Process optimization method and device for traceability of whole process of medicine production and storage medium

Abstract

The invention relates to a process optimization method and device for traceability of a whole pharmaceutical production process and a storage medium. The process optimization method comprises the following steps: establishing a perfect production management system, uniquely identifying raw materials and auxiliary materials, recording production data in real time, establishing a production database, and intelligently optimizing the production process. The step of establishing the perfect production management system comprises system construction and integration and link management module development, and the production management system is composed of an enterprise resource planning (ERP) system and a production execution system (MES) in a cooperative mode. The method has the characteristics that ERP and MES systems are integrated and compatible with GMP requirements, the management quality and efficiency of the whole production chain can be effectively improved, the adopted technical means not only aims at a single link, but also covers the whole production process, and closed-loop management is formed from raw material purchasing to product delivery, so that the transparency of the production process is improved, and the production efficiency is improved. And continuous quality improvement can be realized.

Description

Technical Field

[0001] The present disclosure relates to the technical field of solid dosage drug production, and in particular to a method for optimizing the traceability process of drug production throughout the entire process. Background Art

[0002] Solid dosage drug production is an important part of drug manufacturing, involving various types of drug forms, such as tablets, capsules, granules, etc. This process is complex and requires high precision because it directly affects the quality, efficacy and safety of drugs. However, the existing solid dosage drug production full-process traceability process optimization method cannot predict fluctuations and defects in product quality during use, and cannot diagnose real-time equipment failures and prevent future equipment failures, resulting in more unqualified products and increased scrap rates. In severe cases, it may be necessary to recall products that have already been launched, affecting the company's reputation and economic losses. If equipment problems cannot be detected and resolved in a timely manner, it may lead to a decrease in production efficiency. Frequent downtime and maintenance will lead to production delays, affecting delivery time and customer satisfaction. Summary of the invention

[0003] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and invention title of the present disclosure to avoid blurring the purpose of this section, specification abstract and invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0004] To achieve the above objectives, the present disclosure provides a process optimization method, device and storage medium for full-process traceability of drug production.

[0005] According to a first aspect of an embodiment of the present disclosure, there is provided a process optimization method for full-process traceability of drug production, including: establishing and improving a production management system, uniquely identifying raw materials and excipients, recording production data in real time, establishing a production database, and intelligently optimizing the production process, wherein: the establishment and improvement of the production management system includes system construction and integration and link management module development, the production management system is collaboratively composed of an enterprise resource planning ERP system and a production execution system MES, wherein the ERP system includes a procurement management module, an inventory management module, a production management module, a quality management module, a financial module, a human resources module, and a customer relationship management module, and the MES includes a production scheduling module, an equipment management module, a material tracking and management module, a real-time performance monitoring module, and a data collection and reporting module;

[0006] The unique identification of the raw materials and auxiliary materials includes including detailed information of each batch of raw materials and auxiliary materials in the unique identification, and entering the detailed information of each batch of raw materials and auxiliary materials into the ERP system, wherein the detailed information of each batch of raw materials and auxiliary materials includes one or more of a supplier, a production date, an expiration date, and an inspection report number;

[0007] The real-time recording of production data includes installing sensors and detection equipment at key production links to monitor one or more parameters of temperature, humidity, pressure and stirring speed in real time, and using the MES to automatically collect and record data at the key production links;

[0008] The establishment of the production database includes database construction and production data analysis, wherein the big data analysis technology used in the production data analysis process includes the CART decision tree algorithm; the intelligent optimization of the production process includes establishing a prediction model, predicting equipment failures and quality deviations based on historical data, and implementing preventive measures for the failures and deviations, wherein the prediction model includes a random forest algorithm.

[0009] The system construction and integration include adopting the ERP system to be compatible with the requirements of Good Manufacturing Practice (GMP) for pharmaceutical production, and integrating the MES to achieve real-time monitoring and control of the production process.

[0010] The ERP system realizes the whole process management from raw material procurement, inventory, production batches, finance, human resources to customer relations, and the MES and the ERP system perform data exchange and functional connection through the API interface, and make production decisions based on the interactive data and connected functions.

[0011] The procurement management module is configured to manage purchase orders and delivery schedules using an electronic procurement system, assist in completing procurement contracts and price negotiations, and optimize procurement decisions through data analysis.

[0012] The inventory management module is configured to use an inventory management system including barcode technology to achieve real-time tracking and management of inventory, wherein inventory strategies are adjusted through inventory level analysis and demand forecasting.

