategy.

[0023] Specifically, by evaluating the delay risk coefficient of each order, the delivery process can be managed more accurately and the overall operational efficiency can be improved. Using key indicators such as order type coefficient, order remaining delivery time, and order marking times, the delay risk assessment system can identify high-risk orders and help companies take measures to make adjustments in advance. Among them, the order type coefficient reflects the complexity and priority of different orders, the remaining delivery time provides a reference for time urgency, and the number of order markings can reveal the frequency of potential problems. Combining the above factors, a comprehensive risk assessment coefficient can be generated to guide scheduling decisions. In turn, resource allocation can be effectively optimized, high-risk orders can be prioritized, and delays can be reduced. Not only does it improve the timeliness and accuracy of delivery, but it also enhances customer satisfaction and trust.

[0024] It should be noted that the process of risk analysis of target orders in target factories specifically includes: Confirm the assembly line corresponding to the target order, and set the assembly line as the target assembly line, and then extract assembly line data corresponding to the target assembly line from the corresponding assembly line data in the target factory, wherein the assembly line data includes assembly line equipment data and assembly line product data, wherein the assembly line equipment data includes an assembly line equipment state assessment coefficient and an assembly line equipment operation time assessment coefficient, and wherein the assembly line product data includes a product qualification coefficient and a product rework coefficient; Among them, the corresponding assembly line equipment data and assembly line product data in the target factory can be obtained through machine learning technology; By formula , confirm the assembly line equipment evaluation coefficient corresponding to the target assembly line in the target factory ; in, They are respectively represented as the pipeline equipment status evaluation coefficient and the pipeline equipment running time evaluation coefficient corresponding to the target pipeline. They are respectively represented by the preset standard assembly line equipment status evaluation coefficient and the preset standard assembly line equipment running time evaluation coefficient corresponding to the target assembly line. are respectively expressed as weight coefficients, and e is a natural constant.

[0025] Specifically, by determining the equipment status assessment coefficient and equipment operation time assessment coefficient of the target assembly line, the overall performance and health of the equipment can be comprehensively assessed. The above assessment method can help identify potential equipment failures and inefficiencies. The equipment status assessment coefficient provides immediate feedback on the current operating status of the equipment, while the operation time assessment coefficient reflects the service life and maintenance needs of the equipment. Combining these two indicators, a comprehensive equipment assessment coefficient can be generated to optimize maintenance plans and resource allocation, which can reduce unplanned downtime, improve production efficiency, and extend equipment life. In addition, identifying and resolving equipment problems in advance can help reduce maintenance costs, prevent production interruptions, and ensure the continuity and stability of the production process.

[0026] It should be noted that the process of risk analysis of target orders in target factories also includes: Acquire assembly line product data corresponding to a target assembly line in a target factory, and extract a product qualification coefficient and a product rework coefficient corresponding to the target assembly line from the assembly line product data; By formula , confirm the production line product evaluation coefficient corresponding to the target production line in the target factory ; in, They are respectively expressed as the product qualification coefficient and product rework coefficient corresponding to the target production line. They are respectively represented as the preset standard product qualification coefficient and the preset standard product rework coefficient corresponding to the target assembly line; By formula , confirm the comprehensive evaluation coefficient of the target production line in the target factory ,in, They are respectively represented as weight coefficients corresponding to the preset assembly line equipment evaluation coefficient and assembly line product evaluation coefficient; The comprehensive evaluation coefficient of the target assembly line in the target factory Comprehensive evaluation threshold with preset pipeline Make a comparison; If the comprehensive evaluation coefficient of the target assembly line in the target factory corresponds to , then there is no need to formulate an optimization strategy; If the comprehensive evaluation coefficient of the target assembly line in the target factory corresponds to , an optimization strategy needs to be formulated for the target order.

[0027] Specifically, by determining the product qualification coefficient and rework coefficient of the target assembly line, the overall quality level and efficiency of the production line can be effectively evaluated. The product qualification coefficient reflects the stability of product quality, while the rework coefficient reveals potential problems in the production process. Combining the above indicators, the assembly line product evaluation coefficient can be calculated to help identify weak links in quality control. Using the assembly line product evaluation coefficient, the production process can be optimized, rework and scrap rates can be reduced, thereby reducing production costs and resource waste. In addition, improving product quality and qualification rate helps to enhance customer satisfaction and market competitiveness.

