LLM-based automatic production scheduling method and system for intelligent electric meter and acquisition equipment, and medium

Abstract

The invention provides an LLM-based automatic production scheduling method and system for an intelligent electric meter and acquisition equipment, and a medium, and belongs to the technical field of artificial intelligence and industrial manufacturing. The method comprises the following steps: obtaining production demand information and available capacity information for identification processing, obtaining initial production scheduling instruction information, and extracting order grade information, delivery cycle data and order demand data; querying through a preset production sequence table according to the order grade information to obtain production sequence information; comparing the delivery cycle data with a preset delivery cycle threshold to obtain shift adjustment information; and processing according to the order demand quantity data to obtain production line adjustment information. And optimizing the initial instruction information to obtain optimized production scheduling instruction information, extracting daily utilization rate data of a production line, and finally comparing the daily utilization rate data with a preset daily utilization rate threshold to judge whether requirements are met. The production efficiency and the resource utilization rate are remarkably improved, the production cost is reduced, and the customer satisfaction and the enterprise competitiveness are improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence and industrial manufacturing technology, and more specifically, to an automatic production scheduling method, system and medium for smart meters and data collection equipment based on LLM. Background Art

[0002] Traditional production scheduling methods often rely on manual experience and judgment, making it difficult to achieve large-scale customized production. This leads to low production efficiency and is unable to meet the growing market demand for smart meters and data collection equipment. When market demand changes, it takes a lot of time and effort to adjust the production schedule, which affects the company's response speed and market competitiveness.

[0003] Although the traditional production scheduling technology of smart meters and data collection equipment has played an important role in the construction of smart grids, it still has some defects. In order to overcome these defects, it is necessary to introduce more advanced and intelligent production scheduling technology to improve production efficiency, reduce costs, and improve product quality and flexibility.

[0004] In view of the above problems, effective technical solutions are currently awaited. Summary of the invention

[0005] The purpose of this application is to provide an automatic scheduling method, system and medium for smart meters and collection equipment based on LLM, which can obtain production demand information and available capacity information for identification and processing, obtain initial scheduling instruction information and extract order level information, delivery cycle data and order demand data. According to the order level information, the production sequence information is obtained by querying the preset production sequence list; the shift adjustment information is obtained by comparing the delivery cycle data with the preset delivery cycle threshold; the production line adjustment information is obtained by processing the order demand data. Then the initial instruction information is optimized, the optimized scheduling instruction information is obtained and the production line daily utilization data is extracted, and finally compared with the preset daily utilization threshold to determine whether the requirements are met. This application significantly improves production efficiency and resource utilization, reduces production costs, and improves customer satisfaction and corporate competitiveness.

[0006] The present application provides an automatic production scheduling method for smart meters and collection devices based on LLM, comprising the following steps:

[0007] Acquire multiple production demand information and available capacity information within a preset time period and identify and process them through a preset large language model to obtain initial production scheduling instruction information;

[0008] Extracting multiple order level information, delivery cycle data and multiple order demand quantity data according to the initial production scheduling instruction information;

[0009] According to the plurality of order level information, query through a preset production sequence list to obtain production sequence information;

[0010] Obtaining shift adjustment information based on the delivery cycle data and comparing it with a preset delivery cycle threshold;

[0011] Processing the multiple order demand quantity data to obtain production line adjustment information;

[0012] The initial instruction information is optimized according to the production sequence information, shift adjustment information and production line adjustment information to obtain optimized production scheduling instruction information and extract production line daily utilization data, which is then compared with the preset daily utilization threshold to determine whether the production line daily utilization meets the requirements.

[0013] Among them, in the automatic production scheduling method of the smart meter and the collection device based on LLM described in this application, the initial production scheduling instruction information is obtained specifically as follows:

[0014] Obtain multiple production demand information and available capacity information within a preset time period;

[0015] The production demand information includes demand product type information, demand production quantity information and product demand cycle information;

[0016] The available capacity information includes basic information of the production line, production shift rotation information and basic information of production personnel;

[0017] The initial production scheduling instruction information is obtained by combining the required product type information, required production quantity information and product demand cycle information with the basic information of the production line, production shift rotation information and basic information of production personnel and identifying and processing through a preset large language model.

[0018] Among them, in the automatic production scheduling method of the smart meter and the collection device based on LLM described in this application, the obtaining of the production sequence information is specifically:

[0019] Extracting a plurality of order level marking information and a plurality of order placement time data according to the plurality of order level information;

[0020] The order level marking information includes urgent order information, high priority order information, ordinary order information and low priority order information;

[0021] The production sequence information is obtained by querying through a preset production sequence list according to the multiple order level mark information and the multiple order placement time data.

[0022] Among them, in the automatic production scheduling method based on LLM smart meters and collection equipment described in this application, the shift adjustment information is obtained specifically as follows:

[0023] According to the delivery cycle data and compared with a preset delivery cycle threshold;

[0024] If the delivery cycle data is less than the delivery cycle threshold, the delivery requirements are met;

[0025] If the delivery cycle data is greater than or equal to the delivery cycle threshold, the shift adjustment information is obtained.