[0013] The production management module is configured to use the production scheduling system to optimize production planning and batch management, and to ensure production progress and product quality through real-time monitoring and adjustment of the production process.

[0014] The management module is configured to implement a quality control process including raw material inspection, production process inspection and finished product inspection, and to track and process defective products through a quality traceability system.

[0015] The financial module is configured to integrate financial software to manage costs, budgets, accounting and financial reports, and monitor production costs and budget execution through analysis of financial data.

[0016] The unique identifier includes one or more of a radio frequency identification (RFID) and a two-dimensional code.

[0017] The database construction includes building a special production database and designing a database structure that is easy to query.

[0018] The CART decision tree algorithm includes:

[0019] The construction process, in which the best segmentation feature is selected from the dataset of the current node according to a predetermined criterion, using the Gini index for classification problems and the least squares deviation for regression problems;

[0020] Splitting the data, wherein the data set is split into two or more sub-data sets based on the selected best splitting features and the corresponding feature values;

[0021] Recursively create subtrees, where the same method is used to recursively create a decision tree for each sub-dataset after segmentation;

[0022] Pruning, in which overfitting is avoided by pruning, including removing leaf nodes or subtrees that have little impact on the final prediction and merging similar nodes.

[0023] 12. The process optimization method according to claim 11, wherein:

[0024] The calculation formula of the Gini index is:

[0025]

[0026] Among them, Gini(D) represents the Gini index, D represents the data set, and p i Represents the probability of the i-th category in the data set D;

[0027] And the calculation formula of the Gini index after segmentation is:

[0028]

[0029] Among them, Gini_split represents the Gini index after segmentation, |D| is the total number of samples in the data set D as the parent set, and |D1| and |D2| are the number of samples in the two subsets of the data set D.

[0030] The random forest algorithm includes decision tree construction, which is as follows:

[0031] The information gain calculation formula applied to the first decision tree algorithm is:

[0032]

[0033] Among them, IG(D,p) represents information gain, I represents uncertainty measure, D represents data set, P represents the segmentation point of data features, and D left and D right Represents the segmented sub-dataset;

[0034] And the calculation formula of Gini impurity applied to the second decision tree algorithm is:

[0035]

[0036] Among them, Gini(D) represents the Gini index, pi represents the relative frequency of the i-th category label in the data set D, and k represents the total number of categories.

[0037] The random forest algorithm includes prediction aggregation as follows:

[0038] The calculation formula for the majority voting method for classification problems is:

[0039]

[0040] And the calculation formula of the average method for regression problem is

[0041]

[0042] Among them, n represents the number of decision trees, tree i represents the prediction function of the i-th tree, mode represents the mode of multiple prediction functions, Represents the prediction results of the model.

[0043] According to a second aspect of an embodiment of the present disclosure, a process optimization device for full-process traceability of drug production is provided, comprising: a processor; and a memory storing computer-executable instructions, which, when executed by the processor, enable the processor to execute the process optimization method for full-process traceability of drug production according to the first aspect of an embodiment of the present disclosure.

[0044] According to a third aspect of an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer-executable instructions is provided. When the computer-executable instructions are executed by a processor, the processor enables the processor to implement the process optimization method for full-process traceability of drug production according to the first aspect of an embodiment of the present disclosure.

[0045] According to a fourth aspect of an embodiment of the present disclosure, a computer program product is provided, comprising computer program instructions, which, when executed by a processor, implement the process optimization method for full-process traceability of drug production according to the first aspect of an embodiment of the present disclosure.

[0046] The advantage of the embodiments disclosed herein is that the system for implementing the process optimization method includes the characteristics of ERP and MES system integration and compatibility with GMP requirements, which can effectively improve the management quality and efficiency of the entire production chain. The technical means adopted are not only aimed at a single link, but cover the entire production process, starting from raw material procurement to product delivery, forming a closed-loop management, which improves the transparency of the production process and helps to achieve continuous quality improvement.

[0047] Another advantage of the embodiments of the present disclosure is that the method ensures the real-time and accuracy of the data and improves the scientific nature of the production process control by recording the production data in real time and using sensors and the MES system for automatic monitoring and data collection.

[0048] Another advantage of the embodiments of the present disclosure is that a dedicated production database is established, and big data analysis techniques, such as the CART decision tree algorithm, are used to optimize and analyze the production process, helping to identify production bottlenecks and improve them.

