A method and system for intelligently generating dynamic forms in the whole cycle process of pharmaceutical production

Abstract

The present application belongs to the technical field of pharmacy, and particularly relates to a dynamic form intelligent generation method and system for a whole-cycle process of pharmaceutical production. The present application measures the offset degree of parameters between adjacent processes, compares the parameters with a preset offset range, to identify parameters to be checked that exceed the preset offset range. The parameters to be checked that exceed the preset offset range are compared with a preset product quality scoring standard, to evaluate handover performance scores and determine deviation risks. According to the deviation risks, an index to be optimized is outputted and data feedback is performed, or a confirmation signal is outputted. The present application realizes accurate monitoring of handover states between pharmaceutical production processes and identification of deviation risks, quantitatively evaluates handover performance, and provides an index to be optimized, to effectively avoid abnormal products.

Description

Technical Field

[0001] This invention belongs to the field of pharmaceutical technology, specifically relating to a method and system for intelligent generation of dynamic forms throughout the entire pharmaceutical production cycle. Background Technology

[0002] In today's pharmaceutical industry, ensuring consistent quality between batches of drugs requires more than just random sampling. More and more companies are starting to continuously collect and analyze all key process parameters from raw material input to finished product, so as to make the production process truly controllable.

[0003] Currently, many pharmaceutical companies still use static, pre-set data forms for production data management. These forms have a fixed structure and are difficult to adapt to the dynamic changes that actually occur during the production process. For example, small fluctuations in key parameters such as temperature, pressure, or stirring speed are often not captured and reflected in real time by static forms. The data that management sees often reflects the past state rather than the current working conditions. In this case, it is difficult to detect and intervene in the early stages of any deviations or abnormal signs, which increases the production risk.

[0004] To address the above problems, this invention provides a method and system for intelligent generation of dynamic forms throughout the entire pharmaceutical production cycle. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for intelligent generation of dynamic forms for the entire pharmaceutical production cycle. This system can acquire process handover information between adjacent processes in real time, and output deviation risks and indicators to be optimized in a timely manner based on differentiated parameters and performance scores. While ensuring that the connection between adjacent processes can be carried out in an orderly manner, it can also adjust the corresponding control parameters in a timely manner based on deviation risks, so as to avoid the generation of abnormal products due to untimely or incorrect handover.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0007] A method for intelligently generating dynamic forms for the entire pharmaceutical manufacturing process, when detecting a deviation in process data between adjacent processes that exceeds a preset deviation range, executes the following: performance scoring and risk assessment of the deviation; and outputs corresponding optimization information or confirmation signals based on the assessment results.

[0008] Among them, the deviations in process data throughout the entire pharmaceutical production cycle that exceed the preset offset range between adjacent processes include:

[0009] Acquire data on equipment parameters, environmental parameters, raw material properties, and raw material inputs throughout the entire pharmaceutical production cycle;

[0010] The equipment parameters, environmental parameters, raw material properties, and raw material input data are denoised, standardized, and normalized to form standardized data. The standardized data is then organized into structured process data according to the order of pharmaceutical production processes, and the structured process data is entered into each production process. Finally, the structured process data is classified according to parameter type, and a set of parameters to be evaluated is output.

[0011] Preferably, detecting deviations in process data across adjacent processes throughout the entire pharmaceutical manufacturing cycle that exceed a preset deviation range also includes:

[0012] Based on the sequence of pharmaceutical production processes, adjacent processes are extracted sequentially; using adjacent processes as a benchmark, the offset of parameters in the parameter set to be evaluated is calculated, and the parameters to be verified are output; and the parameters to be verified are compared with the preset offset range to determine whether the offset exceeds the preset offset range.

[0013] Preferably, determining the preset offset range includes:

[0014] Based on the offset standard defined for the parameter to be verified in a continuous historical period, and combined with the set start time point and offset segment, baseline parameters are generated.

[0015] Baseline parameters are used as the basis for determining the preset offset range.

[0016] Preferably, performance scoring and risk assessment of the offset include:

[0017] The parameters to be verified that exceed the preset offset range are compared with the preset product quality scoring standards, and the handover performance score corresponding to each parameter that exceeds the preset offset range is output; and based on the handover performance score, it is determined whether there is a risk of deviation.