[0026] Among them, in the automatic production scheduling method of the smart meter and collection device based on LLM described in this application, the obtaining of production line adjustment information is specifically:

[0027] Comparing the plurality of order demand data with each other to obtain high-demand order information;

[0028] Acquire multiple production line efficiency data within the preset time period and compare them with each other to obtain high-efficiency production line information;

[0029] The high-demand order information is matched with the efficient production line information according to preset rules to obtain production line adjustment information.

[0030] Among them, in the automatic production scheduling method based on LLM smart meters and collection equipment described in this application, the determination of whether the daily utilization rate of the production line meets the requirements is specifically as follows:

[0031] Optimizing the initial instruction information according to the production sequence information, shift adjustment information and production line adjustment information to obtain optimized production scheduling instruction information;

[0032] Extracting daily utilization data of the production line according to the optimized production scheduling instruction information;

[0033] Comparing the daily utilization data of the production line with a preset daily utilization threshold to obtain a daily utilization deviation rate;

[0034] comparing the daily utilization rate deviation rate with a preset daily utilization rate deviation rate threshold;

[0035] If the daily utilization deviation rate is greater than or equal to the daily utilization deviation rate threshold, a low daily utilization rate information of the production line is sent;

[0036] If the daily utilization deviation rate is less than the daily utilization deviation rate threshold, the production line daily utilization qualified information is sent.

[0037] In a second aspect, the present application provides an automatic production scheduling system for a smart meter and a collection device based on LLM, the system comprising: a memory and a processor, the memory comprising a program of an automatic production scheduling method for a smart meter and a collection device based on LLM, and the program of the automatic production scheduling method for a smart meter and a collection device based on LLM is executed by the processor to implement the following steps:

[0038] Acquire multiple production demand information and available capacity information within a preset time period and identify and process them through a preset large language model to obtain initial production scheduling instruction information;

[0039] Extracting multiple order level information, delivery cycle data and multiple order demand quantity data according to the initial production scheduling instruction information;

[0040] According to the plurality of order level information, query through a preset production sequence list to obtain production sequence information;

[0041] Obtaining shift adjustment information based on the delivery cycle data and comparing it with a preset delivery cycle threshold;

[0042] Processing the multiple order demand quantity data to obtain production line adjustment information;

[0043] The initial instruction information is optimized according to the production sequence information, shift adjustment information and production line adjustment information to obtain optimized production scheduling instruction information and extract production line daily utilization data, which is then compared with the preset daily utilization threshold to determine whether the production line daily utilization meets the requirements.

[0044] Among them, in the automatic production scheduling system based on LLM smart meter and collection equipment described in this application, the initial production scheduling instruction information is obtained specifically as follows:

[0045] Obtain multiple production demand information and available capacity information within a preset time period;

[0046] The production demand information includes demand product type information, demand production quantity information and product demand cycle information;

[0047] The available capacity information includes basic information of the production line, production shift rotation information and basic information of production personnel;

[0048] The initial production scheduling instruction information is obtained by combining the required product type information, required production quantity information and product demand cycle information with the basic information of the production line, production shift rotation information and basic information of production personnel and identifying and processing through a preset large language model.

[0049] In the automatic production scheduling system based on LLM smart meters and data collection equipment described in this application, the production sequence information is obtained as follows:

[0050] Extracting a plurality of order level marking information and a plurality of order placement time data according to the plurality of order level information;

[0051] The order level marking information includes urgent order information, high priority order information, ordinary order information and low priority order information;

[0052] The production sequence information is obtained by querying through a preset production sequence list according to the multiple order level mark information and the multiple order placement time data.

[0053] In the third aspect, the present application also provides a computer-readable storage medium, which includes an automatic production scheduling method program for smart meters and collection equipment based on LLM. When the automatic production scheduling method program for smart meters and collection equipment based on LLM is executed by a processor, the steps of the automatic production scheduling method for smart meters and collection equipment based on LLM as described in any one of the above items are implemented.

[0054] As can be seen from the above, the automatic production scheduling method, system and medium based on the smart meter and collection device provided by the embodiment of the present application obtain multiple production demand information and available capacity information and identify and process them through a preset large language model to obtain initial production scheduling instruction information, extract multiple order level information, delivery cycle data and multiple order demand data. According to multiple order level information, query through the preset production sequence list to obtain production sequence information; according to the delivery cycle data and compare with the preset delivery cycle threshold, obtain shift adjustment information; according to multiple order demand data, process and obtain production line adjustment information. Then optimize the initial instruction information, obtain optimized production scheduling instruction information and extract production line daily utilization data, and finally compare with the preset daily utilization threshold to determine whether the production line daily utilization meets the requirements. This application significantly improves production efficiency and resource utilization, reduces production costs, and improves customer satisfaction and corporate competitiveness through efficient data processing, refined order management, flexible production sequence adjustment, intelligent shift and production line adjustment, real-time production line utilization monitoring and optimized production scheduling.