[0049] It should be appreciated that the above advantages do not need to be all realized in one or some specific embodiments, but may be partially dispersed in different embodiments according to the present disclosure. The embodiments according to the present disclosure may have one or some of the above advantages, or may have other advantages alternatively or additionally. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The foregoing and other features and advantages of the present disclosure will become apparent from the following description of the embodiments of the present disclosure in conjunction with the accompanying drawings. The accompanying drawings are incorporated herein and form a part of the specification, and are further used to explain the principles of the present disclosure and enable those skilled in the art to make and use the present disclosure. Among them:

[0051] Figure 1 A flowchart of a process optimization method for full-process traceability of drug production according to an embodiment of the present disclosure is shown;

[0052] Figure 2 An exemplary configuration diagram shows a production management system in a process optimization method for full-process traceability of drug production according to an embodiment of the present disclosure.

[0053] Figure 3 A schematic diagram of the structure of a process optimization device for full-process traceability of drug production according to an embodiment of the present disclosure is shown;

[0054] Figure 4 An exemplary configuration diagram of a computing device implementing an embodiment of the present disclosure is shown.

[0055] Note that in the embodiments described below, sometimes the same reference numerals are used in common between different drawings to represent the same parts or parts with the same functions, and their repeated descriptions are omitted. In some cases, similar numbers and letters are used to represent similar items, so once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0056] For ease of understanding, the position, size, range, etc. of each structure shown in the drawings and the like may not represent the actual position, size, range, etc. Therefore, the present disclosure is not limited to the position, size, range, etc. disclosed in the drawings and the like. DETAILED DESCRIPTION

[0057] Various exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure.

[0058] The following description of at least one exemplary embodiment is in fact merely illustrative and is in no way intended to limit the present disclosure and its application or use. That is, the structures and methods herein are shown in an exemplary manner to illustrate different embodiments of the structures and methods in the present disclosure. However, those skilled in the art will appreciate that they merely illustrate exemplary ways of the present disclosure that can be implemented, rather than exhaustive ways. In addition, the drawings need not be drawn to scale, and some features may be enlarged to illustrate the details of specific components.

[0059] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0060] In order to solve the possible fluctuations and defects in the traceability of the production process of solid dosage drugs, the present disclosure provides a process optimization method for the traceability of the entire process of drug production, in which a system for monitoring and managing the drug production process is designed and integrated, and a unique identification code is assigned to the raw materials and / or excipients involved in the production process, and the data of each production link is recorded in real time and stored in the production database, and a prediction model is established through a variety of algorithms to realize intelligent optimization of the production process, thereby realizing the traceability of the entire process of drug production. The system and the full-process traceability process optimization method implemented by it can effectively improve the management efficiency of the production chain, enhance its transparency and improve its quality in the closed-loop management of the production process.

[0061] For more information, see Figure 1 , Figure 1 The flowchart of the whole process traceability process optimization method for drug production is shown. In step S101, a complete production management system is established, and specifically includes system construction and integration and link management module development. Figure 2 , which shows an exemplary configuration diagram of an integrated production management system. In the field of pharmaceutical production, the construction and integration of the system mainly adopts the requirements of the Enterprise Resource Planning (ERP: Enterprise Resource Planning) system 10 compatible with the Good Manufacturing Practice of Medical Products (GMP: Good Manufacturing Practice of Medical Products) to achieve full process management from raw material procurement to product delivery, and integrates the Manufacturing Execution System (MES: Manufacturing Execution System) 20 to achieve real-time monitoring and control of the production process. Data interaction and functional connection are carried out between the ERP system 10 and the MES system 20 through the API interface 120, and production decisions are made based on the interactive data and connected functions.

[0062] In some embodiments, the ERP system 10 can be customized according to the characteristics of the corresponding drug production to ensure that the ERP system can cover the full process management from drug raw material procurement, inventory, production batches, finance, human resources to customer relations, and correspondingly set up a procurement management module 1010, inventory management module 1020, production management module 1030, quality management module 1040, financial module 1050, human resources module 1060 and customer relationship management module 1070, etc.

[0063] In particular, the procurement management module configuration 1010 is configured to use the electronic procurement system to manage purchase orders and delivery schedules, assist in completing purchase contracts and price negotiations, and optimize procurement decisions through data analysis. The production process of drugs begins with the procurement of raw materials, where detailed information in the purchase order needs to be checked in the electronic procurement system to ensure the compliance of suppliers. Optimized procurement decisions help reduce the inventory cost of raw materials to ensure the quality of raw materials and the continuity of supply.