[0028] It should be noted that the process of formulating an optimization strategy for the target order specifically includes: The above formula is used to calculate the comprehensive reference value of the delay risk of the target order in the target factory. ; in, It is expressed as the delay risk assessment coefficient corresponding to the target order, Represented as a preset correlation function; The comprehensive reference value of the target factory's target order delay risk With the preset comprehensive reference threshold Make a comparison; Comprehensive reference value if there is a risk of delay in the target order in the target factory , the target orders in the target factory need to be scheduled and managed according to the preset secondary optimization strategy; Comprehensive reference value if there is a risk of delay in the target order in the target factory , the target orders in the target factory need to be scheduled and managed according to the preset three-level optimization strategy, and the warning signal and notification information are output to the management personnel through the notification module.

[0029] Specifically, in the embodiment of the present application, the urgency of the optimization strategies is from high to low as follows: three-level optimization strategy > two-level optimization strategy > one-level optimization strategy, wherein the first-level optimization strategy is set to monitor the production process of the order in real time, the second-level optimization strategy is set to improve the efficiency of the assembly line, and the third-level optimization strategy is set to urgently dispatch multiple assembly lines to work.

[0030] Furthermore, the completion status of each order in the target factory is analyzed, and each order is marked based on the analysis result, specifically including: Within a preset time period, each timestamp is obtained, and based on each timestamp, the completion coefficient corresponding to each order in the target factory is obtained, and the completion coefficient corresponding to each order is compared with the preset completion coefficient range. If there is an order whose corresponding completion coefficient is not in the preset completion coefficient range, the order is marked once, and then the number of markings corresponding to each order in the target factory is confirmed.

[0031] Specifically, exemplarily, the completion coefficient corresponding to each order in the target factory at the first timestamp is obtained, and the completion coefficient corresponding to each order is compared with a preset completion coefficient interval. If the completion coefficient corresponding to an order is not within the preset completion coefficient interval, the order is marked once; Secondly, obtain the completion coefficient corresponding to each order in the target factory at the second timestamp, and compare the completion coefficient corresponding to each order with the preset completion coefficient range. If there is an order whose corresponding completion coefficient is not in the preset completion coefficient range, the order is marked once, and then the number of markings corresponding to each order within the preset time period is confirmed, wherein the preset completion coefficient ranges corresponding to different timestamps are different. Example

[0032] The embodiments of the present application also disclose an order delivery optimization scheduling method based on machine learning.

[0033] Reference Figure 2 , the order delivery optimization scheduling method based on machine learning includes the following steps: Collect the corresponding order data and assembly line data in the target factory; Analyze and process the corresponding order data and assembly line data in the target factory, conduct risk analysis on each order in the target factory based on the results of the analysis and processing, and formulate optimization strategies based on the results of the risk analysis; Responding to the optimization strategy, and scheduling corresponding orders in the target factory; Output warning signals to management personnel and output notification information.

[0034] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention, they should all fall within the protection scope of the present invention.

[0035] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0036] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well.

Claims

1. The order delivery optimization scheduling system based on machine learning is characterized by: include: Data collection system, used to collect corresponding order data and assembly line data in the target factory; The analysis and processing module is used to analyze and process the corresponding order data and assembly line data in the target factory, conduct risk analysis on each order in the target factory according to the analysis and processing results, and formulate optimization strategies based on the results of the risk analysis; A response module, used to respond to the optimization strategy and schedule the corresponding orders in the target factory; The notification module is used to output warning signals and notification information to management personnel.

2. The order delivery optimization scheduling system based on machine learning according to claim 1 is characterized in that: The data acquisition system includes a data recognition unit, a data analysis unit and a marking unit; The data identification unit is used to identify the order type data, order remaining delivery time data and order mark data corresponding to each order in the target factory according to the corresponding order data in the target factory; The data analysis unit is used to comprehensively analyze the order type data, order remaining delivery time data, order marking data and assembly line data corresponding to each order in the target factory; The marking unit is used to analyze the completion status of each order in the target factory and mark each order based on the analysis result.

3. The order delivery optimization scheduling system based on machine learning according to claim 2 is characterized in that: Comprehensively analyze the order type data, order remaining delivery time data, order marking data and assembly line data corresponding to each order in the target factory, including: Analyze the delay risk of each order in the target factory based on the order type data, order remaining delivery time data, order tag data and assembly line data corresponding to each order in the target factory; By formula , confirm the delay risk assessment coefficient corresponding to each order in the target factory ; in, Indicates the number corresponding to each order. Indicated as number The order type coefficient corresponding to the order of Indicated as number The remaining delivery time of the order corresponding to the order, Indicated as number The number of marks corresponding to the order; The delay risk assessment coefficient corresponding to each order in the target factory The delay risk assessment threshold range is Make a comparison; If there is a delay risk assessment coefficient corresponding to the order in the target factory , then there is no need to conduct risk analysis on the order of the target factory; If there is a delay risk assessment coefficient corresponding to the order in the target factory In When the target factory has a certain order, the order is set as a target order, and a risk analysis is performed on the target order in the target factory; If there is a delay risk assessment coefficient corresponding to the order in the target factory , then the orders of the target factory need to be scheduled and managed according to the preset first-level optimization strategy.