[0055] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 A flowchart of an automatic production scheduling method for smart meters and collection equipment based on LLM provided in an embodiment of the present application;

[0058] Figure 2 A flowchart of obtaining initial production scheduling instruction information for an automatic production scheduling method based on a smart meter and a collection device provided in an embodiment of the present application;

[0059] Figure 3 A flowchart of obtaining production sequence information of an automatic production scheduling method for a smart meter and a collection device based on LLM provided in an embodiment of the present application;

[0060] Figure 4 A flowchart of obtaining shift adjustment information for an automatic production scheduling method based on a smart meter and a collection device provided in an embodiment of the present application;

[0061] Figure 5 A flowchart of obtaining production line adjustment information for an automatic production scheduling method of a smart meter and a collection device based on LLM provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0063] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0064] Please refer to Figure 1 , Figure 1 The flowchart of the automatic production scheduling method of the smart meter and the collection device based on LLM in some embodiments of the present application. The automatic production scheduling method of the smart meter and the collection device based on LLM is used in terminal devices, such as computers, mobile phone terminals, etc. The automatic production scheduling method of the smart meter and the collection device based on LLM includes the following steps:

[0065] S101, obtaining multiple production demand information and available capacity information within a preset time period, performing recognition and processing through a preset large language model, and obtaining initial production scheduling instruction information;

[0066] S102, extracting a plurality of order level information, delivery cycle data and a plurality of order demand quantity data according to the initial production scheduling instruction information;

[0067] S103, querying through a preset production sequence list according to the plurality of order level information to obtain production sequence information;

[0068] S104, obtaining shift adjustment information based on the delivery cycle data and comparing it with a preset delivery cycle threshold;

[0069] S105, processing the multiple order demand data to obtain production line adjustment information;

[0070] S106. Optimize the initial instruction information according to the production sequence information, shift adjustment information and production line adjustment information to obtain optimized production scheduling instruction information and extract production line daily utilization data, and then compare it with the preset daily utilization threshold to determine whether the production line daily utilization meets the requirements.

[0071] Among them, the present application obtains the initial production scheduling instruction information by obtaining multiple production demand information and available capacity information and identifying and processing them through a preset large language model. The large language model can directly generate production scheduling strategies and production scheduling algorithm codes from natural language descriptions, and quickly output decision suggestions by combining basic information with training knowledge, verify scheduling results, and quickly generate suggestions and adjust strategies, which is more suitable for real-time decision-making. Extract multiple order level information, delivery cycle data, and multiple order demand data according to the initial production scheduling instruction information. Query through the preset production sequence list according to multiple order level information to obtain production sequence information; obtain shift adjustment information according to delivery cycle data and compare with the preset delivery cycle threshold; obtain production line adjustment information according to multiple order demand data. Then optimize the initial instruction information, obtain optimized production scheduling instruction information and extract production line daily utilization data, and finally compare with the preset daily utilization threshold to determine whether the production line daily utilization meets the requirements. This application significantly improves production efficiency and resource utilization, reduces production costs, and enhances customer satisfaction and corporate competitiveness through efficient data processing, refined order management, flexible production sequence adjustment, intelligent shift and production line adjustment, real-time production line utilization monitoring, and optimized production scheduling.

[0072] Please refer to Figure 2 , Figure 2 The flowchart of obtaining the initial production scheduling instruction information of the automatic production scheduling method based on the smart meter and the collection device of LLM in some embodiments of the present application. According to the embodiment of the present invention, the obtaining of the initial production scheduling instruction information is specifically:

[0073] S201, obtaining a plurality of production demand information and available capacity information within a preset time period;

[0074] S202, the production demand information includes demand product type information, demand production quantity information and product demand cycle information;

[0075] S203, the available capacity information includes basic information of the production line, production shift rotation information and basic information of production personnel;

[0076] S204, according to the demand product type information, demand production quantity information and product demand cycle information, combined with the basic information of the production line, production shift rotation information and basic information of production personnel, and through the preset large language model, identification and processing are performed to obtain initial production scheduling instruction information.

[0077] Among them, in order to achieve automated and efficient production scheduling, first obtain multiple production demand information and available capacity information within a preset time period. The production demand information includes demand product type information, demand production quantity information and product demand cycle information. The demand product type information clarifies the product type to be produced, such as smart meters, collection equipment, etc.; the demand production quantity information refers to the specific production quantity demand of each product; the product demand cycle information represents the urgency of product demand and the expected delivery cycle. The available capacity information includes production line basic information, production shift rotation information and production personnel basic information. The production line basic information includes production line type, production capacity, equipment status, etc.; production shift rotation information includes working hours, rest time and shift rotation rules; production personnel basic information includes the number of production personnel, skill level, availability, etc. According to the demand product type information, demand production quantity information and product demand cycle information, combined with the production line basic information, production shift rotation information and production personnel basic information and through the preset large language model for identification and processing, the initial production scheduling instruction information is obtained. This large language model can understand and parse production demand and capacity information described in natural language. Through intelligent analysis, it considers factors such as product type, production quantity, demand cycle, production line capacity, shift rotation and staffing, and generates preliminary production scheduling instruction information.