[0064] Additionally or alternatively, the inventory management module 1020 is configured to use an inventory management system to achieve real-time tracking and management of inventory, wherein inventory strategies are adjusted through inventory level analysis and demand forecasting. The inventory management system uses, for example, barcode technology to register and store information on raw materials, auxiliary materials, and finished products, thereby tracking the location and flow of inventory. Instantly adjusting inventory strategies in response to demand forecasts, shelf life of raw materials or auxiliary materials, and other constraints helps to avoid excess or out-of-stock situations and optimize the inventory management process.

[0065] Additionally or alternatively, the production management module 1030 is configured to use a production scheduling system to optimize production planning and batch management, and to ensure production progress and product quality through real-time monitoring and adjustment of the production process, thereby ensuring the efficiency and compliance of the production process.

[0066] Additionally or alternatively, the quality management module 1040 is configured to implement a quality control process including raw material inspection, production process inspection and finished product inspection, and track and handle defective products through a quality traceability system to ensure that product quality meets specified standards.

[0067] Additionally or alternatively, the financial module 1050 is configured to integrate financial software to manage costs, budgets, accounting, and financial reports, and monitor production costs and budget execution through analysis of financial data.

[0068] In some embodiments, the MES system 20 is integrated to achieve real-time monitoring and control of the production process, including raw material inventory management, production batch management, quality control, product tracking and tracing, etc., and corresponding link management modules are developed and deployed, including a production scheduling module 2010, an equipment management module 2020, a material tracking and management module 2030, a real-time performance monitoring module 2040, and a data collection and reporting module 2040, etc.

[0069] In particular, the production scheduling module 2010 is configured to determine and manage the production plan of each batch based on the production scheduling system, adjust the flow of production materials such as raw materials and auxiliary materials, and use or manage personnel between different production links, and interact with the production management module 1030 to realize the update and change of the production plan.

[0070] Additionally or alternatively, the equipment management module 2020 is configured to manage the equipment used in the drug production process, record and update the usage status of the equipment in real time, including such as in use, adjustment, repair, etc., and interact with the inventory management module 1020 to achieve demand forecasting and adjust inventory accordingly.

[0071] Additionally or alternatively, the material tracking and management module 2030 is configured to track the production process based on labels or identification codes assigned to production materials, and to interact with the raw material procurement module 1010 based on material requirements during the production process.

[0072] Return to reference Figure 1 In step S102, the raw materials and auxiliary materials are uniquely identified. Specifically, the unique identification may include, but is not limited to, generating a unique identification code for each batch of raw materials or auxiliary materials based on radio frequency identification RFID and two-dimensional code technology. The unique identification of each batch contains detailed information on the raw materials and auxiliary materials, and these detailed information are entered into a database such as the inventory management module 1020 (and / or the production management module 1030, etc.) of the ERP system 10. The information includes the supplier, production date, validity period, and inspection report number, etc. The detailed information corresponding to the unique identification is updated in real time with the production process to ensure the accuracy and completeness of the information.

[0073] In step S103, the production data is recorded in real time. The production management system installs sensors and detection equipment in key production links to monitor parameters such as temperature, humidity, pressure and stirring speed in real time. Furthermore, the MES system 20 is used to automatically collect and record these data in key production links of the production process, thereby ensuring the real-time and accuracy of the data and avoiding human errors.

[0074] In step S104, a production database is established, which includes database construction and production data analysis. Specifically, database construction mainly involves building a special production database to ensure secure storage and fast access to data, and designing an easy-to-query database structure to facilitate analysis and processing. Production data analysis mainly involves using big data analysis technology to conduct in-depth analysis of the collected production data, thereby identifying bottlenecks and deficiencies in the production process and providing a basis for improvement.

[0075] In some embodiments, the big data analysis technology may specifically include the CART decision tree algorithm. The specific algorithm includes a construction process, segmentation data, recursive creation of subtrees, and pruning. Among them, the construction process includes selecting the best segmentation features and points, and selecting the best segmentation features from the data set of the current node according to predetermined criteria, such as using the Gini index for classification problems and using the least squares deviation for regression problems. Segmenting the data includes segmenting the data set into two or more sub-data sets based on the selected best segmentation features and corresponding feature values. Recursive creation of subtrees mainly includes recursively creating a decision tree for each sub-data set after segmentation using the same method. And finally, overfitting is avoided by pruning, including strategies such as removing leaf nodes or subtrees that have little effect on the final prediction, and merging similar nodes.

[0076] Generally speaking, the calculation formula of the Gini index is:

[0077]

[0078] Among them, Gini(D) represents the Gini index, D represents the data set, and p i represents the probability of the i-th category in the data set D. In this case, for each split point, it is necessary to calculate the Gini index of each subset and find the features and split points that minimize the sum of the weighted Gini index. The calculation formula of the Gini index after splitting is:

[0079]

[0080] Among them, Gini_split represents the Gini index after segmentation, |D| is the total number of samples in the data set D as the parent set, and |D1| and |D2| are the number of samples in the two subsets of the data set D.

