A medicine production quality risk management and control method, device, system and storage medium

Abstract

The application discloses a medicine production quality risk management and control method, device and system and a storage medium, and belongs to the technical field of medicine production risk control. The medicine production quality risk management and control method comprises the following steps: monitoring a production environment area in real time and acquiring monitoring data of monitoring points; determining risk points according to the monitoring data; generating prompt information based on the risk points to determine corresponding investigators; acquiring investigation test results corresponding to the investigation tests; and obtaining risk management and control results corresponding to the production environment area according to the investigation test results and the monitoring data. Through real-time monitoring, accurate identification of risk points, personalized investigation prompts, comprehensive analysis and risk management and control result generation, effective management and control of quality risks in the medicine production process are realized, production efficiency and product quality are improved, and the safety and reliability of medicines are ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pharmaceutical production risk control, and particularly relates to a pharmaceutical production quality risk management and control method and device and a storage medium. BACKGROUND

[0002] Pharmaceutical quality and risk management is a core link in the pharmaceutical industry, and its importance not only lies in ensuring patient medication safety, but also is a key to enterprise sustainable development and market competitiveness. With the rapid development of the pharmaceutical industry, the types of drugs are increasing, and the production process is becoming more complex, which makes the quality control and risk management of drugs face more challenges. Traditional quality management and risk assessment often rely on manual operation, which is not only low in efficiency, but also easily disturbed by human factors, leading to untimely and inaccurate risk identification and processing.

[0003] The existing pharmaceutical production units generally use manual methods to discover and investigate risk points when conducting risk and quality management. This process usually involves multiple links, including risk identification, cause analysis, problem solving, etc. However, due to the limitations of manual operation, this method has many shortcomings. First, manual identification of risk points often requires a lot of time and effort, and is easily limited by individual experience and knowledge level, leading to incomplete and inaccurate risk identification. Secondly, the layer-by-layer manual arrangement in the risk investigation process prolongs the problem solving period, affecting the efficiency of drug production and market response speed. In addition, with the continuous expansion of drug types and production scale, the number of risk points and quality problems managed by manual methods increases, and the cost of manual management also increases, which brings a large economic burden to enterprises.

[0004] In the existing technical system, one of the main problems faced by pharmaceutical production units is the efficiency and accuracy of risk management. Due to the reliance on manual operation, the process of discovering and investigating risk points is tedious and time-consuming, which not only affects the continuity and stability of drug production, but also increases the operating costs of enterprises. At the same time, the subjectivity and uncertainty of manual operation may also lead to errors in risk assessment, thereby affecting the quality and safety of drugs.

[0005] In addition, the existing pharmaceutical quality and risk management technology also shows its limitations in dealing with complex and variable production environments. With the progress of science and technology and the diversification of market demand, more and more variables are involved in the production process of drugs, and traditional manual management methods are difficult to adapt to such changes, making it difficult to achieve rapid response and effective control of risks. This not only affects the quality and efficacy of drugs, but also may pose a potential threat to patients' health.

[0006] In summary, the existing drug quality and risk management techniques have obvious deficiencies in efficiency, accuracy, cost control, and adaptability. These defects not only affect the economic benefits of drug production, but also pose challenges to the safety and reliability of drugs. Therefore, it is urgent to develop more efficient, accurate, economic, and adaptable drug quality and risk management control techniques to meet the development needs of the modern pharmaceutical industry. SUMMARY

[0007] In a first aspect, the present application provides a drug production quality risk management method, which monitors a production environment area in real time and obtains monitoring data corresponding to monitoring points of the production environment area;

[0008] According to the monitoring data, a risk point is determined;

[0009] Based on the risk point, a corresponding investigator is determined, prompt information for the investigator to conduct an investigative test is generated, and an investigative test result corresponding to the investigative test is obtained;

[0010] According to the investigative test result and the monitoring data, a risk management result corresponding to the production environment area is obtained.

[0011] In an optional embodiment, the monitoring data corresponding to the monitoring points of the production environment area is obtained, including:

[0012] Based on the production environment area, a detection sample corresponding to the monitoring point is obtained;

[0013] The detection sample is detected to obtain detection data, a corresponding processing workstation is determined according to the detection data, and raw data is obtained through the processing workstation;

[0014] According to the raw data, the monitoring data is obtained by calculation.

[0015] In an optional embodiment, the monitoring point in the production environment area is a drug extraction device; the drug extraction device includes a plurality of movable sampling devices in a drug extraction tank; wherein the movable sampling device includes a sampling body and a temperature probe arranged on the sampling body;

[0016] The detection sample corresponding to the monitoring point is obtained based on the production environment area, including:

[0017] The temperature data in the drug extraction tank and the spatial coordinates corresponding to the temperature data are obtained through the temperature probe of the movable sampling device;

[0018] Based on the spatial coordinates, a data matrix corresponding to the drug extraction tank is constructed according to the temperature data;

[0019] Based on the data matrix, a temperature uniformity zone within the drug extraction tank is determined;

[0020] Based on the coordinate range corresponding to the uniform temperature region, the movable sampling device is moved within the coordinate range to obtain the test sample.

[0021] In an optional implementation, moving the movable sampling device within the coordinate range corresponding to the temperature uniformity region to obtain the test sample includes:

[0022] The volume of the temperature uniform region is calculated based on the coordinate range corresponding to the temperature uniform region.

[0023] The number of sampling points in the temperature uniform region is calculated based on the volume.

[0024] The number of sampling points is calculated using the following formula:

[0025]

[0026] Where n represents the number of sampling points; k represents an empirical coefficient; and A represents the volume of the temperature uniformity region.

[0027] Based on the number of sampling points, n sampling coordinate points are generated according to the coordinate range, and the movable sampling device is controlled to move within the coordinate range and sample at the sampling coordinate points to obtain the test specimen.

[0028] In an optional implementation, determining the risk points based on the monitoring data includes:

[0029] Calculate the median of the monitoring data corresponding to the monitoring point, and obtain the absolute median difference;

[0030] The Modified Z-Score is calculated based on the absolute median difference and the median; the formula for calculating the Modified Z-Score is as follows:

[0031]

[0032] Where, x i This represents the i-th monitoring data; The median is represented by MAD; the absolute median difference is represented by MAD.

[0033] If the monitoring data x i If the absolute value of the corresponding Modified Z-Score is greater than 3.5, the monitoring data will be excluded as an outlier.