4. The order delivery optimization scheduling system based on machine learning according to claim 3 is characterized in that: The process of conducting risk analysis on target orders in target factories includes: Confirm the assembly line corresponding to the target order, and set the assembly line as the target assembly line, and then extract assembly line data corresponding to the target assembly line from the corresponding assembly line data in the target factory, wherein the assembly line data includes assembly line equipment data and assembly line product data, wherein the assembly line equipment data includes an assembly line equipment state assessment coefficient and an assembly line equipment operation time assessment coefficient, and wherein the assembly line product data includes a product qualification coefficient and a product rework coefficient; By formula , confirm the assembly line equipment evaluation coefficient corresponding to the target assembly line in the target factory ; in, They are respectively represented as the pipeline equipment status evaluation coefficient and the pipeline equipment running time evaluation coefficient corresponding to the target pipeline. They are respectively represented by the preset standard assembly line equipment status evaluation coefficient and the preset standard assembly line equipment running time evaluation coefficient corresponding to the target assembly line. are respectively expressed as weight coefficients, and e is a natural constant.

5. The order delivery optimization scheduling system based on machine learning according to claim 4 is characterized in that: The process of risk analysis of target orders in target factories also includes: Acquire assembly line product data corresponding to a target assembly line in a target factory, and extract a product qualification coefficient and a product rework coefficient corresponding to the target assembly line from the assembly line product data; By formula , confirm the production line product evaluation coefficient corresponding to the target production line in the target factory ; in, They are respectively expressed as the product qualification coefficient and product rework coefficient corresponding to the target production line. They are respectively represented as the preset standard product qualification coefficient and the preset standard product rework coefficient corresponding to the target assembly line; By formula , confirm the comprehensive evaluation coefficient of the target assembly line in the target factory ,in, They are respectively represented as weight coefficients corresponding to the preset assembly line equipment evaluation coefficient and assembly line product evaluation coefficient; The comprehensive evaluation coefficient of the target assembly line in the target factory Comprehensive evaluation threshold with preset pipeline Make a comparison; If the comprehensive evaluation coefficient of the target assembly line in the target factory corresponds to , then there is no need to formulate an optimization strategy; If the comprehensive evaluation coefficient of the target assembly line in the target factory corresponds to , an optimization strategy needs to be formulated for the target order.

6. The order delivery optimization scheduling system based on machine learning according to claim 5 is characterized in that: The process of formulating an optimization strategy for the target order specifically includes: The above formula is used to calculate the comprehensive reference value of the delay risk of the target order in the target factory. ; in, It is expressed as the delay risk assessment coefficient corresponding to the target order, Represented as a preset correlation function; The comprehensive reference value of the target factory's target order delay risk With the preset comprehensive reference threshold Make a comparison; Comprehensive reference value if there is a risk of delay in the target order in the target factory , the target orders in the target factory need to be scheduled and managed according to the preset secondary optimization strategy; Comprehensive reference value if there is a risk of delay in the target order in the target factory , the target orders in the target factory need to be scheduled and managed according to the preset three-level optimization strategy, and the warning signal and notification information are output to the management personnel through the notification module.

7. The order delivery optimization scheduling system based on machine learning according to claim 2 is characterized in that: The process of analyzing the completion status of each order in the target factory and marking each order based on the analysis results, specifically including: Within a preset time period, each timestamp is obtained, and based on each timestamp, the completion coefficient corresponding to each order in the target factory is obtained, and the completion coefficient corresponding to each order is compared with the preset completion coefficient range. If there is an order whose corresponding completion coefficient is not in the preset completion coefficient range, the order is marked once, and then the number of markings corresponding to each order in the target factory is confirmed.

8. The method for optimizing order delivery scheduling based on machine learning is applied to the system for optimizing order delivery scheduling based on machine learning as described in any one of claims 1 to 7, characterized in that: The following steps are involved: Collect the corresponding order data and assembly line data in the target factory; Analyze and process the corresponding order data and assembly line data in the target factory, conduct risk analysis on each order in the target factory based on the results of the analysis and processing, and formulate optimization strategies based on the results of the risk analysis; Responding to the optimization strategy, and scheduling corresponding orders in the target factory; Output warning signals to management personnel and output notification information.

9. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes the order delivery optimization scheduling system based on machine learning as described in any one of claims 1 to 7.

Images