[0078] Please refer to Figure 3 , Figure 3 The flowchart of the automatic production scheduling method of the smart meter and the collection device based on LLM in some embodiments of the present application is to obtain the production sequence information. According to the embodiment of the present invention, the production sequence information is obtained specifically as follows:

[0079] S301, extracting multiple order level mark information and multiple order time data according to the multiple order level information;

[0080] S302, the order level marking information includes urgent order information, high priority order information, ordinary order information and low priority order information;

[0081] S303: query the preset production sequence list according to the multiple order level mark information and the multiple order time data to obtain production sequence information.

[0082] Among them, multiple order level marking information and multiple order time data are extracted according to multiple order level information, and the order level marking information includes urgent order information, high priority order information, ordinary order information and low priority order information. According to multiple order level marking information and multiple order time data, the preset production sequence list is queried to obtain production sequence information. It should be noted that urgent orders take precedence over high priority orders, high priority orders take precedence over ordinary orders, and ordinary orders take precedence over low priority orders; within the same level, they are sorted from early to late according to order time.

[0083] Please refer to Figure 4 , Figure 4 The following is a flowchart of obtaining shift adjustment information of an automatic production scheduling method based on LLM smart meters and collection devices in some embodiments of the present application. According to an embodiment of the present invention, obtaining shift adjustment information is specifically:

[0084] S401, comparing the delivery cycle data with a preset delivery cycle threshold;

[0085] S402: If the delivery cycle data is less than the delivery cycle threshold, the delivery requirement is met;

[0086] S403: If the delivery cycle data is greater than or equal to the delivery cycle threshold, shift adjustment information is obtained.

[0087] Among them, in order to meet the delivery cycle requirements, the delivery cycle data is compared with the preset delivery cycle threshold. If the delivery cycle data is less than the delivery cycle threshold, the delivery requirements are met; if the delivery cycle data is greater than or equal to the delivery cycle threshold, it means that according to the current production plan and resource allocation, the order cannot be completed and delivered within the specified time, and it is necessary to increase production shifts to increase production capacity output, thereby obtaining shift adjustment information.

[0088] Please refer to Figure 5 , Figure 5 The flowchart of the automatic production scheduling method of the smart meter and the collection device based on LLM in some embodiments of the present application is to obtain the production line adjustment information. According to the embodiment of the present invention, the production line adjustment information is obtained as follows:

[0089] S501, comparing the plurality of order demand data to obtain high-demand order information;

[0090] S502, acquiring multiple production line efficiency data within the preset time period and comparing them with each other to obtain high-efficiency production line information;

[0091] S503: Match the high-demand order information with the high-efficiency production line information according to preset rules to obtain production line adjustment information.

[0092] Among them, in order to improve production efficiency, multiple order demand data are compared with each other to obtain high-demand order information, including order number, product type, demand, etc., and multiple production line efficiency data within a preset time period are obtained and compared with each other to obtain high-efficiency production line information, including production line number, location, production capacity, etc. The high-demand order information and high-efficiency production line information are matched according to preset rules to obtain production line adjustment information. The rule is that orders with large quantities are produced on high-efficiency production lines first.

[0093] According to an embodiment of the present invention, the determination of whether the daily utilization rate of the production line meets the requirement is specifically as follows:

[0094] Optimizing the initial instruction information according to the production sequence information, shift adjustment information and production line adjustment information to obtain optimized production scheduling instruction information;

[0095] Extracting daily utilization data of the production line according to the optimized production scheduling instruction information;

[0096] Comparing the daily utilization data of the production line with a preset daily utilization threshold to obtain a daily utilization deviation rate;

[0097] comparing the daily utilization rate deviation rate with a preset daily utilization rate deviation rate threshold;

[0098] If the daily utilization deviation rate is greater than or equal to the daily utilization deviation rate threshold, a low daily utilization rate information of the production line is sent;

[0099] If the daily utilization deviation rate is less than the daily utilization deviation rate threshold, the production line daily utilization qualified information is sent.

[0100] Among them, in order to verify and optimize the initial production scheduling instructions, the initial instruction information is optimized according to the production sequence information, shift adjustment information and production line adjustment information to obtain the optimized production scheduling instruction information, adjust the production sequence to give priority to urgent and high-priority orders, optimize the shift arrangement to improve production efficiency, and reallocate the production lines to maximize production capacity. According to the optimized production scheduling instruction information, the daily utilization data of the production line is extracted and compared with the preset daily utilization threshold, and the daily utilization deviation rate is obtained and then compared with the preset daily utilization deviation rate threshold. If the daily utilization deviation rate is greater than or equal to the daily utilization deviation rate threshold, the low daily utilization information of the production line is sent, which means that the utilization efficiency of the production line is lower than expected, and additional measures need to be taken to improve production efficiency; if the daily utilization deviation rate is less than the daily utilization deviation rate threshold, the qualified daily utilization information of the production line is sent, indicating that the utilization efficiency of the production line is within an acceptable range and can continue to operate according to the current production plan.