[0034] If the monitoring data x i If the absolute value of the corresponding Modified Z-Score is not greater than 3.5, then the monitoring data is considered a normal value.

[0035] The average value of the monitoring data, which is considered as a normal value, is obtained by averaging the monitoring average value, and then the monitoring average value is compared with a preset threshold range.

[0036] If the average value of the monitoring exceeds the preset threshold range, then the monitoring point is designated as the risk point.

[0037] In an optional implementation, the step of determining the corresponding investigator based on the risk point and generating a prompt message for conducting an investigative test on the investigator includes:

[0038] Based on the risk points, action item information is generated, and the investigators corresponding to the risk points are identified;

[0039] Write the action item information into the investigator's action list;

[0040] Using the action item information for the risk point in the action list as the current information, and using other action item information that is different from the current information as comparison information; obtain the current information and the creation time of the action information for the same risk point in the action list;

[0041] Determine whether there is any comparison information in the action list whose creation time interval with the current information is less than a preset time threshold;

[0042] If so, the current information and comparison information for the same risk point whose establishment time interval is less than a preset time threshold will be merged into one action item information, and the prompt information will be generated.

[0043] In an optional implementation, obtaining the risk control result corresponding to the production environment area based on the survey and test results and the monitoring data includes:

[0044] Compare the survey and test results with the monitoring data;

[0045] The error value is calculated using the following formula:

[0046] E = |x s -x h |;

[0047] Where E represents the error value; x s Represents the monitoring data; x h This represents the results of the survey and testing.

[0048] Compare E with the error threshold T;

[0049] If E≤T, then the data is considered to match, and the risk control result indicates that there is a risk.

[0050] If E > T, it is determined that the data does not match, the risk control result is that the data is questionable, and the execution steps are reversed to obtain the monitoring data corresponding to the monitoring points of the production environment area.

[0051] Secondly, the present invention provides a drug production quality risk control device, comprising:

[0052] The acquisition module is used to monitor the production environment area in real time and acquire the monitoring data corresponding to the monitoring points in the production environment area.

[0053] The determination module is used to determine risk points based on the monitoring data;

[0054] The acquisition module is further configured to determine the corresponding investigator based on the risk point, generate a prompt message for conducting an investigative test on the investigator, and acquire the investigative test results corresponding to the investigative test.

[0055] The output module is used to obtain the risk control results corresponding to the production environment area based on the survey and test results and the monitoring data.

[0056] Thirdly, the present invention provides a pharmaceutical production quality risk control system, including a memory and a processor. The memory stores a pharmaceutical production quality risk control program, and the processor runs the pharmaceutical production quality risk control program to enable the pharmaceutical production quality risk control system to perform the pharmaceutical production quality risk control method as described in any of the foregoing embodiments.

[0057] Fourthly, the present invention provides a computer-readable storage medium storing a drug production quality risk control program, wherein the drug production quality risk control program, when executed by a processor, implements the drug production quality risk control method as described in any of the foregoing embodiments.

[0058] The drug manufacturing quality risk control method provided in this application has the following beneficial effects:

[0059] By monitoring the production environment in real time, changes in the environment can be captured promptly, and real-time data from key monitoring points can be obtained, ensuring the continuity of the production process and the accuracy of the data.

[0060] Using monitoring data to identify risk points helps to quickly identify potential quality problems or risks that may occur during the production process, thereby enabling precise control of the production environment.

[0061] By generating investigative test prompts for specific investigators based on risk points, the targeted and effective nature of the investigation is ensured, and the efficiency of risk assessment is improved.

[0062] By combining monitoring data and survey and testing results, the risk status of the production environment can be comprehensively assessed, providing a more comprehensive and in-depth analysis for risk management.

[0063] The resulting risk management outcomes help guide production adjustments and decisions, ensure the quality and safety of drug production, and reduce the impact of potential risks on production.

[0064] In summary, this application, through real-time monitoring, precise identification of risk points, personalized investigation prompts, comprehensive analysis, and generation of risk control results, has achieved effective management and control of quality risks in the drug production process, improved production efficiency and product quality, and ensured the safety and reliability of drugs. Attached Figure Description

[0065] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope of protection of the present invention. In the various drawings, similar components are numbered similarly.

[0066] Figure 1 This is a schematic diagram of the hardware operating environment involved in an embodiment of the drug production quality risk control method of the present invention;

[0067] Figure 2 This is a flowchart illustrating Example 1 of the drug manufacturing quality risk control method of the present invention;

[0068] Figure 3 This is a detailed flowchart of step S100 in Example 2 of the drug production quality risk control method of the present invention;

[0069] Figure 4 This is a detailed flowchart of step S110 in Example 2 of the drug production quality risk control method of the present invention;

[0070] Figure 5 This is a detailed flowchart of step S200 in Example 3 of the drug production quality risk control method of the present invention;

[0071] Figure 6 This is a detailed flowchart of step S200 in Example 3 of the drug production quality risk control method of the present invention;

[0072] Figure 7 This is a detailed flowchart of step S300 in Example 4 of the drug production quality risk control method of the present invention;

[0073] Figure 8 This is a detailed flowchart of step S400 in Example 5 of the drug production quality risk control method of the present invention;

[0074] Figure 9 This is a schematic diagram of the module connection of the drug production quality risk control device in an embodiment of the present invention. Detailed Implementation

[0075] The embodiments of the present invention are described in detail below, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout.

[0076] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0077] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0078] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0079] like Figure 1 The diagram shown is a structural schematic of the hardware operating environment of the terminal involved in an embodiment of the present invention.

[0080] The pharmaceutical production quality risk control system provided in this embodiment of the invention can be a PC, or a mobile terminal device such as a smartphone, tablet, or portable computer. This pharmaceutical production quality risk control system may include: a processor 1001, such as a CPU; a network interface 1004; a user interface 1003; a memory 1005; and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen, an input unit such as a keyboard, or a remote control; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed RAM memory or a stable memory, such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001. Optionally, the pharmaceutical production quality risk control system may also include RF (Radio Frequency) circuitry, audio circuitry, a Wi-Fi module, etc. In addition, the drug production quality risk control system can also be equipped with other sensors such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, which will not be elaborated here.

[0081] Those skilled in the art will understand that Figure 1 The pharmaceutical manufacturing quality risk control system shown is not intended to limit it and may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. Figure 1 As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a data interface control program, a network connection program, and a drug production quality risk management program.