[0018] Preferably, the handover performance scores corresponding to each parameter to be verified that exceeds the preset offset range include:

[0019] The parameters to be verified that exceed the preset offset range are summarized and compared with the scoring standards of historical products to form a handover performance score.

[0020] Preferably, based on the evaluation results, the corresponding optimization information or confirmation signal output includes:

[0021] If a deviation risk is identified, the corresponding indicator to be optimized is output, and data feedback is sent to adjacent processes for subsequent parameter adjustments; if no deviation risk is identified, a confirmation signal is output, indicating that the dynamic form of the entire pharmaceutical production cycle meets the preset safety requirements.

[0022] Preferably, the corresponding indicators to be optimized include:

[0023] Based on the degree of deviation risk, parameters that have a preset impact on deviation risk are selected, and these parameters are determined as indicators for subsequent parameter adjustments.

[0024] This invention also discloses a dynamic form intelligent generation system for the entire pharmaceutical production cycle, comprising:

[0025] The data acquisition module is configured to acquire data on equipment parameters, environmental parameters, raw material properties, and raw material inputs throughout the entire pharmaceutical production cycle.

[0026] The process data processing module is configured to perform noise reduction, standardization and normalization on the data acquired by the data acquisition module to form standardized data, organize the standardized data into structured process data and enter it into each production process, and classify the structured process data into parameters and output a set of parameters to be evaluated.

[0027] The offset recognition module is configured to respond to the output of the process data processing module, extract adjacent processes according to the order of pharmaceutical production processes, and calculate the offset of parameters in the parameter set to be evaluated in order to identify whether there is an offset of process data between adjacent processes that exceeds the preset offset range.

[0028] The risk assessment module is configured to perform performance scoring and risk assessment on offsets that exceed the preset offset range identified by the offset recognition module.

[0029] It also includes an information output module, configured to respond to the assessment results of the risk assessment module and output corresponding optimization information or confirmation signals; among which, the optimization information includes data feedback to adjacent processes for subsequent parameter adjustments.

[0030] Preferably, the performance scoring and risk assessment of the deviation includes: comparing the parameters to be verified that exceed the preset deviation range with the preset product quality scoring standard, and outputting the handover performance score corresponding to each parameter to be verified that exceeds the preset deviation range; and determining whether there is a deviation risk based on the handover performance score.

[0031] Preferably, the handover performance scores corresponding to each parameter to be verified that exceeds the preset offset range include:

[0032] The parameters to be verified that exceed the preset offset range are summarized and compared with the scoring standards of historical products to form a handover performance score.

[0033] Beneficial effects

[0034] 1. This invention calculates the offset of parameters to be evaluated between adjacent processes and combines it with baseline parameters defined based on continuous historical time periods to identify parameters to be verified that exceed the preset offset range. This enables precise monitoring of the handover status between adjacent processes and identification of deviation risks, overcoming the shortcomings of existing technologies in quantifying and evaluating the handover status between adjacent processes.

[0035] 2. This invention compares the parameters to be verified that exceed the preset offset range with the preset product quality scoring standard and the historical product scoring standard, evaluates the handover performance score, determines the deviation risk, and screens out the indicators to be optimized, thereby realizing the quantitative evaluation of the handover performance between adjacent processes and the identification of deviation risks, and providing indicators to be optimized, effectively improving the level of production process management.

[0036] 3. After determining the deviation risk and identifying the indicators to be optimized, this invention can promptly provide data feedback to adjacent processes for parameter adjustment. This enables real-time early warning and proactive intervention of deviation risks throughout the entire pharmaceutical production cycle. By feeding back optimization information to adjacent processes, parameters are adjusted, effectively preventing the generation of abnormal products due to deviation risks and reducing the scrap rate. Attached Figure Description

[0037] Figure 1 This is a flowchart of the method provided by the present invention;

[0038] Figure 2 This is a system module diagram provided by the present invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments. It should be understood that the specific embodiments described herein are merely for explaining the invention and are not intended to limit the scope of protection of the invention.

[0040] Example 1

[0041] Please refer to Figure 1 As shown, a method for intelligently generating dynamic forms throughout the entire pharmaceutical manufacturing cycle includes the following steps:

[0042] S1, Data Acquisition;

[0043] Real-time monitoring of the entire pharmaceutical production cycle is achieved by acquiring equipment parameters, environmental parameters, raw material properties, and raw material input data from field sensors, production equipment, and other data sources through industrial data buses, IoT protocols, or direct interfaces. This data is continuously aggregated and automatically distributed to the corresponding processing queues.