[0101] According to an embodiment of the present invention, it also includes:

[0102] Obtain product quality compliance rate data for multiple production lines within the preset time period;

[0103] Comparing the product quality compliance rate with a preset product quality compliance rate threshold, obtaining a quality compliance rate deviation rate;

[0104] Comparing the quality compliance rate deviation rate with a preset quality compliance rate deviation rate threshold;

[0105] If the quality compliance rate deviation rate is greater than or equal to the quality compliance rate deviation rate threshold, the quality compliance rate of the production line product is unqualified.

[0106] If the quality compliance rate deviation rate is less than the quality compliance rate deviation rate threshold, the quality compliance rate qualification information of the production line products is sent.

[0107] Among them, in order to improve the product quality of the production line, the product quality compliance rate data of multiple production lines within a preset time period are obtained and compared with the preset product quality compliance rate threshold, the quality compliance rate deviation rate is obtained and then compared with the preset quality compliance rate deviation rate threshold. If the quality compliance rate deviation rate is greater than or equal to the quality compliance rate deviation rate threshold, then the production line product quality compliance rate unqualified information is sent to notify relevant personnel that there are problems with the production line product quality; if the quality compliance rate deviation rate is less than the quality compliance rate deviation rate threshold, then the production line product quality compliance rate qualified information is sent, indicating that the production line product quality meets the standards.

[0108] According to an embodiment of the present invention, it also includes:

[0109] Acquire the completion time data of the smart meter and the completion time data of the collection device within the preset time period;

[0110] Comparing the completion time data of the smart meter with the completion time data of the acquisition device to obtain completion time difference data;

[0111] Comparing the completion time difference data with a preset difference threshold;

[0112] If the completion time difference data is greater than or equal to the difference threshold, a message indicating that the order completion difference is too large is sent;

[0113] If the completion time difference data is less than the difference threshold, the order completion time normal information is sent.

[0114] Among them, in order to ensure the consistency of the factory time of different products in the order, the completion time data of the smart meter and the completion time data of the collection equipment within the preset time period are obtained and compared with each other, and the completion time difference data is obtained and then compared with the preset difference threshold. If the completion time difference data is greater than or equal to the difference threshold, the order completion difference is too large. Information is sent; if the completion time difference data is less than the difference threshold, the order completion time is normal. Information is sent.

[0115] The present invention also discloses an automatic production scheduling system for smart meters and collection devices based on LLM, comprising a memory and a processor, wherein the memory comprises an automatic production scheduling method program for smart meters and collection devices based on LLM, and when the automatic production scheduling method program for smart meters and collection devices based on LLM is executed by the processor, the following steps are implemented:

[0116] Acquire multiple production demand information and available capacity information within a preset time period and identify and process them through a preset large language model to obtain initial production scheduling instruction information;

[0117] Extracting multiple order level information, delivery cycle data and multiple order demand quantity data according to the initial production scheduling instruction information;

[0118] According to the plurality of order level information, query through a preset production sequence list to obtain production sequence information;

[0119] Obtaining shift adjustment information based on the delivery cycle data and comparing it with a preset delivery cycle threshold;

[0120] Processing the multiple order demand quantity data to obtain production line adjustment information;

[0121] The initial instruction information is optimized according to the production sequence information, shift adjustment information and production line adjustment information to obtain optimized production scheduling instruction information and extract production line daily utilization data, which is then compared with the preset daily utilization threshold to determine whether the production line daily utilization meets the requirements.

[0122] Among them, the present application obtains the initial production scheduling instruction information by obtaining multiple production demand information and available capacity information and identifying and processing them through a preset large language model. The large language model can directly generate production scheduling strategies and production scheduling algorithm codes from natural language descriptions, and quickly output decision suggestions by combining basic information with training knowledge, verify scheduling results, and quickly generate suggestions and adjust strategies, which is more suitable for real-time decision-making. Extract multiple order level information, delivery cycle data, and multiple order demand data according to the initial production scheduling instruction information. Query through the preset production sequence list according to multiple order level information to obtain production sequence information; obtain shift adjustment information according to delivery cycle data and compare with the preset delivery cycle threshold; obtain production line adjustment information according to multiple order demand data. Then optimize the initial instruction information, obtain optimized production scheduling instruction information and extract production line daily utilization data, and finally compare with the preset daily utilization threshold to determine whether the production line daily utilization meets the requirements. This application significantly improves production efficiency and resource utilization, reduces production costs, and enhances customer satisfaction and corporate competitiveness through efficient data processing, refined order management, flexible production sequence adjustment, intelligent shift and production line adjustment, real-time production line utilization monitoring, and optimized production scheduling.

[0123] According to an embodiment of the present invention, the obtaining of initial production scheduling instruction information is specifically:

[0124] Obtain multiple production demand information and available capacity information within a preset time period;

[0125] The production demand information includes demand product type information, demand production quantity information and product demand cycle information;

[0126] The available capacity information includes basic information of the production line, production shift rotation information and basic information of production personnel;

[0127] The initial production scheduling instruction information is obtained by combining the required product type information, required production quantity information and product demand cycle information with the basic information of the production line, production shift rotation information and basic information of production personnel and identifying and processing through a preset large language model.