[0082] Example 1

[0083] Reference Figure 2 Embodiment 1 of the present invention provides a method for controlling drug production quality risks, comprising:

[0084] Step S100: Monitor the production environment area in real time and obtain the monitoring data corresponding to the monitoring points in the production environment area;

[0085] The aforementioned production environment area refers to the designated area set up by the pharmaceutical manufacturing unit, which may include, but is not limited to, production workshops, storage warehouses, testing laboratories, research and development laboratories, etc.

[0086] The aforementioned monitoring points are specific units within the production environment area that require monitoring. These may include, but are not limited to, production equipment such as extraction tanks and concentration tanks, as well as production-related equipment such as operating devices and packaging devices, and testing or experimental equipment such as HPLC and UV spectrophotometers.

[0087] This step aims to monitor a specific production environment in real time by setting up monitoring points to collect data, such as the equipment nodes of specific devices in the production workshop. This allows for the real-time acquisition and updating of production environment data, timely monitoring of the status and environmental changes of the production unit, and helps to respond quickly to potential risks and anomalies.

[0088] Step S200: Determine the risk points based on the monitoring data;

[0089] As described above, based on the data collected in step S100, this step analyzes this data to identify potential risk points that may cause certain risks, such as unqualified raw materials, unqualified extracted materials, malfunctioning testing equipment, abnormal temperature and humidity in the workshop, etc. In order to identify risk points, preventive measures can be taken in advance to reduce the probability of risk situations occurring, thereby improving the management of pharmaceutical production units.

[0090] Step S300: Based on the risk points, determine the corresponding investigators, generate prompts for conducting investigative tests on the investigators, and obtain the investigative test results corresponding to the investigative tests;

[0091] The investigators mentioned above are the relevant management staff corresponding to the monitoring points, who are used to investigate potential risk points to determine whether the current risk points pose a risk and whether further control measures are possible.

[0092] The above-mentioned notification information can be delivered via multiple platforms, including apps, email, and telephone.

[0093] The above-mentioned investigation and testing results are those obtained by investigators through repeated testing or inspection of risk points. The testing methods used for these results can be the same as those used for monitoring data.

[0094] This step involves assigning appropriate management personnel to conduct in-depth investigations and tests based on the identified risk points, in order to verify the risk points and perform more detailed analysis.

[0095] Professional investigations and tests can more accurately determine the causes and conditions under which risks occur, which helps to develop more personalized and effective risk management plans.

[0096] Step S400: Obtain the risk control results corresponding to the production environment area based on the survey and test results and the monitoring data.

[0097] By combining survey and testing results with preliminary monitoring data, a comprehensive analysis is conducted to formulate a risk assessment and control recommendations for the entire production environment. The final risk control results provide specific guidance on how to improve the environment and adjust management strategies, thereby reducing the occurrence of future risk events.

[0098] In summary, this embodiment achieves effective management and control of quality risks in the drug production process through real-time monitoring, accurate identification of risk points, personalized investigation prompts, comprehensive analysis, and generation of risk control results. This improves production efficiency and product quality, and ensures the safety and reliability of drugs.

[0099] Example 2

[0100] Reference Figure 3 Embodiment 2 of the present invention provides a method for risk control of pharmaceutical production quality. Based on Embodiment 1 above, step S100, acquiring monitoring data corresponding to monitoring points in the production environment area, includes:

[0101] Step S110: Based on the production environment area, obtain the detection specimens corresponding to the monitoring points;

[0102] In a pharmaceutical manufacturing environment, this step involves collecting samples from critical monitoring points in the production process. Test samples can be intermediate samples of production extracted at specific monitoring points, such as extract samples obtained from extraction tanks. These samples are crucial for assessing the quality and consistency of the production process.

[0103] By obtaining these samples, we can ensure that the production process meets the predetermined quality standards, identify problems in production in a timely manner, and take corresponding measures.

[0104] Automated sampling systems can be used to take samples directly from the production line to reduce human error and ensure the representativeness of the samples.

[0105] Step S120: Detect the test specimen to obtain test data, determine the corresponding processing workstation based on the test data, and obtain the raw data through the processing workstation;

[0106] Necessary tests are performed on the obtained samples, such as chemical composition analysis and active ingredient content determination, to obtain specific data on production quality. Based on this data, an appropriate processing workstation is selected to further process the data, such as data standardization and preliminary analysis.

[0107] The above steps can help to identify any deviations or abnormalities in the production process in a timely manner, adjust production parameters promptly, and ensure product quality.

[0108] For example, analytical instruments such as high performance liquid chromatography (HPLC) and gas chromatography (GC) are used to analyze samples, and the data is processed by a computer system for further analysis.

[0109] It should be noted that different detection data require corresponding processing workstations to open and obtain the raw data. For example, Agilent HPLC data and Shimadzu HPLC data both require dedicated workstations to read and open.

[0110] Step S130: Calculate and obtain monitoring data based on the original data.

[0111] The above describes how raw data obtained from the processing workstation is used to generate final data for monitoring the production process through complex calculations and analyses, such as trend analysis and quality control charts.

[0112] The final monitoring data provides a comprehensive view of the entire production process, helping management make more informed decisions to improve production efficiency and product quality.

[0113] Statistical process control (SPC) and data analysis software (such as MiniTab, JMP) are used to analyze data in order to identify and correct any anomalies in the production process.

[0114] Through these steps, pharmaceutical companies can monitor the production process in real time, ensuring that product quality meets prescribed standards and responding quickly to any potential production problems. This not only improves production efficiency but also guarantees the quality and safety of the final product.

[0115] Furthermore, the monitoring point in the production environment area is a drug extraction device; the drug extraction tank of the drug extraction device includes multiple movable sampling devices; wherein, the movable sampling device includes a sample body and a temperature probe disposed on the sample body;

[0116] The method described above in this embodiment requires specific equipment.

[0117] The aforementioned monitoring points refer to drug extraction equipment within the production environment area. Drug extraction equipment may include drug extraction tanks, heaters, feeding devices, mixing devices, filtering devices, and central control devices, etc.

[0118] The aforementioned mobile sampling device can be structurally equipped with a motor (stepper motor or servo motor) to control its movement within the tank, including in the vertical and horizontal directions.

[0119] Furthermore, it can be moved via guide rails or slide rails. For example, a guide rail or slide rail system can be installed inside the extraction tank, allowing the sampling device to move along these rails to a designated location. These rails need to be resistant to chemical corrosion and high temperatures.