[0044] The equipment parameters include temperature, pressure, and rotation speed; environmental parameters include humidity and cleanliness; and raw material properties include purity and component ratio.

[0045] S2, Data Preprocessing;

[0046] The acquired equipment parameters, environmental parameters, raw material properties, and raw material input data undergo a series of standardization processes, specifically including:

[0047] Perform noise reduction processing to identify and correct outliers or missing values ​​in the data, for example, through statistical methods such as median filtering or interpolation techniques;

[0048] Standardization is performed to convert data of different dimensions into a unified scale. For example, Z-score standardization is performed by calculating the mean and standard deviation of each parameter to eliminate differences in dimensions.

[0049] Normalization is performed to map data values ​​to a preset numerical range to ensure consistency and comparability of data in subsequent processing, ultimately forming standardized data.

[0050] The preset numerical range is preferably 0-1.

[0051] S3. Structured data entry;

[0052] The standardized data is organized into structured process data with predefined fields and record formats according to the order of pharmaceutical production processes. This ensures that the data can be clearly linked to specific production stages and operations. The structured process data is then entered into the management system or database corresponding to each production process to facilitate subsequent querying, analysis and traceability.

[0053] S4. Parameter archiving and grouping;

[0054] Structured process data is classified according to its inherent parameter types. This classification is based on preset parameter classification rules and metadata, and is used to logically group parameters of the same type.

[0055] After processing, the output contains a set of parameters for all inter-process handover analyses to be performed, i.e., the set of parameters to be evaluated.

[0056] The parameter types include physical parameters, chemical parameters, and operational parameters.

[0057] S5. Inter-process handover analysis;

[0058] Based on the sequence of pharmaceutical production processes, adjacent processes are extracted and identified sequentially. Using the intersection point of adjacent processes as a benchmark, the offset of each parameter to be verified in the set of parameters to be evaluated is calculated.

[0059] Specifically: For each parameter to be verified, the difference or percentage deviation is calculated by comparing its actual output value in the current process with the actual output value in the previous adjacent process, or with the preset target value of the parameter at the process junction, so as to quantify its offset.

[0060] The above calculation results not only include the parameter offset but also incorporate a preliminary assessment of its potential impact on the production process, thereby identifying key and related influencing parameters. Among these, the related influencing parameters, as a comprehensive representation of the parameter's state at the process transition point, will serve as the verification basis for subsequent offset judgments. Offset calculations are used to promptly detect minor fluctuations or significant shifts in parameter transmission between processes, ensuring smooth transitions in the production process and avoiding quality risks caused by parameter inconsistencies.

[0061] S6, Offset determination;

[0062] When setting a preset offset range, baseline parameters need to be generated based on the offset standards defined by relevant influencing parameters within a continuous historical period, combined with the set start time and offset segment.

[0063] The deviation standard can be a statistical control limit, a process capability index, or a permissible fluctuation range set by expert experience.

[0064] The starting point is usually set to the start time of a certain production batch; the offset segment defines the analysis window that extends backward from that point in time, and its length is determined by the historical value period and the complete offset period.

[0065] Using baseline parameters as the basis for preset offset ranges allows offset judgments to adapt to natural drift and seasonal changes in the production process, thereby improving accuracy and robustness.

[0066] The historical value period is used to determine the length of the offset segment, which is the time span of past data collection; while the complete offset period is used to determine the length of the offset segment, which is the time span of the complete fluctuation pattern of the covered parameters.

[0067] For the "allowable fluctuation range" in the offset standard, the mean and standard deviation of historical data within a specific confidence interval can be calculated to determine the normal fluctuation range of the parameter.

[0068] The relevant influencing parameters are compared with the dynamically generated preset offset range: if the parameter is within the preset offset range, it is determined to be a matching parameter; if it is outside the preset offset range, it is determined to be a differential parameter.

[0069] S7, Performance Scoring and Risk Assessment;

[0070] The set of all identified differentiation parameters is compared with the preset product quality scoring standards to output the handover performance score corresponding to each differentiation parameter, as follows:

[0071] The differentiated parameters are summarized to form a comprehensive set of differentiated parameters. The preset product quality scoring standard is based on a large amount of historical production data and final product quality results. It defines the weight of the impact of different parameter deviations on product quality and the deduction rules.