[0081] Further, continue to refer to Figure 1 In step S105, the production process is intelligently optimized. A prediction model is established to predict possible problems such as equipment failure and quality deviation based on historical data; and preventive measures are implemented for these problems to reduce production interruptions and defective rates. Specifically, in the use of historical data to establish a prediction model to predict possible problems, the prediction model includes a random forest algorithm, in which the decision tree construction can adopt different decision tree algorithms that meet the specific context of the production process, such as:

[0082] When applied to decision tree algorithms such as ID3 and C4.5, the information gain is calculated using the formula:

[0083]

[0084] Among them, IG(D,p) represents information gain, I represents uncertainty measure, D represents data set, P represents the segmentation point of data features, and D left and D right Represents the sub-dataset after segmentation.

[0085] Alternatively, when applied to the CART decision tree algorithm, the Gini impurity is calculated as follows:

[0086]

[0087] Among them, Gini(D) represents the Gini index, pi represents the relative frequency of the i-th category label in the data set D, and k represents the total number of categories.

[0088] Additionally, establishing a prediction module also includes predicting and aggregating discrete data such as equipment failures and / or quality deviations in the production process. For classification problems, the prediction aggregation method of random forest is the majority voting method, and its calculation formula is:

[0089]

[0090] For regression problems, the average method is used, and its calculation formula is:

[0091]

[0092] Among them, n represents the number of decision trees, tree i represents the prediction function of the i-th tree, mode represents the mode of multiple prediction functions, Represents the prediction results of the model.

[0093] Based on this, the prediction model aggregates the predictions of classification problems and / or regression problems to obtain analysis results of equipment failures and quality deviations in the drug production process. Furthermore, the production management system implements necessary preventive measures based on these analysis results, and adjusts and optimizes the production process to continuously improve production efficiency and product quality.

[0094] In a non-limiting embodiment, taking the granulation process, tableting operation and coating process in the production process of the drug as an example, the production management system monitors the production links corresponding to these processes in the specific implementation. Specifically, sensors are used in the granulation process to monitor the rotation speed of the granulator cutter and the mixing knife, such as ensuring that they operate within the optimal range of 2000-3000rpm; record the granulation time to control the particle size and uniformity, such as ensuring that the granulation time is 30-45 minutes for a specific tablet; monitor the drying temperature to prevent the material from overheating or incomplete drying, such as ensuring that the drying temperature is controlled at 60-70°C.

[0095] Additionally or alternatively, a detection device is installed during the tableting operation to monitor the main pressure and the tablet press speed to ensure the stability of the tableting process, such as the main pressure should be maintained at 15-25 MPa and the tablet press speed should be 20-30 rpm; tablet weight, hardness, tablet thickness, friability and disintegration time should be checked regularly to verify the tableting quality, such as ensuring that the tablet weight is controlled at 100-120 mg and the hardness is 5-7 kg / cm 2 The tablet thickness is 2-4 mm, the friability should be less than 1%, and the disintegration time is within 15-30 minutes.

[0096] Additionally or alternatively, sensors or detection equipment are provided in the coating process to monitor the spray volume, atomization pressure and coating machine speed to control the uniformity and quality of the coating, such as ensuring that the spray volume is 5-10 ml / tablet, the atomization pressure is 0.5-1.0 bar, and the coating machine speed is 50-70 rpm; and the temperature is controlled to prevent the material from being deformed or damaged during the coating process, such as ensuring that the temperature is controlled at 20-25°C.

[0097] Based on this, the quality control performed in the key production links in the whole production process can include combining the above monitoring data, applying data analysis and / or machine learning algorithms to predict and optimize potential problems in the production process. At the same time, real-time quality control is implemented, and samples are regularly taken for dissolution, content uniformity and other tests to ensure that the product meets the corresponding quality standards at each link in the entire production process.

[0098] In another non-limiting embodiment, the intelligent optimization process of step S105 can also be implemented based on a simulation data test model. Specifically, firstly, data is constructed for a simplified drug production process, wherein key parameters include temperature, pressure, humidity, machine running time, etc. These parameters are used as characteristic variables to construct data, as shown in Table 1 below:

[0099] Table 1: Data structure of key parameters

[0100] It should be understood that Table 1 only shows an example of three sets of data, and the data structure can contain any specified number of arrays according to the requirements of the data test model.