[0128] Among them, in order to achieve automated and efficient production scheduling, first obtain multiple production demand information and available capacity information within a preset time period. The production demand information includes demand product type information, demand production quantity information and product demand cycle information. The demand product type information clarifies the product type to be produced, such as smart meters, collection equipment, etc.; the demand production quantity information refers to the specific production quantity demand of each product; the product demand cycle information represents the urgency of product demand and the expected delivery cycle. The available capacity information includes production line basic information, production shift rotation information and production personnel basic information. The production line basic information includes production line type, production capacity, equipment status, etc.; production shift rotation information includes working hours, rest time and shift rotation rules; production personnel basic information includes the number of production personnel, skill level, availability, etc. According to the demand product type information, demand production quantity information and product demand cycle information, combined with the production line basic information, production shift rotation information and production personnel basic information and through the preset large language model for identification and processing, the initial production scheduling instruction information is obtained. This large language model can understand and parse production demand and capacity information described in natural language. Through intelligent analysis, it considers factors such as product type, production quantity, demand cycle, production line capacity, shift rotation and staffing, and generates preliminary production scheduling instruction information.

[0129] According to an embodiment of the present invention, obtaining the production sequence information specifically includes:

[0130] Extracting a plurality of order level marking information and a plurality of order placement time data according to the plurality of order level information;

[0131] The order level marking information includes urgent order information, high priority order information, ordinary order information and low priority order information;

[0132] The production sequence information is obtained by querying through a preset production sequence list according to the multiple order level mark information and the multiple order placement time data.

[0133] Among them, multiple order level marking information and multiple order time data are extracted according to multiple order level information, and the order level marking information includes urgent order information, high priority order information, ordinary order information and low priority order information. According to multiple order level marking information and multiple order time data, the preset production sequence list is queried to obtain production sequence information. It should be noted that urgent orders take precedence over high priority orders, high priority orders take precedence over ordinary orders, and ordinary orders take precedence over low priority orders; within the same level, they are sorted from early to late according to order time.

[0134] According to an embodiment of the present invention, obtaining the shift adjustment information specifically includes:

[0135] According to the delivery cycle data and compared with a preset delivery cycle threshold;

[0136] If the delivery cycle data is less than the delivery cycle threshold, the delivery requirements are met;

[0137] If the delivery cycle data is greater than or equal to the delivery cycle threshold, the shift adjustment information is obtained.

[0138] Among them, in order to meet the delivery cycle requirements, the delivery cycle data is compared with the preset delivery cycle threshold. If the delivery cycle data is less than the delivery cycle threshold, the delivery requirements are met; if the delivery cycle data is greater than or equal to the delivery cycle threshold, it means that according to the current production plan and resource allocation, the order cannot be completed and delivered within the specified time, and it is necessary to increase production shifts to increase production capacity output, thereby obtaining shift adjustment information.

[0139] According to an embodiment of the present invention, obtaining the production line adjustment information specifically includes:

[0140] Comparing the plurality of order demand data with each other to obtain high-demand order information;

[0141] Acquire multiple production line efficiency data within the preset time period and compare them with each other to obtain high-efficiency production line information;

[0142] The high-demand order information is matched with the efficient production line information according to preset rules to obtain production line adjustment information.

[0143] Among them, in order to improve production efficiency, multiple order demand data are compared with each other to obtain high-demand order information, including order number, product type, demand, etc., and multiple production line efficiency data within a preset time period are obtained and compared with each other to obtain high-efficiency production line information, including production line number, location, production capacity, etc. The high-demand order information and high-efficiency production line information are matched according to preset rules to obtain production line adjustment information. The rule is that orders with large quantities are produced on high-efficiency production lines first.

[0144] According to an embodiment of the present invention, the determination of whether the daily utilization rate of the production line meets the requirement is specifically as follows:

[0145] Optimizing the initial instruction information according to the production sequence information, shift adjustment information and production line adjustment information to obtain optimized production scheduling instruction information;

[0146] Extracting daily utilization data of the production line according to the optimized production scheduling instruction information;

[0147] Comparing the daily utilization data of the production line with a preset daily utilization threshold to obtain a daily utilization deviation rate;

[0148] comparing the daily utilization rate deviation rate with a preset daily utilization rate deviation rate threshold;

[0149] If the daily utilization deviation rate is greater than or equal to the daily utilization deviation rate threshold, a low daily utilization rate information of the production line is sent;

[0150] If the daily utilization deviation rate is less than the daily utilization deviation rate threshold, the production line daily utilization qualified information is sent.

[0151] Among them, in order to verify and optimize the initial production scheduling instructions, the initial instruction information is optimized according to the production sequence information, shift adjustment information and production line adjustment information to obtain the optimized production scheduling instruction information, adjust the production sequence to give priority to urgent and high-priority orders, optimize the shift arrangement to improve production efficiency, and reallocate the production lines to maximize production capacity. According to the optimized production scheduling instruction information, the daily utilization data of the production line is extracted and compared with the preset daily utilization threshold, and the daily utilization deviation rate is obtained and then compared with the preset daily utilization deviation rate threshold. If the daily utilization deviation rate is greater than or equal to the daily utilization deviation rate threshold, the low daily utilization information of the production line is sent, which means that the utilization efficiency of the production line is lower than expected, and additional measures need to be taken to improve production efficiency; if the daily utilization deviation rate is less than the daily utilization deviation rate threshold, the qualified daily utilization information of the production line is sent, indicating that the utilization efficiency of the production line is within an acceptable range and can continue to operate according to the current production plan.