[0072] The difference between the score and the evaluation criteria is evaluated to form a quantitative handover performance score. The specific method of difference evaluation is to assign a corresponding deduction or risk weight to each differential parameter according to the degree of its deviation from the preset deviation range. Then, the deductions or weights of all differential parameters are weighted and summed to obtain the overall quantitative handover performance score, that is, the normalized score result.

[0073] The handover performance score is compared with the set difference threshold. If the handover performance score is greater than the difference threshold, it is determined that there is a deviation risk; if the handover performance score is less than or equal to the difference threshold, it is determined that there is no deviation risk, and the difference threshold is set as the benchmark value.

[0074] The above-mentioned quantitative assessment method can objectively reflect the overall performance of the process handover, providing accurate numerical basis for subsequent risk assessment.

[0075] S8, Output optimization information;

[0076] If a deviation risk is determined, parameters that have a preset impact on the deviation risk are selected from the differentiated parameters based on the degree of deviation risk, and these parameters are determined as target parameters for subsequent optimization, i.e., indicators to be optimized.

[0077] The degree of deviation from risk can be measured by the level of the handover performance score, the number of differentiated parameters, or the severity of their deviation.

[0078] Furthermore, the system maintains a database of parameter impact levels, which records the potential impact of different parameters on final product quality and production risks. By comparing differentiated parameters with this database and considering their specific performance in current risk events, the system identifies those parameters that contribute the most to and have the most profound impact on current deviation risks.

[0079] Furthermore, the differential parameters in the set of parameters to be evaluated are statistically sorted, their frequency of occurrence is counted, and the weights are calculated by combining the difference and the frequency. The weights are then sorted from high to low and the weighted set is output.

[0080] When a deviation risk is identified, the highest weighted indicator is selected as the indicator to be optimized. The corresponding indicator to be optimized is then output and data feedback is provided to adjacent processes. This feedback information includes specific parameter adjustment suggestions, risk levels, and relevant influencing parameters to guide subsequent parameter adjustments.

[0081] If it is determined that there is no risk of deviation, the system outputs a confirmation signal, indicating that the dynamic form of the entire pharmaceutical production cycle meets the preset safety requirements.

[0082] If there are no more indicators to be optimized during the entire pharmaceutical production cycle, and the output verification signals are all confirmation signals within the required number of times, it indicates that the current production process is stable and meets the requirements. The system will output the overall deviation risk as "none" and mark the current pharmaceutical production cycle dynamic form as safe.

[0083] Among them, the verification signal refers to the signal used by the system to verify whether the current production process is stable and meets the requirements throughout the entire pharmaceutical production cycle.

[0084] Example 2

[0085] Please see Figure 2 As shown, this embodiment provides a dynamic form intelligent generation system for the entire pharmaceutical production cycle, including the following collaborative modules:

[0086] Data acquisition module

[0087] The data acquisition module is configured to acquire equipment parameters, environmental parameters, raw material properties, and raw material input data throughout the entire pharmaceutical production cycle. Specifically:

[0088] The data acquisition module can collect necessary equipment parameters, environmental parameters, raw material properties, and raw material input data from various field sensors, production equipment controllers, environmental monitoring systems, and raw material batch management systems on the production line, either in real time or periodically. This data forms the basis for subsequent process data processing and offset identification.

[0089] The field sensing equipment includes temperature sensors, pressure sensors, humidity sensors, pH sensors, etc.; the production equipment controllers include reaction vessels, mixers, dryers, etc.

[0090] Process data processing module

[0091] The process data processing module is configured to perform noise reduction, standardization, and normalization on the data acquired by the data acquisition module, forming standardized data. Specifically:

[0092] Denoising can be achieved by using filtering algorithms to remove random noise and outliers from the data; standardization can transform data of different dimensions to a uniform scale, for example, through Z-score standardization; normalization can map the data to a specific interval to facilitate subsequent comparison and analysis.