[0101] Furthermore, data processing such as data cleaning and feature engineering is performed. Data cleaning includes removing outliers, missing values, data standardization or normalization, etc., to facilitate subsequent model processing; feature engineering includes extracting time series features (such as day, week, month, etc.) and creating interactive features (such as temperature*humidity, etc.).

[0102] Further, data prediction is performed, in which the trained model is used to predict new data, such as inputting new feature variables to obtain predicted values ​​when predicting future temperature changes, as shown in Table 2 below:

[0103]

[0104] Table 2: Data prediction for temperature changes

[0105] Based on the analysis results of Table 2, it is concluded that temperature and humidity have a significant impact on product quality. Therefore, it is necessary to control the parameters within a specific range during the production process to ensure product quality; at the same time, suggestions for improving the production environment can also be made based on the prediction results of the data test model, such as adjusting the temperature and humidity control system to improve the consistency of product quality.

[0106] It should be understood that Figure 1 The division of each step in the diagram is only for illustration and not for limitation of the embodiments. These steps can be completed by each subject of the production management system individually, by two or more of them together, or by an external system not shown in the figure in cooperation with the subject of the diagram, and are not limited to the distribution method shown in the figure, and can be completed in sequence according to the order shown in the figure or in parallel in accordance with the data flow direction and system operation rules, and can be completed in steps or in combination.

[0107] Please refer to the following Figure 3 , Figure 3 The schematic diagram of the structure of the process optimization device 3000 for the whole process traceability of drug production according to an embodiment of the present disclosure is shown. The device 3000 may include a processor 3010 and a memory 63020 storing computer executable instructions, which, when executed by the processor 3010, enables the processor 3010 to perform such as Figure 1 The process optimization method shown. Generally, the processor 3010 can be a central processing unit (CPU) of the device 3000, which can be any type of general-purpose processor, or can be a processor specially designed for NTN configuration parameter adjustment, such as an application-specific integrated circuit ("ASIC"). The memory 3020 can include various computer-readable media that can be accessed by the processor 3010.

[0108] The present disclosure also provides a non-transitory computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, enables the processor to implement a process optimization method for full-process traceability of drug production according to any of the aforementioned embodiments of the present disclosure.

[0109] The present disclosure also provides a computer program product, including computer executable instructions, which, when executed by a processor, enable the processor to implement the process optimization method for full-process traceability of drug production according to any of the aforementioned embodiments of the present disclosure.

[0110] Figure 4An exemplary configuration of a computing device that can implement an embodiment of the present disclosure is shown. The computing device includes one or more processors 401, an input / output interface 405 connected to the processor 401 via a bus 404, and memories 402 and 403 connected to the bus 404. In some embodiments, the memory 402 may be a read-only memory (ROM), and the memory 403 may be a random access memory (RAM).

[0111] Processor 401 may be any kind of processor, and may include, but is not limited to, one or more general-purpose processors or special-purpose processors (such as special-purpose processing chips). Memories 402 and 403 may be any non-transitory storage device that can implement data storage, and may include, but is not limited to, disk drives, optical storage devices, solid-state memories, floppy disks, flexible disks, hard disks, tapes or any other magnetic media, compressed disks or any other optical media, cache memories and / or any other storage chips or modules, and / or any other media from which a computer can read data, instructions and / or codes.

[0112] The bus 404 may include, but is not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an Enhanced ISA (EISA) bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0113] In some embodiments, the input / output interface 405 is connected to an input unit 406 configured by an input device such as a keyboard and a mouse for a user to input an operation command, an output unit 407 that outputs a processing operation screen and an image of a processing result to a display device, a storage unit 408 including a hard disk drive and the like for storing programs and various data, and a communication unit 409 including a local area network (LAN) adapter and the like and performing communication processing via a network represented by the Internet. In addition, a drive 410 that reads and writes data from and on a removable storage medium 411 is connected.

[0114] Various aspects, embodiments, implementations or features of the foregoing embodiments may be used alone or in any combination. Various aspects of the foregoing embodiments may be implemented by software, hardware or a combination of hardware and software.

[0115] For example, the foregoing embodiments may be embodied as computer readable code on a computer readable medium. A computer readable medium is any data storage device that can store data that can thereafter be read by a computer system. Examples of computer readable media include read-only memory, random access memory, CD-ROM, DVD, magnetic tape, hard drive, solid state drive, and optical data storage device. The computer readable medium may also be distributed in a network coupled computer system so that the computer readable code is stored and executed in a distributed manner.