[0120] For example, in a drug extraction tank, there is an array of multiple vertically movable rod-shaped slide rails. Each rod-shaped slide rail is equipped with a corresponding movable sampling device. The movable sampling device can move up and down along the rod-shaped slide rails. The slide rails can also be extended or retracted to increase or decrease their height or position in the drug extraction tank.

[0121] The structure for controlling the movement of the movable sampling device in the aforementioned mechanisms is a conventional technical means and will not be described in detail here.

[0122] The portable device needs to include a sample collection unit, which includes an aspiration device for extracting the sample, a container for holding the drug solution, and a temperature probe for detecting the temperature of the current area. The container for holding the drug solution can be connected to an external container via heat-resistant tubing, thereby pumping the sampled drug solution into the external container and transporting the container to the sample processing and testing device for further analysis.

[0123] This highly automated and precisely controlled system ensures that the sampling device can be moved safely and accurately to the designated location in complex drug extraction environments, thereby improving the efficiency and quality of sampling.

[0124] refer to Figure 4 Step S110, based on the production environment area, obtains the detection sample corresponding to the monitoring point, including:

[0125] Step S111: Obtain the temperature data inside the drug extraction tank and the spatial coordinates corresponding to the temperature data through the temperature probe of the movable sampling device;

[0126] It should be noted that temperature variations in different regions during drug extraction can affect the content of the main components in the drug. This is because the solubility, stability, and reaction rate of many chemical components are significantly affected by temperature. Especially in the extraction of traditional Chinese medicine, the different chemical properties of various active ingredients result in varying sensitivities to temperature; therefore, temperature control is crucial for ensuring extraction efficiency and component quality.

[0127] In the extraction of traditional Chinese medicine, temperature has a significant impact on the extraction efficiency and stability of specific chemical components. Some traditional Chinese medicine components are extremely sensitive to temperature due to their unique chemical properties and solubility characteristics. For example, the following drugs:

[0128] 1. Ginseng - Ginsenosides: Ginseng is a widely used medicinal herb in Traditional Chinese Medicine, containing various ginsenosides. These ginsenosides possess anti-fatigue, anti-aging, and immunomodulatory effects. The extraction efficiency of ginsenosides is strongly affected by temperature: at lower temperatures, the solubility of some ginsenosides is lower, potentially leading to lower extraction efficiency. While higher temperatures can increase the solubility and extraction rate of most ginsenosides, excessively high temperatures may cause the decomposition of some sensitive ginsenosides, thereby reducing their content.

[0129] 2. Berberine (Coptis chinensis): Coptis chinensis is a commonly used traditional Chinese medicine. Its main active ingredient is choline, which has significant antibacterial and anti-inflammatory effects. The extraction of choline is significantly affected by temperature: the stability of choline decreases at high temperatures, leading to decomposition. Therefore, the extraction temperature needs to be carefully controlled to avoid loss of active ingredients due to excessively high temperatures.

[0130] 3. Tea Polyphenols: Tea polyphenols are the main active chemical components in tea, possessing antioxidant, antibacterial, and cardiovascular disease risk-reducing effects. The extraction efficiency and stability of tea polyphenols are greatly affected by temperature: high temperatures accelerate the oxidation and degradation of tea polyphenols; therefore, extraction at lower temperatures is generally recommended to maintain their activity and concentration. However, low-temperature extraction can easily result in lower extraction rates, and strict temperature control is often necessary in factory production.

[0131] 4. Tanshinones (Salvia miltiorrhiza): Danshen is a commonly used medicinal herb in traditional Chinese medicine, mainly containing active ingredients such as tanshinone IIA, which have the effects of improving blood circulation and anti-inflammation. The extraction of tanshinones is also affected by temperature: the chemical structure of tanshinones is easily altered at high temperatures, potentially leading to decomposition. A moderate temperature helps maximize extraction efficiency while maintaining the integrity of the chemical structure.

[0132] These examples illustrate that temperature control during the extraction process of traditional Chinese medicine is crucial for ensuring the content and quality of active ingredients in the extract. Proper temperature settings not only improve extraction efficiency but also prevent the thermal degradation of sensitive components, thereby guaranteeing the efficacy and stability of the extract.

[0133] However, pharmaceutical manufacturing facilities often use large-scale drug extraction tanks, which, due to their size and volume, can easily lead to temperature differences at different locations during the extraction process. This phenomenon, known as a temperature gradient, is caused by several factors:

[0134] 1. Heat transfer efficiency: In large extraction tanks, heat may spread unevenly from the heat source to different parts of the tank, especially at different heights of the tank and in areas far from the heat source.

[0135] 2. Mixing Effect: In large-capacity tanks, the stirring and mixing effect of materials is crucial for temperature uniformity. Improperly designed stirring equipment or insufficient stirring speed will lead to uneven temperature distribution.

[0136] 3. Tank Material and Design: The material and design of the tank also affect heat transfer efficiency. For example, the insulation material and thickness of the tank, as well as the shape and size of the tank, will affect the distribution of heat.

[0137] 4. External environmental conditions: The ambient temperature, humidity and other environmental factors of the tank will also affect the internal temperature distribution.

[0138] In addition, although a material mixing system can be used to mix the material to a certain extent and achieve a uniform effect, the large size of the tank itself results in a long mixing time.

[0139] Therefore, in the process of drug production, when large-scale drug extraction equipment is used, there are situations where the temperature of multiple samples is uneven, and the content of the main components is uneven, resulting in false positives and "false risks," which in turn generate false alarms. This seriously affects the efficiency of drug production and risk assessment, and greatly increases the cost of manpower and materials.

[0140] This step utilizes temperature probes installed on a movable sampling device to acquire temperature data and their corresponding spatial coordinates at different locations within the extraction vessel. This helps to understand the temperature distribution within the vessel. Obtaining detailed temperature distribution information ensures the uniformity of the extraction process, thus affecting the final drug quality. It also helps to promptly identify areas of abnormal temperature and prevent quality issues.

[0141] Step S112: Based on the spatial coordinates, construct a data matrix corresponding to the drug extraction tank according to the temperature measurement data;

[0142] The above describes how a data matrix is ​​constructed using the collected temperature data and corresponding spatial coordinates. This matrix will reflect the temperature distribution inside the extraction tank.