[0152] According to an embodiment of the present invention, it also includes:

[0153] Obtain product quality compliance rate data for multiple production lines within the preset time period;

[0154] Comparing the product quality compliance rate with a preset product quality compliance rate threshold, obtaining a quality compliance rate deviation rate;

[0155] Comparing the quality compliance rate deviation rate with a preset quality compliance rate deviation rate threshold;

[0156] If the quality compliance rate deviation rate is greater than or equal to the quality compliance rate deviation rate threshold, the quality compliance rate of the production line product is unqualified.

[0157] If the quality compliance rate deviation rate is less than the quality compliance rate deviation rate threshold, the quality compliance rate qualification information of the production line products is sent.

[0158] Among them, in order to improve the product quality of the production line, the product quality compliance rate data of multiple production lines within a preset time period are obtained and compared with the preset product quality compliance rate threshold, the quality compliance rate deviation rate is obtained and then compared with the preset quality compliance rate deviation rate threshold. If the quality compliance rate deviation rate is greater than or equal to the quality compliance rate deviation rate threshold, then the production line product quality compliance rate unqualified information is sent to notify relevant personnel that there are problems with the production line product quality; if the quality compliance rate deviation rate is less than the quality compliance rate deviation rate threshold, then the production line product quality compliance rate qualified information is sent, indicating that the production line product quality meets the standards.

[0159] According to an embodiment of the present invention, it also includes:

[0160] Acquire the completion time data of the smart meter and the completion time data of the collection device within the preset time period;

[0161] Comparing the completion time data of the smart meter with the completion time data of the acquisition device to obtain completion time difference data;

[0162] Comparing the completion time difference data with a preset difference threshold;

[0163] If the completion time difference data is greater than or equal to the difference threshold, a message indicating that the order completion difference is too large is sent;

[0164] If the completion time difference data is less than the difference threshold, the order completion time normal information is sent.

[0165] Among them, in order to ensure the consistency of the factory time of different products in the order, the completion time data of the smart meter and the completion time data of the collection equipment within the preset time period are obtained and compared with each other, and the completion time difference data is obtained and then compared with the preset difference threshold. If the completion time difference data is greater than or equal to the difference threshold, the order completion difference is too large. Information is sent; if the completion time difference data is less than the difference threshold, the order completion time is normal. Information is sent.

[0166] The third aspect of the present invention provides a computer-readable storage medium, which includes an automatic production scheduling method program for smart meters and collection equipment based on LLM. When the automatic production scheduling method program for smart meters and collection equipment based on LLM is executed by a processor, the steps of the automatic production scheduling method for smart meters and collection equipment based on LLM as described in any one of the above items are implemented.

[0167] The automatic production scheduling method, system and medium of the smart meter and collection device based on LLM disclosed in the present invention obtain multiple production demand information and available capacity information and identify and process them through a preset large language model to obtain initial production scheduling instruction information, extract multiple order level information, delivery cycle data and multiple order demand data. According to multiple order level information, query through the preset production sequence list to obtain production sequence information; according to the delivery cycle data and the preset delivery cycle threshold, obtain shift adjustment information; according to the multiple order demand data, process and obtain production line adjustment information. Then optimize the initial instruction information, obtain optimized production scheduling instruction information and extract production line daily utilization data, and finally compare with the preset daily utilization threshold to determine whether the production line daily utilization meets the requirements. This application significantly improves production efficiency and resource utilization, reduces production costs, and improves customer satisfaction and corporate competitiveness through efficient data processing, refined order management, flexible production sequence adjustment, intelligent shift and production line adjustment, real-time production line utilization monitoring and optimized production scheduling.

[0168] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0169] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0170] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0171] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a readable storage medium, which, when executed, executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories, random access memories, magnetic disks or optical disks, and other media that can store program codes.

[0172] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. The automatic production scheduling method of smart meters and collection equipment based on LLM is characterized by: The following steps are involved: Acquire multiple production demand information and available capacity information within a preset time period and identify and process them through a preset large language model to obtain initial production scheduling instruction information; Extracting multiple order level information, delivery cycle data and multiple order demand quantity data according to the initial production scheduling instruction information; According to the plurality of order level information, query through a preset production sequence list to obtain production sequence information; Obtaining shift adjustment information based on the delivery cycle data and comparing it with a preset delivery cycle threshold; Processing the multiple order demand quantity data to obtain production line adjustment information; The initial instruction information is optimized according to the production sequence information, shift adjustment information and production line adjustment information to obtain optimized production scheduling instruction information and extract production line daily utilization data, which is then compared with the preset daily utilization threshold to determine whether the production line daily utilization meets the requirements.