[0093] The process data processing module organizes standardized data into structured process data according to the sequence of pharmaceutical production processes, and then inputs this structured process data into the database or storage unit corresponding to each production process. Specifically, data from different processes can be stored separately, and relationships between processes can be established. In addition, the process data processing module also classifies the structured process data according to parameter type. For example, continuous parameters such as temperature and pressure are grouped into one category, while discrete parameters such as raw material batches and equipment models are grouped into another category. Finally, it outputs a set of parameters to be evaluated for further analysis by the offset identification module.

[0094] Offset recognition module

[0095] The offset identification module is configured to respond to the output of the process data processing module, i.e., to receive the set of parameters to be evaluated. The offset identification module extracts adjacent processes sequentially according to the order of the pharmaceutical manufacturing processes. For example, for processes A and B, the offset identification module will extract processes A and B as adjacent processes.

[0096] Using adjacent processes as a benchmark, the offset identification module calculates the offset of parameters in the set of parameters to be evaluated and outputs the parameters to be verified. Offset calculation may include calculating the difference, ratio, or statistical distance of the same parameters between adjacent processes.

[0097] The offset recognition module compares the parameter to be verified with a preset offset range to determine whether the offset exceeds the preset offset range. The determination of the preset offset range can be completed by the offset recognition module or the coordination module, specifically including:

[0098] Based on the offset standard defined for the parameter to be verified over a continuous historical period, and combined with the set start time and offset segment, baseline parameters are generated, and these baseline parameters are used as the basis for determining the preset offset range. For example, by analyzing data from historical stable production batches, the normal fluctuation range of parameters between adjacent processes is statistically analyzed, and the preset offset range is set by combining expert experience or statistical methods.

[0099] When the offset of process data between adjacent processes exceeds the preset offset range, the offset identification module will trigger the risk assessment module.

[0100] The statistical method can be the 3σ principle.

[0101] Risk assessment module

[0102] The risk assessment module is configured to respond to offsets identified by the offset recognition module that exceed the preset offset range, and to perform performance scoring and risk assessment on the offsets.

[0103] The risk assessment module compares the parameters to be verified that exceed the preset offset range with the preset product quality scoring standards, and outputs the handover performance score corresponding to each parameter that exceeds the preset offset range. This output includes summarizing the parameters that exceed the preset offset range and evaluating the difference with the scoring standards of historical products to form the handover performance score.

[0104] Specifically, if a deviation in a certain parameter causes a product quality indicator to deviate from a preset standard, a corresponding handover performance score will be assigned based on the degree of deviation. Based on the handover performance score, the risk assessment module determines whether a deviation risk exists. For example, if the handover performance score is lower than the difference threshold, a deviation risk is determined to exist.

[0105] Information output module

[0106] The information output module is configured to respond to the assessment results of the risk assessment module and output corresponding optimization information or confirmation signals.

[0107] If a deviation risk is identified, the information output module outputs the corresponding indicators to be optimized and provides data feedback to adjacent processes for subsequent parameter adjustments. The output of the corresponding indicators to be optimized includes selecting parameters that have a preset impact on the deviation risk based on its severity, and then identifying these parameters as indicators for subsequent parameter adjustments.

[0108] For example, if the risk assessment results indicate that excessively high reaction temperature is the main risk, then "reaction temperature" will be used as an indicator to be optimized, and feedback will be given to the operators of the relevant processes or the automated control system, suggesting that the reaction temperature be adjusted.

[0109] If it is determined that there is no deviation risk, the information output module outputs a confirmation signal, indicating that the dynamic form of the entire pharmaceutical production cycle meets the preset safety requirements. This confirmation signal can be used to automatically update production records, release processes, or notify relevant personnel that the production process is normal.

[0110] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for intelligently generating dynamic forms throughout the entire pharmaceutical manufacturing cycle, characterized in that: When a deviation exceeding a preset offset range is detected in the process data of the entire pharmaceutical manufacturing cycle between adjacent processes, the following action is taken: The offset is evaluated for performance and risk. And based on the evaluation results, output corresponding optimization information or confirmation signals; Among them, the deviations in process data throughout the entire pharmaceutical production cycle that exceed the preset offset range between adjacent processes include: Acquire data on equipment parameters, environmental parameters, raw material properties, and raw material inputs throughout the entire pharmaceutical production cycle; The equipment parameters, environmental parameters, raw material properties, and raw material input data are denoised, standardized, and normalized to form standardized data. The standardized data is then organized into structured process data according to the order of pharmaceutical production processes, and the structured process data is entered into each production process. Finally, the structured process data is classified according to parameter type, and a set of parameters to be evaluated is output.