[0143] The constructed data matrix can intuitively display the spatial distribution of temperature, facilitating the analysis and monitoring of temperature uniformity throughout the extraction process.

[0144] Specifically, data visualization software (such as MATLAB or Python's matplotlib library) can also be used to generate heatmaps of temperature distribution.

[0145] Step S113: Based on the data matrix, determine the temperature uniformity region inside the drug extraction tank;

[0146] As mentioned above, even excluding the effect of stirring, in larger drug extraction tanks, there will still be areas with relatively uniform temperature and areas with large temperature variations. The reasons for this may include the following:

[0147] Heat transfer efficiency: Due to the large volume of large extraction tanks, the propagation of heat from the heating source to different parts of the tank may be delayed, resulting in uneven heat distribution. This delay is caused by physical limitations in the heat conduction and convection processes, especially in areas of the tank far from the heat source.

[0148] Tank shape and structure: The design of the tank, including its shape and internal structure such as flow control plates or baffles, directly affects the dynamics of heat and material flow. Different designs may result in uneven heat distribution within the tank, affecting heating efficiency.

[0149] Tank materials and insulation performance: The thermal conductivity of the tank materials and the performance of the insulation layer also greatly affect the retention and transfer of heat energy within the tank. The thermal conductivity of the materials and the effectiveness of the insulation layer directly determine how heat energy is distributed within the tank and the degree of heat loss.

[0150] Environmental impacts: External environmental conditions, such as ambient temperature and humidity, can also affect the temperature distribution inside the tank. For example, if a part of the tank is exposed to direct sunlight or is in a cold environment, a significant temperature gradient may form.

[0151] In the above steps, the data matrix is ​​analyzed to identify areas with small and uniform temperature variations. These areas indicate that the drug content is relatively uniform, the data is stable, and the data is representative.

[0152] By identifying areas with uniform temperature, the representativeness and consistency of samples taken from these areas can be ensured, thereby improving the accuracy of product quality control.

[0153] Implementation method: Apply statistical analysis methods, such as standard deviation and analysis of variance, to determine the uniformity of temperature distribution.

[0154] Step S114: Based on the coordinate range corresponding to the uniform temperature region, move the movable sampling device to the coordinate range to obtain the test sample.

[0155] Based on identified areas of uniform temperature, the sampling device is moved to these areas to collect samples. This ensures that the obtained samples are more representative and consistent, which is beneficial for subsequent quality analysis and product evaluation.

[0156] These steps not only enable efficient monitoring and control of temperature distribution during drug extraction but also ensure high quality and consistency of the collected samples, thereby effectively improving the control level of the entire production process and the quality of the final product. The implementation of such a system requires highly automated technology and precise temperature control equipment to ensure data accuracy and sampling effectiveness.

[0157] Further reference Figure 5 Step S114, based on the coordinate range corresponding to the temperature uniformity region, involves moving the movable sampling device within the coordinate range to obtain the test sample, including:

[0158] Step S1141: Calculate the volume of the temperature uniform region based on the coordinate range corresponding to the temperature uniform region;

[0159] This step calculates the volume of the temperature-uniform region, providing data support for determining the appropriate number of sampling points. Volume calculation relies on the coordinate range determined by temperature monitoring and data analysis, and typically involves geometric or stereoscopic measurement methods.

[0160] Accurate volume calculations can help ensure the representativeness and scientific validity of sampling, thus making the sampling results more accurately reflect the true condition of the area.

[0161] The system can receive temperature sensor data through an integrated software system, combine it with the tank's design parameters, and use geometric formulas (such as the volume formulas for cubes and cylinders) to calculate the volume.

[0162] Step S1142: Based on the volume, calculate the number of sampling points in the temperature uniform region; the number of sampling points is calculated using the following formula:

[0163]

[0164] Where n represents the number of sampling points; k represents an empirical coefficient; and A represents the volume of the temperature uniformity region.

[0165] Based on the volume of the temperature uniform region, Formula 1 is used to determine the reasonable number of sampling points, where n is the number of sampling points, k is an empirical coefficient (usually set within a certain range according to the actual required number of n), and A is the volume.

[0166] As mentioned above, adjusting the empirical coefficient k requires consideration of various factors, including the concentration of the drug solution, the sensitivity of the drug components, and the uniformity of component distribution during extraction. Below are some situations where adjusting the k value may be necessary:

[0167] 1. High drug concentration: When the drug concentration is high, the distribution of drug components in the liquid may be uneven, especially for those components that are poorly soluble or easily precipitated. In this case, increasing the number of sampling points (i.e., increasing the k-value) can help to better assess and monitor the uniformity of components throughout the extraction vessel.

[0168] 2. Thermal sensitivity of ingredients: For heat-sensitive drug ingredients, temperature fluctuations may cause localized degradation or transformation. If it is known that certain areas may experience this due to improper temperature control, increasing the number of sampling points in those areas can help to more accurately monitor and assess the impact.

[0169] 3. Key Stages in the Extraction Process: During critical stages of the extraction process, such as at the beginning or near completion, more intensive monitoring may be needed to ensure the effectiveness and efficiency of the process. In these cases, appropriately increasing the k-value (i.e., increasing the number of sampling points) can provide more data points for optimizing and adjusting the extraction parameters.

[0170] 4. Specific characteristics of medicinal materials: The physical and chemical properties of different medicinal materials (such as viscosity, solubility, and particle size) may also affect the setting of sampling points. For example, for medicinal materials that are prone to forming suspended matter or precipitation, it may be necessary to increase the number of sampling points in a specific area to ensure the representativeness of the sample.

[0171] 5. Regulatory Requirements and Quality Control Standards: According to Good Manufacturing Practices (GMP) or other relevant regulations, some products may require particularly stringent quality control and validation. In these cases, increasing the number of sampling points can help meet these regulatory requirements and ensure product quality and consistency.

[0172] By adjusting the k-value, the number of sampling points can be flexibly set according to specific production conditions and needs to maximize extraction efficiency and ensure product quality. This strategy requires dynamic adjustment based on practical experience, experimental data, and information monitored during production.

[0173] This method allows for flexible adjustment of the number of sampling points based on the volume of the area, ensuring the comprehensiveness and effectiveness of the sampling.

[0174] This calculation can be performed in the control system software, automatically calculating the number of sampling points based on the input volume data.

[0175] Step S1143: Based on the number of sampling points, generate n sampling coordinate points according to the coordinate range, and control the movable sampling device to move within the coordinate range and sample at the sampling coordinate points to obtain the test specimen.