[0116] For example, the aforementioned embodiments may be in the form of hardware circuits. The hardware circuits may include any combination of combinational logic circuits, clock storage devices (such as floppy disks, flip-flops, latches, etc.), finite state machines, memories such as static random access memories or embedded dynamic random access memories, custom designed circuits, programmable logic arrays, etc.

[0117] In one embodiment, hardware circuits according to the present disclosure may be implemented by coding and designing one or more integrated circuits using a hardware description language (HDL) such as Verilog or VHDL, or in combination using discrete circuits.

[0118] The terms used herein are only for describing specific exemplary embodiments and are not intended to limit the present disclosure. Unless the context clearly indicates otherwise, the singular forms of "one" and "the" used herein are intended to include plural forms as well. It should also be understood that when the word "including" is used in this article, it indicates the existence of the indicated features, wholes, steps, operations, units and / or components, but does not exclude the existence or increase of one or more other features, wholes, steps, operations, units and / or components and / or their combinations. In addition, in the description of the present disclosure, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or order. In addition, in the description of the present disclosure, unless otherwise specified, the meaning of "multiple" is two or more.

[0119] References to "embodiments" or similar expressions in this specification refer to specific features, structures, or characteristics described in conjunction with the embodiment as included in at least one specific embodiment of the present disclosure. Therefore, the appearance of "in an embodiment of the present disclosure" and similar expressions in this specification does not necessarily refer to the same embodiment.

[0120] Those skilled in the art will appreciate that the present disclosure may be implemented in various forms, such as a complete hardware embodiment, a complete software embodiment (including firmware, resident software, microprogram code, etc.), or a combination of software and hardware, which will be referred to below as a "circuit," "module," "unit," or "system." In addition, the present disclosure may also be implemented in any tangible media form as a computer program product having a computer-usable program code stored thereon.

[0121] The relevant description of the present disclosure is described with reference to the flowchart and / or block diagram of the system, device, method and computer program product according to the specific embodiment of the present disclosure. It can be understood that each block in each flowchart and / or block diagram, and any combination of blocks in the flowchart and / or block diagram, can be implemented using computer program instructions. These computer program instructions can be executed by a machine composed of a processor of a general-purpose computer or a special computer or other programmable data processing device, and the instructions are processed by a computer or other programmable data processing device to implement the functions or operations described in the flowchart and / or block diagram.

[0122] The accompanying drawings show the flow charts and block diagrams of the architecture, functions and operations that can be implemented by the systems, devices, methods and computer program products according to various embodiments of the present disclosure. Therefore, each block in the flow chart or block diagram can represent a module, segment, or part of the program code, which includes one or more executable instructions to implement the specified logical function. It should also be noted that in some other embodiments, the functions described in the blocks may not be performed in the order shown in the figure. For example, two blocks connected to each other in the figure can actually be executed simultaneously, or in some cases according to the functions involved, they can also be executed in the opposite order of the icons. It should also be noted that each block diagram and / or flow chart block, as well as the combination of blocks in the block diagram and / or flow chart, can be implemented by a system based on special hardware, or by a combination of special hardware and computer instructions to perform specific functions or operations.

[0123] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to market technologies, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A process optimization method for full-process traceability of drug production, comprising: Establish and improve the production management system, uniquely identify raw materials and auxiliary materials, record production data in real time, establish a production database, and intelligently optimize the production process, including: The establishment and improvement of the production management system includes system construction and integration and link management module development. The production management system is composed of an enterprise resource planning ERP system and a production execution system MES. The ERP system includes a procurement management module, an inventory management module, a production management module, a quality management module, a financial module, a human resources module and a customer relationship management module. The MES includes a production scheduling module, an equipment management module, a material tracking and management module, a real-time performance monitoring module and a data collection and reporting module. The unique identification of the raw materials and auxiliary materials includes including detailed information of each batch of raw materials and auxiliary materials in the unique identification, and entering the detailed information of each batch of raw materials and auxiliary materials into the ERP system, wherein the detailed information of each batch of raw materials and auxiliary materials includes one or more of a supplier, a production date, an expiration date, and an inspection report number; The real-time recording of production data includes installing sensors and detection equipment at key production links to monitor one or more parameters of temperature, humidity, pressure and stirring speed in real time, and using the MES to automatically collect and record data at the key production links; The establishment of the production database includes database construction and production data analysis, wherein the big data analysis technology used in the production data analysis process includes the CART decision tree algorithm; and, The intelligent optimization of the production process includes establishing a prediction model, predicting equipment failures and quality deviations based on historical data, and implementing preventive measures for the failures and the deviations, wherein the prediction model includes a random forest algorithm.