2. The method for intelligently generating dynamic forms for the entire pharmaceutical production cycle according to claim 1, characterized in that, The monitoring of process data throughout the entire pharmaceutical manufacturing cycle showing deviations exceeding the preset offset range between adjacent processes also includes: Based on the sequence of pharmaceutical production processes, adjacent processes are extracted sequentially; using adjacent processes as a benchmark, the offset of parameters in the parameter set to be evaluated is calculated, and the parameters to be verified are output; and the parameters to be verified are compared with the preset offset range to determine whether the offset exceeds the preset offset range.

3. The method for intelligently generating dynamic forms for the entire pharmaceutical production cycle according to claim 2, characterized in that, Determining the preset offset range includes: Based on the offset standard defined for the parameter to be verified in a continuous historical period, and combined with the set start time point and offset segment, baseline parameters are generated. Baseline parameters are used as the basis for determining the preset offset range.

4. The method for intelligently generating dynamic forms for the entire pharmaceutical production cycle according to claim 1, characterized in that, The performance scoring and risk assessment of the offset include: The parameters to be verified that exceed the preset offset range are compared with the preset product quality scoring standards, and the handover performance score corresponding to each parameter that exceeds the preset offset range is output; and based on the handover performance score, it is determined whether there is a risk of deviation.

5. The method for intelligently generating dynamic forms for the entire pharmaceutical production cycle according to claim 4, characterized in that, The output includes the handover performance score for each parameter to be verified that exceeds the preset offset range: The parameters to be verified that exceed the preset offset range are summarized and compared with the scoring standards of historical products to form a handover performance score.

6. The method for intelligently generating dynamic forms for the entire pharmaceutical production cycle according to claim 1, characterized in that, Based on the evaluation results, the corresponding optimization information or confirmation signals output include: If a deviation risk is identified, the corresponding indicator to be optimized is output, and data feedback is sent to adjacent processes for subsequent parameter adjustments; if no deviation risk is identified, a confirmation signal is output, indicating that the dynamic form of the entire pharmaceutical production cycle meets the preset safety requirements.

7. The method for intelligently generating dynamic forms for the entire pharmaceutical production cycle according to claim 6, characterized in that, The corresponding metrics to be optimized include: Based on the degree of deviation risk, parameters that have a preset impact on deviation risk are selected, and these parameters are determined as indicators for subsequent parameter adjustments.

8. A dynamic form intelligent generation system for the entire pharmaceutical production cycle, characterized in that, include: The data acquisition module is configured to acquire data on equipment parameters, environmental parameters, raw material properties, and raw material inputs throughout the entire pharmaceutical production cycle. The process data processing module is configured to perform noise reduction, standardization and normalization on the data acquired by the data acquisition module to form standardized data, organize the standardized data into structured process data and enter it into each production process, and classify the structured process data into parameters and output a set of parameters to be evaluated. The offset recognition module is configured to respond to the output of the process data processing module, extract adjacent processes according to the order of pharmaceutical production processes, and calculate the offset of parameters in the parameter set to be evaluated in order to identify whether there is an offset of process data between adjacent processes that exceeds the preset offset range. The risk assessment module is configured to perform performance scoring and risk assessment on offsets that exceed the preset offset range identified by the offset recognition module. It also includes an information output module, configured to respond to the assessment results of the risk assessment module and output corresponding optimization information or confirmation signals; among which, the optimization information includes data feedback to adjacent processes for subsequent parameter adjustments.

9. The intelligent dynamic form generation system for the entire pharmaceutical production cycle as described in claim 8, characterized in that, The performance scoring and risk assessment of the deviation includes: comparing the parameters to be verified that exceed the preset deviation range with the preset product quality scoring standard, and outputting the handover performance score corresponding to each parameter to be verified that exceeds the preset deviation range; and determining whether there is a deviation risk based on the handover performance score.

10. The intelligent dynamic form generation system for the entire pharmaceutical production cycle according to claim 9, characterized in that, The output includes the handover performance score for each parameter to be verified that exceeds the preset offset range: The parameters to be verified that exceed the preset offset range are summarized and compared with the scoring standards of historical products to form a handover performance score.

Images