[0176] As described above, after calculating the number of sampling points, specific sampling coordinate points are generated, and the movable sampling device is controlled to locate and sample according to these coordinate points.

[0177] By precisely controlling the sampling device to reach the designated coordinates, it can be ensured that each sampling point is accurately sampled, thereby improving the representativeness of the sample and the accuracy of the analysis results.

[0178] Using a highly automated machine control system (such as the mobile sampling device in this embodiment), the sampling device is automatically driven to perform precise sampling based on the generated coordinate points.

[0179] For example, a region with uniform temperature was identified as a cylinder with a height of 2 meters and a base radius of 0.5 meters. The corresponding k value for this liquid was 6.034.

[0180] The formula for calculating the volume of a cylinder is V = πr. 2 h = 1.5708 cubic meters.

[0181] Using formula 1,

[0182] Then, within the coordinate range of the temperature uniformity region, 7 sampling coordinate points (x, y, y) are generated. n ,y n Then, the movable sampling device is controlled to move within the coordinate range and a sample is taken at the sampling coordinate point to obtain the test specimen.

[0183] The method provided in this embodiment not only improves the scientific rigor and accuracy of the sampling process, but also reduces human error through automated control, thereby enhancing operational efficiency and safety. The implementation of these steps relies on advanced data processing software and automated mechanical control technology, ensuring the acquisition of high-quality data and samples even in complex industrial environments.

[0184] Example 3

[0185] Reference Figure 6 Embodiment 3 of the present invention provides a method for risk control in pharmaceutical production quality. Based on Embodiment 1 above, step S200, determining risk points based on the monitoring data, includes:

[0186] Step S210: Calculate the median of the monitoring data corresponding to the monitoring point and obtain the absolute median difference;

[0187] It should be noted that during the monitoring of monitoring points, individual outliers may occur due to measurement errors, data entry errors, equipment malfunctions, or atypical production conditions. If these values ​​are not identified and addressed, they may distort the results of statistical analysis, such as the mean and standard deviation, leading to misleading conclusions. By effectively identifying and eliminating these outliers, Modified Z-Score helps maintain the robustness and reliability of the analysis results.

[0188] In many applications, including production quality control and process monitoring, accurately understanding the central trends and variability of data is crucial. The presence of outliers can significantly impact these statistical measures, and using the Modified Z-Score can more accurately reflect the true characteristics of the data, ensuring that decisions are based on accurate and truthful data analysis.

[0189] Compared to the traditional Z-Score, this embodiment uses a factor of 0.6745 (derived from the normal distribution, making the standard deviation of a standard normal variable equal to the MAD) and MAD for calculation, making it more robust to skewed distributions or datasets containing multiple outliers. This makes the Modified Z-Score particularly suitable for common real-world applications involving non-normal distributions and outliers.

[0190] In production environments, real-time monitoring of data quality and rapid response to potential production anomalies are crucial. Using Modified Z-Score allows for the real-time identification of anomalous fluctuations in data, supporting timely quality control and risk management measures to reduce potential quality issues and production losses.

[0191] Maintaining process stability and product quality consistency is a core requirement in pharmaceutical manufacturing and other strictly controlled industrial processes. By eliminating outliers in the data, process stability and compliance can be assessed more accurately, thereby ensuring that products meet predetermined quality standards.

[0192] In summary, the application of Modified Z-Score provides an effective tool for processing and analyzing complex datasets commonly found in real-world production and research data. By identifying and eliminating outliers, this approach helps improve the quality of data analysis, supports data-driven decision-making, and enhances control over production processes and product quality.

[0193] First, calculate the median of the monitored data, which is the middle value after all data values ​​are sorted by size. Next, calculate the absolute difference between each data point and the median, and then take the median of these absolute differences; this is called the median absolute difference (MAD). This is a method for measuring data variability, particularly suitable for non-normally distributed data.

[0194] The median and MAD provide robust (insensitive to outliers) descriptions of the central tendency and dispersion of a dataset, making them suitable for situations where outliers or skewed distributions may exist.

[0195] Step S220: Calculate the Modified Z-Score based on the absolute median difference and the median; the formula for calculating the Modified Z-Score is:

[0196]

[0197] Where, x i This represents the i-th monitoring data; The median is represented by MAD; the absolute median difference is represented by MAD.

[0198] This calculation method can effectively identify outliers in the data, especially when the data contains outliers or is not normally distributed, and is more robust than the traditional Z-Score.

[0199] Step S230, if the monitoring data x i If the absolute value of the corresponding Modified Z-Score is greater than 3.5, the monitoring data will be excluded as an outlier.

[0200] Based on the Modified Z-Score, if the absolute value of a data point's Modified Z-Score is greater than 3.5, that data point is considered an outlier and excluded. This threshold is typically used to identify extreme statistical outliers.

[0201] This method can remove noise from the data, improving the accuracy and reliability of subsequent analysis.

[0202] Step S240, if the monitoring data x i If the absolute value of the corresponding Modified Z-Score is not greater than 3.5, then the monitoring data is considered a normal value.

[0203] Step S250: Take the average value of the monitoring data that is used as the normal value to obtain the monitoring average value, and compare the monitoring average value with the preset threshold range;

[0204] As mentioned above, there may be multiple normal values ​​at this point, and they may be close in value. Therefore, in order to reduce the consumption of system resources and avoid repeated comparisons, the normal values ​​that may be close in value are averaged to obtain the monitoring average value, and then the average value can be further evaluated.

[0205] Step S260: If the average monitoring value exceeds the preset threshold range, then the monitoring point is designated as the risk point.

[0206] Furthermore, if the average monitoring value does not exceed the preset threshold range, the monitoring point will not be considered as the risk point.

[0207] The above process involves averaging all considered normal monitoring data to obtain the monitoring mean. This mean is then compared to a preset threshold range to determine if any risk exists.

[0208] This step helps determine whether the production process is under control and whether further risk management measures are needed. If the monitoring average exceeds the threshold, it indicates a potential production quality problem, requiring further investigation or improvement measures.

[0209] The advantage of this method lies in its high sensitivity to outliers and adaptability to skewed data, making it an effective tool for monitoring production quality and identifying potential risks in a timely manner. By analyzing monitoring data in real time and responding promptly, the safety and reliability of the production process can be significantly improved.