2. The process optimization method according to claim 1, wherein the system construction and integration includes adopting the ERP system to be compatible with the requirements of the Good Manufacturing Practice (GMP) for pharmaceutical production, and integrating the MES to achieve real-time monitoring and control of the production process.

3. The process optimization method according to claim 2, wherein the ERP system realizes the whole process management from raw material procurement, inventory, production batches, finance, human resources to customer relations, and the MES and the ERP system perform data exchange and functional connection through an API interface, and make production decisions based on the interactive data and connected functions.

4. The process optimization method according to any one of claims 1 to 3, wherein the procurement management module is configured to use an electronic procurement system to manage procurement orders and delivery schedules, assist in completing procurement contracts and price negotiations, and optimize procurement decisions through data analysis.

5. The process optimization method according to any one of claims 1 to 3, wherein the inventory management module is configured to adopt an inventory management system including barcode technology to achieve real-time tracking and management of inventory, wherein the inventory strategy is adjusted through inventory level analysis and demand forecasting.

6. The process optimization method according to any one of claims 1 to 3, wherein the production management module is configured to use a production scheduling system to optimize production planning and batch management, and to ensure production progress and product quality through real-time monitoring and adjustment of the production process.

7. The process optimization method according to any one of claims 1 to 3, wherein the quality management module is configured to implement a quality control process including raw material inspection, production process inspection and finished product inspection, and track and handle defective products through a quality traceability system.

8. The process optimization method according to any one of claims 1 to 3, wherein the financial module is configured to integrate financial software to manage costs, budgets, accounting and financial reports, and monitor production costs and budget execution by analyzing financial data. 9 . The process optimization method according to claim 1 , wherein the unique identifier comprises one or more of a radio frequency identification (RFID) and a two-dimensional code.

10. The process optimization method according to claim 1, wherein the database construction includes building a special production database and designing a database structure that is easy to query.

11. The process optimization method according to claim 1, wherein the CART decision tree algorithm comprises: The construction process, in which the best segmentation feature is selected from the dataset of the current node according to a predetermined criterion, using the Gini index for classification problems and the least squares deviation for regression problems; Splitting the data, wherein the data set is split into two or more sub-data sets based on the selected best splitting features and the corresponding feature values; Recursively create subtrees, where the same method is used to recursively create a decision tree for each sub-dataset after segmentation; Pruning, in which overfitting is avoided by pruning, including removing leaf nodes or subtrees that have little impact on the final prediction and merging similar nodes.

12. The process optimization method according to claim 11, wherein: The calculation formula of the Gini index is: Among them, Gini(D) represents the Gini index, D represents the data set, and p i Represents the probability of the i-th category in the data set D; And the calculation formula of the Gini index after segmentation is: Among them, Gini_split represents the Gini index after segmentation, |D| is the total number of samples in the data set D as the parent set, and |D1| and |D2| are the number of samples in the two subsets of the data set D.

13. The process optimization method according to claim 1, wherein the random forest algorithm comprises decision tree construction, wherein: The information gain calculation formula applied to the first decision tree algorithm is: Among them, IG(D,p) represents information gain, I represents uncertainty measure, D represents data set, P represents the segmentation point of data features, and D left and D right Represents the segmented sub-dataset; And the calculation formula of Gini impurity applied to the second decision tree algorithm is: Among them, Gini(D) represents the Gini index, pi represents the relative frequency of the i-th category label in the data set D, and k represents the total number of categories.

14. The process optimization method according to claim 1, wherein the random forest algorithm comprises prediction aggregation, wherein: The calculation formula for the majority voting method for classification problems is: And the calculation formula of the average method for regression problem is Among them, n represents the number of decision trees, tree i represents the prediction function of the i-th tree, mode represents the mode of multiple prediction functions, Represents the prediction results of the model.

15. A process optimization device for full-process traceability of drug production, comprising: processor; as well as A memory storing computer executable instructions, wherein when the computer executable instructions are executed by the processor, the processor executes the process optimization method for full-process traceability of drug production according to any one of claims 1 to 14.

16. A non-transitory computer-readable storage medium storing computer-executable instructions, wherein when the computer-executable instructions are executed by a processor, the processor implements the process optimization method for full-process traceability of drug production as described in any one of claims 1 to 14.

17. A computer program product, comprising computer executable instructions, which, when executed by a processor, enable the processor to implement the process optimization method for full-process traceability of drug production as described in any one of claims 1 to 14.

Images