2. The automatic production scheduling method of smart meters and collection equipment based on LLM according to claim 1 is characterized in that: The obtaining of the initial production scheduling instruction information is specifically as follows: Obtain multiple production demand information and available capacity information within a preset time period; The production demand information includes demand product type information, demand production quantity information and product demand cycle information; The available capacity information includes basic information of the production line, production shift rotation information and basic information of production personnel; The initial production scheduling instruction information is obtained by combining the required product type information, required production quantity information and product demand cycle information with the basic information of the production line, production shift rotation information and basic information of production personnel and identifying and processing through a preset large language model.

3. The automatic production scheduling method of smart meters and collection equipment based on LLM according to claim 2 is characterized in that: The obtaining of production sequence information is specifically as follows: Extracting a plurality of order level marking information and a plurality of order placement time data according to the plurality of order level information; The order level marking information includes urgent order information, high priority order information, ordinary order information and low priority order information; The production sequence information is obtained by querying through a preset production sequence list according to the multiple order level mark information and the multiple order placement time data.

4. The automatic production scheduling method of smart meters and data collection equipment based on LLM according to claim 3 is characterized in that: The obtaining of shift adjustment information is specifically as follows: According to the delivery cycle data and compared with a preset delivery cycle threshold; If the delivery cycle data is less than the delivery cycle threshold, the delivery requirements are met; If the delivery cycle data is greater than or equal to the delivery cycle threshold, the shift adjustment information is obtained.

5. The automatic production scheduling method of smart meters and data collection equipment based on LLM according to claim 4 is characterized in that: The obtaining of the production line adjustment information is specifically as follows: Comparing the plurality of order demand data with each other to obtain high-demand order information; Acquire multiple production line efficiency data within the preset time period and compare them with each other to obtain high-efficiency production line information; The high-demand order information is matched with the efficient production line information according to preset rules to obtain production line adjustment information.

6. The automatic production scheduling method of smart meters and data collection equipment based on LLM according to claim 5 is characterized in that: The determination of whether the daily utilization rate of the production line meets the requirements is specifically as follows: Optimizing the initial instruction information according to the production sequence information, shift adjustment information and production line adjustment information to obtain optimized production scheduling instruction information; Extracting daily utilization data of the production line according to the optimized production scheduling instruction information; Comparing the daily utilization data of the production line with a preset daily utilization threshold to obtain a daily utilization deviation rate; comparing the daily utilization rate deviation rate with a preset daily utilization rate deviation rate threshold; If the daily utilization deviation rate is greater than or equal to the daily utilization deviation rate threshold, a low daily utilization rate information of the production line is sent; If the daily utilization deviation rate is less than the daily utilization deviation rate threshold, the production line daily utilization qualified information is sent.

7. The automatic production scheduling system of smart meters and collection equipment based on LLM is characterized by: The invention comprises a memory and a processor, wherein the memory comprises an automatic production scheduling method program of a smart meter and a collection device based on LLM, and when the automatic production scheduling method program of the smart meter and the collection device based on LLM is executed by the processor, the following steps are implemented: Acquire multiple production demand information and available capacity information within a preset time period and identify and process them through a preset large language model to obtain initial production scheduling instruction information; Extracting multiple order level information, delivery cycle data and multiple order demand quantity data according to the initial production scheduling instruction information; According to the plurality of order level information, query through a preset production sequence list to obtain production sequence information; Obtaining shift adjustment information based on the delivery cycle data and comparing it with a preset delivery cycle threshold; Processing the multiple order demand quantity data to obtain production line adjustment information; The initial instruction information is optimized according to the production sequence information, shift adjustment information and production line adjustment information to obtain optimized production scheduling instruction information and extract production line daily utilization data, which is then compared with the preset daily utilization threshold to determine whether the production line daily utilization meets the requirements.

8. The automatic production scheduling system of the smart meter and data collection equipment based on LLM according to claim 7 is characterized in that: The obtaining of the initial production scheduling instruction information is specifically as follows: Obtain multiple production demand information and available capacity information within a preset time period; The production demand information includes demand product type information, demand production quantity information and product demand cycle information; The available capacity information includes basic information of the production line, production shift rotation information and basic information of production personnel; The initial production scheduling instruction information is obtained by combining the required product type information, required production quantity information and product demand cycle information with the basic information of the production line, production shift rotation information and basic information of production personnel and identifying and processing through a preset large language model.

9. The automatic production scheduling system of the smart meter and data collection equipment based on LLM according to claim 8 is characterized in that: The obtaining of production sequence information is specifically as follows: Extracting a plurality of order level marking information and a plurality of order placement time data according to the plurality of order level information; The order level marking information includes urgent order information, high priority order information, ordinary order information and low priority order information; The production sequence information is obtained by querying through a preset production sequence list according to the multiple order level mark information and the multiple order placement time data.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes an automatic production scheduling method, system and medium program for smart meters and collection equipment based on LLM. When the automatic production scheduling method, system and medium program for smart meters and collection equipment based on LLM are executed by a processor, the steps of the automatic production scheduling method for smart meters and collection equipment based on LLM are implemented as described in any one of claims 1 to 6.

Images