[0210] Example 4

[0211] Reference Figure 7 Embodiment 4 of the present invention provides a method for risk control in pharmaceutical production quality. Based on Embodiment 1 above, step S300 involves determining the corresponding investigator based on the risk point and generating prompt information for conducting investigative tests on the investigator, including:

[0212] Step S310: Generate action item information based on the risk points and determine the investigators corresponding to the risk points;

[0213] This step involves identifying risk points, generating specific action items (tasks or measures) to address the risk, and assigning appropriate investigators to these tasks. Investigators are selected based on their expertise, experience, or specific responsibilities related to the risk. This ensures that each identified risk point is addressed promptly and effectively, and having a dedicated investigator improves the professionalism and efficiency of risk management.

[0214] Step S320: Write the action item information into the investigator's action list;

[0215] Add the generated action item information to the corresponding investigator's action list. This may involve updating the database or risk management system to ensure all information is properly recorded and tracked. Systematically recording action items ensures no important tasks are missed and facilitates subsequent monitoring and auditing.

[0216] Step S330: Using the action item information for the risk point in the action list as the current information, and using other action item information that is different from the current information as comparison information; obtain the current information and the creation time of the action information for the same risk point in the action list;

[0217] The above records the creation time of each action item. This helps to understand the urgency and time sensitivity of tasks. More urgent tasks can be prioritized based on their timestamps, allowing for more efficient resource allocation.

[0218] Among them, the current action item information for the risk point is used as the current information. In this action list, there are other action item information. Further, other action item information related to the current risk point is extracted.

[0219] Then, the extracted action items are sorted by time.

[0220] It should be noted that for the same risk point, such as drug extraction equipment, where the risk is excessive aristolochic acid content, if it occurs twice, two action items will be generated. If the time interval between the two is close, the investigator may repeat the test. Since the risk is the same, only one test is needed to achieve the purpose of investigation.

[0221] In this step, the creation time of each action item is recorded, which helps with subsequent time management and prioritization. Recording the creation time allows tasks to be processed in chronological order, prioritizing the most urgent tasks, and eliminating "work redundancy" to avoid duplication of effort.

[0222] Step S340: Determine whether there is any comparison information in the action list whose interval with the creation time of the current information is less than a preset time threshold;

[0223] Step S350: If yes, then the current information and comparison information for the same risk point whose establishment time interval is less than a preset time threshold are merged into one action item information, and the prompt information is generated.

[0224] Furthermore, if not, no merging is performed, and the prompt message is generated based on the current information.

[0225] Check if any tasks are very close to the current task in terms of time. This may indicate that similar or related tasks need to be merged logically. This can avoid duplication of work, improve processing efficiency, and ensure that related tasks are considered together.

[0226] Combine tasks that are close in time and target the same risk point into a single task. This typically involves updating the task description to include all relevant action items.

[0227] Consolidating tasks reduces fragmentation, allowing investigators to focus on issues more effectively while reducing management complexity.

[0228] Based on the merged task information, detailed guidance or prompts are generated to instruct investigators on how to perform their tasks. Clear guidance helps investigators execute tasks effectively and ensures that risk points are handled as intended.

[0229] For example, regarding the risk of excessive aristolochic acid in drug extraction equipment, there are: Action Item Information 1 (Comparison Information), March 10; Action Item Information 2 (Current Information), March 12. The preset time threshold is 72 hours.

[0230] The creation time for action item information 1 and action item information 2 is 2 days and 48 hours, respectively, which is less than the preset time threshold of 72 hours. Therefore, the two action item information can be merged into one action item information without repeated execution.

[0231] Example 5

[0232] Reference Figure 8 Embodiment 5 of the present invention provides a method for risk control of pharmaceutical production quality. Based on Embodiment 1 above, step S400, obtaining risk control results corresponding to the production environment area based on the investigation and testing results and the monitoring data, includes:

[0233] Step S410: Compare the survey test results with the monitoring data;

[0234] This step involves comparing the survey and test results obtained from the field or experiment with the data recorded in the real-time monitoring system. This comparison is to verify the accuracy of the monitoring data and to confirm whether the survey results support the initial monitoring observations.

[0235] This comparison helps ensure the accuracy of data from the monitoring system and verifies the authenticity of risk points. It is part of the verification process in risk management, ensuring that actions taken are based on reliable data.

[0236] Step S420: Calculate the error value using the following formula:

[0237] E = |xs -x h |;

[0238] Where E represents the error value; x s Represents the monitoring data; x h This represents the results of the survey and testing.

[0239] As mentioned above, calculating the error value can quantify the difference between the survey test results and the monitoring data, providing a numerical basis for determining whether the two are consistent.

[0240] Step S430: Compare E with the error threshold T;

[0241] The calculated error value E is compared with a preset error threshold T. This threshold defines the maximum acceptable error limit and is typically set based on production standards or quality control standards.

[0242] Step S440: If E≤T, then the data is determined to be matched, and the risk control result indicates that there is a risk.

[0243] In step S450, if E > T, it is determined that the data does not match, the risk control result is that the data is questionable, and step S100 is executed again to obtain the monitoring data corresponding to the monitoring point of the production environment area.

[0244] The consistency between the investigation test results and the monitoring data can be determined by comparison. If the error is within an acceptable range (E≤T), the data is considered to match, and the risk is confirmed. If the error exceeds the threshold (E>T), the data is questionable and may require further investigation or verification. Therefore, the process can return to the initial step, S100, to re-acquire the monitoring data.

[0245] Furthermore, this embodiment provides a drug production quality risk control device, including:

[0246] The acquisition module 10 is used to monitor the production environment area in real time and acquire the monitoring data corresponding to the monitoring points in the production environment area.

[0247] Module 20 is used to determine risk points based on the monitoring data;

[0248] The acquisition module 10 is further configured to determine the corresponding investigator based on the risk point, generate a prompt message for conducting an investigative test on the investigator, and acquire the investigative test results corresponding to the investigative test;

[0249] The output module 30 is used to obtain the risk control results corresponding to the production environment area based on the survey and test results and the monitoring data.

[0250] Furthermore, this embodiment provides a drug production quality risk control system, including a memory and a processor. The memory stores a drug production quality risk control program, and the processor runs the drug production quality risk control program to enable the drug production quality risk control system to perform the drug production quality risk control method as described in any of the foregoing embodiments.

[0251] Furthermore, this embodiment provides a computer-readable storage medium storing a drug production quality risk control program. When the drug production quality risk control program is executed by a processor, it implements the drug production quality risk control method as described in any of the foregoing embodiments.

[0252] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, as an alternative implementation, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0253] In addition, the functional modules or units in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0254] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0255] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for controlling quality risks in pharmaceutical production, characterized in that, The system monitors the production environment area in real time and acquires monitoring data corresponding to monitoring points in the production environment area. The monitoring points in the production environment area are drug extraction devices. The drug extraction tank of the drug extraction device includes multiple movable sampling devices. Each movable sampling device includes a sample body and a temperature probe mounted on the sample body. Acquiring the monitoring data corresponding to the monitoring points in the production environment area includes: acquiring temperature data within the drug extraction tank and the corresponding spatial coordinates of the temperature data through the temperature probe of the movable sampling device; constructing a data matrix corresponding to the drug extraction tank based on the spatial coordinates and the temperature data; determining a temperature uniformity area within the drug extraction tank based on the data matrix; moving the movable sampling device to the coordinate range corresponding to the temperature uniformity area to obtain a test sample; testing the test sample to obtain test data; determining the corresponding processing workstation based on the test data and obtaining raw data through the processing workstation; and calculating monitoring data based on the raw data. Risk points are identified based on the monitoring data; Based on the risk points, the corresponding investigators are identified, and a prompt message is generated for the investigators to conduct investigative tests; and the investigative test results are obtained. Obtaining risk control results corresponding to the production environment area based on the survey and test results and the monitoring data includes: comparing the survey and test results with the monitoring data; The error value is calculated using the following formula: ； in, Represents the error value; x s Represents the monitoring data; x h This represents the results of the survey and testing. Compare E with the error threshold T; If E≤T, then the data is considered to match, and the risk control result indicates that there is a risk. If E > T, it is determined that the data does not match, the risk control result is that the data is questionable, and the execution steps are reversed to obtain the monitoring data corresponding to the monitoring points of the production environment area.

2. The method for controlling drug manufacturing quality risks as described in claim 1, characterized in that, The step of moving the movable sampling device within the coordinate range corresponding to the uniform temperature region to obtain the test sample includes: The volume of the temperature uniform region is calculated based on the coordinate range corresponding to the temperature uniform region. The number of sampling points in the temperature uniform region is calculated based on the volume. The number of sampling points is calculated using the following formula: ； Where n represents the number of sampling points; k represents an empirical coefficient; and A represents the volume of the temperature uniformity region. Based on the number of sampling points, n sampling coordinate points are generated according to the coordinate range, and the movable sampling device is controlled to move within the coordinate range and sample at the sampling coordinate points to obtain the test specimen.

3. The method for controlling drug manufacturing quality risks as described in claim 1, characterized in that, The step of determining risk points based on the monitoring data includes: Calculate the median of the monitoring data corresponding to the monitoring point, and obtain the absolute median difference; The Modified Z-Score is calculated based on the absolute median difference and the median; the formula for calculating the Modified Z-Score is as follows: ； Where, x i This represents the i-th monitoring data; MAD represents the median; MAD represents the absolute median difference. If the monitoring data x i If the absolute value of the corresponding Modified Z-Score is greater than 3.5, the monitoring data will be excluded as an outlier. If the monitoring data x i If the absolute value of the corresponding Modified Z-Score is not greater than 3.5, then the monitoring data is considered a normal value. The average value of the monitoring data, which is considered as a normal value, is obtained by averaging the monitoring average value, and then the monitoring average value is compared with a preset threshold range. If the average value of the monitoring exceeds the preset threshold range, then the monitoring point is designated as the risk point.

4. The method for controlling drug manufacturing quality risks as described in claim 1, characterized in that, The step of determining the corresponding investigator based on the risk point and generating a prompt message for conducting investigative testing on the investigator includes: Based on the risk points, action item information is generated, and the investigators corresponding to the risk points are identified; Write the action item information into the investigator's action list; Using the action item information for the risk point in the action list as the current information, and using other action item information that is different from the current information as comparison information; obtain the current information and the creation time of the action information for the same risk point in the action list; Determine whether there is any comparison information in the action list whose creation time interval with the current information is less than a preset time threshold; If so, the current information and comparison information for the same risk point whose establishment time interval is less than a preset time threshold will be merged into one action item information, and the prompt information will be generated.

5. A drug production quality risk control device, characterized in that, include: An acquisition module is used to monitor a production environment area in real time and acquire monitoring data corresponding to monitoring points in the production environment area. The monitoring points in the production environment area are drug extraction devices. The drug extraction tank of the drug extraction device includes multiple movable sampling devices. Each movable sampling device includes a sample body and a temperature probe mounted on the sample body. Acquiring the monitoring data corresponding to the monitoring points in the production environment area includes: acquiring temperature data within the drug extraction tank and the spatial coordinates corresponding to the temperature data through the temperature probe of the movable sampling device; constructing a data matrix corresponding to the drug extraction tank based on the spatial coordinates and the temperature data; determining a temperature uniformity area within the drug extraction tank based on the data matrix; moving the movable sampling device to the coordinate range corresponding to the temperature uniformity area to obtain a test sample; testing the test sample to obtain test data; determining the corresponding processing workstation based on the test data and obtaining raw data through the processing workstation; and calculating monitoring data based on the raw data. The determination module is used to determine risk points based on the monitoring data; The acquisition module is further configured to determine the corresponding investigator based on the risk point, generate a prompt message for conducting an investigative test on the investigator, and acquire the investigative test results corresponding to the investigative test. The output module is used to obtain risk control results corresponding to the production environment area based on the survey and test results and the monitoring data, including: comparing the survey and test results with the monitoring data; The error value is calculated using the following formula: ； in, Represents the error value; x s Represents the monitoring data; x h This represents the results of the survey and testing. Compare E with the error threshold T; If E≤T, then the data is considered to match, and the risk control result indicates that there is a risk. If E > T, it is determined that the data does not match, the risk control result is that the data is questionable, and the execution steps are reversed to obtain the monitoring data corresponding to the monitoring points of the production environment area.

6. A pharmaceutical production quality risk control system, characterized in that, The system includes a memory and a processor. The memory stores a drug production quality risk control program, and the processor runs the drug production quality risk control program to enable the drug production quality risk control system to perform the drug production quality risk control method as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a drug production quality risk control program, which, when executed by a processor, implements the drug production quality risk control method as described in any one of claims 1-4.

Images